Spaces:
Sleeping
Sleeping
File size: 6,539 Bytes
469eae6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 |
import json
from abc import abstractmethod
from typing import List, Optional, Union, cast
import litellm
from litellm.types.utils import (
Choices,
Delta,
GenericStreamingChunk,
ModelResponse,
ModelResponseStream,
StreamingChoices,
)
class BaseModelResponseIterator:
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]:
return GenericStreamingChunk(
text="",
is_finished=False,
finish_reason="",
usage=None,
index=0,
tool_use=None,
)
# 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
stripped_chunk = litellm.CustomStreamWrapper._strip_sse_data_from_chunk(
str_line
)
try:
if stripped_chunk is not None:
stripped_json_chunk: Optional[dict] = json.loads(stripped_chunk)
else:
stripped_json_chunk = None
except json.JSONDecodeError:
stripped_json_chunk = None
if "[DONE]" in str_line:
return GenericStreamingChunk(
text="",
is_finished=True,
finish_reason="stop",
usage=None,
index=0,
tool_use=None,
)
elif stripped_json_chunk:
return self.chunk_parser(chunk=stripped_json_chunk)
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
chunk = self._handle_string_chunk(str_line=str_line)
return chunk
except StopAsyncIteration:
raise StopAsyncIteration
except ValueError as e:
raise RuntimeError(f"Error parsing chunk: {e},\nReceived chunk: {chunk}")
class MockResponseIterator: # for returning ai21 streaming responses
def __init__(
self, model_response: ModelResponse, json_mode: Optional[bool] = False
):
self.model_response = model_response
self.json_mode = json_mode
self.is_done = False
# Sync iterator
def __iter__(self):
return self
def _chunk_parser(self, chunk_data: ModelResponse) -> ModelResponseStream:
try:
streaming_choices: List[StreamingChoices] = []
for choice in chunk_data.choices:
streaming_choices.append(
StreamingChoices(
index=choice.index,
delta=Delta(
**cast(Choices, choice).message.model_dump(),
),
finish_reason=choice.finish_reason,
)
)
processed_chunk = ModelResponseStream(
id=chunk_data.id,
object="chat.completion",
created=chunk_data.created,
model=chunk_data.model,
choices=streaming_choices,
)
return processed_chunk
except Exception as e:
raise ValueError(f"Failed to decode chunk: {chunk_data}. Error: {e}")
def __next__(self):
if self.is_done:
raise StopIteration
self.is_done = True
return self._chunk_parser(self.model_response)
# Async iterator
def __aiter__(self):
return self
async def __anext__(self):
if self.is_done:
raise StopAsyncIteration
self.is_done = True
return self._chunk_parser(self.model_response)
class FakeStreamResponseIterator:
def __init__(self, model_response, json_mode: Optional[bool] = False):
self.model_response = model_response
self.json_mode = json_mode
self.is_done = False
# Sync iterator
def __iter__(self):
return self
@abstractmethod
def chunk_parser(self, chunk: dict) -> GenericStreamingChunk:
pass
def __next__(self):
if self.is_done:
raise StopIteration
self.is_done = True
return self.chunk_parser(self.model_response)
# Async iterator
def __aiter__(self):
return self
async def __anext__(self):
if self.is_done:
raise StopAsyncIteration
self.is_done = True
return self.chunk_parser(self.model_response)
|