-
Notifications
You must be signed in to change notification settings - Fork 4.8k
Expand file tree
/
Copy pathassistant_create_params.py
More file actions
232 lines (172 loc) · 8.78 KB
/
assistant_create_params.py
File metadata and controls
232 lines (172 loc) · 8.78 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
# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
from __future__ import annotations
from typing import Union, Iterable, Optional
from typing_extensions import Literal, Required, TypeAlias, TypedDict
from ..._types import SequenceNotStr
from ..shared.chat_model import ChatModel
from .assistant_tool_param import AssistantToolParam
from ..shared_params.metadata import Metadata
from ..shared.reasoning_effort import ReasoningEffort
from .assistant_response_format_option_param import AssistantResponseFormatOptionParam
__all__ = [
"AssistantCreateParams",
"ToolResources",
"ToolResourcesCodeInterpreter",
"ToolResourcesFileSearch",
"ToolResourcesFileSearchVectorStore",
"ToolResourcesFileSearchVectorStoreChunkingStrategy",
"ToolResourcesFileSearchVectorStoreChunkingStrategyAuto",
"ToolResourcesFileSearchVectorStoreChunkingStrategyStatic",
"ToolResourcesFileSearchVectorStoreChunkingStrategyStaticStatic",
]
class AssistantCreateParams(TypedDict, total=False):
model: Required[Union[str, ChatModel]]
"""ID of the model to use.
You can use the
[List models](https://platform.openai.com/docs/api-reference/models/list) API to
see all of your available models, or see our
[Model overview](https://platform.openai.com/docs/models) for descriptions of
them.
"""
description: Optional[str]
"""The description of the assistant. The maximum length is 512 characters."""
instructions: Optional[str]
"""The system instructions that the assistant uses.
The maximum length is 256,000 characters.
"""
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.
"""
name: Optional[str]
"""The name of the assistant. The maximum length is 256 characters."""
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: Optional[AssistantResponseFormatOptionParam]
"""Specifies the format that the model must output.
Compatible with [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
[GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
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 JSON mode, which ensures the
message the model generates is valid JSON.
**Important:** when using JSON mode, you **must** also instruct the model to
produce JSON yourself via a system or user message. Without this, the model may
generate an unending stream of whitespace until the generation reaches the token
limit, resulting in a long-running and seemingly "stuck" request. Also note that
the message content may be partially cut off if `finish_reason="length"`, which
indicates the generation exceeded `max_tokens` or the conversation exceeded the
max context length.
"""
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.
"""
tool_resources: Optional[ToolResources]
"""A set of resources that are used by the assistant's tools.
The resources are specific to the type of tool. For example, the
`code_interpreter` tool requires a list of file IDs, while the `file_search`
tool requires a list of vector store IDs.
"""
tools: Iterable[AssistantToolParam]
"""A list of tool enabled on the assistant.
There can be a maximum of 128 tools per assistant. Tools can be of types
`code_interpreter`, `file_search`, or `function`.
"""
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.
"""
class ToolResourcesCodeInterpreter(TypedDict, total=False):
file_ids: SequenceNotStr[str]
"""
A list of [file](https://platform.openai.com/docs/api-reference/files) IDs made
available to the `code_interpreter` tool. There can be a maximum of 20 files
associated with the tool.
"""
class ToolResourcesFileSearchVectorStoreChunkingStrategyAuto(TypedDict, total=False):
"""The default strategy.
This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`.
"""
type: Required[Literal["auto"]]
"""Always `auto`."""
class ToolResourcesFileSearchVectorStoreChunkingStrategyStaticStatic(TypedDict, total=False):
chunk_overlap_tokens: Required[int]
"""The number of tokens that overlap between chunks. The default value is `400`.
Note that the overlap must not exceed half of `max_chunk_size_tokens`.
"""
max_chunk_size_tokens: Required[int]
"""The maximum number of tokens in each chunk.
The default value is `800`. The minimum value is `100` and the maximum value is
`4096`.
"""
class ToolResourcesFileSearchVectorStoreChunkingStrategyStatic(TypedDict, total=False):
static: Required[ToolResourcesFileSearchVectorStoreChunkingStrategyStaticStatic]
type: Required[Literal["static"]]
"""Always `static`."""
ToolResourcesFileSearchVectorStoreChunkingStrategy: TypeAlias = Union[
ToolResourcesFileSearchVectorStoreChunkingStrategyAuto, ToolResourcesFileSearchVectorStoreChunkingStrategyStatic
]
class ToolResourcesFileSearchVectorStore(TypedDict, total=False):
chunking_strategy: ToolResourcesFileSearchVectorStoreChunkingStrategy
"""The chunking strategy used to chunk the file(s).
If not set, will use the `auto` strategy.
"""
file_ids: SequenceNotStr[str]
"""
A list of [file](https://platform.openai.com/docs/api-reference/files) IDs to
add to the vector store. For vector stores created before Nov 2025, there can be
a maximum of 10,000 files in a vector store. For vector stores created starting
in Nov 2025, the limit is 100,000,000 files.
"""
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.
"""
class ToolResourcesFileSearch(TypedDict, total=False):
vector_store_ids: SequenceNotStr[str]
"""
The
[vector store](https://platform.openai.com/docs/api-reference/vector-stores/object)
attached to this assistant. There can be a maximum of 1 vector store attached to
the assistant.
"""
vector_stores: Iterable[ToolResourcesFileSearchVectorStore]
"""
A helper to create a
[vector store](https://platform.openai.com/docs/api-reference/vector-stores/object)
with file_ids and attach it to this assistant. There can be a maximum of 1
vector store attached to the assistant.
"""
class ToolResources(TypedDict, total=False):
"""A set of resources that are used by the assistant's tools.
The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.
"""
code_interpreter: ToolResourcesCodeInterpreter
file_search: ToolResourcesFileSearch