mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 03:04:13 +00:00
0b30e212da
* fix(langfuse.py): prevent double logging requester metadata Fixes https://github.com/BerriAI/litellm/issues/5935 * build(model_prices_and_context_window.json): add mistral pixtral cost tracking Closes https://github.com/BerriAI/litellm/issues/5837 * handle streaming for azure ai studio error * [Perf Proxy] parallel request limiter - use one cache update call (#5932) * fix parallel request limiter - use one cache update call * ci/cd run again * run ci/cd again * use docker username password * fix config.yml * fix config * fix config * fix config.yml * ci/cd run again * use correct typing for batch set cache * fix async_set_cache_pipeline * fix only check user id tpm / rpm limits when limits set * fix test_openai_azure_embedding_with_oidc_and_cf * fix(groq/chat/transformation.py): Fixes https://github.com/BerriAI/litellm/issues/5839 * feat(anthropic/chat.py): return 'retry-after' headers from anthropic Fixes https://github.com/BerriAI/litellm/issues/4387 * feat: raise validation error if message has tool calls without passing `tools` param for anthropic/bedrock Closes https://github.com/BerriAI/litellm/issues/5747 * [Feature]#5940, add max_workers parameter for the batch_completion (#5947) * handle streaming for azure ai studio error * bump: version 1.48.2 → 1.48.3 * docs(data_security.md): add legal/compliance faq's Make it easier for companies to use litellm * docs: resolve imports * [Feature]#5940, add max_workers parameter for the batch_completion method --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com> Co-authored-by: josearangos <josearangos@Joses-MacBook-Pro.local> * fix(converse_transformation.py): fix default message value * fix(utils.py): fix get_model_info to handle finetuned models Fixes issue for standard logging payloads, where model_map_value was null for finetuned openai models * fix(litellm_pre_call_utils.py): add debug statement for data sent after updating with team/key callbacks * fix: fix linting errors * fix(anthropic/chat/handler.py): fix cache creation input tokens * fix(exception_mapping_utils.py): fix missing imports * fix(anthropic/chat/handler.py): fix usage block translation * test: fix test * test: fix tests * style(types/utils.py): trigger new build * test: fix test --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Jose Alberto Arango Sanchez <jose.arangos@udea.edu.co> Co-authored-by: josearangos <josearangos@Joses-MacBook-Pro.local>
88 lines
2.9 KiB
Python
88 lines
2.9 KiB
Python
"""
|
|
Translate from OpenAI's `/v1/chat/completions` to Groq's `/v1/chat/completions`
|
|
"""
|
|
|
|
import types
|
|
from typing import List, Optional, Union
|
|
|
|
from pydantic import BaseModel
|
|
|
|
import litellm
|
|
from litellm.types.llms.openai import AllMessageValues, ChatCompletionAssistantMessage
|
|
|
|
from ...OpenAI.chat.gpt_transformation import OpenAIGPTConfig
|
|
|
|
|
|
class GroqChatConfig(OpenAIGPTConfig):
|
|
|
|
frequency_penalty: Optional[int] = None
|
|
function_call: Optional[Union[str, dict]] = None
|
|
functions: Optional[list] = None
|
|
logit_bias: Optional[dict] = None
|
|
max_tokens: Optional[int] = None
|
|
n: Optional[int] = None
|
|
presence_penalty: Optional[int] = None
|
|
stop: Optional[Union[str, list]] = None
|
|
temperature: Optional[int] = None
|
|
top_p: Optional[int] = None
|
|
response_format: Optional[dict] = None
|
|
tools: Optional[list] = None
|
|
tool_choice: Optional[Union[str, dict]] = None
|
|
|
|
def __init__(
|
|
self,
|
|
frequency_penalty: Optional[int] = None,
|
|
function_call: Optional[Union[str, dict]] = None,
|
|
functions: Optional[list] = None,
|
|
logit_bias: Optional[dict] = None,
|
|
max_tokens: Optional[int] = None,
|
|
n: Optional[int] = None,
|
|
presence_penalty: Optional[int] = None,
|
|
stop: Optional[Union[str, list]] = None,
|
|
temperature: Optional[int] = None,
|
|
top_p: Optional[int] = None,
|
|
response_format: Optional[dict] = None,
|
|
tools: Optional[list] = None,
|
|
tool_choice: Optional[Union[str, dict]] = None,
|
|
) -> None:
|
|
locals_ = locals().copy()
|
|
for key, value in locals_.items():
|
|
if key != "self" and value is not None:
|
|
setattr(self.__class__, key, value)
|
|
|
|
@classmethod
|
|
def get_config(cls):
|
|
return {
|
|
k: v
|
|
for k, v in cls.__dict__.items()
|
|
if not k.startswith("__")
|
|
and not isinstance(
|
|
v,
|
|
(
|
|
types.FunctionType,
|
|
types.BuiltinFunctionType,
|
|
classmethod,
|
|
staticmethod,
|
|
),
|
|
)
|
|
and v is not None
|
|
}
|
|
|
|
def _transform_messages(self, messages: List[AllMessageValues]) -> List:
|
|
for idx, message in enumerate(messages):
|
|
"""
|
|
1. Don't pass 'null' function_call assistant message to groq - https://github.com/BerriAI/litellm/issues/5839
|
|
"""
|
|
if isinstance(message, BaseModel):
|
|
_message = message.model_dump()
|
|
else:
|
|
_message = message
|
|
assistant_message = _message.get("role") == "assistant"
|
|
if assistant_message:
|
|
new_message = ChatCompletionAssistantMessage(role="assistant")
|
|
for k, v in _message.items():
|
|
if v is not None:
|
|
new_message[k] = v # type: ignore
|
|
messages[idx] = new_message
|
|
|
|
return messages
|