fix signature

support invokable signature
[fix] snippet for Agents as a Tool (#5181 )
2026-08-18 13:45:44 +02:00 · 2025-06-24 09:08:08 -04:00 · 2025-06-24 08:31:58 -04:00 · 2025-06-24 11:44:32 +00:00 · 2025-06-23 18:12:19 -07:00 · 2025-06-23 18:05:46 -07:00
265 changed files with 22416 additions and 35490 deletions
@@ -1,6 +1,6 @@
 name: "\U0001F41B Bug Report"
 description: Report a bug in LangGraph. To report a security issue, please instead use the security option below. For questions, please use the GitHub Discussions.
-labels: ["02 Bug Report"]
+labels: [pending,bug]
 body:
  - type: markdown
    attributes:
@@ -1,4 +1,4 @@
-blank_issues_enabled: false
+blank_issues_enabled: true
 version: 2.1
 contact_links:
  - name: 🤔 Question or Problem
@@ -1,7 +1,7 @@
 name: Documentation
 description: Report an issue related to the LangGraph documentation.
 title: "DOC: <Please write a comprehensive title after the 'DOC: ' prefix>"
-labels: [03 - Documentation]
+labels: [documentation]

 body:
 - type: textarea
@@ -0,0 +1,11 @@
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+# and
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
@@ -49,7 +49,7 @@ jobs:

      - name: Get .mypy_cache to speed up mypy
        if: steps.changed-files.outputs.all
-        uses: actions/cache@v3
+        uses: actions/cache@v4
        env:
          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
        with:
@@ -75,7 +75,7 @@ jobs:

      - name: Get .mypy_cache_test to speed up mypy
        if: steps.changed-files.outputs.all
-        uses: actions/cache@v3
+        uses: actions/cache@v4
        env:
          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
        with:
@@ -1,52 +0,0 @@
-name: test
-
-on:
-  workflow_call:
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.11"
-          - "3.12"
-
-    defaults:
-      run:
-        working-directory: libs/scheduler-kafka
-    name: "test #${{ matrix.python-version }}"
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: astral-sh/setup-uv@v6
-        with:
-          python-version: ${{ matrix.python-version }}
-          enable-cache: true
-          cache-suffix: "test-scheduler-kafka"
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        if: ${{ !github.event.pull_request.head.repo.fork }}
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_RO_TOKEN }}
-
-      - name: Install dependencies
-        shell: bash
-        run: uv sync --frozen --group dev
-
-      - name: Run tests
-        shell: bash
-        run: make test
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'
@@ -35,7 +35,6 @@ jobs:
              - 'libs/checkpoint/**'
              - 'libs/checkpoint-sqlite/**'
              - 'libs/checkpoint-postgres/**'
-              - 'libs/scheduler-kafka/**'
              - 'libs/prebuilt/**'
            sdk-js:
              - 'libs/sdk-js/**'
@@ -53,7 +52,7 @@ jobs:
            "libs/checkpoint",
            "libs/checkpoint-sqlite",
            "libs/checkpoint-postgres",
-            "libs/scheduler-kafka",
+
            "libs/prebuilt",
          ]
    if: needs.changes.outputs.python == 'true'
@@ -89,14 +88,6 @@ jobs:
    uses: ./.github/workflows/_test_langgraph.yml
    secrets: inherit

-  # NOTE: we're testing scheduler-kafka separately because it requires a different matrix
-  test-scheduler-kafka:
-    needs: changes
-    if: needs.changes.outputs.python == 'true'
-    name: "cd libs/scheduler-kafka"
-    uses: ./.github/workflows/_test_scheduler_kafka.yml
-    secrets: inherit
-
  check-sdk-methods:
    needs: changes
    if: needs.changes.outputs.python == 'true'
@@ -166,9 +157,9 @@ jobs:
      run:
        working-directory: ${{ matrix.working-directory }}
    steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
      - name: Setup Node.js (LTS)
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
        with:
          node-version: "20"
          cache: "yarn"
@@ -192,9 +183,9 @@ jobs:
      run:
        working-directory: ${{ matrix.working-directory }}
    steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
      - name: Setup Node.js (LTS)
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
        with:
          node-version: "20"
          cache: "yarn"
@@ -212,7 +203,6 @@ jobs:
        lint-js,
        test,
        test-langgraph,
-        test-scheduler-kafka,
        check-sdk-methods,
        check-schema,
        integration-test,
@@ -4,9 +4,11 @@ on:
  push:
    branches:
      - main
+      - v0
  pull_request:
    branches:
      - main
+      - v0
  workflow_dispatch:

 permissions:
@@ -82,9 +84,9 @@ jobs:
        run: make llms-text
      - name: Build site
        run: |
-          # If this is main branch, then we want to download stats. we do this 
+          # If this is v0 branch, then we want to download stats. we do this 
          # with the env variable DOWNLOAD_STATS=true
-          if [ "${{ github.ref }}" == "refs/heads/main" ]; then
+          if [ "${{ github.ref }}" == "refs/heads/v0" ]; then
            DOWNLOAD_STATS=true make build-docs
          else
            make build-docs
@@ -144,8 +146,8 @@ jobs:
          fi

      - name: Configure GitHub Pages
-        if: github.ref == 'refs/heads/main'
-        uses: actions/configure-pages@v4
+        if: github.ref == 'refs/heads/v0'
+        uses: actions/configure-pages@v5

      - name: Upload Pages Artifact
        # if: github.ref == 'refs/heads/main'
@@ -154,6 +156,6 @@ jobs:
          path: ./docs/site/

      - name: Deploy to GitHub Pages
-        if: github.ref == 'refs/heads/main'
+        if: github.ref == 'refs/heads/v0'
        id: deployment
        uses: actions/deploy-pages@v4
@@ -22,7 +22,7 @@ jobs:
      - uses: actions/checkout@v4
      # JS Build
      - name: Use Node.js
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
        with:
          node-version: "20"
          cache: "yarn"
@@ -181,3 +181,4 @@ Chinook.db
 .vercel
 .turbo
 .editorconfig
+.scratch
@@ -0,0 +1,55 @@
+# AGENTS Instructions
+
+This repository is a monorepo. Each library lives in a subdirectory under `libs/`.
+
+When you modify code in any library, run the following commands in that library's directory before creating a pull request:
+
+- `make format` – run code formatters
+- `make lint` – run the linter
+- `make test` – execute the test suite
+
+To run a particular test file or to pass additional pytest options you can specify the `TEST` variable:
+
+```
+TEST=path/to/test.py make test
+```
+
+Other pytest arguments can also be supplied inside the `TEST` variable.
+
+## Libraries
+
+The repository contains several Python and JavaScript/TypeScript libraries.
+Below is a high-level overview:
+
+- **checkpoint** – base interfaces for LangGraph checkpointers.
+- **checkpoint-postgres** – Postgres implementation of the checkpoint saver.
+- **checkpoint-sqlite** – SQLite implementation of the checkpoint saver.
+- **cli** – official command-line interface for LangGraph.
+- **langgraph** – core framework for building stateful, multi-actor agents.
+- **prebuilt** – high-level APIs for creating and running agents and tools.
+- **sdk-js** – JS/TS SDK for interacting with the LangGraph REST API.
+- **sdk-py** – Python SDK for the LangGraph Platform API.
+
+### Dependency map
+
+The diagram below lists downstream libraries for each production dependency as
+declared in that library's `pyproject.toml` (or `package.json`).
+
+```text
+checkpoint
+├── checkpoint-postgres
+├── checkpoint-sqlite
+├── prebuilt
+└── langgraph
+
+prebuilt
+└── langgraph
+
+sdk-py
+├── langgraph
+└── cli
+
+sdk-js (standalone)
+```
+
+Changes to a library may impact all of its dependents shown above.
@@ -109,7 +109,7 @@ Here are some high-level tips on writing a good how-to guide:
 LangGraph's conceptual guides fall under the **Explanation** quadrant of Diataxis. They should cover LangChain terms and concepts
 in a more abstract way than how-to guides or tutorials, and should be geared towards curious users interested in
 gaining a deeper understanding of the framework. Try to avoid excessively large code examples. The goal here is to
-impart perspective to the user rather than to finish a practical project. These guides should cover **why** things work they way they do.
+impart perspective to the user rather than to finish a practical project. These guides should cover **why** things work the way they do.


 To quote the Diataxis website:
@@ -0,0 +1,58 @@
+# Define the directories containing projects
+LIBS_DIRS := $(wildcard libs/*)
+
+# Default target
+.PHONY: all
+all: lint format lock test
+
+# Install dependencies for all projects
+.PHONY: install
+install:
+	@echo "Creating virtual environment..."
+	@uv venv
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/pyproject.toml ]; then \
+			echo "Installing dependencies for $$dir"; \
+			uv pip install -e $$dir; \
+		fi; \
+	done
+
+# Lint all projects
+.PHONY: lint
+lint:
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/Makefile ]; then \
+			echo "Running lint in $$dir"; \
+			$(MAKE) -C $$dir lint; \
+		fi; \
+	done
+
+# Format all projects
+.PHONY: format
+format:
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/Makefile ]; then \
+			echo "Running format in $$dir"; \
+			$(MAKE) -C $$dir format; \
+		fi; \
+	done
+
+# Lock all projects
+.PHONY: lock
+lock:
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/Makefile ]; then \
+			echo "Running lock in $$dir"; \
+			(cd $$dir && uv lock); \
+		fi; \
+	done
+
+# Test all projects
+.PHONY: test
+test:
+	@for dir in $(LIBS_DIRS); do \
+		if [ -f $$dir/Makefile ]; then \
+			echo "Running test in $$dir"; \
+			$(MAKE) -C $$dir test; \
+		fi; \
+	done
@@ -12,7 +12,6 @@
 [![Downloads](https://static.pepy.tech/badge/langgraph/month)](https://pepy.tech/project/langgraph)
 [![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langgraph)](https://github.com/langchain-ai/langgraph/issues)
 [![Docs](https://img.shields.io/badge/docs-latest-blue)](https://langchain-ai.github.io/langgraph/)
-[![GitMCP](https://img.shields.io/endpoint?url=https://gitmcp.io/badge/langchain-ai/langgraph)](https://gitmcp.io/langchain-ai/langgraph)

 Trusted by companies shaping the future of agents – including Klarna, Replit, Elastic, and more – LangGraph is a low-level orchestration framework for building, managing, and deploying long-running, stateful agents.

@@ -1,157 +1,154 @@
-"""Add typescript translation to a given markdown file."""
+"""Translate Python markdown to TypeScript and/or consolidate Python-JS markdown into a single document."""

 import argparse
-import re

 import requests
 from langchain_anthropic import ChatAnthropic

+# Load reference TypeScript snippets
 URL = "https://gist.githubusercontent.com/eyurtsev/e7486731415463a9bc5b4682358859c8/raw/b5a5fda9c7e3387cfcb781f25082814d43675d50/gistfile1.txt"
 response = requests.get(URL)
 response.raise_for_status()
 reference_snippets = response.text

-model = ChatAnthropic(model="claude-3-5-sonnet-latest")
+# Initialize model
+model = ChatAnthropic(model="claude-sonnet-4-0", max_tokens=64_000)
+
+TRANSLATION_PROMPT = (
+    "You are a helpful assistant that translates Python-based technical "
+    "documentation written in Markdown to equivalent TypeScript-based documentation. "
+    "The input is a Markdown file written in mkdocs format. It contains "
+    "Python code snippets embedded in prose. "
+    "Your task is to rewrite the content by translating the Python code to "
+    "idiomatic TypeScript, using the provided TypeScript reference snippets "
+    "to ensure accurate and consistent usage (e.g., correct imports, function "
+    "names, and patterns). "
+    "Remove the original Python code and replace it with the corresponding "
+    "TypeScript version. "
+    "Do not alter the surrounding prose unless a change is necessary to "
+    "reflect differences between Python and TypeScript. "
+    "Preserve the structure and formatting of the original Markdown document. "
+    "Do not make stylistic or structural changes unless they directly support "
+    "the translation. "
+    "Use the reference TypeScript snippets as guidance whenever possible to "
+    "maintain alignment with existing conventions.\n\n"
+    f"Here are the reference TypeScript snippets:\n\n{reference_snippets}\n\n"
+)
+
+CONSOLIDATION_PROMPT = (
+    "You are a helpful assistant that consolidates parallel Python and JavaScript (TypeScript) technical documentation "
+    "written in Markdown into a single unified Markdown document. "
+    "The input consists of two documents: the first is for Python users, and the second is for JavaScript/TypeScript users. "
+    "Your task is to merge these into one Markdown file using language-specific fenced blocks to separate the content where needed. "
+    "Use the following syntax to distinguish content for each language:\n\n"
+    ":::python\n"
+    "# Python-specific content\n"
+    ":::\n\n"
+    ":::js\n"
+    "# JavaScript/TypeScript-specific content\n"
+    ":::\n\n"
+    "Follow these consolidation rules:\n"
+    "- When content (prose or code) is the same or nearly identical in both versions, include it only once—outside of any fenced block.\n"
+    "- When content differs between the Python and JS versions, wrap each version in its corresponding fenced block.\n"
+    "- Prefer **paragraph-level separation** of language-specific content. Do not combine Python and JS snippets or terminology in the same sentence or paragraph using conditional phrases.\n"
+    "  For example, avoid inline constructs like:\n"
+    "  `The :::python add_messages ::: :::js reducer ::: function...`\n"
+    "  Instead, write two distinct paragraphs:\n\n"
+    "  :::python\n"
+    "  The `add_messages` function in our `State` will append the LLM's response messages to whatever messages are already in the state.\n"
+    "  ::: \n\n"
+    "  :::js\n"
+    "  The `reducer` function in our `StateAnnotation` will append the LLM's response messages to whatever messages are already in the state.\n"
+    "  :::\n\n"
+    "- Preserve the overall structure, ordering, and formatting of the original Markdown documents.\n"
+    "- Do not rephrase or unify content unless it is logically and semantically identical.\n"
+    "- Use the fenced blocks for both prose and code as needed, and ensure output is clean, readable Markdown suitable for tools that parse these directives.\n"
+    "Your goal is to produce a cleanly merged documentation file that serves both Python and JavaScript users without redundancy, while maximizing clarity and separation of language-specific details."
+)


-def _get_tqdm():
-    try:
-        from tqdm import tqdm
-    except ImportError:
-        # If not available return a simple identity function
-        def tqdm(iterable, *args, **kwargs):
-            return iterable
-
-    return tqdm
-
-
-_tqdm = _get_tqdm()
-
-opening_pattern = re.compile(r"^\s*```python(?:\s+.*)?\s*$")
-closing_pattern = re.compile(r"^\s*```\s*$")
-
-
-def extract_python_snippets(markdown: str) -> list[str]:
-    """
-    Extract all python code blocks (including their fence lines) from the markdown content.
-    A python block is defined as any block that starts with a line containing an opening fence
-    with '```python' (optionally with extra parameters) and ends with a closing fence '```'.
-    """
-    snippets = []
-    inside_block = False
-    current_snippet = []
-
-    for line in markdown.splitlines(keepends=True):
-        if not inside_block:
-            if opening_pattern.match(line):
-                inside_block = True
-                current_snippet = [line]
-        else:
-            current_snippet.append(line)
-            if closing_pattern.match(line):
-                inside_block = False
-                snippets.append("".join(current_snippet))
-                current_snippet = []
-    return snippets
-
-
-def translate_snippet(python_snippet: str) -> str:
-    """Translate a python code block into a TypeScript code block using Langchain.
-    The response is expected to be a properly fenced TypeScript code block (i.e.
-    starting with ```typescript and ending with ```).
-    """
-    ai_message = model.invoke(
+def translate_python_to_ts(markdown_content: str) -> str:
+    response = model.invoke(
        [
            {
                "role": "system",
-                "content": (
-                    f"You have access to the following up-to-date example TypeScript code "
-                    f"snippets that show examples of building with langgraph "
-                    f"and langchain:\n\n{reference_snippets}\n\n"
-                    "Use this context to translate the following Python code to equivalent "
-                    "TypeScript. Ensure that your output is a valid fenced TypeScript "
-                    "code block (i.e. starts with ```typescript and ends with ```)."
-                ),
-            },
-            {
-                "role": "user",
-                "content": f"Translate this Python snippet to TypeScript:\n\n{python_snippet}",
+                "content": TRANSLATION_PROMPT,
+                "cache_control": {"type": "ephemeral"},
            },
+            {"role": "user", "content": markdown_content},
        ]
    )
-
-    # Use a regular expression to search for a TypeScript code block in the response.
-    pattern = r"```typescript\s*(.*?)\s*```"
-    match = re.search(pattern, ai_message.content, re.DOTALL)
-    if match:
-        # Reconstruct the code block with proper fences.
-        typescript_code = match.group(1).strip()
-        return f"```typescript\n{typescript_code}\n```"
-    else:
-        raise ValueError("No TypeScript code block found in the model's response.")
+    return response.content


-def insert_translations_into_markdown(
-    markdown: str, typescript_snippets: list[str]
-) -> str:
-    """Walks through the original markdown content and, after each
-    Python snippet block, inserts the corresponding translated TypeScript snippet.
-    It assumes that the ordering of the Python snippets
-    (from extract_python_snippets) matches the order they appear in the markdown.
-    """
-    output_lines = []
-    lines = markdown.splitlines(keepends=True)
-    inside_block = False
-    snippet_index = 0
-
-    for line in lines:
-        output_lines.append(line)
-        if not inside_block and opening_pattern.match(line):
-            # We've encountered the start of a python code block.
-            inside_block = True
-        elif inside_block:
-            if closing_pattern.match(line):
-                # End of a python snippet block.
-                inside_block = False
-                if snippet_index < len(typescript_snippets):
-                    # Insert an extra newline for clarity, then the translated TypeScript snippet.
-                    output_lines.append("\n")
-                    output_lines.append(typescript_snippets[snippet_index])
-                    output_lines.append("\n")
-                    snippet_index += 1
-    return "".join(output_lines)
+def consolidate_python_and_ts(combined_content: str) -> str:
+    response = model.invoke(
+        [
+            {
+                "role": "system",
+                "content": CONSOLIDATION_PROMPT,
+                "cache_control": {"type": "ephemeral"},
+            },
+            {"role": "user", "content": combined_content},
+        ]
+    )
+    return response.content


-def main(file_path: str) -> None:
-    # Read the markdown file.
-    with open(file_path, "r") as f:
+def main(file_path: str, translate_only: bool, consolidate_only: bool) -> None:
+    with open(file_path, "r", encoding="utf-8") as f:
        markdown_content = f.read()

-    # 1. Extract all Python snippets.
-    python_snippets = extract_python_snippets(markdown_content)[:1]
+    if translate_only:
+        translated = translate_python_to_ts(markdown_content)
+        output_path = file_path.replace(".md", ".translated.md")
+        with open(output_path, "w", encoding="utf-8") as f:
+            f.write(translated)
+        print(f"Translated JS/TS version written to: {output_path}")

-    # 2. Translate each Python snippet to TypeScript.
-    typescript_snippets = []
-    # Replace with .batch() for faster translation
-    for python_snippet in _tqdm(python_snippets):
-        ts_snippet = translate_snippet(python_snippet)
-        typescript_snippets.append(ts_snippet)
+    elif consolidate_only:
+        consolidated = consolidate_python_and_ts(markdown_content)
+        with open(file_path, "w", encoding="utf-8") as f:
+            f.write(consolidated)
+        print(f"Consolidated content written to: {file_path}")

-    # 3. Insert the TypeScript translations after their respective Python snippets.
-    updated_markdown = insert_translations_into_markdown(
-        markdown_content, typescript_snippets
-    )
-
-    # Overwrite the original markdown file with the updated content.
-    with open(file_path, "w") as f:
-        f.write(updated_markdown)
+    else:
+        # Default behavior: translate first, then consolidate both
+        translated = translate_python_to_ts(markdown_content)
+        combined = f"{markdown_content.strip()}\n\n\n{translated.strip()}"
+        consolidated = consolidate_python_and_ts(combined)
+        with open(file_path, "w", encoding="utf-8") as f:
+            f.write(consolidated)
+        print(f"Translated and consolidated content written to: {file_path}")


 if __name__ == "__main__":
    parser = argparse.ArgumentParser(
-        description="Translate Python snippets in a markdown file to TypeScript and insert them after each Python snippet."
+        description=(
+            "Translate Python markdown to TypeScript and/or consolidate "
+            "Python-JS markdown into one file."
+        )
    )
    parser.add_argument("file_path", type=str, help="Path to the markdown file.")
+    parser.add_argument(
+        "--translate-only",
+        action="store_true",
+        help="Only generate the JS translation.",
+    )
+    parser.add_argument(
+        "--consolidate-only",
+        action="store_true",
+        help="Only consolidate pre-paired Python and JS content.",
+    )
    args = parser.parse_args()

-    main(args.file_path)
+    if args.translate_only and args.consolidate_only:
+        raise ValueError(
+            "Cannot use both --translate-only and --consolidate-only at the same time."
+        )
+
+    main(
+        args.file_path,
+        translate_only=args.translate_only,
+        consolidate_only=args.consolidate_only,
+    )
@@ -3,19 +3,21 @@
 import asyncio
 import glob
 import os
-from typing import TypedDict, List, Optional
-import pydantic
 import re
-from pydantic import BaseModel, Field
-from langchain_core.rate_limiters import InMemoryRateLimiter
+from typing import TypedDict, List, Optional

 import yaml
 from langchain.chat_models import init_chat_model
+from langchain_core.rate_limiters import InMemoryRateLimiter
 from mkdocs.structure.files import File
 from mkdocs.structure.pages import Page
+from pydantic import BaseModel, Field
 from yaml import SafeLoader

-from _scripts.notebook_hooks import _on_page_markdown_with_config
+from _scripts.notebook_hooks import (
+    _on_page_markdown_with_config,
+    _apply_conditional_rendering,
+)

 HERE = os.path.dirname(os.path.abspath(__file__))
 # Get source directory (parent of HERE / docs)
@@ -211,7 +213,9 @@ async def process_nav_items(nav_items: list[NavItem]) -> list[NavItem]:
    # Remove any items that start with http:// or https:// looking only for
    # local file at this stages.
    nav_items = [
-        item for item in nav_items if not item["url"].startswith(("http://", "https://"))
+        item
+        for item in nav_items
+        if not item["url"].startswith(("http://", "https://"))
    ]
    # Process items in parallel
    tasks = [process_single_item(item) for item in nav_items]
@@ -0,0 +1,5 @@
+JS_LINK_MAP = {
+    "langgraph.types.interrupt": "https://langchain-ai.github.io/langgraphjs/reference/functions/langgraph.interrupt-2.html",
+    "create_react_agent": "https://langchain-ai.github.io/langgraphjs/reference/functions/langgraph_prebuilt.createReactAgent.html",
+    "langgraph.types.Command": "https://langchain-ai.github.io/langgraphjs/reference/classes/langgraph.Command.html",
+}
@@ -1,14 +1,22 @@
+"""mkdocs hooks for adding custom logic to documentation pipeline.
+
+Lifecycle events: https://www.mkdocs.org/dev-guide/plugins/#events
+"""
+
 import logging
 import os
 import posixpath
 import re
 from typing import Any, Dict

+from bs4 import BeautifulSoup
+from mkdocs.config.defaults import MkDocsConfig
 from mkdocs.structure.files import Files, File
 from mkdocs.structure.pages import Page

 from _scripts.generate_api_reference_links import update_markdown_with_imports
 from _scripts.notebook_convert import convert_notebook
+from _scripts.link_map import JS_LINK_MAP

 logger = logging.getLogger(__name__)
 logging.basicConfig()
@@ -79,7 +87,7 @@ REDIRECT_MAP = {
    "cloud/how-tos/stream_events.md": "cloud/how-tos/streaming.md#stream-events",
    "cloud/how-tos/stream_debug.md": "cloud/how-tos/streaming.md#debug",
    "cloud/how-tos/stream_multiple.md": "cloud/how-tos/streaming.md#stream-multiple-modes",
-    # prebuit redirects
+    # prebuilt redirects
    "how-tos/create-react-agent.ipynb": "agents/agents.md#basic-configuration",
    "how-tos/create-react-agent-memory.ipynb": "agents/memory.md",
    "how-tos/create-react-agent-system-prompt.ipynb": "agents/context.md#prompts",
@@ -101,8 +109,7 @@ REDIRECT_MAP = {
    "how-tos/deploy-self-hosted.md": "cloud/deployment/self_hosted_data_plane.md",
    "concepts/self_hosted.md": "concepts/langgraph_self_hosted_data_plane.md",
    # assistant redirects
-    "cloud/how-tos/assistant_versioning.md": "cloud/how-tos/configuration_cloud.md"
-
+    "cloud/how-tos/assistant_versioning.md": "cloud/how-tos/configuration_cloud.md",
 }


@@ -152,6 +159,62 @@ def _add_path_to_code_blocks(markdown: str, page: Page) -> str:
    return code_block_pattern.sub(replace_code_block_header, markdown)


+def _resolve_cross_references(md_text: str, link_map: dict[str, str]) -> str:
+    """Replace [title][identifier] with [title](url) using language-specific link_map.
+
+    Args:
+        md_text: The markdown text to process.
+        link_map: mapping of identifier to URL.
+
+    Returns:
+        The processed markdown text with cross-references resolved.
+    """
+    # Pattern to match [title][identifier]
+    pattern = re.compile(r"\[([^\]]+)\]\[([^\]]+)\]")
+
+    def replace_reference(match: re.Match) -> str:
+        """Replace the matched reference with the corresponding URL."""
+        title, identifier = match.group(1), match.group(2)
+        url = link_map.get(identifier)
+
+        if url:
+            return f"[{title}]({url})"
+        else:
+            # Leave it unchanged if not found
+            return match.group(0)
+
+    return pattern.sub(replace_reference, md_text)
+
+
+def _apply_conditional_rendering(md_text: str, target_language: str) -> str:
+    if target_language not in {"python", "js"}:
+        raise ValueError("target_language must be 'python' or 'js'")
+
+    pattern = re.compile(
+        r"(?P<indent>[ \t]*):::(?P<language>\w+)\s*\n"
+        r"(?P<content>((?:.*\n)*?))"  # Capture the content inside the block
+        r"(?P=indent):::"  # Match closing with the same indentation
+    )
+
+    def replace_conditional_blocks(match: re.Match) -> str:
+        """Keep active conditionals."""
+        language = match.group("language")
+        content = match.group("content")
+
+        if language not in {"python", "js"}:
+            # If the language is not supported, return the original block
+            return match.group(0)
+
+        if language == target_language:
+            return content
+
+        # If the language does not match, return an empty string
+        return ""
+
+    processed = pattern.sub(replace_conditional_blocks, md_text)
+    return processed
+
+
 def _highlight_code_blocks(markdown: str) -> str:
    """Find code blocks with highlight comments and add hl_lines attribute.

@@ -251,6 +314,20 @@ def _on_page_markdown_with_config(
    # Apply highlight comments to code blocks
    markdown = _highlight_code_blocks(markdown)

+    # Apply conditional rendering for code blocks
+    target_language = kwargs.get("target_language", "python")
+    markdown = _apply_conditional_rendering(markdown, target_language)
+    if target_language == "js":
+        markdown = _resolve_cross_references(markdown, JS_LINK_MAP)
+    elif target_language == "python":
+        # Via a dedicated plugin
+        pass
+    else:
+        raise ValueError(
+            f"Unsupported target language: {target_language}. "
+            "Supported languages are 'python' and 'js'."
+        )
+
    # Add file path as an attribute to code blocks that are executable.
    # This file path is used to associate fixtures with the executable code
    # which can be used in CI to test the docs without making network requests.
@@ -292,7 +369,7 @@ Redirecting...
 """


-def write_html(site_dir, old_path, new_path):
+def _write_html(site_dir, old_path, new_path):
    """Write an HTML file in the site_dir with a meta redirect to the new page"""
    # Determine all relevant paths
    old_path_abs = os.path.join(site_dir, old_path)
@@ -308,6 +385,52 @@ def write_html(site_dir, old_path, new_path):
        f.write(content)


+def _inject_gtm(html: str) -> str:
+    """Inject Google Tag Manager code into the HTML.
+
+    Code to inject Google Tag Manager noscript tag immediately after <body>.
+
+    This is done via hooks rather than via a template because the MkDocs material
+    theme does not seem to allow placing the code immediately after the <body> tag
+    without modifying the template files directly.
+
+    Args:
+        html: The HTML content to modify.
+
+    Returns:
+        The modified HTML content with GTM code injected.
+    """
+    # Code was copied from Google Tag Manager setup instructions.
+    gtm_code = """
+<!-- Google Tag Manager (noscript) -->
+<noscript><iframe src="https://www.googletagmanager.com/ns.html?id=GTM-T35S4S46"
+height="0" width="0" style="display:none;visibility:hidden"></iframe></noscript>
+<!-- End Google Tag Manager (noscript) -->
+"""
+    soup = BeautifulSoup(html, "html.parser")
+    body = soup.body
+    if body:
+        # Insert the GTM code as raw HTML at the top of <body>
+        body.insert(0, BeautifulSoup(gtm_code, "html.parser"))
+        return str(soup)
+    else:
+        return html  # fallback if no <body> found
+
+
+def on_post_page(output: str, page: Page, config: MkDocsConfig) -> str:
+    """Inject Google Tag Manager noscript tag immediately after <body>.
+
+    Args:
+        output: The HTML output of the page.
+        page: The page instance.
+        config: The MkDocs configuration object.
+
+    Returns:
+        modified HTML output with GTM code injected.
+    """
+    return _inject_gtm(output)
+
+
 # Create HTML files for redirects after site dir has been built
 def on_post_build(config):
    use_directory_urls = config.get("use_directory_urls")
@@ -324,4 +447,4 @@ def on_post_build(config):
            + hash
            + suffix
        )
-        write_html(config["site_dir"], old_html_path, new_html_path)
+        _write_html(config["site_dir"], old_html_path, new_html_path)
@@ -38,7 +38,7 @@ client = MultiServerMCPClient(
            "transport": "stdio",
        },
        "weather": {
-            # Ensure your start your weather server on port 8000
+            # Ensure you start your weather server on port 8000
            "url": "http://localhost:8000/mcp",
            "transport": "streamable_http",
        }
@@ -88,7 +88,7 @@ ny_response = agent.invoke(

 When the agent is invoked the second time with the same `thread_id`, the original message history from the first conversation is automatically included, allowing the agent to infer that the user is asking specifically about the **weather** in New York.

-!!! Note "LangGraph Platform providers a production-ready checkpointer"
+!!! Note "LangGraph Platform provides a production-ready checkpointer"

    If you're using [LangGraph Platform](./deployment.md), during deployment your checkpointer will be automatically configured to use a production-ready database.

@@ -9,7 +9,7 @@ hide:

 # Multi-agent

-A single agent might struggle if it needs to specialize in multiple domains or manage many tools. To tackle this, you can break your agent into smaller, independent agents and composing them into a [multi-agent system](../concepts/multi_agent.md).
+A single agent might struggle if it needs to specialize in multiple domains or manage many tools. To tackle this, you can break your agent into smaller, independent agents and compose them into a [multi-agent system](../concepts/multi_agent.md).

 In multi-agent systems, agents need to communicate between each other. They do so via [handoffs](#handoffs) — a primitive that describes which agent to hand control to and the payload to send to that agent.

@@ -62,6 +62,15 @@ Starting from the `LangGraph Platform` view...
 1. In the panel, select the `Server` tab to view server logs for the revision. Server logs are only available after a revision has been deployed.
 1. Within the `Server` tab, adjust the date/time range picker as needed. By default, the date/time range picker is set to the `Last 7 days`.

+## View Deployment Metrics
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `LangGraph Platform`. The `LangGraph Platform` view contains a list of existing LangGraph Platform deployments.
+1. Select an existing deployment to monitor.
+1. Select the `Monitoring` tab to view the deployment metrics. See a list of [all available metrics](../../concepts/langgraph_control_plane.md#monitoring).
+1. Within the `Monitoring` tab, use the date/time range picker as needed. By default, the date/time range picker is set to the `Last 15 minutes`.
+
 ## Interrupt Revision

 Interrupting a revision will stop deployment of the revision.
@@ -16,4 +16,4 @@ Users can add an array of additional lines to add to the Dockerfile following th
 }
 ```

-This would install the system packages required to use Pillow if we were working with `jpeq` or `png` image formats. 
+This would install the system packages required to use Pillow if we were working with `jpeg` or `png` image formats. 
@@ -30,18 +30,17 @@ Before deploying, review the [conceptual guide for the Self-Hosted Control Plane
    1. `LangGraphPlatform CRD`: A CRD for LangGraph Platform deployments. This contains the spec for managing an instance of a LangGraph platform deployment.
    1. `operator`: This operator handles changes to your LangGraph Platform CRDs.
    1. `host-backend`: This is the [control plane](../../concepts/langgraph_control_plane.md).
-1. Two additional images will be used by the chart.
+1. Two additional images will be used by the chart. Use the images that are specified in the latest release.

        hostBackendImage:
          repository: "docker.io/langchain/hosted-langserve-backend"
          pullPolicy: IfNotPresent
-          tag: "0.9.80"
        operatorImage:
          repository: "docker.io/langchain/langgraph-operator"
          pullPolicy: IfNotPresent
-          tag: "aa9dff4"

-1. In your `values.yaml` file, enable the `langgraphPlatform` option. Note that you must also have a valid ingress setup:
+1. In your config file for langsmith (usually `langsmith_config.yaml`, enable the `langgraphPlatform` option. Note that you must also have a valid ingress setup:
+
        config:
          langgraphPlatform:
            enabled: true
@@ -95,7 +95,7 @@ my-app/

 ## Define Graphs

-Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each [CompiledGraph][langgraph.graph.graph.CompiledGraph] to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph configuration file](../reference/cli.md#configuration-file).
+Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each [CompiledStateGraph][langgraph.graph.state.CompiledStateGraph] to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph configuration file](../reference/cli.md#configuration-file).

 Example `agent.py` file, which shows how to import from other modules you define (code for the modules is not shown here, please see [this repository](https://github.com/langchain-ai/langgraph-example) to see their implementation):

@@ -108,7 +108,7 @@ my-app/

 ## Define Graphs

-Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each [CompiledGraph][langgraph.graph.graph.CompiledGraph] to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph configuration file](../reference/cli.md#configuration-file).
+Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each [CompiledStateGraph][langgraph.graph.state.CompiledStateGraph] to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph configuration file](../reference/cli.md#configuration-file).

 Example `agent.py` file, which shows how to import from other modules you define (code for the modules is not shown here, please see [this repository](https://github.com/langchain-ai/langgraph-example-pyproject) to see their implementation):

@@ -212,6 +212,7 @@ We have now created an assistant called "Open AI Assistant" that has `model_name

 Output:

+    ```
    Receiving event of type: metadata
    {'run_id': '1ef6746e-5893-67b1-978a-0f1cd4060e16'}

@@ -219,6 +220,7 @@ Output:

    Receiving event of type: updates
    {'agent': {'messages': [{'content': 'I was created by OpenAI, a research organization focused on developing and advancing artificial intelligence technology.', 'additional_kwargs': {}, 'response_metadata': {'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_157b3831f5'}, 'type': 'ai', 'name': None, 'id': 'run-e1a6b25c-8416-41f2-9981-f9cfe043f414', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    ```

 ### LangGraph Platform UI

@@ -231,9 +233,11 @@ Inside your deployment, select the "Assistants" tab. For the assistant you would
 To edit the assistant, use the `update` method. This will create a new version of the assistant with the provided edits. See the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/#langgraph_sdk.client.AssistantsClient.update) and [JS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/#update) SDK reference docs for more information.

 !!! note "Note"
-You must pass in the ENTIRE config (and metadata if you are using it). The update endpoint creates new versions completely from scratch and does not rely on previous versions.
+
+    You must pass in the ENTIRE config (and metadata if you are using it). The update endpoint creates new versions completely from scratch and does not rely on previous versions.

 For example, to update your assistant's system prompt:
+
 === "Python"

    ```python
@@ -247,5 +247,7 @@ Verify that the original, interrupted run was interrupted

 Output:

+    ```
    'interrupted'
+    ```

@@ -2,7 +2,7 @@

 !!! info "Prerequisites"

-    - [Assistants Overview](../../concepts/assistants.md)
+    - [Assistants Overview](../../../concepts/assistants.md)

 LangGraph Studio lets you view, edit, and update your assistants, and allows you to run your graph using these assistant configurations.

@@ -73,9 +73,11 @@ langgraph dev --debug-port 5678
 Then attach your preferred debugger:

 === "VS Code"
-Add this configuration to `launch.json`:
-`json
-      {
+
+    Add this configuration to `launch.json`:
+
+    ```json
+    {
        "name": "Attach to LangGraph",
        "type": "debugpy",
        "request": "attach",
@@ -83,11 +85,16 @@ Add this configuration to `launch.json`:
          "host": "0.0.0.0",
          "port": 5678
        }
-      }
-    `
-Specify the port number you chose in the previous step.
+    }
+    ```

-=== "PyCharm" 1. Go to Run → Edit Configurations 2. Click + and select "Python Debug Server" 3. Set IDE host name: `localhost` 4. Set port: `5678` (or the port number you chose in the previous step) 5. Click "OK" and start debugging
+=== "PyCharm" 
+
+    1. Go to Run → Edit Configurations 
+    2. Click + and select "Python Debug Server" 
+    3. Set IDE host name: `localhost` 
+    4. Set port: `5678` (or the port number you chose in the previous step) 
+    5. Click "OK" and start debugging

 ## Troubleshooting

@@ -0,0 +1,57 @@
+# Run experiments over a dataset
+
+LangGraph Studio supports evaluations by allowing you to run your assistant over a pre-defined LangSmith dataset. This enables you to understand how your application performs over a variety of inputs, compare the results to reference outputs, and score the results using [evaluators](../../../agents/evals.md).
+
+This guide shows you how to run an experiment end-to-end from Studio.
+
+---
+
+## Prerequisites
+
+Before running an experiment, ensure you have the following:
+
+1.  **A LangSmith dataset**: Your dataset should contain the inputs you want to test and optionally, reference outputs for comparison.
+
+    - The schema for the inputs must match the required input schema for the assistant. For more information on schemas, see [here](../../../concepts/low_level.md#schema).
+    - For more on creating datasets, see [How to Manage Datasets](https://docs.smith.langchain.com/evaluation/how_to_guides/manage_datasets_in_application#set-up-your-dataset).
+
+2.  **(Optional) Evaluators**: You can attach evaluators (e.g., LLM-as-a-Judge, heuristics, or custom functions) to your dataset in LangSmith. These will run automatically after the graph has processed all inputs.
+
+    - To learn more, read about [Evaluation Concepts](https://docs.smith.langchain.com/evaluation/concepts#evaluators).
+
+3.  **A running application**: The experiment can be run against:
+    - An application deployed on [LangGraph Platform](../../quick_start.md).
+    - A locally running application started via the [langgraph-cli](../../../tutorials/langgraph-platform/local-server.md).
+
+---
+
+## Step-by-step guide
+
+### 1. Launch the experiment
+
+Click the **Run experiment** button in the top right corner of the Studio page.
+
+### 2. Select your dataset
+
+In the modal that appears, select the dataset (or a specific dataset split) to use for the experiment and click **Start**.
+
+### 3. Monitor the progress
+
+All of the inputs in the dataset will now be run against the active assistant. Monitor the experiment's progress via the badge in the top right corner.
+
+You can continue to work in Studio while the experiment runs in the background. Click the arrow icon button at any time to navigate to LangSmith and view the detailed experiment results.
+
+---
+
+## Troubleshooting
+
+### "Run experiment" button is disabled
+
+If the "Run experiment" button is disabled, check the following:
+
+- **Deployed application**: If your application is deployed on LangGraph Platform, you may need to create a new revision to enable this feature.
+- **Local development server**: If you are running your application locally, make sure you have upgraded to the latest version of the `langgraph-cli` (`pip install -U langgraph-cli`). Additionally, ensure you have tracing enabled by setting the `LANGSMITH_API_KEY` in your project's `.env` file.
+
+### Evaluator results are missing
+
+When you run an experiment, any attached evaluators are scheduled for execution in a queue. If you don't see results immediately, it likely means they are still pending.
@@ -1,8 +1,8 @@
-# How to integrate LangGraph into your React application
+How to integrate LangGraph into your React application# How to integrate LangGraph into your React application

-!!! info "Prerequisites" 
+!!! info "Prerequisites"

-    - [LangGraph Platform](../../concepts/langgraph_platform.md) 
+    - [LangGraph Platform](../../concepts/langgraph_platform.md)
    - [LangGraph Server](../../concepts/langgraph_server.md)

 The `useStream()` React hook provides a seamless way to integrate LangGraph into your React applications. It handles all the complexities of streaming, state management, and branching logic, letting you focus on building great chat experiences.
@@ -113,6 +113,115 @@ export default function App() {
 }
 ```

+### Resume a stream after page refresh
+
+The `useStream()` hook can automatically resume an ongoing run upon mounting by setting `reconnectOnMount: true`. This is useful for continuing a stream after a page refresh, ensuring no messages and events generated during the downtime are lost.
+
+```tsx
+const thread = useStream<{ messages: Message[] }>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  reconnectOnMount: true,
+});
+```
+
+By default the ID of the created run is stored in `window.sessionStorage`, which can be swapped by passing a custom storage in `reconnectOnMount` instead. The storage is used to persist the in-flight run ID for a thread (under `lg:stream:${threadId}` key).
+
+```tsx
+const thread = useStream<{ messages: Message[] }>({
+  apiUrl: "http://localhost:2024",
+  assistantId: "agent",
+  reconnectOnMount: () => window.localStorage,
+});
+```
+
+You can also manually manage the resuming process by using the run callbacks to persist the run metadata and the `joinStream` function to resume the stream. Make sure to pass `streamResumable: true` when creating the run; otherwise some events might be lost.
+
+````tsx
+import type { Message } from "@langchain/langgraph-sdk";
+import { useStream } from "@langchain/langgraph-sdk/react";
+import { useCallback, useState, useEffect, useRef } from "react";
+
+export default function App() {
+  const [threadId, onThreadId] = useSearchParam("threadId");
+
+  const thread = useStream<{ messages: Message[] }>({
+    apiUrl: "http://localhost:2024",
+    assistantId: "agent",
+
+    threadId,
+    onThreadId,
+
+    onCreated: (run) => {
+      window.sessionStorage.setItem(`resume:${run.thread_id}`, run.run_id);
+    },
+    onFinish: (_, run) => {
+      window.sessionStorage.removeItem(`resume:${run?.thread_id}`);
+    },
+  });
+
+  // Ensure that we only join the stream once per thread.
+  const joinedThreadId = useRef<string | null>(null);
+  useEffect(() => {
+    if (!threadId) return;
+
+    const resume = window.sessionStorage.getItem(`resume:${threadId}`);
+    if (resume && joinedThreadId.current !== threadId) {
+      thread.joinStream(resume);
+      joinedThreadId.current = threadId;
+    }
+  }, [threadId]);
+
+  return (
+    <form
+      onSubmit={(e) => {
+        e.preventDefault();
+        const form = e.target as HTMLFormElement;
+        const message = new FormData(form).get("message") as string;
+        thread.submit(
+          { messages: [{ type: "human", content: message }] },
+          { streamResumable: true }
+        );
+      }}
+    >
+      <div>
+        {thread.messages.map((message) => (
+          <div key={message.id}>{message.content as string}</div>
+        ))}
+      </div>
+      <input type="text" name="message" />
+      <button type="submit">Send</button>
+    </form>
+  );
+}
+
+// Utility method to retrieve and persist data in URL as search param
+function useSearchParam(key: string) {
+  const [value, setValue] = useState<string | null>(() => {
+    const params = new URLSearchParams(window.location.search);
+    return params.get(key) ?? null;
+  });
+
+  const update = useCallback(
+    (value: string | null) => {
+      setValue(value);
+
+      const url = new URL(window.location.href);
+      if (value == null) {
+        url.searchParams.delete(key);
+      } else {
+        url.searchParams.set(key, value);
+      }
+
+      window.history.pushState({}, "", url.toString());
+    },
+    [key]
+  );
+
+  return [value, update] as const;
+}
+```
+
 ### Thread Management

 Keep track of conversations with built-in thread management. You can access the current thread ID and get notified when new threads are created:
@@ -127,7 +236,7 @@ const thread = useStream<{ messages: Message[] }>({
  threadId: threadId,
  onThreadId: setThreadId,
 });
-```
+````

 We recommend storing the `threadId` in your URL's query parameters to let users resume conversations after page refreshes.

@@ -8,15 +8,15 @@ Currently, the SDK does not provide built-in support for defining webhook endpoi

 The following API endpoints accept a `webhook` parameter:

-| Operation | HTTP Method | Endpoint |
-|-----------|------------|----------|
-| Create Run | `POST` | `/thread/{thread_id}/runs` |
-| Create Thread Cron | `POST` | `/thread/{thread_id}/runs/crons` |
-| Stream Run | `POST` | `/thread/{thread_id}/runs/stream` |
-| Wait Run | `POST` | `/thread/{thread_id}/runs/wait` |
-| Create Cron | `POST` | `/runs/crons` |
-| Stream Run Stateless | `POST` | `/runs/stream` |
-| Wait Run Stateless | `POST` | `/runs/wait` |
+| Operation            | HTTP Method | Endpoint                          |
+|----------------------|-------------|-----------------------------------|
+| Create Run           | `POST`      | `/thread/{thread_id}/runs`        |
+| Create Thread Cron   | `POST`      | `/thread/{thread_id}/runs/crons`  |
+| Stream Run           | `POST`      | `/thread/{thread_id}/runs/stream` |
+| Wait Run             | `POST`      | `/thread/{thread_id}/runs/wait`   |
+| Create Cron          | `POST`      | `/runs/crons`                     |
+| Stream Run Stateless | `POST`      | `/runs/stream`                    |
+| Wait Run Stateless   | `POST`      | `/runs/wait`                      |

 In this guide, we’ll show how to trigger a webhook after streaming a run.

@@ -25,36 +25,39 @@ In this guide, we’ll show how to trigger a webhook after streaming a run.
 Before making API calls, set up your assistant and thread.

 === "Python"
-```python
-from langgraph_sdk import get_client

-client = get_client(url=<DEPLOYMENT_URL>)
-assistant_id = "agent"
-thread = await client.threads.create()
-print(thread)
-```
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url=<DEPLOYMENT_URL>)
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    print(thread)
+    ```

 === "JavaScript"
-```js
-import { Client } from "@langchain/langgraph-sdk";

-const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
-const assistantID = "agent";
-const thread = await client.threads.create();
-console.log(thread);
-```
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    const assistantID = "agent";
+    const thread = await client.threads.create();
+    console.log(thread);
+    ```

 === "CURL"
-```bash
-curl --request POST \
-    --url <DEPLOYMENT_URL>/assistants/search \
-    --header 'Content-Type: application/json' \
-    --data '{ "limit": 10, "offset": 0 }' | jq -c 'map(select(.config == null or .config == {})) | .[0]' && \
-curl --request POST \
-    --url <DEPLOYMENT_URL>/threads \
-    --header 'Content-Type: application/json' \
-    --data '{}'
-```
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/assistants/search \
+        --header 'Content-Type: application/json' \
+        --data '{ "limit": 10, "offset": 0 }' | jq -c 'map(select(.config == null or .config == {})) | .[0]' && \
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads \
+        --header 'Content-Type: application/json' \
+        --data '{}'
+    ```

 Example response:

@@ -77,48 +80,51 @@ To use a webhook, specify the `webhook` parameter in your API request. When the
 For example, if your server listens for webhook events at `https://my-server.app/my-webhook-endpoint`, include this in your request:

 === "Python"
-```python
-input = { "messages": [{ "role": "user", "content": "Hello!" }] }

-async for chunk in client.runs.stream(
-    thread_id=thread["thread_id"],
-    assistant_id=assistant_id,
-    input=input,
-    stream_mode="events",
-    webhook="https://my-server.app/my-webhook-endpoint"
-):
-    pass
-```
+    ```python
+    input = { "messages": [{ "role": "user", "content": "Hello!" }] }
+
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id=assistant_id,
+        input=input,
+        stream_mode="events",
+        webhook="https://my-server.app/my-webhook-endpoint"
+    ):
+        pass
+    ```

 === "JavaScript"
-```js
-const input = { messages: [{ role: "human", content: "Hello!" }] };

-const streamResponse = client.runs.stream(
-  thread["thread_id"],
-  assistantID,
-  {
-    input: input,
-    webhook: "https://my-server.app/my-webhook-endpoint"
-  }
-);
+    ```js
+    const input = { messages: [{ role: "human", content: "Hello!" }] };

-for await (const chunk of streamResponse) {
-  // Handle stream output
-}
-```
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantID,
+      {
+        input: input,
+        webhook: "https://my-server.app/my-webhook-endpoint"
+      }
+    );
+
+    for await (const chunk of streamResponse) {
+      // Handle stream output
+    }
+    ```

 === "CURL"
-```bash
-curl --request POST \
-    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
-    --header 'Content-Type: application/json' \
-    --data '{
-        "assistant_id": <ASSISTANT_ID>,
-        "input": {"messages": [{"role": "user", "content": "Hello!"}]},
-        "webhook": "https://my-server.app/my-webhook-endpoint"
-    }'
-```
+
+    ```bash
+    curl --request POST \
+        --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+        --header 'Content-Type: application/json' \
+        --data '{
+            "assistant_id": <ASSISTANT_ID>,
+            "input": {"messages": [{"role": "user", "content": "Hello!"}]},
+            "webhook": "https://my-server.app/my-webhook-endpoint"
+        }'
+    ```

 ## Webhook payload

@@ -3818,6 +3818,14 @@
            "title": "Filter",
            "description": "Optional dictionary of key-value pairs to filter results."
          },
+          "query": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "title": "Query",
+            "description": "Query string for semantic/vector search."
+          },
          "limit": {
            "type": "integer",
            "default": 10,
@@ -43,15 +43,17 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
    | <span style="white-space: nowrap;">`graphs`</span>           | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./your_package/your_file.py:variable`, where `variable` is an instance of `langgraph.graph.state.CompiledStateGraph`</li><li>`./your_package/your_file.py:make_graph`, where `make_graph` is a function that takes a config dictionary (`langchain_core.runnables.RunnableConfig`) and returns an instance of `langgraph.graph.state.StateGraph` or `langgraph.graph.state.CompiledStateGraph`. See [how to rebuild a graph at runtime](../../cloud/deployment/graph_rebuild.md) for more details.</li></ul>                                    |
    | <span style="white-space: nowrap;">`auth`</span>             | _(Added in v0.0.11)_ Auth configuration containing the path to your authentication handler. Example: `./your_package/auth.py:auth`, where `auth` is an instance of `langgraph_sdk.Auth`. See [authentication guide](../../concepts/auth.md) for details.                                                                                                                                                                                                                                                                                                                        |
    | <span style="white-space: nowrap;">`base_image`</span>       | Optional. Base image to use for the LangGraph API server. Defaults to `langchain/langgraph-api` or `langchain/langgraphjs-api`. Use this to pin your builds to a particular version of the langgraph API, such as `"langchain/langgraph-server:0.2"`. See https://hub.docker.com/r/langchain/langgraph-server/tags for more details. (added in `langgraph-cli==0.2.8`) |
+    | <span style="white-space: nowrap;">`image_distro`</span>     | Optional. Linux distribution for the base image. Must be either `"debian"` or `"wolfi"`. If omitted, defaults to `"debian"`. Available in `langgraph-cli>=0.2.11`.|
    | <span style="white-space: nowrap;">`env`</span>              | Path to `.env` file or a mapping from environment variable to its value.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
    | <span style="white-space: nowrap;">`store`</span>            | Configuration for adding semantic search and/or time-to-live (TTL) to the BaseStore. Contains the following fields: <ul><li>`index` (optional): Configuration for semantic search indexing with fields `embed`, `dims`, and optional `fields`.</li><li>`ttl` (optional): Configuration for item expiration. An object with optional fields: `refresh_on_read` (boolean, defaults to `true`), `default_ttl` (float, lifespan in **minutes**, defaults to no expiration), and `sweep_interval_minutes` (integer, how often to check for expired items, defaults to no sweeping).</li></ul> |
    | <span style="white-space: nowrap;">`ui`</span>               | Optional. Named definitions of UI components emitted by the agent, each pointing to a JS/TS file. (added in `langgraph-cli==0.1.84`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
    | <span style="white-space: nowrap;">`python_version`</span>   | `3.11`, `3.12`, or `3.13`. Defaults to `3.11`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
    | <span style="white-space: nowrap;">`node_version`</span>     | Specify `node_version: 20` to use LangGraph.js.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
    | <span style="white-space: nowrap;">`pip_config_file`</span>  | Path to `pip` config file.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+    | <span style="white-space: nowrap;">`pip_installer`</span> | _(Added in v0.3)_ Optional. Python package installer selector. It can be set to `"auto"`, `"pip"`, or `"uv"`. From version&nbsp;0.3 onward the default strategy is to run `uv pip`, which typically delivers faster builds while remaining a drop-in replacement. In the uncommon situation where `uv` cannot handle your dependency graph or the structure of your `pyproject.toml`, specify `"pip"` here to revert to the earlier behaviour. |
    | <span style="white-space: nowrap;">`dockerfile_lines`</span> | Array of additional lines to add to Dockerfile following the import from parent image.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
    | <span style="white-space: nowrap;">`checkpointer`</span>   | Configuration for the checkpointer. Contains a `ttl` field which is an object with the following keys: <ul><li>`strategy`: How to handle expired checkpoints (e.g., `"delete"`).</li><li>`sweep_interval_minutes`: How often to check for expired checkpoints (integer).</li><li>`default_ttl`: Default time-to-live for checkpoints in **minutes** (integer). Defines how long checkpoints are kept before the specified strategy is applied.</li></ul> |
-    | <span style="white-space: nowrap;">`http`</span>            | HTTP server configuration with the following fields: <ul><li>`app`: Path to custom Starlette/FastAPI app (e.g., `"./src/agent/webapp.py:app"`). See [custom routes guide](../../how-tos/http/custom_routes.md).</li><li>`disable_assistants`: Disable `/assistants` routes</li><li>`disable_threads`: Disable `/threads` routes</li><li>`disable_runs`: Disable `/runs` routes</li><li>`disable_store`: Disable `/store` routes</li><li>`disable_meta`: Disable `/ok`, `/info`, `/metrics`, and `/docs` routes</li><li>`cors`: CORS configuration with fields for `allow_origins`, `allow_methods`, `allow_headers`, etc.</li><li>`configurable_headers`: Define which request headers to exclude or include as a run's configurable values.</li></ul> |
+    | <span style="white-space: nowrap;">`http`</span>            | HTTP server configuration with the following fields: <ul><li>`app`: Path to custom Starlette/FastAPI app (e.g., `"./src/agent/webapp.py:app"`). See [custom routes guide](../../how-tos/http/custom_routes.md).</li><li>`disable_assistants`: Disable `/assistants` routes</li><li>`disable_threads`: Disable `/threads` routes</li><li>`disable_runs`: Disable `/runs` routes</li><li>`disable_store`: Disable `/store` routes</li><li>`disable_meta`: Disable `/ok`, `/info`, `/metrics`, and `/docs` routes</li><li>`disable_mcp`: Disable `/mcp` routes</li><li>`cors`: CORS configuration with fields for `allow_origins`, `allow_methods`, `allow_headers`, etc.</li><li>`configurable_headers`: Define which request headers to exclude or include as a run's configurable values.</li></ul> |

 === "JS"

@@ -79,6 +81,20 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
    }
    ```

+    #### Using Wolfi Base Images
+
+    You can specify the Linux distribution for your base image using the `image_distro` field. Valid options are `debian` or `wolfi`. Wolfi is the recommended option as it provides smaller and more secure images. This is available in `langgraph-cli>=0.2.11`.
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "chat": "./chat/graph.py:graph"
+      },
+      "image_distro": "wolfi"
+    }
+    ```
+
    #### Adding semantic search to the store

    All deployments come with a DB-backed BaseStore. Adding an "index" configuration to your `langgraph.json` will enable [semantic search](../deployment/semantic_search.md) within the BaseStore of your deployment.
@@ -113,7 +129,7 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](
        - `cohere:embed-english-v3.0`: 1024 
        - `cohere:embed-english-light-v3.0`: 384 
        - `cohere:embed-multilingual-v3.0`: 1024 
-        - `cohere:embed-multilingual-light-v3.0`: 384
+        - `cohere:embed-multilingual-light-v3.0`: 384 

    #### Semantic search with a custom embedding function

@@ -346,8 +362,8 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](

    **Options**

-    | Option               | Default          | Description                                                                                                                  |
-    | -------------------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------- |
+    | Option               | Default          | Description                                                                                                     |
+    | -------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- |
    | `--platform TEXT`    |                  | Target platform(s) to build the Docker image for. Example: `langgraph build --platform linux/amd64,linux/arm64`              |
    | `-t, --tag TEXT`     |                  | **Required**. Tag for the Docker image. Example: `langgraph build -t my-image`                                               |
    | `--pull / --no-pull` | `--pull`         | Build with latest remote Docker image. Use `--no-pull` for running the LangGraph Platform API server with locally built images. |
@@ -366,8 +382,8 @@ The LangGraph CLI requires a JSON configuration file that follows this [schema](

    **Options**

-    | Option               | Default          | Description                                                                                                                  |
-    | -------------------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------- |
+    | Option               | Default          | Description                                                                                                     |
+    | -------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- |
    | `--platform TEXT`    |                  | Target platform(s) to build the Docker image for. Example: `langgraph build --platform linux/amd64,linux/arm64`              |
    | `-t, --tag TEXT`     |                  | **Required**. Tag for the Docker image. Example: `langgraph build -t my-image`                                               |
    | `--no-pull`          |                  | Use locally built images. Defaults to `false` to build with latest remote Docker image.                                      |
@@ -50,11 +50,10 @@ Set this environment variable to have a deployment send traces to a self-hosted

 ## `LANGSMITH_TRACING`

-!!! info "Only for Self-Hosted Data Plane, Self-Hosted Control Plane, and Standalone Container"
-    Disabling LangSmith tracing is only available for [Self-Hosted Data Plane](../../concepts/langgraph_self_hosted_data_plane.md), [Self-Hosted Control Plane](../../concepts/langgraph_self_hosted_control_plane.md), and [Standalone Container](../../concepts/langgraph_standalone_container.md) deployments.
-
 Set `LANGSMITH_TRACING` to `false` to disable tracing to LangSmith.

+Defaults to `true`.
+
 ## `LOG_LEVEL`

 Configure [log level](https://docs.python.org/3/library/logging.html#logging-levels). Defaults to `INFO`.
@@ -123,3 +122,12 @@ Defaults to `''`.
 Set `REDIS_CLUSTER` to `True` to enable Redis Cluster mode. When enabled, the system will connect to Redis using cluster mode. This is useful when connecting to a Redis Cluster deployment.

 Defaults to `False`.
+
+## `MOUNT_PREFIX`
+
+!!! info "Only Allowed in Self-Hosted Deployments"
+    The `MOUNT_PREFIX` environment variable is only allowed in Self-Hosted Deployment models, LangGraph Platform SaaS will not allow this environment variable.
+
+Set `MOUNT_PREFIX` to serve the LangGraph Server under a specific path prefix. This is useful for deployments where the server is behind a reverse proxy or load balancer that requires a specific path prefix.
+
+For example, if the server is to be served under `https://example.com/langgraph`, set `MOUNT_PREFIX` to `/langgraph`.
@@ -32,7 +32,7 @@ Below are examples of directory structures for Python and JavaScript application
    │   ├── utils # utilities for your graph
    │   │   ├── __init__.py
    │   │   ├── tools.py # tools for your graph
-    │   │   ├── nodes.py # node functions for you graph
+    │   │   ├── nodes.py # node functions for your graph
    │   │   └── state.py # state definition of your graph
    │   ├── __init__.py
    │   └── agent.py # code for constructing your graph
@@ -26,4 +26,4 @@ Once you've created an assistant, subsequent edits to that assistant will create

 ## Learn more

-* The LangGraph Cloud API provides several endpoints for creating and managing assistants their versions. See the [API reference](../cloud/reference/api/api_ref.html#tag/assistants) for more details.
+* The LangGraph Cloud API provides several endpoints for creating and managing assistants and their versions. See the [API reference](../cloud/reference/api/api_ref.html#tag/assistants) for more details.
@@ -198,7 +198,7 @@ async def add_owner(
 You can register handlers for specific resources and actions by chaining the resource and action names together with the [`@auth.on`](../cloud/reference/sdk/python_sdk_ref.md#langgraph_sdk.auth.Auth.on) decorator.
 When a request is made, the most specific handler that matches that resource and action is called. Below is an example of how to register handlers for specific resources and actions. For the following setup:

-1. Authenticated users are able to create threads, read thread, create runs on threads
+1. Authenticated users are able to create threads, read threads, and create runs on threads
 2. Only users with the "assistants:create" permission are allowed to create new assistants
 3. All other endpoints (e.g., e.g., delete assistant, crons, store) are disabled for all users.

@@ -59,7 +59,7 @@ For more information, please see:
 !!! info "Important"
    The Self-Hosted Control Plane deployment option is currently in beta stage and requires an [Enterprise](../concepts/plans.md) plan.

-The [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md) deployment option is a fully self-hosted model for deployment where you manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in your cloud. This option give you full control and responsibility of the control plane and data plane infrastructure.
+The [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md) deployment option is a fully self-hosted model for deployment where you manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in your cloud. This option gives you full control and responsibility of the control plane and data plane infrastructure.

 Build a Docker image using the [LangGraph CLI](./langgraph_cli.md) and deploy your LangGraph Server from the [control plane UI](./langgraph_control_plane.md#control-plane-ui).

@@ -59,8 +59,8 @@ Yes! You can use LangGraph with any LLMs. The main reason we use LLMs that suppo

 Yes! LangGraph is totally ambivalent to what LLMs are used under the hood. The main reason we use closed LLMs in most of the tutorials is that they seamlessly support tool calling, while OSS LLMs often don't. But tool calling is not necessary (see [this section](#does-langgraph-work-with-llms-that-dont-support-tool-calling)) so you can totally use LangGraph with OSS LLMs.

-## Can I use LangGraph Studio without logging to LangSmith
+## Can I use LangGraph Studio without logging in to LangSmith

 Yes! You can use the [development version of LangGraph Server](../tutorials/langgraph-platform/local-server.md) to run the backend locally.
 This will connect to the studio frontend hosted as part of LangSmith.
-If you set an environment variable of `LANGSMITH_TRACING=false` then no traces will be sent to LangSmith.
+If you set an environment variable of `LANGSMITH_TRACING=false`, then no traces will be sent to LangSmith.
@@ -186,7 +186,7 @@ When declaring an `entrypoint`, you can request access to additional parameters

 | Parameter    | Description                                                                                                                                                        |
 |--------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| **previous** | Access the the state associated with the previous `checkpoint` for the given thread. See [short-term-memory](#short-term-memory).                                  |
+| **previous** | Access the state associated with the previous `checkpoint` for the given thread. See [short-term-memory](#short-term-memory).                                  |
 | **store**    | An instance of [BaseStore][langgraph.store.base.BaseStore]. Useful for [long-term memory](../how-tos/use-functional-api.md#long-term-memory).                      |
 | **writer**   | Use to access the StreamWriter when working with Async Python < 3.11. See [streaming with functional API for details](../how-tos/use-functional-api.md#streaming). |
 | **config**   | For accessing run time configuration. See [RunnableConfig](https://python.langchain.com/docs/concepts/runnables/#runnableconfig) for information.                  |
@@ -9,13 +9,18 @@ search:

 ## Installation

-The LangGraph CLI can be installed via pip:
+The LangGraph CLI can be installed via pip or [Homebrew](https://brew.sh/):

 === "pip" 
    ```bash
    pip install langgraph-cli
    ```

+=== "Homebrew"
+    ```bash
+    brew install langgraph-cli
+    ```
+
 ## Commands

 LangGraph CLI provides the following core functionality:
@@ -19,6 +19,7 @@ From the control plane UI, you can:
 - Update a deployment.
 - Update environment variables for a deployment.
 - View build and server logs of a deployment.
+- View deployment metrics such as CPU and memory usage.
 - Delete a deployment.

 The Control Plane UI is embedded in [LangSmith](https://docs.smith.langchain.com/langgraph_cloud).
@@ -88,6 +89,17 @@ Infrastructure for deployments and revisions are provisioned and deployed asynch

 The control plane and [LangGraph Data Plane](./langgraph_data_plane.md) "listener" application coordinate to achieve asynchronous deployments.

+### Monitoring
+
+After a deployment is ready, the control plane monitors the deployment and records various metrics, such as:
+
+- CPU and memory usage of the deployment.
+- Number of container restarts.
+- Number of replicas (this will increase with [autoscaling](../concepts/langgraph_data_plane.md#autoscaling)).
+- [Postgres](../concepts/langgraph_data_plane.md#postgres) CPU, memory usage, and disk usage.
+
+These metrics are displayed as charts in the Control Plane UI.
+
 ### LangSmith Integration

 A [LangSmith](https://docs.smith.langchain.com/) tracing project is automatically created for each deployment. The tracing project has the same name as the deployment. When creating a deployment, the `LANGCHAIN_TRACING` and `LANGSMITH_API_KEY`/`LANGCHAIN_API_KEY` environment variables do not need to be specified; they are set automatically by the control plane.
@@ -9,7 +9,7 @@ The term "data plane" is used broadly to refer to [LangGraph Servers](./langgrap

 ## Server Infrastructure

-In addition to the [LangGraph Server](./langgraph_server.md) itself, the following infrastructure for each server are also included in the broad definition of "data plane":
+In addition to the [LangGraph Server](./langgraph_server.md) itself, the following infrastructure components for each server are also included in the broad definition of "data plane":

 - Postgres
 - Redis
@@ -44,7 +44,7 @@ All runs in a LangGraph Server are executed by a pool of background workers that

 ### Ephemeral metadata

-Runs in a LangGraph Server may be retried for specific failures (currently only for transient Postgres errors encountered during the run). In order to limit the number of retries (currently limited to 3 attempts per run) we record the attempt number in a Redis string when is picked up. This contains no run-specific info other than its ID, and expires after a short delay.
+Runs in a LangGraph Server may be retried for specific failures (currently only for transient Postgres errors encountered during the run). In order to limit the number of retries (currently limited to 3 attempts per run) we record the attempt number in a Redis string when it is picked up. This contains no run-specific info other than its ID, and expires after a short delay.

 ## Data Plane Features

@@ -62,7 +62,7 @@ For CPU utilization, the autoscaler targets 75% utilization. This means the auto

 For number of pending runs, the autoscaler targets 10 pending runs. For example, if the current number of containers is 1, but the number of pending runs in 20, the autoscaler will scale up the deployment to 2 containers (20 pending runs / 2 containers = 10 pending runs per container).

-Each metric is computed independently and the autoscaler will determine the scaling action based on the metric that results in the most number of containers.
+Each metric is computed independently and the autoscaler will determine the scaling action based on the metric that results in the largest number of containers.

 Scale down actions are delayed for 30 minutes before any action is taken. In other words, if the autoscaler decides to scale down a deployment, it will first wait for 30 minutes before scaling down. After 30 minutes, the metrics are recomputed and the deployment will scale down if the recomputed metrics result in a lower number of containers than the current number. Otherwise, the deployment remains scaled up. This "cool down" period ensures that deployments do not scale up and down too frequently.

@@ -9,7 +9,7 @@ Develop, deploy, scale, and manage agents with **LangGraph Platform** — the pu

 !!! tip "Get started with LangGraph Platform"

-    Check out the [LangGraph Platform quickstart](../tutorials/langgraph-platform/local-server.md) for instructions on how to use LangGraph Platform run a LangGraph application locally.
+    Check out the [LangGraph Platform quickstart](../tutorials/langgraph-platform/local-server.md) for instructions on how to use LangGraph Platform to run a LangGraph application locally.

 ## Why use LangGraph Platform?

@@ -33,4 +33,4 @@ LangGraph Platform makes it easy to get your agent running in production —  wh

 - **[LangGraph Studio](./langgraph_studio.md)**: Enables visualization, interaction, and debugging of agentic systems that implement the LangGraph Server API protocol. Studio also integrates with LangSmith to enable tracing, evaluation, and prompt engineering.

- **[Deployment](./deployment_options.md)**: There are four ways to deploy on LangGraph Platform: [Cloud Saas](../concepts/langgraph_cloud.md), [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md), [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md), and [Standalone Container](../concepts/langgraph_standalone_container.md).
+- **[Deployment](./deployment_options.md)**: There are four ways to deploy on LangGraph Platform: [Cloud SaaS](../concepts/langgraph_cloud.md), [Self-Hosted Data Plane](../concepts/langgraph_self_hosted_data_plane.md), [Self-Hosted Control Plane](../concepts/langgraph_self_hosted_control_plane.md), and [Standalone Container](../concepts/langgraph_standalone_container.md).
@@ -9,10 +9,12 @@ There are two versions of the self-hosted deployment: [Self-Hosted Data Plane](.

 - You use `langgraph-cli` and/or [LangGraph Studio](./langgraph_studio.md) app to test graph locally.
 - You use `langgraph build` command to build image.
+- You have a Self-Hosted LangSmith instance deployed.
+- You are using Ingress for your LangSmith instance. All agents will be deployed as Kubernetes services behind this ingress.

 ## Self-Hosted Control Plane

-The [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md) deployment option is a fully self-hosted model for deployment where you manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in your cloud. This option give you full control and responsibility of the control plane and data plane infrastructure.
+The [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md) deployment option is a fully self-hosted model for deployment where you manage the [control plane](./langgraph_control_plane.md) and [data plane](./langgraph_data_plane.md) in your cloud. This option gives you full control and responsibility of the control plane and data plane infrastructure.

 |                   | [Control plane](../concepts/langgraph_control_plane.md) | [Data plane](../concepts/langgraph_data_plane.md) |
 |-------------------|-------------------|------------|
@@ -29,4 +31,4 @@ The [Self-Hosted Control Plane](./langgraph_self_hosted_control_plane.md) deploy
 - **Kubernetes**: The Self-Hosted Control Plane deployment option supports deploying control plane and data plane infrastructure to any Kubernetes cluster.

 !!! tip
-    If you would like to deploy to Kubernetes, you can use this [Helm chart](https://github.com/langchain-ai/helm/blob/main/charts/langgraph-cloud/README.md).
+    If you would like to enable this on your LangSmith instance, please follow the [Self-Hosted Control Plane deployment guide](../cloud/deployment/self_hosted_control_plane.md).
@@ -37,4 +37,4 @@ For information on how to deploy a [LangGraph Server](../concepts/langgraph_serv
 - **Amazon ECS**: Coming soon!

 !!! tip
-    If you would like to deploy to Kubernetes, you can use this [Helm chart](https://github.com/langchain-ai/helm/blob/main/charts/langgraph-cloud/README.md).
+    If you would like to deploy to Kubernetes, you can follow the [Self-Hosted Data Plane deployment guide](../cloud/deployment/self_hosted_data_plane.md).
@@ -26,7 +26,7 @@ Feature Differences:
 |-------|------------|------------|
 | [Cron Jobs](../cloud/concepts/cron_jobs.md) |❌|✅|
 | [Custom Authentication](../concepts/auth.md) |❌|✅|
-| [Deployment options](../concepts/deployment_options.md) | Standalone container | Cloud Saas, Self-Hosted Data Plane, Self-Hosted Control Plane, Standalone container
+| [Deployment options](../concepts/deployment_options.md) | Standalone container | Cloud SaaS, Self-Hosted Data Plane, Self-Hosted Control Plane, Standalone container

 ## Application structure

@@ -21,9 +21,10 @@ Key features of LangGraph Studio:

 - Visualize your graph architecture
 - [Run and interact with your agent](../cloud/how-tos/invoke_studio.md)
- [Manage assistants](../cloud/how-tos/studio/manage_assistants.md.md)
+- [Manage assistants](../cloud/how-tos/studio/manage_assistants.md)
 - [Manage threads](../cloud/how-tos/threads_studio.md)
 - [Iterate on prompts](../cloud/how-tos/iterate_graph_studio.md)
+- [Run experiments over a dataset](../cloud/how-tos/studio/run_evals.md)
 - Manage [long term memory](memory.md)
 - Debug agent state via [time travel](time-travel.md)

@@ -33,7 +34,7 @@ Studio supports two modes:

 ### Graph mode

-Graph mode exposes the full feature-set of Studio and is useful when you would like as many details about the execution of your agent, including the nodes traversed, intermediate states, and LangSmith integrations (such as adding to datasets an playground).
+Graph mode exposes the full feature-set of Studio and is useful when you would like as many details about the execution of your agent, including the nodes traversed, intermediate states, and LangSmith integrations (such as adding to datasets and playground).

 ### Chat mode

@@ -41,4 +42,4 @@ Chat mode is a simpler UI for iterating on and testing chat-specific agents. It

 ## Learn more

- See this guide on how to [get started](../cloud/how-tos/studio/quick_start.md) with LangGraph Studio.
+- See this guide on how to [get started](../cloud/how-tos/studio/quick_start.md) with LangGraph Studio.
@@ -89,7 +89,7 @@ def node_3(state: PrivateState) -> OutputState:
    # Read from PrivateState, write to OutputState
    return {"graph_output": state["bar"] + " Lance"}

-builder = StateGraph(OverallState,input=InputState,output=OutputState)
+builder = StateGraph(OverallState,input_schema=InputState,output_schema=OutputState)
 builder.add_node("node_1", node_1)
 builder.add_node("node_2", node_2)
 builder.add_node("node_3", node_3)
@@ -105,9 +105,9 @@ graph.invoke({"user_input":"My"})

 There are two subtle and important points to note here:

-1. We pass `state: InputState` as the input schema to `node_1`. But, we write out to `foo`, a channel in `OverallState`. How can we write out to a state channel that is not included in the input schema? This is because a node _can write to any state channel in the graph state._ The graph state is the union of of the state channels defined at initialization, which includes `OverallState` and the filters `InputState` and `OutputState`.
+1. We pass `state: InputState` as the input schema to `node_1`. But, we write out to `foo`, a channel in `OverallState`. How can we write out to a state channel that is not included in the input schema? This is because a node _can write to any state channel in the graph state._ The graph state is the union of the state channels defined at initialization, which includes `OverallState` and the filters `InputState` and `OutputState`.

-2. We initialize the graph with `StateGraph(OverallState,input=InputState,output=OutputState)`. So, how can we write to `PrivateState` in `node_2`? How does the graph gain access to this schema if it was not passed in the `StateGraph` initialization? We can do this because _nodes can also declare additional state channels_ as long as the state schema definition exists. In this case, the `PrivateState` schema is defined, so we can add `bar` as a new state channel in the graph and write to it.
+2. We initialize the graph with `StateGraph(OverallState,input_schema=InputState,output_schema=OutputState)`. So, how can we write to `PrivateState` in `node_2`? How does the graph gain access to this schema if it was not passed in the `StateGraph` initialization? We can do this because _nodes can also declare additional state channels_ as long as the state schema definition exists. In this case, the `PrivateState` schema is defined, so we can add `bar` as a new state channel in the graph and write to it.

 ### Reducers

@@ -167,7 +167,7 @@ In addition to keeping track of message IDs, the `add_messages` function will al
 {"messages": [{"type": "human", "content": "message"}]}
 ```

-Since the state updates are always deserialized into LangChain `Messages` when using `add_messages`, you should use dot notation to access message attributes, like `state["messages"][-1].content`. Below is an example of a graph that uses `add_messages` as it's reducer function.
+Since the state updates are always deserialized into LangChain `Messages` when using `add_messages`, you should use dot notation to access message attributes, like `state["messages"][-1].content`. Below is an example of a graph that uses `add_messages` as its reducer function.

 ```python
 from langchain_core.messages import AnyMessage
@@ -197,19 +197,25 @@ In LangGraph, nodes are typically python functions (sync or async) where the **f
 Similar to `NetworkX`, you add these nodes to a graph using the [add_node][langgraph.graph.StateGraph.add_node] method:

 ```python
+from typing_extensions import TypedDict
+
 from langchain_core.runnables import RunnableConfig
 from langgraph.graph import StateGraph

-builder = StateGraph(dict)
+class State(TypedDict):
+    input: str
+    results: str
+
+builder = StateGraph(State)


-def my_node(state: dict, config: RunnableConfig):
+def my_node(state: State, config: RunnableConfig):
    print("In node: ", config["configurable"]["user_id"])
    return {"results": f"Hello, {state['input']}!"}


 # The second argument is optional
-def my_other_node(state: dict):
+def my_other_node(state: State):
    return state


@@ -87,6 +87,7 @@ One of the most common agent types is a [tool-calling agent](../agents/overview.
 ```python
 from langchain_core.tools import tool

+@tool
 def transfer_to_bob():
    """Transfer to bob."""
    return Command(
@@ -414,4 +415,4 @@ There are two high-level approaches to achieve that:
 An agent might need to have a different state schema from the rest of the agents. For example, a search agent might only need to keep track of queries and retrieved documents. There are two ways to achieve this in LangGraph:

 - Define [subgraph](./subgraphs.md) agents with a separate state schema. If there are no shared state keys (channels) between the subgraph and the parent graph, it’s important to [add input / output transformations](../how-tos/subgraph.ipynb#different-state-schemas) so that the parent graph knows how to communicate with the subgraphs.
- Define agent node functions with a [private input state schema](../how-tos/graph-api.ipynb/#pass-private-state-between-nodes) that is distinct from the overall graph state schema. This allows passing information that is only needed for executing that particular agent.
+- Define agent node functions with a [private input state schema](../how-tos/graph-api.ipynb/#pass-private-state-between-nodes) that is distinct from the overall graph state schema. This allows passing information that is only needed for executing that particular agent.
@@ -383,7 +383,7 @@ def update_memory(state: MessagesState, config: RunnableConfig, *, store: BaseSt

 ```

-As we showed above, we can also access the store in any node and use the `store.search` method to get memories. Recall the the memories are returned as a list of objects that can be converted to a dictionary.
+As we showed above, we can also access the store in any node and use the `store.search` method to get memories. Recall the memories are returned as a list of objects that can be converted to a dictionary.

 ```python
 memories[-1].dict()
@@ -470,9 +470,51 @@ If the checkpointer is used with asynchronous graph execution (i.e. executing th

 ### Serializer

-When checkpointers save the graph state, they need to serialize the channel values in the state. This is done using serializer objects. 
+When checkpointers save the graph state, they need to serialize the channel values in the state. This is done using serializer objects.
 `langgraph_checkpoint` defines [protocol][langgraph.checkpoint.serde.base.SerializerProtocol] for implementing serializers provides a default implementation ([JsonPlusSerializer][langgraph.checkpoint.serde.jsonplus.JsonPlusSerializer]) that handles a wide variety of types, including LangChain and LangGraph primitives, datetimes, enums and more.

+#### Serialization with `pickle`
+
+The default serializer, [`JsonPlusSerializer`][langgraph.checkpoint.serde.jsonplus.JsonPlusSerializer], uses ormsgpack and JSON under the hood, which is not suitable for all types of objects.
+
+If you want to fallback to pickle for objects not currently supported by our msgpack encoder (such as Pandas dataframes),
+you can use the `pickle_fallback` argument of the `JsonPlusSerializer`:
+
+```python
+from langgraph.checkpoint.memory import MemorySaver
+from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
+
+# ... Define the graph ...
+graph.compile(
+    checkpointer=MemorySaver(serde=JsonPlusSerializer(pickle_fallback=True))
+)
+```
+
+#### Encryption
+
+Checkpointers can optionally encrypt all persisted state. To enable this, pass an instance of [`EncryptedSerializer`][langgraph.checkpoint.serde.encrypted.EncryptedSerializer] to the `serde` argument of any `BaseCheckpointSaver` implementation. The easiest way to create an encrypted serializer is via [`from_pycryptodome_aes`][langgraph.checkpoint.serde.encrypted.EncryptedSerializer.from_pycryptodome_aes], which reads the AES key from the `LANGGRAPH_AES_KEY` environment variable (or accepts a `key` argument):
+
+```python
+import sqlite3
+
+from langgraph.checkpoint.serde.encrypted import EncryptedSerializer
+from langgraph.checkpoint.sqlite import SqliteSaver
+
+serde = EncryptedSerializer.from_pycryptodome_aes()  # reads LANGGRAPH_AES_KEY
+checkpointer = SqliteSaver(sqlite3.connect("checkpoint.db"), serde=serde)
+```
+
+```python
+from langgraph.checkpoint.serde.encrypted import EncryptedSerializer
+from langgraph.checkpoint.postgres import PostgresSaver
+
+serde = EncryptedSerializer.from_pycryptodome_aes()
+checkpointer = PostgresSaver.from_conn_string("postgresql://...", serde=serde)
+checkpointer.setup()
+```
+
+When running on LangGraph Platform, encryption is automatically enabled whenever `LANGGRAPH_AES_KEY` is present, so you only need to provide the environment variable. Other encryption schemes can be used by implementing [`CipherProtocol`][langgraph.checkpoint.serde.base.CipherProtocol] and supplying it to `EncryptedSerializer`.
+
 ## Capabilities

 ### Human-in-the-loop
@@ -25,7 +25,7 @@ Each step consists of three phases:

 Repeat until no **actors** are selected for execution, or a maximum number of steps is reached.

-## Actors 
+## Actors

 An **actor** is a `PregelNode`. It subscribes to channels, reads data from them, and writes data to them. It can be thought of as an **actor** in the Pregel algorithm. `PregelNodes` implement LangChain's Runnable interface.

@@ -39,7 +39,7 @@ Channels are used to communicate between actors (PregelNodes). Each channel has

 ## Examples

-While most users will interact with Pregel through the [StateGraph][langgraph.graph.StateGraph] API or 
+While most users will interact with Pregel through the [StateGraph][langgraph.graph.StateGraph] API or
 the [entrypoint][langgraph.func.entrypoint] decorator, it is possible to interact with Pregel directly.

 Below are a few different examples to give you a sense of the Pregel API.
@@ -49,12 +49,12 @@ Below are a few different examples to give you a sense of the Pregel API.
    ```python

    from langgraph.channels import EphemeralValue
-    from langgraph.pregel import Pregel, Channel 
+    from langgraph.pregel import Pregel, NodeBuilder

    node1 = (
-        Channel.subscribe_to("a")
-        | (lambda x: x + x)
-        | Channel.write_to("b")
+        NodeBuilder().subscribe_only("a")
+        .do(lambda x: x + x)
+        .write_to("b")
    )

    app = Pregel(
@@ -78,18 +78,18 @@ Below are a few different examples to give you a sense of the Pregel API.

    ```python
    from langgraph.channels import LastValue, EphemeralValue
-    from langgraph.pregel import Pregel, Channel 
+    from langgraph.pregel import Pregel, NodeBuilder

    node1 = (
-        Channel.subscribe_to("a")
-        | (lambda x: x + x)
-        | Channel.write_to("b")
+        NodeBuilder().subscribe_only("a")
+        .do(lambda x: x + x)
+        .write_to("b")
    )

    node2 = (
-        Channel.subscribe_to("b")
-        | (lambda x: x + x)
-        | Channel.write_to("c")
+        NodeBuilder().subscribe_only("b")
+        .do(lambda x: x + x)
+        .write_to("c")
    )


@@ -115,23 +115,18 @@ Below are a few different examples to give you a sense of the Pregel API.

    ```python
    from langgraph.channels import EphemeralValue, Topic
-    from langgraph.pregel import Pregel, Channel 
+    from langgraph.pregel import Pregel, NodeBuilder

    node1 = (
-        Channel.subscribe_to("a")
-        | (lambda x: x + x)
-        | {
-            "b": Channel.write_to("b"),
-            "c": Channel.write_to("c")
-        }
+        NodeBuilder().subscribe_only("a")
+        .do(lambda x: x + x)
+        .write_to("b", "c")
    )

    node2 = (
-        Channel.subscribe_to("b")
-        | (lambda x: x + x)
-        | {
-            "c": Channel.write_to("c"),
-        }
+        NodeBuilder().subscribe_to("b")
+        .do(lambda x: x["b"] + x["b"])
+        .write_to("c")
    )

    app = Pregel(
@@ -158,24 +153,19 @@ Below are a few different examples to give you a sense of the Pregel API.

    ```python
    from langgraph.channels import EphemeralValue, BinaryOperatorAggregate
-    from langgraph.pregel import Pregel, Channel
+    from langgraph.pregel import Pregel, NodeBuilder


    node1 = (
-        Channel.subscribe_to("a")
-        | (lambda x: x + x)
-        | {
-            "b": Channel.write_to("b"),
-            "c": Channel.write_to("c")
-        }
+        NodeBuilder().subscribe_only("a")
+        .do(lambda x: x + x)
+        .write_to("b", "c")
    )

    node2 = (
-        Channel.subscribe_to("b")
-        | (lambda x: x + x)
-        | {
-            "c": Channel.write_to("c"),
-        }
+        NodeBuilder().subscribe_only("b")
+        .do(lambda x: x + x)
+        .write_to("c")
    )

    def reducer(current, update):
@@ -197,8 +187,7 @@ Below are a few different examples to give you a sense of the Pregel API.

    app.invoke({"a": "foo"})
    ```
-    
-    
+
 === "Cycle"

    This example demonstrates how to introduce a cycle in the graph, by having
@@ -207,12 +196,12 @@ Below are a few different examples to give you a sense of the Pregel API.

    ```python
    from langgraph.channels import EphemeralValue
-    from langgraph.pregel import Pregel, Channel, ChannelWrite, ChannelWriteEntry
+    from langgraph.pregel import Pregel, NodeBuilder, ChannelWriteEntry

    example_node = (
-        Channel.subscribe_to("value")
-        | (lambda x: x + x if len(x) < 10 else None)
-        | ChannelWrite(writes=[ChannelWriteEntry(channel="value", skip_none=True)])
+        NodeBuilder().subscribe_only("value")
+        .do(lambda x: x + x if len(x) < 10 else None)
+        .write_to(ChannelWriteEntry("value", skip_none=True))
    )

    app = Pregel(
@@ -235,7 +224,6 @@ Below are a few different examples to give you a sense of the Pregel API.

 LangGraph provides two high-level APIs for creating a Pregel application: the [StateGraph (Graph API)](./low_level.md) and the [Functional API](functional_api.md).

-
 === "StateGraph (Graph API)"

    The [StateGraph (Graph API)][langgraph.graph.StateGraph] is a higher-level abstraction that simplifies the creation of Pregel applications. It allows you to define a graph of nodes and edges. When you compile the graph, the StateGraph API automatically creates the Pregel application for you.
@@ -266,7 +254,7 @@ LangGraph provides two high-level APIs for creating a Pregel application: the [S
    builder.add_node(score_essay)
    builder.add_edge(START, "write_essay")

-    # Compile the graph. 
+    # Compile the graph.
    # This will return a Pregel instance.
    graph = builder.compile()
    ```
@@ -279,7 +267,7 @@ LangGraph provides two high-level APIs for creating a Pregel application: the [S

    You will see something like this:

-    ```pycon 
+    ```pycon
    {'__start__': <langgraph.pregel.read.PregelNode at 0x7d05e3ba1810>,
     'write_essay': <langgraph.pregel.read.PregelNode at 0x7d05e3ba14d0>,
     'score_essay': <langgraph.pregel.read.PregelNode at 0x7d05e3ba1710>}
@@ -310,7 +298,7 @@ LangGraph provides two high-level APIs for creating a Pregel application: the [S
 === "Functional API"

    In the [Functional API](functional_api.md), you can use an [`entrypoint`][langgraph.func.entrypoint] to create
-    a Pregel application. The `entrypoint` decorator allows you to define a function that takes input and returns output. 
+    a Pregel application. The `entrypoint` decorator allows you to define a function that takes input and returns output.

    ```python
    from typing import TypedDict, Optional
@@ -339,8 +327,8 @@ LangGraph provides two high-level APIs for creating a Pregel application: the [S
    ```

    ```pycon
-    Nodes: 
+    Nodes:
    {'write_essay': <langgraph.pregel.read.PregelNode object at 0x7d05e2f9aad0>}
-    Channels: 
+    Channels:
    {'__start__': <langgraph.channels.ephemeral_value.EphemeralValue object at 0x7d05e2c906c0>, '__end__': <langgraph.channels.last_value.LastValue object at 0x7d05e2c90c40>, '__previous__': <langgraph.channels.last_value.LastValue object at 0x7d05e1007280>}
    ```
@@ -25,7 +25,7 @@ When a graceful shutdown request is received (SIGINT) an instance enters shutdow
 - gives any in-progress runs a limited number of seconds to finish (if not finished it will be put back in the queue)
 - stops the instance from picking up more runs from the queue

-If a hard shutdown occurs due to a server crash or an infrastructure failure, any runs that were in progress will be picked up by a internal sweeper task that looks for in-progress runs that have breached their heartbeat window. The sweeper runs every 2 minutes and will put the runs back in the queue for another instance to pick them up.
+If a hard shutdown occurs due to a server crash or an infrastructure failure, any runs that were in progress will be picked up by an internal sweeper task that looks for in-progress runs that have breached their heartbeat window. The sweeper runs every 2 minutes and will put the runs back in the queue for another instance to pick them up.

 ## Postgres resilience

@@ -94,7 +94,7 @@ def answer_node(state: InputState):
    return {"answer": "bye", "question": state["question"]}

 # Build the graph with explicit schemas
-builder = StateGraph(OverallState, input=InputState, output=OutputState)
+builder = StateGraph(OverallState, input_schema=InputState, output_schema=OutputState)
 builder.add_node(answer_node)
 builder.add_edge(START, "answer_node")
 builder.add_edge("answer_node", END)
@@ -59,8 +59,9 @@ The main question when adding subgraphs is how the parent graph and subgraph com
        response = model.invoke(state["subgraph_messages"])
        return {"subgraph_messages": response}

-    subgraph_builder = StateGraph(State)
-    subgraph_builder.add_node(call_model)
+    subgraph_builder = StateGraph(SubgraphMessagesState)
+    subgraph_builder.add_node("call_model_from_subgraph", call_model)
+    subgraph_builder.add_edge(START, "call_model_from_subgraph")
    ...
    # highlight-next-line
    subgraph = subgraph_builder.compile()
@@ -74,7 +74,7 @@ In your `langgraph.json`, add the path to your auth file:

 ## 3. Connect from the client

-Once you've set up authentication in your server, requests must include the the required authorization information based on your chosen scheme.
+Once you've set up authentication in your server, requests must include the required authorization information based on your chosen scheme.
 Assuming you are using JWT token authentication, you could access your deployments using any of the following methods:

 === "Python Client"
@@ -439,7 +439,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
   "id": "6ec0eb77-874e-443e-8c73-93125b515106",
   "metadata": {},
   "outputs": [
@@ -478,7 +478,7 @@
    "\n",
    "\n",
    "# Build the graph with input and output schemas specified\n",
-    "builder = StateGraph(OverallState, input=InputState, output=OutputState)\n",
+    "builder = StateGraph(OverallState, input_schema=InputState, output_schema=OutputState)\n",
    "builder.add_node(answer_node)  # Add the answer node\n",
    "builder.add_edge(START, \"answer_node\")  # Define the starting edge\n",
    "builder.add_edge(\"answer_node\", END)  # Define the ending edge\n",
@@ -1198,7 +1198,7 @@
    "\n",
    "There are many use cases where you may wish for your node to have a custom retry policy, for example if you are calling an API, querying a database, or calling an LLM, etc. LangGraph lets you add retry policies to nodes.\n",
    "\n",
-    "To configure a retry policy, pass the `retry` parameter to the [add_node](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.state.StateGraph.add_node). The `retry` parameter takes in a `RetryPolicy` named tuple object. Below we instantiate a `RetryPolicy` object with the default parameters and associate it with a node:\n",
+    "To configure a retry policy, pass the `retry_policy` parameter to the [add_node](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.state.StateGraph.add_node). The `retry_policy` parameter takes in a `RetryPolicy` named tuple object. Below we instantiate a `RetryPolicy` object with the default parameters and associate it with a node:\n",
    "\n",
    "```python\n",
    "from langgraph.pregel import RetryPolicy\n",
@@ -1206,7 +1206,7 @@
    "builder.add_node(\n",
    "    \"node_name\",\n",
    "    node_function,\n",
-    "    retry=RetryPolicy(),\n",
+    "    retry_policy=RetryPolicy(),\n",
    ")\n",
    "```"
   ]
@@ -1241,7 +1241,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
   "id": "ad92598c-b688-42fa-aae0-9de36273d584",
   "metadata": {},
   "outputs": [],
@@ -1276,9 +1276,9 @@
    "builder.add_node(\n",
    "    \"query_database\",\n",
    "    query_database,\n",
-    "    retry=RetryPolicy(retry_on=sqlite3.OperationalError),\n",
+    "    retry_policy=RetryPolicy(retry_on=sqlite3.OperationalError),\n",
    ")\n",
-    "builder.add_node(\"model\", call_model, retry=RetryPolicy(max_attempts=5))\n",
+    "builder.add_node(\"model\", call_model, retry_policy=RetryPolicy(max_attempts=5))\n",
    "builder.add_edge(START, \"model\")\n",
    "builder.add_edge(\"model\", \"query_database\")\n",
    "builder.add_edge(\"query_database\", END)\n",
@@ -3416,7 +3416,7 @@
 ],
 "metadata": {
  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
@@ -3430,7 +3430,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.9.6"
  }
 },
 "nbformat": 4,
@@ -34,7 +34,7 @@ def read_root():

 ## Configure `langgraph.json`

-Add the following to your `langgraph.json` configuration file. Make sure the path points to the `app.py` file you created above.
+Add the following to your `langgraph.json` configuration file. Make sure the path points to the FastAPI application instance `app` in the `webapp.py` file you created above.

 ```json
 {
@@ -71,4 +71,4 @@ You can deploy this app as-is to LangGraph Platform or to your self-hosted platf

 ## Next steps

-Now that you've added a custom route to your deployment, you can use this same technique to further customize how your server behaves, such as defining custom [custom middleware](./custom_middleware.md) and [custom lifespan events](./custom_lifespan.md). 
+Now that you've added a custom route to your deployment, you can use this same technique to further customize how your server behaves, such as defining custom [custom middleware](./custom_middleware.md) and [custom lifespan events](./custom_lifespan.md). 
@@ -12,9 +12,9 @@
    "\n",
    "\n",
    "1. **Run the graph** with initial inputs using `invoke` or `stream` APIs.\n",
-    "2. **Identify a checkpoint in an existing thread**: Use the [`get_state_history()`][langgraph.graph.graph.CompiledGraph.get_state_history] method to retrieve the execution history for a specific `thread_id` and locate the desired `checkpoint_id`.  \n",
+    "2. **Identify a checkpoint in an existing thread**: Use the [`get_state_history()`][langgraph.graph.state.CompiledStateGraph.get_state_history] method to retrieve the execution history for a specific `thread_id` and locate the desired `checkpoint_id`.  \n",
    "   Alternatively, set a [breakpoint](../../../concepts/breakpoints/) before the node(s) where you want execution to pause. You can then find the most recent checkpoint recorded up to that breakpoint.\n",
-    "3. **(Optional) modify the graph state**: Use the [`update_state`][langgraph.graph.graph.CompiledGraph.update_state] method to modify the graph’s state at the checkpoint and resume execution from alternative state.\n",
+    "3. **(Optional) modify the graph state**: Use the [`update_state`][langgraph.graph.state.CompiledStateGraph.update_state] method to modify the graph’s state at the checkpoint and resume execution from alternative state.\n",
    "4. **Resume execution from the checkpoint**: Use the `invoke` or `stream` APIs with an input of `None` and a configuration containing the appropriate `thread_id` and `checkpoint_id`.\n",
    "\n",
    "## Example\n",
@@ -405,7 +405,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": null,
   "id": "1954a5f1-91e4-4b32-9be9-c8bc1cc43cb5",
   "metadata": {},
   "outputs": [],
@@ -465,7 +465,9 @@
    "\n",
    "graph_builder = StateGraph(State)\n",
    "graph_builder.add_node(\"agent\", agent)\n",
-    "graph_builder.add_node(\"select_tools\", select_tools, retry=RetryPolicy(max_attempts=3))\n",
+    "graph_builder.add_node(\n",
+    "    \"select_tools\", select_tools, retry_policy=RetryPolicy(max_attempts=3)\n",
+    ")\n",
    "\n",
    "tool_node = ToolNode(tools=tools)\n",
    "graph_builder.add_node(\"tools\", tool_node)\n",
@@ -207,7 +207,7 @@
   "id": "213d661e-6ba4-42b9-bc7f-6c8c423e3419",
   "metadata": {},
   "source": [
-    "Let's now create our agents using the the prebuilt [`create_react_agent`][langgraph.prebuilt.chat_agent_executor.create_react_agent] and our multi-agent workflow. Note that will be calling [`interrupt`][langgraph.types.interrupt] every time after we get the final response from each of the agents."
+    "Let's now create our agents using the prebuilt [`create_react_agent`][langgraph.prebuilt.chat_agent_executor.create_react_agent] and our multi-agent workflow. Note that will be calling [`interrupt`][langgraph.types.interrupt] every time after we get the final response from each of the agents."
   ]
  },
  {
@@ -739,7 +739,6 @@
    "                'id': '1f029ca3-1f5b-6704-8004-820c16b69a5a',\n",
    "                'channel_versions': {'__start__': '00000000000000000000000000000005.0.5290678567601859', 'messages': '00000000000000000000000000000006.0.3205149138784782', 'branch:to:call_model': '00000000000000000000000000000006.0.14611156755133758'}, 'versions_seen': {'__input__': {}, '__start__': {'__start__': '00000000000000000000000000000004.0.5736472536395331'}, 'call_model': {'branch:to:call_model': '00000000000000000000000000000005.0.1410174088651449'}},\n",
    "                'channel_values': {'messages': [HumanMessage(content=\"hi! I'm bob\"), AIMessage(content='Hi Bob! How are you doing today?), HumanMessage(content=\"what's my name?\"), AIMessage(content='Your name is Bob.')]},\n",
-    "                'pending_sends': []\n",
    "            },\n",
    "            metadata={\n",
    "                'source': 'loop',\n",
@@ -856,7 +855,7 @@
    "                    'id': '1f029ca3-1f5b-6704-8004-820c16b69a5a', \n",
    "                    'channel_versions': {'__start__': '00000000000000000000000000000005.0.5290678567601859', 'messages': '00000000000000000000000000000006.0.3205149138784782', 'branch:to:call_model': '00000000000000000000000000000006.0.14611156755133758'}, \n",
    "                    'versions_seen': {'__input__': {}, '__start__': {'__start__': '00000000000000000000000000000004.0.5736472536395331'}, 'call_model': {'branch:to:call_model': '00000000000000000000000000000005.0.1410174088651449'}},\n",
-    "                    'channel_values': {'messages': [HumanMessage(content=\"hi! I'm bob\"), AIMessage(content='Hi Bob! How are you doing today? Is there anything I can help you with?'), HumanMessage(content=\"what's my name?\"), AIMessage(content='Your name is Bob.')]}, 'pending_sends': []\n",
+    "                    'channel_values': {'messages': [HumanMessage(content=\"hi! I'm bob\"), AIMessage(content='Hi Bob! How are you doing today? Is there anything I can help you with?'), HumanMessage(content=\"what's my name?\"), AIMessage(content='Your name is Bob.')]},\n",
    "                },\n",
    "                metadata={'source': 'loop', 'writes': {'call_model': {'messages': AIMessage(content='Your name is Bob.')}}, 'step': 4, 'parents': {}, 'thread_id': '1'}, \n",
    "                parent_config={'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1f029ca3-1790-6b0a-8003-baf965b6a38f'}}, \n",
@@ -870,8 +869,7 @@
    "                    'id': '1f029ca3-1790-6b0a-8003-baf965b6a38f', \n",
    "                    'channel_versions': {'__start__': '00000000000000000000000000000005.0.5290678567601859', 'messages': '00000000000000000000000000000005.0.7935064215293443', 'branch:to:call_model': '00000000000000000000000000000005.0.1410174088651449'}, \n",
    "                    'versions_seen': {'__input__': {}, '__start__': {'__start__': '00000000000000000000000000000004.0.5736472536395331'}, 'call_model': {'branch:to:call_model': '00000000000000000000000000000002.0.9300422176788571'}}, \n",
-    "                    'channel_values': {'messages': [HumanMessage(content=\"hi! I'm bob\"), AIMessage(content='Hi Bob! How are you doing today? Is there anything I can help you with?'), HumanMessage(content=\"what's my name?\")], 'branch:to:call_model': None}, \n",
-    "                    'pending_sends': []\n",
+    "                    'channel_values': {'messages': [HumanMessage(content=\"hi! I'm bob\"), AIMessage(content='Hi Bob! How are you doing today? Is there anything I can help you with?'), HumanMessage(content=\"what's my name?\")], 'branch:to:call_model': None}\n",
    "                }, \n",
    "                metadata={'source': 'loop', 'writes': None, 'step': 3, 'parents': {}, 'thread_id': '1'}, \n",
    "                parent_config={...}, \n",
@@ -885,8 +883,7 @@
    "                    'id': '1f029ca3-1790-616e-8002-9e021694a0cd', \n",
    "                    'channel_versions': {'__start__': '00000000000000000000000000000004.0.5736472536395331', 'messages': '00000000000000000000000000000003.0.7056767754077798', 'branch:to:call_model': '00000000000000000000000000000003.0.22059023329132854'}, \n",
    "                    'versions_seen': {'__input__': {}, '__start__': {'__start__': '00000000000000000000000000000001.0.7040775356287469'}, 'call_model': {'branch:to:call_model': '00000000000000000000000000000002.0.9300422176788571'}}, \n",
-    "                    'channel_values': {'__start__': {'messages': [{'role': 'user', 'content': \"what's my name?\"}]}, 'messages': [HumanMessage(content=\"hi! I'm bob\"), AIMessage(content='Hi Bob! How are you doing today? Is there anything I can help you with?')]}, \n",
-    "                    'pending_sends': []\n",
+    "                    'channel_values': {'__start__': {'messages': [{'role': 'user', 'content': \"what's my name?\"}]}, 'messages': [HumanMessage(content=\"hi! I'm bob\"), AIMessage(content='Hi Bob! How are you doing today? Is there anything I can help you with?')]}\n",
    "                }, \n",
    "                metadata={'source': 'input', 'writes': {'__start__': {'messages': [{'role': 'user', 'content': \"what's my name?\"}]}}, 'step': 2, 'parents': {}, 'thread_id': '1'}, \n",
    "                parent_config={...}, \n",
@@ -900,8 +897,7 @@
    "                    'id': '1f029ca3-178d-6f54-8001-d7b180db0c89', \n",
    "                    'channel_versions': {'__start__': '00000000000000000000000000000002.0.18673090920108737', 'messages': '00000000000000000000000000000003.0.7056767754077798', 'branch:to:call_model': '00000000000000000000000000000003.0.22059023329132854'}, \n",
    "                    'versions_seen': {'__input__': {}, '__start__': {'__start__': '00000000000000000000000000000001.0.7040775356287469'}, 'call_model': {'branch:to:call_model': '00000000000000000000000000000002.0.9300422176788571'}}, \n",
-    "                    'channel_values': {'messages': [HumanMessage(content=\"hi! I'm bob\"), AIMessage(content='Hi Bob! How are you doing today? Is there anything I can help you with?')]}, \n",
-    "                    'pending_sends': []\n",
+    "                    'channel_values': {'messages': [HumanMessage(content=\"hi! I'm bob\"), AIMessage(content='Hi Bob! How are you doing today? Is there anything I can help you with?')]}\n",
    "                }, \n",
    "                metadata={'source': 'loop', 'writes': {'call_model': {'messages': AIMessage(content='Hi Bob! How are you doing today? Is there anything I can help you with?')}}, 'step': 1, 'parents': {}, 'thread_id': '1'}, \n",
    "                parent_config={...}, \n",
@@ -915,8 +911,7 @@
    "                    'id': '1f029ca3-0874-6612-8000-339f2abc83b1', \n",
    "                    'channel_versions': {'__start__': '00000000000000000000000000000002.0.18673090920108737', 'messages': '00000000000000000000000000000002.0.30296526818059655', 'branch:to:call_model': '00000000000000000000000000000002.0.9300422176788571'}, \n",
    "                    'versions_seen': {'__input__': {}, '__start__': {'__start__': '00000000000000000000000000000001.0.7040775356287469'}}, \n",
-    "                    'channel_values': {'messages': [HumanMessage(content=\"hi! I'm bob\")], 'branch:to:call_model': None}, \n",
-    "                    'pending_sends': []\n",
+    "                    'channel_values': {'messages': [HumanMessage(content=\"hi! I'm bob\")], 'branch:to:call_model': None}\n",
    "                }, \n",
    "                metadata={'source': 'loop', 'writes': None, 'step': 0, 'parents': {}, 'thread_id': '1'}, \n",
    "                parent_config={...}, \n",
@@ -930,8 +925,7 @@
    "                    'id': '1f029ca3-0870-6ce2-bfff-1f3f14c3e565', \n",
    "                    'channel_versions': {'__start__': '00000000000000000000000000000001.0.7040775356287469'}, \n",
    "                    'versions_seen': {'__input__': {}}, \n",
-    "                    'channel_values': {'__start__': {'messages': [{'role': 'user', 'content': \"hi! I'm bob\"}]}}, \n",
-    "                    'pending_sends': []\n",
+    "                    'channel_values': {'__start__': {'messages': [{'role': 'user', 'content': \"hi! I'm bob\"}]}}\n",
    "                }, \n",
    "                metadata={'source': 'input', 'writes': {'__start__': {'messages': [{'role': 'user', 'content': \"hi! I'm bob\"}]}}, 'step': -1, 'parents': {}, 'thread_id': '1'}, \n",
    "                parent_config=None, \n",
@@ -1113,10 +1107,10 @@
   "source": [
    "### Use in production\n",
    "\n",
-    "In production, you would want to use a checkpointer backed by a database:\n",
+    "In production, you would want to use a store backed by a database:\n",
    "\n",
    "```python\n",
-    "from langgraph.checkpoint.postgres import PostgresSaver\n",
+    "from langgraph.store.postgres import PostgresStore\n",
    "\n",
    "DB_URI = \"postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable\"\n",
    "# highlight-next-line\n",
@@ -321,7 +321,7 @@ attempts = 0
 # The default RetryPolicy is optimized for retrying specific network errors.
 retry_policy = RetryPolicy(retry_on=ValueError)

-@task(retry=retry_policy) 
+@task(retry_policy=retry_policy) 
 def get_info():
    global attempts
    attempts += 1
@@ -12,12 +12,18 @@
    options:
      members:
        - SerializerProtocol
+        - CipherProtocol

 ::: langgraph.checkpoint.serde.jsonplus
    options:
      members:
        - JsonPlusSerializer

+::: langgraph.checkpoint.serde.encrypted
+    options:
+      members:
+        - EncryptedSerializer
+
 ::: langgraph.checkpoint.memory

 ::: langgraph.checkpoint.sqlite
@@ -32,4 +38,4 @@
 ::: langgraph.checkpoint.postgres.aio
    options:
      members:
-        - AsyncPostgresSaver
+        - AsyncPostgresSaver
@@ -36,41 +36,6 @@
        - aget_subgraphs
        - with_config

-::: langgraph.graph.graph.Graph
-    options:
-      show_if_no_docstring: true
-      show_root_heading: true
-      show_root_full_path: false
-      members:
-        - add_node
-        - add_edge
-        - add_conditional_edges
-        - compile
-
-::: langgraph.graph.graph.CompiledGraph
-    options:
-      show_if_no_docstring: true
-      show_root_heading: true
-      show_root_full_path: false
-      members:
-        - stream
-        - astream
-        - invoke
-        - ainvoke
-        - get_state
-        - aget_state
-        - get_state_history
-        - aget_state_history
-        - update_state
-        - aupdate_state
-        - bulk_update_state
-        - abulk_update_state
-        - get_graph
-        - aget_graph
-        - get_subgraphs
-        - aget_subgraphs
-        - with_config
-
 ::: langgraph.graph.message
    options:
      members:
@@ -22,7 +22,7 @@ Welcome to the LangGraph reference docs! These pages detail the core interfaces

 ## LangGraph

-The core APIs for the LangGraph opens source library.
+The core APIs for the LangGraph open source library.

 - [Graphs](graphs.md): Main graph abstraction and usage.
 - [Functional API](func.md): Functional programming interface for graphs.
@@ -1,5 +1,21 @@
 # Pregel

+::: langgraph.pregel.NodeBuilder
+    options:
+      show_if_no_docstring: true
+      show_root_heading: true
+      show_root_full_path: false
+      members:
+        - subscribe_only
+        - subscribe_to
+        - read_from
+        - do
+        - write_to
+        - meta
+        - retry
+        - cache
+        - build
+
 ::: langgraph.pregel.Pregel
    options:
      show_if_no_docstring: true
@@ -580,9 +580,7 @@
    "    ]\n",
    ")\n",
    "\n",
-    "evaluator = prompt | ChatOpenAI(model=\"gpt-4-turbo-preview\").with_structured_output(\n",
-    "    RedTeamingResult, method=\"function_calling\"\n",
-    ")\n",
+    "evaluator = prompt | ChatOpenAI(model=\"gpt-4o\").with_structured_output(RedTeamingResult)\n",
    "\n",
    "\n",
    "def did_resist(run, example):\n",
@@ -833,7 +833,7 @@
    "@tool\n",
    "def book_excursion(recommendation_id: int) -> str:\n",
    "    \"\"\"\n",
-    "    Book a excursion by its recommendation ID.\n",
+    "    Book an excursion by its recommendation ID.\n",
    "\n",
    "    Args:\n",
    "        recommendation_id (int): The ID of the trip recommendation to book.\n",
@@ -32,7 +32,7 @@ from typing import Annotated

 from typing_extensions import TypedDict

-from langgraph.graph import StateGraph, START
+from langgraph.graph import StateGraph, START, END
 from langgraph.graph.message import add_messages


@@ -100,7 +100,16 @@ Add an `entry` point to tell the graph **where to start its work** each time it
 graph_builder.add_edge(START, "chatbot")
 ```

-## 5. Compile the graph
+## 5. Add an `exit` point
+
+Add an `exit` point to indicate **where the graph should finish execution**. This is helpful for more complex flows, but even in a simple graph like this, adding an end node improves clarity.
+
+```python
+graph_builder.add_edge("chatbot", END)
+```
+This tells the graph to terminate after running the chatbot node.
+
+## 6. Compile the graph

 Before running the graph, we'll need to compile it. We can do so by calling `compile()`
 on the graph builder. This creates a `CompiledGraph` we can invoke on our state.
@@ -109,7 +118,7 @@ on the graph builder. This creates a `CompiledGraph` we can invoke on our state.
 graph = graph_builder.compile()
 ```

-## 6. Visualize the graph (optional)
+## 7. Visualize the graph (optional)

 You can visualize the graph using the `get_graph` method and one of the "draw" methods, like `draw_ascii` or `draw_png`. The `draw` methods each require additional dependencies.

@@ -126,7 +135,7 @@ except Exception:
 ![basic chatbot diagram](basic-chatbot.png)


-## 7. Run the chatbot
+## 8. Run the chatbot

 Now run the chatbot! 

@@ -171,7 +180,7 @@ from typing import Annotated
 from langchain.chat_models import init_chat_model
 from typing_extensions import TypedDict

-from langgraph.graph import StateGraph, START
+from langgraph.graph import StateGraph, START, END
 from langgraph.graph.message import add_messages


@@ -194,6 +203,7 @@ def chatbot(state: State):
 # the node is used.
 graph_builder.add_node("chatbot", chatbot)
 graph_builder.add_edge(START, "chatbot")
+graph_builder.add_edge("chatbot", END)
 graph = graph_builder.compile()
 ```

@@ -1,6 +1,6 @@
 # Add tools

-To handle queries you chatbot can't answer "from memory", integrate a web search tool. The chatbot can use this tool to find relevant information and provide better responses.
+To handle queries that your chatbot can't answer "from memory", integrate a web search tool. The chatbot can use this tool to find relevant information and provide better responses.

 !!! note

@@ -164,7 +164,7 @@ llm = init_chat_model("anthropic:claude-3-5-sonnet-latest")
 ```
 -->

-```python
+```python hl_lines="36 37"
 from typing import Annotated

 from langchain.chat_models import init_chat_model
@@ -206,4 +206,4 @@ graph = graph_builder.compile(checkpointer=memory)

 ## Next steps

-In the next tutorial, you will [add human-in-the-loop to the chatbot](./4-human-in-the-loop.md) to handle situations where it may need guidance or verification before proceeding.
+In the next tutorial, you will [add human-in-the-loop to the chatbot](./4-human-in-the-loop.md) to handle situations where it may need guidance or verification before proceeding.
@@ -471,7 +471,7 @@
    "\n",
    "_get_pass(\"TAVILY_API_KEY\")\n",
    "\n",
-    "calculate = get_math_tool(ChatOpenAI(model=\"gpt-4-turbo-preview\"))\n",
+    "calculate = get_math_tool(ChatOpenAI(model=\"gpt-4o\"))\n",
    "search = TavilySearchResults(\n",
    "    max_results=1,\n",
    "    description='tavily_search_results_json(query=\"the search query\") - a search engine.',\n",
@@ -540,11 +540,11 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "================================\u001b[1m System Message \u001b[0m================================\n",
+      "================================\u001B[1m System Message \u001B[0m================================\n",
      "\n",
-      "Given a user query, create a plan to solve it with the utmost parallelizability. Each plan should comprise an action from the following \u001b[33;1m\u001b[1;3m{num_tools}\u001b[0m types:\n",
-      "\u001b[33;1m\u001b[1;3m{tool_descriptions}\u001b[0m\n",
-      "\u001b[33;1m\u001b[1;3m{num_tools}\u001b[0m. join(): Collects and combines results from prior actions.\n",
+      "Given a user query, create a plan to solve it with the utmost parallelizability. Each plan should comprise an action from the following \u001B[33;1m\u001B[1;3m{num_tools}\u001B[0m types:\n",
+      "\u001B[33;1m\u001B[1;3m{tool_descriptions}\u001B[0m\n",
+      "\u001B[33;1m\u001B[1;3m{num_tools}\u001B[0m. join(): Collects and combines results from prior actions.\n",
      "\n",
      " - An LLM agent is called upon invoking join() to either finalize the user query or wait until the plans are executed.\n",
      " - join should always be the last action in the plan, and will be called in two scenarios:\n",
@@ -561,11 +561,11 @@
      " - Only use the provided action types. If a query cannot be addressed using these, invoke the join action for the next steps.\n",
      " - Never introduce new actions other than the ones provided.\n",
      "\n",
-      "=============================\u001b[1m Messages Placeholder \u001b[0m=============================\n",
+      "=============================\u001B[1m Messages Placeholder \u001B[0m=============================\n",
      "\n",
-      "\u001b[33;1m\u001b[1;3m{messages}\u001b[0m\n",
+      "\u001B[33;1m\u001B[1;3m{messages}\u001B[0m\n",
      "\n",
-      "================================\u001b[1m System Message \u001b[0m================================\n",
+      "================================\u001B[1m System Message \u001B[0m================================\n",
      "\n",
      "Remember, ONLY respond with the task list in the correct format! E.g.:\n",
      "idx. tool(arg_name=args)\n",
@@ -1030,7 +1030,7 @@
    "joiner_prompt = hub.pull(\"wfh/llm-compiler-joiner\").partial(\n",
    "    examples=\"\"\n",
    ")  # You can optionally add examples\n",
-    "llm = ChatOpenAI(model=\"gpt-4-turbo-preview\")\n",
+    "llm = ChatOpenAI(model=\"gpt-4o\")\n",
    "\n",
    "runnable = joiner_prompt | llm.with_structured_output(\n",
    "    JoinOutputs, method=\"function_calling\"\n",
@@ -135,7 +135,6 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "from langchain import hub\n",
    "from langchain_openai import ChatOpenAI\n",
    "\n",
    "from langgraph.prebuilt import create_react_agent\n",
@@ -90,7 +90,11 @@
   "id": "9ac1c2cd-81fb-40eb-8ba1-e9197800cba6",
   "metadata": {},
   "source": [
-    "## Create Index"
+    "## Create Index\n",
+    "\n",
+    "Set up a vector database using OpenAI Embeddings and the Chroma vector database.  \n",
+    "Input URLs of blog posts related to agents, prompt engineering, and large language models (LLMs).  \n",
+    "Generate vector indices for use in Retrieval-Augmented Generation (RAG)."
   ]
  },
  {
@@ -159,6 +163,21 @@
    "</div>"
   ]
  },
+  {
+   "cell_type": "markdown",
+   "id": "6cdd5ac0-fa18-4ee9-8051-062a0c56268f",
+   "metadata": {},
+   "source": [
+    "### Router for Query Analysis\n",
+    "\n",
+    "Let’s start with Routing. First, assign the query analysis to the LLM.\n",
+    "\n",
+    "Create a RouteQuery data model and specify it in a structured format for the LLM. The decision for routing should be embedded in the prompt. You need to clearly define which parts of the document should be directed to RAG based on the topic.\n",
+    "\n",
+    "While you could automate this process by having the LLM summarize the RAG documents again, it’s more cost-effective to manually manage this when dealing with large documents, as automation could become expensive.\n",
+    "\n"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 4,
@@ -219,6 +238,18 @@
    "print(question_router.invoke({\"question\": \"What are the types of agent memory?\"}))"
   ]
  },
+  {
+   "cell_type": "markdown",
+   "id": "cb248c94-0b0c-4d86-8565-32aa8d7424e4",
+   "metadata": {},
+   "source": [
+    "### Retrieval Grader\n",
+    "\n",
+    "After performing retrieval, evaluate the results. Although you initially decided to use RAG based on the query, the retrieved documents might not be satisfactory. Assess whether the retrieved documents are sufficiently relevant to the query.\n",
+    "\n",
+    "For this, rely on the LLM to evaluate the relevance, providing a binary ‘yes’ or ‘no’ decision."
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 5,
@@ -309,6 +340,17 @@
    "print(generation)"
   ]
  },
+  {
+   "cell_type": "markdown",
+   "id": "cb0ab54a-4a4f-45fa-b1c5-cea1bf4c59d5",
+   "metadata": {},
+   "source": [
+    "### Hallucination Grader\n",
+    "\n",
+    "Verify if the LLM produced any hallucinations by comparing its output to the retrieved facts.  \n",
+    "Provide the LLM’s evaluation in a binary ‘yes’ or ‘no’ format.\n"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 7,
@@ -357,6 +399,16 @@
    "hallucination_grader.invoke({\"documents\": docs, \"generation\": generation})"
   ]
  },
+  {
+   "cell_type": "markdown",
+   "id": "4f58502a-c25f-4d80-a402-5583b0cd3e41",
+   "metadata": {},
+   "source": [
+    "### Answer Grader\n",
+    "\n",
+    "Evaluate the answer finally."
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 8,
@@ -405,6 +457,18 @@
    "answer_grader.invoke({\"question\": question, \"generation\": generation})"
   ]
  },
+  {
+   "cell_type": "markdown",
+   "id": "af77946c-2646-4039-86b0-e2fde1ab7459",
+   "metadata": {},
+   "source": [
+    "### Question Rewriting\n",
+    "\n",
+    "The original question from user was directly used in RAG.  \n",
+    "However, the user’s question might not be in a form suitable for RAG.  \n",
+    "To improve retrieval, rephrase the question to ensure it aligns better with vector similarity search."
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 9,
@@ -450,7 +514,9 @@
   "id": "d07c0b31-b919-4498-869f-9673125c2473",
   "metadata": {},
   "source": [
-    "## Web Search Tool"
+    "## Web Search Tool\n",
+    "\n",
+    "Use Tavily Search tool to get information from the web."
   ]
  },
  {
@@ -516,11 +582,13 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
   "id": "b76b5ec3-0720-443d-85b1-c0e79659ca0a",
   "metadata": {},
   "outputs": [],
   "source": [
+    "from pprint import pprint\n",
+    "\n",
    "from langchain.schema import Document\n",
    "\n",
    "\n",
@@ -796,7 +864,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
   "id": "29acc541-d726-4b75-84d1-a215845fe88a",
   "metadata": {},
   "outputs": [
@@ -823,8 +891,6 @@
    }
   ],
   "source": [
-    "from pprint import pprint\n",
-    "\n",
    "# Run\n",
    "inputs = {\n",
    "    \"question\": \"What player at the Bears expected to draft first in the 2024 NFL draft?\"\n",
@@ -185,7 +185,7 @@
    "\n",
    "\n",
    "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
    "structured_llm_grader = llm.with_structured_output(GradeDocuments)\n",
    "\n",
    "# Prompt\n",
@@ -389,7 +389,7 @@
     "text": [
      "{'generate': {'messages': [AIMessage(content='Title: The Little Prince: A Topical Allegory for Modern Life\\n\\nIntroduction:\\nAntoine de Saint-Exupéry\\'s \"The Little Prince\" is a classic novella that has captured the hearts of millions since its publication in 1943. While it might be easy to dismiss this work as a children\\'s story, its profound themes and timeless message make it a relevant and topical piece in modern life. This essay will explore the allegorical nature of \"The Little Prince\" and discuss how its message can be applied to the complexities of the modern world.\\n\\nBody Paragraph 1 - The Allegory of the Little Prince:\\n\"The Little Prince\" is an allegorical tale that explores various aspects of the human condition through its whimsical characters and situations. The Little Prince himself represents innocence, curiosity, and the importance of human connection. As the story unfolds, readers encounter different characters that symbolize various aspects of adult life, such as vanity, materialism, and authority. These representations allow the story to transcend age and culture, making it relatable to a wide range of readers, even in the modern context.\\n\\nBody Paragraph 2 - The Relevance of the Little Prince\\'s Message:\\nThe Little Prince\\'s message is centered around the importance of looking beyond superficial appearances and forming meaningful connections with others. In a world increasingly dominated by technology and social media, where surface-level interactions are commonplace, this message is more relevant than ever. The Little Prince encourages readers to cherish and nurture genuine relationships, reminding us that true happiness and fulfillment come from understanding and empathizing with others.\\n\\nBody Paragraph 3 - The Critique of Modern Society:\\n\"The Little Prince\" also offers a critique of modern society, highlighting the dangers of materialism, consumerism, and the pursuit of power. These themes resonate strongly in today\\'s world, where wealth inequality and environmental degradation are pressing issues. The story serves as a reminder that the pursuit of material possessions and status often comes at the expense of our own happiness and the well-being of our planet.\\n\\nConclusion:\\nIn conclusion, \"The Little Prince\" remains a topical and relevant work in modern life due to its allegorical nature, timeless message, and critique of modern society. Its exploration of human connections, materialism, and the pursuit of power offers valuable insights for readers of all ages. By embracing the story\\'s wisdom, we can better navigate the complexities of the modern world and foster a more compassionate, sustainable, and interconnected society.', response_metadata={'token_usage': {'prompt_tokens': 72, 'total_tokens': 632, 'completion_tokens': 560}, 'model_name': 'accounts/fireworks/models/mixtral-8x7b-instruct', 'system_fingerprint': '', 'finish_reason': 'stop', 'logprobs': None}, id='run-b39a25ab-24f6-42d0-96c2-0f74c3ecc8f7-0', usage_metadata={'input_tokens': 72, 'output_tokens': 560, 'total_tokens': 632})]}}\n",
      "---\n",
-      "{'reflect': {'messages': [HumanMessage(content='Essay Critique and Recommendations:\\n\\nTitle: The Little Prince: A Topical Allegory for Modern Life\\n\\nIntroduction:\\nThe introduction effectively sets the stage for the essay by providing background information on \"The Little Prince\" and its relevance in modern life. However, consider adding a hook to engage the reader\\'s attention and create a stronger first impression.\\n\\nBody Paragraph 1 - The Allegory of the Little Prince:\\nThis paragraph provides a clear explanation of the allegorical nature of \"The Little Prince.\" To enhance this section, consider offering specific examples from the text to illustrate how the characters and situations symbolize various aspects of adult life. This will strengthen your analysis and make it more engaging for the reader.\\n\\nBody Paragraph 2 - The Relevance of the Little Prince\\'s Message:\\nThe relevance of the Little Prince\\'s message is well-articulated in this paragraph. To further strengthen your argument, consider discussing the consequences of ignoring this message in the context of modern society. This will help emphasize the importance of the Little Prince\\'s wisdom and its relevance to contemporary issues.\\n\\nBody Paragraph 3 - The Critique of Modern Society:\\nThis paragraph effectively highlights the story\\'s critique of modern society. To deepen your analysis, explore how the themes of materialism, consumerism, and the pursuit of power interconnect and contribute to the challenges faced by modern society. Additionally, consider discussing potential solutions or actions inspired by the Little Prince\\'s message that could help address these issues.\\n\\nConclusion:\\nThe conclusion effectively summarizes the main points of the essay and emphasizes the relevance of \"The Little Prince\" in modern life. To further enhance this section, consider incorporating a thought-provoking question or statement that encourages readers to reflect on the story\\'s message and its implications for their own lives.\\n\\nRecommendations:\\n1. Expand the essay to approximately 1,200-1,500 words to allow for a more in-depth analysis.\\n2. Incorporate specific examples and quotes from \"The Little Prince\" to support your arguments and engage the reader.\\n3. Ensure that each body paragraph contains a clear thesis statement, supporting evidence, and analysis.\\n4. Consider discussing counterarguments or potential criticisms of the Little Prince\\'s message to add depth and complexity to your essay.\\n5. Revise and edit the essay for clarity, coherence, and grammar.')]}}\n",
+      "{'reflect': {'messages': [HumanMessage(content='Essay Critique and Recommendations:\\n\\nTitle: The Little Prince: A Topical Allegory for Modern Life\\n\\nIntroduction:\\nThe introduction effectively sets the stage for the essay by providing background information on \"The Little Prince\" and its relevance in modern life. However, consider adding a hook to engage the reader\\'s attention and create a stronger first impression.\\n\\nBody Paragraph 1 - The Allegory of the Little Prince:\\nThis paragraph provides a clear explanation of the allegorical nature of \"The Little Prince.\" To enhance this section, consider offering specific examples from the text to illustrate how the characters and situations symbolize various aspects of adult life. This will strengthen your analysis and make it more engaging for the reader.\\n\\nBody Paragraph 2 - The Relevance of the Little Prince\\'s Message:\\nThe relevance of the Little Prince\\'s message is well-articulated in this paragraph. To further strengthen your argument, consider discussing the consequences of ignoring this message in the context of modern society. This will help emphasize the importance of the Little Prince\\'s wisdom and its relevance to contemporary issues.\\n\\nBody Paragraph 3 - The Critique of Modern Society:\\nThis paragraph effectively highlights the story\\'s critique of modern society. To deepen your analysis, explore how themes of materialism, consumerism, and the pursuit of power interconnect and contribute to the challenges faced by modern society. Additionally, consider discussing potential solutions or actions inspired by the Little Prince\\'s message that could help address these issues.\\n\\nConclusion:\\nThe conclusion effectively summarizes the main points of the essay and emphasizes the relevance of \"The Little Prince\" in modern life. To further enhance this section, consider incorporating a thought-provoking question or statement that encourages readers to reflect on the story\\'s message and its implications for their own lives.\\n\\nRecommendations:\\n1. Expand the essay to approximately 1,200-1,500 words to allow for a more in-depth analysis.\\n2. Incorporate specific examples and quotes from \"The Little Prince\" to support your arguments and engage the reader.\\n3. Ensure that each body paragraph contains a clear thesis statement, supporting evidence, and analysis.\\n4. Consider discussing counterarguments or potential criticisms of the Little Prince\\'s message to add depth and complexity to your essay.\\n5. Revise and edit the essay for clarity, coherence, and grammar.')]}}\n",
      "---\n",
      "{'generate': {'messages': [AIMessage(content='Title: The Little Prince: A Topical Allegory for Modern Life\\n\\nIntroduction:\\nIn Antoine de Saint-Exupéry\\'s classic novella \"The Little Prince,\" a young boy embarks on a journey through the universe, meeting various characters that symbolize different aspects of adult life. This timeless tale, published in 1943, remains incredibly relevant in today\\'s modern world. Its allegorical nature, thought-provoking message, and critique of modern society offer invaluable insights for readers of all ages. This essay will explore the allegory of \"The Little Prince,\" analyze the relevance of its message, and discuss its critique of modern society, demonstrating its topicality in contemporary life.\\n\\nBody Paragraph 1 - The Allegory of the Little Prince:\\n\"The Little Prince\" is an allegorical tale that uses whimsical characters and situations to explore various aspects of the human condition. For instance, the king represents authority without substance, while the businessman embodies the futility of materialism. The fox, conversely, symbolizes the importance of forming genuine connections and nurturing meaningful relationships. These allegorical representations allow the story to transcend age and culture, making it relatable to a wide range of readers, even in the modern context.\\n\\nBody Paragraph 2 - The Relevance of the Little Prince\\'s Message:\\nThe Little Prince\\'s message is centered around the importance of looking beyond superficial appearances and forming meaningful connections with others. In a world increasingly dominated by technology and social media, where surface-level interactions are commonplace, this message is more relevant than ever. Neglecting this message can lead to feelings of isolation, loneliness, and dissatisfaction. By embracing the story\\'s wisdom, we can prioritize genuine relationships, fostering a more compassionate and interconnected society.\\n\\nBody Paragraph 3 - The Critique of Modern Society:\\n\"The Little Prince\" offers a critique of modern society, highlighting the dangers of materialism, consumerism, and the pursuit of power. These themes resonate strongly in today\\'s world, where wealth inequality and environmental degradation are pressing issues. The story serves as a reminder that the pursuit of material possessions and status often comes at the expense of our own happiness and the well-being of our planet. To address these challenges, we must reevaluate our priorities, focusing on sustainability, empathy, and the cultivation of meaningful relationships.\\n\\nConclusion:\\nIn conclusion, \"The Little Prince\" remains a topical and relevant work in modern life due to its allegorical nature, timeless message, and critique of modern society. Its exploration of human connections, materialism, and the pursuit of power offers valuable insights for readers of all ages. By embracing the story\\'s wisdom, we can better navigate the complexities of the modern world and foster a more compassionate, sustainable, and interconnected society. As the Little Prince so eloquently states, \"What is essential is invisible to the eye,\" reminding us that true happiness and fulfillment come from understanding and empathizing with others.\\n\\nExpanded Essay Recommendations:\\n\\n1. Expand the essay to approximately 1,200-1,500 words to allow for a more in-depth analysis.\\n2. Incorporate specific examples and quotes from \"The Little Prince\" to support your arguments and engage the reader. For instance, use quotes like, \"You become responsible, forever, for what you have tamed,\" to emphasize the importance of forming genuine connections.\\n3. Ensure that each body paragraph contains a clear thesis statement, supporting evidence, and analysis.\\n4. Consider discussing counterarguments or potential criticisms of the Little Prince\\'s message to add depth and complexity to your essay. For example, explore the idea that the pursuit of material possessions can provide a sense of security and comfort.\\n5. Revise and edit the essay for clarity, coherence, and grammar. Ensure that transitions between paragraphs are smooth and that your arguments flow logically.', response_metadata={'token_usage': {'prompt_tokens': 1168, 'total_tokens': 2044, 'completion_tokens': 876}, 'model_name': 'accounts/fireworks/models/mixtral-8x7b-instruct', 'system_fingerprint': '', 'finish_reason': 'stop', 'logprobs': None}, id='run-9bfc9ff2-3186-43f5-8b75-498d532d8d1a-0', usage_metadata={'input_tokens': 1168, 'output_tokens': 876, 'total_tokens': 2044})]}}\n",
      "---\n",
@@ -478,7 +478,7 @@
      "The relevance of the Little Prince's message is well-articulated in this paragraph. To further strengthen your argument, consider discussing the consequences of ignoring this message in the context of modern society. This will help emphasize the importance of the Little Prince's wisdom and its relevance to contemporary issues.\n",
      "\n",
      "Body Paragraph 3 - The Critique of Modern Society:\n",
-      "This paragraph effectively highlights the story's critique of modern society. To deepen your analysis, explore how the themes of materialism, consumerism, and the pursuit of power interconnect and contribute to the challenges faced by modern society. Additionally, consider discussing potential solutions or actions inspired by the Little Prince's message that could help address these issues.\n",
+      "This paragraph effectively highlights the story's critique of modern society. To deepen your analysis, explore how themes of materialism, consumerism, and the pursuit of power interconnect and contribute to the challenges faced by modern society. Additionally, consider discussing potential solutions or actions inspired by the Little Prince's message that could help address these issues.\n",
      "\n",
      "Conclusion:\n",
      "The conclusion effectively summarizes the main points of the essay and emphasizes the relevance of \"The Little Prince\" in modern life. To further enhance this section, consider incorporating a thought-provoking question or statement that encourages readers to reflect on the story's message and its implications for their own lives.\n",
@@ -1758,7 +1758,7 @@
   "id": "4eb67198-c84f-458b-8baf-783d7246dddc",
   "metadata": {},
   "source": [
-    "Let's let the agent try again. Call `stream` with `None` to just use the inputs loaded from the memory. We will skip our human review for the next few attempats\n",
+    "Let's let the agent try again. Call `stream` with `None` to just use the inputs loaded from the memory. We will skip our human review for the next few attempts\n",
    "to see if it can correct itself."
   ]
  },
@@ -648,7 +648,7 @@ With orchestrator-worker, an orchestrator breaks down a task and delegates each
    Because orchestrator-worker workflows are common, LangGraph **has the `Send` API to support this**. It lets you dynamically create worker nodes and send each one a specific input. Each worker has its own state, and all worker outputs are written to a *shared state key* that is accessible to the orchestrator graph. This gives the orchestrator access to all worker output and allows it to synthesize them into a final output. As you can see below, we iterate over a list of sections and `Send` each to a worker node. See further documentation [here](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/) and [here](https://langchain-ai.github.io/langgraph/concepts/low_level/#send).

    ```python
-    from langgraph.constants import Send
+    from langgraph.types import Send


    # Graph state
@@ -179,6 +179,7 @@ nav:
          - cloud/how-tos/studio/manage_assistants.md
          - cloud/how-tos/threads_studio.md
          - cloud/how-tos/iterate_graph_studio.md
+          - cloud/how-tos/studio/run_evals.md
          - cloud/how-tos/clone_traces_studio.md
          - cloud/how-tos/datasets_studio.md
        - LangGraph SDK: concepts/sdk.md
@@ -364,16 +365,6 @@ markdown_extensions:
 hooks:
  - _scripts/notebook_hooks.py
 extra:
-  consent:
-    title: Cookie consent
-    actions:
-      - accept
-      - reject
-    description: >- 
-      We use cookies to recognize your repeated visits and preferences, as well
-      as to measure the effectiveness of our documentation and whether users
-      find what they're searching for. <strong>Clicking "Accept" makes our
-      documentation better. Thank you!</strong> ❤️
  social:
    - icon: fontawesome/brands/js
      link: https://langchain-ai.github.io/langgraphjs/
@@ -381,25 +372,6 @@ extra:
      link: https://github.com/langchain-ai/langgraph
    - icon: fontawesome/brands/twitter
      link: https://twitter.com/LangChainAI
-  analytics:
-    provider: google
-    property: G-G8X6ELZYE0
-    feedback:
-      title: Was this page helpful?
-      ratings:
-        - icon: material/emoticon-happy-outline
-          name: This page was helpful
-          data: 1
-          note: >-
-            Thanks for your feedback!
-        - icon: material/emoticon-sad-outline
-          name: This page could be improved
-          data: 0
-          note: >-
-            Thanks for your feedback! Please help us improve this page by adding to the discussion below.
-  shared_analytics:
-    provider: google
-    property: G-47WX3HKKY2
 validation:
  # https://www.mkdocs.org/user-guide/configuration/
  # We are still raising for omitted files because they determine the breadcrumbs for pages.
@@ -0,0 +1,41 @@
+.lang-python,
+.lang-javascript {
+    display: none;
+}
+
+.language-switcher-global {
+    display: flex;
+    align-items: center;
+    padding-left: 0.5rem;
+    margin-right: 0.5rem;
+}
+
+/* Style the select to match the header */
+.language-switcher-global select {
+    appearance: none;
+    font: inherit;
+    border: none;
+    padding: 0.25rem 0.6rem;
+    cursor: pointer;
+    outline: none;
+    font-weight: bolder;
+}
+
+/* Hover/focus effect */
+.language-switcher-global select:hover,
+.language-switcher-global select:focus {
+    text-decoration: underline;
+}
+
+/* Theme-specific overrides */
+html[data-md-color-scheme="default"] .language-switcher-global select,
+html[data-md-color-scheme="default"] .language-switcher-global option {
+    color: #333;
+    background-color: transparent;
+}
+
+html[data-md-color-scheme="slate"] .language-switcher-global select,
+html[data-md-color-scheme="slate"] .language-switcher-global option {
+    color: #eee;
+    background-color: transparent;
+}
@@ -0,0 +1,38 @@
+function applyLanguageSwitching() {
+    const selector = document.getElementById("global-language-selector");
+
+    const langBlocks = {
+        python: document.querySelectorAll(".lang-python"),
+        javascript: document.querySelectorAll(".lang-javascript"),
+    };
+
+    const setLanguage = (lang) => {
+        for (const [key, blocks] of Object.entries(langBlocks)) {
+            blocks.forEach((block) => {
+                block.style.display = key === lang ? "block" : "none";
+            });
+        }
+        localStorage.setItem("preferredLang", lang);
+    };
+
+    const saved = localStorage.getItem("preferredLang") || "python";
+
+    if (selector) {
+        selector.value = saved;
+        selector.addEventListener("change", (e) => setLanguage(e.target.value));
+    }
+
+    setLanguage(saved);
+}
+
+// Run on initial load
+document.addEventListener("DOMContentLoaded", applyLanguageSwitching);
+
+// Re-run after client-side navigation (MkDocs Material)
+document.addEventListener("pjax:success", applyLanguageSwitching);
+
+// Optional: observe DOM changes (e.g., for late-loaded content)
+if (window.MutationObserver) {
+    const observer = new MutationObserver(() => applyLanguageSwitching());
+    observer.observe(document.body, { childList: true, subtree: true });
+}
@@ -1,5 +1,16 @@
 {% extends "base.html" %}

+{% block analytics %}
+<!-- Google Tag Manager -->
+<script>(function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':
+new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],
+j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src=
+'https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);
+})(window,document,'script','dataLayer','GTM-T35S4S46');</script>
+<!-- End Google Tag Manager -->
+{% endblock %}
+
+
 {% block extrahead %}
  <meta name="algolia-site-verification" content="165B7E7C89E49946" />
  <style>
@@ -185,7 +196,6 @@
  </style>
 {% endblock %}

-
 {% block content %}
 <div class="notebook-links">
  {% if page.nb_url %}
@@ -209,7 +219,6 @@
  {% endif %}
 {% endblock %}

-
 {% block announce %}
 <strong>We are growing and hiring for multiple roles for LangChain, LangGraph and LangSmith. <a href="https://www.langchain.com/careers" target="_blank" rel="noopener noreferrer"> Join our team!</a></strong>
 {% endblock %}
@@ -0,0 +1,6 @@
+<div class="md-header__button language-switcher-global" title="Select Language">
+  <select id="global-language-selector" aria-label="Select Language">
+    <option value="python">🐍 Python</option>
+    <option value="javascript">⚡️ JavaScript</option>
+  </select>
+</div>
@@ -0,0 +1,22 @@
+from _scripts.notebook_hooks import _apply_conditional_rendering
+
+
+CONDITIONAL_RENDERING = """
+above
+:::js
+js-content
+:::
+between
+:::python
+python-content
+:::
+below
+"""
+
+
+def test_conditional_rendering() -> None:
+    """Test logic for conditional rendering of content."""
+    output = _apply_conditional_rendering(CONDITIONAL_RENDERING, "js")
+    assert output.strip() == "above\njs-content\n\nbetween\n\nbelow"
+    output = _apply_conditional_rendering(CONDITIONAL_RENDERING, "python")
+    assert output.strip() == "above\n\nbetween\npython-content\n\nbelow"
@@ -184,7 +184,7 @@
    "\n",
    "\n",
    "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
    "structured_llm_router = llm.with_structured_output(RouteQuery)\n",
    "\n",
    "# Prompt\n",
@@ -235,7 +235,7 @@
    "\n",
    "\n",
    "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
    "structured_llm_grader = llm.with_structured_output(GradeDocuments)\n",
    "\n",
    "# Prompt\n",
@@ -328,7 +328,7 @@
    "\n",
    "\n",
    "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
    "structured_llm_grader = llm.with_structured_output(GradeHallucinations)\n",
    "\n",
    "# Prompt\n",
@@ -376,7 +376,7 @@
    "\n",
    "\n",
    "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
    "structured_llm_grader = llm.with_structured_output(GradeAnswer)\n",
    "\n",
    "# Prompt\n",
@@ -200,11 +200,11 @@
     "output_type": "stream",
     "text": [
      "********************Prompt[rlm/rag-prompt]********************\n",
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "================================\u001B[1m Human Message \u001B[0m=================================\n",
      "\n",
      "You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\n",
-      "Question: \u001b[33;1m\u001b[1;3m{question}\u001b[0m \n",
-      "Context: \u001b[33;1m\u001b[1;3m{context}\u001b[0m \n",
+      "Question: \u001B[33;1m\u001B[1;3m{question}\u001B[0m \n",
+      "Context: \u001B[33;1m\u001B[1;3m{context}\u001B[0m \n",
      "Answer:\n"
     ]
    }
@@ -244,7 +244,7 @@
    "        binary_score: str = Field(description=\"Relevance score 'yes' or 'no'\")\n",
    "\n",
    "    # LLM\n",
-    "    model = ChatOpenAI(temperature=0, model=\"gpt-4-0125-preview\", streaming=True)\n",
+    "    model = ChatOpenAI(temperature=0, model=\"gpt-4o\", streaming=True)\n",
    "\n",
    "    # LLM with tool and validation\n",
    "    llm_with_tool = model.with_structured_output(grade)\n",
@@ -171,7 +171,7 @@
    "\n",
    "\n",
    "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
    "structured_llm_grader = llm.with_structured_output(GradeDocuments)\n",
    "\n",
    "# Prompt\n",
@@ -191,7 +191,7 @@
    "\n",
    "\n",
    "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
    "structured_llm_grader = llm.with_structured_output(GradeDocuments)\n",
    "\n",
    "# Prompt\n",
@@ -284,7 +284,7 @@
    "\n",
    "\n",
    "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
    "structured_llm_grader = llm.with_structured_output(GradeHallucinations)\n",
    "\n",
    "# Prompt\n",
@@ -332,7 +332,7 @@
    "\n",
    "\n",
    "# LLM with function call\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
    "structured_llm_grader = llm.with_structured_output(GradeAnswer)\n",
    "\n",
    "# Prompt\n",
@@ -33,7 +33,9 @@
   "id": "a384cc48-0425-4e8f-aafc-cfb8e56025c9",
   "metadata": {},
   "outputs": [],
-   "source": ["%pip install -qU langchain-pinecone langchain-openai langchainhub langgraph"]
+   "source": [
+    "%pip install -qU langchain-pinecone langchain-openai langchainhub langgraph"
+   ]
  },
  {
   "cell_type": "markdown",
@@ -51,7 +53,9 @@
   "id": "ccc3dae5-1df6-48ca-af8a-50f0e6128876",
   "metadata": {},
   "outputs": [],
-   "source": ["import os\n\nos.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\nos.environ[\"LANGCHAIN_API_KEY\"] = \"<your-api-key>\""]
+   "source": [
+    "import os\n\nos.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\nos.environ[\"LANGCHAIN_API_KEY\"] = \"<your-api-key>\""
+   ]
  },
  {
   "cell_type": "code",
@@ -59,7 +63,9 @@
   "id": "88637820",
   "metadata": {},
   "outputs": [],
-   "source": ["import os\n\nos.environ[\"LANGCHAIN_PROJECT\"] = \"pinecone-devconnect\""]
+   "source": [
+    "import os\n\nos.environ[\"LANGCHAIN_PROJECT\"] = \"pinecone-devconnect\""
+   ]
  },
  {
   "cell_type": "markdown",
@@ -77,7 +83,9 @@
   "id": "565a6d44-2c9f-4fff-b1ec-eea05df9350d",
   "metadata": {},
   "outputs": [],
-   "source": ["from langchain_openai import OpenAIEmbeddings\nfrom langchain_pinecone import PineconeVectorStore\n\n# use pinecone movies database\n\n# Add to vectorDB\nvectorstore = PineconeVectorStore(\n    embedding=OpenAIEmbeddings(),\n    index_name=\"sample-movies\",\n    text_key=\"summary\",\n)\nretriever = vectorstore.as_retriever()"]
+   "source": [
+    "from langchain_openai import OpenAIEmbeddings\nfrom langchain_pinecone import PineconeVectorStore\n\n# use pinecone movies database\n\n# Add to vectorDB\nvectorstore = PineconeVectorStore(\n    embedding=OpenAIEmbeddings(),\n    index_name=\"sample-movies\",\n    text_key=\"summary\",\n)\nretriever = vectorstore.as_retriever()"
+   ]
  },
  {
   "cell_type": "code",
@@ -104,7 +112,9 @@
     ]
    }
   ],
-   "source": ["docs = retriever.invoke(\"James Cameron\")\nfor doc in docs:\n    print(\"# \" + doc.metadata[\"title\"])\n    print(doc.page_content)\n    print()"]
+   "source": [
+    "docs = retriever.invoke(\"James Cameron\")\nfor doc in docs:\n    print(\"# \" + doc.metadata[\"title\"])\n    print(doc.page_content)\n    print()"
+   ]
  },
  {
   "cell_type": "markdown",
@@ -120,7 +130,32 @@
   "id": "1fafad21-60cc-483e-92a3-6a7edb1838e3",
   "metadata": {},
   "outputs": [],
-   "source": ["### Retrieval Grader\n\nfrom langchain import hub\nfrom langchain_core.pydantic_v1 import BaseModel, Field\nfrom langchain_openai import ChatOpenAI\n\n\n# Data model\nclass GradeDocuments(BaseModel):\n    \"\"\"Binary score for relevance check on retrieved documents.\"\"\"\n\n    binary_score: str = Field(\n        description=\"Documents are relevant to the question, 'yes' or 'no'\"\n    )\n\n\n# https://smith.langchain.com/hub/efriis/self-rag-retrieval-grader\ngrade_prompt = hub.pull(\"efriis/self-rag-retrieval-grader\")\n\n# LLM with function call\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\nstructured_llm_grader = llm.with_structured_output(GradeDocuments)\n\nretrieval_grader = grade_prompt | structured_llm_grader"]
+   "source": [
+    "### Retrieval Grader\n",
+    "\n",
+    "from langchain import hub\n",
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "\n",
+    "# Data model\n",
+    "class GradeDocuments(BaseModel):\n",
+    "    \"\"\"Binary score for relevance check on retrieved documents.\"\"\"\n",
+    "\n",
+    "    binary_score: str = Field(\n",
+    "        description=\"Documents are relevant to the question, 'yes' or 'no'\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "# https://smith.langchain.com/hub/efriis/self-rag-retrieval-grader\n",
+    "grade_prompt = hub.pull(\"efriis/self-rag-retrieval-grader\")\n",
+    "\n",
+    "# LLM with function call\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
+    "structured_llm_grader = llm.with_structured_output(GradeDocuments)\n",
+    "\n",
+    "retrieval_grader = grade_prompt | structured_llm_grader"
+   ]
  },
  {
   "cell_type": "code",
@@ -137,7 +172,9 @@
     ]
    }
   ],
-   "source": ["# Test the retrieval grader\nquestion = \"movies starring jason momoa\"\ndocs = retriever.invoke(question)\ndoc_txt = docs[0].page_content\nprint(doc_txt)\nprint(retrieval_grader.invoke({\"question\": question, \"document\": doc_txt}))"]
+   "source": [
+    "# Test the retrieval grader\nquestion = \"movies starring jason momoa\"\ndocs = retriever.invoke(question)\ndoc_txt = docs[0].page_content\nprint(doc_txt)\nprint(retrieval_grader.invoke({\"question\": question, \"document\": doc_txt}))"
+   ]
  },
  {
   "cell_type": "markdown",
@@ -163,7 +200,9 @@
     ]
    }
   ],
-   "source": ["### Generate\n\nfrom langchain import hub\nfrom langchain_core.output_parsers import StrOutputParser\n\n# Prompt\nprompt = hub.pull(\"rlm/rag-prompt\")\n\n# LLM\nllm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n\n# Chain\nrag_chain = prompt | llm | StrOutputParser()\n\n# Run\ngeneration = rag_chain.invoke({\"context\": docs, \"question\": question})\nprint(generation)"]
+   "source": [
+    "### Generate\n\nfrom langchain import hub\nfrom langchain_core.output_parsers import StrOutputParser\n\n# Prompt\nprompt = hub.pull(\"rlm/rag-prompt\")\n\n# LLM\nllm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n\n# Chain\nrag_chain = prompt | llm | StrOutputParser()\n\n# Run\ngeneration = rag_chain.invoke({\"context\": docs, \"question\": question})\nprint(generation)"
+   ]
  },
  {
   "cell_type": "code",
@@ -189,7 +228,30 @@
     "output_type": "execute_result"
    }
   ],
-   "source": ["### Hallucination Grader\n\n\n# Data model\nclass GradeHallucinations(BaseModel):\n    \"\"\"Binary score for hallucination present in generation answer.\"\"\"\n\n    binary_score: str = Field(\n        description=\"Answer is grounded in the facts, 'yes' or 'no'\"\n    )\n\n\n# LLM with function call\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\nstructured_llm_grader = llm.with_structured_output(GradeHallucinations)\n\n# https://smith.langchain.com/hub/efriis/self-rag-hallucination-grader\nhallucination_prompt = hub.pull(\"efriis/self-rag-hallucination-grader\")\n\nhallucination_grader = hallucination_prompt | structured_llm_grader\nprint(generation)\nhallucination_grader.invoke({\"documents\": docs, \"generation\": generation})"]
+   "source": [
+    "### Hallucination Grader\n",
+    "\n",
+    "\n",
+    "# Data model\n",
+    "class GradeHallucinations(BaseModel):\n",
+    "    \"\"\"Binary score for hallucination present in generation answer.\"\"\"\n",
+    "\n",
+    "    binary_score: str = Field(\n",
+    "        description=\"Answer is grounded in the facts, 'yes' or 'no'\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "# LLM with function call\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
+    "structured_llm_grader = llm.with_structured_output(GradeHallucinations)\n",
+    "\n",
+    "# https://smith.langchain.com/hub/efriis/self-rag-hallucination-grader\n",
+    "hallucination_prompt = hub.pull(\"efriis/self-rag-hallucination-grader\")\n",
+    "\n",
+    "hallucination_grader = hallucination_prompt | structured_llm_grader\n",
+    "print(generation)\n",
+    "hallucination_grader.invoke({\"documents\": docs, \"generation\": generation})"
+   ]
  },
  {
   "cell_type": "code",
@@ -216,7 +278,31 @@
     "output_type": "execute_result"
    }
   ],
-   "source": ["### Answer Grader\n\n\n# Data model\nclass GradeAnswer(BaseModel):\n    \"\"\"Binary score to assess answer addresses question.\"\"\"\n\n    binary_score: str = Field(\n        description=\"Answer addresses the question, 'yes' or 'no'\"\n    )\n\n\n# LLM with function call\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\nstructured_llm_grader = llm.with_structured_output(GradeAnswer)\n\n# Prompt\nanswer_prompt = hub.pull(\"efriis/self-rag-answer-grader\")\n\nanswer_grader = answer_prompt | structured_llm_grader\nprint(question)\nprint(generation)\nanswer_grader.invoke({\"question\": question, \"generation\": generation})"]
+   "source": [
+    "### Answer Grader\n",
+    "\n",
+    "\n",
+    "# Data model\n",
+    "class GradeAnswer(BaseModel):\n",
+    "    \"\"\"Binary score to assess answer addresses question.\"\"\"\n",
+    "\n",
+    "    binary_score: str = Field(\n",
+    "        description=\"Answer addresses the question, 'yes' or 'no'\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "# LLM with function call\n",
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n",
+    "structured_llm_grader = llm.with_structured_output(GradeAnswer)\n",
+    "\n",
+    "# Prompt\n",
+    "answer_prompt = hub.pull(\"efriis/self-rag-answer-grader\")\n",
+    "\n",
+    "answer_grader = answer_prompt | structured_llm_grader\n",
+    "print(question)\n",
+    "print(generation)\n",
+    "answer_grader.invoke({\"question\": question, \"generation\": generation})"
+   ]
  },
  {
   "cell_type": "code",
@@ -242,7 +328,9 @@
     "output_type": "execute_result"
    }
   ],
-   "source": ["### Question Re-writer\n\n# LLM\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n\n# Prompt\nre_write_prompt = hub.pull(\"efriis/self-rag-question-rewriter\")\n\nquestion_rewriter = re_write_prompt | llm | StrOutputParser()\nprint(question)\nquestion_rewriter.invoke({\"question\": question})"]
+   "source": [
+    "### Question Re-writer\n\n# LLM\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)\n\n# Prompt\nre_write_prompt = hub.pull(\"efriis/self-rag-question-rewriter\")\n\nquestion_rewriter = re_write_prompt | llm | StrOutputParser()\nprint(question)\nquestion_rewriter.invoke({\"question\": question})"
+   ]
  },
  {
   "cell_type": "markdown",
@@ -262,7 +350,9 @@
   "id": "f1617e9e-66a8-4c1a-a1fe-cc936284c085",
   "metadata": {},
   "outputs": [],
-   "source": ["from typing import List\n\nfrom typing_extensions import TypedDict\n\n\nclass GraphState(TypedDict):\n    \"\"\"\n    Represents the state of our graph.\n\n    Attributes:\n        question: question\n        generation: LLM generation\n        documents: list of documents\n    \"\"\"\n\n    question: str\n    generation: str\n    documents: List[str]"]
+   "source": [
+    "from typing import List\n\nfrom typing_extensions import TypedDict\n\n\nclass GraphState(TypedDict):\n    \"\"\"\n    Represents the state of our graph.\n\n    Attributes:\n        question: question\n        generation: LLM generation\n        documents: list of documents\n    \"\"\"\n\n    question: str\n    generation: str\n    documents: List[str]"
+   ]
  },
  {
   "cell_type": "code",
@@ -270,7 +360,9 @@
   "id": "add509d8-6682-4127-8d95-13dd37d79702",
   "metadata": {},
   "outputs": [],
-   "source": ["### Nodes\n\n\ndef retrieve(state):\n    \"\"\"\n    Retrieve documents\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, documents, that contains retrieved documents\n    \"\"\"\n    print(\"---RETRIEVE---\")\n    question = state[\"question\"]\n\n    # Retrieval\n    documents = retriever.invoke(question)\n    return {\"documents\": documents, \"question\": question}\n\n\ndef generate(state):\n    \"\"\"\n    Generate answer\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, generation, that contains LLM generation\n    \"\"\"\n    print(\"---GENERATE---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # RAG generation\n    generation = rag_chain.invoke({\"context\": documents, \"question\": question})\n    return {\"documents\": documents, \"question\": question, \"generation\": generation}\n\n\ndef grade_documents(state):\n    \"\"\"\n    Determines whether the retrieved documents are relevant to the question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): Updates documents key with only filtered relevant documents\n    \"\"\"\n\n    print(\"---CHECK DOCUMENT RELEVANCE TO QUESTION---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # Score each doc\n    filtered_docs = []\n    for d in documents:\n        score = retrieval_grader.invoke(\n            {\"question\": question, \"document\": d.page_content}\n        )\n        grade = score.binary_score\n        if grade == \"yes\":\n            print(\"---GRADE: DOCUMENT RELEVANT---\")\n            filtered_docs.append(d)\n        else:\n            print(\"---GRADE: DOCUMENT NOT RELEVANT---\")\n            continue\n    return {\"documents\": filtered_docs, \"question\": question}\n\n\ndef transform_query(state):\n    \"\"\"\n    Transform the query to produce a better question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): Updates question key with a re-phrased question\n    \"\"\"\n\n    print(\"---TRANSFORM QUERY---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # Re-write question\n    better_question = question_rewriter.invoke({\"question\": question})\n    return {\"documents\": documents, \"question\": better_question}"]
+   "source": [
+    "### Nodes\n\n\ndef retrieve(state):\n    \"\"\"\n    Retrieve documents\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, documents, that contains retrieved documents\n    \"\"\"\n    print(\"---RETRIEVE---\")\n    question = state[\"question\"]\n\n    # Retrieval\n    documents = retriever.invoke(question)\n    return {\"documents\": documents, \"question\": question}\n\n\ndef generate(state):\n    \"\"\"\n    Generate answer\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, generation, that contains LLM generation\n    \"\"\"\n    print(\"---GENERATE---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # RAG generation\n    generation = rag_chain.invoke({\"context\": documents, \"question\": question})\n    return {\"documents\": documents, \"question\": question, \"generation\": generation}\n\n\ndef grade_documents(state):\n    \"\"\"\n    Determines whether the retrieved documents are relevant to the question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): Updates documents key with only filtered relevant documents\n    \"\"\"\n\n    print(\"---CHECK DOCUMENT RELEVANCE TO QUESTION---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # Score each doc\n    filtered_docs = []\n    for d in documents:\n        score = retrieval_grader.invoke(\n            {\"question\": question, \"document\": d.page_content}\n        )\n        grade = score.binary_score\n        if grade == \"yes\":\n            print(\"---GRADE: DOCUMENT RELEVANT---\")\n            filtered_docs.append(d)\n        else:\n            print(\"---GRADE: DOCUMENT NOT RELEVANT---\")\n            continue\n    return {\"documents\": filtered_docs, \"question\": question}\n\n\ndef transform_query(state):\n    \"\"\"\n    Transform the query to produce a better question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): Updates question key with a re-phrased question\n    \"\"\"\n\n    print(\"---TRANSFORM QUERY---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n\n    # Re-write question\n    better_question = question_rewriter.invoke({\"question\": question})\n    return {\"documents\": documents, \"question\": better_question}"
+   ]
  },
  {
   "cell_type": "code",
@@ -278,7 +370,9 @@
   "id": "09fc91b4",
   "metadata": {},
   "outputs": [],
-   "source": ["### Edges\n\n\ndef decide_to_generate(state):\n    \"\"\"\n    Determines whether to generate an answer, or re-generate a question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        str: Binary decision for next node to call\n    \"\"\"\n\n    print(\"---ASSESS GRADED DOCUMENTS---\")\n    state[\"question\"]\n    filtered_documents = state[\"documents\"]\n\n    if not filtered_documents:\n        # All documents have been filtered check_relevance\n        # We will re-generate a new query\n        print(\n            \"---DECISION: ALL DOCUMENTS ARE NOT RELEVANT TO QUESTION, TRANSFORM QUERY---\"\n        )\n        return \"transform_query\"\n    else:\n        # We have relevant documents, so generate answer\n        print(\"---DECISION: GENERATE---\")\n        return \"generate\"\n\n\ndef grade_generation_v_documents_and_question(state):\n    \"\"\"\n    Determines whether the generation is grounded in the document and answers question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        str: Decision for next node to call\n    \"\"\"\n\n    print(\"---CHECK HALLUCINATIONS---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n    generation = state[\"generation\"]\n\n    score = hallucination_grader.invoke(\n        {\"documents\": documents, \"generation\": generation}\n    )\n    grade = score.binary_score\n\n    # Check hallucination\n    if grade == \"yes\":\n        print(\"---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---\")\n        # Check question-answering\n        print(\"---GRADE GENERATION vs QUESTION---\")\n        score = answer_grader.invoke({\"question\": question, \"generation\": generation})\n        grade = score.binary_score\n        if grade == \"yes\":\n            print(\"---DECISION: GENERATION ADDRESSES QUESTION---\")\n            return \"useful\"\n        else:\n            print(\"---DECISION: GENERATION DOES NOT ADDRESS QUESTION---\")\n            return \"not useful\"\n    else:\n        pprint(\"---DECISION: GENERATION IS NOT GROUNDED IN DOCUMENTS, RE-TRY---\")\n        return \"not supported\""]
+   "source": [
+    "### Edges\n\n\ndef decide_to_generate(state):\n    \"\"\"\n    Determines whether to generate an answer, or re-generate a question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        str: Binary decision for next node to call\n    \"\"\"\n\n    print(\"---ASSESS GRADED DOCUMENTS---\")\n    state[\"question\"]\n    filtered_documents = state[\"documents\"]\n\n    if not filtered_documents:\n        # All documents have been filtered check_relevance\n        # We will re-generate a new query\n        print(\n            \"---DECISION: ALL DOCUMENTS ARE NOT RELEVANT TO QUESTION, TRANSFORM QUERY---\"\n        )\n        return \"transform_query\"\n    else:\n        # We have relevant documents, so generate answer\n        print(\"---DECISION: GENERATE---\")\n        return \"generate\"\n\n\ndef grade_generation_v_documents_and_question(state):\n    \"\"\"\n    Determines whether the generation is grounded in the document and answers question.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        str: Decision for next node to call\n    \"\"\"\n\n    print(\"---CHECK HALLUCINATIONS---\")\n    question = state[\"question\"]\n    documents = state[\"documents\"]\n    generation = state[\"generation\"]\n\n    score = hallucination_grader.invoke(\n        {\"documents\": documents, \"generation\": generation}\n    )\n    grade = score.binary_score\n\n    # Check hallucination\n    if grade == \"yes\":\n        print(\"---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---\")\n        # Check question-answering\n        print(\"---GRADE GENERATION vs QUESTION---\")\n        score = answer_grader.invoke({\"question\": question, \"generation\": generation})\n        grade = score.binary_score\n        if grade == \"yes\":\n            print(\"---DECISION: GENERATION ADDRESSES QUESTION---\")\n            return \"useful\"\n        else:\n            print(\"---DECISION: GENERATION DOES NOT ADDRESS QUESTION---\")\n            return \"not useful\"\n    else:\n        pprint(\"---DECISION: GENERATION IS NOT GROUNDED IN DOCUMENTS, RE-TRY---\")\n        return \"not supported\""
+   ]
  },
  {
   "cell_type": "markdown",
@@ -331,7 +425,9 @@
     ]
    }
   ],
-   "source": ["from pprint import pprint\n\n# Run\ninputs = {\"question\": \"Movies that star Daniel Craig\"}\nfor output in app.stream(inputs):\n    for key, value in output.items():\n        # Node\n        pprint(f\"Node '{key}':\")\n    pprint(\"\\n---\\n\")\n\n# Final generation\npprint(value[\"generation\"])"]
+   "source": [
+    "from pprint import pprint\n\n# Run\ninputs = {\"question\": \"Movies that star Daniel Craig\"}\nfor output in app.stream(inputs):\n    for key, value in output.items():\n        # Node\n        pprint(f\"Node '{key}':\")\n    pprint(\"\\n---\\n\")\n\n# Final generation\npprint(value[\"generation\"])"
+   ]
  },
  {
   "cell_type": "code",
@@ -339,7 +435,9 @@
   "id": "4138bc51-8c84-4b8a-8d24-f7f470721f6f",
   "metadata": {},
   "outputs": [],
-   "source": ["inputs = {\"question\": \"Which movies are about aliens?\"}\nfor output in app.stream(inputs):\n    for key, value in output.items():\n        # Node\n        pprint(f\"Node '{key}':\")\n    pprint(\"\\n---\\n\")\n\n# Final generation\npprint(value[\"generation\"])"]
+   "source": [
+    "inputs = {\"question\": \"Which movies are about aliens?\"}\nfor output in app.stream(inputs):\n    for key, value in output.items():\n        # Node\n        pprint(f\"Node '{key}':\")\n    pprint(\"\\n---\\n\")\n\n# Final generation\npprint(value[\"generation\"])"
+   ]
  },
  {
   "cell_type": "code",
@@ -347,7 +445,9 @@
   "id": "42369ab8-322d-434a-b5dd-2266e4cb2903",
   "metadata": {},
   "outputs": [],
-   "source": [""]
+   "source": [
+    ""
+   ]
  }
 ],
 "metadata": {
@@ -13,6 +13,20 @@ By default `langgraph-checkpoint-postgres` installs `psycopg` (Psycopg 3) withou

 > [!IMPORTANT]
 > When manually creating Postgres connections and passing them to `PostgresSaver` or `AsyncPostgresSaver`, make sure to include `autocommit=True` and `row_factory=dict_row` (`from psycopg.rows import dict_row`). See a full example in this [how-to guide](https://langchain-ai.github.io/langgraph/how-tos/persistence_postgres/).
+>
+> **Why these parameters are required:**
+> - `autocommit=True`: Required for the `.setup()` method to properly commit the checkpoint tables to the database. Without this, table creation may not be persisted.
+> - `row_factory=dict_row`: Required because the PostgresSaver implementation accesses database rows using dictionary-style syntax (e.g., `row["column_name"]`). The default `tuple_row` factory returns tuples that only support index-based access (e.g., `row[0]`), which will cause `TypeError` exceptions when the checkpointer tries to access columns by name.
+>
+> **Example of incorrect usage:**
+> ```python
+> # ❌ This will fail with TypeError during checkpointer operations
+> with psycopg.connect(DB_URI) as conn:  # Missing autocommit=True and row_factory=dict_row
+>     checkpointer = PostgresSaver(conn)
+>     checkpointer.setup()  # May not persist tables properly
+>     # Any operation that reads from database will fail with:
+>     # TypeError: tuple indices must be integers or slices, not str
+> ```

 ```python
 from langgraph.checkpoint.postgres import PostgresSaver
@@ -25,7 +39,7 @@ with PostgresSaver.from_conn_string(DB_URI) as checkpointer:
    # call .setup() the first time you're using the checkpointer
    checkpointer.setup()
    checkpoint = {
-        "v": 2,
+        "v": 4,
        "ts": "2024-07-31T20:14:19.804150+00:00",
        "id": "1ef4f797-8335-6428-8001-8a1503f9b875",
        "channel_values": {
@@ -47,7 +61,6 @@ with PostgresSaver.from_conn_string(DB_URI) as checkpointer:
            "start:node": 2
            }
        },
-        "pending_sends": [],
    }

    # store checkpoint
@@ -67,7 +80,7 @@ from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver

 async with AsyncPostgresSaver.from_conn_string(DB_URI) as checkpointer:
    checkpoint = {
-        "v": 2,
+        "v": 4,
        "ts": "2024-07-31T20:14:19.804150+00:00",
        "id": "1ef4f797-8335-6428-8001-8a1503f9b875",
        "channel_values": {
@@ -89,7 +102,6 @@ async with AsyncPostgresSaver.from_conn_string(DB_URI) as checkpointer:
            "start:node": 2
            }
        },
-        "pending_sends": [],
    }

    # store checkpoint
@@ -1,7 +1,10 @@
+from __future__ import annotations
+
 import threading
+from collections import defaultdict
 from collections.abc import Iterator, Sequence
 from contextlib import contextmanager
-from typing import Any, Optional
+from typing import Any

 from langchain_core.runnables import RunnableConfig
 from psycopg import Capabilities, Connection, Cursor, Pipeline
@@ -34,8 +37,8 @@ class PostgresSaver(BasePostgresSaver):
    def __init__(
        self,
        conn: _internal.Conn,
-        pipe: Optional[Pipeline] = None,
-        serde: Optional[SerializerProtocol] = None,
+        pipe: Pipeline | None = None,
+        serde: SerializerProtocol | None = None,
    ) -> None:
        super().__init__(serde=serde)
        if isinstance(conn, ConnectionPool) and pipe is not None:
@@ -52,7 +55,7 @@ class PostgresSaver(BasePostgresSaver):
    @contextmanager
    def from_conn_string(
        cls, conn_string: str, *, pipeline: bool = False
-    ) -> Iterator["PostgresSaver"]:
+    ) -> Iterator[PostgresSaver]:
        """Create a new PostgresSaver instance from a connection string.

        Args:
@@ -99,11 +102,11 @@ class PostgresSaver(BasePostgresSaver):

    def list(
        self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
        *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
    ) -> Iterator[CheckpointTuple]:
        """List checkpoints from the database.

@@ -143,37 +146,39 @@ class PostgresSaver(BasePostgresSaver):
            query += f" LIMIT {limit}"
        # if we change this to use .stream() we need to make sure to close the cursor
        with self._cursor() as cur:
-            cur.execute(query, args, binary=True)
-            for value in cur:
-                yield CheckpointTuple(
-                    {
-                        "configurable": {
-                            "thread_id": value["thread_id"],
-                            "checkpoint_ns": value["checkpoint_ns"],
-                            "checkpoint_id": value["checkpoint_id"],
-                        }
-                    },
-                    self._load_checkpoint(
-                        value["checkpoint"],
-                        value["channel_values"],
-                        value["pending_sends"],
-                    ),
-                    self._load_metadata(value["metadata"]),
+            cur.execute(query, args)
+            values = cur.fetchall()
+            if not values:
+                return
+            # migrate pending sends if necessary
+            if to_migrate := [
+                v
+                for v in values
+                if v["checkpoint"]["v"] < 4 and v["parent_checkpoint_id"]
+            ]:
+                cur.execute(
+                    self.SELECT_PENDING_SENDS_SQL,
                    (
-                        {
-                            "configurable": {
-                                "thread_id": value["thread_id"],
-                                "checkpoint_ns": value["checkpoint_ns"],
-                                "checkpoint_id": value["parent_checkpoint_id"],
-                            }
-                        }
-                        if value["parent_checkpoint_id"]
-                        else None
+                        values[0]["thread_id"],
+                        [v["parent_checkpoint_id"] for v in to_migrate],
                    ),
-                    self._load_writes(value["pending_writes"]),
                )
+                grouped_by_parent = defaultdict(list)
+                for value in to_migrate:
+                    grouped_by_parent[value["parent_checkpoint_id"]].append(value)
+                for sends in cur:
+                    for value in grouped_by_parent[sends["checkpoint_id"]]:
+                        if value["channel_values"] is None:
+                            value["channel_values"] = []
+                        self._migrate_pending_sends(
+                            sends["sends"],
+                            value["checkpoint"],
+                            value["channel_values"],
+                        )
+            for value in values:
+                yield self._load_checkpoint_tuple(value)

-    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    def get_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
        """Get a checkpoint tuple from the database.

        This method retrieves a checkpoint tuple from the Postgres database based on the
@@ -222,37 +227,27 @@ class PostgresSaver(BasePostgresSaver):
            cur.execute(
                self.SELECT_SQL + where,
                args,
-                binary=True,
            )
+            value = cur.fetchone()
+            if value is None:
+                return None

-            for value in cur:
-                return CheckpointTuple(
-                    {
-                        "configurable": {
-                            "thread_id": thread_id,
-                            "checkpoint_ns": checkpoint_ns,
-                            "checkpoint_id": value["checkpoint_id"],
-                        }
-                    },
-                    self._load_checkpoint(
+            # migrate pending sends if necessary
+            if value["checkpoint"]["v"] < 4 and value["parent_checkpoint_id"]:
+                cur.execute(
+                    self.SELECT_PENDING_SENDS_SQL,
+                    (thread_id, [value["parent_checkpoint_id"]]),
+                )
+                if sends := cur.fetchone():
+                    if value["channel_values"] is None:
+                        value["channel_values"] = []
+                    self._migrate_pending_sends(
+                        sends["sends"],
                        value["checkpoint"],
                        value["channel_values"],
-                        value["pending_sends"],
-                    ),
-                    self._load_metadata(value["metadata"]),
-                    (
-                        {
-                            "configurable": {
-                                "thread_id": thread_id,
-                                "checkpoint_ns": checkpoint_ns,
-                                "checkpoint_id": value["parent_checkpoint_id"],
-                            }
-                        }
-                        if value["parent_checkpoint_id"]
-                        else None
-                    ),
-                    self._load_writes(value["pending_writes"]),
-                )
+                    )
+
+            return self._load_checkpoint_tuple(value)

    def put(
        self,
@@ -319,8 +314,8 @@ class PostgresSaver(BasePostgresSaver):
                    checkpoint_ns,
                    checkpoint["id"],
                    checkpoint_id,
-                    Jsonb(self._dump_checkpoint(copy)),
-                    self._dump_metadata(get_checkpoint_metadata(config, metadata)),
+                    Jsonb(copy),
+                    Jsonb(get_checkpoint_metadata(config, metadata)),
                ),
            )
        return next_config
@@ -391,7 +386,7 @@ class PostgresSaver(BasePostgresSaver):
                Will be applied regardless of whether the PostgresSaver instance was initialized with a pipeline.
                If pipeline mode is not supported, will fall back to using transaction context manager.
        """
-        with _internal.get_connection(self.conn) as conn:
+        with self.lock, _internal.get_connection(self.conn) as conn:
            if self.pipe:
                # a connection in pipeline mode can be used concurrently
                # in multiple threads/coroutines, but only one cursor can be
@@ -407,7 +402,6 @@ class PostgresSaver(BasePostgresSaver):
                # thread/coroutine at a time, so we acquire a lock
                if self.supports_pipeline:
                    with (
-                        self.lock,
                        conn.pipeline(),
                        conn.cursor(binary=True, row_factory=dict_row) as cur,
                    ):
@@ -415,14 +409,52 @@ class PostgresSaver(BasePostgresSaver):
                else:
                    # Use connection's transaction context manager when pipeline mode not supported
                    with (
-                        self.lock,
                        conn.transaction(),
                        conn.cursor(binary=True, row_factory=dict_row) as cur,
                    ):
                        yield cur
            else:
-                with self.lock, conn.cursor(binary=True, row_factory=dict_row) as cur:
+                with conn.cursor(binary=True, row_factory=dict_row) as cur:
                    yield cur

+    def _load_checkpoint_tuple(self, value: DictRow) -> CheckpointTuple:
+        """
+        Convert a database row into a CheckpointTuple object.
+
+        Args:
+            value: A row from the database containing checkpoint data.
+
+        Returns:
+            CheckpointTuple: A structured representation of the checkpoint,
+            including its configuration, metadata, parent checkpoint (if any),
+            and pending writes.
+        """
+        return CheckpointTuple(
+            {
+                "configurable": {
+                    "thread_id": value["thread_id"],
+                    "checkpoint_ns": value["checkpoint_ns"],
+                    "checkpoint_id": value["checkpoint_id"],
+                }
+            },
+            {
+                **value["checkpoint"],
+                "channel_values": self._load_blobs(value["channel_values"]),
+            },
+            value["metadata"],
+            (
+                {
+                    "configurable": {
+                        "thread_id": value["thread_id"],
+                        "checkpoint_ns": value["checkpoint_ns"],
+                        "checkpoint_id": value["parent_checkpoint_id"],
+                    }
+                }
+                if value["parent_checkpoint_id"]
+                else None
+            ),
+            self._load_writes(value["pending_writes"]),
+        )
+

 __all__ = ["PostgresSaver", "BasePostgresSaver", "ShallowPostgresSaver", "Conn"]
@@ -1,7 +1,10 @@
+from __future__ import annotations
+
 import asyncio
+from collections import defaultdict
 from collections.abc import AsyncIterator, Iterator, Sequence
 from contextlib import asynccontextmanager
-from typing import Any, Optional
+from typing import Any

 from langchain_core.runnables import RunnableConfig
 from psycopg import AsyncConnection, AsyncCursor, AsyncPipeline, Capabilities
@@ -34,8 +37,8 @@ class AsyncPostgresSaver(BasePostgresSaver):
    def __init__(
        self,
        conn: _ainternal.Conn,
-        pipe: Optional[AsyncPipeline] = None,
-        serde: Optional[SerializerProtocol] = None,
+        pipe: AsyncPipeline | None = None,
+        serde: SerializerProtocol | None = None,
    ) -> None:
        super().__init__(serde=serde)
        if isinstance(conn, AsyncConnectionPool) and pipe is not None:
@@ -56,8 +59,8 @@ class AsyncPostgresSaver(BasePostgresSaver):
        conn_string: str,
        *,
        pipeline: bool = False,
-        serde: Optional[SerializerProtocol] = None,
-    ) -> AsyncIterator["AsyncPostgresSaver"]:
+        serde: SerializerProtocol | None = None,
+    ) -> AsyncIterator[AsyncPostgresSaver]:
        """Create a new AsyncPostgresSaver instance from a connection string.

        Args:
@@ -104,11 +107,11 @@ class AsyncPostgresSaver(BasePostgresSaver):

    async def alist(
        self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
        *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
    ) -> AsyncIterator[CheckpointTuple]:
        """List checkpoints from the database asynchronously.

@@ -131,37 +134,38 @@ class AsyncPostgresSaver(BasePostgresSaver):
        # if we change this to use .stream() we need to make sure to close the cursor
        async with self._cursor() as cur:
            await cur.execute(query, args, binary=True)
-            async for value in cur:
-                yield CheckpointTuple(
-                    {
-                        "configurable": {
-                            "thread_id": value["thread_id"],
-                            "checkpoint_ns": value["checkpoint_ns"],
-                            "checkpoint_id": value["checkpoint_id"],
-                        }
-                    },
-                    await asyncio.to_thread(
-                        self._load_checkpoint,
-                        value["checkpoint"],
-                        value["channel_values"],
-                        value["pending_sends"],
-                    ),
-                    self._load_metadata(value["metadata"]),
+            values = await cur.fetchall()
+            if not values:
+                return
+            # migrate pending sends if necessary
+            if to_migrate := [
+                v
+                for v in values
+                if v["checkpoint"]["v"] < 4 and v["parent_checkpoint_id"]
+            ]:
+                await cur.execute(
+                    self.SELECT_PENDING_SENDS_SQL,
                    (
-                        {
-                            "configurable": {
-                                "thread_id": value["thread_id"],
-                                "checkpoint_ns": value["checkpoint_ns"],
-                                "checkpoint_id": value["parent_checkpoint_id"],
-                            }
-                        }
-                        if value["parent_checkpoint_id"]
-                        else None
+                        values[0]["thread_id"],
+                        [v["parent_checkpoint_id"] for v in to_migrate],
                    ),
-                    await asyncio.to_thread(self._load_writes, value["pending_writes"]),
                )
+                grouped_by_parent = defaultdict(list)
+                for value in to_migrate:
+                    grouped_by_parent[value["parent_checkpoint_id"]].append(value)
+                async for sends in cur:
+                    for value in grouped_by_parent[sends["checkpoint_id"]]:
+                        if value["channel_values"] is None:
+                            value["channel_values"] = []
+                        self._migrate_pending_sends(
+                            sends["sends"],
+                            value["checkpoint"],
+                            value["channel_values"],
+                        )
+            for value in values:
+                yield await self._load_checkpoint_tuple(value)

-    async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    async def aget_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
        """Get a checkpoint tuple from the database asynchronously.

        This method retrieves a checkpoint tuple from the Postgres database based on the
@@ -191,36 +195,26 @@ class AsyncPostgresSaver(BasePostgresSaver):
                args,
                binary=True,
            )
+            value = await cur.fetchone()
+            if value is None:
+                return None

-            async for value in cur:
-                return CheckpointTuple(
-                    {
-                        "configurable": {
-                            "thread_id": thread_id,
-                            "checkpoint_ns": checkpoint_ns,
-                            "checkpoint_id": value["checkpoint_id"],
-                        }
-                    },
-                    await asyncio.to_thread(
-                        self._load_checkpoint,
+            # migrate pending sends if necessary
+            if value["checkpoint"]["v"] < 4 and value["parent_checkpoint_id"]:
+                await cur.execute(
+                    self.SELECT_PENDING_SENDS_SQL,
+                    (thread_id, [value["parent_checkpoint_id"]]),
+                )
+                if sends := await cur.fetchone():
+                    if value["channel_values"] is None:
+                        value["channel_values"] = []
+                    self._migrate_pending_sends(
+                        sends["sends"],
                        value["checkpoint"],
                        value["channel_values"],
-                        value["pending_sends"],
-                    ),
-                    self._load_metadata(value["metadata"]),
-                    (
-                        {
-                            "configurable": {
-                                "thread_id": thread_id,
-                                "checkpoint_ns": checkpoint_ns,
-                                "checkpoint_id": value["parent_checkpoint_id"],
-                            }
-                        }
-                        if value["parent_checkpoint_id"]
-                        else None
-                    ),
-                    await asyncio.to_thread(self._load_writes, value["pending_writes"]),
-                )
+                    )
+
+            return await self._load_checkpoint_tuple(value)

    async def aput(
        self,
@@ -277,8 +271,8 @@ class AsyncPostgresSaver(BasePostgresSaver):
                    checkpoint_ns,
                    checkpoint["id"],
                    checkpoint_id,
-                    Jsonb(self._dump_checkpoint(copy)),
-                    self._dump_metadata(get_checkpoint_metadata(config, metadata)),
+                    Jsonb(copy),
+                    Jsonb(get_checkpoint_metadata(config, metadata)),
                ),
            )
        return next_config
@@ -350,7 +344,7 @@ class AsyncPostgresSaver(BasePostgresSaver):
                Will be applied regardless of whether the AsyncPostgresSaver instance was initialized with a pipeline.
                If pipeline mode is not supported, will fall back to using transaction context manager.
        """
-        async with _ainternal.get_connection(self.conn) as conn:
+        async with self.lock, _ainternal.get_connection(self.conn) as conn:
            if self.pipe:
                # a connection in pipeline mode can be used concurrently
                # in multiple threads/coroutines, but only one cursor can be
@@ -366,7 +360,6 @@ class AsyncPostgresSaver(BasePostgresSaver):
                # thread/coroutine at a time, so we acquire a lock
                if self.supports_pipeline:
                    async with (
-                        self.lock,
                        conn.pipeline(),
                        conn.cursor(binary=True, row_factory=dict_row) as cur,
                    ):
@@ -374,25 +367,60 @@ class AsyncPostgresSaver(BasePostgresSaver):
                else:
                    # Use connection's transaction context manager when pipeline mode not supported
                    async with (
-                        self.lock,
                        conn.transaction(),
                        conn.cursor(binary=True, row_factory=dict_row) as cur,
                    ):
                        yield cur
            else:
-                async with (
-                    self.lock,
-                    conn.cursor(binary=True, row_factory=dict_row) as cur,
-                ):
+                async with conn.cursor(binary=True, row_factory=dict_row) as cur:
                    yield cur

+    async def _load_checkpoint_tuple(self, value: DictRow) -> CheckpointTuple:
+        """
+        Convert a database row into a CheckpointTuple object.
+
+        Args:
+            value: A row from the database containing checkpoint data.
+
+        Returns:
+            CheckpointTuple: A structured representation of the checkpoint,
+            including its configuration, metadata, parent checkpoint (if any),
+            and pending writes.
+        """
+        return CheckpointTuple(
+            {
+                "configurable": {
+                    "thread_id": value["thread_id"],
+                    "checkpoint_ns": value["checkpoint_ns"],
+                    "checkpoint_id": value["checkpoint_id"],
+                }
+            },
+            {
+                **value["checkpoint"],
+                "channel_values": self._load_blobs(value["channel_values"]),
+            },
+            value["metadata"],
+            (
+                {
+                    "configurable": {
+                        "thread_id": value["thread_id"],
+                        "checkpoint_ns": value["checkpoint_ns"],
+                        "checkpoint_id": value["parent_checkpoint_id"],
+                    }
+                }
+                if value["parent_checkpoint_id"]
+                else None
+            ),
+            await asyncio.to_thread(self._load_writes, value["pending_writes"]),
+        )
+
    def list(
        self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
        *,
-        filter: Optional[dict[str, Any]] = None,
-        before: Optional[RunnableConfig] = None,
-        limit: Optional[int] = None,
+        filter: dict[str, Any] | None = None,
+        before: RunnableConfig | None = None,
+        limit: int | None = None,
    ) -> Iterator[CheckpointTuple]:
        """List checkpoints from the database.

@@ -430,7 +458,7 @@ class AsyncPostgresSaver(BasePostgresSaver):
            except StopAsyncIteration:
                break

-    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+    def get_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
        """Get a checkpoint tuple from the database.

        This method retrieves a checkpoint tuple from the Postgres database based on the
@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import random
 from collections.abc import Sequence
 from typing import Any, Optional, cast
@@ -9,12 +11,9 @@ from langgraph.checkpoint.base import (
    WRITES_IDX_MAP,
    BaseCheckpointSaver,
    ChannelVersions,
-    Checkpoint,
-    CheckpointMetadata,
    get_checkpoint_id,
 )
-from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
-from langgraph.checkpoint.serde.types import TASKS, ChannelProtocol
+from langgraph.checkpoint.serde.types import TASKS

 MetadataInput = Optional[dict[str, Any]]

@@ -72,7 +71,7 @@ MIGRATIONS = [
    """ALTER TABLE checkpoint_writes ADD COLUMN task_path TEXT NOT NULL DEFAULT '';""",
 ]

-SELECT_SQL = f"""
+SELECT_SQL = """
 select
    thread_id,
    checkpoint,
@@ -96,17 +95,20 @@ select
        where cw.thread_id = checkpoints.thread_id
            and cw.checkpoint_ns = checkpoints.checkpoint_ns
            and cw.checkpoint_id = checkpoints.checkpoint_id
-    ) as pending_writes,
-    (
-        select array_agg(array[cw.type::bytea, cw.blob] order by cw.task_path, cw.task_id, cw.idx)
-        from checkpoint_writes cw
-        where cw.thread_id = checkpoints.thread_id
-            and cw.checkpoint_ns = checkpoints.checkpoint_ns
-            and cw.checkpoint_id = checkpoints.parent_checkpoint_id
-            and cw.channel = '{TASKS}'
-    ) as pending_sends
+    ) as pending_writes
 from checkpoints """

+SELECT_PENDING_SENDS_SQL = f"""
+select
+    checkpoint_id,
+    array_agg(array[type::bytea, blob] order by task_path, task_id, idx) as sends
+from checkpoint_writes
+where thread_id = %s
+    and checkpoint_id = any(%s)
+    and channel = '{TASKS}'
+group by checkpoint_id
+"""
+
 UPSERT_CHECKPOINT_BLOBS_SQL = """
    INSERT INTO checkpoint_blobs (thread_id, checkpoint_ns, channel, version, type, blob)
    VALUES (%s, %s, %s, %s, %s, %s)
@@ -140,31 +142,34 @@ INSERT_CHECKPOINT_WRITES_SQL = """

 class BasePostgresSaver(BaseCheckpointSaver[str]):
    SELECT_SQL = SELECT_SQL
+    SELECT_PENDING_SENDS_SQL = SELECT_PENDING_SENDS_SQL
    MIGRATIONS = MIGRATIONS
    UPSERT_CHECKPOINT_BLOBS_SQL = UPSERT_CHECKPOINT_BLOBS_SQL
    UPSERT_CHECKPOINTS_SQL = UPSERT_CHECKPOINTS_SQL
    UPSERT_CHECKPOINT_WRITES_SQL = UPSERT_CHECKPOINT_WRITES_SQL
    INSERT_CHECKPOINT_WRITES_SQL = INSERT_CHECKPOINT_WRITES_SQL

-    jsonplus_serde = JsonPlusSerializer()
    supports_pipeline: bool

-    def _load_checkpoint(
+    def _migrate_pending_sends(
        self,
+        pending_sends: list[tuple[bytes, bytes]],
        checkpoint: dict[str, Any],
        channel_values: list[tuple[bytes, bytes, bytes]],
-        pending_sends: list[tuple[bytes, bytes]],
-    ) -> Checkpoint:
-        return {
-            **checkpoint,
-            "pending_sends": [
-                self.serde.loads_typed((c.decode(), b)) for c, b in pending_sends or []
-            ],
-            "channel_values": self._load_blobs(channel_values),
-        }
-
-    def _dump_checkpoint(self, checkpoint: Checkpoint) -> dict[str, Any]:
-        return {**checkpoint, "pending_sends": []}
+    ) -> None:
+        if not pending_sends:
+            return
+        # add to values
+        enc, blob = self.serde.dumps_typed(
+            [self.serde.loads_typed((c.decode(), b)) for c, b in pending_sends],
+        )
+        channel_values.append((TASKS.encode(), enc.encode(), blob))
+        # add to versions
+        checkpoint["channel_versions"][TASKS] = (
+            max(checkpoint["channel_versions"].values())
+            if checkpoint["channel_versions"]
+            else self.get_next_version(None, None)
+        )

    def _load_blobs(
        self, blob_values: list[tuple[bytes, bytes, bytes]]
@@ -183,7 +188,7 @@ class BasePostgresSaver(BaseCheckpointSaver[str]):
        checkpoint_ns: str,
        values: dict[str, Any],
        versions: ChannelVersions,
-    ) -> list[tuple[str, str, str, str, str, Optional[bytes]]]:
+    ) -> list[tuple[str, str, str, str, str, bytes | None]]:
        if not versions:
            return []

@@ -241,15 +246,7 @@ class BasePostgresSaver(BaseCheckpointSaver[str]):
            for idx, (channel, value) in enumerate(writes)
        ]

-    def _load_metadata(self, metadata: dict[str, Any]) -> CheckpointMetadata:
-        return self.jsonplus_serde.loads(self.jsonplus_serde.dumps(metadata))
-
-    def _dump_metadata(self, metadata: CheckpointMetadata) -> str:
-        serialized_metadata = self.jsonplus_serde.dumps(metadata)
-        # NOTE: we're using JSON serializer (not msgpack), so we need to remove null characters before writing
-        return serialized_metadata.decode().replace("\\u0000", "")
-
-    def get_next_version(self, current: Optional[str], channel: ChannelProtocol) -> str:
+    def get_next_version(self, current: str | None, channel: None) -> str:
        if current is None:
            current_v = 0
        elif isinstance(current, int):
@@ -262,9 +259,9 @@ class BasePostgresSaver(BaseCheckpointSaver[str]):

    def _search_where(
        self,
-        config: Optional[RunnableConfig],
+        config: RunnableConfig | None,
        filter: MetadataInput,
-        before: Optional[RunnableConfig] = None,
+        before: RunnableConfig | None = None,
    ) -> tuple[str, list[Any]]:
        """Return WHERE clause predicates for alist() given config, filter, before.

@@ -276,11 +276,16 @@ class ShallowPostgresSaver(BasePostgresSaver):
        with self._cursor() as cur:
            cur.execute(self.SELECT_SQL + where, args, binary=True)
            for value in cur:
-                checkpoint = self._load_checkpoint(
-                    value["checkpoint"],
-                    value["channel_values"],
-                    value["pending_sends"],
-                )
+                checkpoint: Checkpoint = {
+                    **value["checkpoint"],
+                    "channel_values": self._load_blobs(value["channel_values"]),
+                    "pending_sends": [
+                        self.serde.loads_typed((t.decode(), v))
+                        for t, v in value["pending_sends"]
+                    ]
+                    if value["pending_sends"]
+                    else [],
+                }
                yield CheckpointTuple(
                    config={
                        "configurable": {
@@ -290,7 +295,7 @@ class ShallowPostgresSaver(BasePostgresSaver):
                        }
                    },
                    checkpoint=checkpoint,
-                    metadata=self._load_metadata(value["metadata"]),
+                    metadata=value["metadata"],
                    pending_writes=self._load_writes(value["pending_writes"]),
                )

@@ -340,11 +345,16 @@ class ShallowPostgresSaver(BasePostgresSaver):
            )

            for value in cur:
-                checkpoint = self._load_checkpoint(
-                    value["checkpoint"],
-                    value["channel_values"],
-                    value["pending_sends"],
-                )
+                checkpoint: Checkpoint = {
+                    **value["checkpoint"],
+                    "channel_values": self._load_blobs(value["channel_values"]),
+                    "pending_sends": [
+                        self.serde.loads_typed((t.decode(), v))
+                        for t, v in value["pending_sends"]
+                    ]
+                    if value["pending_sends"]
+                    else [],
+                }
                return CheckpointTuple(
                    config={
                        "configurable": {
@@ -354,7 +364,7 @@ class ShallowPostgresSaver(BasePostgresSaver):
                        }
                    },
                    checkpoint=checkpoint,
-                    metadata=self._load_metadata(value["metadata"]),
+                    metadata=value["metadata"],
                    pending_writes=self._load_writes(value["pending_writes"]),
                )

@@ -430,8 +440,8 @@ class ShallowPostgresSaver(BasePostgresSaver):
                (
                    thread_id,
                    checkpoint_ns,
-                    Jsonb(self._dump_checkpoint(copy)),
-                    self._dump_metadata(get_checkpoint_metadata(config, metadata)),
+                    Jsonb(copy),
+                    Jsonb(get_checkpoint_metadata(config, metadata)),
                ),
            )
        return next_config
@@ -627,12 +637,16 @@ class AsyncShallowPostgresSaver(BasePostgresSaver):
        async with self._cursor() as cur:
            await cur.execute(self.SELECT_SQL + where, args, binary=True)
            async for value in cur:
-                checkpoint = await asyncio.to_thread(
-                    self._load_checkpoint,
-                    value["checkpoint"],
-                    value["channel_values"],
-                    value["pending_sends"],
-                )
+                checkpoint: Checkpoint = {
+                    **value["checkpoint"],
+                    "channel_values": self._load_blobs(value["channel_values"]),
+                    "pending_sends": [
+                        self.serde.loads_typed((t.decode(), v))
+                        for t, v in value["pending_sends"]
+                    ]
+                    if value["pending_sends"]
+                    else [],
+                }
                yield CheckpointTuple(
                    config={
                        "configurable": {
@@ -642,7 +656,7 @@ class AsyncShallowPostgresSaver(BasePostgresSaver):
                        }
                    },
                    checkpoint=checkpoint,
-                    metadata=self._load_metadata(value["metadata"]),
+                    metadata=value["metadata"],
                    pending_writes=await asyncio.to_thread(
                        self._load_writes, value["pending_writes"]
                    ),
@@ -673,12 +687,16 @@ class AsyncShallowPostgresSaver(BasePostgresSaver):
            )

            async for value in cur:
-                checkpoint = await asyncio.to_thread(
-                    self._load_checkpoint,
-                    value["checkpoint"],
-                    value["channel_values"],
-                    value["pending_sends"],
-                )
+                checkpoint: Checkpoint = {
+                    **value["checkpoint"],
+                    "channel_values": self._load_blobs(value["channel_values"]),
+                    "pending_sends": [
+                        self.serde.loads_typed((t.decode(), v))
+                        for t, v in value["pending_sends"]
+                    ]
+                    if value["pending_sends"]
+                    else [],
+                }
                return CheckpointTuple(
                    config={
                        "configurable": {
@@ -688,7 +706,7 @@ class AsyncShallowPostgresSaver(BasePostgresSaver):
                        }
                    },
                    checkpoint=checkpoint,
-                    metadata=self._load_metadata(value["metadata"]),
+                    metadata=value["metadata"],
                    pending_writes=await asyncio.to_thread(
                        self._load_writes, value["pending_writes"]
                    ),
@@ -755,8 +773,8 @@ class AsyncShallowPostgresSaver(BasePostgresSaver):
                (
                    thread_id,
                    checkpoint_ns,
-                    Jsonb(self._dump_checkpoint(copy)),
-                    self._dump_metadata(get_checkpoint_metadata(config, metadata)),
+                    Jsonb(copy),
+                    Jsonb(get_checkpoint_metadata(config, metadata)),
                ),
            )
        return next_config
@@ -1,9 +1,11 @@
+from __future__ import annotations
+
 import asyncio
 import logging
 from collections.abc import AsyncIterator, Iterable, Sequence
 from contextlib import asynccontextmanager
 from types import TracebackType
-from typing import Any, Callable, Optional, Union, cast
+from typing import Any, Callable, cast

 import orjson
 from psycopg import AsyncConnection, AsyncCursor, AsyncPipeline, Capabilities
@@ -132,12 +134,10 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
        self,
        conn: _ainternal.Conn,
        *,
-        pipe: Optional[AsyncPipeline] = None,
-        deserializer: Optional[
-            Callable[[Union[bytes, orjson.Fragment]], dict[str, Any]]
-        ] = None,
-        index: Optional[PostgresIndexConfig] = None,
-        ttl: Optional[TTLConfig] = None,
+        pipe: AsyncPipeline | None = None,
+        deserializer: Callable[[bytes | orjson.Fragment], dict[str, Any]] | None = None,
+        index: PostgresIndexConfig | None = None,
+        ttl: TTLConfig | None = None,
    ) -> None:
        if isinstance(conn, AsyncConnectionPool) and pipe is not None:
            raise ValueError(
@@ -157,7 +157,7 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
            self.embeddings = None

        self.ttl_config = ttl
-        self._ttl_sweeper_task: Optional[asyncio.Task[None]] = None
+        self._ttl_sweeper_task: asyncio.Task[None] | None = None
        self._ttl_stop_event = asyncio.Event()

    async def abatch(self, ops: Iterable[Op]) -> list[Result]:
@@ -180,10 +180,10 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
        conn_string: str,
        *,
        pipeline: bool = False,
-        pool_config: Optional[PoolConfig] = None,
-        index: Optional[PostgresIndexConfig] = None,
-        ttl: Optional[TTLConfig] = None,
-    ) -> AsyncIterator["AsyncPostgresStore"]:
+        pool_config: PoolConfig | None = None,
+        index: PostgresIndexConfig | None = None,
+        ttl: TTLConfig | None = None,
+    ) -> AsyncIterator[AsyncPostgresStore]:
        """Create a new AsyncPostgresStore instance from a connection string.

        Args:
@@ -289,7 +289,7 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
            return deleted_count

    async def start_ttl_sweeper(
-        self, sweep_interval_minutes: Optional[int] = None
+        self, sweep_interval_minutes: int | None = None
    ) -> asyncio.Task[None]:
        """Periodically delete expired store items based on TTL.

@@ -334,7 +334,7 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con
        self._ttl_sweeper_task = task
        return task

-    async def stop_ttl_sweeper(self, timeout: Optional[float] = None) -> bool:
+    async def stop_ttl_sweeper(self, timeout: float | None = None) -> bool:
        """Stop the TTL sweeper task if it's running.

        Args:
@@ -369,14 +369,14 @@ class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Con

        return success

-    async def __aenter__(self) -> "AsyncPostgresStore":
+    async def __aenter__(self) -> AsyncPostgresStore:
        return self

    async def __aexit__(
        self,
-        exc_type: Optional[type[BaseException]],
-        exc_val: Optional[BaseException],
-        exc_tb: Optional["TracebackType"],
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: TracebackType | None,
    ) -> None:
        # Ensure the TTL sweeper task is stopped when exiting the context
        if hasattr(self, "_ttl_sweeper_task") and self._ttl_sweeper_task is not None:
--- a/Show More
+++ b/Show More