Ashwin Bharambe 07b87365ab [inference api] modify content types so they follow a more standard structure (#841) ... Some small updates to the inference types to make them more standard Specifically: - image data is now located in a "image" subkey - similarly tool call data is located in a "tool_call" subkey The pattern followed is `dict(type="foo", foo=<...>)`		2025-01-22 12:16:18 -08:00
..
bedrock	Convert SamplingParams.strategy to a union (#767)	2025-01-15 05:38:51 -08:00
cerebras	Convert SamplingParams.strategy to a union (#767)	2025-01-15 05:38:51 -08:00
databricks	remove conflicting default for tool prompt format in chat completion (#742)	2025-01-10 10:41:53 -08:00
fireworks	Fix fireworks client sdk chat completion with images (#840)	2025-01-22 11:25:10 -08:00
groq	[inference api] modify content types so they follow a more standard structure (#841)	2025-01-22 12:16:18 -08:00
nvidia	[inference api] modify content types so they follow a more standard structure (#841)	2025-01-22 12:16:18 -08:00
ollama	[ez] structured output for /completion ollama & enable tests (#822)	2025-01-21 21:10:24 -08:00
sample	[remove import *] clean up import *'s (#689)	2024-12-27 15:45:44 -08:00
tgi	Fix tgi adapter (#796)	2025-01-16 17:44:12 -08:00
together	remove conflicting default for tool prompt format in chat completion (#742)	2025-01-10 10:41:53 -08:00
vllm	fix again vllm for non base64 (#818)	2025-01-17 18:33:40 -08:00
__init__.py	impls -> inline, adapters -> remote (#381)	2024-11-06 14:54:05 -08:00