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
|
import json
from typing import Optional
import litellm
from litellm import verbose_logger
from litellm.types.llms.openai import (
ChatCompletionToolCallChunk,
ChatCompletionToolCallFunctionChunk,
ChatCompletionUsageBlock,
)
from litellm.types.utils import GenericStreamingChunk, Usage
class ModelResponseIterator:
def __init__(self, streaming_response, sync_stream: bool):
self.streaming_response = streaming_response
def chunk_parser(self, chunk: dict) -> GenericStreamingChunk:
try:
processed_chunk = litellm.ModelResponseStream(**chunk)
text = ""
tool_use: Optional[ChatCompletionToolCallChunk] = None
is_finished = False
finish_reason = ""
usage: Optional[ChatCompletionUsageBlock] = None
if processed_chunk.choices[0].delta.content is not None: # type: ignore
text = processed_chunk.choices[0].delta.content # type: ignore
if (
processed_chunk.choices[0].delta.tool_calls is not None # type: ignore
and len(processed_chunk.choices[0].delta.tool_calls) > 0 # type: ignore
and processed_chunk.choices[0].delta.tool_calls[0].function is not None # type: ignore
and processed_chunk.choices[0].delta.tool_calls[0].function.arguments # type: ignore
is not None
):
tool_use = ChatCompletionToolCallChunk(
id=processed_chunk.choices[0].delta.tool_calls[0].id, # type: ignore
type="function",
function=ChatCompletionToolCallFunctionChunk(
name=processed_chunk.choices[0]
.delta.tool_calls[0] # type: ignore
.function.name,
arguments=processed_chunk.choices[0]
.delta.tool_calls[0] # type: ignore
.function.arguments,
),
index=processed_chunk.choices[0].delta.tool_calls[0].index,
)
if processed_chunk.choices[0].finish_reason is not None:
is_finished = True
finish_reason = processed_chunk.choices[0].finish_reason
usage_chunk: Optional[Usage] = getattr(processed_chunk, "usage", None)
if usage_chunk is not None:
usage = ChatCompletionUsageBlock(
prompt_tokens=usage_chunk.prompt_tokens,
completion_tokens=usage_chunk.completion_tokens,
total_tokens=usage_chunk.total_tokens,
)
return GenericStreamingChunk(
text=text,
tool_use=tool_use,
is_finished=is_finished,
finish_reason=finish_reason,
usage=usage,
index=0,
)
except json.JSONDecodeError:
raise ValueError(f"Failed to decode JSON from chunk: {chunk}")
# Sync iterator
def __iter__(self):
self.response_iterator = self.streaming_response
return self
def __next__(self):
if not hasattr(self, "response_iterator"):
self.response_iterator = self.streaming_response
try:
chunk = self.response_iterator.__next__()
except StopIteration:
raise StopIteration
except ValueError as e:
raise RuntimeError(f"Error receiving chunk from stream: {e}")
try:
chunk = litellm.CustomStreamWrapper._strip_sse_data_from_chunk(chunk) or ""
chunk = chunk.strip()
if len(chunk) > 0:
json_chunk = json.loads(chunk)
return self.chunk_parser(chunk=json_chunk)
else:
return GenericStreamingChunk(
text="",
is_finished=False,
finish_reason="",
usage=None,
index=0,
tool_use=None,
)
except StopIteration:
raise StopIteration
except ValueError as e:
verbose_logger.debug(
f"Error parsing chunk: {e},\nReceived chunk: {chunk}. Defaulting to empty chunk here."
)
return GenericStreamingChunk(
text="",
is_finished=False,
finish_reason="",
usage=None,
index=0,
tool_use=None,
)
# 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}")
except Exception as e:
raise RuntimeError(f"Error receiving chunk from stream: {e}")
try:
chunk = litellm.CustomStreamWrapper._strip_sse_data_from_chunk(chunk) or ""
chunk = chunk.strip()
if chunk == "[DONE]":
raise StopAsyncIteration
if len(chunk) > 0:
json_chunk = json.loads(chunk)
return self.chunk_parser(chunk=json_chunk)
else:
return GenericStreamingChunk(
text="",
is_finished=False,
finish_reason="",
usage=None,
index=0,
tool_use=None,
)
except StopAsyncIteration:
raise StopAsyncIteration
except ValueError as e:
verbose_logger.debug(
f"Error parsing chunk: {e},\nReceived chunk: {chunk}. Defaulting to empty chunk here."
)
return GenericStreamingChunk(
text="",
is_finished=False,
finish_reason="",
usage=None,
index=0,
tool_use=None,
)
|
