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

orq_ai_sdk/models/getonepromptop.py

@@ -68,6 +68,7 @@ GetOnePromptModelType = Literal[
     "tts",
     "stt",
     "rerank",
+    "ocr",
     "moderation",
     "vision",
 ]
@@ -666,7 +667,7 @@ GetOnePromptContent = TypeAliasType(
 r"""The contents of the user message. Either the text content of the message or an array of content parts with a defined type, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Can be null for tool messages in certain scenarios."""
 
 
-GetOnePromptPromptsType = Literal["function",]
+GetOnePromptPromptsResponseType = Literal["function",]
 
 
 class GetOnePromptFunctionTypedDict(TypedDict):
@@ -683,14 +684,14 @@ class GetOnePromptFunction(BaseModel):
 
 
 class GetOnePromptToolCallsTypedDict(TypedDict):
-    type: GetOnePromptPromptsType
+    type: GetOnePromptPromptsResponseType
     function: GetOnePromptFunctionTypedDict
     id: NotRequired[str]
     index: NotRequired[float]
 
 
 class GetOnePromptToolCalls(BaseModel):
-    type: GetOnePromptPromptsType
+    type: GetOnePromptPromptsResponseType
 
     function: GetOnePromptFunction
 
@@ -1197,6 +1198,154 @@ class GetOnePromptGuardrails(BaseModel):
     r"""Determines whether the guardrail runs on the input (user message) or output (model response)."""
 
 
+class GetOnePromptFallbacksTypedDict(TypedDict):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class GetOnePromptFallbacks(BaseModel):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class GetOnePromptRetryTypedDict(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 GetOnePromptRetry(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
+
+
+GetOnePromptPromptsType = Literal["exact_match",]
+
+
+class GetOnePromptCacheTypedDict(TypedDict):
+    r"""Cache configuration for the request."""
+
+    type: GetOnePromptPromptsType
+    ttl: NotRequired[float]
+    r"""Time to live for cached responses in seconds. Maximum 259200 seconds (3 days)."""
+
+
+class GetOnePromptCache(BaseModel):
+    r"""Cache configuration for the request."""
+
+    type: GetOnePromptPromptsType
+
+    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
+
+
+GetOnePromptLoadBalancerType = Literal["weight_based",]
+
+
+class GetOnePromptLoadBalancerModelsTypedDict(TypedDict):
+    model: str
+    r"""Model identifier for load balancing"""
+    weight: NotRequired[float]
+    r"""Weight assigned to this model for load balancing"""
+
+
+class GetOnePromptLoadBalancerModels(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 GetOnePromptLoadBalancer1TypedDict(TypedDict):
+    type: GetOnePromptLoadBalancerType
+    models: List[GetOnePromptLoadBalancerModelsTypedDict]
+
+
+class GetOnePromptLoadBalancer1(BaseModel):
+    type: GetOnePromptLoadBalancerType
+
+    models: List[GetOnePromptLoadBalancerModels]
+
+
+GetOnePromptLoadBalancerTypedDict = GetOnePromptLoadBalancer1TypedDict
+r"""Load balancer configuration for the request."""
+
+
+GetOnePromptLoadBalancer = GetOnePromptLoadBalancer1
+r"""Load balancer configuration for the request."""
+
+
+class GetOnePromptTimeoutTypedDict(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 GetOnePromptTimeout(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"""
+
+
 GetOnePromptMessagesPromptsResponse200Role = Literal["tool",]
 r"""The role of the messages author, in this case tool."""
 
@@ -1772,6 +1921,8 @@ GetOnePromptPromptsMessages = Annotated[
 class GetOnePromptPromptFieldTypedDict(TypedDict):
     r"""Prompt configuration with model and messages. Use this instead of prompt_config."""
 
+    name: NotRequired[str]
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
     audio: NotRequired[Nullable[GetOnePromptAudioTypedDict]]
     r"""Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]. Learn more."""
     frequency_penalty: NotRequired[Nullable[float]]
@@ -1826,6 +1977,16 @@ class GetOnePromptPromptFieldTypedDict(TypedDict):
     r"""Output types that you would like the model to generate. Most models are capable of generating text, which is the default: [\"text\"]. The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use: [\"text\", \"audio\"]."""
     guardrails: NotRequired[List[GetOnePromptGuardrailsTypedDict]]
     r"""A list of guardrails to apply to the request."""
+    fallbacks: NotRequired[List[GetOnePromptFallbacksTypedDict]]
+    r"""Array of fallback models to use if primary model fails"""
+    retry: NotRequired[GetOnePromptRetryTypedDict]
+    r"""Retry configuration for the request"""
+    cache: NotRequired[GetOnePromptCacheTypedDict]
+    r"""Cache configuration for the request."""
+    load_balancer: NotRequired[GetOnePromptLoadBalancerTypedDict]
+    r"""Load balancer configuration for the request."""
+    timeout: NotRequired[GetOnePromptTimeoutTypedDict]
+    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."""
     messages: NotRequired[List[GetOnePromptPromptsMessagesTypedDict]]
     r"""Array of messages that make up the conversation. Each message has a role (system, user, assistant, or tool) and content."""
     model: NotRequired[Nullable[str]]
@@ -1836,6 +1997,9 @@ class GetOnePromptPromptFieldTypedDict(TypedDict):
 class GetOnePromptPromptField(BaseModel):
     r"""Prompt configuration with model and messages. Use this instead of prompt_config."""
 
+    name: Optional[str] = None
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
+
     audio: OptionalNullable[GetOnePromptAudio] = UNSET
     r"""Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]. Learn more."""
 
@@ -1912,6 +2076,21 @@ class GetOnePromptPromptField(BaseModel):
     guardrails: Optional[List[GetOnePromptGuardrails]] = None
     r"""A list of guardrails to apply to the request."""
 
+    fallbacks: Optional[List[GetOnePromptFallbacks]] = None
+    r"""Array of fallback models to use if primary model fails"""
+
+    retry: Optional[GetOnePromptRetry] = None
+    r"""Retry configuration for the request"""
+
+    cache: Optional[GetOnePromptCache] = None
+    r"""Cache configuration for the request."""
+
+    load_balancer: Optional[GetOnePromptLoadBalancer] = None
+    r"""Load balancer configuration for the request."""
+
+    timeout: Optional[GetOnePromptTimeout] = 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."""
+
     messages: Optional[List[GetOnePromptPromptsMessages]] = None
     r"""Array of messages that make up the conversation. Each message has a role (system, user, assistant, or tool) and content."""
 
@@ -1924,6 +2103,7 @@ class GetOnePromptPromptField(BaseModel):
     def serialize_model(self, handler):
         optional_fields = set(
             [
+                "name",
                 "audio",
                 "frequency_penalty",
                 "max_tokens",
@@ -1946,6 +2126,11 @@ class GetOnePromptPromptField(BaseModel):
                 "parallel_tool_calls",
                 "modalities",
                 "guardrails",
+                "fallbacks",
+                "retry",
+                "cache",
+                "load_balancer",
+                "timeout",
                 "messages",
                 "model",
                 "version",

orq_ai_sdk/models/getpromptversionop.py

@@ -97,6 +97,7 @@ GetPromptVersionModelType = Literal[
     "tts",
     "stt",
     "rerank",
+    "ocr",
     "moderation",
     "vision",
 ]
@@ -707,7 +708,7 @@ GetPromptVersionContent = TypeAliasType(
 r"""The contents of the user message. Either the text content of the message or an array of content parts with a defined type, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Can be null for tool messages in certain scenarios."""
 
 
-GetPromptVersionType = Literal["function",]
+GetPromptVersionPromptsType = Literal["function",]
 
 
 class GetPromptVersionFunctionTypedDict(TypedDict):
@@ -724,14 +725,14 @@ class GetPromptVersionFunction(BaseModel):
 
 
 class GetPromptVersionToolCallsTypedDict(TypedDict):
-    type: GetPromptVersionType
+    type: GetPromptVersionPromptsType
     function: GetPromptVersionFunctionTypedDict
     id: NotRequired[str]
     index: NotRequired[float]
 
 
 class GetPromptVersionToolCalls(BaseModel):
-    type: GetPromptVersionType
+    type: GetPromptVersionPromptsType
 
     function: GetPromptVersionFunction
 
@@ -1241,6 +1242,154 @@ class GetPromptVersionGuardrails(BaseModel):
     r"""Determines whether the guardrail runs on the input (user message) or output (model response)."""
 
 
+class GetPromptVersionFallbacksTypedDict(TypedDict):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class GetPromptVersionFallbacks(BaseModel):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class GetPromptVersionRetryTypedDict(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 GetPromptVersionRetry(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
+
+
+GetPromptVersionType = Literal["exact_match",]
+
+
+class GetPromptVersionCacheTypedDict(TypedDict):
+    r"""Cache configuration for the request."""
+
+    type: GetPromptVersionType
+    ttl: NotRequired[float]
+    r"""Time to live for cached responses in seconds. Maximum 259200 seconds (3 days)."""
+
+
+class GetPromptVersionCache(BaseModel):
+    r"""Cache configuration for the request."""
+
+    type: GetPromptVersionType
+
+    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
+
+
+GetPromptVersionLoadBalancerType = Literal["weight_based",]
+
+
+class GetPromptVersionLoadBalancerModelsTypedDict(TypedDict):
+    model: str
+    r"""Model identifier for load balancing"""
+    weight: NotRequired[float]
+    r"""Weight assigned to this model for load balancing"""
+
+
+class GetPromptVersionLoadBalancerModels(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 GetPromptVersionLoadBalancer1TypedDict(TypedDict):
+    type: GetPromptVersionLoadBalancerType
+    models: List[GetPromptVersionLoadBalancerModelsTypedDict]
+
+
+class GetPromptVersionLoadBalancer1(BaseModel):
+    type: GetPromptVersionLoadBalancerType
+
+    models: List[GetPromptVersionLoadBalancerModels]
+
+
+GetPromptVersionLoadBalancerTypedDict = GetPromptVersionLoadBalancer1TypedDict
+r"""Load balancer configuration for the request."""
+
+
+GetPromptVersionLoadBalancer = GetPromptVersionLoadBalancer1
+r"""Load balancer configuration for the request."""
+
+
+class GetPromptVersionTimeoutTypedDict(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 GetPromptVersionTimeout(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"""
+
+
 GetPromptVersionMessagesPromptsResponse200Role = Literal["tool",]
 r"""The role of the messages author, in this case tool."""
 
@@ -1819,6 +1968,8 @@ GetPromptVersionPromptsMessages = Annotated[
 class GetPromptVersionPromptFieldTypedDict(TypedDict):
     r"""Prompt configuration with model and messages. Use this instead of prompt_config."""
 
+    name: NotRequired[str]
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
     audio: NotRequired[Nullable[GetPromptVersionAudioTypedDict]]
     r"""Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]. Learn more."""
     frequency_penalty: NotRequired[Nullable[float]]
@@ -1873,6 +2024,16 @@ class GetPromptVersionPromptFieldTypedDict(TypedDict):
     r"""Output types that you would like the model to generate. Most models are capable of generating text, which is the default: [\"text\"]. The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use: [\"text\", \"audio\"]."""
     guardrails: NotRequired[List[GetPromptVersionGuardrailsTypedDict]]
     r"""A list of guardrails to apply to the request."""
+    fallbacks: NotRequired[List[GetPromptVersionFallbacksTypedDict]]
+    r"""Array of fallback models to use if primary model fails"""
+    retry: NotRequired[GetPromptVersionRetryTypedDict]
+    r"""Retry configuration for the request"""
+    cache: NotRequired[GetPromptVersionCacheTypedDict]
+    r"""Cache configuration for the request."""
+    load_balancer: NotRequired[GetPromptVersionLoadBalancerTypedDict]
+    r"""Load balancer configuration for the request."""
+    timeout: NotRequired[GetPromptVersionTimeoutTypedDict]
+    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."""
     messages: NotRequired[List[GetPromptVersionPromptsMessagesTypedDict]]
     r"""Array of messages that make up the conversation. Each message has a role (system, user, assistant, or tool) and content."""
     model: NotRequired[Nullable[str]]
@@ -1883,6 +2044,9 @@ class GetPromptVersionPromptFieldTypedDict(TypedDict):
 class GetPromptVersionPromptField(BaseModel):
     r"""Prompt configuration with model and messages. Use this instead of prompt_config."""
 
+    name: Optional[str] = None
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
+
     audio: OptionalNullable[GetPromptVersionAudio] = UNSET
     r"""Parameters for audio output. Required when audio output is requested with modalities: [\"audio\"]. Learn more."""
 
@@ -1959,6 +2123,21 @@ class GetPromptVersionPromptField(BaseModel):
     guardrails: Optional[List[GetPromptVersionGuardrails]] = None
     r"""A list of guardrails to apply to the request."""
 
+    fallbacks: Optional[List[GetPromptVersionFallbacks]] = None
+    r"""Array of fallback models to use if primary model fails"""
+
+    retry: Optional[GetPromptVersionRetry] = None
+    r"""Retry configuration for the request"""
+
+    cache: Optional[GetPromptVersionCache] = None
+    r"""Cache configuration for the request."""
+
+    load_balancer: Optional[GetPromptVersionLoadBalancer] = None
+    r"""Load balancer configuration for the request."""
+
+    timeout: Optional[GetPromptVersionTimeout] = 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."""
+
     messages: Optional[List[GetPromptVersionPromptsMessages]] = None
     r"""Array of messages that make up the conversation. Each message has a role (system, user, assistant, or tool) and content."""
 
@@ -1971,6 +2150,7 @@ class GetPromptVersionPromptField(BaseModel):
     def serialize_model(self, handler):
         optional_fields = set(
             [
+                "name",
                 "audio",
                 "frequency_penalty",
                 "max_tokens",
@@ -1993,6 +2173,11 @@ class GetPromptVersionPromptField(BaseModel):
                 "parallel_tool_calls",
                 "modalities",
                 "guardrails",
+                "fallbacks",
+                "retry",
+                "cache",
+                "load_balancer",
+                "timeout",
                 "messages",
                 "model",
                 "version",

orq_ai_sdk/models/invokedeploymentrequest.py

@@ -10,6 +10,7 @@ from .imagecontentpartschema import (
     ImageContentPartSchema,
     ImageContentPartSchemaTypedDict,
 )
+from .publicidentity import PublicIdentity, PublicIdentityTypedDict
 from .reasoningpartschema import ReasoningPartSchema, ReasoningPartSchemaTypedDict
 from .redactedreasoningpartschema import (
     RedactedReasoningPartSchema,
@@ -202,14 +203,14 @@ InvokeDeploymentRequestPrefixMessages4Role = Literal["assistant",]
 r"""The role of the messages author, in this case `assistant`."""
 
 
-class AudioTypedDict(TypedDict):
+class AudioModelTypedDict(TypedDict):
     r"""Data about a previous audio response from the model."""
 
     id: str
     r"""Unique identifier for a previous audio response from the model."""
 
 
-class Audio(BaseModel):
+class AudioModel(BaseModel):
     r"""Data about a previous audio response from the model."""
 
     id: str
@@ -301,7 +302,7 @@ class AssistantMessageTypedDict(TypedDict):
     r"""The refusal message by the assistant."""
     name: NotRequired[str]
     r"""An optional name for the participant. Provides the model information to differentiate between participants of the same role."""
-    audio: NotRequired[Nullable[AudioTypedDict]]
+    audio: NotRequired[Nullable[AudioModelTypedDict]]
     r"""Data about a previous audio response from the model."""
     tool_calls: NotRequired[List[ToolCallsTypedDict]]
     r"""The tool calls generated by the model, such as function calls."""
@@ -320,7 +321,7 @@ class AssistantMessage(BaseModel):
     name: Optional[str] = None
     r"""An optional name for the participant. Provides the model information to differentiate between participants of the same role."""
 
-    audio: OptionalNullable[Audio] = UNSET
+    audio: OptionalNullable[AudioModel] = UNSET
     r"""Data about a previous audio response from the model."""
 
     tool_calls: Optional[List[ToolCalls]] = None
@@ -1953,6 +1954,8 @@ class InvokeDeploymentRequestTypedDict(TypedDict):
     r"""A list of messages to include after the `System` message, but before the  `User` and `Assistant` pairs configured in your deployment."""
     messages: NotRequired[List[MessagesTypedDict]]
     r"""A list of messages to send to the deployment."""
+    identity: NotRequired[PublicIdentityTypedDict]
+    r"""Information about the identity making the request. If the identity does not exist, it will be created automatically."""
     file_ids: NotRequired[List[str]]
     r"""A list of file IDs that are associated with the deployment request."""
     metadata: NotRequired[Dict[str, Any]]
@@ -1988,6 +1991,9 @@ class InvokeDeploymentRequest(BaseModel):
     messages: Optional[List[Messages]] = None
     r"""A list of messages to send to the deployment."""
 
+    identity: Optional[PublicIdentity] = None
+    r"""Information about the identity making the request. If the identity does not exist, it will be created automatically."""
+
     file_ids: Optional[List[str]] = None
     r"""A list of file IDs that are associated with the deployment request."""
 
@@ -2016,6 +2022,7 @@ class InvokeDeploymentRequest(BaseModel):
                 "context",
                 "prefix_messages",
                 "messages",
+                "identity",
                 "file_ids",
                 "metadata",
                 "extra_params",