Chat¶
client.chat.completions creates chat completions, with or without streaming.
Response models live in Types.
Resource classes¶
Chat
¶
Chat(client)
Source code in dashscope/resources/chat/__init__.py
33 34 | |
AsyncChat
¶
AsyncChat(client)
Source code in dashscope/resources/chat/__init__.py
38 39 | |
Completions
¶
Completions(client)
Source code in dashscope/resources/chat/completions.py
926 927 | |
create
¶
create(
*,
model: str,
messages: Union[str, List[MessageInput]],
stream: Literal[True],
tools: Optional[List[Dict[str, Any]]] = None,
temperature: Optional[float] = None,
top_p: Optional[float] = None,
max_tokens: Optional[int] = None,
stop: Union[str, List[str], None] = None,
seed: Optional[int] = None,
repetition_penalty: Optional[float] = None,
presence_penalty: Optional[float] = None,
enable_thinking: Optional[bool] = None,
response_format: Optional[Dict[str, Any]] = None,
top_k: Optional[int] = None,
tool_choice: Union[str, Dict[str, Any], None] = None,
n: Optional[int] = None,
logprobs: Optional[bool] = None,
top_logprobs: Optional[int] = None,
thinking_budget: Optional[int] = None,
enable_search: Optional[bool] = None,
search_options: Optional[Dict[str, Any]] = None,
parallel_tool_calls: Optional[bool] = None,
incremental_output: Optional[bool] = None,
parameters: Optional[Dict[str, Any]] = None,
timeout: Optional[float] = None,
api_key: Optional[str] = None,
workspace: Optional[str] = None,
extra_headers: Optional[Mapping[str, str]] = None,
extra_query: Optional[Mapping[str, Any]] = None,
extra_body: Optional[Mapping[str, Any]] = None,
max_retries: Optional[int] = None,
raw: Literal[False] = False
) -> ChatStream
create(
*,
model: str,
messages: Union[str, List[MessageInput]],
stream: Literal[False] = False,
tools: Optional[List[Dict[str, Any]]] = None,
temperature: Optional[float] = None,
top_p: Optional[float] = None,
max_tokens: Optional[int] = None,
stop: Union[str, List[str], None] = None,
seed: Optional[int] = None,
repetition_penalty: Optional[float] = None,
presence_penalty: Optional[float] = None,
enable_thinking: Optional[bool] = None,
response_format: Optional[Dict[str, Any]] = None,
top_k: Optional[int] = None,
tool_choice: Union[str, Dict[str, Any], None] = None,
n: Optional[int] = None,
logprobs: Optional[bool] = None,
top_logprobs: Optional[int] = None,
thinking_budget: Optional[int] = None,
enable_search: Optional[bool] = None,
search_options: Optional[Dict[str, Any]] = None,
parallel_tool_calls: Optional[bool] = None,
incremental_output: Optional[bool] = None,
parameters: Optional[Dict[str, Any]] = None,
timeout: Optional[float] = None,
api_key: Optional[str] = None,
workspace: Optional[str] = None,
extra_headers: Optional[Mapping[str, str]] = None,
extra_query: Optional[Mapping[str, Any]] = None,
extra_body: Optional[Mapping[str, Any]] = None,
max_retries: Optional[int] = None,
raw: Literal[False] = False
) -> ChatCompletion
create(
*,
model: str,
messages: Union[str, List[MessageInput]],
stream: Literal[False] = False,
tools: Optional[List[Dict[str, Any]]] = None,
temperature: Optional[float] = None,
top_p: Optional[float] = None,
max_tokens: Optional[int] = None,
stop: Union[str, List[str], None] = None,
seed: Optional[int] = None,
repetition_penalty: Optional[float] = None,
presence_penalty: Optional[float] = None,
enable_thinking: Optional[bool] = None,
response_format: Optional[Dict[str, Any]] = None,
top_k: Optional[int] = None,
tool_choice: Union[str, Dict[str, Any], None] = None,
n: Optional[int] = None,
logprobs: Optional[bool] = None,
top_logprobs: Optional[int] = None,
thinking_budget: Optional[int] = None,
enable_search: Optional[bool] = None,
search_options: Optional[Dict[str, Any]] = None,
parallel_tool_calls: Optional[bool] = None,
incremental_output: Optional[bool] = None,
parameters: Optional[Dict[str, Any]] = None,
timeout: Optional[float] = None,
api_key: Optional[str] = None,
workspace: Optional[str] = None,
extra_headers: Optional[Mapping[str, str]] = None,
extra_query: Optional[Mapping[str, Any]] = None,
extra_body: Optional[Mapping[str, Any]] = None,
max_retries: Optional[int] = None,
raw: Literal[True]
) -> "APIResponse"
create(
*,
model: str,
messages: Union[str, List[MessageInput]],
stream: bool = False,
tools: Optional[List[Dict[str, Any]]] = None,
temperature: Optional[float] = None,
top_p: Optional[float] = None,
max_tokens: Optional[int] = None,
stop: Union[str, List[str], None] = None,
seed: Optional[int] = None,
repetition_penalty: Optional[float] = None,
presence_penalty: Optional[float] = None,
enable_thinking: Optional[bool] = None,
response_format: Optional[Dict[str, Any]] = None,
top_k: Optional[int] = None,
tool_choice: Union[str, Dict[str, Any], None] = None,
n: Optional[int] = None,
logprobs: Optional[bool] = None,
top_logprobs: Optional[int] = None,
thinking_budget: Optional[int] = None,
enable_search: Optional[bool] = None,
search_options: Optional[Dict[str, Any]] = None,
parallel_tool_calls: Optional[bool] = None,
incremental_output: Optional[bool] = None,
parameters: Optional[Dict[str, Any]] = None,
timeout: Optional[float] = None,
api_key: Optional[str] = None,
workspace: Optional[str] = None,
extra_headers: Optional[Mapping[str, str]] = None,
extra_query: Optional[Mapping[str, Any]] = None,
extra_body: Optional[Mapping[str, Any]] = None,
max_retries: Optional[int] = None,
raw: bool = False
) -> Union[ChatCompletion, ChatStream, "APIResponse"]
Run one chat completion.
raw=True returns the :class:~dashscope.transport.APIResponse
before any error check, so a caller can read the status, headers and
elapsed of the response or re-parse it itself. It is only
available with stream=False: a streaming response body is never
materialized, so there is nothing to hand back. Combining the two
raises ValueError.
Source code in dashscope/resources/chat/completions.py
1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 | |
AsyncCompletions
¶
AsyncCompletions(client)
Source code in dashscope/resources/chat/completions.py
1143 1144 | |
create
async
¶
create(
*,
model: str,
messages: Union[str, List[MessageInput]],
stream: Literal[True],
tools: Optional[List[Dict[str, Any]]] = None,
temperature: Optional[float] = None,
top_p: Optional[float] = None,
max_tokens: Optional[int] = None,
stop: Union[str, List[str], None] = None,
seed: Optional[int] = None,
repetition_penalty: Optional[float] = None,
presence_penalty: Optional[float] = None,
enable_thinking: Optional[bool] = None,
response_format: Optional[Dict[str, Any]] = None,
top_k: Optional[int] = None,
tool_choice: Union[str, Dict[str, Any], None] = None,
n: Optional[int] = None,
logprobs: Optional[bool] = None,
top_logprobs: Optional[int] = None,
thinking_budget: Optional[int] = None,
enable_search: Optional[bool] = None,
search_options: Optional[Dict[str, Any]] = None,
parallel_tool_calls: Optional[bool] = None,
incremental_output: Optional[bool] = None,
parameters: Optional[Dict[str, Any]] = None,
timeout: Optional[float] = None,
api_key: Optional[str] = None,
workspace: Optional[str] = None,
extra_headers: Optional[Mapping[str, str]] = None,
extra_query: Optional[Mapping[str, Any]] = None,
extra_body: Optional[Mapping[str, Any]] = None,
max_retries: Optional[int] = None,
raw: Literal[False] = False
) -> AsyncChatStream
create(
*,
model: str,
messages: Union[str, List[MessageInput]],
stream: Literal[False] = False,
tools: Optional[List[Dict[str, Any]]] = None,
temperature: Optional[float] = None,
top_p: Optional[float] = None,
max_tokens: Optional[int] = None,
stop: Union[str, List[str], None] = None,
seed: Optional[int] = None,
repetition_penalty: Optional[float] = None,
presence_penalty: Optional[float] = None,
enable_thinking: Optional[bool] = None,
response_format: Optional[Dict[str, Any]] = None,
top_k: Optional[int] = None,
tool_choice: Union[str, Dict[str, Any], None] = None,
n: Optional[int] = None,
logprobs: Optional[bool] = None,
top_logprobs: Optional[int] = None,
thinking_budget: Optional[int] = None,
enable_search: Optional[bool] = None,
search_options: Optional[Dict[str, Any]] = None,
parallel_tool_calls: Optional[bool] = None,
incremental_output: Optional[bool] = None,
parameters: Optional[Dict[str, Any]] = None,
timeout: Optional[float] = None,
api_key: Optional[str] = None,
workspace: Optional[str] = None,
extra_headers: Optional[Mapping[str, str]] = None,
extra_query: Optional[Mapping[str, Any]] = None,
extra_body: Optional[Mapping[str, Any]] = None,
max_retries: Optional[int] = None,
raw: Literal[False] = False
) -> ChatCompletion
create(
*,
model: str,
messages: Union[str, List[MessageInput]],
stream: Literal[False] = False,
tools: Optional[List[Dict[str, Any]]] = None,
temperature: Optional[float] = None,
top_p: Optional[float] = None,
max_tokens: Optional[int] = None,
stop: Union[str, List[str], None] = None,
seed: Optional[int] = None,
repetition_penalty: Optional[float] = None,
presence_penalty: Optional[float] = None,
enable_thinking: Optional[bool] = None,
response_format: Optional[Dict[str, Any]] = None,
top_k: Optional[int] = None,
tool_choice: Union[str, Dict[str, Any], None] = None,
n: Optional[int] = None,
logprobs: Optional[bool] = None,
top_logprobs: Optional[int] = None,
thinking_budget: Optional[int] = None,
enable_search: Optional[bool] = None,
search_options: Optional[Dict[str, Any]] = None,
parallel_tool_calls: Optional[bool] = None,
incremental_output: Optional[bool] = None,
parameters: Optional[Dict[str, Any]] = None,
timeout: Optional[float] = None,
api_key: Optional[str] = None,
workspace: Optional[str] = None,
extra_headers: Optional[Mapping[str, str]] = None,
extra_query: Optional[Mapping[str, Any]] = None,
extra_body: Optional[Mapping[str, Any]] = None,
max_retries: Optional[int] = None,
raw: Literal[True]
) -> "APIResponse"
create(
*,
model: str,
messages: Union[str, List[MessageInput]],
stream: bool = False,
tools: Optional[List[Dict[str, Any]]] = None,
temperature: Optional[float] = None,
top_p: Optional[float] = None,
max_tokens: Optional[int] = None,
stop: Union[str, List[str], None] = None,
seed: Optional[int] = None,
repetition_penalty: Optional[float] = None,
presence_penalty: Optional[float] = None,
enable_thinking: Optional[bool] = None,
response_format: Optional[Dict[str, Any]] = None,
top_k: Optional[int] = None,
tool_choice: Union[str, Dict[str, Any], None] = None,
n: Optional[int] = None,
logprobs: Optional[bool] = None,
top_logprobs: Optional[int] = None,
thinking_budget: Optional[int] = None,
enable_search: Optional[bool] = None,
search_options: Optional[Dict[str, Any]] = None,
parallel_tool_calls: Optional[bool] = None,
incremental_output: Optional[bool] = None,
parameters: Optional[Dict[str, Any]] = None,
timeout: Optional[float] = None,
api_key: Optional[str] = None,
workspace: Optional[str] = None,
extra_headers: Optional[Mapping[str, str]] = None,
extra_query: Optional[Mapping[str, Any]] = None,
extra_body: Optional[Mapping[str, Any]] = None,
max_retries: Optional[int] = None,
raw: bool = False
) -> Union[ChatCompletion, AsyncChatStream, "APIResponse"]
Run one chat completion.
raw=True returns the :class:~dashscope.transport.APIResponse
before any error check, so a caller can read the status, headers and
elapsed of the response or re-parse it itself. It is only
available with stream=False: a streaming response body is never
materialized, so there is nothing to hand back. Combining the two
raises ValueError.
Source code in dashscope/resources/chat/completions.py
1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 | |
ChatStream
¶
ChatStream(
inner: Stream[ChatCompletionChunk],
*,
merge_incremental: bool = False,
server_cumulative: bool = False,
strict_validation: bool = False,
response: Optional[Response] = None
)
Typed iterator over chat chunks with text/aggregate helpers.
With merge_incremental=True every yielded chunk is a cumulative
snapshot (1.x incremental_output=False behavior), so
text_stream emits the full text so far on each step.
server_cumulative=True means the server itself streamed
cumulative snapshots (native wire incremental_output=False), so
get_final_message takes each choice's last snapshot instead of
concatenating deltas.
Source code in dashscope/resources/chat/completions.py
280 281 282 283 284 285 286 287 288 289 290 291 292 293 | |
cumulative
property
¶
cumulative: bool
True when each frame carries the whole text so far, not a delta.
Callers that append frames to a terminal have to check this: with
incremental_output=False (or a protocol merged client-side for
1.x compatibility) writing every frame in sequence repeats the
answer -- "Hi" then "Hi!" comes out as "HiHi!".
get_final_message
¶
get_final_message() -> ChatCompletion
Source code in dashscope/resources/chat/completions.py
332 333 334 335 336 337 338 339 340 341 342 | |
close
¶
close() -> None
Source code in dashscope/resources/chat/completions.py
349 350 | |
AsyncChatStream
¶
AsyncChatStream(
inner: AsyncStream[ChatCompletionChunk],
*,
merge_incremental: bool = False,
server_cumulative: bool = False,
strict_validation: bool = False,
response: Optional[Response] = None
)
Source code in dashscope/resources/chat/completions.py
354 355 356 357 358 359 360 361 362 363 364 365 366 367 | |
cumulative
property
¶
cumulative: bool
True when each frame carries the whole text so far, not a delta.
Async twin of :attr:ChatStream.cumulative; see that docstring for
why a caller appending frames to a terminal has to check it.
get_final_message
async
¶
get_final_message() -> ChatCompletion
Source code in dashscope/resources/chat/completions.py
418 419 420 421 422 423 424 425 426 427 428 429 | |
aclose
async
¶
aclose() -> None
Source code in dashscope/resources/chat/completions.py
436 437 | |
See also¶
- ChatCompletion / ChatCompletionChunk — response models.
- Types — messages, choices, deltas and usage.