forked from phoenix/litellm-mirror
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>
60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
"""
|
|
Handles the chat completion request for groq
|
|
"""
|
|
|
|
from typing import Any, Callable, Optional, Union
|
|
|
|
from httpx._config import Timeout
|
|
|
|
from litellm.utils import ModelResponse
|
|
|
|
from ...groq.chat.transformation import GroqChatConfig
|
|
from ...OpenAI.openai import OpenAIChatCompletion
|
|
|
|
|
|
class GroqChatCompletion(OpenAIChatCompletion):
|
|
def __init__(self, **kwargs):
|
|
super().__init__(**kwargs)
|
|
|
|
def completion(
|
|
self,
|
|
model_response: ModelResponse,
|
|
timeout: Union[float, Timeout],
|
|
optional_params: dict,
|
|
logging_obj: Any,
|
|
model: Optional[str] = None,
|
|
messages: Optional[list] = None,
|
|
print_verbose: Optional[Callable[..., Any]] = None,
|
|
api_key: Optional[str] = None,
|
|
api_base: Optional[str] = None,
|
|
acompletion: bool = False,
|
|
litellm_params=None,
|
|
logger_fn=None,
|
|
headers: Optional[dict] = None,
|
|
custom_prompt_dict: dict = {},
|
|
client=None,
|
|
organization: Optional[str] = None,
|
|
custom_llm_provider: Optional[str] = None,
|
|
drop_params: Optional[bool] = None,
|
|
):
|
|
messages = GroqChatConfig()._transform_messages(messages) # type: ignore
|
|
return super().completion(
|
|
model_response,
|
|
timeout,
|
|
optional_params,
|
|
logging_obj,
|
|
model,
|
|
messages,
|
|
print_verbose,
|
|
api_key,
|
|
api_base,
|
|
acompletion,
|
|
litellm_params,
|
|
logger_fn,
|
|
headers,
|
|
custom_prompt_dict,
|
|
client,
|
|
organization,
|
|
custom_llm_provider,
|
|
drop_params,
|
|
)
|