RAG

A GPU document parser that combines OCR, layout analysis, table and formula recognition into one CUDA and TensorRT pipeline, converting pages to Markdown at up to hundreds of images per second.

• RAG
• Inference

JamAI Base is an open-source retrieval-augmented-generation backend that pairs an embedded SQLite database with an embedded LanceDB vector store behind a spreadsheet-like UI and a REST API, so LLM calls, embeddings and reranking can be wired together as table columns.

• RAG
• Databases

A Python framework for end-to-end fine-tuning, inference and distillation of RAG retrieval models, covering embedding, ColBERT-style late-interaction, and reranker models.

• RAG

A CLI and MCP tool that turns PDFs, Office files, scans, screenshots, charts and diagrams into AI-ready Markdown, using any OpenAI-compatible multimodal model instead of a fixed OCR pipeline.

• MCP servers
• RAG

An open-source, self-hosted enterprise and site search server built on OpenSearch, with a web crawler for sites, file systems and databases, a REST API, and AI/RAG semantic search.

• RAG
• Databases

An enterprise-grade solution accelerator for building agentic retrieval-augmented generation systems on Microsoft Foundry, with Zero-Trust architecture and infrastructure-as-code deployment templates.

• RAG

An open command-line tool for integrating Volcengine's AI search, recommendation, and conversational retrieval into agent systems and business systems.

• RAG
• CLI tools

An enterprise AI knowledge platform that combines a multimodal document- and video-parsing engine with an ontology-driven knowledge graph, vector and graph indexing, and source-grounded retrieval.

• Agent memory
• RAG

A Python toolkit for retrieval-augmented generation that stores and searches documents in DuckDB or PostgreSQL, with configurable LLMs, rerankers, and hybrid keyword-and-vector search.

• RAG

A self-hosted search gateway for AI agents that exposes a single Perplexity-compatible search API backed by several providers, falling back to the next one automatically if one is rate-limited or down.

• RAG
• LLM gateways

A high-performance AI search and retrieval platform built for retrieval-augmented generation, semantic search, and hybrid search, designed to hold up to a billion vectors on a single node.

• RAG
• Databases

A local, ripgrep-based code search engine that uses vector embeddings to let developers search a codebase by meaning rather than exact text.

• RAG

A minimalist, multisource, multimodal local embedding pipeline built in Rust that generates embeddings from text, images, audio, and PDFs and streams them into a vector database with low memory use.

• RAG

A production-ready retrieval-augmented generation platform that combines graph RAG, vector search, and full-text search with AI agents, MCP support, and Kubernetes deployment for enterprise use.

• RAG

A personal knowledge-base tool that turns videos saved in a Bilibili favorites folder into a searchable, source-tracing archive by transcribing them, embedding the text, and answering questions through retrieval-augmented generation.

• RAG

A curated list of research papers, workshops, and tools on retrieval-augmented generation for large language models, organized by topic from embeddings to evaluation.

• RAG
• Papers

A curated list of tools, frameworks, techniques, and learning resources for building retrieval-augmented generation systems, organized by architecture patterns, frameworks, techniques, metrics, and production considerations.

• RAG
• Curated lists

An LLM knowledge-compilation engine that reads raw documents, such as PDFs, spreadsheets and transcripts, and synthesizes them into a persistent, cross-referenced wiki stored as local Markdown files, as an alternative to RAG.

• Agent memory
• RAG

A local-first codebase intelligence tool that gives coding agents and teams cited context from current code, git history and technical web research before they edit, review or debug.

• Agent memory
• RAG

A modified version of RAGFlow that adds an administrative backend for managing users, teams, files and knowledge bases, with document parsing switched to MinerU for better layout and image handling.

• RAG

A self-hosted enterprise knowledge hub and MCP server that compiles an organization's documents into a structured, permission-scoped wiki that Claude and other LLMs can query.

• MCP servers
• RAG

A Chinese medical question-answering system that combines a Neo4j knowledge graph of diseases with BERT-based entity recognition and a local LLM, using structured graph retrieval instead of a vector database to reduce hallucination.

• RAG
• Databases

An open-source enterprise AI platform that unifies multi-provider model routing, multimodal chat, file and RAG retrieval, MCP tools, usage billing, identity and audit logs into one deployable product.

• RAG
• LLM gateways

An advanced retrieval-augmented generation agent that uses a deterministic graph to answer complex questions over a user's own data that simple similarity search cannot solve.

• Agent frameworks
• RAG