Timmy Time 181d4129ea feat(knowledge): add Conference Talk Summarizer ...

Issue #138 — 7.6: Conference Talk Summarizer.

Adds a complete pipeline for ingesting conference talk transcripts
into the compounding-intelligence knowledge store.

### New files

- scripts/conference_summarizer.py
  - Reads plain-text transcript files
  - Calls LLM (mimo-v2-pro default) to extract knowledge items
  - Deduplicates against existing store
  - Assigns IDs following {domain}:{category}:{NNN} schema
  - Writes to knowledge/index.json and knowledge/conferences/talks.md
  - Supports --dry-run, --domain, --conference tags

- templates/conference-summary-prompt.md
  - Specialized prompt for conference talk knowledge extraction
  - Mirrors harvester prompt structure but tuned for talk context
  - Categories: fact, pitfall, pattern, tool-quirk, question
  - Evidence required per item
  - Domain tagging (global|repo|agent|compounding-intelligence)

### Acceptance criteria

- ✅ Finds talk transcripts — accepts any plain-text transcript file
- ✅ Generates summary — LLM produces structured knowledge items
- ✅ Extracts key takeaways — fact/pattern/pitfall/tool-quirk/question
- ✅ Stores in knowledge base — writes to index.json + conferences/talks.md
- ✅ Weekly — script can be scheduled via cron (usage example in doc)

### Usage example

  python3 scripts/conference_summarizer.py \
    --transcript ~/Downloads/ai拂晓-2026-04-10.txt \
    --conference "AI拂晓 2026" \
    --title "Scaling Autonomous Agents" \
    --speaker "Alexander" \
    --domain global \
    --dry-run

Run without --dry-run to actually write to knowledge store.
API key resolved from HARVESTER_API_KEY or ~/.config/nous/key etc.

Closes #138

2026-04-26 07:18:26 -04:00

10 KiB

Executable File

Raw Blame History

View Raw