#Retrieval
Showing 60 of 85 repositories tagged #retrieval, ranked by stars
๐ PageIndex: Document Index for Vectorless, Reasoning-based RAG
Open-source context retrieval layer for AI agents
Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read
SimpleMem: Efficient Lifelong Memory for LLM Agents โ Text & Multimodal
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
OpenKB: Open LLM Knowledge Base
User Profile-Based Long-Term Memory for AI Chatbot Applications.
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
โก Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platformsโก
Open-source inference server and production cluster for all the models your agent needs.
Study guides for MIT's 15.003 Data Science Tools
Fast BM25 search in Python, powered by Numpy and Numba
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Open CLI for integrating AI search, recommendation, and conversational retrieval into agent systems and business systems
Parsing-free RAG supported by VLMs
Rust library for generating vector embeddings, reranking locally!
Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
Epsilla is a high performance Vector Database Management System
Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.
Generative Representational Instruction Tuning
๐ฅ Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation ๐ฅ. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techniques, 24+ state-of-the-art Reranking models, and multiple RAG methods.
Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch
Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps ๅฝ้ ๆๆ่ต 2024 ๅญฃๅๆนๆก
97% token reduction for AI coding sessions โ zero deps, 31 languages, MCP server
Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache.
In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.
The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.
Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.
Intelligent error monitoring agent that uses Airweave to find context from your code, tickets, and Slack. Clusters similar errors, enriches with relevant context, and creates actionable alerts.
Recipes for learning, fine-tuning, and adapting ColPali to your multimodal RAG use cases. ๐จ๐ปโ๐ณ
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.
Benchmarking library for RAG
Open-source RAG evaluation through users' feedback
Atmospheric data Community Toolkit - A python based toolkit for exploring and analyzing time series atmospheric datasets
Generate vector embeddings in NodeJS
๐ง Production-grade memory sidecar for AI agents โ gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-tested. | ็ไบง็บงๅคๆ่ฎฐๅฟ็ณป็ป๏ผๅ ผๅฎนHermes/Claude/Cursor็ญไปปๆAIๆบ่ฝไฝ
LLM for Drug Editing, ICLR 2024
(ACL 2025 Main) A Comprehensive Benchmark for Code Information Retrieval.
ChatIndex: Tree indexing and retrieval for long conversational memory
[EMNLP 2024] OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs.
Go implementation of @qdrant/fastembed.
Local coding-agent orchestrator โ DAG of auto-approved, git-worktree-isolated sub-sessions across LLM providers (Claude/Kimi/Grok/DeepSeek/local). AGPL-3.0.
Complete Code for "Hard-Aware-Deeply-Cascaded-Embedding"
Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.
A resource-efficient C++ vector index engine built for low-RAM production workloads
The relocalization task aims to estimate the 6-DoF pose of a novel (unseen) frame in the coordinate system given by the prior model of the world.
Context Runtime โ a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused substrate, and learns from the outcome.
RMAC implementation in Keras
High-quality search for AI-native applications.
Demo UI for the axgen library
Implementation of Marge, Pre-training via Paraphrasing, in Pytorch
An experimental implementation of the retrieval-enhanced language model
All-in-One: Text Embedding, Retrieval, Reranking and RAG in Transformers
Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment
Command-line tool for extracting DINO, CLIP, SigLIP2, TIPSv2, RADIO, features for images and videos