Simple Streamlit as well as Chainlit app to have interaction with your website URL.
- OpenAI model as Large Language model
- Ollama and
mistral
as Large Language model - LangChain as a Framework for LLM
- Streamlit as well as Chainlit for deploying.
You must have Python 3.9 or later installed. Earlier versions of python may not compile.
- Fork this repository and create a codespace in GitHub as I showed you in the youtube video OR Clone it locally.
git clone https://github.com/sudarshan-koirala/chat-with-website.git
cd chat-with-website
-
Rename example.env to .env with
cp example.env .env
and input the OpenAI API key as follows. Get OpenAI API key from this URL. You need to create an account in OpenAI webiste if you haven't already.OPENAI_API_KEY=your_openai_api_key
For langsmith, take the environment variables from LangSmith website
-
Create a virtualenv and activate it
python3 -m venv .venv && source .venv/bin/activate
-
Run the following command in the terminal to install necessary python packages:
pip install -r requirements.txt
-
Run the following command in your terminal to start the chat UI:
streamlit run chat_with_website_openai.py streamlit run chat_with_website_ollama.py
-
For chainlit, use the following command in your terminal.
python3 ingest.py #for ingesting
chainlit run main.py #for chainlit ui