Skip to content

Commit b1463a2

Browse files
fern-api[bot]fern-api[bot]
authored
SDK regeneration (#705)
1 parent 570cd2e commit b1463a2

File tree

7 files changed

+132
-20
lines changed

7 files changed

+132
-20
lines changed

‎poetry.lock‎

Lines changed: 29 additions & 15 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

‎pyproject.toml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ name = "cohere"
33

44
[tool.poetry]
55
name = "cohere"
6-
version = "5.19.0"
6+
version = "5.20.0"
77
description = ""
88
readme = "README.md"
99
authors = []

‎src/cohere/core/client_wrapper.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -22,10 +22,10 @@ def __init__(
2222

2323
def get_headers(self) -> typing.Dict[str, str]:
2424
headers: typing.Dict[str, str] = {
25-
"User-Agent": "cohere/5.19.0",
25+
"User-Agent": "cohere/5.20.0",
2626
"X-Fern-Language": "Python",
2727
"X-Fern-SDK-Name": "cohere",
28-
"X-Fern-SDK-Version": "5.19.0",
28+
"X-Fern-SDK-Version": "5.20.0",
2929
}
3030
if self._client_name is not None:
3131
headers["X-Client-Name"] = self._client_name

‎src/cohere/types/chat_finish_reason.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,5 +3,5 @@
33
import typing
44

55
ChatFinishReason = typing.Union[
6-
typing.Literal["COMPLETE", "STOP_SEQUENCE", "MAX_TOKENS", "TOOL_CALL", "ERROR"], typing.Any
6+
typing.Literal["COMPLETE", "STOP_SEQUENCE", "MAX_TOKENS", "TOOL_CALL", "ERROR", "TIMEOUT"], typing.Any
77
]

‎src/cohere/types/finish_reason.py‎

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,8 @@
33
import typing
44

55
FinishReason = typing.Union[
6-
typing.Literal["COMPLETE", "STOP_SEQUENCE", "ERROR", "ERROR_TOXIC", "ERROR_LIMIT", "USER_CANCEL", "MAX_TOKENS"],
6+
typing.Literal[
7+
"COMPLETE", "STOP_SEQUENCE", "ERROR", "ERROR_TOXIC", "ERROR_LIMIT", "USER_CANCEL", "MAX_TOKENS", "TIMEOUT"
8+
],
79
typing.Any,
810
]

‎src/cohere/v2/client.py‎

Lines changed: 48 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -66,6 +66,7 @@ def chat_stream(
6666
logprobs: typing.Optional[bool] = OMIT,
6767
tool_choice: typing.Optional[V2ChatStreamRequestToolChoice] = OMIT,
6868
thinking: typing.Optional[Thinking] = OMIT,
69+
priority: typing.Optional[int] = OMIT,
6970
request_options: typing.Optional[RequestOptions] = None,
7071
) -> typing.Iterator[V2ChatStreamResponse]:
7172
"""
@@ -158,6 +159,10 @@ def chat_stream(
158159
159160
thinking : typing.Optional[Thinking]
160161
162+
priority : typing.Optional[int]
163+
The priority of the request (lower means earlier handling; default 0 highest priority).
164+
Higher priority requests are handled first, and dropped last when the system is under load.
165+
161166
request_options : typing.Optional[RequestOptions]
162167
Request-specific configuration.
163168
@@ -205,6 +210,7 @@ def chat_stream(
205210
logprobs=logprobs,
206211
tool_choice=tool_choice,
207212
thinking=thinking,
213+
priority=priority,
208214
request_options=request_options,
209215
) as r:
210216
yield from r.data
@@ -231,6 +237,7 @@ def chat(
231237
logprobs: typing.Optional[bool] = OMIT,
232238
tool_choice: typing.Optional[V2ChatRequestToolChoice] = OMIT,
233239
thinking: typing.Optional[Thinking] = OMIT,
240+
priority: typing.Optional[int] = OMIT,
234241
request_options: typing.Optional[RequestOptions] = None,
235242
) -> V2ChatResponse:
236243
"""
@@ -323,6 +330,10 @@ def chat(
323330
324331
thinking : typing.Optional[Thinking]
325332
333+
priority : typing.Optional[int]
334+
The priority of the request (lower means earlier handling; default 0 highest priority).
335+
Higher priority requests are handled first, and dropped last when the system is under load.
336+
326337
request_options : typing.Optional[RequestOptions]
327338
Request-specific configuration.
328339
@@ -368,6 +379,7 @@ def chat(
368379
logprobs=logprobs,
369380
tool_choice=tool_choice,
370381
thinking=thinking,
382+
priority=priority,
371383
request_options=request_options,
372384
)
373385
return _response.data
@@ -384,6 +396,7 @@ def embed(
384396
output_dimension: typing.Optional[int] = OMIT,
385397
embedding_types: typing.Optional[typing.Sequence[EmbeddingType]] = OMIT,
386398
truncate: typing.Optional[V2EmbedRequestTruncate] = OMIT,
399+
priority: typing.Optional[int] = OMIT,
387400
request_options: typing.Optional[RequestOptions] = None,
388401
) -> EmbedByTypeResponse:
389402
"""
@@ -437,6 +450,10 @@ def embed(
437450
438451
If `NONE` is selected, when the input exceeds the maximum input token length an error will be returned.
439452
453+
priority : typing.Optional[int]
454+
The priority of the request (lower means earlier handling; default 0 highest priority).
455+
Higher priority requests are handled first, and dropped last when the system is under load.
456+
440457
request_options : typing.Optional[RequestOptions]
441458
Request-specific configuration.
442459
@@ -470,6 +487,7 @@ def embed(
470487
output_dimension=output_dimension,
471488
embedding_types=embedding_types,
472489
truncate=truncate,
490+
priority=priority,
473491
request_options=request_options,
474492
)
475493
return _response.data
@@ -482,6 +500,7 @@ def rerank(
482500
documents: typing.Sequence[str],
483501
top_n: typing.Optional[int] = OMIT,
484502
max_tokens_per_doc: typing.Optional[int] = OMIT,
503+
priority: typing.Optional[int] = OMIT,
485504
request_options: typing.Optional[RequestOptions] = None,
486505
) -> V2RerankResponse:
487506
"""
@@ -509,6 +528,10 @@ def rerank(
509528
max_tokens_per_doc : typing.Optional[int]
510529
Defaults to `4096`. Long documents will be automatically truncated to the specified number of tokens.
511530
531+
priority : typing.Optional[int]
532+
The priority of the request (lower means earlier handling; default 0 highest priority).
533+
Higher priority requests are handled first, and dropped last when the system is under load.
534+
512535
request_options : typing.Optional[RequestOptions]
513536
Request-specific configuration.
514537
@@ -544,6 +567,7 @@ def rerank(
544567
documents=documents,
545568
top_n=top_n,
546569
max_tokens_per_doc=max_tokens_per_doc,
570+
priority=priority,
547571
request_options=request_options,
548572
)
549573
return _response.data
@@ -586,6 +610,7 @@ async def chat_stream(
586610
logprobs: typing.Optional[bool] = OMIT,
587611
tool_choice: typing.Optional[V2ChatStreamRequestToolChoice] = OMIT,
588612
thinking: typing.Optional[Thinking] = OMIT,
613+
priority: typing.Optional[int] = OMIT,
589614
request_options: typing.Optional[RequestOptions] = None,
590615
) -> typing.AsyncIterator[V2ChatStreamResponse]:
591616
"""
@@ -678,6 +703,10 @@ async def chat_stream(
678703
679704
thinking : typing.Optional[Thinking]
680705
706+
priority : typing.Optional[int]
707+
The priority of the request (lower means earlier handling; default 0 highest priority).
708+
Higher priority requests are handled first, and dropped last when the system is under load.
709+
681710
request_options : typing.Optional[RequestOptions]
682711
Request-specific configuration.
683712
@@ -733,6 +762,7 @@ async def main() -> None:
733762
logprobs=logprobs,
734763
tool_choice=tool_choice,
735764
thinking=thinking,
765+
priority=priority,
736766
request_options=request_options,
737767
) as r:
738768
async for _chunk in r.data:
@@ -760,6 +790,7 @@ async def chat(
760790
logprobs: typing.Optional[bool] = OMIT,
761791
tool_choice: typing.Optional[V2ChatRequestToolChoice] = OMIT,
762792
thinking: typing.Optional[Thinking] = OMIT,
793+
priority: typing.Optional[int] = OMIT,
763794
request_options: typing.Optional[RequestOptions] = None,
764795
) -> V2ChatResponse:
765796
"""
@@ -852,6 +883,10 @@ async def chat(
852883
853884
thinking : typing.Optional[Thinking]
854885
886+
priority : typing.Optional[int]
887+
The priority of the request (lower means earlier handling; default 0 highest priority).
888+
Higher priority requests are handled first, and dropped last when the system is under load.
889+
855890
request_options : typing.Optional[RequestOptions]
856891
Request-specific configuration.
857892
@@ -905,6 +940,7 @@ async def main() -> None:
905940
logprobs=logprobs,
906941
tool_choice=tool_choice,
907942
thinking=thinking,
943+
priority=priority,
908944
request_options=request_options,
909945
)
910946
return _response.data
@@ -921,6 +957,7 @@ async def embed(
921957
output_dimension: typing.Optional[int] = OMIT,
922958
embedding_types: typing.Optional[typing.Sequence[EmbeddingType]] = OMIT,
923959
truncate: typing.Optional[V2EmbedRequestTruncate] = OMIT,
960+
priority: typing.Optional[int] = OMIT,
924961
request_options: typing.Optional[RequestOptions] = None,
925962
) -> EmbedByTypeResponse:
926963
"""
@@ -974,6 +1011,10 @@ async def embed(
9741011
9751012
If `NONE` is selected, when the input exceeds the maximum input token length an error will be returned.
9761013
1014+
priority : typing.Optional[int]
1015+
The priority of the request (lower means earlier handling; default 0 highest priority).
1016+
Higher priority requests are handled first, and dropped last when the system is under load.
1017+
9771018
request_options : typing.Optional[RequestOptions]
9781019
Request-specific configuration.
9791020
@@ -1015,6 +1056,7 @@ async def main() -> None:
10151056
output_dimension=output_dimension,
10161057
embedding_types=embedding_types,
10171058
truncate=truncate,
1059+
priority=priority,
10181060
request_options=request_options,
10191061
)
10201062
return _response.data
@@ -1027,6 +1069,7 @@ async def rerank(
10271069
documents: typing.Sequence[str],
10281070
top_n: typing.Optional[int] = OMIT,
10291071
max_tokens_per_doc: typing.Optional[int] = OMIT,
1072+
priority: typing.Optional[int] = OMIT,
10301073
request_options: typing.Optional[RequestOptions] = None,
10311074
) -> V2RerankResponse:
10321075
"""
@@ -1054,6 +1097,10 @@ async def rerank(
10541097
max_tokens_per_doc : typing.Optional[int]
10551098
Defaults to `4096`. Long documents will be automatically truncated to the specified number of tokens.
10561099
1100+
priority : typing.Optional[int]
1101+
The priority of the request (lower means earlier handling; default 0 highest priority).
1102+
Higher priority requests are handled first, and dropped last when the system is under load.
1103+
10571104
request_options : typing.Optional[RequestOptions]
10581105
Request-specific configuration.
10591106
@@ -1097,6 +1144,7 @@ async def main() -> None:
10971144
documents=documents,
10981145
top_n=top_n,
10991146
max_tokens_per_doc=max_tokens_per_doc,
1147+
priority=priority,
11001148
request_options=request_options,
11011149
)
11021150
return _response.data

0 commit comments

Comments
 (0)