Arsham Mirehvandi 46cc17e5d5 Update LLM configuration and enhance vector search capabilities ... - Changed `thinking_budget` to `thinking_level` in `config.yaml` for Gemini models, updating the logic to reflect the new parameter. - Updated LLM models in `config.yaml` to `gemini-3.8-flash` and `gemini-3.1-pro-preview`, adjusting their respective `max_tokens` and `thinking_level`. - Enhanced `docker-compose.yml` to include a new `reranker-transformers` service for improved product ranking. - Modified vector search logic in `vector.py` to incorporate reranking with the local transformers model, improving the accuracy of product recommendations. - Updated unit tests to validate the new reranking functionality and ensure correct behavior in product searches.		2026-10-07 16:25:54 +02:00
..
test_advice_context.py	Update treatment interval handling and refine advice generation logic	2026-09-22 09:57:06 +02:00
test_advice_summary.py	Refactor advisory generation and update database schema	2026-09-30 14:43:08 +02:00
test_assemble.py	Refactor advisory generation and update database schema	2026-09-30 14:43:08 +02:00
test_disease.py	Refactor advisory generation and update database schema	2026-09-30 14:43:08 +02:00
test_incubations.py	Refactor advisory generation and update database schema	2026-09-30 14:43:08 +02:00
test_products.py	Refactor advisory generation and update database schema	2026-09-30 14:43:08 +02:00
test_treatments.py	Refactor treatment history handling and enhance product filtering logic	2026-09-20 23:38:25 +02:00
test_vector.py	Update LLM configuration and enhance vector search capabilities	2026-10-07 16:25:54 +02:00