orq-ai-sdk 4.2.0rc48__py3-none-any.whl → 4.2.12__py3-none-any.whl

orq_ai_sdk/orq_responses.py

@@ -0,0 +1,398 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from .basesdk import BaseSDK
+from enum import Enum
+from orq_ai_sdk import models, utils
+from orq_ai_sdk._hooks import HookContext
+from orq_ai_sdk.models import createresponseop as models_createresponseop
+from orq_ai_sdk.types import OptionalNullable, UNSET
+from orq_ai_sdk.utils import eventstreaming, get_security_from_env
+from orq_ai_sdk.utils.unmarshal_json_response import unmarshal_json_response
+from typing import Dict, List, Mapping, Optional, Union
+
+
+class CreateAcceptEnum(str, Enum):
+    APPLICATION_JSON = "application/json"
+    TEXT_EVENT_STREAM = "text/event-stream"
+
+
+class OrqResponses(BaseSDK):
+    def create(
+        self,
+        *,
+        model: str,
+        input_: Union[
+            models_createresponseop.CreateResponseInput,
+            models_createresponseop.CreateResponseInputTypedDict,
+        ],
+        metadata: Optional[Dict[str, str]] = None,
+        temperature: OptionalNullable[float] = UNSET,
+        top_p: OptionalNullable[float] = UNSET,
+        previous_response_id: OptionalNullable[str] = UNSET,
+        instructions: OptionalNullable[str] = UNSET,
+        reasoning: OptionalNullable[
+            Union[
+                models_createresponseop.Reasoning,
+                models_createresponseop.ReasoningTypedDict,
+            ]
+        ] = UNSET,
+        max_output_tokens: OptionalNullable[int] = UNSET,
+        text: OptionalNullable[
+            Union[
+                models_createresponseop.CreateResponseText,
+                models_createresponseop.CreateResponseTextTypedDict,
+            ]
+        ] = UNSET,
+        include: OptionalNullable[List[models_createresponseop.Include]] = UNSET,
+        parallel_tool_calls: OptionalNullable[bool] = UNSET,
+        store: OptionalNullable[bool] = True,
+        tools: Optional[
+            Union[
+                List[models_createresponseop.CreateResponseTools],
+                List[models_createresponseop.CreateResponseToolsTypedDict],
+            ]
+        ] = None,
+        tool_choice: Optional[
+            Union[
+                models_createresponseop.CreateResponseToolChoice,
+                models_createresponseop.CreateResponseToolChoiceTypedDict,
+            ]
+        ] = None,
+        stream: Optional[bool] = False,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+        accept_header_override: Optional[CreateAcceptEnum] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
+    ) -> models.CreateResponseResponse:
+        r"""Create response
+
+        Creates a model response for the given input.
+
+        :param model: ID of the model to use. You can use the List models API to see all of your available models.
+        :param input: The actual user input(s) for the model. Can be a simple string, or an array of structured input items (messages, tool outputs) representing a conversation history or complex input.
+        :param metadata: Developer-defined key-value pairs that will be included in response objects
+        :param temperature: 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.
+        :param top_p: 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.
+        :param previous_response_id: The ID of a previous response to continue the conversation from. The model will have access to the previous response context.
+        :param instructions: Developer-provided instructions that the model should follow. Overwrites the default system message.
+        :param reasoning: Configuration for reasoning models
+        :param max_output_tokens: The maximum number of tokens that can be generated in the response
+        :param text:
+        :param include: Specifies which (potentially large) fields to include in the response. By default, the results of Code Interpreter and file searches are excluded. Available options:
+            - code_interpreter_call.outputs: Include the outputs of Code Interpreter tool calls
+            - computer_call_output.output.image_url: Include the image URLs from computer use tool calls
+            - file_search_call.results: Include the results of file search tool calls
+            - message.input_image.image_url: Include URLs of input images
+            - message.output_text.logprobs: Include log probabilities for output text (when logprobs is enabled)
+            - reasoning.encrypted_content: Include encrypted reasoning content for reasoning models
+        :param parallel_tool_calls: Whether to enable parallel function calling during tool use.
+        :param store: Whether to store this response for use in distillations or evals.
+        :param tools: A list of tools the model may call. Use this to provide a list of functions the model may generate JSON inputs for.
+        :param tool_choice: How the model should select which tool (or tools) to use when generating a response. Can be a string (`none`, `auto`, `required`) or an object to force a specific tool.
+        :param stream:
+        :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 timeout_ms is None:
+            timeout_ms = 600000
+
+        if server_url is not None:
+            base_url = server_url
+        else:
+            base_url = self._get_url(base_url, url_variables)
+
+        request = models.CreateResponseRequestBody(
+            model=model,
+            metadata=metadata,
+            temperature=temperature,
+            top_p=top_p,
+            previous_response_id=previous_response_id,
+            instructions=instructions,
+            reasoning=utils.get_pydantic_model(
+                reasoning, OptionalNullable[models.Reasoning]
+            ),
+            max_output_tokens=max_output_tokens,
+            text=utils.get_pydantic_model(
+                text, OptionalNullable[models.CreateResponseText]
+            ),
+            input=utils.get_pydantic_model(input_, models.CreateResponseInput),
+            include=include,
+            parallel_tool_calls=parallel_tool_calls,
+            store=store,
+            tools=utils.get_pydantic_model(
+                tools, Optional[List[models.CreateResponseTools]]
+            ),
+            tool_choice=utils.get_pydantic_model(
+                tool_choice, Optional[models.CreateResponseToolChoice]
+            ),
+            stream=stream,
+        )
+
+        req = self._build_request(
+            method="POST",
+            path="/v2/router/responses",
+            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=accept_header_override.value
+            if accept_header_override is not None
+            else "application/json;q=1, text/event-stream;q=0",
+            http_headers=http_headers,
+            security=self.sdk_configuration.security,
+            get_serialized_body=lambda: utils.serialize_request_body(
+                request, False, False, "json", models.CreateResponseRequestBody
+            ),
+            allow_empty_value=None,
+            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="createResponse",
+                oauth2_scopes=None,
+                security_source=get_security_from_env(
+                    self.sdk_configuration.security, models.Security
+                ),
+            ),
+            request=req,
+            error_status_codes=["4XX", "5XX"],
+            stream=True,
+            retry_config=retry_config,
+        )
+
+        if utils.match_response(http_res, "200", "application/json"):
+            http_res_text = utils.stream_to_text(http_res)
+            return unmarshal_json_response(
+                models.CreateResponseResponseBody, 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.CreateResponseRouterResponsesResponseBody
+                ),
+                sentinel="[DONE]",
+                client_ref=self,
+            )
+        if utils.match_response(http_res, "4XX", "*"):
+            http_res_text = utils.stream_to_text(http_res)
+            raise models.APIError("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 models.APIError("API error occurred", http_res, http_res_text)
+
+        http_res_text = utils.stream_to_text(http_res)
+        raise models.APIError("Unexpected response received", http_res, http_res_text)
+
+    async def create_async(
+        self,
+        *,
+        model: str,
+        input_: Union[
+            models_createresponseop.CreateResponseInput,
+            models_createresponseop.CreateResponseInputTypedDict,
+        ],
+        metadata: Optional[Dict[str, str]] = None,
+        temperature: OptionalNullable[float] = UNSET,
+        top_p: OptionalNullable[float] = UNSET,
+        previous_response_id: OptionalNullable[str] = UNSET,
+        instructions: OptionalNullable[str] = UNSET,
+        reasoning: OptionalNullable[
+            Union[
+                models_createresponseop.Reasoning,
+                models_createresponseop.ReasoningTypedDict,
+            ]
+        ] = UNSET,
+        max_output_tokens: OptionalNullable[int] = UNSET,
+        text: OptionalNullable[
+            Union[
+                models_createresponseop.CreateResponseText,
+                models_createresponseop.CreateResponseTextTypedDict,
+            ]
+        ] = UNSET,
+        include: OptionalNullable[List[models_createresponseop.Include]] = UNSET,
+        parallel_tool_calls: OptionalNullable[bool] = UNSET,
+        store: OptionalNullable[bool] = True,
+        tools: Optional[
+            Union[
+                List[models_createresponseop.CreateResponseTools],
+                List[models_createresponseop.CreateResponseToolsTypedDict],
+            ]
+        ] = None,
+        tool_choice: Optional[
+            Union[
+                models_createresponseop.CreateResponseToolChoice,
+                models_createresponseop.CreateResponseToolChoiceTypedDict,
+            ]
+        ] = None,
+        stream: Optional[bool] = False,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+        accept_header_override: Optional[CreateAcceptEnum] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
+    ) -> models.CreateResponseResponse:
+        r"""Create response
+
+        Creates a model response for the given input.
+
+        :param model: ID of the model to use. You can use the List models API to see all of your available models.
+        :param input: The actual user input(s) for the model. Can be a simple string, or an array of structured input items (messages, tool outputs) representing a conversation history or complex input.
+        :param metadata: Developer-defined key-value pairs that will be included in response objects
+        :param temperature: 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.
+        :param top_p: 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.
+        :param previous_response_id: The ID of a previous response to continue the conversation from. The model will have access to the previous response context.
+        :param instructions: Developer-provided instructions that the model should follow. Overwrites the default system message.
+        :param reasoning: Configuration for reasoning models
+        :param max_output_tokens: The maximum number of tokens that can be generated in the response
+        :param text:
+        :param include: Specifies which (potentially large) fields to include in the response. By default, the results of Code Interpreter and file searches are excluded. Available options:
+            - code_interpreter_call.outputs: Include the outputs of Code Interpreter tool calls
+            - computer_call_output.output.image_url: Include the image URLs from computer use tool calls
+            - file_search_call.results: Include the results of file search tool calls
+            - message.input_image.image_url: Include URLs of input images
+            - message.output_text.logprobs: Include log probabilities for output text (when logprobs is enabled)
+            - reasoning.encrypted_content: Include encrypted reasoning content for reasoning models
+        :param parallel_tool_calls: Whether to enable parallel function calling during tool use.
+        :param store: Whether to store this response for use in distillations or evals.
+        :param tools: A list of tools the model may call. Use this to provide a list of functions the model may generate JSON inputs for.
+        :param tool_choice: How the model should select which tool (or tools) to use when generating a response. Can be a string (`none`, `auto`, `required`) or an object to force a specific tool.
+        :param stream:
+        :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 timeout_ms is None:
+            timeout_ms = 600000
+
+        if server_url is not None:
+            base_url = server_url
+        else:
+            base_url = self._get_url(base_url, url_variables)
+
+        request = models.CreateResponseRequestBody(
+            model=model,
+            metadata=metadata,
+            temperature=temperature,
+            top_p=top_p,
+            previous_response_id=previous_response_id,
+            instructions=instructions,
+            reasoning=utils.get_pydantic_model(
+                reasoning, OptionalNullable[models.Reasoning]
+            ),
+            max_output_tokens=max_output_tokens,
+            text=utils.get_pydantic_model(
+                text, OptionalNullable[models.CreateResponseText]
+            ),
+            input=utils.get_pydantic_model(input_, models.CreateResponseInput),
+            include=include,
+            parallel_tool_calls=parallel_tool_calls,
+            store=store,
+            tools=utils.get_pydantic_model(
+                tools, Optional[List[models.CreateResponseTools]]
+            ),
+            tool_choice=utils.get_pydantic_model(
+                tool_choice, Optional[models.CreateResponseToolChoice]
+            ),
+            stream=stream,
+        )
+
+        req = self._build_request_async(
+            method="POST",
+            path="/v2/router/responses",
+            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=accept_header_override.value
+            if accept_header_override is not None
+            else "application/json;q=1, text/event-stream;q=0",
+            http_headers=http_headers,
+            security=self.sdk_configuration.security,
+            get_serialized_body=lambda: utils.serialize_request_body(
+                request, False, False, "json", models.CreateResponseRequestBody
+            ),
+            allow_empty_value=None,
+            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="createResponse",
+                oauth2_scopes=None,
+                security_source=get_security_from_env(
+                    self.sdk_configuration.security, models.Security
+                ),
+            ),
+            request=req,
+            error_status_codes=["4XX", "5XX"],
+            stream=True,
+            retry_config=retry_config,
+        )
+
+        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.CreateResponseResponseBody, 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.CreateResponseRouterResponsesResponseBody
+                ),
+                sentinel="[DONE]",
+                client_ref=self,
+            )
+        if utils.match_response(http_res, "4XX", "*"):
+            http_res_text = await utils.stream_to_text_async(http_res)
+            raise models.APIError("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 models.APIError("API error occurred", http_res, http_res_text)
+
+        http_res_text = await utils.stream_to_text_async(http_res)
+        raise models.APIError("Unexpected response received", http_res, http_res_text)