RAG

The source code for a paper on a token-efficient, agentic retrieval-augmented generation framework that compresses both retrieved content and reasoning steps to answer complex queries with fewer tokens and faster reasoning.

• RAG
• Papers

Notebook code for building production-oriented retrieval-augmented generation systems with LangGraph orchestration and local Ollama models, aimed at keeping document data and inference on the developer's own machine.

• RAG
• Tutorials

A Python integration that lets the Haystack framework use Qdrant as its document store, as a drop-in replacement for other vector embedding stores.

• RAG
• Databases

The official implementation of a paper on retrieval-augmented generation that decides when to retrieve based on statistics from the model's pre-training corpus, rather than relying on the model's own, often miscalibrated, internal confidence signals.

• RAG
• Papers

An open benchmark, harness and set of embedding models for fashion product retrieval, letting a shopper find products from a photo or a plain-language description and measuring results at full catalog scale against other embedding models.

• RAG
• AI evals

A local-first Windows desktop application and read-only MCP server for searching private Markdown, PDF and Tika-backed document collections using a combination of exact text search and semantic vector search.

• MCP servers
• RAG

A Python framework for declarative document indexing, where typed schemas describe what to extract from a document and Ennoia runs the extraction, stores the structured output, and serves combined filter and vector search over it.

• RAG

A local-first context-compression pipeline for Claude Code that uses hybrid BM25 and embedding retrieval plus AST-aware code chunking to reduce how many tokens of a codebase are sent to the model.

• Agent memory
• RAG

An embedded, ACID-compliant database that combines SQL tables, vector and keyword search, and a bi-temporal knowledge graph in one engine and file, and assembles token-budgeted context for an LLM in a single query.

• RAG
• Databases

A SQL-like query language and command-line shell for the Qdrant vector database, letting a developer write insert, search and filter statements instead of calling the Qdrant Python client directly.

• RAG
• Databases

A local retrieval and maintenance layer for a Markdown knowledge base such as Obsidian or Logseq, indexing notes into SQLite with full-text search, embeddings and a link graph, and exposing it to any MCP client.

• MCP servers
• RAG

An experimental retrieval-augmented generation system that ingests any MediaWiki site through its API and answers questions about that content through an OpenAI-compatible API, built as a Moodle Research project.

• RAG

An autonomous multi-agent research orchestrator that runs specialized AI agents for literature mining, data synthesis and hypothesis testing, allocating shared compute as tradeable market credits.

• Agent frameworks
• RAG

A research implementation of retrieval-augmented generation for relation extraction, providing an end-to-end pipeline that runs with and without retrieval across several standard relation-extraction datasets.

• RAG
• Papers

A production-style document assistant that lets a user upload PDFs such as financial reports or legal contracts and chat with a retrieval-augmented model that cites the exact source page for every answer.

• RAG

A toolkit that collects content from Git, Confluence, JIRA, public documentation sites and local files, vectorizes it into a Qdrant database, and serves it back through an MCP search server.

• MCP servers
• RAG

A post-retrieval layer for RAG pipelines that filters out expired documents, applies time decay and freshness scoring, and reranks results so a fresh, still-valid document outranks an outdated one.

• RAG

A citation and ontology knowledge graph built from structured PubMed metadata rather than LLM extraction, used to answer biomedical questions with traceable evidence and no answer when a claim cannot be traced.

• RAG

An airgapped, closed-corpus question-answering demo where a self-hosted Qwen3.6 agent explores a zipped document collection with local tools, such as bash, grep, embeddings and rerankers, under a fixed token budget, to test how test-time compute affects search.

• RAG

A single-binary, fully offline Rust CLI that combines semantic and lexical search over a codebase to hand an AI agent only the relevant code, with file paths, line ranges and confidence scores, instead of full files.

• RAG
• CLI tools

An MCP server and command-line tool that makes a folder of Markdown notes searchable by meaning rather than only by keyword, splitting notes into chunks, embedding them with a locally or remotely configured model, and indexing the result in a local FAISS store.

• MCP servers
• RAG

An enterprise, multi-tenant Agentic RAG knowledge-base system with a Vue.js frontend, a Spring Boot backend and a FastAPI LLM service, where the model chooses its own retrieval tools across several rounds and exposes knowledge bases to agents over MCP.

• RAG

A Python library for migrating a vector index to a new embedding model progressively, serving search from the existing index while target vectors are computed and cached in the background, instead of re-embedding the whole corpus before the new model can serve any traffic.

• RAG
• Databases

A local code-indexing MCP server for AI coding agents that combines SQLite full-text search, tree-sitter parsing and embeddings into a single searchable index, replacing many rounds of grep and file reads with direct symbol, call-graph and semantic queries.

• MCP servers
• RAG