checkpoint-postgres: vbump & add a note to readme (#1295)

* review tool calls

* spelling

* link

* link

---------

Co-authored-by: isaac hershenson <ihershenson@hmc.edu>

docs/_scripts/copy_notebooks.py

@@ -59,6 +59,7 @@ _MANUAL = {
         "human_in_the_loop/time-travel.ipynb",
         "human_in_the_loop/edit-graph-state.ipynb",
         "human_in_the_loop/wait-user-input.ipynb",
+        "human_in_the_loop/review-tool-calls.ipynb",
         "node-retries.ipynb",
     ],
     "tutorials": [

docs/docs/concepts/low_level.md

@@ -52,7 +52,11 @@ By default, all nodes in the graph will share the same state. This means that th
 
 ### Reducers
 
-Reducers are key to understanding how updates from nodes are applied to the `State`. Each key in the `State` has its own independent reducer function. If no reducer function is explicitly specified then it is assumed that all updates to that key should override it. Let's take a look at a few examples to understand them better.
+Reducers are key to understanding how updates from nodes are applied to the `State`. Each key in the `State` has its own independent reducer function. If no reducer function is explicitly specified then it is assumed that all updates to that key should override it. There are a few different types of reducers, starting with the default type of reducer:
+
+#### Default Reducer
+
+These two examples show how to use the default reducer:
 
 **Example A:**
 
@@ -79,6 +83,10 @@ class State(TypedDict):
 
 In this example, we've used the `Annotated` type to specify a reducer function (`operator.add`) for the second key (`bar`). Note that the first key remains unchanged. Let's assume the input to the graph is `{"foo": 1, "bar": ["hi"]}`. Let's then assume the first `Node` returns `{"foo": 2}`. This is treated as an update to the state. Notice that the `Node` does not need to return the whole `State` schema - just an update. After applying this update, the `State` would then be `{"foo": 2, "bar": ["hi"]}`. If the second node returns `{"bar": ["bye"]}` then the `State` would then be `{"foo": 2, "bar": ["hi", "bye"]}`. Notice here that the `bar` key is updated by adding the two lists together.
 
+#### Context Reducer
+
+You can use `Context` channels to define shared resources (such as database connections) that are managed outside of your graph's nodes and excluded from checkpointing. The context manager provided to the Context channel is entered before the first step of the graph execution and exited after the last step, allowing you to set up and clean up resources for the duration of the graph invocation. Read this [how to](https://langchain-ai.github.io/langgraph/how-tos/state-context-key) to see an example of using the `Context` channel in your graph.
+
 ### Working with Messages in Graph State
 
 #### Why use messages?

docs/docs/how-tos/index.md

@@ -25,7 +25,7 @@ LangGraph makes it easy to persist state across graph runs. The guide below show
 - [How to manage conversation history](memory/manage-conversation-history.ipynb)
 - [How to delete messages](memory/delete-messages.ipynb)
 - [How to add summary conversation memory](memory/add-summary-conversation-history.ipynb)
-- [How to create a custom checkpointer using Postgres](persistence_postgres.ipynb)
+- [How to use Postgres checkpointer for persistence](persistence_postgres.ipynb)
 - [How to create a custom checkpointer using MongoDB](persistence_mongodb.ipynb)
 - [How to create a custom checkpointer using Redis](persistence_redis.ipynb)
 
@@ -38,6 +38,7 @@ These guides cover common examples of that.
 - [How to edit graph state](human_in_the_loop/edit-graph-state.ipynb)
 - [How to wait for user input](human_in_the_loop/wait-user-input.ipynb)
 - [How to view and update past graph state](human_in_the_loop/time-travel.ipynb)
+- [Review tool calls](human_in_the_loop/review-tool-calls.ipynb)
 
 ## Streaming
 

docs/docs/reference/checkpoints.md

@@ -40,4 +40,15 @@ LangGraph also natively provides the following checkpoint implementations.
 ### SqliteSaver
 
 ::: langgraph.checkpoint.sqlite.SqliteSaver
+
+### AsyncPostgresSaver
+
+::: langgraph.checkpoint.postgres.aio.AsyncPostgresSaver
+
+### PostgresSaver
+
+::: langgraph.checkpoint.postgres.PostgresSaver
+handler: python
+
+
 handler: python

docs/mkdocs.yml

@@ -134,7 +134,7 @@ nav:
           - Manage conversation history: how-tos/memory/manage-conversation-history.ipynb
           - Delete messages: how-tos/memory/delete-messages.ipynb
           - Add summary of the conversation history: how-tos/memory/add-summary-conversation-history.ipynb
-          - Create custom checkpointer using Postgres: how-tos/persistence_postgres.ipynb
+          - Use Postgres checkpointer for persistence: how-tos/persistence_postgres.ipynb
           - Create custom checkpointer using MongoDB: how-tos/persistence_mongodb.ipynb
           - Create custom checkpointer using Redis: how-tos/persistence_redis.ipynb
       - Human-in-the-loop:
@@ -142,6 +142,7 @@ nav:
           - Wait for user input: how-tos/human_in_the_loop/wait-user-input.ipynb
           - View and update past graph state: how-tos/human_in_the_loop/time-travel.ipynb
           - Edit graph state: how-tos/human_in_the_loop/edit-graph-state.ipynb
+          - Review tool calls: how-tos/human_in_the_loop/review-tool-calls.ipynb
       - Streaming:
           - Stream full state: how-tos/stream-values.ipynb
           - Stream state updates: how-tos/stream-updates.ipynb

examples/chatbots/customer-support.ipynb

@@ -32,7 +32,10 @@
     "scrolled": true
    },
    "outputs": [],
-   "source": ["%%capture --no-stderr\n%pip install -U langgraph langchain-community langchain-openai scikit-learn"]
+   "source": [
+    "%%capture --no-stderr\n",
+    "%pip install -U langgraph langchain-community langchain-openai scikit-learn"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -48,7 +51,15 @@
    "id": "3d1ef253-6b0c-4481-868c-e1fe84f2c8ff",
    "metadata": {},
    "outputs": [],
-   "source": ["import requests\n\nurl = \"https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db\"\nresponse = requests.get(url)\n\nwith open(\"Chinook.db\", \"wb\") as file:\n    file.write(response.content)"]
+   "source": [
+    "import requests\n",
+    "\n",
+    "url = \"https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db\"\n",
+    "response = requests.get(url)\n",
+    "\n",
+    "with open(\"Chinook.db\", \"wb\") as file:\n",
+    "    file.write(response.content)"
+   ]
   },
   {
    "cell_type": "code",
@@ -77,7 +88,12 @@
      "output_type": "execute_result"
     }
    ],
-   "source": ["from langchain_community.utilities import SQLDatabase\n\ndb = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")\ndb.get_usable_table_names()"]
+   "source": [
+    "from langchain_community.utilities import SQLDatabase\n",
+    "\n",
+    "db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")\n",
+    "db.get_usable_table_names()"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -96,7 +112,11 @@
    "id": "d9ea4e80-30e6-4d46-b480-35f0be2fb055",
    "metadata": {},
    "outputs": [],
-   "source": ["from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(temperature=0, streaming=True, model=\"gpt-4o\")"]
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI(temperature=0, streaming=True, model=\"gpt-4o\")"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -118,7 +138,9 @@
    "id": "ea958e9f-ab1f-49b5-bd85-16332055297c",
    "metadata": {},
    "outputs": [],
-   "source": ["from langchain_core.messages import HumanMessage, SystemMessage"]
+   "source": [
+    "from langchain_core.messages import HumanMessage, SystemMessage"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -137,7 +159,12 @@
    "id": "975b039a",
    "metadata": {},
    "outputs": [],
-   "source": ["# This tool is given to the agent to look up information about a customer\ndef get_customer_info(customer_id: int):\n    \"\"\"Look up customer info given their ID. ALWAYS make sure you have the customer ID before invoking this.\"\"\"\n    return db.run(f\"SELECT * FROM Customer WHERE CustomerID = {customer_id};\")"]
+   "source": [
+    "# This tool is given to the agent to look up information about a customer\n",
+    "def get_customer_info(customer_id: int):\n",
+    "    \"\"\"Look up customer info given their ID. ALWAYS make sure you have the customer ID before invoking this.\"\"\"\n",
+    "    return db.run(f\"SELECT * FROM Customer WHERE CustomerID = {customer_id};\")"
+   ]
   },
   {
    "cell_type": "code",
@@ -145,7 +172,20 @@
    "id": "1d5fa446",
    "metadata": {},
    "outputs": [],
-   "source": ["customer_prompt = \"\"\"Your job is to help a user update their profile.\n\nYou only have certain tools you can use. These tools require specific input. If you don't know the required input, then ask the user for it.\n\nIf you are unable to help the user, you can \"\"\"\n\n\ndef get_customer_messages(messages):\n    return [SystemMessage(content=customer_prompt)] + messages\n\n\ncustomer_chain = get_customer_messages | model.bind_tools([get_customer_info])"]
+   "source": [
+    "customer_prompt = \"\"\"Your job is to help a user update their profile.\n",
+    "\n",
+    "You only have certain tools you can use. These tools require specific input. If you don't know the required input, then ask the user for it.\n",
+    "\n",
+    "If you are unable to help the user, you can \"\"\"\n",
+    "\n",
+    "\n",
+    "def get_customer_messages(messages):\n",
+    "    return [SystemMessage(content=customer_prompt)] + messages\n",
+    "\n",
+    "\n",
+    "customer_chain = get_customer_messages | model.bind_tools([get_customer_info])"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -166,7 +206,19 @@
    "id": "a8604a3b-b484-4b2b-a914-4236cb98c524",
    "metadata": {},
    "outputs": [],
-   "source": ["from langchain_community.vectorstores import SKLearnVectorStore\nfrom langchain_openai import OpenAIEmbeddings\n\nartists = db._execute(\"select * from Artist\")\nsongs = db._execute(\"select * from Track\")\nartist_retriever = SKLearnVectorStore.from_texts(\n    [a[\"Name\"] for a in artists], OpenAIEmbeddings(), metadatas=artists\n).as_retriever()\nsong_retriever = SKLearnVectorStore.from_texts(\n    [a[\"Name\"] for a in songs], OpenAIEmbeddings(), metadatas=songs\n).as_retriever()"]
+   "source": [
+    "from langchain_community.vectorstores import SKLearnVectorStore\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "artists = db._execute(\"select * from Artist\")\n",
+    "songs = db._execute(\"select * from Track\")\n",
+    "artist_retriever = SKLearnVectorStore.from_texts(\n",
+    "    [a[\"Name\"] for a in artists], OpenAIEmbeddings(), metadatas=artists\n",
+    ").as_retriever()\n",
+    "song_retriever = SKLearnVectorStore.from_texts(\n",
+    "    [a[\"Name\"] for a in songs], OpenAIEmbeddings(), metadatas=songs\n",
+    ").as_retriever()"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -182,7 +234,16 @@
    "id": "0a2a2b74",
    "metadata": {},
    "outputs": [],
-   "source": ["def get_albums_by_artist(artist):\n    \"\"\"Get albums by an artist (or similar artists).\"\"\"\n    docs = artist_retriever.get_relevant_documents(artist)\n    artist_ids = \", \".join([str(d.metadata[\"ArtistId\"]) for d in docs])\n    return db.run(\n        f\"SELECT Title, Name FROM Album LEFT JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Album.ArtistId in ({artist_ids});\",\n        include_columns=True,\n    )"]
+   "source": [
+    "def get_albums_by_artist(artist):\n",
+    "    \"\"\"Get albums by an artist (or similar artists).\"\"\"\n",
+    "    docs = artist_retriever.get_relevant_documents(artist)\n",
+    "    artist_ids = \", \".join([str(d.metadata[\"ArtistId\"]) for d in docs])\n",
+    "    return db.run(\n",
+    "        f\"SELECT Title, Name FROM Album LEFT JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Album.ArtistId in ({artist_ids});\",\n",
+    "        include_columns=True,\n",
+    "    )"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -198,7 +259,16 @@
    "id": "da533f50",
    "metadata": {},
    "outputs": [],
-   "source": ["def get_tracks_by_artist(artist):\n    \"\"\"Get songs by an artist (or similar artists).\"\"\"\n    docs = artist_retriever.invoke(artist)\n    artist_ids = \", \".join([str(d.metadata[\"ArtistId\"]) for d in docs])\n    return db.run(\n        f\"SELECT Track.Name as SongName, Artist.Name as ArtistName FROM Album LEFT JOIN Artist ON Album.ArtistId = Artist.ArtistId LEFT JOIN Track ON Track.AlbumId = Album.AlbumId WHERE Album.ArtistId in ({artist_ids});\",\n        include_columns=True,\n    )"]
+   "source": [
+    "def get_tracks_by_artist(artist):\n",
+    "    \"\"\"Get songs by an artist (or similar artists).\"\"\"\n",
+    "    docs = artist_retriever.invoke(artist)\n",
+    "    artist_ids = \", \".join([str(d.metadata[\"ArtistId\"]) for d in docs])\n",
+    "    return db.run(\n",
+    "        f\"SELECT Track.Name as SongName, Artist.Name as ArtistName FROM Album LEFT JOIN Artist ON Album.ArtistId = Artist.ArtistId LEFT JOIN Track ON Track.AlbumId = Album.AlbumId WHERE Album.ArtistId in ({artist_ids});\",\n",
+    "        include_columns=True,\n",
+    "    )"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -214,7 +284,11 @@
    "id": "b3c07010",
    "metadata": {},
    "outputs": [],
-   "source": ["def check_for_songs(song_title):\n    \"\"\"Check if a song exists by its name.\"\"\"\n    return song_retriever.invoke(song_title)"]
+   "source": [
+    "def check_for_songs(song_title):\n",
+    "    \"\"\"Check if a song exists by its name.\"\"\"\n",
+    "    return song_retriever.invoke(song_title)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -230,7 +304,23 @@
    "id": "72a14d5c",
    "metadata": {},
    "outputs": [],
-   "source": ["song_system_message = \"\"\"Your job is to help a customer find any songs they are looking for. \n\nYou only have certain tools you can use. If a customer asks you to look something up that you don't know how, politely tell them what you can help with.\n\nWhen looking up artists and songs, sometimes the artist/song will not be found. In that case, the tools will return information \\\non similar songs and artists. This is intentional, it is not the tool messing up.\"\"\"\n\n\ndef get_song_messages(messages):\n    return [SystemMessage(content=song_system_message)] + messages\n\n\nsong_recc_chain = get_song_messages | model.bind_tools(\n    [get_albums_by_artist, get_tracks_by_artist, check_for_songs]\n)"]
+   "source": [
+    "song_system_message = \"\"\"Your job is to help a customer find any songs they are looking for. \n",
+    "\n",
+    "You only have certain tools you can use. If a customer asks you to look something up that you don't know how, politely tell them what you can help with.\n",
+    "\n",
+    "When looking up artists and songs, sometimes the artist/song will not be found. In that case, the tools will return information \\\n",
+    "on similar songs and artists. This is intentional, it is not the tool messing up.\"\"\"\n",
+    "\n",
+    "\n",
+    "def get_song_messages(messages):\n",
+    "    return [SystemMessage(content=song_system_message)] + messages\n",
+    "\n",
+    "\n",
+    "song_recc_chain = get_song_messages | model.bind_tools(\n",
+    "    [get_albums_by_artist, get_tracks_by_artist, check_for_songs]\n",
+    ")"
+   ]
   },
   {
    "cell_type": "code",
@@ -249,7 +339,10 @@
      "output_type": "execute_result"
     }
    ],
-   "source": ["msgs = [HumanMessage(content=\"hi! can you help me find songs by amy whinehouse?\")]\nsong_recc_chain.invoke(msgs)"]
+   "source": [
+    "msgs = [HumanMessage(content=\"hi! can you help me find songs by amy whinehouse?\")]\n",
+    "song_recc_chain.invoke(msgs)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -267,7 +360,32 @@
    "id": "73e74268",
    "metadata": {},
    "outputs": [],
-   "source": ["from langchain_core.messages import AIMessage, HumanMessage, SystemMessage\nfrom langchain_core.pydantic_v1 import BaseModel, Field\n\n\nclass Router(BaseModel):\n    \"\"\"Call this if you are able to route the user to the appropriate representative.\"\"\"\n\n    choice: str = Field(description=\"should be one of: music, customer\")\n\n\nsystem_message = \"\"\"Your job is to help as a customer service representative for a music store.\n\nYou should interact politely with customers to try to figure out how you can help. You can help in a few ways:\n\n- Updating user information: if a customer wants to update the information in the user database. Call the router with `customer`\n- Recommending music: if a customer wants to find some music or information about music. Call the router with `music`\n\nIf the user is asking or wants to ask about updating or accessing their information, send them to that route.\nIf the user is asking or wants to ask about music, send them to that route.\nOtherwise, respond.\"\"\"\n\n\ndef get_messages(messages):\n    return [SystemMessage(content=system_message)] + messages"]
+   "source": [
+    "from langchain_core.messages import AIMessage, HumanMessage, SystemMessage\n",
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class Router(BaseModel):\n",
+    "    \"\"\"Call this if you are able to route the user to the appropriate representative.\"\"\"\n",
+    "\n",
+    "    choice: str = Field(description=\"should be one of: music, customer\")\n",
+    "\n",
+    "\n",
+    "system_message = \"\"\"Your job is to help as a customer service representative for a music store.\n",
+    "\n",
+    "You should interact politely with customers to try to figure out how you can help. You can help in a few ways:\n",
+    "\n",
+    "- Updating user information: if a customer wants to update the information in the user database. Call the router with `customer`\n",
+    "- Recommending music: if a customer wants to find some music or information about music. Call the router with `music`\n",
+    "\n",
+    "If the user is asking or wants to ask about updating or accessing their information, send them to that route.\n",
+    "If the user is asking or wants to ask about music, send them to that route.\n",
+    "Otherwise, respond.\"\"\"\n",
+    "\n",
+    "\n",
+    "def get_messages(messages):\n",
+    "    return [SystemMessage(content=system_message)] + messages"
+   ]
   },
   {
    "cell_type": "code",
@@ -275,7 +393,9 @@
    "id": "ddf27314",
    "metadata": {},
    "outputs": [],
-   "source": ["chain = get_messages | model.bind_tools([Router])"]
+   "source": [
+    "chain = get_messages | model.bind_tools([Router])"
+   ]
   },
   {
    "cell_type": "code",
@@ -294,7 +414,10 @@
      "output_type": "execute_result"
     }
    ],
-   "source": ["msgs = [HumanMessage(content=\"hi! can you help me find a good song?\")]\nchain.invoke(msgs)"]
+   "source": [
+    "msgs = [HumanMessage(content=\"hi! can you help me find a good song?\")]\n",
+    "chain.invoke(msgs)"
+   ]
   },
   {
    "cell_type": "code",
@@ -313,7 +436,10 @@
      "output_type": "execute_result"
     }
    ],
-   "source": ["msgs = [HumanMessage(content=\"hi! what's the email you have for me?\")]\nchain.invoke(msgs)"]
+   "source": [
+    "msgs = [HumanMessage(content=\"hi! what's the email you have for me?\")]\n",
+    "chain.invoke(msgs)"
+   ]
   },
   {
    "cell_type": "code",
@@ -321,7 +447,15 @@
    "id": "bd6ddd8b-7500-46a7-811d-3bcb937bda51",
    "metadata": {},
    "outputs": [],
-   "source": ["from langchain_core.messages import AIMessage\n\n\ndef add_name(message, name):\n    _dict = message.dict()\n    _dict[\"name\"] = name\n    return AIMessage(**_dict)"]
+   "source": [
+    "from langchain_core.messages import AIMessage\n",
+    "\n",
+    "\n",
+    "def add_name(message, name):\n",
+    "    _dict = message.dict()\n",
+    "    _dict[\"name\"] = name\n",
+    "    return AIMessage(**_dict)"
+   ]
   },
   {
    "cell_type": "code",
@@ -329,7 +463,45 @@
    "id": "27494de5-8345-4c23-bc0e-81e0dd5d47d8",
    "metadata": {},
    "outputs": [],
-   "source": ["import json\n\nfrom langgraph.graph import END, START\n\n\ndef _get_last_ai_message(messages):\n    for m in messages[::-1]:\n        if isinstance(m, AIMessage):\n            return m\n    return None\n\n\ndef _is_tool_call(msg):\n    return hasattr(msg, \"additional_kwargs\") and \"tool_calls\" in msg.additional_kwargs\n\n\ndef _route(messages):\n    last_message = messages[-1]\n    if isinstance(last_message, AIMessage):\n        if not last_message.tool_calls:\n            return END\n        else:\n            if last_message.name == \"general\":\n                if len(last_message.tool_calls) > 1:\n                    raise ValueError(\"Too many tools\")\n                return last_message.tool_calls[0][\"args\"][\"choice\"]\n            else:\n                return \"tools\"\n    last_m = _get_last_ai_message(messages)\n    if last_m is None:\n        return \"general\"\n    if last_m.name == \"music\":\n        return \"music\"\n    elif last_m.name == \"customer\":\n        return \"customer\"\n    else:\n        return \"general\""]
+   "source": [
+    "import json\n",
+    "\n",
+    "from langgraph.graph import END, START\n",
+    "\n",
+    "\n",
+    "def _get_last_ai_message(messages):\n",
+    "    for m in messages[::-1]:\n",
+    "        if isinstance(m, AIMessage):\n",
+    "            return m\n",
+    "    return None\n",
+    "\n",
+    "\n",
+    "def _is_tool_call(msg):\n",
+    "    return hasattr(msg, \"additional_kwargs\") and \"tool_calls\" in msg.additional_kwargs\n",
+    "\n",
+    "\n",
+    "def _route(messages):\n",
+    "    last_message = messages[-1]\n",
+    "    if isinstance(last_message, AIMessage):\n",
+    "        if not last_message.tool_calls:\n",
+    "            return END\n",
+    "        else:\n",
+    "            if last_message.name == \"general\":\n",
+    "                if len(last_message.tool_calls) > 1:\n",
+    "                    raise ValueError(\"Too many tools\")\n",
+    "                return last_message.tool_calls[0][\"args\"][\"choice\"]\n",
+    "            else:\n",
+    "                return \"tools\"\n",
+    "    last_m = _get_last_ai_message(messages)\n",
+    "    if last_m is None:\n",
+    "        return \"general\"\n",
+    "    if last_m.name == \"music\":\n",
+    "        return \"music\"\n",
+    "    elif last_m.name == \"customer\":\n",
+    "        return \"customer\"\n",
+    "    else:\n",
+    "        return \"general\""
+   ]
   },
   {
    "cell_type": "code",
@@ -337,7 +509,12 @@
    "id": "8aec704a-46fe-4fb3-bdee-11c3bbffc370",
    "metadata": {},
    "outputs": [],
-   "source": ["from langgraph.prebuilt import ToolNode\n\ntools = [get_albums_by_artist, get_tracks_by_artist, check_for_songs, get_customer_info]\ntool_node = ToolNode(tools)"]
+   "source": [
+    "from langgraph.prebuilt import ToolNode\n",
+    "\n",
+    "tools = [get_albums_by_artist, get_tracks_by_artist, check_for_songs, get_customer_info]\n",
+    "tool_node = ToolNode(tools)"
+   ]
   },
   {
    "cell_type": "code",
@@ -345,7 +522,16 @@
    "id": "4d5b75c6-73e0-4922-a765-a15be63f869e",
    "metadata": {},
    "outputs": [],
-   "source": ["def _filter_out_routes(messages):\n    ms = []\n    for m in messages:\n        if _is_tool_call(m):\n            if m.name == \"general\":\n                continue\n        ms.append(m)\n    return ms"]
+   "source": [
+    "def _filter_out_routes(messages):\n",
+    "    ms = []\n",
+    "    for m in messages:\n",
+    "        if _is_tool_call(m):\n",
+    "            if m.name == \"general\":\n",
+    "                continue\n",
+    "        ms.append(m)\n",
+    "    return ms"
+   ]
   },
   {
    "cell_type": "code",
@@ -353,7 +539,13 @@
    "id": "fd4dbf98-dbb3-411a-bad6-2bb334072aaf",
    "metadata": {},
    "outputs": [],
-   "source": ["from functools import partial\n\ngeneral_node = _filter_out_routes | chain | partial(add_name, name=\"general\")\nmusic_node = _filter_out_routes | song_recc_chain | partial(add_name, name=\"music\")\ncustomer_node = _filter_out_routes | customer_chain | partial(add_name, name=\"customer\")"]
+   "source": [
+    "from functools import partial\n",
+    "\n",
+    "general_node = _filter_out_routes | chain | partial(add_name, name=\"general\")\n",
+    "music_node = _filter_out_routes | song_recc_chain | partial(add_name, name=\"music\")\n",
+    "customer_node = _filter_out_routes | customer_chain | partial(add_name, name=\"customer\")"
+   ]
   },
   {
    "cell_type": "code",
@@ -361,7 +553,33 @@
    "id": "dcade924",
    "metadata": {},
    "outputs": [],
-   "source": ["from langgraph.checkpoint.sqlite import SqliteSaver\n\nfrom langgraph.graph import MessageGraph\n\nmemory = SqliteSaver.from_conn_string(\":memory:\")\ngraph = MessageGraph()\nnodes = {\n    \"general\": \"general\",\n    \"music\": \"music\",\n    END: END,\n    \"tools\": \"tools\",\n    \"customer\": \"customer\",\n}\n# Define a new graph\nworkflow = MessageGraph()\nworkflow.add_node(\"general\", general_node)\nworkflow.add_node(\"music\", music_node)\nworkflow.add_node(\"customer\", customer_node)\nworkflow.add_node(\"tools\", tool_node)\nworkflow.add_conditional_edges(\"general\", _route, nodes)\nworkflow.add_conditional_edges(\"tools\", _route, nodes)\nworkflow.add_conditional_edges(\"music\", _route, nodes)\nworkflow.add_conditional_edges(\"customer\", _route, nodes)\nworkflow.add_conditional_edges(START, _route, nodes)\ngraph = workflow.compile()"]
+   "source": [
+    "from langgraph.checkpoint.memory import MemorySaver\n",
+    "\n",
+    "from langgraph.graph import MessageGraph\n",
+    "\n",
+    "memory = MemorySaver()\n",
+    "graph = MessageGraph()\n",
+    "nodes = {\n",
+    "    \"general\": \"general\",\n",
+    "    \"music\": \"music\",\n",
+    "    END: END,\n",
+    "    \"tools\": \"tools\",\n",
+    "    \"customer\": \"customer\",\n",
+    "}\n",
+    "# Define a new graph\n",
+    "workflow = MessageGraph()\n",
+    "workflow.add_node(\"general\", general_node)\n",
+    "workflow.add_node(\"music\", music_node)\n",
+    "workflow.add_node(\"customer\", customer_node)\n",
+    "workflow.add_node(\"tools\", tool_node)\n",
+    "workflow.add_conditional_edges(\"general\", _route, nodes)\n",
+    "workflow.add_conditional_edges(\"tools\", _route, nodes)\n",
+    "workflow.add_conditional_edges(\"music\", _route, nodes)\n",
+    "workflow.add_conditional_edges(\"customer\", _route, nodes)\n",
+    "workflow.add_conditional_edges(START, _route, nodes)\n",
+    "graph = workflow.compile()"
+   ]
   },
   {
    "cell_type": "code",
@@ -370,7 +588,7 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "User (q/Q to quit):  what music do you have?\n"
@@ -395,7 +613,7 @@
      ]
     },
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "User (q/Q to quit):  how about shakira?\n"
@@ -446,7 +664,7 @@
      ]
     },
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "User (q/Q to quit):  hm cool\n"
@@ -483,7 +701,7 @@
      ]
     },
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "User (q/Q to quit):  q\n"
@@ -497,7 +715,27 @@
      ]
     }
    ],
-   "source": ["import uuid\n\nfrom langchain_core.messages import HumanMessage\n\nfrom langgraph.graph.graph import START\n\nhistory = []\nwhile True:\n    user = input(\"User (q/Q to quit): \")\n    if user in {\"q\", \"Q\"}:\n        print(\"AI: Byebye\")\n        break\n    history.append(HumanMessage(content=user))\n    async for output in graph.astream(history):\n        for key, value in output.items():\n            print(f\"Output from node '{key}':\")\n            print(\"---\")\n            print(value)\n        print(\"\\n---\\n\")"]
+   "source": [
+    "import uuid\n",
+    "\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "from langgraph.graph.graph import START\n",
+    "\n",
+    "history = []\n",
+    "while True:\n",
+    "    user = input(\"User (q/Q to quit): \")\n",
+    "    if user in {\"q\", \"Q\"}:\n",
+    "        print(\"AI: Byebye\")\n",
+    "        break\n",
+    "    history.append(HumanMessage(content=user))\n",
+    "    async for output in graph.astream(history):\n",
+    "        for key, value in output.items():\n",
+    "            print(f\"Output from node '{key}':\")\n",
+    "            print(\"---\")\n",
+    "            print(value)\n",
+    "        print(\"\\n---\\n\")"
+   ]
   }
  ],
  "metadata": {

examples/chatbots/information-gather-prompting.ipynb

@@ -176,10 +176,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import START, MessageGraph\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "workflow = MessageGraph()\n",
     "workflow.add_node(\"info\", chain)\n",
     "workflow.add_node(\"prompt\", prompt_gen_chain)\n",

examples/code_assistant/langgraph_code_assistant_mistral.ipynb

@@ -154,7 +154,7 @@
    "id": "2dff2209-44c7-4e2c-b607-ba6675f9e45f",
    "metadata": {},
    "outputs": [],
-   "source": ["from langgraph.checkpoint.sqlite import SqliteSaver\nfrom langgraph.graph import END, StateGraph, START\n\nbuilder = StateGraph(GraphState)\n\n# Define the nodes\nbuilder.add_node(\"generate\", generate)  # generation solution\nbuilder.add_node(\"check_code\", code_check)  # check code\n\n# Build graph\nbuilder.add_edge(START, \"generate\")\nbuilder.add_edge(\"generate\", \"check_code\")\nbuilder.add_conditional_edges(\n    \"check_code\",\n    decide_to_finish,\n    {\n        \"end\": END,\n        \"generate\": \"generate\",\n    },\n)\n\nmemory = SqliteSaver.from_conn_string(\":memory:\")\ngraph = builder.compile(checkpointer=memory)"]
+   "source": ["from langgraph.checkpoint.memory import MemorySaver\nfrom langgraph.graph import END, StateGraph, START\n\nbuilder = StateGraph(GraphState)\n\n# Define the nodes\nbuilder.add_node(\"generate\", generate)  # generation solution\nbuilder.add_node(\"check_code\", code_check)  # check code\n\n# Build graph\nbuilder.add_edge(START, \"generate\")\nbuilder.add_edge(\"generate\", \"check_code\")\nbuilder.add_conditional_edges(\n    \"check_code\",\n    decide_to_finish,\n    {\n        \"end\": END,\n        \"generate\": \"generate\",\n    },\n)\n\nmemory = MemorySaver()\ngraph = builder.compile(checkpointer=memory)"]
   },
   {
    "cell_type": "code",

examples/human-in-the-loop.ipynb

@@ -39,7 +39,10 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_openai"]
+   "source": [
+    "%%capture --no-stderr\n",
+    "%pip install --quiet -U langgraph langchain_openai"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -55,7 +58,18 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": ["import getpass\nimport os\n\n\ndef _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\")"]
+   "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",
@@ -71,7 +85,10 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n_set_env(\"LANGCHAIN_API_KEY\")"]
+   "source": [
+    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "_set_env(\"LANGCHAIN_API_KEY\")"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -89,7 +106,22 @@
    "id": "6098e5cb",
    "metadata": {},
    "outputs": [],
-   "source": ["from typing import Annotated\n\nfrom typing_extensions import TypedDict\n\nfrom langgraph.graph.message import add_messages\n\n# `add_messages`` essentially does this\n# (with more robust handling)\n# def add_messages(left: list, right: list):\n#     return left + right\n\n\nclass State(TypedDict):\n    messages: Annotated[list, add_messages]"]
+   "source": [
+    "from typing import Annotated\n",
+    "\n",
+    "from typing_extensions import TypedDict\n",
+    "\n",
+    "from langgraph.graph.message import add_messages\n",
+    "\n",
+    "# `add_messages`` essentially does this\n",
+    "# (with more robust handling)\n",
+    "# def add_messages(left: list, right: list):\n",
+    "#     return left + right\n",
+    "\n",
+    "\n",
+    "class State(TypedDict):\n",
+    "    messages: Annotated[list, add_messages]"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -109,7 +141,22 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": ["from langchain_core.tools import tool\n\n\n@tool\ndef search(query: str):\n    \"\"\"Call to surf the web.\"\"\"\n    # This is a placeholder for the actual implementation\n    # Don't let the LLM know this though 😊\n    return [\n        \"It's sunny in San Francisco, but you better look out if you're a Gemini 😈.\"\n    ]\n\n\ntools = [search]"]
+   "source": [
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def search(query: str):\n",
+    "    \"\"\"Call to surf the web.\"\"\"\n",
+    "    # This is a placeholder for the actual implementation\n",
+    "    # Don't let the LLM know this though 😊\n",
+    "    return [\n",
+    "        \"It's sunny in San Francisco, but you better look out if you're a Gemini 😈.\"\n",
+    "    ]\n",
+    "\n",
+    "\n",
+    "tools = [search]"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -127,7 +174,11 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
+   "source": [
+    "from langgraph.prebuilt import ToolExecutor\n",
+    "\n",
+    "tool_executor = ToolExecutor(tools)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -148,7 +199,11 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": ["from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(temperature=0)"]
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI(temperature=0)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -166,7 +221,9 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": ["model = model.bind_tools(tools)"]
+   "source": [
+    "model = model.bind_tools(tools)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -201,7 +258,53 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation from the function_call\n    tool_call = last_message.tool_calls[0]\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    response = tool_executor.invoke(action)\n    # We use the response to create a ToolMessage\n    tool_message = ToolMessage(\n        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n    )\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [tool_message]}"]
+   "source": [
+    "from langchain_core.messages import ToolMessage\n",
+    "\n",
+    "from langgraph.prebuilt import ToolInvocation\n",
+    "\n",
+    "\n",
+    "# Define the function that determines whether to continue or not\n",
+    "def should_continue(state):\n",
+    "    messages = state[\"messages\"]\n",
+    "    last_message = messages[-1]\n",
+    "    # If there is no function call, then we finish\n",
+    "    if not last_message.tool_calls:\n",
+    "        return \"end\"\n",
+    "    # Otherwise if there is, we continue\n",
+    "    else:\n",
+    "        return \"continue\"\n",
+    "\n",
+    "\n",
+    "# Define the function that calls the model\n",
+    "def call_model(state):\n",
+    "    messages = state[\"messages\"]\n",
+    "    response = model.invoke(messages)\n",
+    "    # We return a list, because this will get added to the existing list\n",
+    "    return {\"messages\": [response]}\n",
+    "\n",
+    "\n",
+    "# Define the function to execute tools\n",
+    "def call_tool(state):\n",
+    "    messages = state[\"messages\"]\n",
+    "    # Based on the continue condition\n",
+    "    # we know the last message involves a function call\n",
+    "    last_message = messages[-1]\n",
+    "    # We construct an ToolInvocation from the function_call\n",
+    "    tool_call = last_message.tool_calls[0]\n",
+    "    action = ToolInvocation(\n",
+    "        tool=tool_call[\"name\"],\n",
+    "        tool_input=tool_call[\"args\"],\n",
+    "    )\n",
+    "    # We call the tool_executor and get back a response\n",
+    "    response = tool_executor.invoke(action)\n",
+    "    # We use the response to create a ToolMessage\n",
+    "    tool_message = ToolMessage(\n",
+    "        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n",
+    "    )\n",
+    "    # We return a list, because this will get added to the existing list\n",
+    "    return {\"messages\": [tool_message]}"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -219,7 +322,45 @@
    "id": "812b4e70-4956-4415-8880-db48b3dcbad2",
    "metadata": {},
    "outputs": [],
-   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(State)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")"]
+   "source": [
+    "from langgraph.graph import END, StateGraph, START\n",
+    "\n",
+    "# Define a new graph\n",
+    "workflow = StateGraph(State)\n",
+    "\n",
+    "# Define the two nodes we will cycle between\n",
+    "workflow.add_node(\"agent\", call_model)\n",
+    "workflow.add_node(\"action\", call_tool)\n",
+    "\n",
+    "# Set the entrypoint as `agent`\n",
+    "# This means that this node is the first one called\n",
+    "workflow.add_edge(START, \"agent\")\n",
+    "\n",
+    "# We now add a conditional edge\n",
+    "workflow.add_conditional_edges(\n",
+    "    # First, we define the start node. We use `agent`.\n",
+    "    # This means these are the edges taken after the `agent` node is called.\n",
+    "    \"agent\",\n",
+    "    # Next, we pass in the function that will determine which node is called next.\n",
+    "    should_continue,\n",
+    "    # Finally we pass in a mapping.\n",
+    "    # The keys are strings, and the values are other nodes.\n",
+    "    # END is a special node marking that the graph should finish.\n",
+    "    # What will happen is we will call `should_continue`, and then the output of that\n",
+    "    # will be matched against the keys in this mapping.\n",
+    "    # Based on which one it matches, that node will then be called.\n",
+    "    {\n",
+    "        # If `tools`, then we call the tool node.\n",
+    "        \"continue\": \"action\",\n",
+    "        # Otherwise we finish.\n",
+    "        \"end\": END,\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "# We now add a normal edge from `tools` to `agent`.\n",
+    "# This means that after `tools` is called, `agent` node is called next.\n",
+    "workflow.add_edge(\"action\", \"agent\")"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -237,7 +378,11 @@
    "id": "6845ed6a-d155-4105-9160-28849877248b",
    "metadata": {},
    "outputs": [],
-   "source": ["from langgraph.checkpoint.sqlite import SqliteSaver\n\nmemory = SqliteSaver.from_conn_string(\":memory:\")"]
+   "source": [
+    "from langgraph.checkpoint.memory import MemorySaver\n",
+    "\n",
+    "memory = MemorySaver()"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -255,7 +400,12 @@
    "id": "79d29875-8aa8-434c-9f20-1c58346a6249",
    "metadata": {},
    "outputs": [],
-   "source": ["# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile(checkpointer=memory, interrupt_before=[\"action\"])"]
+   "source": [
+    "# Finally, we compile it!\n",
+    "# This compiles it into a LangChain Runnable,\n",
+    "# meaning you can use it as you would any other runnable\n",
+    "app = workflow.compile(checkpointer=memory, interrupt_before=[\"action\"])"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -282,7 +432,11 @@
      "output_type": "display_data"
     }
    ],
-   "source": ["from IPython.display import Image, display\n\ndisplay(Image(app.get_graph().draw_mermaid_png()))"]
+   "source": [
+    "from IPython.display import Image, display\n",
+    "\n",
+    "display(Image(app.get_graph().draw_mermaid_png()))"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -313,7 +467,14 @@
      ]
     }
    ],
-   "source": ["from langchain_core.messages import HumanMessage\n\nthread = {\"configurable\": {\"thread_id\": \"2\"}}\ninputs = [HumanMessage(content=\"hi! I'm bob\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "thread = {\"configurable\": {\"thread_id\": \"2\"}}\n",
+    "inputs = [HumanMessage(content=\"hi! I'm bob\")]\n",
+    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
   },
   {
    "cell_type": "code",
@@ -334,7 +495,11 @@
      ]
     }
    ],
-   "source": ["inputs = [HumanMessage(content=\"What did I tell you my name was?\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
+   "source": [
+    "inputs = [HumanMessage(content=\"What did I tell you my name was?\")]\n",
+    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
   },
   {
    "cell_type": "code",
@@ -358,7 +523,11 @@
      ]
     }
    ],
-   "source": ["inputs = [HumanMessage(content=\"what's the weather in sf now?\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
+   "source": [
+    "inputs = [HumanMessage(content=\"what's the weather in sf now?\")]\n",
+    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -392,7 +561,10 @@
      ]
     }
    ],
-   "source": ["for event in app.stream(None, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
+   "source": [
+    "for event in app.stream(None, thread, stream_mode=\"values\"):\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -427,7 +599,43 @@
    "id": "5454f436-d56e-4499-9381-06192aca1b56",
    "metadata": {},
    "outputs": [],
-   "source": ["import json\nfrom typing import Optional\n\nfrom langchain_core.messages import AIMessage\n\n\n# Helper function to construct message asking for verification\ndef generate_verification_message(message: AIMessage) -> None:\n    \"\"\"Generate \"verification message\" from message with tool calls.\"\"\"\n    serialized_tool_calls = json.dumps(\n        message.tool_calls,\n        indent=2,\n    )\n    return AIMessage(\n        content=(\n            \"I plan to invoke the following tools, do you approve?\\n\\n\"\n            \"Type 'y' if you do, anything else to stop.\\n\\n\"\n            f\"{serialized_tool_calls}\"\n        ),\n        id=message.id,\n    )\n\n\n# Helper function to stream output from the graph\ndef stream_app_catch_tool_calls(inputs, thread) -> Optional[AIMessage]:\n    \"\"\"Stream app, catching tool calls.\"\"\"\n    tool_call_message = None\n    for event in app.stream(inputs, thread, stream_mode=\"values\"):\n        message = event[\"messages\"][-1]\n        if isinstance(message, AIMessage) and message.tool_calls:\n            tool_call_message = message\n        else:\n            message.pretty_print()\n\n    return tool_call_message"]
+   "source": [
+    "import json\n",
+    "from typing import Optional\n",
+    "\n",
+    "from langchain_core.messages import AIMessage\n",
+    "\n",
+    "\n",
+    "# Helper function to construct message asking for verification\n",
+    "def generate_verification_message(message: AIMessage) -> None:\n",
+    "    \"\"\"Generate \"verification message\" from message with tool calls.\"\"\"\n",
+    "    serialized_tool_calls = json.dumps(\n",
+    "        message.tool_calls,\n",
+    "        indent=2,\n",
+    "    )\n",
+    "    return AIMessage(\n",
+    "        content=(\n",
+    "            \"I plan to invoke the following tools, do you approve?\\n\\n\"\n",
+    "            \"Type 'y' if you do, anything else to stop.\\n\\n\"\n",
+    "            f\"{serialized_tool_calls}\"\n",
+    "        ),\n",
+    "        id=message.id,\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "# Helper function to stream output from the graph\n",
+    "def stream_app_catch_tool_calls(inputs, thread) -> Optional[AIMessage]:\n",
+    "    \"\"\"Stream app, catching tool calls.\"\"\"\n",
+    "    tool_call_message = None\n",
+    "    for event in app.stream(inputs, thread, stream_mode=\"values\"):\n",
+    "        message = event[\"messages\"][-1]\n",
+    "        if isinstance(message, AIMessage) and message.tool_calls:\n",
+    "            tool_call_message = message\n",
+    "        else:\n",
+    "            message.pretty_print()\n",
+    "\n",
+    "    return tool_call_message"
+   ]
   },
   {
    "cell_type": "code",
@@ -514,7 +722,43 @@
      ]
     }
    ],
-   "source": ["import uuid\n\nthread = {\"configurable\": {\"thread_id\": \"3\"}}\n\ntool_call_message = stream_app_catch_tool_calls(\n    {\"messages\": [HumanMessage(\"what's the weather in sf now?\")]},\n    thread,\n)\n\nwhile tool_call_message:\n    verification_message = generate_verification_message(tool_call_message)\n    verification_message.pretty_print()\n    input_message = HumanMessage(input())\n    if input_message.content == \"exit\":\n        break\n    input_message.pretty_print()\n\n    # First we update the state with the verification message and the input message.\n    # note that `generate_verification_message` sets the message ID to be the same\n    # as the ID from the original tool call message. Updating the state with this\n    # message will overwrite the previous tool call.\n    snapshot = app.get_state(thread)\n    snapshot.values[\"messages\"] += [verification_message, input_message]\n\n    if input_message.content == \"y\":\n        tool_call_message.id = str(uuid.uuid4())\n        # If verified, we append the tool call message to the state\n        # and resume execution.\n        snapshot.values[\"messages\"] += [tool_call_message]\n        app.update_state(thread, snapshot.values, as_node=\"agent\")\n    else:\n        # Otherwise, resume execution from the input message.\n        app.update_state(thread, snapshot.values, as_node=\"__start__\")\n\n    tool_call_message = stream_app_catch_tool_calls(None, thread)"]
+   "source": [
+    "import uuid\n",
+    "\n",
+    "thread = {\"configurable\": {\"thread_id\": \"3\"}}\n",
+    "\n",
+    "tool_call_message = stream_app_catch_tool_calls(\n",
+    "    {\"messages\": [HumanMessage(\"what's the weather in sf now?\")]},\n",
+    "    thread,\n",
+    ")\n",
+    "\n",
+    "while tool_call_message:\n",
+    "    verification_message = generate_verification_message(tool_call_message)\n",
+    "    verification_message.pretty_print()\n",
+    "    input_message = HumanMessage(input())\n",
+    "    if input_message.content == \"exit\":\n",
+    "        break\n",
+    "    input_message.pretty_print()\n",
+    "\n",
+    "    # First we update the state with the verification message and the input message.\n",
+    "    # note that `generate_verification_message` sets the message ID to be the same\n",
+    "    # as the ID from the original tool call message. Updating the state with this\n",
+    "    # message will overwrite the previous tool call.\n",
+    "    snapshot = app.get_state(thread)\n",
+    "    snapshot.values[\"messages\"] += [verification_message, input_message]\n",
+    "\n",
+    "    if input_message.content == \"y\":\n",
+    "        tool_call_message.id = str(uuid.uuid4())\n",
+    "        # If verified, we append the tool call message to the state\n",
+    "        # and resume execution.\n",
+    "        snapshot.values[\"messages\"] += [tool_call_message]\n",
+    "        app.update_state(thread, snapshot.values, as_node=\"agent\")\n",
+    "    else:\n",
+    "        # Otherwise, resume execution from the input message.\n",
+    "        app.update_state(thread, snapshot.values, as_node=\"__start__\")\n",
+    "\n",
+    "    tool_call_message = stream_app_catch_tool_calls(None, thread)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -535,7 +779,34 @@
    "id": "03232f16-d6fe-46d0-afa0-a6f0d0bf16de",
    "metadata": {},
    "outputs": [],
-   "source": ["class State(TypedDict):\n    messages: Annotated[list, add_messages]\n    tool_call_message: Optional[AIMessage]\n\n\ndef call_model(state):\n    messages = state[\"messages\"]\n    if messages[-1].content == \"y\":\n        return {\n            \"messages\": [state[\"tool_call_message\"]],\n            \"tool_call_message\": None,\n        }\n    else:\n        response = model.invoke(messages)\n        if response.tool_calls:\n            verification_message = generate_verification_message(response)\n            response.id = str(uuid.uuid4())\n            return {\n                \"messages\": [verification_message],\n                \"tool_call_message\": response,\n            }\n        else:\n            return {\n                \"messages\": [response],\n                \"tool_call_message\": None,\n            }"]
+   "source": [
+    "class State(TypedDict):\n",
+    "    messages: Annotated[list, add_messages]\n",
+    "    tool_call_message: Optional[AIMessage]\n",
+    "\n",
+    "\n",
+    "def call_model(state):\n",
+    "    messages = state[\"messages\"]\n",
+    "    if messages[-1].content == \"y\":\n",
+    "        return {\n",
+    "            \"messages\": [state[\"tool_call_message\"]],\n",
+    "            \"tool_call_message\": None,\n",
+    "        }\n",
+    "    else:\n",
+    "        response = model.invoke(messages)\n",
+    "        if response.tool_calls:\n",
+    "            verification_message = generate_verification_message(response)\n",
+    "            response.id = str(uuid.uuid4())\n",
+    "            return {\n",
+    "                \"messages\": [verification_message],\n",
+    "                \"tool_call_message\": response,\n",
+    "            }\n",
+    "        else:\n",
+    "            return {\n",
+    "                \"messages\": [response],\n",
+    "                \"tool_call_message\": None,\n",
+    "            }"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -551,7 +822,27 @@
    "id": "502dc688-c926-407e-8759-8c9e39eb4257",
    "metadata": {},
    "outputs": [],
-   "source": ["workflow = StateGraph(State)\n\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\nworkflow.add_edge(START, \"agent\")\n\nworkflow.add_conditional_edges(\n    \"agent\",\n    should_continue,\n    {\n        \"continue\": \"action\",\n        \"end\": END,\n    },\n)\n\nworkflow.add_edge(\"action\", \"agent\")\n\napp = workflow.compile(checkpointer=memory)"]
+   "source": [
+    "workflow = StateGraph(State)\n",
+    "\n",
+    "workflow.add_node(\"agent\", call_model)\n",
+    "workflow.add_node(\"action\", call_tool)\n",
+    "\n",
+    "workflow.add_edge(START, \"agent\")\n",
+    "\n",
+    "workflow.add_conditional_edges(\n",
+    "    \"agent\",\n",
+    "    should_continue,\n",
+    "    {\n",
+    "        \"continue\": \"action\",\n",
+    "        \"end\": END,\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "workflow.add_edge(\"action\", \"agent\")\n",
+    "\n",
+    "app = workflow.compile(checkpointer=memory)"
+   ]
   },
   {
    "cell_type": "code",
@@ -584,7 +875,13 @@
      ]
     }
    ],
-   "source": ["thread = {\"configurable\": {\"thread_id\": \"4\"}}\n\ninputs = [HumanMessage(content=\"what's the weather in sf?\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
+   "source": [
+    "thread = {\"configurable\": {\"thread_id\": \"4\"}}\n",
+    "\n",
+    "inputs = [HumanMessage(content=\"what's the weather in sf?\")]\n",
+    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
   },
   {
    "cell_type": "code",
@@ -617,7 +914,11 @@
      ]
     }
    ],
-   "source": ["inputs = [HumanMessage(content=\"can you specify sf in CA?\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
+   "source": [
+    "inputs = [HumanMessage(content=\"can you specify sf in CA?\")]\n",
+    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
   },
   {
    "cell_type": "code",
@@ -648,7 +949,11 @@
      ]
     }
    ],
-   "source": ["inputs = [HumanMessage(content=\"y\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
+   "source": [
+    "inputs = [HumanMessage(content=\"y\")]\n",
+    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
   }
  ],
  "metadata": {

examples/input_output_schema.ipynb

@@ -42,7 +42,6 @@
     "def answer_node(state: InputState):\n",
     "    return {\"answer\": \"bye\"}\n",
     "\n",
-    "check = SqliteSaver.from_conn_string(\":memory:\")\n",
     "graph = StateGraph(input=InputState, output=OutputState)\n",
     "graph.add_node(answer_node)\n",
     "graph.add_edge(START, \"answer_node\")\n",

examples/introduction.ipynb

@@ -848,7 +848,7 @@
     "\n",
     "We will see later that **checkpointing** is _much_ more powerful than simple chat memory - it lets you save and resume complex state at any time for error recovery, human-in-the-loop workflows, time travel interactions, and more. But before we get too ahead of ourselves, let's add checkpointing to enable multi-turn conversations.\n",
     "\n",
-    "To get started, create a `SqliteSaver` checkpointer."
+    "To get started, create a `MemorySaver` checkpointer."
    ]
   },
   {
@@ -858,9 +858,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")"
+    "memory = MemorySaver()"
    ]
   },
   {
@@ -868,7 +868,7 @@
    "id": "08d3d11a-1b42-4cbb-8e11-2a4294263d90",
    "metadata": {},
    "source": [
-    "**Notice** that we've specified `:memory` as the Sqlite DB path. This is convenient for our tutorial (it saves it all in-memory). In a production application, you would likely change this to connect to your own DB and/or use one of the other checkpointer classes.\n",
+    "**Notice** we're using an in-memory checkpointer. This is convenient for our tutorial (it saves it all in-memory). In a production application, you would likely change this to use `SqliteSaver` or `PostgresSaver` and connect to your own DB.\n",
     "\n",
     "Next define the graph. Now that you've already built your own `BasicToolNode`, we'll replace it with LangGraph's prebuilt `ToolNode` and `tools_condition`, since these do some nice things like parallel API execution. Apart from that, the following is all copied from Part 2."
    ]
@@ -1199,7 +1199,7 @@
     "from langchain_core.messages import BaseMessage\n",
     "from typing_extensions import TypedDict\n",
     "\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import StateGraph\n",
     "from langgraph.graph.message import add_messages\n",
     "from langgraph.prebuilt import ToolNode\n",
@@ -1277,12 +1277,12 @@
     "from langchain_core.messages import BaseMessage\n",
     "from typing_extensions import TypedDict\n",
     "\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import StateGraph, START\n",
     "from langgraph.graph.message import add_messages\n",
     "from langgraph.prebuilt import ToolNode, tools_condition\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "\n",
     "\n",
     "class State(TypedDict):\n",
@@ -1508,7 +1508,7 @@
     "from langchain_core.messages import BaseMessage\n",
     "from typing_extensions import TypedDict\n",
     "\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import StateGraph\n",
     "from langgraph.graph.message import add_messages\n",
     "from langgraph.prebuilt import ToolNode\n",
@@ -1543,7 +1543,7 @@
     "graph_builder.add_edge(\"tools\", \"chatbot\")\n",
     "graph_builder.set_entry_point(\"chatbot\")\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "graph = graph_builder.compile(\n",
     "    checkpointer=memory,\n",
     "    # This is new!\n",
@@ -1593,7 +1593,7 @@
     "from langchain_core.messages import BaseMessage\n",
     "from typing_extensions import TypedDict\n",
     "\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import StateGraph, START\n",
     "from langgraph.graph.message import add_messages\n",
     "from langgraph.prebuilt import ToolNode, tools_condition\n",
@@ -1627,7 +1627,7 @@
     ")\n",
     "graph_builder.add_edge(\"tools\", \"chatbot\")\n",
     "graph_builder.add_edge(START, \"chatbot\")\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "graph = graph_builder.compile(\n",
     "    checkpointer=memory,\n",
     "    # This is new!\n",
@@ -2092,7 +2092,7 @@
     "from langchain_core.messages import BaseMessage\n",
     "from typing_extensions import TypedDict\n",
     "\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import StateGraph, START\n",
     "from langgraph.graph.message import add_messages\n",
     "from langgraph.prebuilt import ToolNode, tools_condition\n",
@@ -2289,7 +2289,7 @@
     "graph_builder.add_edge(\"tools\", \"chatbot\")\n",
     "graph_builder.add_edge(\"human\", \"chatbot\")\n",
     "graph_builder.add_edge(START, \"chatbot\")\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "graph = graph_builder.compile(\n",
     "    checkpointer=memory,\n",
     "    # We interrupt before 'human' here instead.\n",
@@ -2539,7 +2539,7 @@
     "from langchain_core.pydantic_v1 import BaseModel\n",
     "from typing_extensions import TypedDict\n",
     "\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import StateGraph\n",
     "from langgraph.graph.message import add_messages\n",
     "from langgraph.prebuilt import ToolNode, tools_condition\n",
@@ -2626,7 +2626,7 @@
     "graph_builder.add_edge(\"tools\", \"chatbot\")\n",
     "graph_builder.add_edge(\"human\", \"chatbot\")\n",
     "graph_builder.set_entry_point(\"chatbot\")\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "graph = graph_builder.compile(\n",
     "    checkpointer=memory,\n",
     "    interrupt_before=[\"human\"],\n",
@@ -2665,11 +2665,11 @@
     "\n",
     "from langchain_anthropic import ChatAnthropic\n",
     "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_core.messages import AIMessage, BaseMessage, ToolMessage\n",
+    "from langchain_core.messages import AIMessage, ToolMessage\n",
     "from langchain_core.pydantic_v1 import BaseModel\n",
     "from typing_extensions import TypedDict\n",
     "\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import StateGraph, START\n",
     "from langgraph.graph.message import add_messages\n",
     "from langgraph.prebuilt import ToolNode, tools_condition\n",
@@ -2756,7 +2756,7 @@
     "graph_builder.add_edge(\"tools\", \"chatbot\")\n",
     "graph_builder.add_edge(\"human\", \"chatbot\")\n",
     "graph_builder.add_edge(START, \"chatbot\")\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "graph = graph_builder.compile(\n",
     "    checkpointer=memory,\n",
     "    interrupt_before=[\"human\"],\n",

examples/memory/add-summary-conversation-history.ipynb

@@ -105,10 +105,10 @@
     "\n",
     "from langchain_anthropic import ChatAnthropic\n",
     "from langchain_core.messages import SystemMessage, RemoveMessage\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import MessagesState, StateGraph, START, END\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "\n",
     "\n",
     "# We will add a `summary` attribute (in addition to `messages` key,\n",

examples/memory/delete-messages.ipynb

@@ -112,11 +112,11 @@
     "from langchain_anthropic import ChatAnthropic\n",
     "from langchain_core.tools import tool\n",
     "\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import MessagesState, StateGraph, START\n",
     "from langgraph.prebuilt import ToolNode\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "\n",
     "\n",
     "@tool\n",

examples/memory/manage-conversation-history.ipynb

@@ -103,11 +103,11 @@
     "from langchain_anthropic import ChatAnthropic\n",
     "from langchain_core.tools import tool\n",
     "\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import MessagesState, StateGraph, START\n",
     "from langgraph.prebuilt import ToolNode\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "\n",
     "\n",
     "@tool\n",
@@ -234,11 +234,11 @@
     "from langchain_anthropic import ChatAnthropic\n",
     "from langchain_core.tools import tool\n",
     "\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import MessagesState, StateGraph, START\n",
     "from langgraph.prebuilt import ToolNode\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "\n",
     "\n",
     "@tool\n",

examples/persistence.ipynb

@@ -17,11 +17,11 @@
         "Example:\n",
         "```python\n",
         "from langgraph.graph import StateGraph\n",
-        "from langgraph.checkpoint.sqlite.aio import AsyncSqliteSaver\n",
+        "from langgraph.checkpoint.memory import MemorySaver\n",
         "\n",
         "builder = StateGraph(....)\n",
         "# ... define the graph\n",
-        "memory = AsyncSqliteSaver.from_conn_string(\":memory:\")\n",
+        "memory = MemorySaver()\n",
         "graph = builder.compile(checkpointer=memory)\n",
         "...\n",
         "```\n",
@@ -361,9 +361,9 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+        "from langgraph.checkpoint.memory import MemorySaver\n",
         "\n",
-        "memory = SqliteSaver.from_conn_string(\":memory:\")"
+        "memory = MemorySaver()"
       ]
     },
     {

examples/time-travel.ipynb

@@ -246,7 +246,7 @@
    "id": "6845ed6a-d155-4105-9160-28849877248b",
    "metadata": {},
    "outputs": [],
-   "source": ["from langgraph.checkpoint.sqlite import SqliteSaver\n\nmemory = SqliteSaver.from_conn_string(\":memory:\")"]
+   "source": ["from langgraph.checkpoint.memory import MemorySaver\n\nmemory = MemorySaver()"]
   },
   {
    "cell_type": "code",

examples/tutorials/rag-agent-testing.ipynb

@@ -574,7 +574,7 @@
     }
    ],
    "source": [
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import START, END, StateGraph\n",
     "from langgraph.prebuilt import tools_condition\n",
     "from IPython.display import Image, display\n",
@@ -597,7 +597,7 @@
     "builder.add_edge(\"tools\", \"assistant\")\n",
     "\n",
     "# The checkpointer lets the graph persist its state\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "react_graph = builder.compile(checkpointer=memory)\n",
     "\n",
     "# Show\n",

examples/tutorials/tool-calling-agent-local.ipynb

@@ -253,7 +253,7 @@
     "\n",
     "\n",
     "from IPython.display import Image, display\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "from langgraph.graph import END, START, StateGraph\n",
     "from langgraph.prebuilt import tools_condition\n",
     "\n",
@@ -275,7 +275,7 @@
     "builder.add_edge(\"tools\", \"assistant\")\n",
     "\n",
     "# The checkpointer lets the graph persist its state\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "react_graph = builder.compile(checkpointer=memory)\n",
     "\n",
     "# Show\n",

examples/usaco/usaco.ipynb

@@ -598,7 +598,7 @@
    "id": "e6e73e85-1232-4848-beba-3139ac7d0a64",
    "metadata": {},
    "outputs": [],
-   "source": ["from langgraph.checkpoint.sqlite import SqliteSaver\nfrom langgraph.graph import END, StateGraph, START\n\nbuilder = StateGraph(State)\nbuilder.add_node(\"draft\", draft_solver)\nbuilder.add_edge(START, \"draft\")\nbuilder.add_node(\"retrieve\", retrieve_examples)\nbuilder.add_node(\"solve\", solver)\nbuilder.add_node(\"evaluate\", evaluate)\n# Add connectivity\nbuilder.add_edge(\"draft\", \"retrieve\")\nbuilder.add_edge(\"retrieve\", \"solve\")\nbuilder.add_edge(\"solve\", \"evaluate\")\n\n\ndef control_edge(state: State):\n    if state.get(\"status\") == \"success\":\n        return END\n    return \"solve\"\n\n\nbuilder.add_conditional_edges(\"evaluate\", control_edge, {END: END, \"solve\": \"solve\"})\n\n\ncheckpointer = SqliteSaver.from_conn_string(\":memory:\")\ngraph = builder.compile(checkpointer=checkpointer)"]
+   "source": ["from langgraph.checkpoint.memory import MemorySaver\nfrom langgraph.graph import END, StateGraph, START\n\nbuilder = StateGraph(State)\nbuilder.add_node(\"draft\", draft_solver)\nbuilder.add_edge(START, \"draft\")\nbuilder.add_node(\"retrieve\", retrieve_examples)\nbuilder.add_node(\"solve\", solver)\nbuilder.add_node(\"evaluate\", evaluate)\n# Add connectivity\nbuilder.add_edge(\"draft\", \"retrieve\")\nbuilder.add_edge(\"retrieve\", \"solve\")\nbuilder.add_edge(\"solve\", \"evaluate\")\n\n\ndef control_edge(state: State):\n    if state.get(\"status\") == \"success\":\n        return END\n    return \"solve\"\n\n\nbuilder.add_conditional_edges(\"evaluate\", control_edge, {END: END, \"solve\": \"solve\"})\n\n\ncheckpointer = MemorySaver()\ngraph = builder.compile(checkpointer=checkpointer)"]
   },
   {
    "cell_type": "code",
@@ -809,7 +809,7 @@
    "id": "3c6456ba-363c-4133-8631-6dabb042b6ce",
    "metadata": {},
    "outputs": [],
-   "source": ["# This is all the same as before\nfrom langgraph.checkpoint.sqlite import SqliteSaver\nfrom langgraph.graph import END, StateGraph, START\n\nbuilder = StateGraph(State)\nprompt = hub.pull(\"wfh/usaco-draft-solver\")\nllm = ChatAnthropic(model=\"claude-3-opus-20240229\", max_tokens_to_sample=4000)\n\ndraft_solver = Solver(llm, prompt.partial(examples=\"\"))\nbuilder.add_node(\"draft\", draft_solver)\nbuilder.add_edge(START, \"draft\")\nbuilder.add_node(\"retrieve\", retrieve_examples)\nsolver = Solver(llm, prompt)\nbuilder.add_node(\"solve\", solver)\nbuilder.add_node(\"evaluate\", evaluate)\nbuilder.add_edge(\"draft\", \"retrieve\")\nbuilder.add_edge(\"retrieve\", \"solve\")\nbuilder.add_edge(\"solve\", \"evaluate\")\n\n\ndef control_edge(state: State):\n    if state.get(\"status\") == \"success\":\n        return END\n    return \"solve\"\n\n\nbuilder.add_conditional_edges(\"evaluate\", control_edge, {END: END, \"solve\": \"solve\"})\ncheckpointer = SqliteSaver.from_conn_string(\":memory:\")"]
+   "source": ["# This is all the same as before\nfrom langgraph.checkpoint.memory import MemorySaver\nfrom langgraph.graph import END, StateGraph, START\n\nbuilder = StateGraph(State)\nprompt = hub.pull(\"wfh/usaco-draft-solver\")\nllm = ChatAnthropic(model=\"claude-3-opus-20240229\", max_tokens_to_sample=4000)\n\ndraft_solver = Solver(llm, prompt.partial(examples=\"\"))\nbuilder.add_node(\"draft\", draft_solver)\nbuilder.add_edge(START, \"draft\")\nbuilder.add_node(\"retrieve\", retrieve_examples)\nsolver = Solver(llm, prompt)\nbuilder.add_node(\"solve\", solver)\nbuilder.add_node(\"evaluate\", evaluate)\nbuilder.add_edge(\"draft\", \"retrieve\")\nbuilder.add_edge(\"retrieve\", \"solve\")\nbuilder.add_edge(\"solve\", \"evaluate\")\n\n\ndef control_edge(state: State):\n    if state.get(\"status\") == \"success\":\n        return END\n    return \"solve\"\n\n\nbuilder.add_conditional_edges(\"evaluate\", control_edge, {END: END, \"solve\": \"solve\"})\ncheckpointer = MemorySaver()"]
   },
   {
    "cell_type": "markdown",

libs/checkpoint-postgres/README.md

@@ -4,6 +4,12 @@ Implementation of LangGraph CheckpointSaver that uses Postgres.
 
 ## Usage
 
+> [!IMPORTANT]
+> When using Postgres checkpointers for the first time, make sure to call `.setup()` method on them to create required tables. See example below.
+
+> [!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/).
+
 ```python
 from langgraph.checkpoint.postgres import PostgresSaver
 
@@ -12,6 +18,8 @@ read_config = {"configurable": {"thread_id": "1"}}
 
 DB_URI = "postgres://postgres:postgres@localhost:5432/postgres?sslmode=disable"
 with PostgresSaver.from_conn_string(DB_URI) as checkpointer:
+    # call .setup() the first time you're using the checkpointer
+    checkpointer.setup()
     checkpoint = {
         "v": 1,
         "ts": "2024-07-31T20:14:19.804150+00:00",
@@ -90,4 +98,4 @@ async with AsyncPostgresSaver.from_conn_string(DB_URI) as checkpointer:
 
     # list checkpoints
     [c async for c in checkpointer.alist(read_config)]
-```
+```

libs/checkpoint-postgres/langgraph/checkpoint/postgres/__init__.py

@@ -61,9 +61,9 @@ class PostgresSaver(BasePostgresSaver):
     def setup(self) -> None:
         """Set up the checkpoint database asynchronously.
 
-        This method creates the necessary tables in the SQLite database if they don't
-        already exist. It is called automatically when needed and should not be called
-        directly by the user.
+        This method creates the necessary tables in the Postgres database if they don't
+        already exist and runs database migrations. It MUST be called directly by the user
+        the first time checkpointer is used.
         """
         with self.lock:
             with self.conn.cursor(binary=True) as cur:
@@ -90,6 +90,38 @@ class PostgresSaver(BasePostgresSaver):
         before: Optional[RunnableConfig] = None,
         limit: Optional[int] = None,
     ) -> Iterator[CheckpointTuple]:
+        """List checkpoints from the database.
+
+        This method retrieves a list of checkpoint tuples from the Postgres database based
+        on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
+
+        Args:
+            config (RunnableConfig): The config to use for listing the checkpoints.
+            filter (Optional[Dict[str, Any]]): Additional filtering criteria for metadata. Defaults to None.
+            before (Optional[RunnableConfig]): If provided, only checkpoints before the specified checkpoint ID are returned. Defaults to None.
+            limit (Optional[int]): The maximum number of checkpoints to return. Defaults to None.
+
+        Yields:
+            Iterator[CheckpointTuple]: An iterator of checkpoint tuples.
+
+        Examples:
+            >>> from langgraph.checkpoint.postgres import PostgresSaver
+            >>> DB_URI = "postgres://postgres:postgres@localhost:5432/postgres?sslmode=disable"
+            >>> with PostgresSaver.from_conn_string(DB_URI) as memory:
+            ... # Run a graph, then list the checkpoints
+            >>>     config = {"configurable": {"thread_id": "1"}}
+            >>>     checkpoints = list(memory.list(config, limit=2))
+            >>> print(checkpoints)
+            [CheckpointTuple(...), CheckpointTuple(...)]
+
+            >>> config = {"configurable": {"thread_id": "1"}}
+            >>> before = {"configurable": {"checkpoint_id": "1ef4f797-8335-6428-8001-8a1503f9b875"}}
+            >>> with PostgresSaver.from_conn_string(DB_URI) as memory:
+            ... # Run a graph, then list the checkpoints
+            >>>     checkpoints = list(memory.list(config, before=before))
+            >>> print(checkpoints)
+            [CheckpointTuple(...), ...]
+        """
         where, args = self._search_where(config, filter, before)
         query = self.SELECT_SQL + where + " ORDER BY checkpoint_id DESC"
         if limit:
@@ -121,6 +153,40 @@ class PostgresSaver(BasePostgresSaver):
             )
 
     def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+        """Get a checkpoint tuple from the database.
+
+        This method retrieves a checkpoint tuple from the Postgres database based on the
+        provided config. If the config contains a "checkpoint_id" key, the checkpoint with
+        the matching thread ID and timestamp is retrieved. Otherwise, the latest checkpoint
+        for the given thread ID is retrieved.
+
+        Args:
+            config (RunnableConfig): The config to use for retrieving the checkpoint.
+
+        Returns:
+            Optional[CheckpointTuple]: The retrieved checkpoint tuple, or None if no matching checkpoint was found.
+
+        Examples:
+
+            Basic:
+            >>> config = {"configurable": {"thread_id": "1"}}
+            >>> checkpoint_tuple = memory.get_tuple(config)
+            >>> print(checkpoint_tuple)
+            CheckpointTuple(...)
+
+            With timestamp:
+
+            >>> config = {
+            ...    "configurable": {
+            ...        "thread_id": "1",
+            ...        "checkpoint_ns": "",
+            ...        "checkpoint_id": "1ef4f797-8335-6428-8001-8a1503f9b875",
+            ...    }
+            ... }
+            >>> checkpoint_tuple = memory.get_tuple(config)
+            >>> print(checkpoint_tuple)
+            CheckpointTuple(...)
+        """  # noqa
         thread_id = config["configurable"]["thread_id"]
         checkpoint_id = get_checkpoint_id(config)
         checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
@@ -171,6 +237,31 @@ class PostgresSaver(BasePostgresSaver):
         metadata: CheckpointMetadata,
         new_versions: ChannelVersions,
     ) -> RunnableConfig:
+        """Save a checkpoint to the database.
+
+        This method saves a checkpoint to the Postgres database. The checkpoint is associated
+        with the provided config and its parent config (if any).
+
+        Args:
+            config (RunnableConfig): The config to associate with the checkpoint.
+            checkpoint (Checkpoint): The checkpoint to save.
+            metadata (CheckpointMetadata): Additional metadata to save with the checkpoint.
+            new_versions (ChannelVersions): New channel versions as of this write.
+
+        Returns:
+            RunnableConfig: Updated configuration after storing the checkpoint.
+
+        Examples:
+
+            >>> from langgraph.checkpoint.postgres import PostgresSaver
+            >>> DB_URI = "postgres://postgres:postgres@localhost:5432/postgres?sslmode=disable"
+            >>> with PostgresSaver.from_conn_string(DB_URI) as memory:
+            >>>     config = {"configurable": {"thread_id": "1", "checkpoint_ns": ""}}
+            >>>     checkpoint = {"ts": "2024-05-04T06:32:42.235444+00:00", "id": "1ef4f797-8335-6428-8001-8a1503f9b875", "data": {"key": "value"}}
+            >>>     saved_config = memory.put(config, checkpoint, {"source": "input", "step": 1, "writes": {"key": "value"}}, {})
+            >>> print(saved_config)
+            {'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1ef4f797-8335-6428-8001-8a1503f9b875'}}
+        """
         configurable = config["configurable"].copy()
         thread_id = configurable.pop("thread_id")
         checkpoint_ns = configurable.pop("checkpoint_ns")
@@ -194,7 +285,6 @@ class PostgresSaver(BasePostgresSaver):
                     thread_id,
                     checkpoint_ns,
                     copy.pop("channel_values"),
-                    copy["channel_versions"],
                     new_versions,
                 ),
             )
@@ -217,6 +307,15 @@ class PostgresSaver(BasePostgresSaver):
         writes: List[tuple[str, Any]],
         task_id: str,
     ) -> None:
+        """Store intermediate writes linked to a checkpoint.
+
+        This method saves intermediate writes associated with a checkpoint to the Postgres database.
+
+        Args:
+            config (RunnableConfig): Configuration of the related checkpoint.
+            writes (List[Tuple[str, Any]]): List of writes to store.
+            task_id (str): Identifier for the task creating the writes.
+        """
         with self._cursor() as cur:
             cur.executemany(
                 self.UPSERT_CHECKPOINT_WRITES_SQL,

libs/checkpoint-postgres/langgraph/checkpoint/postgres/aio.py

@@ -59,18 +59,17 @@ class AsyncPostgresSaver(BasePostgresSaver):
     async def setup(self) -> None:
         """Set up the checkpoint database asynchronously.
 
-        This method creates the necessary tables in the SQLite database if they don't
-        already exist. It is called automatically when needed and should not be called
-        directly by the user.
+        This method creates the necessary tables in the Postgres database if they don't
+        already exist and runs database migrations. It MUST be called directly by the user
+        the first time checkpointer is used.
         """
         async with self.lock:
             async with self.conn.cursor(binary=True) as cur:
                 try:
-                    version = (
-                        await cur.execute(
-                            "SELECT v FROM checkpoint_migrations ORDER BY v DESC LIMIT 1"
-                        )
-                    ).fetchone()["v"]
+                    results = await cur.execute(
+                        "SELECT v FROM checkpoint_migrations ORDER BY v DESC LIMIT 1"
+                    )
+                    version = (await results.fetchone())["v"]
                 except UndefinedTable:
                     version = -1
                 for v, migration in zip(
@@ -92,6 +91,20 @@ class AsyncPostgresSaver(BasePostgresSaver):
         before: Optional[RunnableConfig] = None,
         limit: Optional[int] = None,
     ) -> AsyncIterator[CheckpointTuple]:
+        """List checkpoints from the database asynchronously.
+
+        This method retrieves a list of checkpoint tuples from the Postgres database based
+        on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
+
+        Args:
+            config (Optional[RunnableConfig]): Base configuration for filtering checkpoints.
+            filter (Optional[Dict[str, Any]]): Additional filtering criteria for metadata.
+            before (Optional[RunnableConfig]): If provided, only checkpoints before the specified checkpoint ID are returned. Defaults to None.
+            limit (Optional[int]): Maximum number of checkpoints to return.
+
+        Yields:
+            AsyncIterator[CheckpointTuple]: An asynchronous iterator of matching checkpoint tuples.
+        """
         where, args = self._search_where(config, filter, before)
         query = self.SELECT_SQL + where + " ORDER BY checkpoint_id DESC"
         if limit:
@@ -125,6 +138,19 @@ class AsyncPostgresSaver(BasePostgresSaver):
             )
 
     async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
+        """Get a checkpoint tuple from the database asynchronously.
+
+        This method retrieves a checkpoint tuple from the Postgres database based on the
+        provided config. If the config contains a "checkpoint_id" key, the checkpoint with
+        the matching thread ID and "checkpoint_id" is retrieved. Otherwise, the latest checkpoint
+        for the given thread ID is retrieved.
+
+        Args:
+            config (RunnableConfig): The config to use for retrieving the checkpoint.
+
+        Returns:
+            Optional[CheckpointTuple]: The retrieved checkpoint tuple, or None if no matching checkpoint was found.
+        """
         thread_id = config["configurable"]["thread_id"]
         checkpoint_id = get_checkpoint_id(config)
         checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
@@ -177,6 +203,20 @@ class AsyncPostgresSaver(BasePostgresSaver):
         metadata: CheckpointMetadata,
         new_versions: ChannelVersions,
     ) -> RunnableConfig:
+        """Save a checkpoint to the database asynchronously.
+
+        This method saves a checkpoint to the Postgres database. The checkpoint is associated
+        with the provided config and its parent config (if any).
+
+        Args:
+            config (RunnableConfig): The config to associate with the checkpoint.
+            checkpoint (Checkpoint): The checkpoint to save.
+            metadata (CheckpointMetadata): Additional metadata to save with the checkpoint.
+            new_versions (ChannelVersions): New channel versions as of this write.
+
+        Returns:
+            RunnableConfig: Updated configuration after storing the checkpoint.
+        """
         configurable = config["configurable"].copy()
         thread_id = configurable.pop("thread_id")
         checkpoint_ns = configurable.pop("checkpoint_ns")
@@ -201,7 +241,6 @@ class AsyncPostgresSaver(BasePostgresSaver):
                     thread_id,
                     checkpoint_ns,
                     copy.pop("channel_values"),
-                    copy["channel_versions"],
                     new_versions,
                 ),
             )
@@ -224,6 +263,15 @@ class AsyncPostgresSaver(BasePostgresSaver):
         writes: list[tuple[str, Any]],
         task_id: str,
     ) -> None:
+        """Store intermediate writes linked to a checkpoint asynchronously.
+
+        This method saves intermediate writes associated with a checkpoint to the database.
+
+        Args:
+            config (RunnableConfig): Configuration of the related checkpoint.
+            writes (Sequence[Tuple[str, Any]]): List of writes to store, each as (channel, value) pair.
+            task_id (str): Identifier for the task creating the writes.
+        """
         async with self._cursor() as cur:
             await cur.executemany(
                 self.UPSERT_CHECKPOINT_WRITES_SQL,

libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py

@@ -40,7 +40,7 @@ MIGRATIONS = [
     channel TEXT NOT NULL,
     version TEXT NOT NULL,
     type TEXT NOT NULL,
-    blob BYTEA NOT NULL,
+    blob BYTEA,
     PRIMARY KEY (thread_id, checkpoint_ns, channel, version)
 );""",
     """CREATE TABLE IF NOT EXISTS checkpoint_writes (
@@ -54,6 +54,7 @@ MIGRATIONS = [
     blob BYTEA NOT NULL,
     PRIMARY KEY (thread_id, checkpoint_ns, checkpoint_id, task_id, idx)
 );""",
+    "ALTER TABLE checkpoint_blobs ALTER COLUMN blob DROP not null;",
 ]
 
 SELECT_SQL = """
@@ -140,6 +141,7 @@ class BasePostgresSaver(BaseCheckpointSaver):
         return {
             k.decode(): self.serde.loads_typed((t.decode(), v))
             for k, t, v in blob_values
+            if t.decode() != "empty"
         }
 
     def _dump_blobs(
@@ -148,24 +150,23 @@ class BasePostgresSaver(BaseCheckpointSaver):
         checkpoint_ns: str,
         values: dict[str, Any],
         versions: dict[str, str],
-        new_versions: Optional[dict[str, str]],
     ) -> list[tuple[str, str, str, str, str, bytes]]:
         if not versions:
             return []
 
-        if new_versions:
-            versions = new_versions
-
         return [
             (
                 thread_id,
                 checkpoint_ns,
                 k,
                 ver,
-                *self.serde.dumps_typed(values[k]),
+                *(
+                    self.serde.dumps_typed(values[k])
+                    if k in values
+                    else ("empty", None)
+                ),
             )
             for k, ver in versions.items()
-            if k in values
         ]
 
     def _load_writes(

libs/checkpoint-postgres/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph-checkpoint-postgres"
-version = "1.0.0"
+version = "1.0.3"
 description = "Library with a Postgres implementation of LangGraph checkpoint saver."
 authors = []
 license = "MIT"

libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/__init__.py

@@ -176,7 +176,7 @@ class SqliteSaver(BaseCheckpointSaver):
 
         This method retrieves a checkpoint tuple from the SQLite database based on the
         provided config. If the config contains a "checkpoint_id" key, the checkpoint with
-        the matching thread ID and timestamp is retrieved. Otherwise, the latest checkpoint
+        the matching thread ID and checkpoint ID is retrieved. Otherwise, the latest checkpoint
         for the given thread ID is retrieved.
 
         Args:
@@ -193,12 +193,12 @@ class SqliteSaver(BaseCheckpointSaver):
             >>> print(checkpoint_tuple)
             CheckpointTuple(...)
 
-            With timestamp:
+            With checkpoint ID:
 
             >>> config = {
             ...    "configurable": {
             ...        "thread_id": "1",
-           ...         "checkpoint_ns": "",
+            ...        "checkpoint_ns": "",
             ...        "checkpoint_id": "1ef4f797-8335-6428-8001-8a1503f9b875",
             ...    }
             ... }
@@ -283,12 +283,12 @@ class SqliteSaver(BaseCheckpointSaver):
         """List checkpoints from the database.
 
         This method retrieves a list of checkpoint tuples from the SQLite database based
-        on the provided config. The checkpoints are ordered by timestamp in descending order.
+        on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
 
         Args:
             config (RunnableConfig): The config to use for listing the checkpoints.
             filter (Optional[Dict[str, Any]]): Additional filtering criteria for metadata. Defaults to None.
-            before (Optional[RunnableConfig]): If provided, only checkpoints before the specified timestamp are returned. Defaults to None.
+            before (Optional[RunnableConfig]): If provided, only checkpoints before the specified checkpoint ID are returned. Defaults to None.
             limit (Optional[int]): The maximum number of checkpoints to return. Defaults to None.
 
         Yields:
@@ -367,10 +367,11 @@ class SqliteSaver(BaseCheckpointSaver):
         Args:
             config (RunnableConfig): The config to associate with the checkpoint.
             checkpoint (Checkpoint): The checkpoint to save.
-            metadata (Optional[dict[str, Any]]): Additional metadata to save with the checkpoint. Defaults to None.
+            metadata (CheckpointMetadata): Additional metadata to save with the checkpoint.
+            new_versions (ChannelVersions): New channel versions as of this write.
 
         Returns:
-            RunnableConfig: The updated config containing the saved checkpoint's timestamp.
+            RunnableConfig: Updated configuration after storing the checkpoint.
 
         Examples:
 

libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/aio.py

@@ -230,7 +230,7 @@ class AsyncSqliteSaver(BaseCheckpointSaver):
 
         This method retrieves a checkpoint tuple from the SQLite database based on the
         provided config. If the config contains a "checkpoint_id" key, the checkpoint with
-        the matching thread ID and timestamp is retrieved. Otherwise, the latest checkpoint
+        the matching thread ID and checkpoint ID is retrieved. Otherwise, the latest checkpoint
         for the given thread ID is retrieved.
 
         Args:
@@ -317,12 +317,12 @@ class AsyncSqliteSaver(BaseCheckpointSaver):
         """List checkpoints from the database asynchronously.
 
         This method retrieves a list of checkpoint tuples from the SQLite database based
-        on the provided config. The checkpoints are ordered by timestamp in descending order.
+        on the provided config. The checkpoints are ordered by checkpoint ID in descending order (newest first).
 
         Args:
             config (Optional[RunnableConfig]): Base configuration for filtering checkpoints.
             filter (Optional[Dict[str, Any]]): Additional filtering criteria for metadata.
-            before (Optional[RunnableConfig]): List checkpoints created before this configuration.
+            before (Optional[RunnableConfig]): If provided, only checkpoints before the specified checkpoint ID are returned. Defaults to None.
             limit (Optional[int]): Maximum number of checkpoints to return.
 
         Yields:
@@ -385,10 +385,10 @@ class AsyncSqliteSaver(BaseCheckpointSaver):
             config (RunnableConfig): The config to associate with the checkpoint.
             checkpoint (Checkpoint): The checkpoint to save.
             metadata (CheckpointMetadata): Additional metadata to save with the checkpoint.
-            new_versions (dict): New versions as of this write
+            new_versions (ChannelVersions): New channel versions as of this write.
 
         Returns:
-            RunnableConfig: The updated config containing the saved checkpoint's timestamp.
+            RunnableConfig: Updated configuration after storing the checkpoint.
         """
         await self.setup()
         thread_id = config["configurable"]["thread_id"]

libs/checkpoint/langgraph/checkpoint/base/__init__.py

@@ -289,7 +289,7 @@ class BaseCheckpointSaver(ABC):
             config (RunnableConfig): Configuration for the checkpoint.
             checkpoint (Checkpoint): The checkpoint to store.
             metadata (CheckpointMetadata): Additional metadata for the checkpoint.
-            new_versions (dict): New versions as of this write
+            new_versions (ChannelVersions): New channel versions as of this write.
 
         Returns:
             RunnableConfig: Updated configuration after storing the checkpoint.
@@ -381,7 +381,7 @@ class BaseCheckpointSaver(ABC):
             config (RunnableConfig): Configuration for the checkpoint.
             checkpoint (Checkpoint): The checkpoint to store.
             metadata (CheckpointMetadata): Additional metadata for the checkpoint.
-            new_versions (dict): New versions as of this write
+            new_versions (ChannelVersions): New channel versions as of this write.
 
         Returns:
             RunnableConfig: Updated configuration after storing the checkpoint.

libs/langgraph/langgraph/constants.py

@@ -27,11 +27,15 @@ CHECKPOINT_NAMESPACE_SEPARATOR = "|"
 class Send:
     """A message or packet to send to a specific node in the graph.
 
-    The `Send` class is used within a `StateGraph`'s conditional edges to dynamically
-    route states to different nodes based on certain conditions. This enables
-    creating "map-reduce" like workflows, where a node can be invoked multiple times
-    in parallel on different states, and the results can be aggregated back into the
-    main graph's state.
+    The `Send` class is used within a `StateGraph`'s conditional edges to
+    dynamically invoke a node with a custom state at the next step.
+
+    Importantly, the sent state can differ from the core graph's state,
+    allowing for flexible and dynamic workflow management.
+
+    One such example is a "map-reduce" workflow where your graph invokes
+    the same node multiple times in parallel with different states,
+    before aggregating the results back into the main graph's state.
 
     Attributes:
         node (str): The name of the target node to send the message to.
@@ -55,6 +59,8 @@ class Send:
         >>> builder.add_conditional_edges(START, continue_to_jokes)
         >>> builder.add_edge("generate_joke", END)
         >>> graph = builder.compile()
+        >>>
+        >>> # Invoking with two subjects results in a generated joke for each
         >>> graph.invoke({"subjects": ["cats", "dogs"]})
         {'subjects': ['cats', 'dogs'], 'jokes': ['Joke about cats', 'Joke about dogs']}
     """

libs/langgraph/langgraph/pregel/__init__.py

@@ -100,6 +100,7 @@ from langgraph.pregel.types import (
     StateSnapshot,
     StreamMode,
 )
+from langgraph.pregel.utils import get_new_channel_versions
 from langgraph.pregel.validate import validate_graph, validate_keys
 from langgraph.pregel.write import ChannelWrite, ChannelWriteEntry
 
@@ -517,6 +518,9 @@ class Pregel(
         # get last checkpoint
         saved = self.checkpointer.get_tuple(config)
         checkpoint = copy_checkpoint(saved.checkpoint) if saved else empty_checkpoint()
+        checkpoint_previous_versions = (
+            saved.checkpoint["channel_versions"] if saved else {}
+        )
         step = saved.metadata.get("step", -1) if saved else -1
         # merge configurable fields with previous checkpoint config
         checkpoint_config = {
@@ -606,6 +610,9 @@ class Pregel(
                 checkpoint, channels, [task], self.checkpointer.get_next_version
             )
 
+            new_versions = get_new_channel_versions(
+                checkpoint_previous_versions, checkpoint["channel_versions"]
+            )
             return self.checkpointer.put(
                 checkpoint_config,
                 create_checkpoint(checkpoint, channels, step + 1),
@@ -614,7 +621,7 @@ class Pregel(
                     "step": step + 1,
                     "writes": {as_node: values},
                 },
-                {},
+                new_versions,
             )
 
     async def aupdate_state(
@@ -629,6 +636,9 @@ class Pregel(
         # get last checkpoint
         saved = await self.checkpointer.aget_tuple(config)
         checkpoint = copy_checkpoint(saved.checkpoint) if saved else empty_checkpoint()
+        checkpoint_previous_versions = (
+            saved.checkpoint["channel_versions"] if saved else {}
+        )
         step = saved.metadata.get("step", -1) if saved else -1
         # merge configurable fields with previous checkpoint config
         checkpoint_config = {
@@ -716,6 +726,9 @@ class Pregel(
                 checkpoint, channels, [task], self.checkpointer.get_next_version
             )
 
+            new_versions = get_new_channel_versions(
+                checkpoint_previous_versions, checkpoint["channel_versions"]
+            )
             return await self.checkpointer.aput(
                 checkpoint_config,
                 create_checkpoint(checkpoint, channels, step + 1),
@@ -724,7 +737,7 @@ class Pregel(
                     "step": step + 1,
                     "writes": {as_node: values},
                 },
-                {},
+                new_versions,
             )
 
     def _defaults(

libs/langgraph/langgraph/pregel/loop.py

@@ -61,6 +61,7 @@ from langgraph.pregel.executor import (
 )
 from langgraph.pregel.io import map_input, map_output_updates, map_output_values, single
 from langgraph.pregel.types import PregelExecutableTask
+from langgraph.pregel.utils import get_new_channel_versions
 
 if TYPE_CHECKING:
     from langgraph.pregel import Pregel
@@ -336,16 +337,9 @@ class PregelLoop:
             }
 
             channel_versions = self.checkpoint["channel_versions"].copy()
-            if self.checkpoint_previous_versions:
-                new_versions = {
-                    k: v
-                    for k, v in channel_versions.items()
-                    if k not in self.checkpoint_previous_versions
-                    or k in self.checkpoint_previous_versions
-                    and v > self.checkpoint_previous_versions[k]
-                }
-            else:
-                new_versions = channel_versions
+            new_versions = get_new_channel_versions(
+                self.checkpoint_previous_versions, channel_versions
+            )
 
             self.checkpoint_previous_versions = channel_versions
 

libs/langgraph/langgraph/pregel/utils.py

@@ -0,0 +1,19 @@
+from langgraph.checkpoint.base import ChannelVersions
+
+
+def get_new_channel_versions(
+    previous_versions: ChannelVersions, current_versions: ChannelVersions
+) -> ChannelVersions:
+    """Get new channel versions."""
+    if previous_versions:
+        version_type = type(next(iter(current_versions.values()), None))
+        null_version = version_type()
+        new_versions = {
+            k: v
+            for k, v in current_versions.items()
+            if v > previous_versions.get(k, null_version)
+        }
+    else:
+        new_versions = current_versions
+
+    return new_versions

libs/langgraph/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph"
-version = "0.2.2"
+version = "0.2.3"
 description = "Building stateful, multi-actor applications with LLMs"
 authors = []
 license = "MIT"

libs/langgraph/tests/test_interruption.py

@@ -1,10 +1,18 @@
 from typing import TypedDict
 
-from langgraph.checkpoint.memory import MemorySaver
+import pytest
+from pytest_mock import MockerFixture
+
 from langgraph.graph import END, START, StateGraph
 
 
-def test_interruption_without_state_updates():
+@pytest.mark.parametrize(
+    "checkpointer_name",
+    ["memory", "sqlite", "postgres", "postgres_pipe"],
+)
+def test_interruption_without_state_updates(
+    request: pytest.FixtureRequest, checkpointer_name: str, mocker: MockerFixture
+) -> None:
     """Test interruption without state updates. This test confirms that
     interrupting doesn't require a state key having been updated in the prev step"""
 
@@ -23,9 +31,8 @@ def test_interruption_without_state_updates():
     builder.add_edge("step_2", "step_3")
     builder.add_edge("step_3", END)
 
-    memory = MemorySaver()
-
-    graph = builder.compile(checkpointer=memory, interrupt_after="*")
+    checkpointer = request.getfixturevalue(f"checkpointer_{checkpointer_name}")
+    graph = builder.compile(checkpointer=checkpointer, interrupt_after="*")
 
     initial_input = {"input": "hello world"}
     thread = {"configurable": {"thread_id": "1"}}
@@ -40,7 +47,13 @@ def test_interruption_without_state_updates():
     assert graph.get_state(thread).next == ()
 
 
-async def test_interruption_without_state_updates_async():
+@pytest.mark.parametrize(
+    "checkpointer_name",
+    ["memory", "sqlite_aio", "postgres_aio", "postgres_aio_pipe"],
+)
+async def test_interruption_without_state_updates_async(
+    request: pytest.FixtureRequest, checkpointer_name: str, mocker: MockerFixture
+):
     """Test interruption without state updates. This test confirms that
     interrupting doesn't require a state key having been updated in the prev step"""
 
@@ -59,9 +72,8 @@ async def test_interruption_without_state_updates_async():
     builder.add_edge("step_2", "step_3")
     builder.add_edge("step_3", END)
 
-    memory = MemorySaver()
-
-    graph = builder.compile(checkpointer=memory, interrupt_after="*")
+    checkpointer = request.getfixturevalue(f"checkpointer_{checkpointer_name}")
+    graph = builder.compile(checkpointer=checkpointer, interrupt_after="*")
 
     initial_input = {"input": "hello world"}
     thread = {"configurable": {"thread_id": "1"}}

libs/langgraph/tests/test_prebuilt.py

@@ -18,11 +18,8 @@ from langchain_core.tools import BaseTool
 from langchain_core.tools import tool as dec_tool
 from pydantic import BaseModel as BaseModelV2
 
-from langgraph.checkpoint.base import BaseCheckpointSaver
 from langgraph.prebuilt import ToolNode, ValidationNode, create_react_agent
 from langgraph.prebuilt.tool_node import InjectedState
-from tests.any_str import AnyStr
-from tests.memory_assert import MemorySaverAssertImmutable
 from tests.messages import _AnyIdHumanMessage
 
 
@@ -54,18 +51,13 @@ class FakeToolCallingModel(BaseChatModel):
 
 
 @pytest.mark.parametrize(
-    "checkpointer",
-    [
-        MemorySaverAssertImmutable(),
-        None,
-    ],
-    ids=[
-        "memory",
-        "none",
-    ],
+    "checkpointer_name",
+    ["memory", "sqlite", "postgres", "postgres_pipe"],
 )
-def test_no_modifier(checkpointer: Optional[BaseCheckpointSaver]):
+def test_no_modifier(request: pytest.FixtureRequest, checkpointer_name: str) -> None:
+    checkpointer = request.getfixturevalue("checkpointer_" + checkpointer_name)
     model = FakeToolCallingModel()
+
     agent = create_react_agent(model, [], checkpointer=checkpointer)
     inputs = [HumanMessage("hi?")]
     thread = {"configurable": {"thread_id": "123"}}
@@ -76,30 +68,12 @@ def test_no_modifier(checkpointer: Optional[BaseCheckpointSaver]):
     if checkpointer:
         saved = checkpointer.get_tuple(thread)
         assert saved is not None
-        assert saved.checkpoint == {
-            "v": 1,
-            "ts": AnyStr(),
-            "id": AnyStr(),
-            "channel_values": {
-                "messages": [
-                    _AnyIdHumanMessage(content="hi?"),
-                    AIMessage(content="hi?", id="0"),
-                ],
-                "agent": "agent",
-            },
-            "channel_versions": {
-                "__start__": 2,
-                "messages": 3,
-                "start:agent": 3,
-                "agent": 3,
-            },
-            "versions_seen": {
-                "__input__": {},
-                "__start__": {"__start__": 1},
-                "agent": {"start:agent": 2},
-            },
-            "pending_sends": [],
-            "current_tasks": {},
+        assert saved.checkpoint["channel_values"] == {
+            "messages": [
+                _AnyIdHumanMessage(content="hi?"),
+                AIMessage(content="hi?", id="0"),
+            ],
+            "agent": "agent",
         }
         assert saved.metadata == {
             "source": "loop",
@@ -110,18 +84,16 @@ def test_no_modifier(checkpointer: Optional[BaseCheckpointSaver]):
 
 
 @pytest.mark.parametrize(
-    "checkpointer",
-    [
-        MemorySaverAssertImmutable(),
-        None,
-    ],
-    ids=[
-        "memory",
-        "none",
-    ],
+    "checkpointer_name",
+    ["memory", "sqlite_aio", "postgres_aio", "postgres_aio_pipe"],
 )
-async def test_no_modifier_async(checkpointer: Optional[BaseCheckpointSaver]):
+async def test_no_modifier_async(
+    request: pytest.FixtureRequest, checkpointer_name: str
+) -> None:
+    checkpointer = request.getfixturevalue(f"checkpointer_{checkpointer_name}")
+
     model = FakeToolCallingModel()
+
     agent = create_react_agent(model, [], checkpointer=checkpointer)
     inputs = [HumanMessage("hi?")]
     thread = {"configurable": {"thread_id": "123"}}
@@ -132,30 +104,12 @@ async def test_no_modifier_async(checkpointer: Optional[BaseCheckpointSaver]):
     if checkpointer:
         saved = await checkpointer.aget_tuple(thread)
         assert saved is not None
-        assert saved.checkpoint == {
-            "v": 1,
-            "ts": AnyStr(),
-            "id": AnyStr(),
-            "channel_values": {
-                "messages": [
-                    _AnyIdHumanMessage(content="hi?"),
-                    AIMessage(content="hi?", id="0"),
-                ],
-                "agent": "agent",
-            },
-            "channel_versions": {
-                "__start__": 2,
-                "messages": 3,
-                "start:agent": 3,
-                "agent": 3,
-            },
-            "versions_seen": {
-                "__input__": {},
-                "__start__": {"__start__": 1},
-                "agent": {"start:agent": 2},
-            },
-            "pending_sends": [],
-            "current_tasks": {},
+        assert saved.checkpoint["channel_values"] == {
+            "messages": [
+                _AnyIdHumanMessage(content="hi?"),
+                AIMessage(content="hi?", id="0"),
+            ],
+            "agent": "agent",
         }
         assert saved.metadata == {
             "source": "loop",

libs/langgraph/tests/test_pregel.py

@@ -36,6 +36,7 @@ from syrupy import SnapshotAssertion
 from langgraph.channels.base import BaseChannel
 from langgraph.channels.binop import BinaryOperatorAggregate
 from langgraph.channels.context import Context
+from langgraph.channels.ephemeral_value import EphemeralValue
 from langgraph.channels.last_value import LastValue
 from langgraph.channels.topic import Topic
 from langgraph.channels.untracked_value import UntrackedValue
@@ -7452,12 +7453,20 @@ def test_simple_multi_edge(snapshot: SnapshotAssertion) -> None:
 
     assert app.get_graph().draw_mermaid(with_styles=False) == snapshot
     assert app.invoke({"my_key": "my_value"}) == {"my_key": "my_value_more"}
-    assert [*app.stream({"my_key": "my_value"})] == [
-        {"up": None},
-        {"side": None},
-        {"other": {"my_key": "_more"}},
-        {"down": None},
-    ]
+    assert [*app.stream({"my_key": "my_value"})] in (
+        [
+            {"up": None},
+            {"side": None},
+            {"other": {"my_key": "_more"}},
+            {"down": None},
+        ],
+        [
+            {"up": None},
+            {"other": {"my_key": "_more"}},
+            {"side": None},
+            {"down": None},
+        ],
+    )
 
 
 def test_nested_graph_xray(snapshot: SnapshotAssertion) -> None:
@@ -9191,7 +9200,13 @@ def test_checkpoint_metadata() -> None:
         assert chkpnt_tuple.metadata["test_config_4"] == "bar"
 
 
-def test_remove_message_via_state_update():
+@pytest.mark.parametrize(
+    "checkpointer_name",
+    ["memory", "sqlite", "postgres", "postgres_pipe"],
+)
+def test_remove_message_via_state_update(
+    request: pytest.FixtureRequest, checkpointer_name: str
+) -> None:
     from langchain_core.messages import AIMessage, HumanMessage, RemoveMessage
 
     workflow = MessageGraph()
@@ -9207,7 +9222,7 @@ def test_remove_message_via_state_update():
     workflow.set_entry_point("chatbot")
     workflow.add_edge("chatbot", END)
 
-    checkpointer = MemorySaver()
+    checkpointer = request.getfixturevalue("checkpointer_" + checkpointer_name)
     app = workflow.compile(checkpointer=checkpointer)
     config = {"configurable": {"thread_id": "1"}}
     output = app.invoke([HumanMessage(content="Hi")], config=config)
@@ -9370,3 +9385,29 @@ def test_xray_lance(snapshot: SnapshotAssertion):
     # View
     assert graph.get_graph().to_json() == snapshot
     assert graph.get_graph(xray=1).to_json() == snapshot
+
+
+@pytest.mark.parametrize(
+    "checkpointer_name",
+    ["memory", "sqlite", "postgres", "postgres_pipe"],
+)
+def test_channel_values(request: pytest.FixtureRequest, checkpointer_name: str) -> None:
+    checkpointer = request.getfixturevalue(f"checkpointer_{checkpointer_name}")
+
+    config = {"configurable": {"thread_id": "1"}}
+    chain = Channel.subscribe_to("input") | Channel.write_to("output")
+    app = Pregel(
+        nodes={
+            "one": chain,
+        },
+        channels={
+            "ephemeral": EphemeralValue(Any),
+            "input": LastValue(int),
+            "output": LastValue(int),
+        },
+        input_channels=["input", "ephemeral"],
+        output_channels="output",
+        checkpointer=checkpointer,
+    )
+    app.invoke({"input": 1, "ephemeral": "meow"}, config)
+    assert checkpointer.get(config)["channel_values"] == {"input": 1, "output": 1}

libs/langgraph/tests/test_pregel_async.py

@@ -2,8 +2,7 @@ import asyncio
 import json
 import operator
 from collections import Counter
-from contextlib import AbstractAsyncContextManager, asynccontextmanager, contextmanager
-from types import TracebackType
+from contextlib import asynccontextmanager, contextmanager
 from typing import (
     Annotated,
     Any,
@@ -67,19 +66,6 @@ from tests.memory_assert import (
 from tests.messages import _AnyIdAIMessage, _AnyIdHumanMessage
 
 
-class NoneContextManager(AbstractAsyncContextManager):
-    async def __aenter__(self) -> None:
-        return None
-
-    async def __aexit__(
-        self,
-        __exc_type: Optional[type[BaseException]],
-        __exc_value: Optional[BaseException],
-        __traceback: Optional[TracebackType],
-    ) -> Optional[bool]:
-        return
-
-
 async def test_checkpoint_errors() -> None:
     class FaultyGetCheckpointer(MemorySaver):
         async def aget_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:

libs/sdk-js/src/schema.ts

@@ -27,7 +27,7 @@ export interface Config {
     /**
      * Timestamp of the state checkpoint
      */
-    thread_ts?: string;
+    checkpoint_id?: string;
     [key: string]: unknown;
   };
 }

libs/sdk-py/langgraph_sdk/client.py

@@ -783,7 +783,8 @@ class ThreadsClient:
                         'configurable':
                             {
                                 'thread_id': 'e2496803-ecd5-4e0c-a779-3226296181c2',
-                                'thread_ts': '1ef4a9b8-e6fb-67b1-8001-abd5184439d1'
+                                'checkpoint_ns': '',
+                                'checkpoint_id': '1ef4a9b8-e6fb-67b1-8001-abd5184439d1'
                             }
                     },
                 'metadata':
@@ -822,7 +823,8 @@ class ThreadsClient:
                         'configurable':
                             {
                                 'thread_id': 'e2496803-ecd5-4e0c-a779-3226296181c2',
-                                'thread_ts': '1ef4a9b8-d80d-6fa7-8000-9300467fad0f'
+                                'checkpoint_ns': '',
+                                'checkpoint_id': '1ef4a9b8-d80d-6fa7-8000-9300467fad0f'
                             }
                     }
             }
@@ -1184,7 +1186,7 @@ class RunsClient:
                                         'user_id': None,
                                         'graph_id': 'agent',
                                         'thread_id': 'my_thread_id',
-                                        'thread_ts': None,
+                                        'checkpoint_id': None,
                                         'model_name': "openai",
                                         'assistant_id': 'my_assistant_id'
                                     }

poetry.lock

@@ -968,7 +968,7 @@ typing-extensions = ">=4.7"
 
 [[package]]
 name = "langgraph"
-version = "0.1.17"
+version = "0.2.2"
 description = "Building stateful, multi-actor applications with LLMs"
 optional = false
 python-versions = ">=3.9.0,<4.0"
@@ -977,6 +977,7 @@ develop = true
 
 [package.dependencies]
 langchain-core = ">=0.2.27,<0.3"
+langgraph-checkpoint = "^1.0.2"
 
 [package.source]
 type = "directory"
@@ -984,7 +985,7 @@ url = "libs/langgraph"
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "1.0.0"
+version = "1.0.2"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -999,16 +1000,35 @@ type = "directory"
 url = "libs/checkpoint"
 
 [[package]]
-name = "langgraph-checkpoint-sqlite"
-version = "1.0.0"
-description = "Library with a SQLite implementation of LangGraph checkpoint saver."
+name = "langgraph-checkpoint-postgres"
+version = "1.0.1"
+description = "Library with a Postgres implementation of LangGraph checkpoint saver."
 optional = false
 python-versions = "^3.9.0,<4.0"
 files = []
 develop = true
 
+[package.dependencies]
+langgraph-checkpoint = "^1.0.1"
+orjson = ">=3.10.1"
+psycopg = {version = ">=3.1.19", extras = ["binary"]}
+
+[package.source]
+type = "directory"
+url = "libs/checkpoint-postgres"
+
+[[package]]
+name = "langgraph-checkpoint-sqlite"
+version = "1.0.0"
+description = "Library with a SQLite implementation of LangGraph checkpoint saver."
+optional = false
+python-versions = "^3.9.0"
+files = []
+develop = true
+
 [package.dependencies]
 aiosqlite = "^0.20.0"
+langgraph-checkpoint = "^1.0.1"
 
 [package.source]
 type = "directory"
@@ -1016,7 +1036,7 @@ url = "libs/checkpoint-sqlite"
 
 [[package]]
 name = "langgraph-sdk"
-version = "0.1.26"
+version = "0.1.27"
 description = "SDK for interacting with LangGraph API"
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -1852,6 +1872,92 @@ files = [
 [package.extras]
 test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
 
+[[package]]
+name = "psycopg"
+version = "3.2.1"
+description = "PostgreSQL database adapter for Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "psycopg-3.2.1-py3-none-any.whl", hash = "sha256:ece385fb413a37db332f97c49208b36cf030ff02b199d7635ed2fbd378724175"},
+    {file = "psycopg-3.2.1.tar.gz", hash = "sha256:dc8da6dc8729dacacda3cc2f17d2c9397a70a66cf0d2b69c91065d60d5f00cb7"},
+]
+
+[package.dependencies]
+psycopg-binary = {version = "3.2.1", optional = true, markers = "implementation_name != \"pypy\" and extra == \"binary\""}
+typing-extensions = ">=4.4"
+tzdata = {version = "*", markers = "sys_platform == \"win32\""}
+
+[package.extras]
+binary = ["psycopg-binary (==3.2.1)"]
+c = ["psycopg-c (==3.2.1)"]
+dev = ["ast-comments (>=1.1.2)", "black (>=24.1.0)", "codespell (>=2.2)", "dnspython (>=2.1)", "flake8 (>=4.0)", "mypy (>=1.6)", "types-setuptools (>=57.4)", "wheel (>=0.37)"]
+docs = ["Sphinx (>=5.0)", "furo (==2022.6.21)", "sphinx-autobuild (>=2021.3.14)", "sphinx-autodoc-typehints (>=1.12)"]
+pool = ["psycopg-pool"]
+test = ["anyio (>=4.0)", "mypy (>=1.6)", "pproxy (>=2.7)", "pytest (>=6.2.5)", "pytest-cov (>=3.0)", "pytest-randomly (>=3.5)"]
+
+[[package]]
+name = "psycopg-binary"
+version = "3.2.1"
+description = "PostgreSQL database adapter for Python -- C optimisation distribution"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "psycopg_binary-3.2.1-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:cad2de17804c4cfee8640ae2b279d616bb9e4734ac3c17c13db5e40982bd710d"},
+    {file = "psycopg_binary-3.2.1-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:592b27d6c46a40f9eeaaeea7c1fef6f3c60b02c634365eb649b2d880669f149f"},
+    {file = "psycopg_binary-3.2.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9a997efbaadb5e1a294fb5760e2f5643d7b8e4e3fe6cb6f09e6d605fd28e0291"},
+    {file = "psycopg_binary-3.2.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c1d2b6438fb83376f43ebb798bf0ad5e57bc56c03c9c29c85bc15405c8c0ac5a"},
+    {file = "psycopg_binary-3.2.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b1f087bd84bdcac78bf9f024ebdbfacd07fc0a23ec8191448a50679e2ac4a19e"},
+    {file = "psycopg_binary-3.2.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:415c3b72ea32119163255c6504085f374e47ae7345f14bc3f0ef1f6e0976a879"},
+    {file = "psycopg_binary-3.2.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:f092114f10f81fb6bae544a0ec027eb720e2d9c74a4fcdaa9dd3899873136935"},
+    {file = "psycopg_binary-3.2.1-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:06a7aae34edfe179ddc04da005e083ff6c6b0020000399a2cbf0a7121a8a22ea"},
+    {file = "psycopg_binary-3.2.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:0b018631e5c80ce9bc210b71ea885932f9cca6db131e4df505653d7e3873a938"},
+    {file = "psycopg_binary-3.2.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:f8a509aeaac364fa965454e80cd110fe6d48ba2c80f56c9b8563423f0b5c3cfd"},
+    {file = "psycopg_binary-3.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:413977d18412ff83486eeb5875eb00b185a9391c57febac45b8993bf9c0ff489"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:62b1b7b07e00ee490afb39c0a47d8282a9c2822c7cfed9553a04b0058adf7e7f"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:f8afb07114ea9b924a4a0305ceb15354ccf0ef3c0e14d54b8dbeb03e50182dd7"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:40bb515d042f6a345714ec0403df68ccf13f73b05e567837d80c886c7c9d3805"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6418712ba63cebb0c88c050b3997185b0ef54173b36568522d5634ac06153040"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:101472468d59c74bb8565fab603e032803fd533d16be4b2d13da1bab8deb32a3"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa3931f308ab4a479d0ee22dc04bea867a6365cac0172e5ddcba359da043854b"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:dc314a47d44fe1a8069b075a64abffad347a3a1d8652fed1bab5d3baea37acb2"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:cc304a46be1e291031148d9d95c12451ffe783ff0cc72f18e2cc7ec43cdb8c68"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:6f9e13600647087df5928875559f0eb8f496f53e6278b7da9511b4b3d0aff960"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b140182830c76c74d17eba27df3755a46442ce8d4fb299e7f1cf2f74a87c877b"},
+    {file = "psycopg_binary-3.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:3c838806eeb99af39f934b7999e35f947a8e577997cc892c12b5053a97a9057f"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:7066d3dca196ed0dc6172f9777b2d62e4f138705886be656cccff2d555234d60"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:28ada5f610468c57d8a4a055a8ea915d0085a43d794266c4f3b9d02f4288f4db"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2e8213bf50af073b1aa8dc3cff123bfeedac86332a16c1b7274910bc88a847c7"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:74d623261655a169bc84a9669890975c229f2fa6e19a7f2d10a77675dcf1a707"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:42781ba94e8842ee98bca5a7d0c44cc9d067500fedca2d6a90fa3609b6d16b42"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:33e6669091d09f8ba36e10ce678a6d9916e110446236a9b92346464a3565635e"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:b09e8a576a2ac69d695032ee76f31e03b30781828b5dd6d18c6a009e5a3d1c35"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:8f28ff0cb9f1defdc4a6f8c958bf6787274247e7dfeca811f6e2f56602695fb1"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:4c84fcac8a3a3479ac14673095cc4e1fdba2935499f72c436785ac679bec0d1a"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:950fd666ec9e9fe6a8eeb2b5a8f17301790e518953730ad44d715b59ffdbc67f"},
+    {file = "psycopg_binary-3.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:334046a937bb086c36e2c6889fe327f9f29bfc085d678f70fac0b0618949f674"},
+    {file = "psycopg_binary-3.2.1-cp38-cp38-macosx_12_0_x86_64.whl", hash = "sha256:1d6833f607f3fc7b22226a9e121235d3b84c0eda1d3caab174673ef698f63788"},
+    {file = "psycopg_binary-3.2.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1d353e028b8f848b9784450fc2abf149d53a738d451eab3ee4c85703438128b9"},
+    {file = "psycopg_binary-3.2.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f34e369891f77d0738e5d25727c307d06d5344948771e5379ea29c76c6d84555"},
+    {file = "psycopg_binary-3.2.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0ab58213cc976a1666f66bc1cb2e602315cd753b7981a8e17237ac2a185bd4a1"},
+    {file = "psycopg_binary-3.2.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b0104a72a17aa84b3b7dcab6c84826c595355bf54bb6ea6d284dcb06d99c6801"},
+    {file = "psycopg_binary-3.2.1-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:059cbd4e6da2337e17707178fe49464ed01de867dc86c677b30751755ec1dc51"},
+    {file = "psycopg_binary-3.2.1-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:73f9c9b984be9c322b5ec1515b12df1ee5896029f5e72d46160eb6517438659c"},
+    {file = "psycopg_binary-3.2.1-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:af0469c00f24c4bec18c3d2ede124bf62688d88d1b8a5f3c3edc2f61046fe0d7"},
+    {file = "psycopg_binary-3.2.1-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:463d55345f73ff391df8177a185ad57b552915ad33f5cc2b31b930500c068b22"},
+    {file = "psycopg_binary-3.2.1-cp38-cp38-win_amd64.whl", hash = "sha256:302b86f92c0d76e99fe1b5c22c492ae519ce8b98b88d37ef74fda4c9e24c6b46"},
+    {file = "psycopg_binary-3.2.1-cp39-cp39-macosx_12_0_x86_64.whl", hash = "sha256:0879b5d76b7d48678d31278242aaf951bc2d69ca4e4d7cef117e4bbf7bfefda9"},
+    {file = "psycopg_binary-3.2.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f99e59f8a5f4dcd9cbdec445f3d8ac950a492fc0e211032384d6992ed3c17eb7"},
+    {file = "psycopg_binary-3.2.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:84837e99353d16c6980603b362d0f03302d4b06c71672a6651f38df8a482923d"},
+    {file = "psycopg_binary-3.2.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7ce965caf618061817f66c0906f0452aef966c293ae0933d4fa5a16ea6eaf5bb"},
+    {file = "psycopg_binary-3.2.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78c2007caf3c90f08685c5378e3ceb142bafd5636be7495f7d86ec8a977eaeef"},
+    {file = "psycopg_binary-3.2.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:7a84b5eb194a258116154b2a4ff2962ea60ea52de089508db23a51d3d6b1c7d1"},
+    {file = "psycopg_binary-3.2.1-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:4a42b8f9ab39affcd5249b45cac763ac3cf12df962b67e23fd15a2ee2932afe5"},
+    {file = "psycopg_binary-3.2.1-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:788ffc43d7517c13e624c83e0e553b7b8823c9655e18296566d36a829bfb373f"},
+    {file = "psycopg_binary-3.2.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:21927f41c4d722ae8eb30d62a6ce732c398eac230509af5ba1749a337f8a63e2"},
+    {file = "psycopg_binary-3.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:921f0c7f39590763d64a619de84d1b142587acc70fd11cbb5ba8fa39786f3073"},
+]
+
 [[package]]
 name = "ptyprocess"
 version = "0.7.0"
@@ -2723,4 +2829,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "e55f683b5c1fc8f540cf53e9f80e180996e199250fbae54954dd7981c389fbec"
+content-hash = "8bbefefef5e786ed86783a98ff0809cfaaad26d59b2d83623c269587a3bf5f7a"

pyproject.toml

@@ -13,6 +13,7 @@ python = "^3.10"
 langgraph = { path = "libs/langgraph/", develop = true }
 langgraph-checkpoint = { path = "libs/checkpoint/", develop = true }
 langgraph-checkpoint-sqlite = { path = "libs/checkpoint-sqlite", develop = true }
+langgraph-checkpoint-postgres = { path = "libs/checkpoint-postgres", develop = true }
 langgraph-sdk = {path = "libs/sdk-py", develop = true}
 mkdocs = "^1.6.0"
 mkdocstrings = "^0.25.1"