feat(knowledge): add Conference Talk Summarizer #254

Open
Rockachopa wants to merge 1 commits from step35/138-7-6-conference-talk-summariz into main
Owner

Summary

Adds Conference Talk Summarizer (issue #138).

Files added:

  • scripts/conference_summarizer.py — standalone summarizer script
  • templates/conference-summary-prompt.md — extraction prompt

Features:

  • Reads plain-text transcripts
  • Calls LLM to extract knowledge (fact/pitfall/pattern/tool-quirk/question)
  • Deduplicates against knowledge store
  • Assigns IDs per domain/category sequence
  • Writes to knowledge/index.json and knowledge/conferences/talks.md
  • Dry-run mode supported

Closes #138

## Summary Adds Conference Talk Summarizer (issue #138). **Files added:** - `scripts/conference_summarizer.py` — standalone summarizer script - `templates/conference-summary-prompt.md` — extraction prompt Features: - Reads plain-text transcripts - Calls LLM to extract knowledge (fact/pitfall/pattern/tool-quirk/question) - Deduplicates against knowledge store - Assigns IDs per domain/category sequence - Writes to knowledge/index.json and knowledge/conferences/talks.md - Dry-run mode supported **Closes #138**
Rockachopa added 1 commit 2026-04-26 11:19:48 +00:00
feat(knowledge): add Conference Talk Summarizer
Some checks failed
Test / pytest (pull_request) Failing after 9s
181d4129ea
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
Some checks failed
Test / pytest (pull_request) Failing after 9s
Checking for merge conflicts…
View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.
git fetch -u origin step35/138-7-6-conference-talk-summariz:step35/138-7-6-conference-talk-summariz
git checkout step35/138-7-6-conference-talk-summariz
Sign in to join this conversation.