Commit graph

3 commits

Author SHA1 Message Date
Pieter
754fddef12 Add generic LLM provider terminology
- Update all documentation to use "LLM API" instead of "OpenAI GPT-4o-mini"
- Rename OPENAI_API_KEY to LLM_API_KEY in configuration
- Update code comments to reflect generic LLM usage
- Keep OpenAI-compatible client library (supports any LLM provider)
- Add LOCAL_OPERATIONS.md and accounts.txt to .gitignore
2026-04-18 20:27:09 +02:00
Pieter
2ff5ed78da Complete toxicity analysis system setup and testing
- Copy and integrate analysis templates from Bluesky collector
- Add template filters (format_number, time_ago, truncate_text)
- Add Analysis link to navigation
- Fix analyzer database schema compatibility (account_db_id, status_type)
- Add OPENAI_API_KEY to docker-compose environment
- Successfully tested analyzer on 100 statuses ($0.0116, 75.4 seconds)

Web interface available at /analysis and /analysis/flagged

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2026-03-30 15:39:36 +02:00
Pieter
27582c7b77 Add toxicity analysis system for Mastodon statuses
Implements comprehensive toxicity analysis following the Bluesky collector architecture:

- Analyzer module with async batch processing using GPT-4o-mini
- Database schema for toxicity scores and analysis run tracking
- 12 toxicity categories (toxic, threat, hate_speech, racism, antisemitism, islamophobia, sexism, homophobia, insult, dehumanization, extremism, ableism)
- Web interface routes for analysis dashboard and flagged content review
- Manual review API endpoint for human validation
- Analysis helper functions for database queries
- Dutch language support with coded political term recognition

Usage:
  docker exec mastodon-collector-collector-1 python -m app.analyzer

See TOXICITY_ANALYSIS.md for full documentation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2026-03-30 14:43:35 +02:00