chore: initial public snapshot for github upload
This commit is contained in:
Your Name
@@ -0,0 +1,131 @@
|
||||
"""
|
||||
Sambanova Chat Completions API
|
||||
|
||||
this is OpenAI compatible - no translation needed / occurs
|
||||
"""
|
||||
|
||||
from typing import Any, Coroutine, List, Literal, Optional, Union, overload
|
||||
|
||||
from litellm.litellm_core_utils.prompt_templates.common_utils import (
|
||||
handle_messages_with_content_list_to_str_conversion,
|
||||
)
|
||||
from litellm.llms.openai.chat.gpt_transformation import OpenAIGPTConfig
|
||||
from litellm.types.llms.openai import AllMessageValues
|
||||
|
||||
|
||||
class SambanovaConfig(OpenAIGPTConfig):
|
||||
"""
|
||||
Reference: https://docs.sambanova.ai/cloud/api-reference/
|
||||
|
||||
Below are the parameters:
|
||||
"""
|
||||
|
||||
max_tokens: Optional[int] = None
|
||||
temperature: Optional[int] = None
|
||||
top_p: Optional[int] = None
|
||||
top_k: Optional[int] = None
|
||||
stop: Optional[Union[str, list]] = None
|
||||
stream: Optional[bool] = None
|
||||
stream_options: Optional[dict] = None
|
||||
tool_choice: Optional[str] = None
|
||||
response_format: Optional[dict] = None
|
||||
tools: Optional[list] = None
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
max_tokens: Optional[int] = None,
|
||||
response_format: Optional[dict] = None,
|
||||
stop: Optional[str] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[dict] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
top_k: Optional[int] = None,
|
||||
tool_choice: Optional[str] = None,
|
||||
tools: Optional[list] = 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 super().get_config()
|
||||
|
||||
def get_supported_openai_params(self, model: str) -> list:
|
||||
"""
|
||||
Get the supported OpenAI params for the given model
|
||||
|
||||
"""
|
||||
from litellm.utils import supports_function_calling
|
||||
|
||||
params = [
|
||||
"max_completion_tokens",
|
||||
"max_tokens",
|
||||
"response_format",
|
||||
"stop",
|
||||
"stream",
|
||||
"stream_options",
|
||||
"temperature",
|
||||
"top_p",
|
||||
"top_k",
|
||||
]
|
||||
|
||||
if supports_function_calling(model, custom_llm_provider="sambanova"):
|
||||
params.append("tools")
|
||||
params.append("tool_choice")
|
||||
params.append("parallel_tool_calls")
|
||||
|
||||
return params
|
||||
|
||||
def map_openai_params(
|
||||
self,
|
||||
non_default_params: dict,
|
||||
optional_params: dict,
|
||||
model: str,
|
||||
drop_params: bool,
|
||||
) -> dict:
|
||||
"""
|
||||
map max_completion_tokens param to max_tokens
|
||||
"""
|
||||
supported_openai_params = self.get_supported_openai_params(model=model)
|
||||
for param, value in non_default_params.items():
|
||||
if param == "max_completion_tokens":
|
||||
optional_params["max_tokens"] = value
|
||||
elif param in supported_openai_params:
|
||||
optional_params[param] = value
|
||||
return optional_params
|
||||
|
||||
@overload
|
||||
def _transform_messages(
|
||||
self, messages: List[AllMessageValues], model: str, is_async: Literal[True]
|
||||
) -> Coroutine[Any, Any, List[AllMessageValues]]:
|
||||
...
|
||||
|
||||
@overload
|
||||
def _transform_messages(
|
||||
self,
|
||||
messages: List[AllMessageValues],
|
||||
model: str,
|
||||
is_async: Literal[False] = False,
|
||||
) -> List[AllMessageValues]:
|
||||
...
|
||||
|
||||
def _transform_messages(
|
||||
self, messages: List[AllMessageValues], model: str, is_async: bool = False
|
||||
) -> Union[List[AllMessageValues], Coroutine[Any, Any, List[AllMessageValues]]]:
|
||||
"""
|
||||
Transform messages to handle content list conversion.
|
||||
|
||||
SambaNova API doesn't support content as a list - only string content.
|
||||
This converts content lists like [{"type": "text", "text": "..."}] to strings.
|
||||
"""
|
||||
|
||||
async def _async_transform():
|
||||
return handle_messages_with_content_list_to_str_conversion(messages)
|
||||
|
||||
if is_async:
|
||||
return _async_transform()
|
||||
messages = handle_messages_with_content_list_to_str_conversion(messages)
|
||||
return messages
|
||||
@@ -0,0 +1,6 @@
|
||||
from litellm.llms.base_llm.chat.transformation import BaseLLMException
|
||||
|
||||
|
||||
class SambaNovaError(BaseLLMException):
|
||||
def __init__(self, status_code, message, headers):
|
||||
super().__init__(status_code=status_code, message=message, headers=headers)
|
||||
@@ -0,0 +1,5 @@
|
||||
"""
|
||||
SambaNova Embedding - uses `llm_http_handler.py` to make httpx requests
|
||||
|
||||
Request/Response transformation is handled in `transformation.py`
|
||||
"""
|
||||
@@ -0,0 +1,139 @@
|
||||
"""
|
||||
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 ..common_utils import SambaNovaError
|
||||
|
||||
|
||||
class SambaNovaEmbeddingConfig(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:
|
||||
if api_base is None:
|
||||
raise ValueError("api_base is required for SambaNova embeddings")
|
||||
# Remove trailing slashes and ensure clean base URL
|
||||
api_base = api_base.rstrip("/")
|
||||
if not api_base.endswith("/embeddings"):
|
||||
api_base = f"{api_base}/embeddings"
|
||||
return api_base
|
||||
|
||||
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("SAMBANOVA_API_KEY")
|
||||
|
||||
default_headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"accept": "application/json",
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
|
||||
# If 'Authorization' is provided in headers, it overrides the default.
|
||||
if "Authorization" in headers:
|
||||
default_headers["Authorization"] = headers["Authorization"]
|
||||
|
||||
# Merge other headers, overriding any default ones except Authorization
|
||||
return {**default_headers, **headers}
|
||||
|
||||
def get_supported_openai_params(self, model: str):
|
||||
"""
|
||||
Non additional params supported, placeholder method for future supported params
|
||||
https://docs.sambanova.ai/cloud/api-reference/endpoints/embeddings-api
|
||||
"""
|
||||
return []
|
||||
|
||||
def map_openai_params(
|
||||
self,
|
||||
non_default_params: dict,
|
||||
optional_params: dict,
|
||||
model: str,
|
||||
drop_params: bool,
|
||||
):
|
||||
"""
|
||||
No transformation is applied - SambaNova is openai compatible
|
||||
"""
|
||||
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 SambaNovaError(
|
||||
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 SambaNovaError(
|
||||
message=error_message, status_code=status_code, headers=headers
|
||||
)
|
||||
Reference in New Issue
Block a user