RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 53 of 53
Deterministic coordinate pre-routing and epistemic abstention for legal RAG
Sentence-level claim and NLI verification with KV-cache rollback during generation, for legal RAG
Shared-budget extractive context trimming for LlamaIndex text nodes.
A small, fully local retrieval-augmented Q&A CLI — no internet needed at query time, no data leaves your machine.
Convert text into compact logical form for token-efficient RAG
A response generator run with Ollama and ChromaDb.
LLM dataset preparation, pedagogical semantic chunking, and RAG ingestion from OpenStax textbooks
Local-first Hybrid GraphRAG retrieval engine and MCP server for linked knowledge bases
A modular, multi-paradigm Retrieval-Augmented Generation (RAG) framework supporting Vector, Agentic, and Graph RAG architectures.
Evidence-backed RAG with verified citations and refusal on insufficient evidence.
Agentic retrieval at scale: an agent ranks and reads passages, a chain of sub-questions names the evidence the question leaves unnamed, and one call answers with exact citations.
Optional Python client SDK for witty-rag / rag_core REST APIs
Measure whether a retrieval system is actually retrieving the right things
Private, local document search: PDFs, Office files and images, with page-level citations.
The project for RAG example workflow
A domain-retargetable, open-core engine for hybrid retrieval + knowledge-graph RAG: parsing, chunking, embedding, hybrid search, reranking, graph extraction, entity resolution, ontology-driven knowledge, and a capability runtime.
Load and chunk documents, create embeddings, and retrieve context for RAG applications
A framework for building, evaluating, and diagnosing RAG systems.
Python SDK for the RAGnarok HTTP API (/api/v1): auth, streaming queries, ingest, graph and sources.
Domain-agnostic RAG toolkit: embeddings, chunking, vector stores, retrieval, ingestion, evaluation, and jobs.
Pre-ingestion diagnostic for RAG knowledge bases, grounded in the Garani 2026 taxonomy of 33 RAG failure modes
Evaluation-first RAG pipeline: retrieval, generation, deterministic metrics, and guardrails for sensitive domains.
Evidence-first RAG retrieval diagnostics, built to run locally.
Local RAG search engine and MCP server for AI agents (Claude Code, Cursor, VS Code): hybrid BM25 + semantic search with reranking over Markdown and Obsidian notes, PDF, Office files and emails, fast at tens of millions of passages. Backlinks, metadata filters, browser UI. Runs on your own GPU or CPU: no cloud, no API keys.
Grounded question answering over technical books, with citation and code verification.
Tune LangChain, LangGraph, and Google ADK RAG pipelines
Measure which parts of a Turkish RAG pipeline pay off: chunking, stemming, embedding model, fusion.
Production hierarchical RAG: structure-aware Search, agentic retrieval, experience edges
HPO RAG as implemented by Brandon T. Garcia 2025.
Retrieval augmented generation composition for the Aoguan Python SDK
A RAG agent built on Pydantic.
Chunk-level quality verification for RAG ingestion: independence, completeness, traceability, semantic independence, template completeness
Multimodal visual context extraction from screen shares, meeting recordings and real-world videos for Video RAG pipelines
RAG knowledge base and long-term memory for BanglaClaw (Bangla-aware chunking, Qdrant)
Cross-agent Raw-RAG incremental memory indexer and MLX two-stage retrieval MCP server for Claude Code, Codex, OpenCode, Oh My Pi, and Antigravity
An AI agent CLI package with Web UI and the RAG.
Headless diagnostic for PDF RAG pipelines: attributes a lost answer to the pipeline stage that lost it.
SDK for building RAG chatbots from dynamic sources
Persistent retrieval, inference, documents and graphs for LangChain with Antfly
Retrieval-augmented generation with verifiable citations over technical documentation, source code and immutable records.
Production-grade modular RAG framework
Local Markdown knowledge retrieval with versioned evidence
Placeholder: name reserved for RagScene, a docs-retrieval (RAG) product. No functionality yet.
Python SDK for SeaArt RAG and RAGFlow APIs
超极速、零算力、零幻觉的纯文本 RAG 检索结构 (Base90 极简硬路由)
Local retrieval over your own authoritative documents. Every answer carries a quote that a check confirms, or says it is not in the sources.
Multimodal local search over documents and media — pdf, office files, notes, images, audio and subtitles — from any MCP-capable agent.
Native Rust RAG evaluation with Odia-first multilingual, BM25/RRF and local reranking support
Build, evaluate, and ship Retrieval-Augmented Generation (RAG) for Persian text — offline-first, with a free Persian course.
Persian-first retrieval-augmented generation toolkit
Find and automatically repair broken RAG chunks before you embed them. Zero dependencies.
Evidence search tools and workflows for agents using Ragwell
Efferent composable agent framework, 0.22.0. Node 24 or Bun.
Efferent composable agent framework, 0.22.0. Node 24 or Bun.
Native Python retrieval with source-linked evidence, coverage estimates and execution diagnostics.
LangChain adapter for Cragkit retrieval with access scope bound by the application.
Pydantic AI capability for Asyntai: give your agent a whole website's knowledge, chats and leads
Unofficial implementation of SpectRAG (Sahinoglu, Mohammed, Kazangirler and Kazangirler, arXiv:2610.36991): spectral graph-augmented retrieval for multi-hop RAG. Official code: github.com/SightAndCite/SpectRAG