Easyrag
What is Easyrag
easyrag is a set of Easy RAG scripts designed for a local, embedded, MCP-enabled knowledge store, facilitating document processing and retrieval augmented generation using advanced technologies.
Use cases
Use cases for easyrag include academic research where large volumes of documents need to be processed, enterprise knowledge management systems for quick information retrieval, and personal projects that involve embedding and searching through diverse data formats.
How to use
To use easyrag, set up a virtual environment, install dependencies, configure your Google API key in a .env file, and then use the provided commands for data ingestion and searching within your knowledge store.
Key features
Key features of easyrag include integration with LlamaIndex for document processing, Gemini for generating embeddings, and LanceDB for efficient vector storage, enabling seamless retrieval and generation of information.
Where to use
easyrag can be used in various fields such as research, education, and any domain requiring efficient document retrieval and knowledge management, particularly where local and embedded solutions are preferred.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Easyrag
easyrag is a set of Easy RAG scripts designed for a local, embedded, MCP-enabled knowledge store, facilitating document processing and retrieval augmented generation using advanced technologies.
Use cases
Use cases for easyrag include academic research where large volumes of documents need to be processed, enterprise knowledge management systems for quick information retrieval, and personal projects that involve embedding and searching through diverse data formats.
How to use
To use easyrag, set up a virtual environment, install dependencies, configure your Google API key in a .env file, and then use the provided commands for data ingestion and searching within your knowledge store.
Key features
Key features of easyrag include integration with LlamaIndex for document processing, Gemini for generating embeddings, and LanceDB for efficient vector storage, enabling seamless retrieval and generation of information.
Where to use
easyrag can be used in various fields such as research, education, and any domain requiring efficient document retrieval and knowledge management, particularly where local and embedded solutions are preferred.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
LLM RAG
A RAG (Retrieval Augmented Generation) implementation using LlamaIndex for document processing, Gemini for embeddings, and LanceDB for vector storage.
Setup
This project uses uv for dependency management and direnv for environment management. To get started:
- Install dependencies:
# Create and activate a new virtual environment
uv venv
source .venv/bin/activate
# Install dependencies
uv pip install -e .
- Set up environment:
# Create .env file with your Google API key
echo "GOOGLE_API_KEY=your_key_here" > .env
# Allow direnv to load the environment
direnv allow
Usage
Data Ingestion
python -m llm_rag.ingest --source /path/to/source --type [code|url|pdf]
Search Server
python -m llm_rag.search --db /path/to/lancedb
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
