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

orq_ai_sdk/models/createembeddingop.py

@@ -0,0 +1,579 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from .publiccontact import PublicContact, PublicContactTypedDict
+from .publicidentity import PublicIdentity, PublicIdentityTypedDict
+from orq_ai_sdk.types import BaseModel, UNSET_SENTINEL
+import pydantic
+from pydantic import model_serializer
+from typing import List, Literal, Optional, Union
+from typing_extensions import Annotated, NotRequired, TypeAliasType, TypedDict
+
+
+CreateEmbeddingInputTypedDict = TypeAliasType(
+    "CreateEmbeddingInputTypedDict", Union[str, List[str]]
+)
+r"""Input text to embed, encoded as a string or array of tokens."""
+
+
+CreateEmbeddingInput = TypeAliasType("CreateEmbeddingInput", Union[str, List[str]])
+r"""Input text to embed, encoded as a string or array of tokens."""
+
+
+EncodingFormat = Literal[
+    "base64",
+    "float",
+]
+r"""Type of the document element"""
+
+
+class CreateEmbeddingFallbacksTypedDict(TypedDict):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class CreateEmbeddingFallbacks(BaseModel):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class CreateEmbeddingRetryTypedDict(TypedDict):
+    r"""Retry configuration for the request"""
+
+    count: NotRequired[float]
+    r"""Number of retry attempts (1-5)"""
+    on_codes: NotRequired[List[float]]
+    r"""HTTP status codes that trigger retry logic"""
+
+
+class CreateEmbeddingRetry(BaseModel):
+    r"""Retry configuration for the request"""
+
+    count: Optional[float] = 3
+    r"""Number of retry attempts (1-5)"""
+
+    on_codes: Optional[List[float]] = None
+    r"""HTTP status codes that trigger retry logic"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["count", "on_codes"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+CreateEmbeddingType = Literal["exact_match",]
+
+
+class CreateEmbeddingCacheTypedDict(TypedDict):
+    r"""Cache configuration for the request."""
+
+    type: CreateEmbeddingType
+    ttl: NotRequired[float]
+    r"""Time to live for cached responses in seconds. Maximum 259200 seconds (3 days)."""
+
+
+class CreateEmbeddingCache(BaseModel):
+    r"""Cache configuration for the request."""
+
+    type: CreateEmbeddingType
+
+    ttl: Optional[float] = 1800
+    r"""Time to live for cached responses in seconds. Maximum 259200 seconds (3 days)."""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["ttl"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+CreateEmbeddingLoadBalancerType = Literal["weight_based",]
+
+
+class CreateEmbeddingLoadBalancerModelsTypedDict(TypedDict):
+    model: str
+    r"""Model identifier for load balancing"""
+    weight: NotRequired[float]
+    r"""Weight assigned to this model for load balancing"""
+
+
+class CreateEmbeddingLoadBalancerModels(BaseModel):
+    model: str
+    r"""Model identifier for load balancing"""
+
+    weight: Optional[float] = 0.5
+    r"""Weight assigned to this model for load balancing"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["weight"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class CreateEmbeddingLoadBalancer1TypedDict(TypedDict):
+    type: CreateEmbeddingLoadBalancerType
+    models: List[CreateEmbeddingLoadBalancerModelsTypedDict]
+
+
+class CreateEmbeddingLoadBalancer1(BaseModel):
+    type: CreateEmbeddingLoadBalancerType
+
+    models: List[CreateEmbeddingLoadBalancerModels]
+
+
+CreateEmbeddingLoadBalancerTypedDict = CreateEmbeddingLoadBalancer1TypedDict
+r"""Load balancer configuration for the request."""
+
+
+CreateEmbeddingLoadBalancer = CreateEmbeddingLoadBalancer1
+r"""Load balancer configuration for the request."""
+
+
+class CreateEmbeddingTimeoutTypedDict(TypedDict):
+    r"""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."""
+
+    call_timeout: float
+    r"""Timeout value in milliseconds"""
+
+
+class CreateEmbeddingTimeout(BaseModel):
+    r"""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."""
+
+    call_timeout: float
+    r"""Timeout value in milliseconds"""
+
+
+class CreateEmbeddingRouterEmbeddingsFallbacksTypedDict(TypedDict):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class CreateEmbeddingRouterEmbeddingsFallbacks(BaseModel):
+    model: str
+    r"""Fallback model identifier"""
+
+
+CreateEmbeddingRouterEmbeddingsType = Literal["exact_match",]
+
+
+class CreateEmbeddingRouterEmbeddingsCacheTypedDict(TypedDict):
+    r"""Cache configuration for the request."""
+
+    type: CreateEmbeddingRouterEmbeddingsType
+    ttl: NotRequired[float]
+    r"""Time to live for cached responses in seconds. Maximum 259200 seconds (3 days)."""
+
+
+class CreateEmbeddingRouterEmbeddingsCache(BaseModel):
+    r"""Cache configuration for the request."""
+
+    type: CreateEmbeddingRouterEmbeddingsType
+
+    ttl: Optional[float] = 1800
+    r"""Time to live for cached responses in seconds. Maximum 259200 seconds (3 days)."""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["ttl"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class CreateEmbeddingRouterEmbeddingsRetryTypedDict(TypedDict):
+    r"""Retry configuration for the request"""
+
+    count: NotRequired[float]
+    r"""Number of retry attempts (1-5)"""
+    on_codes: NotRequired[List[float]]
+    r"""HTTP status codes that trigger retry logic"""
+
+
+class CreateEmbeddingRouterEmbeddingsRetry(BaseModel):
+    r"""Retry configuration for the request"""
+
+    count: Optional[float] = 3
+    r"""Number of retry attempts (1-5)"""
+
+    on_codes: Optional[List[float]] = None
+    r"""HTTP status codes that trigger retry logic"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["count", "on_codes"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+CreateEmbeddingLoadBalancerRouterEmbeddingsType = Literal["weight_based",]
+
+
+class CreateEmbeddingLoadBalancerRouterEmbeddingsModelsTypedDict(TypedDict):
+    model: str
+    r"""Model identifier for load balancing"""
+    weight: NotRequired[float]
+    r"""Weight assigned to this model for load balancing"""
+
+
+class CreateEmbeddingLoadBalancerRouterEmbeddingsModels(BaseModel):
+    model: str
+    r"""Model identifier for load balancing"""
+
+    weight: Optional[float] = 0.5
+    r"""Weight assigned to this model for load balancing"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["weight"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class CreateEmbeddingLoadBalancerRouterEmbeddings1TypedDict(TypedDict):
+    type: CreateEmbeddingLoadBalancerRouterEmbeddingsType
+    models: List[CreateEmbeddingLoadBalancerRouterEmbeddingsModelsTypedDict]
+
+
+class CreateEmbeddingLoadBalancerRouterEmbeddings1(BaseModel):
+    type: CreateEmbeddingLoadBalancerRouterEmbeddingsType
+
+    models: List[CreateEmbeddingLoadBalancerRouterEmbeddingsModels]
+
+
+CreateEmbeddingRouterEmbeddingsLoadBalancerTypedDict = (
+    CreateEmbeddingLoadBalancerRouterEmbeddings1TypedDict
+)
+r"""Array of models with weights for load balancing requests"""
+
+
+CreateEmbeddingRouterEmbeddingsLoadBalancer = (
+    CreateEmbeddingLoadBalancerRouterEmbeddings1
+)
+r"""Array of models with weights for load balancing requests"""
+
+
+class CreateEmbeddingRouterEmbeddingsTimeoutTypedDict(TypedDict):
+    r"""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."""
+
+    call_timeout: float
+    r"""Timeout value in milliseconds"""
+
+
+class CreateEmbeddingRouterEmbeddingsTimeout(BaseModel):
+    r"""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."""
+
+    call_timeout: float
+    r"""Timeout value in milliseconds"""
+
+
+class CreateEmbeddingOrqTypedDict(TypedDict):
+    name: NotRequired[str]
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
+    fallbacks: NotRequired[List[CreateEmbeddingRouterEmbeddingsFallbacksTypedDict]]
+    r"""Array of fallback models to use if primary model fails"""
+    cache: NotRequired[CreateEmbeddingRouterEmbeddingsCacheTypedDict]
+    r"""Cache configuration for the request."""
+    retry: NotRequired[CreateEmbeddingRouterEmbeddingsRetryTypedDict]
+    r"""Retry configuration for the request"""
+    identity: NotRequired[PublicIdentityTypedDict]
+    r"""Information about the identity making the request. If the identity does not exist, it will be created automatically."""
+    contact: NotRequired[PublicContactTypedDict]
+    r"""@deprecated Use identity instead. Information about the contact making the request."""
+    load_balancer: NotRequired[CreateEmbeddingRouterEmbeddingsLoadBalancerTypedDict]
+    r"""Array of models with weights for load balancing requests"""
+    timeout: NotRequired[CreateEmbeddingRouterEmbeddingsTimeoutTypedDict]
+    r"""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."""
+
+
+class CreateEmbeddingOrq(BaseModel):
+    name: Optional[str] = None
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
+
+    fallbacks: Optional[List[CreateEmbeddingRouterEmbeddingsFallbacks]] = None
+    r"""Array of fallback models to use if primary model fails"""
+
+    cache: Optional[CreateEmbeddingRouterEmbeddingsCache] = None
+    r"""Cache configuration for the request."""
+
+    retry: Optional[CreateEmbeddingRouterEmbeddingsRetry] = None
+    r"""Retry configuration for the request"""
+
+    identity: Optional[PublicIdentity] = None
+    r"""Information about the identity making the request. If the identity does not exist, it will be created automatically."""
+
+    contact: Annotated[
+        Optional[PublicContact],
+        pydantic.Field(
+            deprecated="warning: ** DEPRECATED ** - This will be removed in a future release, please migrate away from it as soon as possible."
+        ),
+    ] = None
+    r"""@deprecated Use identity instead. Information about the contact making the request."""
+
+    load_balancer: Optional[CreateEmbeddingRouterEmbeddingsLoadBalancer] = None
+    r"""Array of models with weights for load balancing requests"""
+
+    timeout: Optional[CreateEmbeddingRouterEmbeddingsTimeout] = None
+    r"""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."""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(
+            [
+                "name",
+                "fallbacks",
+                "cache",
+                "retry",
+                "identity",
+                "contact",
+                "load_balancer",
+                "timeout",
+            ]
+        )
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class CreateEmbeddingRequestBodyTypedDict(TypedDict):
+    r"""input"""
+
+    input: CreateEmbeddingInputTypedDict
+    r"""Input text to embed, encoded as a string or array of tokens."""
+    model: str
+    r"""ID of the model to use"""
+    encoding_format: NotRequired[EncodingFormat]
+    r"""Type of the document element"""
+    dimensions: NotRequired[float]
+    r"""The number of dimensions the resulting output embeddings should have."""
+    user: NotRequired[str]
+    r"""A unique identifier representing your end-user"""
+    name: NotRequired[str]
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
+    fallbacks: NotRequired[List[CreateEmbeddingFallbacksTypedDict]]
+    r"""Array of fallback models to use if primary model fails"""
+    retry: NotRequired[CreateEmbeddingRetryTypedDict]
+    r"""Retry configuration for the request"""
+    cache: NotRequired[CreateEmbeddingCacheTypedDict]
+    r"""Cache configuration for the request."""
+    load_balancer: NotRequired[CreateEmbeddingLoadBalancerTypedDict]
+    r"""Load balancer configuration for the request."""
+    timeout: NotRequired[CreateEmbeddingTimeoutTypedDict]
+    r"""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."""
+    orq: NotRequired[CreateEmbeddingOrqTypedDict]
+
+
+class CreateEmbeddingRequestBody(BaseModel):
+    r"""input"""
+
+    input: CreateEmbeddingInput
+    r"""Input text to embed, encoded as a string or array of tokens."""
+
+    model: str
+    r"""ID of the model to use"""
+
+    encoding_format: Optional[EncodingFormat] = "float"
+    r"""Type of the document element"""
+
+    dimensions: Optional[float] = None
+    r"""The number of dimensions the resulting output embeddings should have."""
+
+    user: Optional[str] = None
+    r"""A unique identifier representing your end-user"""
+
+    name: Optional[str] = None
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
+
+    fallbacks: Optional[List[CreateEmbeddingFallbacks]] = None
+    r"""Array of fallback models to use if primary model fails"""
+
+    retry: Optional[CreateEmbeddingRetry] = None
+    r"""Retry configuration for the request"""
+
+    cache: Optional[CreateEmbeddingCache] = None
+    r"""Cache configuration for the request."""
+
+    load_balancer: Optional[CreateEmbeddingLoadBalancer] = None
+    r"""Load balancer configuration for the request."""
+
+    timeout: Optional[CreateEmbeddingTimeout] = None
+    r"""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."""
+
+    orq: Optional[CreateEmbeddingOrq] = None
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(
+            [
+                "encoding_format",
+                "dimensions",
+                "user",
+                "name",
+                "fallbacks",
+                "retry",
+                "cache",
+                "load_balancer",
+                "timeout",
+                "orq",
+            ]
+        )
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+CreateEmbeddingObject = Literal["list",]
+
+
+CreateEmbeddingRouterEmbeddingsObject = Literal["embedding",]
+r"""The object type, which is always `embedding`."""
+
+
+EmbeddingTypedDict = TypeAliasType("EmbeddingTypedDict", Union[List[float], str])
+r"""The embedding vector, which is a list of floats. The length of vector depends on the model."""
+
+
+Embedding = TypeAliasType("Embedding", Union[List[float], str])
+r"""The embedding vector, which is a list of floats. The length of vector depends on the model."""
+
+
+class CreateEmbeddingDataTypedDict(TypedDict):
+    object: CreateEmbeddingRouterEmbeddingsObject
+    r"""The object type, which is always `embedding`."""
+    embedding: EmbeddingTypedDict
+    r"""The embedding vector, which is a list of floats. The length of vector depends on the model."""
+    index: float
+    r"""The index of the embedding in the list of embeddings."""
+
+
+class CreateEmbeddingData(BaseModel):
+    object: CreateEmbeddingRouterEmbeddingsObject
+    r"""The object type, which is always `embedding`."""
+
+    embedding: Embedding
+    r"""The embedding vector, which is a list of floats. The length of vector depends on the model."""
+
+    index: float
+    r"""The index of the embedding in the list of embeddings."""
+
+
+class CreateEmbeddingUsageTypedDict(TypedDict):
+    r"""The usage information for the request."""
+
+    prompt_tokens: float
+    r"""The number of tokens used by the prompt."""
+    total_tokens: float
+    r"""The total number of tokens used by the request."""
+
+
+class CreateEmbeddingUsage(BaseModel):
+    r"""The usage information for the request."""
+
+    prompt_tokens: float
+    r"""The number of tokens used by the prompt."""
+
+    total_tokens: float
+    r"""The total number of tokens used by the request."""
+
+
+class CreateEmbeddingResponseBodyTypedDict(TypedDict):
+    r"""Returns the embedding vector."""
+
+    object: CreateEmbeddingObject
+    data: List[CreateEmbeddingDataTypedDict]
+    model: str
+    r"""ID of the model to used."""
+    usage: CreateEmbeddingUsageTypedDict
+    r"""The usage information for the request."""
+
+
+class CreateEmbeddingResponseBody(BaseModel):
+    r"""Returns the embedding vector."""
+
+    object: CreateEmbeddingObject
+
+    data: List[CreateEmbeddingData]
+
+    model: str
+    r"""ID of the model to used."""
+
+    usage: CreateEmbeddingUsage
+    r"""The usage information for the request."""