Skip to content

Latest commit

 

History

History
47 lines (38 loc) · 1.22 KB

README_en.md

File metadata and controls

47 lines (38 loc) · 1.22 KB

semantic-file-retrieval

A lightweight semantic file retrieval application based on LLM and vector db.

中文版README

Architecture

architecture_image

Demo

retrieve_image.mp4

Quick Start

  1. Install Dependencies
pip install -r requirements.txt

  1. Config your OLLAMA_BASE_URL or GLM_API_KEY in local .env file

  2. Run the project

streamlit run main.py

Docker Deployment

  1. Build the docker image
docker build -t semantic-file-retrieval:latest .
  1. Run the docker container
docker run -d -e OLLAMA_BASE_URL="http://x.x.x.x:11434" -p 8501:8501 semantic-file-retrieval:latest

All the environment variables in .env file can be overridden by docker run command

TODO

  • Support audios
  • Support videos
  • Support parsing scanned pdf
  • Support office documents
  • Support retrieve image by image
  • Support batch uploading(upload folders)
  • Provide restful APIs for customized integration
  • Support offline processing for large files
  • Support filtering retrieving results by file type
  • Support traditional file retrival(querying by keywords)