RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 48 of 53
Rag
A Python package for RAG pipelines using OpenAI and FAISS.
Portable Retrieval-Augmented Generation Library
Portable Retrieval-Augmented Generation Library
Retrive PDF files context for your LLMs
ragpipe: iterate quickly on your RAG pipelines.
RAG in 3 functions. Ingest any data source into vector databases.
ragpipe-lite: unified RAG ingestion pipeline (loaders, chunking, embeddings, vector store export).
Lightweight, production-ready RAG toolkit with 50-70% accuracy improvements. Enhanced BM25, BGE-Base embeddings, and semantic chunking - 100% offline.
Unified RAG service abstraction for vector stores like Qdrant.
This project implements a local-first RAG chat system that reads and processes various text-based log files. It splits the content into manageable chunks, generates embeddings using Ollama or OpenAI, and allows users to interactively query the logs for specific information. The application features a customizable response format and supports configuration for user preferences.
A modular RAG SDK for ingesting web, document, and API sources, chunking them, and storing embeddings in pluggable vector databases.
Unified data extraction and preprocessing toolkit for Retrieval-Augmented Generation (RAG) pipelines.
retrieval-augmented generation made simple
Zero-config RAG integration for LangChain, LlamaIndex, and AI agents
RAG over CSVs and documents, with citations, ingestion diagnostics, and a built-in evaluation harness.
Async RAG toolkit on top of Postgres/pgvector and Voyage AI.
Ragstack is a one-click solution to deploy the retrieval augmented generation stack on your own infrastructure with open-source LLMs.
DataStax RAGStack
DataStax RAGStack Colbert implementation
DataStax RAGStack Langchain
DataStax RAGStack Llama Index
CLI tool to help retrieve RAG context from a corpus of documents.
RAG pipelines
Fetch, distill, and store authoritative references for external libraries
ragstruct - A Pseudo-Finetuning RAG Framework for structured JSON-based retrieval
Crossing Minds RAGsys python library
Python bindings for the Ragtastic API
Modular toolkit for building Retrieval-Augmented Generation (RAG) pipelines.
It is a ragtrain!
Add your description here
A package that abstracts most of the utilities used in RAG applications
Self-optimizing RAG: adaptive pipeline routing, multi-LLM, citations, persistence
Async-first version tracking system for RAG applications
A open-source tool to to visualise your RAG documents 🔮.
The way to build RAG — modular, configurable, plugin-based
Production-grade RAG toolkit for document ingestion and retrieval with hybrid search support
Production-grade RAG in 4 lines — hybrid search, streaming, and agent tools on by default.
A simple RAG (Retrieval-Augumented Generation) Task Manager
A RAG (Retrieval-Augmented Generation) toolkit with Milvus integration
A open-source tool to to visualise your RAG documents 🔮.
A simple RAG (Retrieval-Augmented Generation) framework for Python.
Fast local RAG - search your documents with AI, no cloud needed
Haystack pipelines with Ray
Simple, Safe, and Secure RAG from Haize Labs
RAG读取与构建index知识库
Add your description here
No-brainer vectorless RAG combining docling and toon-python
Integration of the Restless and Haystack libraries for Django
retrievalagent — multi-backend retrieval-augmented generation with LangGraph
RAG functions
Fast, efficient, minimal, extendible and elegant RAG system
Add your description here
RUBRIC Autograder Workbench for evaluating retrieval, generation, and RAG information systems
A RAG stack installer
A document-ingesting agent that monitors specified directories, keeping stored documents up to date in a vector database for Retrieval-Augmented Generation (RAG) queries.
Pipelines for RAG on scientific papers
A short description of your project.
TOON-Native Auto-Embedding & RAG Toolkit for MariaDB — VECTOR(N), HNSW, VEC_DISTANCE_COSINE, with TOON tabular output that saves 10-55% LLM tokens vs JSON.
My tiny package
SECURAG
Sgraal memory governance filter for RAG pipelines
Significance-threshold retrieval for RAG pipelines — stop injecting noise into your LLM context
A simple interface for using Ollama with LangChain's RAGChain
A minimal, easy-to-use RAG (Retrieval Augmented Generation) library.
Reflection-RAG
This package will help you talk to your data using Retrieval Augmented Generation (RAG).
Sinapsis templates for LlamaIndex retrieval and ingestion.
A minimal, dependency-free Retrieval-Augmented Generation (RAG) engine using SQLite as a local vector store.
Small-to-Big RAG implementation for more effective retrieval augmented generation
A smart Multi-modal RAG (Retrieval Augmented Generation) library for processing PDFs with various language models
Retrieval Augmented Generation with Image Snippets from PDFs
A Snowflake integration for the Haystack framework.
Small vector-search layer (ChromaDB and sentence-transformers) extracted from the Socrates prototype (research prototype)
Minimal local-first Retrieval-Augmented Generation (RAG) library using SQLite with sqlite-vec
A modular toolkit for decomposed question answering, rank chunks , summaring these chunks for a final answer using LLM's in RAG pipelines.
Reusable components and complete chat system to improve Large Language Models (LLMs) capabilities when generating SPARQL queries for a given set of endpoints, using Retrieval-Augmented Generation (RAG) and SPARQL query validation from the endpoint schema.
spRAG
Python-first application framework over SPECTER and RAGOT
Client library for SPT Neo RAG API
An open-source Generative AI (GenAI) application designed to provide users
Prepare and query vector embeddings for RAG applications using DuckDB
Config-driven enterprise RAG architecture generator for serverless infrastructure
Haystack integration for supabase
Super-performant RAG pipelines for AI apps
Verified data deletion and leak detection for RAG systems
Sutra-RAG: The Contextual Retriever library bridging raw data with LLM prompts
GPU-first RAG engine with cross-encoder reranking and quality validation. One engine, any domain.
Haystack components for Swiss Truth — certified knowledge base for AI agents
LangChain tools for Swiss Truth — certified knowledge base for AI agents
LlamaIndex tools & retriever for Swiss Truth — certified knowledge base for AI agents
Production-oriented Python framework for building RAG services on top of FastAPI.
Enhancing translation with RAG-powered large language models
RAG library
Topology-Aware Retrieval for RAG — structure from folders down to sections inside files, with no LLM in the routing
Production-ready Telegram FAQ bot with Russian LLMs, RAG, and multi-provider fallback