langchain-dev-utils 1.4.5

A practical utility library for LangChain and LangGraph development

🦜️🧰 langchain-dev-utils

🚀 High-efficiency toolkit designed for LangChain and LangGraph developers

📚 English • 中文

This is the English version. For the Chinese version, please visit 中文版本

✨ Why choose langchain-dev-utils?

Tired of writing repetitive code in LangChain development? langchain-dev-utils is the solution you need! This lightweight yet powerful toolkit is designed to enhance the development experience of LangChain and LangGraph, helping you:

• ⚡ Boost development efficiency - Reduce boilerplate code, allowing you to focus on core functionality
• 🧩 Simplify complex workflows - Easily manage multi-model, multi-tool, and multi-agent applications
• 🔧 Enhance code quality - Improve consistency and readability, reducing maintenance costs
• 🎯 Accelerate prototype development - Quickly implement ideas, iterate and validate faster

🎯 Core Features

• 🔌 Unified model management - Specify model providers through strings, easily switch and combine different models
• 💬 Flexible message handling - Support for chain-of-thought concatenation, streaming processing, and message formatting
• 🛠️ Powerful tool calling - Built-in tool call detection, parameter parsing, and human review functionality
• 🤖 Efficient Agent development - Simplify agent creation process, expand more common middleware
• 📊 Convenient State Graph Construction - Provides pre-built functions to easily create sequential or parallel state graphs

⚡ Quick Start

This library is primarily used to connect to models that expose an OpenAI-Compatible API. The example below uses a qwen2.5-7b model served by vLLM.

1. Install langchain-dev-utils

pip install -U "langchain-dev-utils[standard]"

Note: This feature requires installing langchain-dev-utils[standard].

2. Start using

from langchain.tools import tool
from langchain_core.messages import HumanMessage
from langchain_dev_utils.chat_models import register_model_provider, load_chat_model
from langchain_dev_utils.agents import create_agent

# Register model provider
register_model_provider("vllm", "openai-compatible", base_url="http://localhost:8000/v1")

@tool
def get_current_weather(location: str) -> str:
    """Get the current weather for the specified location"""
    return f"25 degrees, {location}"

# Dynamically load model using string
model = load_chat_model("vllm:qwen2.5-7b")
response = model.invoke("Hello")
print(response)

# Create agent
agent = create_agent("vllm:qwen2.5-7b", tools=[get_current_weather])
response = agent.invoke({"messages": [HumanMessage(content="What's the weather like in New York today?")]})
print(response)

For more features of this library, please visit the full documentation

🛠️ GitHub Repository

Visit the GitHub repository to view the source code and report issues.

---

Developed with ❤️ and ☕

If this project helps you, please give us a ⭐️