mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 11:14:04 +00:00
5253f639cd
* fix(health.md): add rerank model health check information * build(model_prices_and_context_window.json): add gemini 2.0 for google ai studio - pricing + commercial rate limits * build(model_prices_and_context_window.json): add gemini-2.0 supports audio output = true * docs(team_model_add.md): clarify allowing teams to add models is an enterprise feature * fix(o1_transformation.py): add support for 'n', 'response_format' and 'stop' params for o1 and 'stream_options' param for o1-mini * build(model_prices_and_context_window.json): add 'supports_system_message' to supporting openai models needed as o1-preview, and o1-mini models don't support 'system message * fix(o1_transformation.py): translate system message based on if o1 model supports it * fix(o1_transformation.py): return 'stream' param support if o1-mini/o1-preview o1 currently doesn't support streaming, but the other model versions do Fixes https://github.com/BerriAI/litellm/issues/7292 * fix(o1_transformation.py): return tool calling/response_format in supported params if model map says so Fixes https://github.com/BerriAI/litellm/issues/7292 * fix: fix linting errors * fix: update '_transform_messages' * fix(o1_transformation.py): fix provider passed for supported param checks * test(base_llm_unit_tests.py): skip test if api takes >5s to respond * fix(utils.py): return false in 'supports_factory' if can't find value * fix(o1_transformation.py): always return stream + stream_options as supported params + handle stream options being passed in for azure o1 * feat(openai.py): support stream faking natively in openai handler Allows o1 calls to be faked for just the "o1" model, allows native streaming for o1-mini, o1-preview Fixes https://github.com/BerriAI/litellm/issues/7292 * fix(openai.py): use inference param instead of original optional param
85 lines
2.8 KiB
Python
85 lines
2.8 KiB
Python
"""
|
|
Handles the chat completion request for Databricks
|
|
"""
|
|
|
|
from typing import Any, Callable, List, Literal, Optional, Tuple, Union, cast
|
|
|
|
from httpx._config import Timeout
|
|
|
|
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
|
|
from litellm.types.llms.openai import AllMessageValues
|
|
from litellm.types.utils import CustomStreamingDecoder
|
|
from litellm.utils import ModelResponse
|
|
|
|
from ...openai_like.chat.handler import OpenAILikeChatHandler
|
|
from ..common_utils import DatabricksBase
|
|
from ..exceptions import DatabricksError
|
|
from .transformation import DatabricksConfig
|
|
|
|
|
|
class DatabricksChatCompletion(OpenAILikeChatHandler, DatabricksBase):
|
|
def __init__(self, **kwargs):
|
|
super().__init__(**kwargs)
|
|
|
|
def completion(
|
|
self,
|
|
*,
|
|
model: str,
|
|
messages: list,
|
|
api_base: str,
|
|
custom_llm_provider: str,
|
|
custom_prompt_dict: dict,
|
|
model_response: ModelResponse,
|
|
print_verbose: Callable,
|
|
encoding,
|
|
api_key: Optional[str],
|
|
logging_obj,
|
|
optional_params: dict,
|
|
acompletion=None,
|
|
litellm_params=None,
|
|
logger_fn=None,
|
|
headers: Optional[dict] = None,
|
|
timeout: Optional[Union[float, Timeout]] = None,
|
|
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
|
|
custom_endpoint: Optional[bool] = None,
|
|
streaming_decoder: Optional[CustomStreamingDecoder] = None,
|
|
fake_stream: bool = False,
|
|
):
|
|
messages = DatabricksConfig()._transform_messages(
|
|
messages=cast(List[AllMessageValues], messages), model=model
|
|
)
|
|
api_base, headers = self.databricks_validate_environment(
|
|
api_base=api_base,
|
|
api_key=api_key,
|
|
endpoint_type="chat_completions",
|
|
custom_endpoint=custom_endpoint,
|
|
headers=headers,
|
|
)
|
|
|
|
if optional_params.get("stream") is True:
|
|
fake_stream = DatabricksConfig()._should_fake_stream(optional_params)
|
|
else:
|
|
fake_stream = False
|
|
|
|
return super().completion(
|
|
model=model,
|
|
messages=messages,
|
|
api_base=api_base,
|
|
custom_llm_provider=custom_llm_provider,
|
|
custom_prompt_dict=custom_prompt_dict,
|
|
model_response=model_response,
|
|
print_verbose=print_verbose,
|
|
encoding=encoding,
|
|
api_key=api_key,
|
|
logging_obj=logging_obj,
|
|
optional_params=optional_params,
|
|
acompletion=acompletion,
|
|
litellm_params=litellm_params,
|
|
logger_fn=logger_fn,
|
|
headers=headers,
|
|
timeout=timeout,
|
|
client=client,
|
|
custom_endpoint=True,
|
|
streaming_decoder=streaming_decoder,
|
|
fake_stream=fake_stream,
|
|
)
|