orq-ai-sdk 4.2.0rc28__py3-none-any.whl → 4.2.6__py3-none-any.whl

orq_ai_sdk/models/createdatasetop.py

@@ -2,9 +2,10 @@
 
 from __future__ import annotations
 from datetime import datetime
-from orq_ai_sdk.types import BaseModel
+from orq_ai_sdk.types import BaseModel, UNSET_SENTINEL
 from orq_ai_sdk.utils import parse_datetime
 import pydantic
+from pydantic import model_serializer
 from typing import Optional
 from typing_extensions import Annotated, NotRequired, TypedDict
 
@@ -93,5 +94,21 @@ class CreateDatasetResponseBody(BaseModel):
     created: Optional[datetime] = None
     r"""The date and time the resource was created"""
 
-    updated: Optional[datetime] = parse_datetime("2026-01-14T08:04:31.906Z")
+    updated: Optional[datetime] = parse_datetime("2026-01-25T15:02:07.185Z")
     r"""The date and time the resource was last updated"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["created_by_id", "updated_by_id", "created", "updated"])
+        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

orq_ai_sdk/models/createdatasourceop.py

@@ -44,6 +44,22 @@ class ChunkingConfiguration2(BaseModel):
     chunk_overlap: Optional[float] = 0
     r"""Specifies the number of characters to overlap between consecutive chunks. This overlap helps maintain semantic continuity when splitting large text elements."""
 
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["chunk_max_characters", "chunk_overlap"])
+        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
+
 
 ChunkingConfigurationType = Literal["default",]
 
@@ -125,6 +141,33 @@ class ChunkingCleanupOptions(BaseModel):
     clean_whitespaces: Optional[bool] = None
     r"""Trims and normalizes excessive whitespace throughout the text."""
 
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(
+            [
+                "delete_emails",
+                "delete_credit_cards",
+                "delete_phone_numbers",
+                "clean_bullet_points",
+                "clean_numbered_list",
+                "clean_unicode",
+                "clean_dashes",
+                "clean_whitespaces",
+            ]
+        )
+        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 ChunkingOptionsTypedDict(TypedDict):
     r"""Configuration options specifying how the datasource file is chunked. Required if `file_id` is specified. Defaults to standard chunking options if omitted."""
@@ -144,6 +187,22 @@ class ChunkingOptions(BaseModel):
     chunking_cleanup_options: Optional[ChunkingCleanupOptions] = None
     r"""The cleanup options applied to the datasource content. All options are enabled by default to ensure enhanced security and optimal chunk quality. Defaults to system-standard cleanup options if not specified."""
 
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["chunking_configuration", "chunking_cleanup_options"])
+        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 CreateDatasourceRequestBodyTypedDict(TypedDict):
     display_name: NotRequired[str]
@@ -164,6 +223,22 @@ class CreateDatasourceRequestBody(BaseModel):
     chunking_options: Optional[ChunkingOptions] = None
     r"""Configuration options specifying how the datasource file is chunked. Required if `file_id` is specified. Defaults to standard chunking options if omitted."""
 
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["display_name", "file_id", "chunking_options"])
+        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 CreateDatasourceRequestTypedDict(TypedDict):
     knowledge_id: str
@@ -239,7 +314,7 @@ class CreateDatasourceResponseBody(BaseModel):
     r"""The number of chunks in the datasource"""
 
     id: Annotated[Optional[str], pydantic.Field(alias="_id")] = (
-        "01KEXRJ89VZH4Z1W4D7HZA5JX9"
+        "01KFTTTRHXGP67Y2P1W8B66Q4Y"
     )
     r"""The unique identifier of the data source"""
 
@@ -257,36 +332,27 @@ class CreateDatasourceResponseBody(BaseModel):
 
     @model_serializer(mode="wrap")
     def serialize_model(self, handler):
-        optional_fields = [
-            "_id",
-            "description",
-            "file_id",
-            "created_by_id",
-            "update_by_id",
-        ]
-        nullable_fields = ["file_id", "created_by_id", "update_by_id"]
-        null_default_fields = []
-
+        optional_fields = set(
+            ["_id", "description", "file_id", "created_by_id", "update_by_id"]
+        )
+        nullable_fields = set(["file_id", "created_by_id", "update_by_id"])
         serialized = handler(self)
-
         m = {}
 
         for n, f in type(self).model_fields.items():
             k = f.alias or n
             val = serialized.get(k)
-            serialized.pop(k, None)
-
-            optional_nullable = k in optional_fields and k in nullable_fields
-            is_set = (
-                self.__pydantic_fields_set__.intersection({n})
-                or k in null_default_fields
-            )  # pylint: disable=no-member
-
-            if val is not None and val != UNSET_SENTINEL:
-                m[k] = val
-            elif val != UNSET_SENTINEL and (
-                not k in optional_fields or (optional_nullable and is_set)
-            ):
-                m[k] = val
+            is_nullable_and_explicitly_set = (
+                k in nullable_fields
+                and (self.__pydantic_fields_set__.intersection({n}))  # pylint: disable=no-member
+            )
+
+            if val != UNSET_SENTINEL:
+                if (
+                    val is not None
+                    or k not in optional_fields
+                    or is_nullable_and_explicitly_set
+                ):
+                    m[k] = val
 
         return m

orq_ai_sdk/models/createembeddingop.py

@@ -0,0 +1,384 @@
+"""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"""
+
+
+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
+
+
+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
+
+
+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"""Array of models with weights for load balancing requests"""
+
+
+CreateEmbeddingLoadBalancer = CreateEmbeddingLoadBalancer1
+r"""Array of models with weights for load balancing requests"""
+
+
+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 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[CreateEmbeddingFallbacksTypedDict]]
+    r"""Array of fallback models to use if primary model fails"""
+    cache: NotRequired[CreateEmbeddingCacheTypedDict]
+    r"""Cache configuration for the request."""
+    retry: NotRequired[CreateEmbeddingRetryTypedDict]
+    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[CreateEmbeddingLoadBalancerTypedDict]
+    r"""Array of models with weights for load balancing requests"""
+    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."""
+
+
+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[CreateEmbeddingFallbacks]] = None
+    r"""Array of fallback models to use if primary model fails"""
+
+    cache: Optional[CreateEmbeddingCache] = None
+    r"""Cache configuration for the request."""
+
+    retry: Optional[CreateEmbeddingRetry] = 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[CreateEmbeddingLoadBalancer] = None
+    r"""Array of models with weights for load balancing requests"""
+
+    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."""
+
+    @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"""
+    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"""
+
+    orq: Optional[CreateEmbeddingOrq] = None
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["encoding_format", "dimensions", "user", "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."""