phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(utils.py): add together ai exception mapping

Browse source
This commit is contained in:
Krrish Dholakia 2024-06-20 11:29:39 -07:00
parent 1a4467c1a5
commit bc01a66e44
2 changed files with 18 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

11
litellm/model_prices_and_context_window_backup.json
View file

@ -865,7 +865,7 @@
}, },
"deepseek-coder": { "deepseek-coder": {
"max_tokens": 4096, "max_tokens": 4096,
"max_input_tokens": 16000, "max_input_tokens": 32000,
"max_output_tokens": 4096, "max_output_tokens": 4096,
"input_cost_per_token": 0.00000014, "input_cost_per_token": 0.00000014,
"output_cost_per_token": 0.00000028, "output_cost_per_token": 0.00000028,
@ -1984,6 +1984,15 @@
"litellm_provider": "replicate", "litellm_provider": "replicate",
"mode": "chat" "mode": "chat"
}, },
"openrouter/deepseek/deepseek-coder": {
"max_tokens": 4096,
"max_input_tokens": 32000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000014,
"output_cost_per_token": 0.00000028,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/microsoft/wizardlm-2-8x22b:nitro": { "openrouter/microsoft/wizardlm-2-8x22b:nitro": {
"max_tokens": 65536, "max_tokens": 65536,
"input_cost_per_token": 0.000001, "input_cost_per_token": 0.000001,

8
litellm/utils.py
View file

@ -5741,7 +5741,15 @@ def exception_type(
response=original_exception.response, response=original_exception.response,
litellm_debug_info=extra_information, litellm_debug_info=extra_information,
) )
elif "Web server is returning an unknown error" in error_str:
exception_mapping_worked = True
raise litellm.InternalServerError(
message=f"{exception_provider} - {message}",
model=model,
llm_provider=custom_llm_provider,
)
elif "Request too large" in error_str: elif "Request too large" in error_str:
exception_mapping_worked = True
raise RateLimitError( raise RateLimitError(
message=f"RateLimitError: {exception_provider} - {message}", message=f"RateLimitError: {exception_provider} - {message}",
model=model, model=model,