-
Notifications
You must be signed in to change notification settings - Fork 4.7k
Expand file tree
/
Copy pathcompletion_create_params.py
More file actions
461 lines (357 loc) · 18 KB
/
completion_create_params.py
File metadata and controls
461 lines (357 loc) · 18 KB
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
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
from __future__ import annotations
from typing import Dict, List, Union, Iterable, Optional
from typing_extensions import Literal, Required, TypeAlias, TypedDict
from ..._types import SequenceNotStr
from ..shared.chat_model import ChatModel
from ..shared_params.metadata import Metadata
from ..shared.reasoning_effort import ReasoningEffort
from .chat_completion_audio_param import ChatCompletionAudioParam
from .chat_completion_message_param import ChatCompletionMessageParam
from .chat_completion_tool_union_param import ChatCompletionToolUnionParam
from ..shared_params.function_parameters import FunctionParameters
from ..shared_params.response_format_text import ResponseFormatText
from .chat_completion_stream_options_param import ChatCompletionStreamOptionsParam
from .chat_completion_prediction_content_param import ChatCompletionPredictionContentParam
from .chat_completion_tool_choice_option_param import ChatCompletionToolChoiceOptionParam
from ..shared_params.response_format_json_object import ResponseFormatJSONObject
from ..shared_params.response_format_json_schema import ResponseFormatJSONSchema
from .chat_completion_function_call_option_param import ChatCompletionFunctionCallOptionParam
__all__ = [
"CompletionCreateParamsBase",
"FunctionCall",
"Function",
"ResponseFormat",
"WebSearchOptions",
"WebSearchOptionsUserLocation",
"WebSearchOptionsUserLocationApproximate",
"CompletionCreateParamsNonStreaming",
"CompletionCreateParamsStreaming",
]
class CompletionCreateParamsBase(TypedDict, total=False):
messages: Required[Iterable[ChatCompletionMessageParam]]
"""A list of messages comprising the conversation so far.
Depending on the [model](https://platform.openai.com/docs/models) you use,
different message types (modalities) are supported, like
[text](https://platform.openai.com/docs/guides/text-generation),
[images](https://platform.openai.com/docs/guides/vision), and
[audio](https://platform.openai.com/docs/guides/audio).
"""
model: Required[Union[str, ChatModel]]
"""Model ID used to generate the response, like `gpt-4o` or `o3`.
OpenAI offers a wide range of models with different capabilities, performance
characteristics, and price points. Refer to the
[model guide](https://platform.openai.com/docs/models) to browse and compare
available models.
"""
audio: Optional[ChatCompletionAudioParam]
"""Parameters for audio output.
Required when audio output is requested with `modalities: ["audio"]`.
[Learn more](https://platform.openai.com/docs/guides/audio).
"""
frequency_penalty: Optional[float]
"""Number between -2.0 and 2.0.
Positive values penalize new tokens based on their existing frequency in the
text so far, decreasing the model's likelihood to repeat the same line verbatim.
"""
function_call: FunctionCall
"""Deprecated in favor of `tool_choice`.
Controls which (if any) function is called by the model.
`none` means the model will not call a function and instead generates a message.
`auto` means the model can pick between generating a message or calling a
function.
Specifying a particular function via `{"name": "my_function"}` forces the model
to call that function.
`none` is the default when no functions are present. `auto` is the default if
functions are present.
"""
functions: Iterable[Function]
"""Deprecated in favor of `tools`.
A list of functions the model may generate JSON inputs for.
"""
logit_bias: Optional[Dict[str, int]]
"""Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the
tokenizer) to an associated bias value from -100 to 100. Mathematically, the
bias is added to the logits generated by the model prior to sampling. The exact
effect will vary per model, but values between -1 and 1 should decrease or
increase likelihood of selection; values like -100 or 100 should result in a ban
or exclusive selection of the relevant token.
"""
logprobs: Optional[bool]
"""Whether to return log probabilities of the output tokens or not.
If true, returns the log probabilities of each output token returned in the
`content` of `message`.
"""
max_completion_tokens: Optional[int]
"""
An upper bound for the number of tokens that can be generated for a completion,
including visible output tokens and
[reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
"""
max_tokens: Optional[int]
"""
The maximum number of [tokens](/tokenizer) that can be generated in the chat
completion. This value can be used to control
[costs](https://openai.com/api/pricing/) for text generated via API.
This value is now deprecated in favor of `max_completion_tokens`, and is not
compatible with
[o-series models](https://platform.openai.com/docs/guides/reasoning).
"""
metadata: Optional[Metadata]
"""Set of 16 key-value pairs that can be attached to an object.
This can be useful for storing additional information about the object in a
structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with
a maximum length of 512 characters.
"""
modalities: Optional[List[Literal["text", "audio"]]]
"""
Output types that you would like the model to generate. Most models are capable
of generating text, which is the default:
`["text"]`
The `gpt-4o-audio-preview` model can also be used to
[generate audio](https://platform.openai.com/docs/guides/audio). To request that
this model generate both text and audio responses, you can use:
`["text", "audio"]`
"""
n: Optional[int]
"""How many chat completion choices to generate for each input message.
Note that you will be charged based on the number of generated tokens across all
of the choices. Keep `n` as `1` to minimize costs.
"""
parallel_tool_calls: bool
"""
Whether to enable
[parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
during tool use.
"""
prediction: Optional[ChatCompletionPredictionContentParam]
"""
Static predicted output content, such as the content of a text file that is
being regenerated.
"""
presence_penalty: Optional[float]
"""Number between -2.0 and 2.0.
Positive values penalize new tokens based on whether they appear in the text so
far, increasing the model's likelihood to talk about new topics.
"""
prompt_cache_key: str
"""
Used by OpenAI to cache responses for similar requests to optimize your cache
hit rates. Replaces the `user` field.
[Learn more](https://platform.openai.com/docs/guides/prompt-caching).
"""
prompt_cache_retention: Optional[Literal["in-memory", "24h"]]
"""The retention policy for the prompt cache.
Set to `24h` to enable extended prompt caching, which keeps cached prefixes
active for longer, up to a maximum of 24 hours.
[Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
"""
reasoning_effort: Optional[ReasoningEffort]
"""
Constrains effort on reasoning for
[reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
Reducing reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
- `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
calls are supported for all reasoning values in gpt-5.1.
- All models before `gpt-5.1` default to `medium` reasoning effort, and do not
support `none`.
- The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
- `xhigh` is supported for all models after `gpt-5.1-codex-max`.
"""
response_format: ResponseFormat
"""An object specifying the format that the model must output.
Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
Outputs which ensures the model will match your supplied JSON schema. Learn more
in the
[Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
Setting to `{ "type": "json_object" }` enables the older JSON mode, which
ensures the message the model generates is valid JSON. Using `json_schema` is
preferred for models that support it.
"""
safety_identifier: str
"""
A stable identifier used to help detect users of your application that may be
violating OpenAI's usage policies. The IDs should be a string that uniquely
identifies each user, with a maximum length of 64 characters. We recommend
hashing their username or email address, in order to avoid sending us any
identifying information.
[Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
"""
seed: Optional[int]
"""
This feature is in Beta. If specified, our system will make a best effort to
sample deterministically, such that repeated requests with the same `seed` and
parameters should return the same result. Determinism is not guaranteed, and you
should refer to the `system_fingerprint` response parameter to monitor changes
in the backend.
"""
service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]]
"""Specifies the processing type used for serving the request.
- If set to 'auto', then the request will be processed with the service tier
configured in the Project settings. Unless otherwise configured, the Project
will use 'default'.
- If set to 'default', then the request will be processed with the standard
pricing and performance for the selected model.
- If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
'[priority](https://openai.com/api-priority-processing/)', then the request
will be processed with the corresponding service tier.
- When not set, the default behavior is 'auto'.
When the `service_tier` parameter is set, the response body will include the
`service_tier` value based on the processing mode actually used to serve the
request. This response value may be different from the value set in the
parameter.
"""
stop: Union[Optional[str], SequenceNotStr[str], None]
"""Not supported with latest reasoning models `o3` and `o4-mini`.
Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
"""
store: Optional[bool]
"""
Whether or not to store the output of this chat completion request for use in
our [model distillation](https://platform.openai.com/docs/guides/distillation)
or [evals](https://platform.openai.com/docs/guides/evals) products.
Supports text and image inputs. Note: image inputs over 8MB will be dropped.
"""
stream_options: Optional[ChatCompletionStreamOptionsParam]
"""Options for streaming response. Only set this when you set `stream: true`."""
temperature: Optional[float]
"""What sampling temperature to use, between 0 and 2.
Higher values like 0.8 will make the output more random, while lower values like
0.2 will make it more focused and deterministic. We generally recommend altering
this or `top_p` but not both.
"""
tool_choice: ChatCompletionToolChoiceOptionParam
"""
Controls which (if any) tool is called by the model. `none` means the model will
not call any tool and instead generates a message. `auto` means the model can
pick between generating a message or calling one or more tools. `required` means
the model must call one or more tools. Specifying a particular tool via
`{"type": "function", "function": {"name": "my_function"}}` forces the model to
call that tool.
`none` is the default when no tools are present. `auto` is the default if tools
are present.
"""
tools: Iterable[ChatCompletionToolUnionParam]
"""A list of tools the model may call.
You can provide either
[custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools)
or [function tools](https://platform.openai.com/docs/guides/function-calling).
"""
top_logprobs: Optional[int]
"""
An integer between 0 and 20 specifying the number of most likely tokens to
return at each token position, each with an associated log probability.
`logprobs` must be set to `true` if this parameter is used.
"""
top_p: Optional[float]
"""
An alternative to sampling with temperature, called nucleus sampling, where the
model considers the results of the tokens with top_p probability mass. So 0.1
means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or `temperature` but not both.
"""
user: str
"""This field is being replaced by `safety_identifier` and `prompt_cache_key`.
Use `prompt_cache_key` instead to maintain caching optimizations. A stable
identifier for your end-users. Used to boost cache hit rates by better bucketing
similar requests and to help OpenAI detect and prevent abuse.
[Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
"""
verbosity: Optional[Literal["low", "medium", "high"]]
"""Constrains the verbosity of the model's response.
Lower values will result in more concise responses, while higher values will
result in more verbose responses. Currently supported values are `low`,
`medium`, and `high`.
"""
web_search_options: WebSearchOptions
"""
This tool searches the web for relevant results to use in a response. Learn more
about the
[web search tool](https://platform.openai.com/docs/guides/tools-web-search?api-mode=chat).
"""
FunctionCall: TypeAlias = Union[Literal["none", "auto"], ChatCompletionFunctionCallOptionParam]
class Function(TypedDict, total=False):
name: Required[str]
"""The name of the function to be called.
Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length
of 64.
"""
description: str
"""
A description of what the function does, used by the model to choose when and
how to call the function.
"""
parameters: FunctionParameters
"""The parameters the functions accepts, described as a JSON Schema object.
See the [guide](https://platform.openai.com/docs/guides/function-calling) for
examples, and the
[JSON Schema reference](https://json-schema.org/understanding-json-schema/) for
documentation about the format.
Omitting `parameters` defines a function with an empty parameter list.
"""
ResponseFormat: TypeAlias = Union[ResponseFormatText, ResponseFormatJSONSchema, ResponseFormatJSONObject]
class WebSearchOptionsUserLocationApproximate(TypedDict, total=False):
"""Approximate location parameters for the search."""
city: str
"""Free text input for the city of the user, e.g. `San Francisco`."""
country: str
"""
The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of
the user, e.g. `US`.
"""
region: str
"""Free text input for the region of the user, e.g. `California`."""
timezone: str
"""
The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the
user, e.g. `America/Los_Angeles`.
"""
class WebSearchOptionsUserLocation(TypedDict, total=False):
"""Approximate location parameters for the search."""
approximate: Required[WebSearchOptionsUserLocationApproximate]
"""Approximate location parameters for the search."""
type: Required[Literal["approximate"]]
"""The type of location approximation. Always `approximate`."""
class WebSearchOptions(TypedDict, total=False):
"""
This tool searches the web for relevant results to use in a response.
Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search?api-mode=chat).
"""
search_context_size: Literal["low", "medium", "high"]
"""
High level guidance for the amount of context window space to use for the
search. One of `low`, `medium`, or `high`. `medium` is the default.
"""
user_location: Optional[WebSearchOptionsUserLocation]
"""Approximate location parameters for the search."""
class CompletionCreateParamsNonStreaming(CompletionCreateParamsBase, total=False):
stream: Optional[Literal[False]]
"""
If set to true, the model response data will be streamed to the client as it is
generated using
[server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
See the
[Streaming section below](https://platform.openai.com/docs/api-reference/chat/streaming)
for more information, along with the
[streaming responses](https://platform.openai.com/docs/guides/streaming-responses)
guide for more information on how to handle the streaming events.
"""
class CompletionCreateParamsStreaming(CompletionCreateParamsBase):
stream: Required[Literal[True]]
"""
If set to true, the model response data will be streamed to the client as it is
generated using
[server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
See the
[Streaming section below](https://platform.openai.com/docs/api-reference/chat/streaming)
for more information, along with the
[streaming responses](https://platform.openai.com/docs/guides/streaming-responses)
guide for more information on how to handle the streaming events.
"""
CompletionCreateParams = Union[CompletionCreateParamsNonStreaming, CompletionCreateParamsStreaming]