mirror of
https://github.com/wassname/openrouter-python-sdk-retry-errors.git
synced 2026-07-29 11:23:49 +08:00
Initial commit: OpenRouter Python SDK
Auto-generated Python SDK for OpenRouter API, providing comprehensive client library with: - Chat completions and streaming support - Embeddings API - Model and provider information - API key management - Analytics and usage tracking - OAuth authentication flows - Full type hints and error handling
This commit is contained in:
Matt Apperson
@@ -0,0 +1,751 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from .basesdk import BaseSDK
|
||||
from enum import Enum
|
||||
from openrouter import errors, models, utils
|
||||
from openrouter._hooks import HookContext
|
||||
from openrouter.types import OptionalNullable, UNSET
|
||||
from openrouter.utils import eventstreaming, get_security_from_env
|
||||
from openrouter.utils.unmarshal_json_response import unmarshal_json_response
|
||||
from typing import Any, Dict, List, Literal, Mapping, Optional, Union, overload
|
||||
|
||||
|
||||
class SendAcceptEnum(str, Enum):
|
||||
APPLICATION_JSON = "application/json"
|
||||
TEXT_EVENT_STREAM = "text/event-stream"
|
||||
|
||||
|
||||
class Chat(BaseSDK):
|
||||
@overload
|
||||
def send(
|
||||
self,
|
||||
*,
|
||||
messages: Union[List[models.Message], List[models.MessageTypedDict]],
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
frequency_penalty: OptionalNullable[float] = UNSET,
|
||||
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
||||
logprobs: OptionalNullable[bool] = UNSET,
|
||||
top_logprobs: OptionalNullable[float] = UNSET,
|
||||
max_completion_tokens: OptionalNullable[float] = UNSET,
|
||||
max_tokens: OptionalNullable[float] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
presence_penalty: OptionalNullable[float] = UNSET,
|
||||
reasoning: Optional[Union[models.Reasoning, models.ReasoningTypedDict]] = None,
|
||||
response_format: Optional[
|
||||
Union[
|
||||
models.ChatGenerationParamsResponseFormatUnion,
|
||||
models.ChatGenerationParamsResponseFormatUnionTypedDict,
|
||||
]
|
||||
] = None,
|
||||
seed: OptionalNullable[int] = UNSET,
|
||||
stop: OptionalNullable[
|
||||
Union[
|
||||
models.ChatGenerationParamsStop,
|
||||
models.ChatGenerationParamsStopTypedDict,
|
||||
]
|
||||
] = UNSET,
|
||||
stream: Union[Literal[False], None] = None,
|
||||
stream_options: OptionalNullable[
|
||||
Union[models.ChatStreamOptions, models.ChatStreamOptionsTypedDict]
|
||||
] = UNSET,
|
||||
temperature: OptionalNullable[float] = UNSET,
|
||||
tool_choice: Optional[Any] = None,
|
||||
tools: Optional[
|
||||
Union[
|
||||
List[models.ToolDefinitionJSON],
|
||||
List[models.ToolDefinitionJSONTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
user: Optional[str] = None,
|
||||
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
||||
server_url: Optional[str] = None,
|
||||
timeout_ms: Optional[int] = None,
|
||||
http_headers: Optional[Mapping[str, str]] = None,
|
||||
) -> models.ChatResponse:
|
||||
r"""Create a chat completion
|
||||
|
||||
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
||||
|
||||
:param messages:
|
||||
:param model:
|
||||
:param models:
|
||||
:param frequency_penalty:
|
||||
:param logit_bias:
|
||||
:param logprobs:
|
||||
:param top_logprobs:
|
||||
:param max_completion_tokens:
|
||||
:param max_tokens:
|
||||
:param metadata:
|
||||
:param presence_penalty:
|
||||
:param reasoning:
|
||||
:param response_format:
|
||||
:param seed:
|
||||
:param stop:
|
||||
:param stream:
|
||||
:param stream_options:
|
||||
:param temperature:
|
||||
:param tool_choice:
|
||||
:param tools:
|
||||
:param top_p:
|
||||
:param user:
|
||||
:param retries: Override the default retry configuration for this method
|
||||
:param server_url: Override the default server URL for this method
|
||||
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
||||
:param accept_header_override: Override the default accept header for this method
|
||||
:param http_headers: Additional headers to set or replace on requests.
|
||||
"""
|
||||
|
||||
@overload
|
||||
def send(
|
||||
self,
|
||||
*,
|
||||
messages: Union[List[models.Message], List[models.MessageTypedDict]],
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
frequency_penalty: OptionalNullable[float] = UNSET,
|
||||
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
||||
logprobs: OptionalNullable[bool] = UNSET,
|
||||
top_logprobs: OptionalNullable[float] = UNSET,
|
||||
max_completion_tokens: OptionalNullable[float] = UNSET,
|
||||
max_tokens: OptionalNullable[float] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
presence_penalty: OptionalNullable[float] = UNSET,
|
||||
reasoning: Optional[Union[models.Reasoning, models.ReasoningTypedDict]] = None,
|
||||
response_format: Optional[
|
||||
Union[
|
||||
models.ChatGenerationParamsResponseFormatUnion,
|
||||
models.ChatGenerationParamsResponseFormatUnionTypedDict,
|
||||
]
|
||||
] = None,
|
||||
seed: OptionalNullable[int] = UNSET,
|
||||
stop: OptionalNullable[
|
||||
Union[
|
||||
models.ChatGenerationParamsStop,
|
||||
models.ChatGenerationParamsStopTypedDict,
|
||||
]
|
||||
] = UNSET,
|
||||
stream: Literal[True],
|
||||
stream_options: OptionalNullable[
|
||||
Union[models.ChatStreamOptions, models.ChatStreamOptionsTypedDict]
|
||||
] = UNSET,
|
||||
temperature: OptionalNullable[float] = UNSET,
|
||||
tool_choice: Optional[Any] = None,
|
||||
tools: Optional[
|
||||
Union[
|
||||
List[models.ToolDefinitionJSON],
|
||||
List[models.ToolDefinitionJSONTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
user: Optional[str] = None,
|
||||
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
||||
server_url: Optional[str] = None,
|
||||
timeout_ms: Optional[int] = None,
|
||||
http_headers: Optional[Mapping[str, str]] = None,
|
||||
) -> eventstreaming.EventStream[models.ChatStreamingResponseChunk]:
|
||||
r"""Create a chat completion
|
||||
|
||||
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
||||
|
||||
:param messages:
|
||||
:param model:
|
||||
:param models:
|
||||
:param frequency_penalty:
|
||||
:param logit_bias:
|
||||
:param logprobs:
|
||||
:param top_logprobs:
|
||||
:param max_completion_tokens:
|
||||
:param max_tokens:
|
||||
:param metadata:
|
||||
:param presence_penalty:
|
||||
:param reasoning:
|
||||
:param response_format:
|
||||
:param seed:
|
||||
:param stop:
|
||||
:param stream:
|
||||
:param stream_options:
|
||||
:param temperature:
|
||||
:param tool_choice:
|
||||
:param tools:
|
||||
:param top_p:
|
||||
:param user:
|
||||
:param retries: Override the default retry configuration for this method
|
||||
:param server_url: Override the default server URL for this method
|
||||
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
||||
:param accept_header_override: Override the default accept header for this method
|
||||
:param http_headers: Additional headers to set or replace on requests.
|
||||
"""
|
||||
|
||||
def send(
|
||||
self,
|
||||
*,
|
||||
messages: Union[List[models.Message], List[models.MessageTypedDict]],
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
frequency_penalty: OptionalNullable[float] = UNSET,
|
||||
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
||||
logprobs: OptionalNullable[bool] = UNSET,
|
||||
top_logprobs: OptionalNullable[float] = UNSET,
|
||||
max_completion_tokens: OptionalNullable[float] = UNSET,
|
||||
max_tokens: OptionalNullable[float] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
presence_penalty: OptionalNullable[float] = UNSET,
|
||||
reasoning: Optional[Union[models.Reasoning, models.ReasoningTypedDict]] = None,
|
||||
response_format: Optional[
|
||||
Union[
|
||||
models.ChatGenerationParamsResponseFormatUnion,
|
||||
models.ChatGenerationParamsResponseFormatUnionTypedDict,
|
||||
]
|
||||
] = None,
|
||||
seed: OptionalNullable[int] = UNSET,
|
||||
stop: OptionalNullable[
|
||||
Union[
|
||||
models.ChatGenerationParamsStop,
|
||||
models.ChatGenerationParamsStopTypedDict,
|
||||
]
|
||||
] = UNSET,
|
||||
stream: Optional[bool] = False,
|
||||
stream_options: OptionalNullable[
|
||||
Union[models.ChatStreamOptions, models.ChatStreamOptionsTypedDict]
|
||||
] = UNSET,
|
||||
temperature: OptionalNullable[float] = UNSET,
|
||||
tool_choice: Optional[Any] = None,
|
||||
tools: Optional[
|
||||
Union[
|
||||
List[models.ToolDefinitionJSON],
|
||||
List[models.ToolDefinitionJSONTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
user: Optional[str] = None,
|
||||
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
||||
server_url: Optional[str] = None,
|
||||
timeout_ms: Optional[int] = None,
|
||||
http_headers: Optional[Mapping[str, str]] = None,
|
||||
) -> models.SendChatCompletionRequestResponse:
|
||||
r"""Create a chat completion
|
||||
|
||||
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
||||
|
||||
:param messages:
|
||||
:param model:
|
||||
:param models:
|
||||
:param frequency_penalty:
|
||||
:param logit_bias:
|
||||
:param logprobs:
|
||||
:param top_logprobs:
|
||||
:param max_completion_tokens:
|
||||
:param max_tokens:
|
||||
:param metadata:
|
||||
:param presence_penalty:
|
||||
:param reasoning:
|
||||
:param response_format:
|
||||
:param seed:
|
||||
:param stop:
|
||||
:param stream:
|
||||
:param stream_options:
|
||||
:param temperature:
|
||||
:param tool_choice:
|
||||
:param tools:
|
||||
:param top_p:
|
||||
:param user:
|
||||
:param retries: Override the default retry configuration for this method
|
||||
:param server_url: Override the default server URL for this method
|
||||
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
||||
:param accept_header_override: Override the default accept header for this method
|
||||
:param http_headers: Additional headers to set or replace on requests.
|
||||
"""
|
||||
base_url = None
|
||||
url_variables = None
|
||||
if timeout_ms is None:
|
||||
timeout_ms = self.sdk_configuration.timeout_ms
|
||||
|
||||
if server_url is not None:
|
||||
base_url = server_url
|
||||
else:
|
||||
base_url = self._get_url(base_url, url_variables)
|
||||
|
||||
request = models.ChatGenerationParams(
|
||||
messages=utils.get_pydantic_model(messages, List[models.Message]),
|
||||
model=model,
|
||||
models=models,
|
||||
frequency_penalty=frequency_penalty,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
top_logprobs=top_logprobs,
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
max_tokens=max_tokens,
|
||||
metadata=metadata,
|
||||
presence_penalty=presence_penalty,
|
||||
reasoning=utils.get_pydantic_model(reasoning, Optional[models.Reasoning]),
|
||||
response_format=utils.get_pydantic_model(
|
||||
response_format,
|
||||
Optional[models.ChatGenerationParamsResponseFormatUnion],
|
||||
),
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=utils.get_pydantic_model(
|
||||
stream_options, OptionalNullable[models.ChatStreamOptions]
|
||||
),
|
||||
temperature=temperature,
|
||||
tool_choice=tool_choice,
|
||||
tools=utils.get_pydantic_model(
|
||||
tools, Optional[List[models.ToolDefinitionJSON]]
|
||||
),
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
|
||||
req = self._build_request(
|
||||
method="POST",
|
||||
path="/chat/completions",
|
||||
base_url=base_url,
|
||||
url_variables=url_variables,
|
||||
request=request,
|
||||
request_body_required=True,
|
||||
request_has_path_params=False,
|
||||
request_has_query_params=True,
|
||||
user_agent_header="user-agent",
|
||||
accept_header_value="text/event-stream" if stream else "application/json",
|
||||
http_headers=http_headers,
|
||||
security=self.sdk_configuration.security,
|
||||
get_serialized_body=lambda: utils.serialize_request_body(
|
||||
request, False, False, "json", models.ChatGenerationParams
|
||||
),
|
||||
timeout_ms=timeout_ms,
|
||||
)
|
||||
|
||||
if retries == UNSET:
|
||||
if self.sdk_configuration.retry_config is not UNSET:
|
||||
retries = self.sdk_configuration.retry_config
|
||||
|
||||
retry_config = None
|
||||
if isinstance(retries, utils.RetryConfig):
|
||||
retry_config = (retries, ["429", "500", "502", "503", "504"])
|
||||
|
||||
http_res = self.do_request(
|
||||
hook_ctx=HookContext(
|
||||
config=self.sdk_configuration,
|
||||
base_url=base_url or "",
|
||||
operation_id="sendChatCompletionRequest",
|
||||
oauth2_scopes=None,
|
||||
security_source=get_security_from_env(
|
||||
self.sdk_configuration.security, models.Security
|
||||
),
|
||||
),
|
||||
request=req,
|
||||
error_status_codes=["400", "401", "429", "4XX", "500", "5XX"],
|
||||
stream=True,
|
||||
retry_config=retry_config,
|
||||
)
|
||||
|
||||
response_data: Any = None
|
||||
if utils.match_response(http_res, "200", "application/json"):
|
||||
http_res_text = utils.stream_to_text(http_res)
|
||||
return unmarshal_json_response(models.ChatResponse, http_res, http_res_text)
|
||||
if utils.match_response(http_res, "200", "text/event-stream"):
|
||||
return eventstreaming.EventStream(
|
||||
http_res,
|
||||
lambda raw: utils.unmarshal_json(
|
||||
raw, models.ChatStreamingResponseChunk
|
||||
),
|
||||
sentinel="[DONE]",
|
||||
client_ref=self,
|
||||
)
|
||||
if utils.match_response(http_res, ["400", "401", "429"], "application/json"):
|
||||
http_res_text = utils.stream_to_text(http_res)
|
||||
response_data = unmarshal_json_response(
|
||||
errors.ChatErrorData, http_res, http_res_text
|
||||
)
|
||||
raise errors.ChatError(response_data, http_res, http_res_text)
|
||||
if utils.match_response(http_res, "500", "application/json"):
|
||||
http_res_text = utils.stream_to_text(http_res)
|
||||
response_data = unmarshal_json_response(
|
||||
errors.ChatErrorData, http_res, http_res_text
|
||||
)
|
||||
raise errors.ChatError(response_data, http_res, http_res_text)
|
||||
if utils.match_response(http_res, "4XX", "*"):
|
||||
http_res_text = utils.stream_to_text(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
if utils.match_response(http_res, "5XX", "*"):
|
||||
http_res_text = utils.stream_to_text(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
|
||||
http_res_text = utils.stream_to_text(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"Unexpected response received", http_res, http_res_text
|
||||
)
|
||||
|
||||
@overload
|
||||
async def send_async(
|
||||
self,
|
||||
*,
|
||||
messages: Union[List[models.Message], List[models.MessageTypedDict]],
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
frequency_penalty: OptionalNullable[float] = UNSET,
|
||||
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
||||
logprobs: OptionalNullable[bool] = UNSET,
|
||||
top_logprobs: OptionalNullable[float] = UNSET,
|
||||
max_completion_tokens: OptionalNullable[float] = UNSET,
|
||||
max_tokens: OptionalNullable[float] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
presence_penalty: OptionalNullable[float] = UNSET,
|
||||
reasoning: Optional[Union[models.Reasoning, models.ReasoningTypedDict]] = None,
|
||||
response_format: Optional[
|
||||
Union[
|
||||
models.ChatGenerationParamsResponseFormatUnion,
|
||||
models.ChatGenerationParamsResponseFormatUnionTypedDict,
|
||||
]
|
||||
] = None,
|
||||
seed: OptionalNullable[int] = UNSET,
|
||||
stop: OptionalNullable[
|
||||
Union[
|
||||
models.ChatGenerationParamsStop,
|
||||
models.ChatGenerationParamsStopTypedDict,
|
||||
]
|
||||
] = UNSET,
|
||||
stream: Union[Literal[False], None] = None,
|
||||
stream_options: OptionalNullable[
|
||||
Union[models.ChatStreamOptions, models.ChatStreamOptionsTypedDict]
|
||||
] = UNSET,
|
||||
temperature: OptionalNullable[float] = UNSET,
|
||||
tool_choice: Optional[Any] = None,
|
||||
tools: Optional[
|
||||
Union[
|
||||
List[models.ToolDefinitionJSON],
|
||||
List[models.ToolDefinitionJSONTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
user: Optional[str] = None,
|
||||
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
||||
server_url: Optional[str] = None,
|
||||
timeout_ms: Optional[int] = None,
|
||||
http_headers: Optional[Mapping[str, str]] = None,
|
||||
) -> models.ChatResponse:
|
||||
r"""Create a chat completion
|
||||
|
||||
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
||||
|
||||
:param messages:
|
||||
:param model:
|
||||
:param models:
|
||||
:param frequency_penalty:
|
||||
:param logit_bias:
|
||||
:param logprobs:
|
||||
:param top_logprobs:
|
||||
:param max_completion_tokens:
|
||||
:param max_tokens:
|
||||
:param metadata:
|
||||
:param presence_penalty:
|
||||
:param reasoning:
|
||||
:param response_format:
|
||||
:param seed:
|
||||
:param stop:
|
||||
:param stream:
|
||||
:param stream_options:
|
||||
:param temperature:
|
||||
:param tool_choice:
|
||||
:param tools:
|
||||
:param top_p:
|
||||
:param user:
|
||||
:param retries: Override the default retry configuration for this method
|
||||
:param server_url: Override the default server URL for this method
|
||||
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
||||
:param accept_header_override: Override the default accept header for this method
|
||||
:param http_headers: Additional headers to set or replace on requests.
|
||||
"""
|
||||
|
||||
@overload
|
||||
async def send_async(
|
||||
self,
|
||||
*,
|
||||
messages: Union[List[models.Message], List[models.MessageTypedDict]],
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
frequency_penalty: OptionalNullable[float] = UNSET,
|
||||
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
||||
logprobs: OptionalNullable[bool] = UNSET,
|
||||
top_logprobs: OptionalNullable[float] = UNSET,
|
||||
max_completion_tokens: OptionalNullable[float] = UNSET,
|
||||
max_tokens: OptionalNullable[float] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
presence_penalty: OptionalNullable[float] = UNSET,
|
||||
reasoning: Optional[Union[models.Reasoning, models.ReasoningTypedDict]] = None,
|
||||
response_format: Optional[
|
||||
Union[
|
||||
models.ChatGenerationParamsResponseFormatUnion,
|
||||
models.ChatGenerationParamsResponseFormatUnionTypedDict,
|
||||
]
|
||||
] = None,
|
||||
seed: OptionalNullable[int] = UNSET,
|
||||
stop: OptionalNullable[
|
||||
Union[
|
||||
models.ChatGenerationParamsStop,
|
||||
models.ChatGenerationParamsStopTypedDict,
|
||||
]
|
||||
] = UNSET,
|
||||
stream: Literal[True],
|
||||
stream_options: OptionalNullable[
|
||||
Union[models.ChatStreamOptions, models.ChatStreamOptionsTypedDict]
|
||||
] = UNSET,
|
||||
temperature: OptionalNullable[float] = UNSET,
|
||||
tool_choice: Optional[Any] = None,
|
||||
tools: Optional[
|
||||
Union[
|
||||
List[models.ToolDefinitionJSON],
|
||||
List[models.ToolDefinitionJSONTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
user: Optional[str] = None,
|
||||
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
||||
server_url: Optional[str] = None,
|
||||
timeout_ms: Optional[int] = None,
|
||||
http_headers: Optional[Mapping[str, str]] = None,
|
||||
) -> eventstreaming.EventStreamAsync[models.ChatStreamingResponseChunk]:
|
||||
r"""Create a chat completion
|
||||
|
||||
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
||||
|
||||
:param messages:
|
||||
:param model:
|
||||
:param models:
|
||||
:param frequency_penalty:
|
||||
:param logit_bias:
|
||||
:param logprobs:
|
||||
:param top_logprobs:
|
||||
:param max_completion_tokens:
|
||||
:param max_tokens:
|
||||
:param metadata:
|
||||
:param presence_penalty:
|
||||
:param reasoning:
|
||||
:param response_format:
|
||||
:param seed:
|
||||
:param stop:
|
||||
:param stream:
|
||||
:param stream_options:
|
||||
:param temperature:
|
||||
:param tool_choice:
|
||||
:param tools:
|
||||
:param top_p:
|
||||
:param user:
|
||||
:param retries: Override the default retry configuration for this method
|
||||
:param server_url: Override the default server URL for this method
|
||||
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
||||
:param accept_header_override: Override the default accept header for this method
|
||||
:param http_headers: Additional headers to set or replace on requests.
|
||||
"""
|
||||
|
||||
async def send_async(
|
||||
self,
|
||||
*,
|
||||
messages: Union[List[models.Message], List[models.MessageTypedDict]],
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
frequency_penalty: OptionalNullable[float] = UNSET,
|
||||
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
||||
logprobs: OptionalNullable[bool] = UNSET,
|
||||
top_logprobs: OptionalNullable[float] = UNSET,
|
||||
max_completion_tokens: OptionalNullable[float] = UNSET,
|
||||
max_tokens: OptionalNullable[float] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
presence_penalty: OptionalNullable[float] = UNSET,
|
||||
reasoning: Optional[Union[models.Reasoning, models.ReasoningTypedDict]] = None,
|
||||
response_format: Optional[
|
||||
Union[
|
||||
models.ChatGenerationParamsResponseFormatUnion,
|
||||
models.ChatGenerationParamsResponseFormatUnionTypedDict,
|
||||
]
|
||||
] = None,
|
||||
seed: OptionalNullable[int] = UNSET,
|
||||
stop: OptionalNullable[
|
||||
Union[
|
||||
models.ChatGenerationParamsStop,
|
||||
models.ChatGenerationParamsStopTypedDict,
|
||||
]
|
||||
] = UNSET,
|
||||
stream: Optional[bool] = False,
|
||||
stream_options: OptionalNullable[
|
||||
Union[models.ChatStreamOptions, models.ChatStreamOptionsTypedDict]
|
||||
] = UNSET,
|
||||
temperature: OptionalNullable[float] = UNSET,
|
||||
tool_choice: Optional[Any] = None,
|
||||
tools: Optional[
|
||||
Union[
|
||||
List[models.ToolDefinitionJSON],
|
||||
List[models.ToolDefinitionJSONTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
user: Optional[str] = None,
|
||||
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
||||
server_url: Optional[str] = None,
|
||||
timeout_ms: Optional[int] = None,
|
||||
http_headers: Optional[Mapping[str, str]] = None,
|
||||
) -> models.SendChatCompletionRequestResponse:
|
||||
r"""Create a chat completion
|
||||
|
||||
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
||||
|
||||
:param messages:
|
||||
:param model:
|
||||
:param models:
|
||||
:param frequency_penalty:
|
||||
:param logit_bias:
|
||||
:param logprobs:
|
||||
:param top_logprobs:
|
||||
:param max_completion_tokens:
|
||||
:param max_tokens:
|
||||
:param metadata:
|
||||
:param presence_penalty:
|
||||
:param reasoning:
|
||||
:param response_format:
|
||||
:param seed:
|
||||
:param stop:
|
||||
:param stream:
|
||||
:param stream_options:
|
||||
:param temperature:
|
||||
:param tool_choice:
|
||||
:param tools:
|
||||
:param top_p:
|
||||
:param user:
|
||||
:param retries: Override the default retry configuration for this method
|
||||
:param server_url: Override the default server URL for this method
|
||||
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
||||
:param accept_header_override: Override the default accept header for this method
|
||||
:param http_headers: Additional headers to set or replace on requests.
|
||||
"""
|
||||
base_url = None
|
||||
url_variables = None
|
||||
if timeout_ms is None:
|
||||
timeout_ms = self.sdk_configuration.timeout_ms
|
||||
|
||||
if server_url is not None:
|
||||
base_url = server_url
|
||||
else:
|
||||
base_url = self._get_url(base_url, url_variables)
|
||||
|
||||
request = models.ChatGenerationParams(
|
||||
messages=utils.get_pydantic_model(messages, List[models.Message]),
|
||||
model=model,
|
||||
models=models,
|
||||
frequency_penalty=frequency_penalty,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
top_logprobs=top_logprobs,
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
max_tokens=max_tokens,
|
||||
metadata=metadata,
|
||||
presence_penalty=presence_penalty,
|
||||
reasoning=utils.get_pydantic_model(reasoning, Optional[models.Reasoning]),
|
||||
response_format=utils.get_pydantic_model(
|
||||
response_format,
|
||||
Optional[models.ChatGenerationParamsResponseFormatUnion],
|
||||
),
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=utils.get_pydantic_model(
|
||||
stream_options, OptionalNullable[models.ChatStreamOptions]
|
||||
),
|
||||
temperature=temperature,
|
||||
tool_choice=tool_choice,
|
||||
tools=utils.get_pydantic_model(
|
||||
tools, Optional[List[models.ToolDefinitionJSON]]
|
||||
),
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
|
||||
req = self._build_request_async(
|
||||
method="POST",
|
||||
path="/chat/completions",
|
||||
base_url=base_url,
|
||||
url_variables=url_variables,
|
||||
request=request,
|
||||
request_body_required=True,
|
||||
request_has_path_params=False,
|
||||
request_has_query_params=True,
|
||||
user_agent_header="user-agent",
|
||||
accept_header_value="text/event-stream" if stream else "application/json",
|
||||
http_headers=http_headers,
|
||||
security=self.sdk_configuration.security,
|
||||
get_serialized_body=lambda: utils.serialize_request_body(
|
||||
request, False, False, "json", models.ChatGenerationParams
|
||||
),
|
||||
timeout_ms=timeout_ms,
|
||||
)
|
||||
|
||||
if retries == UNSET:
|
||||
if self.sdk_configuration.retry_config is not UNSET:
|
||||
retries = self.sdk_configuration.retry_config
|
||||
|
||||
retry_config = None
|
||||
if isinstance(retries, utils.RetryConfig):
|
||||
retry_config = (retries, ["429", "500", "502", "503", "504"])
|
||||
|
||||
http_res = await self.do_request_async(
|
||||
hook_ctx=HookContext(
|
||||
config=self.sdk_configuration,
|
||||
base_url=base_url or "",
|
||||
operation_id="sendChatCompletionRequest",
|
||||
oauth2_scopes=None,
|
||||
security_source=get_security_from_env(
|
||||
self.sdk_configuration.security, models.Security
|
||||
),
|
||||
),
|
||||
request=req,
|
||||
error_status_codes=["400", "401", "429", "4XX", "500", "5XX"],
|
||||
stream=True,
|
||||
retry_config=retry_config,
|
||||
)
|
||||
|
||||
response_data: Any = None
|
||||
if utils.match_response(http_res, "200", "application/json"):
|
||||
http_res_text = await utils.stream_to_text_async(http_res)
|
||||
return unmarshal_json_response(models.ChatResponse, http_res, http_res_text)
|
||||
if utils.match_response(http_res, "200", "text/event-stream"):
|
||||
return eventstreaming.EventStreamAsync(
|
||||
http_res,
|
||||
lambda raw: utils.unmarshal_json(
|
||||
raw, models.ChatStreamingResponseChunk
|
||||
),
|
||||
sentinel="[DONE]",
|
||||
client_ref=self,
|
||||
)
|
||||
if utils.match_response(http_res, ["400", "401", "429"], "application/json"):
|
||||
http_res_text = await utils.stream_to_text_async(http_res)
|
||||
response_data = unmarshal_json_response(
|
||||
errors.ChatErrorData, http_res, http_res_text
|
||||
)
|
||||
raise errors.ChatError(response_data, http_res, http_res_text)
|
||||
if utils.match_response(http_res, "500", "application/json"):
|
||||
http_res_text = await utils.stream_to_text_async(http_res)
|
||||
response_data = unmarshal_json_response(
|
||||
errors.ChatErrorData, http_res, http_res_text
|
||||
)
|
||||
raise errors.ChatError(response_data, http_res, http_res_text)
|
||||
if utils.match_response(http_res, "4XX", "*"):
|
||||
http_res_text = await utils.stream_to_text_async(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
if utils.match_response(http_res, "5XX", "*"):
|
||||
http_res_text = await utils.stream_to_text_async(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
|
||||
http_res_text = await utils.stream_to_text_async(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"Unexpected response received", http_res, http_res_text
|
||||
)
|
||||
Reference in New Issue
Block a user