chore: initial snapshot for gitea/github upload
This commit is contained in:
Your Name
@@ -0,0 +1,160 @@
|
||||
"""
|
||||
Support for OVHCloud AI Endpoints `/v1/audio/transcriptions` endpoint.
|
||||
|
||||
Our unified API follows the OpenAI standard.
|
||||
More information on our website: https://endpoints.ai.cloud.ovh.net
|
||||
"""
|
||||
|
||||
from typing import List, Optional, Union
|
||||
|
||||
import httpx
|
||||
|
||||
from litellm.litellm_core_utils.audio_utils.utils import process_audio_file
|
||||
from litellm.llms.base_llm.audio_transcription.transformation import (
|
||||
AudioTranscriptionRequestData,
|
||||
BaseAudioTranscriptionConfig,
|
||||
)
|
||||
from litellm.llms.base_llm.chat.transformation import BaseLLMException
|
||||
from litellm.secret_managers.main import get_secret_str
|
||||
from litellm.types.llms.openai import (
|
||||
AllMessageValues,
|
||||
OpenAIAudioTranscriptionOptionalParams,
|
||||
)
|
||||
from litellm.types.utils import FileTypes, TranscriptionResponse
|
||||
|
||||
from ..utils import OVHCloudException
|
||||
|
||||
|
||||
class OVHCloudAudioTranscriptionConfig(BaseAudioTranscriptionConfig):
|
||||
def get_supported_openai_params(
|
||||
self, model: str
|
||||
) -> List[OpenAIAudioTranscriptionOptionalParams]:
|
||||
# OVHCloud implements the OpenAI-compatible Whisper interface.
|
||||
# We pass through the same optional params as the OpenAI Whisper API.
|
||||
return [
|
||||
"language",
|
||||
"prompt",
|
||||
"response_format",
|
||||
"timestamp_granularities",
|
||||
"temperature",
|
||||
]
|
||||
|
||||
def map_openai_params(
|
||||
self,
|
||||
non_default_params: dict,
|
||||
optional_params: dict,
|
||||
model: str,
|
||||
drop_params: bool,
|
||||
) -> dict:
|
||||
supported_params = self.get_supported_openai_params(model)
|
||||
for k, v in non_default_params.items():
|
||||
if k in supported_params:
|
||||
optional_params[k] = v
|
||||
return optional_params
|
||||
|
||||
def get_complete_url(
|
||||
self,
|
||||
api_base: Optional[str],
|
||||
api_key: Optional[str],
|
||||
model: str,
|
||||
optional_params: dict,
|
||||
litellm_params: dict,
|
||||
stream: Optional[bool] = None,
|
||||
) -> str:
|
||||
api_base = (
|
||||
"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1"
|
||||
if api_base is None
|
||||
else api_base.rstrip("/")
|
||||
)
|
||||
complete_url = f"{api_base}/audio/transcriptions"
|
||||
return complete_url
|
||||
|
||||
def get_error_class(
|
||||
self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
|
||||
) -> BaseLLMException:
|
||||
return OVHCloudException(
|
||||
message=error_message,
|
||||
status_code=status_code,
|
||||
headers=headers,
|
||||
)
|
||||
|
||||
def validate_environment(
|
||||
self,
|
||||
headers: dict,
|
||||
model: str,
|
||||
messages: List[AllMessageValues],
|
||||
optional_params: dict,
|
||||
litellm_params: dict,
|
||||
api_key: Optional[str] = None,
|
||||
api_base: Optional[str] = None,
|
||||
) -> dict:
|
||||
if api_key is None:
|
||||
api_key = get_secret_str("OVHCLOUD_API_KEY")
|
||||
|
||||
default_headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"accept": "application/json",
|
||||
}
|
||||
|
||||
# Caller can override / extend headers if needed
|
||||
default_headers.update(headers or {})
|
||||
return default_headers
|
||||
|
||||
def transform_audio_transcription_request(
|
||||
self,
|
||||
model: str,
|
||||
audio_file: FileTypes,
|
||||
optional_params: dict,
|
||||
litellm_params: dict,
|
||||
) -> AudioTranscriptionRequestData:
|
||||
"""
|
||||
Transform the audio transcription request into OpenAI-compatible form-data.
|
||||
|
||||
OVHCloud follows OpenAI's `/audio/transcriptions` format, so we:
|
||||
- Build a multipart form-data body with `file`, `model`, and optional params
|
||||
- Let the shared HTTP handler set the proper content-type boundary
|
||||
"""
|
||||
processed_audio = process_audio_file(audio_file)
|
||||
|
||||
# Base form fields: model + OpenAI-compatible optional params
|
||||
form_fields: dict = {
|
||||
"model": model,
|
||||
}
|
||||
|
||||
# Include OpenAI-compatible optional params
|
||||
for key in self.get_supported_openai_params(model):
|
||||
value = optional_params.get(key)
|
||||
if value is not None:
|
||||
form_fields[key] = value
|
||||
|
||||
files = {
|
||||
"file": (
|
||||
processed_audio.filename,
|
||||
processed_audio.file_content,
|
||||
processed_audio.content_type,
|
||||
)
|
||||
}
|
||||
|
||||
return AudioTranscriptionRequestData(data=form_fields, files=files)
|
||||
|
||||
def transform_audio_transcription_response(
|
||||
self,
|
||||
raw_response: httpx.Response,
|
||||
) -> TranscriptionResponse:
|
||||
"""
|
||||
Transform OVHCloud audio transcription response to OpenAI-compatible TranscriptionResponse.
|
||||
"""
|
||||
try:
|
||||
response_json = raw_response.json()
|
||||
except Exception:
|
||||
raise OVHCloudException(
|
||||
message=raw_response.text,
|
||||
status_code=raw_response.status_code,
|
||||
headers=raw_response.headers,
|
||||
)
|
||||
|
||||
text = response_json.get("text") or response_json.get("transcript") or ""
|
||||
response = TranscriptionResponse(text=text)
|
||||
|
||||
response._hidden_params = response_json
|
||||
return response
|
||||
@@ -0,0 +1,148 @@
|
||||
"""
|
||||
Support for OVHCloud AI Endpoints `/v1/chat/completions` endpoint.
|
||||
|
||||
Our unified API follows the OpenAI standard.
|
||||
More information on our website: https://endpoints.ai.cloud.ovh.net
|
||||
"""
|
||||
from typing import Optional, Union, List
|
||||
|
||||
import httpx
|
||||
from litellm.utils import ModelResponseStream, get_model_info
|
||||
from litellm.llms.openai.chat.gpt_transformation import OpenAIGPTConfig
|
||||
from litellm._logging import verbose_logger
|
||||
from litellm.llms.ovhcloud.utils import OVHCloudException
|
||||
from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator
|
||||
from litellm.llms.base_llm.chat.transformation import BaseLLMException
|
||||
from litellm.types.llms.openai import AllMessageValues
|
||||
|
||||
|
||||
class OVHCloudChatConfig(OpenAIGPTConfig):
|
||||
@property
|
||||
def custom_llm_provider(self) -> Optional[str]:
|
||||
return "ovhcloud"
|
||||
|
||||
def get_supported_openai_params(self, model: str) -> list:
|
||||
"""
|
||||
Details about function calling support can be found here:
|
||||
https://help.ovhcloud.com/csm/en-gb-public-cloud-ai-endpoints-function-calling?id=kb_article_view&sysparm_article=KB0071907
|
||||
"""
|
||||
supports_function_calling: Optional[bool] = None
|
||||
try:
|
||||
model_info = get_model_info(model, custom_llm_provider="ovhcloud")
|
||||
supports_function_calling = model_info.get(
|
||||
"supports_function_calling", False
|
||||
)
|
||||
except Exception as e:
|
||||
verbose_logger.debug(f"Error getting supported OpenAI params: {e}")
|
||||
pass
|
||||
|
||||
optional_params = super().get_supported_openai_params(model)
|
||||
if supports_function_calling is not True:
|
||||
verbose_logger.debug(
|
||||
"You can see our models supporting function_calling in our catalog: https://endpoints.ai.cloud.ovh.net/catalog "
|
||||
)
|
||||
optional_params.remove("tools")
|
||||
optional_params.remove("tool_choice")
|
||||
optional_params.remove("function_call")
|
||||
optional_params.remove("response_format")
|
||||
return optional_params
|
||||
|
||||
def get_complete_url(
|
||||
self,
|
||||
api_base: Optional[str],
|
||||
api_key: Optional[str],
|
||||
model: str,
|
||||
optional_params: dict,
|
||||
litellm_params: dict,
|
||||
stream: Optional[bool] = None,
|
||||
) -> str:
|
||||
api_base = (
|
||||
"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1"
|
||||
if api_base is None
|
||||
else api_base.rstrip("/")
|
||||
)
|
||||
complete_url = f"{api_base}/chat/completions"
|
||||
return complete_url
|
||||
|
||||
def get_error_class(
|
||||
self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
|
||||
) -> BaseLLMException:
|
||||
return OVHCloudException(
|
||||
message=error_message,
|
||||
status_code=status_code,
|
||||
headers=headers,
|
||||
)
|
||||
|
||||
def map_openai_params(
|
||||
self,
|
||||
non_default_params: dict,
|
||||
optional_params: dict,
|
||||
model: str,
|
||||
drop_params: bool,
|
||||
) -> dict:
|
||||
mapped_openai_params = super().map_openai_params(
|
||||
non_default_params, optional_params, model, drop_params
|
||||
)
|
||||
return mapped_openai_params
|
||||
|
||||
def transform_request(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[AllMessageValues],
|
||||
optional_params: dict,
|
||||
litellm_params: dict,
|
||||
headers: dict,
|
||||
) -> dict:
|
||||
extra_body = optional_params.pop("extra_body", {})
|
||||
response = super().transform_request(
|
||||
model, messages, optional_params, litellm_params, headers
|
||||
)
|
||||
response.update(extra_body)
|
||||
return response
|
||||
|
||||
|
||||
class OVHCloudChatCompletionStreamingHandler(BaseModelResponseIterator):
|
||||
"""
|
||||
Handler for OVHCloud AI Endpoints streaming chat completion responses
|
||||
"""
|
||||
|
||||
def chunk_parser(self, chunk: dict) -> ModelResponseStream:
|
||||
"""
|
||||
Parse individual chunks from streaming response
|
||||
"""
|
||||
try:
|
||||
if "error" in chunk:
|
||||
error_chunk = chunk["error"]
|
||||
error_message = "OVHCloud Error: {}".format(
|
||||
error_chunk.get("message", "Unknown error")
|
||||
)
|
||||
raise OVHCloudException(
|
||||
message=error_message,
|
||||
status_code=error_chunk.get("code", 400),
|
||||
headers={"Content-Type": "application/json"},
|
||||
)
|
||||
|
||||
new_choices = []
|
||||
for choice in chunk["choices"]:
|
||||
if "delta" in choice and "reasoning" in choice["delta"]:
|
||||
choice["delta"]["reasoning_content"] = choice["delta"].get(
|
||||
"reasoning"
|
||||
)
|
||||
new_choices.append(choice)
|
||||
|
||||
return ModelResponseStream(
|
||||
id=chunk["id"],
|
||||
object="chat.completion.chunk",
|
||||
created=chunk["created"],
|
||||
usage=chunk.get("usage"),
|
||||
model=chunk["model"],
|
||||
choices=new_choices,
|
||||
)
|
||||
except KeyError as e:
|
||||
raise OVHCloudException(
|
||||
message=f"KeyError: {e}, Got unexpected response from CometAPI: {chunk}",
|
||||
status_code=400,
|
||||
headers={"Content-Type": "application/json"},
|
||||
)
|
||||
except Exception as e:
|
||||
raise e
|
||||
@@ -0,0 +1,126 @@
|
||||
"""
|
||||
This is OpenAI compatible - no transformation is applied
|
||||
|
||||
"""
|
||||
from typing import List, Optional, Union
|
||||
|
||||
import httpx
|
||||
|
||||
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
|
||||
from litellm.llms.base_llm.chat.transformation import BaseLLMException
|
||||
from litellm.llms.base_llm.embedding.transformation import BaseEmbeddingConfig
|
||||
from litellm.secret_managers.main import get_secret_str
|
||||
from litellm.types.llms.openai import AllEmbeddingInputValues, AllMessageValues
|
||||
from litellm.types.utils import EmbeddingResponse, Usage
|
||||
|
||||
from ..utils import OVHCloudException
|
||||
|
||||
|
||||
class OVHCloudEmbeddingConfig(BaseEmbeddingConfig):
|
||||
def __init__(self) -> None:
|
||||
pass
|
||||
|
||||
def get_complete_url(
|
||||
self,
|
||||
api_base: Optional[str],
|
||||
api_key: Optional[str],
|
||||
model: str,
|
||||
optional_params: dict,
|
||||
litellm_params: dict,
|
||||
stream: Optional[bool] = None,
|
||||
) -> str:
|
||||
api_base = (
|
||||
"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1"
|
||||
if api_base is None
|
||||
else api_base.rstrip("/")
|
||||
)
|
||||
complete_url = f"{api_base}/embeddings"
|
||||
return complete_url
|
||||
|
||||
def validate_environment(
|
||||
self,
|
||||
headers: dict,
|
||||
model: str,
|
||||
messages: List[AllMessageValues],
|
||||
optional_params: dict,
|
||||
litellm_params: dict,
|
||||
api_key: Optional[str] = None,
|
||||
api_base: Optional[str] = None,
|
||||
) -> dict:
|
||||
if api_key is None:
|
||||
api_key = get_secret_str("OVHCLOUD_API_KEY")
|
||||
|
||||
default_headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"accept": "application/json",
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
|
||||
if "Authorization" in headers:
|
||||
default_headers["Authorization"] = headers["Authorization"]
|
||||
|
||||
return {**default_headers, **headers}
|
||||
|
||||
def get_supported_openai_params(self, model: str):
|
||||
return []
|
||||
|
||||
def map_openai_params(
|
||||
self,
|
||||
non_default_params: dict,
|
||||
optional_params: dict,
|
||||
model: str,
|
||||
drop_params: bool,
|
||||
):
|
||||
supported_openai_params = self.get_supported_openai_params(model)
|
||||
for param, value in non_default_params.items():
|
||||
if param in supported_openai_params:
|
||||
optional_params[param] = value
|
||||
return optional_params
|
||||
|
||||
def transform_embedding_request(
|
||||
self,
|
||||
model: str,
|
||||
input: AllEmbeddingInputValues,
|
||||
optional_params: dict,
|
||||
headers: dict,
|
||||
) -> dict:
|
||||
return {"input": input, "model": model, **optional_params}
|
||||
|
||||
def transform_embedding_response(
|
||||
self,
|
||||
model: str,
|
||||
raw_response: httpx.Response,
|
||||
model_response: EmbeddingResponse,
|
||||
logging_obj: LiteLLMLoggingObj,
|
||||
api_key: Optional[str],
|
||||
request_data: dict,
|
||||
optional_params: dict,
|
||||
litellm_params: dict,
|
||||
) -> EmbeddingResponse:
|
||||
try:
|
||||
raw_response_json = raw_response.json()
|
||||
except Exception:
|
||||
raise OVHCloudException(
|
||||
message=raw_response.text,
|
||||
status_code=raw_response.status_code,
|
||||
headers=raw_response.headers,
|
||||
)
|
||||
|
||||
model_response.model = raw_response_json.get("model")
|
||||
model_response.data = raw_response_json.get("data")
|
||||
model_response.object = raw_response_json.get("object")
|
||||
|
||||
usage = Usage(
|
||||
prompt_tokens=raw_response_json.get("usage", {}).get("prompt_tokens", 0),
|
||||
total_tokens=raw_response_json.get("usage", {}).get("total_tokens", 0),
|
||||
)
|
||||
|
||||
model_response.usage = usage
|
||||
return model_response
|
||||
|
||||
def get_error_class(
|
||||
self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
|
||||
) -> BaseLLMException:
|
||||
return OVHCloudException(
|
||||
message=error_message, status_code=status_code, headers=headers
|
||||
)
|
||||
@@ -0,0 +1,7 @@
|
||||
from litellm.llms.base_llm.chat.transformation import BaseLLMException
|
||||
|
||||
|
||||
class OVHCloudException(BaseLLMException):
|
||||
"""OVHCloud AI Endpoints exception handling class"""
|
||||
|
||||
pass
|
||||
Reference in New Issue
Block a user