Langgraph Bigtool

langgraph-bigtool

`langgraph-bigtool` is a Python library for creating [LangGraph](https://langchain-ai.github.io/langgraph/) agents that can access large numbers of tools. It leverages LangGraph's long-term [memory store](https://langchain-ai.github.io/langgraph/how-tos/memory/semantic-search/) to allow an agent to search for and retrieve relevant tools for a given problem.

Features

• 🧰 Scalable access to tools: Equip agents with hundreds or thousands of tools.
• 📝 Storage of tool metadata: Control storage of tool descriptions, namespaces, and other information through LangGraph's built-in persistence layer. Includes support for in-memory and Postgres backends.
• 💡 Customization of tool retrieval: Optionally define custom functions for tool retrieval.

This library is built on top of [LangGraph](https://github.com/langchain-ai/langgraph), a powerful framework for building agent applications, and comes with out-of-box support for [streaming](https://langchain-ai.github.io/langgraph/how-tos/#streaming), [short-term and long-term memory](https://langchain-ai.github.io/langgraph/concepts/memory/) and [human-in-the-loop](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/).

Installation

pip install langgraph-bigtool

Quickstart

We demonstrate `langgraph-bigtool` by equipping an agent with all functions from Python's built-in `math` library.

[!NOTE] This includes about 50 tools. Some LLMs can handle this number of tools together in a single invocation without issue. This example is for demonstration purposes.

pip install langgraph-bigtool "langchain[openai]"

export OPENAI_API_KEY=

import math
import types
import uuid

from langc