Ultra-Lightweight 1M Parameter OCR Model 'Indra' Released: 49 Pages per Second on CPU
Vik Paruchuri has released Indra, an ultra-lightweight 1M parameter OCR model capable of processing 49 pages per second on CPU. Delivering 11x faster speeds tha
#RAG
TAU-HOME.COM stories tagged RAG.
Google Releases EmbeddingGemma 2: Lightweight 740M Multimodal On-Device Embedding Model
Google has launched EmbeddingGemma 2, an open 740M-parameter multimodal embedding model for text, code, images, video, and audio on local devices, now on Huggin
LlamaIndex Launches OpenDocRouter, a Unified API for Document Parsing
LlamaIndex launched OpenDocRouter, placing 10 document parsing models behind one API. One-line model swaps and ParseBench quality/cost scores are the core of th
Two open-source tools that turn messy documents into AI-ready data
A faithful translation of the two verified entries (Unstructured and Docling) from @DivyanshT91162's list of document-parsing GitHub repositories, with official
10 Open-Source Web Scraping and Crawler Repositories for AI RAG and Data Extraction
A technical breakdown of 10 open-source web scraping tools from Crawlee and Scrapy to Crawl4AI, exploring anti-bot evasion, concurrency, and LLM RAG markdown pi
10 Essential Open-Source GitHub Repositories for Building AI Search Engines
A comprehensive breakdown of 10 key open-source repositories—including Perplexica, SearXNG, Meilisearch, Qdrant, and Weaviate—for building self-hosted AI search
How to Connect Claude Code and Google NotebookLM via MCP to Slash Document Search Tokens
A step-by-step guide to connecting Google NotebookLM to Claude Code via MCP to query extensive documentation without context bloating or hallucinations.
10 Open-Source Context Tools to Stop Agent Prompt Bloat and 3 Production Pipelines
A practical guide to 10 open-source GitHub tools—including Context7, Serena, and Repomix—and 3 specialized pipelines designed to feed AI agents minimal, high-pr
jamwithai/production-agentic-rag-course: Open-Source Production Agentic RAG Engineering Pipeline
An open-source reference course and production architecture covering OpenSearch 2.19 hybrid search, Docling paper parsing, Airflow pipelines, LangGraph agentic
Awesome LLM Apps: A Repository of 100+ Open-Source AI Agents and RAG Apps
A repository featuring over 100 open-source AI agents, RAG applications, and agent skills ready for cloning and deployment. Supports various LLMs and released u
Tencent Releases WeKnora v0.8.0: Agentic RAG Shift with Sandbox Isolation and Memory
Tencent has released WeKnora v0.8.0, transforming its open-source LLM knowledge platform into an agentic RAG system with session sandboxing, cross-session memor