Emerson Gomes ba80191f5b Handle exception for token cost calculation (#4474) ...

The code for token cost calculation fails when using a LiteLLM proxy due to mismatch with the provider naming. For now, just handle this exception and assume cost 0 when that happens instead of breaking the flow - A more precise, LiteLLM proxy based cost calculation (relying in the `/model/info`) LiteLLM Proxy method will be needed

2025-04-07 20:30:50 -07:00

..

__init__.py

welcome to onyx

2024-12-13 09:56:10 -08:00

chat_llm.py

feat: Vertex AI support (#4458)

2025-04-08 00:56:47 +00:00

custom_llm.py

use max_tokens to do better rate limit handling (#4224)

2025-03-06 18:12:05 -08:00

exceptions.py

welcome to onyx

2024-12-13 09:56:10 -08:00

factory.py

Contextual Retrieval (#4029)

2025-03-30 18:49:09 +00:00

interfaces.py

feat: Vertex AI support (#4458)

2025-04-08 00:56:47 +00:00

llm_provider_options.py

feat: Vertex AI support (#4458)

2025-04-08 00:56:47 +00:00

models.py

Agent search history displayed answer (#4052)

2025-02-19 15:52:16 -08:00

override_models.py

welcome to onyx

2024-12-13 09:56:10 -08:00

utils.py

Handle exception for token cost calculation (#4474)

2025-04-07 20:30:50 -07:00