RAG

A fast, efficient universal vector embedding utility package.

Data augmentation for NLP, presented at EMNLP 2019

[NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

Research feedback grounded in the papers that define your field

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.

A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).

memX: self-learning, self-maintaining memory plugin for AI agents; native support for claude code, codex, and openclaw

Transformers 3rd Edition

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

Implementation of triplet loss in TensorFlow

A deep dive into embeddings starting from fundamentals

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in Claude Code, Codex, Cursor, Aider, OpenHands.

Own your AI memory — import ChatGPT, Claude and Gemini exports, see what each AI knows about you. Checkpoint/restore and cross-model continuity for agents.

PostgreSQL vector database extension for building AI applications

A code repository indexing tool to supercharge your LLM experience.

面向 AI 助手的代码库索引与语义搜索 MCP Server

Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.

unified embedding model

SGPT: GPT Sentence Embeddings for Semantic Search

An LLM-powered advanced RAG pipeline built from scratch

Magick is a cutting-edge toolkit for a new kind of AI builder. Make Magick with us!

🪿 LinGoose is a Go framework for building awesome AI/LLM applications.

Fuzzy string matching, grouping, and evaluation.

Curated List of Persian Natural Language Processing and Information Retrieval Tools and Resources

The prime repository for state-of-the-art Multilingual Question Answering research and development.

LLMFlows - Simple, Explicit and Transparent LLM Apps

VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of your choice.

Generative Representational Instruction Tuning

NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve the relevance of search results on different platforms (i.e. Elasticsearch)

Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

Querying local documents, powered by LLM

Open-source, self-hosted alternative to NotebookLM. Chat with your documents, generate audio summaries, and ground AI in your own sources—built with Supabase and N8N on a React frontend.

A Python vector database you just need - no more, no less.

Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案

Hybrid search engine, combining best features of text and semantic search worlds

Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine

Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型，支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.

Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache.

🤖 A prototype assistant for writing and thinking

A Survey on Multimodal Retrieval-Augmented Generation

🔎 SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.

Your Local Artificial Memory on your Device.

Code For Medium Article: "How To Create Natural Language Semantic Search for Arbitrary Objects With Deep Learning"

[EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.

Semantic grep powered by Jina embeddings v5 (MLX on Apple Silicon)

High performance embedded vector database

Smart local file search app that understands your files