Tag

RAG

24 AI tools 11 articles
Advertisement
AI tools24
AgentOS

TypeScript agent framework where agents write their own tools

AI Directory
Alibaba Cloud Bailian 阿里云百炼 (Model Studio)

Alibaba's AI model supermarket for Qwen, DeepSeek, Kimi and more

AI Directory
Allganize (올거나이즈)

Enterprise RAG 'AI coworkers' with layout-aware source citations

AI Directory
Cohere

Enterprise and sovereign AI — RAG-grade models, on-prem deployment

AI Directory
Dify

Open-source LLM app builder: workflows, agents, RAG, one canvas

AI Directory
Exa

Web search and retrieval API built for AI agents and apps

AI Directory
Firecrawl

Scrapes any site into LLM-ready markdown for RAG and agents

AI Directory
Glean

Enterprise search and AI assistant for work

AI Directory
Inkeep

Turns your docs and support history into AI agents

AI Directory
LangChain

Most popular framework for building LLM applications

AI Directory
LightOn (Paradigm)

Sovereign on-prem GenAI platform for regulated European enterprises

AI Directory
LlamaCloud

Managed document parsing and RAG indexing from LlamaIndex

AI Directory
LlamaIndex

Framework for production retrieval-augmented generation

AI Directory
MaxKB

Open-source RAG and workflow platform for building enterprise agents

AI Directory
Mendable

AI chat search for product docs — Firecrawl's quieter sibling

AI Directory
PandaWiki

Open-source, self-hosted AI wiki from Chaitin — 9.9k GitHub stars

AI Directory
Pinecone

Serverless vector database with pay-per-use pricing

AI Directory
Pleias

Small open LLMs trained only on permissively licensed data

AI Directory
Reducto

Document-parsing API tuned for messy PDFs, tables and forms

AI Directory
Stockmark

Tokyo's low-hallucination LLM shop, used by 30% of Nikkei 225

AI Directory
Unstructured

Open-source ETL for turning messy documents into LLM-ready data

AI Directory
Vanna AI

RAG-powered text-to-SQL library now pivoting toward paid agents

AI Directory
Weaviate

Open-source vector DB with hybrid search, now backed by $200M

AI Directory
Youdao QAnything

Open-source RAG engine for document Q&A, with private deployment

AI Directory
Advertisement
Articles11
A close-up of a row of pale locker doors, each fitted with its own separate lock Privacy & Data 6 min 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 Priya Nair 21 Aug A close-up of a measuring tape marked in centimetres, with a pen tip and a magnifying lens resting beside it AI & ML 7 min 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 Kenji Tanaka 21 Aug A hand holding a brass T-shaped plumbing fitting, three separate threaded ports joined into a single body AI & ML 5 min 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 Kenji Tanaka 21 Aug The sharpened tips of many coloured pencils packed tightly together, each one a distinct point of colour among its neighbours AI & ML 6 min 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 Kenji Tanaka 21 Aug A close-up of a vintage printed road map around Paris, where places sit at fixed positions and the ones near each other on the paper are near each other in fact AI & ML 6 min 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 Kenji Tanaka 21 Aug The wooden drawers of an aged library card catalogue with brass fittings. AI & ML 13 min 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 Kenji Tanaka 26 Jul A computer with a black screen on a stand beside a row of steel server racks in a data centre. AI & ML 13 min 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 Kenji Tanaka 21 Jul A close-up of dewdrops on a spider web woven across a thorny branch in autumn. AI & ML 13 min 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 Maya Lin 21 Jul A close-up of a white llama with fluffy fur under a bright blue sky. AI & ML 17 min 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 Kenji Tanaka 21 Jul Connected nodes — choosing an LLM orchestration framework in 2026 AI & ML 10 min 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 Kenji Tanaka 14 Jul A monochrome image of a lens on an open dictionary page, highlighting words. AI & ML 6 min 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 AI Tools Desk 2 Jul
Advertisement