phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

fix checking mode on health checks

Browse source
This commit is contained in:
Ishaan Jaff 2024-07-27 20:21:39 -07:00
parent 9b69e500e5
commit 0627468455
2 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/main.py
View file

@ -4797,12 +4797,12 @@ async def ahealth_check(
raise Exception("model not set") raise Exception("model not set")
if model in litellm.model_cost and mode is None: if model in litellm.model_cost and mode is None:
mode = litellm.model_cost[model]["mode"] mode = litellm.model_cost[model].get("mode")
model, custom_llm_provider, _, _ = get_llm_provider(model=model) model, custom_llm_provider, _, _ = get_llm_provider(model=model)
if model in litellm.model_cost and mode is None: if model in litellm.model_cost and mode is None:
mode = litellm.model_cost[model]["mode"] mode = litellm.model_cost[model].get("mode")
mode = mode or "chat" # default to chat completion calls mode = mode or "chat" # default to chat completion calls

10
litellm/model_prices_and_context_window_backup.json
View file

@ -4373,7 +4373,7 @@
"litellm_provider": "perplexity", "litellm_provider": "perplexity",
"mode": "chat" "mode": "chat"
}, },
"fireworks_ai/firefunction-v2": { "fireworks_ai/accounts/fireworks/models/firefunction-v2": {
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 8192, "max_input_tokens": 8192,
"max_output_tokens": 8192, "max_output_tokens": 8192,
@ -4384,7 +4384,7 @@
"supports_function_calling": true, "supports_function_calling": true,
"source": "https://fireworks.ai/pricing" "source": "https://fireworks.ai/pricing"
}, },
"fireworks_ai/mixtral-8x22b-instruct-hf": { "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": {
"max_tokens": 65536, "max_tokens": 65536,
"max_input_tokens": 65536, "max_input_tokens": 65536,
"max_output_tokens": 65536, "max_output_tokens": 65536,
@ -4395,7 +4395,7 @@
"supports_function_calling": true, "supports_function_calling": true,
"source": "https://fireworks.ai/pricing" "source": "https://fireworks.ai/pricing"
}, },
"fireworks_ai/qwen2-72b-instruct": { "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": {
"max_tokens": 32768, "max_tokens": 32768,
"max_input_tokens": 32768, "max_input_tokens": 32768,
"max_output_tokens": 32768, "max_output_tokens": 32768,
@ -4406,7 +4406,7 @@
"supports_function_calling": true, "supports_function_calling": true,
"source": "https://fireworks.ai/pricing" "source": "https://fireworks.ai/pricing"
}, },
"fireworks_ai/yi-large": { "fireworks_ai/accounts/fireworks/models/yi-large": {
"max_tokens": 32768, "max_tokens": 32768,
"max_input_tokens": 32768, "max_input_tokens": 32768,
"max_output_tokens": 32768, "max_output_tokens": 32768,
@ -4417,7 +4417,7 @@
"supports_function_calling": true, "supports_function_calling": true,
"source": "https://fireworks.ai/pricing" "source": "https://fireworks.ai/pricing"
}, },
"fireworks_ai/deepseek-coder-v2-instruct": { "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": {
"max_tokens": 65536, "max_tokens": 65536,
"max_input_tokens": 65536, "max_input_tokens": 65536,
"max_output_tokens": 8192, "max_output_tokens": 8192,