orq-ai-sdk 4.2.0rc28__py3-none-any.whl → 4.3.0rc7__py3-none-any.whl

orq_ai_sdk/completions.py

@@ -0,0 +1,438 @@
+"""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 createcompletionop as models_createcompletionop
+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 List, Mapping, Optional, Union
+
+
+class CreateAcceptEnum(str, Enum):
+    APPLICATION_JSON = "application/json"
+    TEXT_EVENT_STREAM = "text/event-stream"
+
+
+class Completions(BaseSDK):
+    def create(
+        self,
+        *,
+        model: str,
+        prompt: str,
+        echo: OptionalNullable[bool] = False,
+        frequency_penalty: OptionalNullable[float] = 0,
+        max_tokens: OptionalNullable[float] = 16,
+        presence_penalty: OptionalNullable[float] = 0,
+        seed: OptionalNullable[float] = UNSET,
+        stop: OptionalNullable[
+            Union[
+                models_createcompletionop.CreateCompletionStop,
+                models_createcompletionop.CreateCompletionStopTypedDict,
+            ]
+        ] = UNSET,
+        temperature: OptionalNullable[float] = 1,
+        top_p: OptionalNullable[float] = 1,
+        n: OptionalNullable[float] = 1,
+        user: Optional[str] = None,
+        name: Optional[str] = None,
+        fallbacks: Optional[
+            Union[
+                List[models_createcompletionop.CreateCompletionFallbacks],
+                List[models_createcompletionop.CreateCompletionFallbacksTypedDict],
+            ]
+        ] = None,
+        retry: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionRetry,
+                models_createcompletionop.CreateCompletionRetryTypedDict,
+            ]
+        ] = None,
+        cache: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionCache,
+                models_createcompletionop.CreateCompletionCacheTypedDict,
+            ]
+        ] = None,
+        load_balancer: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionLoadBalancer,
+                models_createcompletionop.CreateCompletionLoadBalancerTypedDict,
+            ]
+        ] = None,
+        timeout: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionTimeout,
+                models_createcompletionop.CreateCompletionTimeoutTypedDict,
+            ]
+        ] = None,
+        orq: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionOrq,
+                models_createcompletionop.CreateCompletionOrqTypedDict,
+            ]
+        ] = 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.CreateCompletionResponse:
+        r"""Create completion
+
+        For sending requests to legacy completion models
+
+        :param model: ID of the model to use
+        :param prompt: The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.
+        :param echo: Echo back the prompt in addition to the completion
+        :param frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
+        :param max_tokens: The maximum number of tokens that can be generated in the completion.
+        :param presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
+        :param seed: If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
+        :param stop: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
+        :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 n: How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota.
+        :param user: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
+        :param name: The name to display on the trace. If not specified, the default system name will be used.
+        :param fallbacks: Array of fallback models to use if primary model fails
+        :param retry: Retry configuration for the request
+        :param cache: Cache configuration for the request.
+        :param load_balancer: Load balancer configuration for the request.
+        :param timeout: Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured.
+        :param orq: Leverage Orq's intelligent routing capabilities to enhance your AI application with enterprise-grade reliability and observability. Orq provides automatic request management including retries on failures, model fallbacks for high availability, identity-level analytics tracking, conversation threading, and dynamic prompt templating with variable substitution.
+        :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.CreateCompletionRequestBody(
+            model=model,
+            prompt=prompt,
+            echo=echo,
+            frequency_penalty=frequency_penalty,
+            max_tokens=max_tokens,
+            presence_penalty=presence_penalty,
+            seed=seed,
+            stop=stop,
+            temperature=temperature,
+            top_p=top_p,
+            n=n,
+            user=user,
+            name=name,
+            fallbacks=utils.get_pydantic_model(
+                fallbacks, Optional[List[models.CreateCompletionFallbacks]]
+            ),
+            retry=utils.get_pydantic_model(
+                retry, Optional[models.CreateCompletionRetry]
+            ),
+            cache=utils.get_pydantic_model(
+                cache, Optional[models.CreateCompletionCache]
+            ),
+            load_balancer=utils.get_pydantic_model(
+                load_balancer, Optional[models.CreateCompletionLoadBalancer]
+            ),
+            timeout=utils.get_pydantic_model(
+                timeout, Optional[models.CreateCompletionTimeout]
+            ),
+            orq=utils.get_pydantic_model(orq, Optional[models.CreateCompletionOrq]),
+            stream=stream,
+        )
+
+        req = self._build_request(
+            method="POST",
+            path="/v2/router/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=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.CreateCompletionRequestBody
+            ),
+            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="createCompletion",
+                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.CreateCompletionResponseBody, 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.CreateCompletionRouterCompletionsResponseBody
+                ),
+                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,
+        prompt: str,
+        echo: OptionalNullable[bool] = False,
+        frequency_penalty: OptionalNullable[float] = 0,
+        max_tokens: OptionalNullable[float] = 16,
+        presence_penalty: OptionalNullable[float] = 0,
+        seed: OptionalNullable[float] = UNSET,
+        stop: OptionalNullable[
+            Union[
+                models_createcompletionop.CreateCompletionStop,
+                models_createcompletionop.CreateCompletionStopTypedDict,
+            ]
+        ] = UNSET,
+        temperature: OptionalNullable[float] = 1,
+        top_p: OptionalNullable[float] = 1,
+        n: OptionalNullable[float] = 1,
+        user: Optional[str] = None,
+        name: Optional[str] = None,
+        fallbacks: Optional[
+            Union[
+                List[models_createcompletionop.CreateCompletionFallbacks],
+                List[models_createcompletionop.CreateCompletionFallbacksTypedDict],
+            ]
+        ] = None,
+        retry: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionRetry,
+                models_createcompletionop.CreateCompletionRetryTypedDict,
+            ]
+        ] = None,
+        cache: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionCache,
+                models_createcompletionop.CreateCompletionCacheTypedDict,
+            ]
+        ] = None,
+        load_balancer: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionLoadBalancer,
+                models_createcompletionop.CreateCompletionLoadBalancerTypedDict,
+            ]
+        ] = None,
+        timeout: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionTimeout,
+                models_createcompletionop.CreateCompletionTimeoutTypedDict,
+            ]
+        ] = None,
+        orq: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionOrq,
+                models_createcompletionop.CreateCompletionOrqTypedDict,
+            ]
+        ] = 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.CreateCompletionResponse:
+        r"""Create completion
+
+        For sending requests to legacy completion models
+
+        :param model: ID of the model to use
+        :param prompt: The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.
+        :param echo: Echo back the prompt in addition to the completion
+        :param frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
+        :param max_tokens: The maximum number of tokens that can be generated in the completion.
+        :param presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
+        :param seed: If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
+        :param stop: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
+        :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 n: How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota.
+        :param user: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
+        :param name: The name to display on the trace. If not specified, the default system name will be used.
+        :param fallbacks: Array of fallback models to use if primary model fails
+        :param retry: Retry configuration for the request
+        :param cache: Cache configuration for the request.
+        :param load_balancer: Load balancer configuration for the request.
+        :param timeout: Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured.
+        :param orq: Leverage Orq's intelligent routing capabilities to enhance your AI application with enterprise-grade reliability and observability. Orq provides automatic request management including retries on failures, model fallbacks for high availability, identity-level analytics tracking, conversation threading, and dynamic prompt templating with variable substitution.
+        :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.CreateCompletionRequestBody(
+            model=model,
+            prompt=prompt,
+            echo=echo,
+            frequency_penalty=frequency_penalty,
+            max_tokens=max_tokens,
+            presence_penalty=presence_penalty,
+            seed=seed,
+            stop=stop,
+            temperature=temperature,
+            top_p=top_p,
+            n=n,
+            user=user,
+            name=name,
+            fallbacks=utils.get_pydantic_model(
+                fallbacks, Optional[List[models.CreateCompletionFallbacks]]
+            ),
+            retry=utils.get_pydantic_model(
+                retry, Optional[models.CreateCompletionRetry]
+            ),
+            cache=utils.get_pydantic_model(
+                cache, Optional[models.CreateCompletionCache]
+            ),
+            load_balancer=utils.get_pydantic_model(
+                load_balancer, Optional[models.CreateCompletionLoadBalancer]
+            ),
+            timeout=utils.get_pydantic_model(
+                timeout, Optional[models.CreateCompletionTimeout]
+            ),
+            orq=utils.get_pydantic_model(orq, Optional[models.CreateCompletionOrq]),
+            stream=stream,
+        )
+
+        req = self._build_request_async(
+            method="POST",
+            path="/v2/router/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=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.CreateCompletionRequestBody
+            ),
+            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="createCompletion",
+                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.CreateCompletionResponseBody, 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.CreateCompletionRouterCompletionsResponseBody
+                ),
+                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)