Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// Software stack

Enterprise RAG knowledge base

Team-scale document Q&A: deep document parsing, a scalable vector database, one model gateway, plus tracing and quality evaluation.

6 pieces5 setup stepsscenario: Build RAG and process documents

What goes in it

  1. 1

    ragflow Document parsing & web scraping Open source

    RAG engine and knowledge-base console

    RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

    ★ 93k
  2. 2

    MinerU Document parsing & web scraping Open source

    Parses complex PDFs with tables and formulas

    Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

    ★ 82k
  3. 3

    milvus Retrieval, vector DBs & embeddings Open source

    Distributed vector database

    Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

    ★ 46k
  4. 4

    litellm Model gateways, routing & usage Open source

    One gateway to many models, with cost and rate limits

    The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

    ★ 62k
  5. 5

    langfuse Observability & tracing Open source

    Traces retrieval and answers for quality evaluation

    🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

    ★ 36k
  6. 6

    ragas optional Evaluation, red-teaming & guardrails Open source

    Evaluates RAG answer quality

    Supercharge Your LLM Application Evaluations 🚀

    ★ 16k

How to set it up

  1. 01Inventory sources and permissions: which departments, which documents, who may see what
  2. 02Parse PDFs with tables and formulas using MinerU and spot-check the output by hand
  3. 03Deploy RAGFlow, create knowledge bases per department, use Milvus as the vector store
  4. 04Route every model call through LiteLLM with per-department budgets and rate limits
  5. 05Trace with Langfuse and run Ragas on a 50–100 question gold set before launch and weekly after

✓ Good fit

  • Many documents, complex formats, many users and departments
  • You need auditing and quality evaluation

✗ Look elsewhere if

  • Just trying it out: start with the built-in knowledge base in Dify or Open WebUI

Data updated: AI software & hot ranks · Solutions & stack guides(UTC+8)