mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 02:34:29 +00:00
169 lines
No EOL
5.7 KiB
Python
169 lines
No EOL
5.7 KiB
Python
import json
|
|
from typing import List, Optional, Union
|
|
|
|
from litellm.llms.base_llm.chat.transformation import BaseLLMException
|
|
from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator
|
|
from litellm.types.llms.openai import AllMessageValues
|
|
from litellm.types.utils import (
|
|
ChatCompletionToolCallChunk,
|
|
ChatCompletionUsageBlock,
|
|
GenericStreamingChunk,
|
|
ModelResponseStream
|
|
)
|
|
|
|
|
|
class AioHttpOpenAIError(BaseLLMException):
|
|
def __init__(self, status_code, message):
|
|
super().__init__(status_code=status_code, message=message)
|
|
|
|
|
|
def validate_environment(
|
|
headers: dict,
|
|
model: str,
|
|
messages: List[AllMessageValues],
|
|
optional_params: dict,
|
|
api_key: Optional[str] = None,
|
|
) -> dict:
|
|
"""
|
|
Return headers to use for aiopenhttp_openai chat completion request
|
|
"""
|
|
headers.update(
|
|
{
|
|
"Request-Source": "unspecified:litellm",
|
|
"accept": "application/json",
|
|
"content-type": "application/json",
|
|
}
|
|
)
|
|
if api_key:
|
|
headers["Authorization"] = f"bearer {api_key}"
|
|
return headers
|
|
|
|
class ModelResponseIterator:
|
|
def __init__(
|
|
self, streaming_response, sync_stream: bool, json_mode: Optional[bool] = False
|
|
):
|
|
self.streaming_response = streaming_response
|
|
self.response_iterator = self.streaming_response
|
|
self.json_mode = json_mode
|
|
|
|
def chunk_parser(self, chunk: dict) -> Union[GenericStreamingChunk, ModelResponseStream]:
|
|
try:
|
|
# Initialize default values
|
|
text = ""
|
|
tool_use: Optional[ChatCompletionToolCallChunk] = None
|
|
is_finished = False
|
|
finish_reason = ""
|
|
usage: Optional[ChatCompletionUsageBlock] = None
|
|
provider_specific_fields = None
|
|
|
|
# Extract the index from the chunk
|
|
index = int(chunk.get("choices", [{}])[0].get("index", 0))
|
|
|
|
# Extract the text or delta content from the first choice
|
|
delta = chunk.get("choices", [{}])[0].get("delta", {})
|
|
if "content" in delta:
|
|
text = delta["content"]
|
|
|
|
# Check for finish_reason
|
|
finish_reason = chunk.get("choices", [{}])[0].get("finish_reason", "")
|
|
|
|
# Determine if the stream has finished
|
|
is_finished = finish_reason in ("length", "stop")
|
|
|
|
# Create and return the parsed chunk
|
|
returned_chunk = GenericStreamingChunk(
|
|
text=text,
|
|
tool_use=tool_use,
|
|
is_finished=is_finished,
|
|
finish_reason=finish_reason,
|
|
usage=usage,
|
|
index=index,
|
|
provider_specific_fields=provider_specific_fields,
|
|
)
|
|
|
|
return returned_chunk
|
|
|
|
except json.JSONDecodeError:
|
|
raise ValueError(f"Failed to decode JSON from chunk: {chunk}")
|
|
|
|
|
|
# Sync iterator
|
|
def __iter__(self):
|
|
return self
|
|
|
|
def _handle_string_chunk(
|
|
self, str_line: str
|
|
) -> Union[GenericStreamingChunk, ModelResponseStream]:
|
|
# chunk is a str at this point
|
|
if "[DONE]" in str_line:
|
|
return GenericStreamingChunk(
|
|
text="",
|
|
is_finished=True,
|
|
finish_reason="stop",
|
|
usage=None,
|
|
index=0,
|
|
tool_use=None,
|
|
)
|
|
elif str_line.startswith("data:"):
|
|
data_json = json.loads(str_line[5:])
|
|
return self.chunk_parser(chunk=data_json)
|
|
else:
|
|
return GenericStreamingChunk(
|
|
text="",
|
|
is_finished=False,
|
|
finish_reason="",
|
|
usage=None,
|
|
index=0,
|
|
tool_use=None,
|
|
)
|
|
|
|
def __next__(self):
|
|
try:
|
|
chunk = self.response_iterator.__next__()
|
|
except StopIteration:
|
|
raise StopIteration
|
|
except ValueError as e:
|
|
raise RuntimeError(f"Error receiving chunk from stream: {e}")
|
|
|
|
try:
|
|
str_line = chunk
|
|
if isinstance(chunk, bytes): # Handle binary data
|
|
str_line = chunk.decode("utf-8") # Convert bytes to string
|
|
index = str_line.find("data:")
|
|
if index != -1:
|
|
str_line = str_line[index:]
|
|
# chunk is a str at this point
|
|
return self._handle_string_chunk(str_line=str_line)
|
|
except StopIteration:
|
|
raise StopIteration
|
|
except ValueError as e:
|
|
raise RuntimeError(f"Error parsing chunk: {e},\nReceived chunk: {chunk}")
|
|
|
|
# Async iterator
|
|
def __aiter__(self):
|
|
self.async_response_iterator = self.streaming_response.__aiter__()
|
|
return self
|
|
|
|
async def __anext__(self):
|
|
try:
|
|
chunk = await self.async_response_iterator.__anext__()
|
|
except StopAsyncIteration:
|
|
raise StopAsyncIteration
|
|
except ValueError as e:
|
|
raise RuntimeError(f"Error receiving chunk from stream: {e}")
|
|
|
|
try:
|
|
str_line = chunk
|
|
if isinstance(chunk, bytes): # Handle binary data
|
|
str_line = chunk.decode("utf-8") # Convert bytes to string
|
|
index = str_line.find("data:")
|
|
if index != -1:
|
|
str_line = str_line[index:]
|
|
|
|
# chunk is a str at this point
|
|
return self._handle_string_chunk(str_line=str_line)
|
|
except StopAsyncIteration:
|
|
raise StopAsyncIteration
|
|
except ValueError as e:
|
|
raise RuntimeError(f"Error parsing chunk: {e},\nReceived chunk: {chunk}")
|
|
|