graphiti/tests/llm_client
Daniel Chalef 689d669559
Gemini client improvements; Gemini reranker (#645)
* add support for Gemini 2.5 model thinking budget

* allow adding thinking config to support current and future gemini models

* merge

* improve client; add reranker

* refactor: change type hint for gemini_messages to Any for flexibility

* refactor: update GeminiRerankerClient to use direct relevance scoring and improve ranking logic. Add tests

* fix fixtures

---------

Co-authored-by: realugbun <github.disorder751@passmail.net>
2025-06-30 12:55:17 -07:00
..
test_anthropic_client.py Anthropic client (#361) 2025-04-16 12:35:07 -07:00
test_anthropic_client_int.py Anthropic cleanup (#431) 2025-05-03 09:15:03 -04:00
test_client.py Anthropic cleanup (#431) 2025-05-03 09:15:03 -04:00
test_errors.py Anthropic client (#361) 2025-04-16 12:35:07 -07:00
test_gemini_client.py Gemini client improvements; Gemini reranker (#645) 2025-06-30 12:55:17 -07:00