Matthew Farrellee a3e249807b chore: remove vision model URL workarounds and simplify client creation (#2775) ... The vision models are now available at the standard URL, so the workaround code has been removed. This also simplifies the codebase by eliminating the need for per-model client caching. - Remove special URL handling for meta/llama-3.2-11b/90b-vision-instruct models - Convert _get_client method to _client property for cleaner API - Remove unnecessary lru_cache decorator and functools import - Simplify client creation logic to use single base URL for all models		2025-07-16 07:10:04 -07:00
..
anthropic	ci: test safety with starter (#2628)	2025-07-09 16:53:50 +02:00
bedrock	ci: test safety with starter (#2628)	2025-07-09 16:53:50 +02:00
cerebras	ci: test safety with starter (#2628)	2025-07-09 16:53:50 +02:00
cerebras_openai_compat	feat: introduce APIs for retrieving chat completion requests (#2145)	2025-05-18 21:43:19 -07:00
databricks	ci: test safety with starter (#2628)	2025-07-09 16:53:50 +02:00
fireworks	ci: test safety with starter (#2628)	2025-07-09 16:53:50 +02:00
fireworks_openai_compat	feat: introduce APIs for retrieving chat completion requests (#2145)	2025-05-18 21:43:19 -07:00
gemini	ci: test safety with starter (#2628)	2025-07-09 16:53:50 +02:00
groq	fix: Don't cache clients for passthrough auth providers (#2728)	2025-07-11 13:38:27 -07:00
groq_openai_compat	feat: introduce APIs for retrieving chat completion requests (#2145)	2025-05-18 21:43:19 -07:00
llama_openai_compat	feat: introduce APIs for retrieving chat completion requests (#2145)	2025-05-18 21:43:19 -07:00
nvidia	chore: remove vision model URL workarounds and simplify client creation (#2775)	2025-07-16 07:10:04 -07:00
ollama	fix: Safety in starter (#2731)	2025-07-14 15:07:40 -07:00
openai	fix: Don't cache clients for passthrough auth providers (#2728)	2025-07-11 13:38:27 -07:00
passthrough	feat: consolidate most distros into "starter" (#2516)	2025-07-04 15:58:03 +02:00
runpod	ci: test safety with starter (#2628)	2025-07-09 16:53:50 +02:00
sambanova	fix: sambanova shields and model validation (#2693)	2025-07-11 16:29:15 -04:00
sambanova_openai_compat	feat: introduce APIs for retrieving chat completion requests (#2145)	2025-05-18 21:43:19 -07:00
tgi	feat: consolidate most distros into "starter" (#2516)	2025-07-04 15:58:03 +02:00
together	fix: Don't cache clients for passthrough auth providers (#2728)	2025-07-11 13:38:27 -07:00
together_openai_compat	feat: introduce APIs for retrieving chat completion requests (#2145)	2025-05-18 21:43:19 -07:00
vllm	refactor(env)!: enhanced environment variable substitution (#2490)	2025-06-26 08:20:08 +05:30
watsonx	fix: allow default empty vars for conditionals (#2570)	2025-07-01 14:42:05 +02:00
__init__.py	impls -> inline, adapters -> remote (#381)	2024-11-06 14:54:05 -08:00