Add memory how-to (#2629)

docs/docs/how-tos/memory/semantic-search.ipynb

@@ -0,0 +1,424 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to add semantic search to your agent's memory\n",
+    "\n",
+    "This guide shows how to enable semantic search in your agent's memory store. This lets search for items in the store by semantic similarity.\n",
+    "\n",
+    "First, install this guide's prerequisites."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%capture --no-stderr\n",
+    "%pip install -U langgraph langchain-openai langchain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "\n",
+    "def _set_env(var: str):\n",
+    "    if not os.environ.get(var):\n",
+    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
+    "\n",
+    "\n",
+    "_set_env(\"OPENAI_API_KEY\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Next, create the store."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import init_embeddings\n",
+    "from langgraph.store.memory import InMemoryStore\n",
+    "\n",
+    "# Create store with semantic search enabled\n",
+    "embeddings = init_embeddings(\"openai:text-embedding-3-small\")\n",
+    "store = InMemoryStore(\n",
+    "    index={\n",
+    "        \"embed\": embeddings,\n",
+    "        \"dims\": 1536,\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now let's store some memories:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Store some memories\n",
+    "store.put((\"user_123\", \"memories\"), \"1\", {\"text\": \"I love pizza\"})\n",
+    "store.put((\"user_123\", \"memories\"), \"2\", {\"text\": \"I prefer Italian food\"})\n",
+    "store.put((\"user_123\", \"memories\"), \"3\", {\"text\": \"I don't like spicy food\"})\n",
+    "store.put((\"user_123\", \"memories\"), \"3\", {\"text\": \"I am studying econometrics\"})\n",
+    "store.put((\"user_123\", \"memories\"), \"3\", {\"text\": \"I am a plumber\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Search memories using natural language:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Memory: I prefer Italian food (similarity: 0.46482669521168163)\n",
+      "Memory: I love pizza (similarity: 0.35514845174380766)\n",
+      "Memory: I am a plumber (similarity: 0.155698702336571)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Find memories about food preferences\n",
+    "memories = store.search((\"user_123\", \"memories\"), query=\"I like food?\", limit=5)\n",
+    "\n",
+    "for memory in memories:\n",
+    "    print(f'Memory: {memory.value[\"text\"]} (similarity: {memory.score})')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Using in your agent\n",
+    "\n",
+    "Add semantic search to any node by injecting the store:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import uuid\n",
+    "from typing import Optional\n",
+    "\n",
+    "from langchain.chat_models import init_chat_model\n",
+    "from langchain_core.tools import InjectedToolArg\n",
+    "from langgraph.store.base import BaseStore\n",
+    "from typing_extensions import Annotated\n",
+    "\n",
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "\n",
+    "def add_memories(state, *, store: BaseStore):\n",
+    "    # Search based on user's last message\n",
+    "    items = store.search(\n",
+    "        (\"user_123\", \"memories\"), query=state[\"messages\"][-1].content, limit=2\n",
+    "    )\n",
+    "    memories = \"\\n\".join(item.value[\"text\"] for item in items)\n",
+    "    memories = f\"## Memories of user\\n{memories}\" if memories else \"\"\n",
+    "    return [\n",
+    "        {\"role\": \"system\", \"content\": f\"You are a helpful assistant.\\n{memories}\"}\n",
+    "    ] + state[\"messages\"]\n",
+    "\n",
+    "\n",
+    "def upsert_memory(\n",
+    "    content: str,\n",
+    "    *,\n",
+    "    memory_id: Optional[uuid.UUID] = None,\n",
+    "    store: Annotated[BaseStore, InjectedToolArg],\n",
+    "):\n",
+    "    \"\"\"Upsert a memory in the database.\"\"\"\n",
+    "    mem_id = memory_id or uuid.uuid4()\n",
+    "    store.put(\n",
+    "        (\"user_123\", \"memories\"),\n",
+    "        key=str(mem_id),\n",
+    "        value={\"text\": content},\n",
+    "    )\n",
+    "    return f\"Stored memory {mem_id}\"\n",
+    "\n",
+    "\n",
+    "agent = create_react_agent(\n",
+    "    init_chat_model(\"openai:gpt-4o-mini\"),\n",
+    "    tools=[upsert_memory],\n",
+    "    state_modifier=add_memories,\n",
+    "    store=store,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "What are you in the mood for? Since you love Italian food and pizza, would you like some recommendations for a delicious pizza or a different Italian dish?"
+     ]
+    }
+   ],
+   "source": [
+    "async for message, metadata in agent.astream(\n",
+    "    input={\"messages\": [{\"role\": \"user\", \"content\": \"I'm hungry\"}]},\n",
+    "    stream_mode=\"messages\",\n",
+    "):\n",
+    "    print(message.content, end=\"\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Advanced Usage\n",
+    "\n",
+    "#### Multi-vector indexing\n",
+    "\n",
+    "Store and search different aspects of memories separately to improve recall or omit certain fields from being indexed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Configure store to embed both memory content and emotional context\n",
+    "store = InMemoryStore(\n",
+    "    index={\"embed\": embeddings, \"dims\": 1536, \"fields\": [\"memory\", \"emotional_context\"]}\n",
+    ")\n",
+    "# Store memories with different content/emotion pairs\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem1\",\n",
+    "    {\n",
+    "        \"memory\": \"Had pizza with friends at Mario's\",\n",
+    "        \"emotional_context\": \"felt happy and connected\",\n",
+    "        \"this_isnt_indexed\": \"I prefer ravioli though\",\n",
+    "    },\n",
+    ")\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem2\",\n",
+    "    {\n",
+    "        \"memory\": \"Ate alone at home\",\n",
+    "        \"emotional_context\": \"felt a bit lonely\",\n",
+    "        \"this_isnt_indexed\": \"I like pie\",\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "# Search focusing on emotional state - matches mem2\n",
+    "results = store.search(\n",
+    "    (\"user_123\", \"memories\"), query=\"times they felt isolated\", limit=1\n",
+    ")\n",
+    "print(\"Expect mem 2\")\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Emotion: {r.value['emotional_context']}\\n\")\n",
+    "\n",
+    "# Search focusing on social eating - matches mem1\n",
+    "print(\"Expect mem1\")\n",
+    "results = store.search((\"user_123\", \"memories\"), query=\"fun pizza\", limit=1)\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Emotion: {r.value['emotional_context']}\\n\")\n",
+    "\n",
+    "print(\"Expect random lower score (ravioli not indexed)\")\n",
+    "results = store.search((\"user_123\", \"memories\"), query=\"ravioli\", limit=1)\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Emotion: {r.value['emotional_context']}\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Override fields at storage time\n",
+    "You can override which fields to embed when storing a specific memory using `put(..., index=[...fields])`, regardless of the store's default configuration."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Expect mem1\n",
+      "Item: mem1; Score (0.3374698138722726)\n",
+      "Memory: I love spicy food\n",
+      "Context: At a Thai restaurant\n",
+      "\n",
+      "Expect mem2\n",
+      "Item: mem2; Score (0.3679447999059255)\n",
+      "Memory: The restaurant was too loud\n",
+      "Context: Dinner at an Italian place\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = init_embeddings(\"openai:text-embedding-3-small\")\n",
+    "store = InMemoryStore(\n",
+    "    index={\n",
+    "        \"embed\": embeddings,\n",
+    "        \"dims\": 1536,\n",
+    "        \"fields\": [\"memory\"],\n",
+    "    }  # Default to embed memory field\n",
+    ")\n",
+    "\n",
+    "# Store one memory with default indexing\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem1\",\n",
+    "    {\"memory\": \"I love spicy food\", \"context\": \"At a Thai restaurant\"},\n",
+    ")\n",
+    "\n",
+    "# Store another overriding which fields to embed\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem2\",\n",
+    "    {\"memory\": \"The restaurant was too loud\", \"context\": \"Dinner at an Italian place\"},\n",
+    "    index=[\"context\"],  # Override: only embed the context\n",
+    ")\n",
+    "\n",
+    "# Search about food - matches mem1 (using default field)\n",
+    "print(\"Expect mem1\")\n",
+    "results = store.search(\n",
+    "    (\"user_123\", \"memories\"), query=\"what food do they like\", limit=1\n",
+    ")\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Context: {r.value['context']}\\n\")\n",
+    "\n",
+    "# Search about restaurant atmosphere - matches mem2 (using overridden field)\n",
+    "print(\"Expect mem2\")\n",
+    "results = store.search(\n",
+    "    (\"user_123\", \"memories\"), query=\"restaurant environment\", limit=1\n",
+    ")\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Context: {r.value['context']}\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Disable Indexing for Specific Memories\n",
+    "\n",
+    "Some memories shouldn't be searchable by content. You can disable indexing for these while still storing them using \n",
+    "`put(..., index=False)`. Example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "store = InMemoryStore(index={\"embed\": embeddings, \"dims\": 1536, \"fields\": [\"memory\"]})\n",
+    "\n",
+    "# Store a normal indexed memory\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem1\",\n",
+    "    {\"memory\": \"I love chocolate ice cream\", \"type\": \"preference\"},\n",
+    ")\n",
+    "\n",
+    "# Store a system memory without indexing\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem2\",\n",
+    "    {\"memory\": \"User completed onboarding\", \"type\": \"system\"},\n",
+    "    index=False,  # Disable indexing entirely\n",
+    ")\n",
+    "\n",
+    "# Search about food preferences - finds mem1\n",
+    "print(\"Expect mem1\")\n",
+    "results = store.search((\"user_123\", \"memories\"), query=\"what food preferences\", limit=1)\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Type: {r.value['type']}\\n\")\n",
+    "\n",
+    "# Search about onboarding - won't find mem2 (not indexed)\n",
+    "print(\"Expect low score (mem2 not indexed)\")\n",
+    "results = store.search((\"user_123\", \"memories\"), query=\"onboarding status\", limit=1)\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Type: {r.value['type']}\\n\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/mkdocs.yml

@@ -164,6 +164,7 @@ nav:
             - how-tos/memory/manage-conversation-history.ipynb
             - how-tos/memory/delete-messages.ipynb
             - how-tos/memory/add-summary-conversation-history.ipynb
+            - how-tos/memory/semantic-search.ipynb
         - Human-in-the-loop:
             - Human-in-the-loop: how-tos#human-in-the-loop
             - how-tos/human_in_the_loop/breakpoints.ipynb

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -2862,30 +2862,30 @@ adal = ["adal (>=1.0.2)"]
 
 [[package]]
 name = "langchain"
-version = "0.3.1"
+version = "0.3.9"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "langchain-0.3.1-py3-none-any.whl", hash = "sha256:94e5ee7464d4366e4b158aa5704953c39701ea237b9ed4b200096d49e83bb3ae"},
-    {file = "langchain-0.3.1.tar.gz", hash = "sha256:54d6e3abda2ec056875a231a418a4130ba7576e629e899067e499bfc847b7586"},
+    {file = "langchain-0.3.9-py3-none-any.whl", hash = "sha256:ade5a1fee2f94f2e976a6c387f97d62cc7f0b9f26cfe0132a41d2bda761e1045"},
+    {file = "langchain-0.3.9.tar.gz", hash = "sha256:4950c4ad627d0aa95ce6bda7de453e22059b7e7836b562a8f781fb0b05d7294c"},
 ]
 
 [package.dependencies]
 aiohttp = ">=3.8.3,<4.0.0"
 async-timeout = {version = ">=4.0.0,<5.0.0", markers = "python_version < \"3.11\""}
-langchain-core = ">=0.3.6,<0.4.0"
+langchain-core = ">=0.3.21,<0.4.0"
 langchain-text-splitters = ">=0.3.0,<0.4.0"
 langsmith = ">=0.1.17,<0.2.0"
 numpy = [
-    {version = ">=1,<2", markers = "python_version < \"3.12\""},
-    {version = ">=1.26.0,<2.0.0", markers = "python_version >= \"3.12\""},
+    {version = ">=1.22.4,<2", markers = "python_version < \"3.12\""},
+    {version = ">=1.26.2,<3", markers = "python_version >= \"3.12\""},
 ]
 pydantic = ">=2.7.4,<3.0.0"
 PyYAML = ">=5.3"
 requests = ">=2,<3"
 SQLAlchemy = ">=1.4,<3"
-tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
+tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<10"
 
 [[package]]
 name = "langchain-anthropic"
@@ -2933,13 +2933,13 @@ tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
 
 [[package]]
 name = "langchain-core"
-version = "0.3.15"
+version = "0.3.21"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "langchain_core-0.3.15-py3-none-any.whl", hash = "sha256:3d4ca6dbb8ed396a6ee061063832a2451b0ce8c345570f7b086ffa7288e4fa29"},
-    {file = "langchain_core-0.3.15.tar.gz", hash = "sha256:b1a29787a4ffb7ec2103b4e97d435287201da7809b369740dd1e32f176325aba"},
+    {file = "langchain_core-0.3.21-py3-none-any.whl", hash = "sha256:7e723dff80946a1198976c6876fea8326dc82566ef9bcb5f8d9188f738733665"},
+    {file = "langchain_core-0.3.21.tar.gz", hash = "sha256:561b52b258ffa50a9fb11d7a1940ebfd915654d1ec95b35e81dfd5ee84143411"},
 ]
 
 [package.dependencies]
@@ -3035,7 +3035,7 @@ langchain-core = ">=0.3.0,<0.4.0"
 
 [[package]]
 name = "langgraph"
-version = "0.2.52"
+version = "0.2.54"
 description = "Building stateful, multi-actor applications with LLMs"
 optional = false
 python-versions = ">=3.9.0,<4.0"
@@ -3045,7 +3045,7 @@ develop = true
 [package.dependencies]
 langchain-core = ">=0.2.43,<0.4.0,!=0.3.0,!=0.3.1,!=0.3.2,!=0.3.3,!=0.3.4,!=0.3.5,!=0.3.6,!=0.3.7,!=0.3.8,!=0.3.9,!=0.3.10,!=0.3.11,!=0.3.12,!=0.3.13,!=0.3.14"
 langgraph-checkpoint = "^2.0.4"
-langgraph-sdk = "^0.1.32"
+langgraph-sdk = "^0.1.42"
 
 [package.source]
 type = "directory"
@@ -3053,7 +3053,7 @@ url = "libs/langgraph"
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "2.0.5"
+version = "2.0.8"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -3070,7 +3070,7 @@ url = "libs/checkpoint"
 
 [[package]]
 name = "langgraph-checkpoint-postgres"
-version = "2.0.3"
+version = "2.0.7"
 description = "Library with a Postgres implementation of LangGraph checkpoint saver."
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -3078,10 +3078,10 @@ files = []
 develop = true
 
 [package.dependencies]
-langgraph-checkpoint = "^2.0.2"
+langgraph-checkpoint = "^2.0.7"
 orjson = ">=3.10.1"
-psycopg = "^3.0.0"
-psycopg-pool = "^3.0.0"
+psycopg = "^3.2.0"
+psycopg-pool = "^3.2.0"
 
 [package.source]
 type = "directory"
@@ -3106,7 +3106,7 @@ url = "libs/checkpoint-sqlite"
 
 [[package]]
 name = "langgraph-sdk"
-version = "0.1.36"
+version = "0.1.42"
 description = "SDK for interacting with LangGraph API"
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -3115,7 +3115,6 @@ develop = true
 
 [package.dependencies]
 httpx = ">=0.25.2"
-httpx-sse = ">=0.4.0"
 orjson = ">=3.10.1"
 
 [package.source]
@@ -3586,7 +3585,6 @@ optional = false
 python-versions = ">=3.6"
 files = [
     {file = "mkdocs-redirects-1.2.1.tar.gz", hash = "sha256:9420066d70e2a6bb357adf86e67023dcdca1857f97f07c7fe450f8f1fb42f861"},
-    {file = "mkdocs_redirects-1.2.1-py3-none-any.whl", hash = "sha256:497089f9e0219e7389304cffefccdfa1cac5ff9509f2cb706f4c9b221726dffb"},
 ]
 
 [package.dependencies]
@@ -6964,7 +6962,6 @@ description = "Automatically mock your HTTP interactions to simplify and speed u
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "vcrpy-6.0.1-py2.py3-none-any.whl", hash = "sha256:621c3fb2d6bd8aa9f87532c688e4575bcbbde0c0afeb5ebdb7e14cac409edfdd"},
     {file = "vcrpy-6.0.1.tar.gz", hash = "sha256:9e023fee7f892baa0bbda2f7da7c8ac51165c1c6e38ff8688683a12a4bde9278"},
 ]
 
@@ -7476,4 +7473,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "776ee42630769f08e3896338f18ec81830166695d32d2208dc31dedb22d3b22d"
+content-hash = "cf18eed5e183fc4f7786d095540b6c9261e130750f2d1fcc427e08b78d522c61"

pyproject.toml

@@ -34,7 +34,7 @@ ruff = "^0.6.8"
 jupyter = "^1.1.1"
 
 [tool.poetry.group.test.dependencies]
-langchain = "^0.3.1"
+langchain = "^0.3.8"
 langchain-openai = "^0.2.0"
 langchain-anthropic = "^0.2.1"
 langchain-nomic = "^0.1.3"