693d9e0d60
fix: reduce LLM timeouts — truncate docs to 8k/6k chars, cut num_predict 16k→4k, tighten prompts, trim anti-hallucination rules
2026-04-16 18:56:11 +00:00
cd782d1552
fix(extractor): streaming with guardrails + catalyst_type normalization
...
- Switch Ollama calls from non-streaming to streaming with early termination
- Add loop detection, max token limit, and stall timeout guards
- Add catalyst_type alias normalizer to handle model hallucinations
- Add explicit enum values in extraction prompt for catalyst_type
- Add streaming config knobs to OllamaConfig
2026-04-12 15:28:20 -07:00
66ed38bf18
phase 17: switch to gemma4:e4b, rewrite prompts for fill-the-fields style with forced ticker inclusion
2026-04-12 10:05:31 -07:00
28b3361833
phase 17: remove embedded JSON schema from user prompt (4.7KB saved), Ollama format param handles it
2026-04-12 09:28:28 -07:00
57d0fc7d33
phase 17: pass all tracked tickers to extractor, soften prompt for macro-to-company relevance
2026-04-12 09:18:08 -07:00
109440c91e
phase 15: fix ruff lint errors across services
2026-04-11 12:10:01 -07:00
ce10afa034
phase 14-15: docker build validation and helm deployment
2026-04-11 11:59:45 -07:00
Celes Renata