Hybrid RAG
Zero-cloud SQLite FTS5 RAG engine & GitHub Action
What it does
Context-grounded repository AI assistant using Hybrid RAG (Okapi BM25 + Dense Semantic Vector Search + Reciprocal Rank Fusion k=60). Features markdown AST-aware chunking for deterministic line-span citations ([file#L-L]), zero-dependency @vercel/ncc bundling, and zero-cloud SQLite FTS5 execution.
Context-grounded repository AI assistant using Hybrid RAG (BM25 + Semantic Vector Search + Reciprocal Rank Fusion) and GitHub Models. - Cagrik34/hybrid-rag-action
A production-grade, context-grounded GitHub Action that automatically answers Issues , Pull Requests , and Discussions using a state-of-the-art Hybrid RAG (BM25 + Dense Semantic Vector Search + Reciprocal Rank Fusion) architecture. flowchart LR A[Issue / PR Event] --> B[Hybrid Chunker] B --> C1[Sparse: Okapi BM25] B --> C2[Dense: Semantic Vectors] C1 & C2 --> D[Reciprocal Rank Fusion - RRF] D --> E[Grounded Prompt Assembly] E --> F[Inference: GitHub Models / Phi-4] F --> G[Verified Markdown Comment with Citations] Loading 💎 Key Features Zero-Container Overhead: Executes natively on node20 in under 3 seconds. Hybrid Search Engine: Combines exact keyword matching (Okapi BM25) with dense…from github.com
Does the same job
all alternatives →
- AOAirgapped Offline RAG – Run LLMs Locally with Llama, Mistral, & Gemini2024 · github.com · ▲9
I've built an airgapped Retrieval-Augmented Generation (RAG) system for question-answering on documents, running entirely offline with local inference. Using Llama 3, Mistral, and Gemini, this setup allows secure, private NLP on your own machine. Perfect for researchers, data scientists, and developers who need to process sensitive data without cloud dependencies. Built with Llama C++, LangChain, and Streamlit, it supports quantized models and provides a sleek UI for document processing. Check it out, contribute, or suggest new features!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com