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

Local private knowledge base

Documents never leave your machine: a local model answers and a local vector store retrieves. Good for individuals and small teams turning PDFs and notes into a Q&A knowledge base.

4 pieces5 setup stepsscenario: Build RAG and process documents

What goes in it

  1. 1

    Ollama Local inference & serving Open source

    Runs chat and embedding models locally

    Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

    ★ 184k
  2. 2

    open-webui AI apps & chat clients Open source

    Chat UI with built-in knowledge upload and retrieval

    User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

    ★ 156k
  3. 3

    docling Document parsing & web scraping Open source

    Parses PDFs and Office files into clean Markdown

    Get your documents ready for gen AI

    ★ 69k
  4. 4

    qdrant optional Retrieval, vector DBs & embeddings Open source

    Vector store for larger collections

    Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

    ★ 35k

How to set it up

  1. 01Install Ollama and pull one chat model and one embedding model from the official library
  2. 02Start Open WebUI with Docker and connect it to the local Ollama (the docker run command in the official quick start)
  3. 03Convert complex PDFs to Markdown with Docling first, then upload them to an Open WebUI knowledge base
  4. 04Ask questions referencing the knowledge base and check the cited passages
  5. 05Move vector storage to Qdrant once you have tens of thousands of documents or many users

✓ Good fit

  • Documents must not go to the cloud (contracts, medical, internal)
  • Individuals or teams under ~10 people

✗ Look elsewhere if

  • You need frontier-model answers and data may go to the cloud: a hosted tool such as NotebookLM is simpler
  • Hundreds of users with fine-grained permissions: see the enterprise RAG stack

Similar stacks: what’s different

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