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
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
|
import asyncio
import contextvars
from functools import partial
from typing import Any, Dict, Iterable, List, Literal, Optional, Union
import httpx
import litellm
from litellm.constants import request_timeout
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.llms.base_llm.responses.transformation import BaseResponsesAPIConfig
from litellm.llms.custom_httpx.llm_http_handler import BaseLLMHTTPHandler
from litellm.responses.utils import ResponsesAPIRequestUtils
from litellm.types.llms.openai import (
Reasoning,
ResponseIncludable,
ResponseInputParam,
ResponsesAPIOptionalRequestParams,
ResponsesAPIResponse,
ResponseTextConfigParam,
ToolChoice,
ToolParam,
)
from litellm.types.router import GenericLiteLLMParams
from litellm.utils import ProviderConfigManager, client
from .streaming_iterator import BaseResponsesAPIStreamingIterator
####### ENVIRONMENT VARIABLES ###################
# Initialize any necessary instances or variables here
base_llm_http_handler = BaseLLMHTTPHandler()
#################################################
@client
async def aresponses(
input: Union[str, ResponseInputParam],
model: str,
include: Optional[List[ResponseIncludable]] = None,
instructions: Optional[str] = None,
max_output_tokens: Optional[int] = None,
metadata: Optional[Dict[str, Any]] = None,
parallel_tool_calls: Optional[bool] = None,
previous_response_id: Optional[str] = None,
reasoning: Optional[Reasoning] = None,
store: Optional[bool] = None,
stream: Optional[bool] = None,
temperature: Optional[float] = None,
text: Optional[ResponseTextConfigParam] = None,
tool_choice: Optional[ToolChoice] = None,
tools: Optional[Iterable[ToolParam]] = None,
top_p: Optional[float] = None,
truncation: Optional[Literal["auto", "disabled"]] = None,
user: Optional[str] = None,
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
# The extra values given here take precedence over values defined on the client or passed to this method.
extra_headers: Optional[Dict[str, Any]] = None,
extra_query: Optional[Dict[str, Any]] = None,
extra_body: Optional[Dict[str, Any]] = None,
timeout: Optional[Union[float, httpx.Timeout]] = None,
# LiteLLM specific params,
custom_llm_provider: Optional[str] = None,
**kwargs,
) -> Union[ResponsesAPIResponse, BaseResponsesAPIStreamingIterator]:
"""
Async: Handles responses API requests by reusing the synchronous function
"""
local_vars = locals()
try:
loop = asyncio.get_event_loop()
kwargs["aresponses"] = True
# get custom llm provider so we can use this for mapping exceptions
if custom_llm_provider is None:
_, custom_llm_provider, _, _ = litellm.get_llm_provider(
model=model, api_base=local_vars.get("base_url", None)
)
func = partial(
responses,
input=input,
model=model,
include=include,
instructions=instructions,
max_output_tokens=max_output_tokens,
metadata=metadata,
parallel_tool_calls=parallel_tool_calls,
previous_response_id=previous_response_id,
reasoning=reasoning,
store=store,
stream=stream,
temperature=temperature,
text=text,
tool_choice=tool_choice,
tools=tools,
top_p=top_p,
truncation=truncation,
user=user,
extra_headers=extra_headers,
extra_query=extra_query,
extra_body=extra_body,
timeout=timeout,
custom_llm_provider=custom_llm_provider,
**kwargs,
)
ctx = contextvars.copy_context()
func_with_context = partial(ctx.run, func)
init_response = await loop.run_in_executor(None, func_with_context)
if asyncio.iscoroutine(init_response):
response = await init_response
else:
response = init_response
return response
except Exception as e:
raise litellm.exception_type(
model=model,
custom_llm_provider=custom_llm_provider,
original_exception=e,
completion_kwargs=local_vars,
extra_kwargs=kwargs,
)
@client
def responses(
input: Union[str, ResponseInputParam],
model: str,
include: Optional[List[ResponseIncludable]] = None,
instructions: Optional[str] = None,
max_output_tokens: Optional[int] = None,
metadata: Optional[Dict[str, Any]] = None,
parallel_tool_calls: Optional[bool] = None,
previous_response_id: Optional[str] = None,
reasoning: Optional[Reasoning] = None,
store: Optional[bool] = None,
stream: Optional[bool] = None,
temperature: Optional[float] = None,
text: Optional[ResponseTextConfigParam] = None,
tool_choice: Optional[ToolChoice] = None,
tools: Optional[Iterable[ToolParam]] = None,
top_p: Optional[float] = None,
truncation: Optional[Literal["auto", "disabled"]] = None,
user: Optional[str] = None,
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
# The extra values given here take precedence over values defined on the client or passed to this method.
extra_headers: Optional[Dict[str, Any]] = None,
extra_query: Optional[Dict[str, Any]] = None,
extra_body: Optional[Dict[str, Any]] = None,
timeout: Optional[Union[float, httpx.Timeout]] = None,
# LiteLLM specific params,
custom_llm_provider: Optional[str] = None,
**kwargs,
):
"""
Synchronous version of the Responses API.
Uses the synchronous HTTP handler to make requests.
"""
local_vars = locals()
try:
litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj") # type: ignore
litellm_call_id: Optional[str] = kwargs.get("litellm_call_id", None)
_is_async = kwargs.pop("aresponses", False) is True
# get llm provider logic
litellm_params = GenericLiteLLMParams(**kwargs)
model, custom_llm_provider, dynamic_api_key, dynamic_api_base = (
litellm.get_llm_provider(
model=model,
custom_llm_provider=custom_llm_provider,
api_base=litellm_params.api_base,
api_key=litellm_params.api_key,
)
)
# get provider config
responses_api_provider_config: Optional[BaseResponsesAPIConfig] = (
ProviderConfigManager.get_provider_responses_api_config(
model=model,
provider=litellm.LlmProviders(custom_llm_provider),
)
)
if responses_api_provider_config is None:
raise litellm.BadRequestError(
model=model,
llm_provider=custom_llm_provider,
message=f"Responses API not available for custom_llm_provider={custom_llm_provider}, model: {model}",
)
local_vars.update(kwargs)
# Get ResponsesAPIOptionalRequestParams with only valid parameters
response_api_optional_params: ResponsesAPIOptionalRequestParams = (
ResponsesAPIRequestUtils.get_requested_response_api_optional_param(
local_vars
)
)
# Get optional parameters for the responses API
responses_api_request_params: Dict = (
ResponsesAPIRequestUtils.get_optional_params_responses_api(
model=model,
responses_api_provider_config=responses_api_provider_config,
response_api_optional_params=response_api_optional_params,
)
)
# Pre Call logging
litellm_logging_obj.update_environment_variables(
model=model,
user=user,
optional_params=dict(responses_api_request_params),
litellm_params={
"litellm_call_id": litellm_call_id,
**responses_api_request_params,
},
custom_llm_provider=custom_llm_provider,
)
# Call the handler with _is_async flag instead of directly calling the async handler
response = base_llm_http_handler.response_api_handler(
model=model,
input=input,
responses_api_provider_config=responses_api_provider_config,
response_api_optional_request_params=responses_api_request_params,
custom_llm_provider=custom_llm_provider,
litellm_params=litellm_params,
logging_obj=litellm_logging_obj,
extra_headers=extra_headers,
extra_body=extra_body,
timeout=timeout or request_timeout,
_is_async=_is_async,
client=kwargs.get("client"),
fake_stream=responses_api_provider_config.should_fake_stream(
model=model, stream=stream, custom_llm_provider=custom_llm_provider
),
)
return response
except Exception as e:
raise litellm.exception_type(
model=model,
custom_llm_provider=custom_llm_provider,
original_exception=e,
completion_kwargs=local_vars,
extra_kwargs=kwargs,
)
|
