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

How to trace decisions and conflicts across meeting notes with Carrel

Build a knowledge graph over meeting notes to follow relationships, sources, and conflicting facts.

  • Research
  • Advanced
  • 2 hours
  • From the README
  • Any agent

Who it is forA project lead or analyst who needs to see how a decision changed across many weeks of meeting notes.

The problemPlain keyword or vector search finds passages but does not show how entities, decisions, and dates connect or where facts conflict.

The outcomeThe agent can follow graph relationships and report facts with their sources, time information, and conflict indicators.

What you need first

  • Linux, macOS with Docker Desktop, or Windows through WSL2 (native Windows is not supported)
  • Python 3.12+ and Docker 25+ with Compose v2
  • A text embedding endpoint and a vision-language endpoint, either local or hosted
  • A chat model if you want knowledge graphs
  • Optional: an NVIDIA GPU with NVIDIA Container Toolkit for the local model stack

Steps

  1. Run ./deploy.sh and set your embedding and vision endpoints in config/knowledge-base.env.
  2. Register a chat model in the console at http://127.0.0.1:9800 and select it in the knowledge-base settings.
  3. Enable graph building for the meeting-notes folder under runtime/mirror/<notes-folder>/.
  4. Wait for the scheduled tasks to finish, then query the search endpoint with curl -sS http://127.0.0.1:9810/search -H 'Content-Type: application/json' -d '{"question": "Which decisions about <topic> changed over time?", "top_k": 8}'. (inferred, check the README)

Prompt for your agent

Using the FengZhenfei/carrel search API at http://127.0.0.1:9810/search, ask about how <decision topic> changed across the meeting notes, and follow graph relationships when more evidence is needed. Return a dated timeline with sources and mark any conflicting facts. Verify that each dated item links to a source passage.

Caveat. Knowledge graph construction needs a chat model that you configure, and the README does not describe how accurate the extracted facts are.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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