AI Agent Skills

The video search layer for AI agents. Search video by meaning — across speech, visuals, and on-screen text.

A Survey on Multimodal Retrieval-Augmented Generation

Notebooks and Code about Generative Ai, LLMs, MLOPS, NLP , CV and Graph databases

Secure AI conversations with documents, video, audio, and more. Personal workspaces for focused context, group spaces for shared insight. Classify docs, reuse prompts, a…

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM appli…

MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

The self-hosted AI workstation. Autonomous screen agents, 3-tier neural routing, parallel agent swarms, video generation, 4K/8K upscaling, RAG, voice interface, 70+ tool…

On-device AI SDK for Flutter — LLM inference, vision, STT, TTS, image generation, embeddings, RAG, and function calling. Metal GPU on iOS/macOS.

Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual intelligence (image/table capt…

A python wrapper for the Doc2X API and comes with native texts processing (to improve PDF recall in RAG). | Doc2X API的python封装，同时附带本地的文本处理(提升PDF在RAG中的召回率)。

Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.

Parsing-free RAG supported by VLMs

Extends pageIndex into an AI document workspace with multi-format parsing, OCR, visual TOC, custom models, citations, and agentic QA.

PDFStract - Extract, Chunking and Embedding Layer in Your RAG Pipeline - Available as CLI - WEBUI - API

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-rea…

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…