RAG
TypeScript agent framework where agents write their own tools
Alibaba's AI model supermarket for Qwen, DeepSeek, Kimi and more
Enterprise RAG 'AI coworkers' with layout-aware source citations
Enterprise and sovereign AI — RAG-grade models, on-prem deployment
Open-source LLM app builder: workflows, agents, RAG, one canvas
Web search and retrieval API built for AI agents and apps
Scrapes any site into LLM-ready markdown for RAG and agents
Enterprise search and AI assistant for work
Turns your docs and support history into AI agents
Most popular framework for building LLM applications
Sovereign on-prem GenAI platform for regulated European enterprises
Managed document parsing and RAG indexing from LlamaIndex
Framework for production retrieval-augmented generation
Open-source RAG and workflow platform for building enterprise agents
AI chat search for product docs — Firecrawl's quieter sibling
Open-source, self-hosted AI wiki from Chaitin — 9.9k GitHub stars
Serverless vector database with pay-per-use pricing
Small open LLMs trained only on permissively licensed data
Document-parsing API tuned for messy PDFs, tables and forms
Tokyo's low-hallucination LLM shop, used by 30% of Nikkei 225
Open-source ETL for turning messy documents into LLM-ready data
RAG-powered text-to-SQL library now pivoting toward paid agents
Open-source vector DB with hybrid search, now backed by $200M
Open-source RAG engine for document Q&A, with private deployment
How to Stop an Agent Returning Documents the User Should Not See
A vector search scoped three ways, and measured each time. Unfiltered, four in five results belonged to anothe...
PR
21 Aug
How to Measure Whether Your RAG Is Retrieving the Right Documents
Twenty questions with known answers, run over 205 real documents. Prefixing titles to chunks raised hit@1 from...
KE
21 Aug
How to Give an Agent Search Over Your Own Documents
Seventy-eight lines with no dependencies join a local embedding model, a vector store and MCP. The interesting...
KE
21 Aug
How to Generate Embeddings Locally
A 46 MB model, running on your laptop, turns text into positions in space. The demonstration: a query whose on...
KE
21 Aug
How to Self-Host Qdrant in Docker
Every retrieval tutorial says "point it at your vector database" and none of them tells you how to run one. On...
KE
21 Aug
MCP, RAG, Agents, Skills: The New AI Vocabulary in Plain English
Somebody says the agent will use MCP to hit the connector, then RAG over the docs, and the skill handles the r...
KE
26 Jul
Qdrant vs Weaviate vs Milvus vs Pinecone: Vector Databases for RAG (2026)
Four vector databases compared for RAG in 2026: licenses, Docker self-host commands, embedded modes, managed p...
KE
21 Jul
Firecrawl vs Crawl4AI vs Jina Reader vs Browser Use — Getting Web Data Into Your LLM (2026)
Four open-source ways to feed web data to an LLM compared: licenses, self-host parity, pricing bases, robots.t...
MA
21 Jul
How to Self-Host AnythingLLM with Docker and Ollama (2026)
We self-hosted AnythingLLM 1.15.0 with Docker and Ollama, embedded a document over the API, and got cited RAG...
KE
21 Jul
LangChain vs LlamaIndex vs LangGraph: Which Orchestration Layer? (2026)
LangChain is now an agent harness on LangGraph, and LlamaIndex moved to Workflows 2.x. We compare all three or...
KE
14 Jul
Mistral OCR 4 Adds Structure to Document AI: Bounding Boxes, Confidence Scores and 170 Languages
Mistral released OCR 4 on 23 June 2026, a document-intelligence model that returns bounding boxes, typed-block...
AI
2 Jul