DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to chat with your own documents using a local model with Pinvou Agent

Point the app at a local vLLM endpoint and query a local knowledge base with source references.

Who it is forA researcher or analyst who wants to question private documents without sending them to a cloud service.

The problemCloud chat tools send document content to outside services, and answers often lack clear sources.

The outcomeAnswers grounded in your own collections, with collection and file provenance shown, using a model that runs locally.

What you need first

  • Git with submodule support
  • Node.js and npm
  • A current Rust toolchain
  • Tauri 2 system dependencies for your platform (see https://v2.tauri.app/start/prerequisites/)
  • An accessible OpenAI-compatible model endpoint, such as local vLLM

Steps

  1. git clone --recursive https://github.com/Pinvou/pinvou-agent.git
  2. cd pinvou-agent/pinvou3-app
  3. npm ci
  4. cd ..
  5. export DEEPSEEK_BASE_URL="http://127.0.0.1:8000/v1"
  6. export DEEPSEEK_API_KEY="local-no-auth"
  7. export DEEPSEEK_MODEL="your-model-name"
  8. ./pinvou3-app/run-dev.sh

Prompt for your agent

Using the Pinvou/pinvou-agent repo, configure a local vLLM endpoint at http://127.0.0.1:8000/v1, create a knowledge collection from <document-folder>, and ask a question about its contents. Expected output: an answer that cites the source collection and file. Verify that disabling that collection removes it from retrieval.

Caveat. A local vLLM server must already be running at the URL you set, because the README does not describe how to start one.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page