phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Litellm dev 12 25 2025 p2 (#7420)

Browse source 
* test: add new test image embedding to base llm unit tests

Addresses https://github.com/BerriAI/litellm/issues/6515

* fix(bedrock/embed/multimodal-embeddings): strip data prefix from image urls for bedrock multimodal embeddings

Fix https://github.com/BerriAI/litellm/issues/6515

* feat: initial commit for fireworks ai audio transcription support

Relevant issue: https://github.com/BerriAI/litellm/issues/7134

* test: initial fireworks ai test

* feat(fireworks_ai/): implemented fireworks ai audio transcription config

* fix(utils.py): register fireworks ai audio transcription config, in config manager

* fix(utils.py): add fireworks ai param translation to 'get_optional_params_transcription'

* refactor(fireworks_ai/): define text completion route with model name handling

moves model name handling to specific fireworks routes, as required by their api

* refactor(fireworks_ai/chat): define transform_Request - allows fixing model if accounts/ is missing

* fix: fix linting errors

* fix: fix linting errors

* fix: fix linting errors

* fix: fix linting errors

* fix(handler.py): fix linting errors

* fix(main.py): fix tgai text completion route

* refactor(together_ai/completion): refactors together ai text completion route to just use provider transform request

* refactor: move test_fine_tuning_api out of local_testing

reduces local testing ci/cd time
This commit is contained in:
Krish Dholakia 2024-12-25 18:35:34 -08:00 • committed by GitHub
parent 9237357bcc
commit 760328b6ad
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 709 additions and 177 deletions
Download patch file Download diff file Expand all files Collapse all files

21
litellm/llms/openai/completion/handler.py
View file

@ -8,7 +8,8 @@ from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLogging
from litellm.litellm_core_utils.streaming_handler import CustomStreamWrapper
from litellm.llms.base import BaseLLM
from litellm.types.llms.openai import AllMessageValues, OpenAITextCompletionUserMessage
from litellm.types.utils import ModelResponse, TextCompletionResponse
from litellm.types.utils import LlmProviders, ModelResponse, TextCompletionResponse
from litellm.utils import ProviderConfigManager
from ..common_utils import OpenAIError
from .transformation import OpenAITextCompletionConfig
@ -35,6 +36,7 @@ class OpenAITextCompletion(BaseLLM):
model: str,
messages: Union[List[AllMessageValues], List[OpenAITextCompletionUserMessage]],
timeout: float,
custom_llm_provider: str,
logging_obj: LiteLLMLoggingObj,
optional_params: dict,
print_verbose: Optional[Callable] = None,
@ -54,11 +56,17 @@ class OpenAITextCompletion(BaseLLM):
# don't send max retries to the api, if set
prompt = self.openai_text_completion_global_config._transform_prompt(
messages
provider_config = ProviderConfigManager.get_provider_text_completion_config(
model=model,
provider=LlmProviders(custom_llm_provider),
)
data = {"model": model, "prompt": prompt, **optional_params}
data = provider_config.transform_text_completion_request(
model=model,
messages=messages,
optional_params=optional_params,
headers=headers,
)
max_retries = data.pop("max_retries", 2)
## LOGGING
logging_obj.pre_call(
@ -86,7 +94,7 @@ class OpenAITextCompletion(BaseLLM):
organization=organization,
)
else:
return self.acompletion(api_base=api_base, data=data, headers=headers, model_response=model_response, prompt=prompt, api_key=api_key, logging_obj=logging_obj, model=model, timeout=timeout, max_retries=max_retries, organization=organization, client=client) # type: ignore
return self.acompletion(api_base=api_base, data=data, headers=headers, model_response=model_response, api_key=api_key, logging_obj=logging_obj, model=model, timeout=timeout, max_retries=max_retries, organization=organization, client=client) # type: ignore
elif optional_params.get("stream", False):
return self.streaming(
logging_obj=logging_obj,
@ -120,7 +128,6 @@ class OpenAITextCompletion(BaseLLM):
## LOGGING
logging_obj.post_call(
input=prompt,
api_key=api_key,
original_response=response_json,
additional_args={
@ -149,7 +156,6 @@ class OpenAITextCompletion(BaseLLM):
data: dict,
headers: dict,
model_response: ModelResponse,
prompt: str,
api_key: str,
model: str,
timeout: float,
@ -178,7 +184,6 @@ class OpenAITextCompletion(BaseLLM):
## LOGGING
logging_obj.post_call(
input=prompt,
api_key=api_key,
original_response=response,
additional_args={