doc-search-chain
This is a web application that provides a simplified RAG (Retrieval-Augmented Generation) functionality. By allowing documents (in formats such as txt and html) to be read by an LLM (ChatGPT), it offers a feature that answers questions based on the content described in the documents.
Getting Start
-
docker compose up -d --build - Access http://127.0.0.1:5000/
- Set the OpenAI API Key from the settings
- Open the "Document" tab and upload the document you want the LLM to read
- Press the "Loading the documents" button
- Finally, open the "Search" tab and ask the LLM a question
Setting Up Your Local Development Environment
-
mkdir ./docs echo '{"default_language": "Japanese", "theme": "light", "api_key": ""}' > app/config.json -
python -m venv venv - （for Windows）
.\venv\Scripts\activate -
pip install -r requirements.txt -
python .\app.py - Access http://127.0.0.1:5000/
Run the tests
python .\tests\test.py