profit 74870f7c0d Add Ollama backend + Qwen3 local inference support ...

- Extractor now supports two backends: ollama (local) and anthropic (cloud)
- Default is ollama with qwen3:14b (fits 16GB VRAM)
- Set num_ctx to 32768 for full-script processing
- Added --backend and --ollama-url CLI flags
- Added The Last Backup test script
- Tested: 12/12 scenes valid on dialogue_heavy, 12/13 on the_last_backup

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-06 16:28:53 -07:00

..

expected

Phase 1 implementation: script ingestion + AI extraction pipeline

2026-04-06 15:49:43 -07:00

action_heavy.fountain

Phase 1 implementation: script ingestion + AI extraction pipeline

2026-04-06 15:49:43 -07:00

dialogue_heavy.fountain

Phase 1 implementation: script ingestion + AI extraction pipeline

2026-04-06 15:49:43 -07:00

nonstandard.fountain

Phase 1 implementation: script ingestion + AI extraction pipeline

2026-04-06 15:49:43 -07:00

the_last_backup.fountain

Add Ollama backend + Qwen3 local inference support

2026-04-06 16:28:53 -07:00