mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 19:24:27 +00:00
LiteLLM Minor Fixes & Improvements (09/21/2024) (#5819)
* fix(router.py): fix error message * Litellm disable keys (#5814) * build(schema.prisma): allow blocking/unblocking keys Fixes https://github.com/BerriAI/litellm/issues/5328 * fix(key_management_endpoints.py): fix pop * feat(auth_checks.py): allow admin to enable/disable virtual keys Closes https://github.com/BerriAI/litellm/issues/5328 * docs(vertex.md): add auth section for vertex ai Addresses - https://github.com/BerriAI/litellm/issues/5768#issuecomment-2365284223 * build(model_prices_and_context_window.json): show which models support prompt_caching Closes https://github.com/BerriAI/litellm/issues/5776 * fix(router.py): allow setting default priority for requests * fix(router.py): add 'retry-after' header for concurrent request limit errors Fixes https://github.com/BerriAI/litellm/issues/5783 * fix(router.py): correctly raise and use retry-after header from azure+openai Fixes https://github.com/BerriAI/litellm/issues/5783 * fix(user_api_key_auth.py): fix valid token being none * fix(auth_checks.py): fix model dump for cache management object * fix(user_api_key_auth.py): pass prisma_client to obj * test(test_otel.py): update test for new key check * test: fix test
This commit is contained in:
Krish Dholakia
GitHub
parent
f0543a6f9d
commit
f3fa2160a0
25 changed files with 1006 additions and 182 deletions
|
|
@ -704,7 +704,6 @@ class OpenAIChatCompletion(BaseLLM):
|
|||
drop_params: Optional[bool] = None,
|
||||
):
|
||||
super().completion()
|
||||
exception_mapping_worked = False
|
||||
try:
|
||||
if headers:
|
||||
optional_params["extra_headers"] = headers
|
||||
|
|
@ -911,6 +910,9 @@ class OpenAIChatCompletion(BaseLLM):
|
|||
status_code = getattr(e, "status_code", 500)
|
||||
error_headers = getattr(e, "headers", None)
|
||||
error_text = getattr(e, "text", str(e))
|
||||
error_response = getattr(e, "response", None)
|
||||
if error_headers is None and error_response:
|
||||
error_headers = getattr(error_response, "headers", None)
|
||||
raise OpenAIError(
|
||||
status_code=status_code, message=error_text, headers=error_headers
|
||||
)
|
||||
|
|
@ -1003,8 +1005,12 @@ class OpenAIChatCompletion(BaseLLM):
|
|||
raise e
|
||||
# e.message
|
||||
except Exception as e:
|
||||
exception_response = getattr(e, "response", None)
|
||||
status_code = getattr(e, "status_code", 500)
|
||||
error_headers = getattr(e, "headers", None)
|
||||
if error_headers is None and exception_response:
|
||||
error_headers = getattr(exception_response, "headers", None)
|
||||
|
||||
raise OpenAIError(
|
||||
status_code=status_code, message=str(e), headers=error_headers
|
||||
)
|
||||
|
|
@ -1144,10 +1150,13 @@ class OpenAIChatCompletion(BaseLLM):
|
|||
raise e
|
||||
|
||||
error_headers = getattr(e, "headers", None)
|
||||
status_code = getattr(e, "status_code", 500)
|
||||
error_response = getattr(e, "response", None)
|
||||
if error_headers is None and error_response:
|
||||
error_headers = getattr(error_response, "headers", None)
|
||||
if response is not None and hasattr(response, "text"):
|
||||
error_headers = getattr(e, "headers", None)
|
||||
raise OpenAIError(
|
||||
status_code=500,
|
||||
status_code=status_code,
|
||||
message=f"{str(e)}\n\nOriginal Response: {response.text}", # type: ignore
|
||||
headers=error_headers,
|
||||
)
|
||||
|
|
@ -1272,8 +1281,12 @@ class OpenAIChatCompletion(BaseLLM):
|
|||
)
|
||||
status_code = getattr(e, "status_code", 500)
|
||||
error_headers = getattr(e, "headers", None)
|
||||
error_text = getattr(e, "text", str(e))
|
||||
error_response = getattr(e, "response", None)
|
||||
if error_headers is None and error_response:
|
||||
error_headers = getattr(error_response, "headers", None)
|
||||
raise OpenAIError(
|
||||
status_code=status_code, message=str(e), headers=error_headers
|
||||
status_code=status_code, message=error_text, headers=error_headers
|
||||
)
|
||||
|
||||
def embedding( # type: ignore
|
||||
|
|
@ -1352,8 +1365,12 @@ class OpenAIChatCompletion(BaseLLM):
|
|||
except Exception as e:
|
||||
status_code = getattr(e, "status_code", 500)
|
||||
error_headers = getattr(e, "headers", None)
|
||||
error_text = getattr(e, "text", str(e))
|
||||
error_response = getattr(e, "response", None)
|
||||
if error_headers is None and error_response:
|
||||
error_headers = getattr(error_response, "headers", None)
|
||||
raise OpenAIError(
|
||||
status_code=status_code, message=str(e), headers=error_headers
|
||||
status_code=status_code, message=error_text, headers=error_headers
|
||||
)
|
||||
|
||||
async def aimage_generation(
|
||||
|
|
@ -1774,7 +1791,15 @@ class OpenAITextCompletion(BaseLLM):
|
|||
## RESPONSE OBJECT
|
||||
return TextCompletionResponse(**response_json)
|
||||
except Exception as e:
|
||||
raise e
|
||||
status_code = getattr(e, "status_code", 500)
|
||||
error_headers = getattr(e, "headers", None)
|
||||
error_text = getattr(e, "text", str(e))
|
||||
error_response = getattr(e, "response", None)
|
||||
if error_headers is None and error_response:
|
||||
error_headers = getattr(error_response, "headers", None)
|
||||
raise OpenAIError(
|
||||
status_code=status_code, message=error_text, headers=error_headers
|
||||
)
|
||||
|
||||
async def acompletion(
|
||||
self,
|
||||
|
|
@ -1825,7 +1850,15 @@ class OpenAITextCompletion(BaseLLM):
|
|||
response_obj._hidden_params.original_response = json.dumps(response_json)
|
||||
return response_obj
|
||||
except Exception as e:
|
||||
raise e
|
||||
status_code = getattr(e, "status_code", 500)
|
||||
error_headers = getattr(e, "headers", None)
|
||||
error_text = getattr(e, "text", str(e))
|
||||
error_response = getattr(e, "response", None)
|
||||
if error_headers is None and error_response:
|
||||
error_headers = getattr(error_response, "headers", None)
|
||||
raise OpenAIError(
|
||||
status_code=status_code, message=error_text, headers=error_headers
|
||||
)
|
||||
|
||||
def streaming(
|
||||
self,
|
||||
|
|
@ -1860,8 +1893,12 @@ class OpenAITextCompletion(BaseLLM):
|
|||
except Exception as e:
|
||||
status_code = getattr(e, "status_code", 500)
|
||||
error_headers = getattr(e, "headers", None)
|
||||
error_text = getattr(e, "text", str(e))
|
||||
error_response = getattr(e, "response", None)
|
||||
if error_headers is None and error_response:
|
||||
error_headers = getattr(error_response, "headers", None)
|
||||
raise OpenAIError(
|
||||
status_code=status_code, message=str(e), headers=error_headers
|
||||
status_code=status_code, message=error_text, headers=error_headers
|
||||
)
|
||||
streamwrapper = CustomStreamWrapper(
|
||||
completion_stream=response,
|
||||
|
|
@ -1871,8 +1908,19 @@ class OpenAITextCompletion(BaseLLM):
|
|||
stream_options=data.get("stream_options", None),
|
||||
)
|
||||
|
||||
for chunk in streamwrapper:
|
||||
yield chunk
|
||||
try:
|
||||
for chunk in streamwrapper:
|
||||
yield chunk
|
||||
except Exception as e:
|
||||
status_code = getattr(e, "status_code", 500)
|
||||
error_headers = getattr(e, "headers", None)
|
||||
error_text = getattr(e, "text", str(e))
|
||||
error_response = getattr(e, "response", None)
|
||||
if error_headers is None and error_response:
|
||||
error_headers = getattr(error_response, "headers", None)
|
||||
raise OpenAIError(
|
||||
status_code=status_code, message=error_text, headers=error_headers
|
||||
)
|
||||
|
||||
async def async_streaming(
|
||||
self,
|
||||
|
|
@ -1910,8 +1958,19 @@ class OpenAITextCompletion(BaseLLM):
|
|||
stream_options=data.get("stream_options", None),
|
||||
)
|
||||
|
||||
async for transformed_chunk in streamwrapper:
|
||||
yield transformed_chunk
|
||||
try:
|
||||
async for transformed_chunk in streamwrapper:
|
||||
yield transformed_chunk
|
||||
except Exception as e:
|
||||
status_code = getattr(e, "status_code", 500)
|
||||
error_headers = getattr(e, "headers", None)
|
||||
error_text = getattr(e, "text", str(e))
|
||||
error_response = getattr(e, "response", None)
|
||||
if error_headers is None and error_response:
|
||||
error_headers = getattr(error_response, "headers", None)
|
||||
raise OpenAIError(
|
||||
status_code=status_code, message=error_text, headers=error_headers
|
||||
)
|
||||
|
||||
|
||||
class OpenAIFilesAPI(BaseLLM):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue