Skip to main content

Use Composio to get array of tools with LnagGraph Agent Workflows

Project description

🦜🕸️ Using Composio With LangGraph

Integrate Composio with LangGraph Agentic workflows & enable them to interact seamlessly with external apps, enhancing their functionality and reach.

Goal

  • Star a repository on GitHub using natural language commands through a LangGraph Agent.

Installation and Setup

Ensure you have the necessary packages installed and connect your GitHub account to allow your agents to utilize GitHub functionalities.

# Install Composio LangGraph package
pip install composio-langgraph

# Connect your GitHub account
composio-cli add github

# View available applications you can connect with
composio-cli show-apps

Usage Steps

1. Import Base Packages

Prepare your environment by initializing necessary imports from LangGraph & LangChain for setting up your agent.

from typing import Literal

from langchain_openai import ChatOpenAI
from langgraph.graph import MessagesState, StateGraph
from langgraph.prebuilt import ToolNode

2. Fetch GitHub LangGraph Tools via Composio

Access GitHub tools provided by Composio for LangGraph, initialize a ToolNode with necessary tools obtaned from ComposioToolSet.

from composio_langgraph import Action, ComposioToolSet

# Initialize the toolset for GitHub
composio_toolset = ComposioToolSet()
tools = composio_toolset.get_actions(
    actions=[
        Action.GITHUB_ACTIVITY_STAR_REPO_FOR_AUTHENTICATED_USER,
        Action.GITHUB_USERS_GET_AUTHENTICATED,
    ])
tool_node = ToolNode(tools)

3. Prepare the model

Initialize the LLM class and bind obtained tools to the model.

model = ChatOpenAI(temperature=0, streaming=True)
model_with_tools = model.bind_tools(functions)

4. Define the Graph Nodes

LangGraph expects you to define different nodes of the agentic workflow as separate functions. Here we define a node for calling the LLM model.

def call_model(state: MessagesState):
    messages = state["messages"]
    response = model_with_tools.invoke(messages)
    return {"messages": [response]}

5. Define the Graph Nodes and Edges

To establish the agent's workflow, we begin by initializing the workflow with agent and tools node, followed by specifying the connecting edges between nodes, finally compiling the workflow. These edges can be straightforward or conditional, depending on the workflow requirements.

def should_continue(state: MessagesState) -> Literal["tools", "__end__"]:
    messages = state["messages"]
    last_message = messages[-1]
    if last_message.tool_calls:
        return "tools"
    return "__end__"


workflow = StateGraph(MessagesState)

# Define the two nodes we will cycle between
workflow.add_node("agent", call_model)
workflow.add_node("tools", tool_node)

workflow.add_edge("__start__", "agent")
workflow.add_conditional_edges(
    "agent",
    should_continue,
)
workflow.add_edge("tools", "agent")

app = workflow.compile()

6. Invoke & Check Response

After the compilation of workflow, we invoke the LLM with a task, and stream the response.

for chunk in app.stream(
    {
        "messages": [
            (
                "human",
                # "Star the Github Repository composiohq/composio",
                "Get my information.",
            )
        ]
    },
    stream_mode="values",
):
    chunk["messages"][-1].pretty_print()

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

composio_langgraph-0.5.46.tar.gz (3.7 kB view details)

Uploaded Source

Built Distribution

composio_langgraph-0.5.46-py3-none-any.whl (4.2 kB view details)

Uploaded Python 3

File details

Details for the file composio_langgraph-0.5.46.tar.gz.

File metadata

  • Download URL: composio_langgraph-0.5.46.tar.gz
  • Upload date:
  • Size: 3.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for composio_langgraph-0.5.46.tar.gz
Algorithm Hash digest
SHA256 df7e0ce49ee85d6a30757e8b3ff78a576fe419aacbee36584eda9065a66e411b
MD5 b2995743656d783e59703bf861d45441
BLAKE2b-256 d109cdb90e8731366725dc1f585e19b6ce29998816c95a281310349312954499

See more details on using hashes here.

File details

Details for the file composio_langgraph-0.5.46-py3-none-any.whl.

File metadata

File hashes

Hashes for composio_langgraph-0.5.46-py3-none-any.whl
Algorithm Hash digest
SHA256 c29509e43dfe0562d70cb803635ed101104bca0a6093cb8e397a039db3f28b80
MD5 68e11aa24238f2ae25c45451f1aa025b
BLAKE2b-256 a0d9de8105eda176bb8453acabe3525715a01a0d08300d5a6ec0c96bfb5867cb

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page