mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 10:44:24 +00:00
LiteLLM Minor Fixes + Improvements (#5474)
* feat(proxy/_types.py): add lago billing to callbacks ui Closes https://github.com/BerriAI/litellm/issues/5472 * fix(anthropic.py): return anthropic prompt caching information Fixes https://github.com/BerriAI/litellm/issues/5364 * feat(bedrock/chat.py): support 'json_schema' for bedrock models Closes https://github.com/BerriAI/litellm/issues/5434 * fix(bedrock/embed/embeddings.py): support async embeddings for amazon titan models * fix: linting fixes * fix: handle key errors * fix(bedrock/chat.py): fix bedrock ai21 streaming object * feat(bedrock/embed): support bedrock embedding optional params * fix(databricks.py): fix usage chunk * fix(internal_user_endpoints.py): apply internal user defaults, if user role updated Fixes issue where user update wouldn't apply defaults * feat(slack_alerting.py): provide multiple slack channels for a given alert type multiple channels might be interested in receiving an alert for a given type * docs(alerting.md): add multiple channel alerting to docs
This commit is contained in:
Krish Dholakia
GitHub
parent
02f288a8a3
commit
f9e6507cd1
22 changed files with 720 additions and 209 deletions
|
|
@ -2550,7 +2550,7 @@ def get_optional_params_image_gen(
|
|||
|
||||
def get_optional_params_embeddings(
|
||||
# 2 optional params
|
||||
model=None,
|
||||
model: str,
|
||||
user=None,
|
||||
encoding_format=None,
|
||||
dimensions=None,
|
||||
|
|
@ -2606,7 +2606,7 @@ def get_optional_params_embeddings(
|
|||
):
|
||||
raise UnsupportedParamsError(
|
||||
status_code=500,
|
||||
message=f"Setting dimensions is not supported for OpenAI `text-embedding-3` and later models. To drop it from the call, set `litellm.drop_params = True`.",
|
||||
message="Setting dimensions is not supported for OpenAI `text-embedding-3` and later models. To drop it from the call, set `litellm.drop_params = True`.",
|
||||
)
|
||||
if custom_llm_provider == "triton":
|
||||
keys = list(non_default_params.keys())
|
||||
|
|
@ -2641,39 +2641,57 @@ def get_optional_params_embeddings(
|
|||
)
|
||||
final_params = {**optional_params, **kwargs}
|
||||
return final_params
|
||||
if custom_llm_provider == "vertex_ai":
|
||||
if len(non_default_params.keys()) > 0:
|
||||
if litellm.drop_params is True: # drop the unsupported non-default values
|
||||
keys = list(non_default_params.keys())
|
||||
for k in keys:
|
||||
non_default_params.pop(k, None)
|
||||
final_params = {**non_default_params, **kwargs}
|
||||
return final_params
|
||||
raise UnsupportedParamsError(
|
||||
status_code=500,
|
||||
message=f"Setting user/encoding format is not supported by {custom_llm_provider}. To drop it from the call, set `litellm.drop_params = True`.",
|
||||
)
|
||||
if custom_llm_provider == "bedrock":
|
||||
# if dimensions is in non_default_params -> pass it for model=bedrock/amazon.titan-embed-text-v2
|
||||
if (
|
||||
"dimensions" in non_default_params.keys()
|
||||
and "amazon.titan-embed-text-v2" in model
|
||||
):
|
||||
kwargs["dimensions"] = non_default_params["dimensions"]
|
||||
non_default_params.pop("dimensions", None)
|
||||
if "amazon.titan-embed-text-v1" in model:
|
||||
object: Any = litellm.AmazonTitanG1Config()
|
||||
elif "amazon.titan-embed-image-v1" in model:
|
||||
object = litellm.AmazonTitanMultimodalEmbeddingG1Config()
|
||||
elif "amazon.titan-embed-text-v2:0" in model:
|
||||
object = litellm.AmazonTitanV2Config()
|
||||
elif "cohere.embed-multilingual-v3" in model:
|
||||
object = litellm.BedrockCohereEmbeddingConfig()
|
||||
else: # unmapped model
|
||||
supported_params = []
|
||||
_check_valid_arg(supported_params=supported_params)
|
||||
final_params = {**kwargs}
|
||||
return final_params
|
||||
|
||||
if len(non_default_params.keys()) > 0:
|
||||
if litellm.drop_params is True: # drop the unsupported non-default values
|
||||
keys = list(non_default_params.keys())
|
||||
for k in keys:
|
||||
non_default_params.pop(k, None)
|
||||
final_params = {**non_default_params, **kwargs}
|
||||
return final_params
|
||||
raise UnsupportedParamsError(
|
||||
status_code=500,
|
||||
message=f"Setting user/encoding format is not supported by {custom_llm_provider}. To drop it from the call, set `litellm.drop_params = True`.",
|
||||
)
|
||||
return {**non_default_params, **kwargs}
|
||||
supported_params = object.get_supported_openai_params()
|
||||
_check_valid_arg(supported_params=supported_params)
|
||||
optional_params = object.map_openai_params(
|
||||
non_default_params=non_default_params, optional_params={}
|
||||
)
|
||||
final_params = {**optional_params, **kwargs}
|
||||
return final_params
|
||||
# elif model == "amazon.titan-embed-image-v1":
|
||||
# supported_params = litellm.AmazonTitanG1Config().get_supported_openai_params()
|
||||
# _check_valid_arg(supported_params=supported_params)
|
||||
# optional_params = litellm.AmazonTitanG1Config().map_openai_params(
|
||||
# non_default_params=non_default_params, optional_params={}
|
||||
# )
|
||||
# final_params = {**optional_params, **kwargs}
|
||||
# return final_params
|
||||
|
||||
# if (
|
||||
# "dimensions" in non_default_params.keys()
|
||||
# and "amazon.titan-embed-text-v2" in model
|
||||
# ):
|
||||
# kwargs["dimensions"] = non_default_params["dimensions"]
|
||||
# non_default_params.pop("dimensions", None)
|
||||
|
||||
# if len(non_default_params.keys()) > 0:
|
||||
# if litellm.drop_params is True: # drop the unsupported non-default values
|
||||
# keys = list(non_default_params.keys())
|
||||
# for k in keys:
|
||||
# non_default_params.pop(k, None)
|
||||
# final_params = {**non_default_params, **kwargs}
|
||||
# return final_params
|
||||
# raise UnsupportedParamsError(
|
||||
# status_code=500,
|
||||
# message=f"Setting user/encoding format is not supported by {custom_llm_provider}. To drop it from the call, set `litellm.drop_params = True`.",
|
||||
# )
|
||||
# return {**non_default_params, **kwargs}
|
||||
if custom_llm_provider == "mistral":
|
||||
supported_params = get_supported_openai_params(
|
||||
model=model,
|
||||
|
|
@ -9888,11 +9906,7 @@ class CustomStreamWrapper:
|
|||
|
||||
if anthropic_response_obj["usage"] is not None:
|
||||
model_response.usage = litellm.Usage(
|
||||
prompt_tokens=anthropic_response_obj["usage"]["prompt_tokens"],
|
||||
completion_tokens=anthropic_response_obj["usage"][
|
||||
"completion_tokens"
|
||||
],
|
||||
total_tokens=anthropic_response_obj["usage"]["total_tokens"],
|
||||
**anthropic_response_obj["usage"]
|
||||
)
|
||||
|
||||
if (
|
||||
|
|
@ -10507,10 +10521,10 @@ class CustomStreamWrapper:
|
|||
original_chunk.system_fingerprint
|
||||
)
|
||||
print_verbose(f"self.sent_first_chunk: {self.sent_first_chunk}")
|
||||
if self.sent_first_chunk == False:
|
||||
if self.sent_first_chunk is False:
|
||||
model_response.choices[0].delta["role"] = "assistant"
|
||||
self.sent_first_chunk = True
|
||||
elif self.sent_first_chunk == True and hasattr(
|
||||
elif self.sent_first_chunk is True and hasattr(
|
||||
model_response.choices[0].delta, "role"
|
||||
):
|
||||
_initial_delta = model_response.choices[
|
||||
|
|
@ -10575,7 +10589,7 @@ class CustomStreamWrapper:
|
|||
model_response.choices[0].delta.tool_calls is not None
|
||||
or model_response.choices[0].delta.function_call is not None
|
||||
):
|
||||
if self.sent_first_chunk == False:
|
||||
if self.sent_first_chunk is False:
|
||||
model_response.choices[0].delta["role"] = "assistant"
|
||||
self.sent_first_chunk = True
|
||||
return model_response
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue