Skip to content

LLM App created using LangChain framework, connected to external data sources

License

Notifications You must be signed in to change notification settings

jaymit123/icebreaker

Repository files navigation

Ice Breaker

This web application provides information about a person and some ice breakers you can ask them.

Goal of this project to create a real world LLM based application using Langchain Framework

Technology used:

  • Langchain
    • Chat based LLM using Chat-GPT 3.5 turbo.
    • Langchain Agent of ZERO_SHOT_REACT_DESCRIPTION type.
    • PydanticOutputParser to serialize llm response to Python Object/JSON.
  • ProxyCurl scraping API - Search for LinkedIn accounts by name
  • SerpAPI - Get details for LinkedIn Accounts

Environment Variables

To run this project, you will need to add the following environment variables to your .env file

PYTHONPATH=/{YOUR_PATH_TO_PROJECT}/ice_breaker

OPENAI_API_KEY

PROXYCURL_API_KEY

SERPAPI_API_KEY

Run Locally

Clone the project

  git clone https://github.com/emarco177/ice_breaker.git

Go to the project directory

  cd ice_breaker

Install dependencies

  pipenv install

Start the flask server

  pipenv run app.py

Running Tests

To run tests, run the following command

  pipenv run pytest .

About

LLM App created using LangChain framework, connected to external data sources

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published