scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-03 02:22:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 81

Merge pull request #3226 from BerriAI/litellm_alerting_fix

Browse source 
[Bug-Fix] Alerting - don't send hanging request alert on failed request
This commit is contained in:
Ishaan Jaff 2024-04-22 16:32:35 -07:00 • committed by GitHub
commit 9886392694
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 14 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
litellm/model_prices_and_context_window_backup.json
View file

@ -1535,6 +1535,13 @@
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/meta-llama/llama-3-70b-instruct": {
"max_tokens": 8192,
"input_cost_per_token": 0.0000008,
"output_cost_per_token": 0.0000008,
"litellm_provider": "openrouter",
"mode": "chat"
},
"j2-ultra": {
"max_tokens": 8192,
"max_input_tokens": 8192,

6
litellm/proxy/proxy_server.py
View file

@ -3471,6 +3471,7 @@ async def completion(
fastapi_response.headers["x-litellm-model-id"] = model_id
return response
except Exception as e:
data["litellm_status"] = "fail" # used for alerting
verbose_proxy_logger.debug("EXCEPTION RAISED IN PROXY MAIN.PY")
verbose_proxy_logger.debug(
"\033[1;31mAn error occurred: %s\n\n Debug this by setting `--debug`, e.g. `litellm --model gpt-3.5-turbo --debug`",
@ -3720,6 +3721,7 @@ async def chat_completion(
return response
except Exception as e:
data["litellm_status"] = "fail" # used for alerting
traceback.print_exc()
await proxy_logging_obj.post_call_failure_hook(
user_api_key_dict=user_api_key_dict, original_exception=e
@ -3914,6 +3916,7 @@ async def embeddings(
return response
except Exception as e:
data["litellm_status"] = "fail" # used for alerting
await proxy_logging_obj.post_call_failure_hook(
user_api_key_dict=user_api_key_dict, original_exception=e
)
@ -4069,6 +4072,7 @@ async def image_generation(
return response
except Exception as e:
data["litellm_status"] = "fail" # used for alerting
await proxy_logging_obj.post_call_failure_hook(
user_api_key_dict=user_api_key_dict, original_exception=e
)
@ -4247,6 +4251,7 @@ async def audio_transcriptions(
data["litellm_status"] = "success" # used for alerting
return response
except Exception as e:
data["litellm_status"] = "fail" # used for alerting
await proxy_logging_obj.post_call_failure_hook(
user_api_key_dict=user_api_key_dict, original_exception=e
)
@ -4408,6 +4413,7 @@ async def moderations(
return response
except Exception as e:
data["litellm_status"] = "fail" # used for alerting
await proxy_logging_obj.post_call_failure_hook(
user_api_key_dict=user_api_key_dict, original_exception=e
)

1
litellm/proxy/utils.py
View file

@ -346,6 +346,7 @@ class ProxyLogging:
if (
request_data is not None
and request_data.get("litellm_status", "") != "success"
and request_data.get("litellm_status", "") != "fail"
):
if request_data.get("deployment", None) is not None and isinstance(
request_data["deployment"], dict