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
|
"""
Azure Batches API Handler
"""
from typing import Any, Coroutine, Optional, Union, cast
import httpx
from litellm.llms.azure.azure import AsyncAzureOpenAI, AzureOpenAI
from litellm.types.llms.openai import (
Batch,
CancelBatchRequest,
CreateBatchRequest,
RetrieveBatchRequest,
)
from litellm.types.utils import LiteLLMBatch
from ..common_utils import BaseAzureLLM
class AzureBatchesAPI(BaseAzureLLM):
"""
Azure methods to support for batches
- create_batch()
- retrieve_batch()
- cancel_batch()
- list_batch()
"""
def __init__(self) -> None:
super().__init__()
async def acreate_batch(
self,
create_batch_data: CreateBatchRequest,
azure_client: AsyncAzureOpenAI,
) -> LiteLLMBatch:
response = await azure_client.batches.create(**create_batch_data)
return LiteLLMBatch(**response.model_dump())
def create_batch(
self,
_is_async: bool,
create_batch_data: CreateBatchRequest,
api_key: Optional[str],
api_base: Optional[str],
api_version: Optional[str],
timeout: Union[float, httpx.Timeout],
max_retries: Optional[int],
client: Optional[Union[AzureOpenAI, AsyncAzureOpenAI]] = None,
litellm_params: Optional[dict] = None,
) -> Union[LiteLLMBatch, Coroutine[Any, Any, LiteLLMBatch]]:
azure_client: Optional[Union[AzureOpenAI, AsyncAzureOpenAI]] = (
self.get_azure_openai_client(
api_key=api_key,
api_base=api_base,
api_version=api_version,
client=client,
_is_async=_is_async,
litellm_params=litellm_params or {},
)
)
if azure_client is None:
raise ValueError(
"OpenAI client is not initialized. Make sure api_key is passed or OPENAI_API_KEY is set in the environment."
)
if _is_async is True:
if not isinstance(azure_client, AsyncAzureOpenAI):
raise ValueError(
"OpenAI client is not an instance of AsyncOpenAI. Make sure you passed an AsyncOpenAI client."
)
return self.acreate_batch( # type: ignore
create_batch_data=create_batch_data, azure_client=azure_client
)
response = cast(AzureOpenAI, azure_client).batches.create(**create_batch_data)
return LiteLLMBatch(**response.model_dump())
async def aretrieve_batch(
self,
retrieve_batch_data: RetrieveBatchRequest,
client: AsyncAzureOpenAI,
) -> LiteLLMBatch:
response = await client.batches.retrieve(**retrieve_batch_data)
return LiteLLMBatch(**response.model_dump())
def retrieve_batch(
self,
_is_async: bool,
retrieve_batch_data: RetrieveBatchRequest,
api_key: Optional[str],
api_base: Optional[str],
api_version: Optional[str],
timeout: Union[float, httpx.Timeout],
max_retries: Optional[int],
client: Optional[AzureOpenAI] = None,
litellm_params: Optional[dict] = None,
):
azure_client: Optional[Union[AzureOpenAI, AsyncAzureOpenAI]] = (
self.get_azure_openai_client(
api_key=api_key,
api_base=api_base,
api_version=api_version,
client=client,
_is_async=_is_async,
litellm_params=litellm_params or {},
)
)
if azure_client is None:
raise ValueError(
"OpenAI client is not initialized. Make sure api_key is passed or OPENAI_API_KEY is set in the environment."
)
if _is_async is True:
if not isinstance(azure_client, AsyncAzureOpenAI):
raise ValueError(
"OpenAI client is not an instance of AsyncOpenAI. Make sure you passed an AsyncOpenAI client."
)
return self.aretrieve_batch( # type: ignore
retrieve_batch_data=retrieve_batch_data, client=azure_client
)
response = cast(AzureOpenAI, azure_client).batches.retrieve(
**retrieve_batch_data
)
return LiteLLMBatch(**response.model_dump())
async def acancel_batch(
self,
cancel_batch_data: CancelBatchRequest,
client: AsyncAzureOpenAI,
) -> Batch:
response = await client.batches.cancel(**cancel_batch_data)
return response
def cancel_batch(
self,
_is_async: bool,
cancel_batch_data: CancelBatchRequest,
api_key: Optional[str],
api_base: Optional[str],
api_version: Optional[str],
timeout: Union[float, httpx.Timeout],
max_retries: Optional[int],
client: Optional[AzureOpenAI] = None,
litellm_params: Optional[dict] = None,
):
azure_client: Optional[Union[AzureOpenAI, AsyncAzureOpenAI]] = (
self.get_azure_openai_client(
api_key=api_key,
api_base=api_base,
api_version=api_version,
client=client,
_is_async=_is_async,
litellm_params=litellm_params or {},
)
)
if azure_client is None:
raise ValueError(
"OpenAI client is not initialized. Make sure api_key is passed or OPENAI_API_KEY is set in the environment."
)
response = azure_client.batches.cancel(**cancel_batch_data)
return response
async def alist_batches(
self,
client: AsyncAzureOpenAI,
after: Optional[str] = None,
limit: Optional[int] = None,
):
response = await client.batches.list(after=after, limit=limit) # type: ignore
return response
def list_batches(
self,
_is_async: bool,
api_key: Optional[str],
api_base: Optional[str],
api_version: Optional[str],
timeout: Union[float, httpx.Timeout],
max_retries: Optional[int],
after: Optional[str] = None,
limit: Optional[int] = None,
client: Optional[AzureOpenAI] = None,
litellm_params: Optional[dict] = None,
):
azure_client: Optional[Union[AzureOpenAI, AsyncAzureOpenAI]] = (
self.get_azure_openai_client(
api_key=api_key,
api_base=api_base,
api_version=api_version,
client=client,
_is_async=_is_async,
litellm_params=litellm_params or {},
)
)
if azure_client is None:
raise ValueError(
"OpenAI client is not initialized. Make sure api_key is passed or OPENAI_API_KEY is set in the environment."
)
if _is_async is True:
if not isinstance(azure_client, AsyncAzureOpenAI):
raise ValueError(
"OpenAI client is not an instance of AsyncOpenAI. Make sure you passed an AsyncOpenAI client."
)
return self.alist_batches( # type: ignore
client=azure_client, after=after, limit=limit
)
response = azure_client.batches.list(after=after, limit=limit) # type: ignore
return response
|
