Python package to create the LangChain tool from the Tool Directory For LangChain.
Can create LangChain tool from definition in the Tool Directory.
pip install pytool-directory
- Search tools for your destination from Tool Directory For LangChain.
- Load tools from the name of integration.
from tool_directory import ToolLoader
tools = ToolLoader('openweather').get_tools(parameters={'appid': 'YOUR_APP_ID_FOR_OPENWEATHER'})
- Ask question to LLM with tools.
llm = ChatOpenAI(temperature=0, model_name='gpt-4')
agent = initialize_agent(tools, llm, agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
answer = agent('Please tell me about the temperature in tokyo.')
Use a tool for the OpenWeather API to get the weather information on specified location.
This example execute following conversation via ChatGPT.
User: Please tell me about the temperature in tokyo.
Bot: The current temperature in Tokyo is 29.54°C, but it feels like 32.72°C. The minimum and maximum temperatures today are 27.74°C and 30.45°C respectively. The humidity is 64%.
- Fork and clone repository.
- Install development dependencies.
pip install '.[dev]'
- Install pre-commit hook for linter and formatter.
pre-commit install
- Commit your changes and send pull request.