openaivec 0.14.6__py3-none-any.whl → 0.14.8__py3-none-any.whl

openaivec/pandas_ext.py

@@ -42,7 +42,8 @@ to easily interact with OpenAI APIs for tasks like generating responses or embed
 import inspect
 import json
 import logging
-from typing import Awaitable, Callable, List, Type, TypeVar
+from collections.abc import Awaitable, Callable
+from typing import TypeVar
 
 import numpy as np
 import pandas as pd
@@ -179,7 +180,7 @@ class OpenAIVecSeriesAccessor:
         self,
         instructions: str,
         cache: BatchingMapProxy[str, ResponseFormat],
-        response_format: Type[ResponseFormat] = str,
+        response_format: type[ResponseFormat] = str,
         temperature: float | None = 0.0,
         top_p: float = 1.0,
         **api_kwargs,
@@ -193,7 +194,7 @@ class OpenAIVecSeriesAccessor:
             instructions (str): System prompt prepended to every user message.
             cache (BatchingMapProxy[str, ResponseFormat]): Explicit cache instance for
                 batching and deduplication control.
-            response_format (Type[ResponseFormat], optional): Pydantic model or built-in
+            response_format (type[ResponseFormat], optional): Pydantic model or built-in
                 type the assistant should return. Defaults to ``str``.
             temperature (float | None, optional): Sampling temperature. Defaults to ``0.0``.
             top_p (float, optional): Nucleus sampling parameter. Defaults to ``1.0``.
@@ -221,7 +222,7 @@ class OpenAIVecSeriesAccessor:
     def responses(
         self,
         instructions: str,
-        response_format: Type[ResponseFormat] = str,
+        response_format: type[ResponseFormat] = str,
         batch_size: int | None = None,
         temperature: float | None = 0.0,
         top_p: float = 1.0,
@@ -247,7 +248,7 @@ class OpenAIVecSeriesAccessor:
 
         Args:
             instructions (str): System prompt prepended to every user message.
-            response_format (Type[ResponseFormat], optional): Pydantic model or built‑in
+            response_format (type[ResponseFormat], optional): Pydantic model or built‑in
                 type the assistant should return. Defaults to ``str``.
             batch_size (int | None, optional): Number of prompts grouped into a single
                 request. Defaults to ``None`` (automatic batch size optimization
@@ -633,7 +634,7 @@ class OpenAIVecDataFrameAccessor:
         self,
         instructions: str,
         cache: BatchingMapProxy[str, ResponseFormat],
-        response_format: Type[ResponseFormat] = str,
+        response_format: type[ResponseFormat] = str,
         temperature: float | None = 0.0,
         top_p: float = 1.0,
         **api_kwargs,
@@ -667,7 +668,7 @@ class OpenAIVecDataFrameAccessor:
             cache (BatchingMapProxy[str, ResponseFormat]): Pre-configured cache
                 instance for managing API call batching and deduplication.
                 Set cache.batch_size=None to enable automatic batch size optimization.
-            response_format (Type[ResponseFormat], optional): Desired Python type of the
+            response_format (type[ResponseFormat], optional): Desired Python type of the
                 responses. Defaults to ``str``.
             temperature (float | None, optional): Sampling temperature. Defaults to ``0.0``.
             top_p (float, optional): Nucleus sampling parameter. Defaults to ``1.0``.
@@ -687,7 +688,7 @@ class OpenAIVecDataFrameAccessor:
     def responses(
         self,
         instructions: str,
-        response_format: Type[ResponseFormat] = str,
+        response_format: type[ResponseFormat] = str,
         batch_size: int | None = None,
         temperature: float | None = 0.0,
         top_p: float = 1.0,
@@ -717,7 +718,7 @@ class OpenAIVecDataFrameAccessor:
 
         Args:
             instructions (str): System prompt for the assistant.
-            response_format (Type[ResponseFormat], optional): Desired Python type of the
+            response_format (type[ResponseFormat], optional): Desired Python type of the
                 responses. Defaults to ``str``.
             batch_size (int | None, optional): Number of requests sent in one batch.
                 Defaults to ``None`` (automatic batch size optimization
@@ -969,7 +970,7 @@ class OpenAIVecDataFrameAccessor:
         if missing_rows.empty:
             return self._obj
 
-        filled_values: List[FillNaResponse] = missing_rows.ai.task(
+        filled_values: list[FillNaResponse] = missing_rows.ai.task(
             task=task, batch_size=batch_size, show_progress=show_progress, **api_kwargs
         )
 
@@ -1123,7 +1124,7 @@ class AsyncOpenAIVecSeriesAccessor:
         self,
         instructions: str,
         cache: AsyncBatchingMapProxy[str, ResponseFormat],
-        response_format: Type[ResponseFormat] = str,
+        response_format: type[ResponseFormat] = str,
         temperature: float | None = 0.0,
         top_p: float = 1.0,
         **api_kwargs,
@@ -1150,7 +1151,7 @@ class AsyncOpenAIVecSeriesAccessor:
             cache (AsyncBatchingMapProxy[str, ResponseFormat]): Pre-configured cache
                 instance for managing API call batching and deduplication.
                 Set cache.batch_size=None to enable automatic batch size optimization.
-            response_format (Type[ResponseFormat], optional): Pydantic model or built‑in
+            response_format (type[ResponseFormat], optional): Pydantic model or built‑in
                 type the assistant should return. Defaults to ``str``.
             temperature (float | None, optional): Sampling temperature. ``None`` omits the
                 parameter (recommended for reasoning models). Defaults to ``0.0``.
@@ -1181,7 +1182,7 @@ class AsyncOpenAIVecSeriesAccessor:
     async def responses(
         self,
         instructions: str,
-        response_format: Type[ResponseFormat] = str,
+        response_format: type[ResponseFormat] = str,
         batch_size: int | None = None,
         temperature: float | None = 0.0,
         top_p: float = 1.0,
@@ -1209,7 +1210,7 @@ class AsyncOpenAIVecSeriesAccessor:
 
         Args:
             instructions (str): System prompt prepended to every user message.
-            response_format (Type[ResponseFormat], optional): Pydantic model or built‑in
+            response_format (type[ResponseFormat], optional): Pydantic model or built‑in
                 type the assistant should return. Defaults to ``str``.
             batch_size (int | None, optional): Number of prompts grouped into a single
                 request. Defaults to ``None`` (automatic batch size optimization
@@ -1558,7 +1559,7 @@ class AsyncOpenAIVecDataFrameAccessor:
         self,
         instructions: str,
         cache: AsyncBatchingMapProxy[str, ResponseFormat],
-        response_format: Type[ResponseFormat] = str,
+        response_format: type[ResponseFormat] = str,
         temperature: float | None = 0.0,
         top_p: float = 1.0,
         **api_kwargs,
@@ -1594,7 +1595,7 @@ class AsyncOpenAIVecDataFrameAccessor:
             cache (AsyncBatchingMapProxy[str, ResponseFormat]): Pre-configured cache
                 instance for managing API call batching and deduplication.
                 Set cache.batch_size=None to enable automatic batch size optimization.
-            response_format (Type[ResponseFormat], optional): Desired Python type of the
+            response_format (type[ResponseFormat], optional): Desired Python type of the
                 responses. Defaults to ``str``.
             temperature (float | None, optional): Sampling temperature. Defaults to ``0.0``.
             top_p (float, optional): Nucleus sampling parameter. Defaults to ``1.0``.
@@ -1618,7 +1619,7 @@ class AsyncOpenAIVecDataFrameAccessor:
     async def responses(
         self,
         instructions: str,
-        response_format: Type[ResponseFormat] = str,
+        response_format: type[ResponseFormat] = str,
         batch_size: int | None = None,
         temperature: float | None = 0.0,
         top_p: float = 1.0,
@@ -1650,7 +1651,7 @@ class AsyncOpenAIVecDataFrameAccessor:
 
         Args:
             instructions (str): System prompt for the assistant.
-            response_format (Type[ResponseFormat], optional): Desired Python type of the
+            response_format (type[ResponseFormat], optional): Desired Python type of the
                 responses. Defaults to ``str``.
             batch_size (int | None, optional): Number of requests sent in one batch.
                 Defaults to ``None`` (automatic batch size optimization
@@ -1936,7 +1937,7 @@ class AsyncOpenAIVecDataFrameAccessor:
         if missing_rows.empty:
             return self._obj
 
-        filled_values: List[FillNaResponse] = await missing_rows.aio.task(
+        filled_values: list[FillNaResponse] = await missing_rows.aio.task(
             task=task, batch_size=batch_size, max_concurrency=max_concurrency, show_progress=show_progress, **api_kwargs
         )
 

openaivec/spark.py

@@ -123,8 +123,9 @@ Note: This module provides asynchronous support through the pandas extensions.
 
 import asyncio
 import logging
+from collections.abc import Iterator
 from enum import Enum
-from typing import Dict, Iterator, List, Type, Union, get_args, get_origin
+from typing import Union, get_args, get_origin
 
 import numpy as np
 import pandas as pd
@@ -157,13 +158,13 @@ _LOGGER: logging.Logger = logging.getLogger(__name__)
 def _python_type_to_spark(python_type):
     origin = get_origin(python_type)
 
-    # For list types (e.g., List[int])
-    if origin is list or origin is List:
+    # For list types (e.g., list[int])
+    if origin is list:
         # Retrieve the inner type and recursively convert it
         inner_type = get_args(python_type)[0]
         return ArrayType(_python_type_to_spark(inner_type))
 
-    # For Optional types (Union[..., None])
+    # For Optional types (T | None via Union internally)
     elif origin is Union:
         non_none_args = [arg for arg in get_args(python_type) if arg is not type(None)]
         if len(non_none_args) == 1:
@@ -196,7 +197,7 @@ def _python_type_to_spark(python_type):
         raise ValueError(f"Unsupported type: {python_type}")
 
 
-def _pydantic_to_spark_schema(model: Type[BaseModel]) -> StructType:
+def _pydantic_to_spark_schema(model: type[BaseModel]) -> StructType:
     fields = []
     for field_name, field in model.model_fields.items():
         field_type = field.annotation
@@ -218,7 +219,7 @@ def _safe_cast_str(x: str | None) -> str | None:
         return None
 
 
-def _safe_dump(x: BaseModel | None) -> Dict:
+def _safe_dump(x: BaseModel | None) -> dict:
     try:
         if x is None:
             return {}
@@ -231,7 +232,7 @@ def _safe_dump(x: BaseModel | None) -> Dict:
 
 def responses_udf(
     instructions: str,
-    response_format: Type[ResponseFormat] = str,
+    response_format: type[ResponseFormat] = str,
     model_name: str = "gpt-4.1-mini",
     batch_size: int | None = None,
     temperature: float | None = 0.0,
@@ -261,7 +262,7 @@ def responses_udf(
 
     Args:
         instructions (str): The system prompt or instructions for the model.
-        response_format (Type[ResponseFormat]): The desired output format. Either `str` for plain text
+        response_format (type[ResponseFormat]): The desired output format. Either `str` for plain text
             or a Pydantic `BaseModel` for structured JSON output. Defaults to `str`.
         model_name (str): For Azure OpenAI, use your deployment name (e.g., "my-gpt4-deployment").
             For OpenAI, use the model name (e.g., "gpt-4.1-mini"). Defaults to "gpt-4.1-mini".
@@ -555,12 +556,12 @@ def embeddings_udf(
     return _embeddings_udf  # type: ignore[return-value]
 
 
-def split_to_chunks_udf(max_tokens: int, sep: List[str]) -> UserDefinedFunction:
+def split_to_chunks_udf(max_tokens: int, sep: list[str]) -> UserDefinedFunction:
     """Create a pandas‑UDF that splits text into token‑bounded chunks.
 
     Args:
         max_tokens (int): Maximum tokens allowed per chunk.
-        sep (List[str]): Ordered list of separator strings used by ``TextChunker``.
+        sep (list[str]): Ordered list of separator strings used by ``TextChunker``.
 
     Returns:
         A pandas UDF producing an ``ArrayType(StringType())`` column whose

openaivec/task/customer_support/customer_sentiment.py

@@ -61,7 +61,7 @@ Attributes:
         top_p=1.0 for deterministic output.
 """
 
-from typing import List, Literal
+from typing import Literal
 
 from pydantic import BaseModel, Field
 
@@ -86,7 +86,7 @@ class CustomerSentiment(BaseModel):
     )
     sentiment_intensity: float = Field(description="Intensity of sentiment from 0.0 (mild) to 1.0 (extreme)")
     polarity_score: float = Field(description="Polarity score from -1.0 (very negative) to 1.0 (very positive)")
-    tone_indicators: List[str] = Field(description="Specific words or phrases indicating tone")
+    tone_indicators: list[str] = Field(description="Specific words or phrases indicating tone")
     relationship_status: Literal["new", "loyal", "at_risk", "detractor", "advocate"] = Field(
         description="Customer relationship status (new, loyal, at_risk, detractor, advocate)"
     )

openaivec/task/customer_support/inquiry_classification.py

@@ -92,7 +92,7 @@ Example:
     ```
 """
 
-from typing import Dict, List, Literal
+from typing import Dict, Literal
 
 from pydantic import BaseModel, Field
 
@@ -106,7 +106,7 @@ class InquiryClassification(BaseModel):
     subcategory: str = Field(description="Specific subcategory within the primary category")
     confidence: float = Field(description="Confidence score for classification (0.0-1.0)")
     routing: str = Field(description="Recommended routing destination")
-    keywords: List[str] = Field(description="Key terms that influenced the classification")
+    keywords: list[str] = Field(description="Key terms that influenced the classification")
     priority: Literal["low", "medium", "high", "urgent"] = Field(
         description="Suggested priority level (low, medium, high, urgent)"
     )
@@ -114,25 +114,25 @@ class InquiryClassification(BaseModel):
 
 
 def inquiry_classification(
-    categories: Dict[str, List[str]] | None = None,
+    categories: Dict[str, list[str]] | None = None,
     routing_rules: Dict[str, str] | None = None,
     priority_rules: Dict[str, str] | None = None,
     business_context: str = "general customer support",
-    custom_keywords: Dict[str, List[str]] | None = None,
+    custom_keywords: Dict[str, list[str]] | None = None,
     temperature: float = 0.0,
     top_p: float = 1.0,
 ) -> PreparedTask:
     """Create a configurable inquiry classification task.
 
     Args:
-        categories (Dict[str, List[str]] | None): Dictionary mapping category names to lists of subcategories.
+        categories (dict[str, list[str]] | None): Dictionary mapping category names to lists of subcategories.
             Default provides standard support categories.
-        routing_rules (Dict[str, str] | None): Dictionary mapping categories to routing destinations.
+        routing_rules (dict[str, str] | None): Dictionary mapping categories to routing destinations.
             Default provides standard routing options.
-        priority_rules (Dict[str, str] | None): Dictionary mapping keywords/patterns to priority levels.
+        priority_rules (dict[str, str] | None): Dictionary mapping keywords/patterns to priority levels.
             Default uses standard priority indicators.
         business_context (str): Description of the business context to help with classification.
-        custom_keywords (Dict[str, List[str]] | None): Dictionary mapping categories to relevant keywords.
+        custom_keywords (dict[str, list[str]] | None): Dictionary mapping categories to relevant keywords.
         temperature (float): Sampling temperature (0.0-1.0).
         top_p (float): Nucleus sampling parameter (0.0-1.0).
 

openaivec/task/customer_support/inquiry_summary.py

@@ -59,7 +59,7 @@ Attributes:
         top_p=1.0 for deterministic output.
 """
 
-from typing import List, Literal
+from typing import Literal
 
 from pydantic import BaseModel, Field
 
@@ -71,15 +71,15 @@ __all__ = ["inquiry_summary"]
 class InquirySummary(BaseModel):
     summary: str = Field(description="Concise summary of the customer inquiry (2-3 sentences)")
     main_issue: str = Field(description="Primary problem or request being addressed")
-    secondary_issues: List[str] = Field(description="Additional issues mentioned in the inquiry")
+    secondary_issues: list[str] = Field(description="Additional issues mentioned in the inquiry")
     customer_background: str = Field(description="Relevant customer context or history mentioned")
-    actions_taken: List[str] = Field(description="Steps the customer has already attempted")
+    actions_taken: list[str] = Field(description="Steps the customer has already attempted")
     timeline: str = Field(description="Timeline of events or when the issue started")
     impact_description: str = Field(description="How the issue affects the customer")
     resolution_status: Literal["not_started", "in_progress", "needs_escalation", "resolved"] = Field(
         description="Current status (not_started, in_progress, needs_escalation, resolved)"
     )
-    key_details: List[str] = Field(description="Important technical details, error messages, or specifics")
+    key_details: list[str] = Field(description="Important technical details, error messages, or specifics")
     follow_up_needed: bool = Field(description="Whether follow-up communication is required")
     summary_confidence: float = Field(description="Confidence in summary accuracy (0.0-1.0)")
 

openaivec/task/customer_support/intent_analysis.py

@@ -57,7 +57,7 @@ Attributes:
         top_p=1.0 for deterministic output.
 """
 
-from typing import List, Literal
+from typing import Literal
 
 from pydantic import BaseModel, Field
 
@@ -80,7 +80,7 @@ class IntentAnalysis(BaseModel):
         description="Primary customer intent (get_help, make_purchase, cancel_service, "
         "get_refund, report_issue, seek_information, request_feature, provide_feedback)"
     )
-    secondary_intents: List[str] = Field(description="Additional intents if multiple goals are present")
+    secondary_intents: list[str] = Field(description="Additional intents if multiple goals are present")
     action_required: Literal[
         "provide_information", "troubleshoot", "process_request", "escalate", "redirect", "schedule_callback"
     ] = Field(
@@ -92,9 +92,9 @@ class IntentAnalysis(BaseModel):
         description="Likelihood of successful resolution (very_high, high, medium, low, very_low)"
     )
     customer_goal: str = Field(description="What the customer ultimately wants to achieve")
-    implicit_needs: List[str] = Field(description="Unstated needs or concerns that may need addressing")
-    blocking_factors: List[str] = Field(description="Potential obstacles to achieving customer goal")
-    next_steps: List[str] = Field(description="Recommended next steps to address customer intent")
+    implicit_needs: list[str] = Field(description="Unstated needs or concerns that may need addressing")
+    blocking_factors: list[str] = Field(description="Potential obstacles to achieving customer goal")
+    next_steps: list[str] = Field(description="Recommended next steps to address customer intent")
     resolution_complexity: Literal["simple", "moderate", "complex", "very_complex"] = Field(
         description="Complexity of resolution (simple, moderate, complex, very_complex)"
     )

openaivec/task/customer_support/response_suggestion.py

@@ -57,7 +57,7 @@ Attributes:
         top_p=1.0 for deterministic output.
 """
 
-from typing import List, Literal
+from typing import Literal
 
 from pydantic import BaseModel, Field
 
@@ -77,14 +77,14 @@ class ResponseSuggestion(BaseModel):
     response_type: Literal["acknowledgment", "solution", "escalation", "information_request", "closure"] = Field(
         description="Type of response (acknowledgment, solution, escalation, information_request, closure)"
     )
-    key_points: List[str] = Field(description="Main points that must be addressed in the response")
+    key_points: list[str] = Field(description="Main points that must be addressed in the response")
     follow_up_required: bool = Field(description="Whether follow-up communication is needed")
     escalation_suggested: bool = Field(description="Whether escalation to management is recommended")
-    resources_needed: List[str] = Field(description="Additional resources or information required")
+    resources_needed: list[str] = Field(description="Additional resources or information required")
     estimated_resolution_time: Literal["immediate", "hours", "days", "weeks"] = Field(
         description="Estimated time to resolution (immediate, hours, days, weeks)"
     )
-    alternative_responses: List[str] = Field(description="Alternative response options for different scenarios")
+    alternative_responses: list[str] = Field(description="Alternative response options for different scenarios")
     personalization_notes: str = Field(description="Suggestions for personalizing the response")
 
 

openaivec/task/customer_support/urgency_analysis.py

@@ -96,7 +96,7 @@ Example:
     ```
 """
 
-from typing import Dict, List, Literal
+from typing import Dict, Literal
 
 from pydantic import BaseModel, Field
 
@@ -115,7 +115,7 @@ class UrgencyAnalysis(BaseModel):
         "(immediate, within_1_hour, within_4_hours, within_24_hours)"
     )
     escalation_required: bool = Field(description="Whether this inquiry requires escalation to management")
-    urgency_indicators: List[str] = Field(description="Specific words or phrases that indicate urgency")
+    urgency_indicators: list[str] = Field(description="Specific words or phrases that indicate urgency")
     business_impact: Literal["none", "low", "medium", "high", "critical"] = Field(
         description="Potential business impact (none, low, medium, high, critical)"
     )
@@ -131,7 +131,7 @@ def urgency_analysis(
     response_times: Dict[str, str] | None = None,
     customer_tiers: Dict[str, str] | None = None,
     escalation_rules: Dict[str, str] | None = None,
-    urgency_keywords: Dict[str, List[str]] | None = None,
+    urgency_keywords: Dict[str, list[str]] | None = None,
     business_context: str = "general customer support",
     business_hours: str = "24/7 support",
     sla_rules: Dict[str, str] | None = None,
@@ -141,14 +141,14 @@ def urgency_analysis(
     """Create a configurable urgency analysis task.
 
     Args:
-        urgency_levels (Dict[str, str] | None): Dictionary mapping urgency levels to descriptions.
-        response_times (Dict[str, str] | None): Dictionary mapping urgency levels to response times.
-        customer_tiers (Dict[str, str] | None): Dictionary mapping tier names to descriptions.
-        escalation_rules (Dict[str, str] | None): Dictionary mapping conditions to escalation actions.
-        urgency_keywords (Dict[str, List[str]] | None): Dictionary mapping urgency levels to indicator keywords.
+        urgency_levels (dict[str, str] | None): Dictionary mapping urgency levels to descriptions.
+        response_times (dict[str, str] | None): Dictionary mapping urgency levels to response times.
+        customer_tiers (dict[str, str] | None): Dictionary mapping tier names to descriptions.
+        escalation_rules (dict[str, str] | None): Dictionary mapping conditions to escalation actions.
+        urgency_keywords (dict[str, list[str]] | None): Dictionary mapping urgency levels to indicator keywords.
         business_context (str): Description of the business context.
         business_hours (str): Description of business hours for response time calculation.
-        sla_rules (Dict[str, str] | None): Dictionary mapping customer tiers to SLA requirements.
+        sla_rules (dict[str, str] | None): Dictionary mapping customer tiers to SLA requirements.
         temperature (float): Sampling temperature (0.0-1.0).
         top_p (float): Nucleus sampling parameter (0.0-1.0).
 

openaivec/task/nlp/dependency_parsing.py

@@ -48,8 +48,6 @@ Attributes:
         top_p=1.0 for deterministic output.
 """
 
-from typing import List
-
 from pydantic import BaseModel, Field
 
 from openaivec._model import PreparedTask
@@ -66,8 +64,8 @@ class DependencyRelation(BaseModel):
 
 
 class DependencyParsing(BaseModel):
-    tokens: List[str] = Field(description="List of tokens in the sentence")
-    dependencies: List[DependencyRelation] = Field(description="Dependency relations between tokens")
+    tokens: list[str] = Field(description="List of tokens in the sentence")
+    dependencies: list[DependencyRelation] = Field(description="Dependency relations between tokens")
     root_word: str = Field(description="Root word of the sentence")
     syntactic_structure: str = Field(description="Tree representation of the syntactic structure")
 

openaivec/task/nlp/keyword_extraction.py

@@ -50,8 +50,6 @@ Attributes:
         top_p=1.0 for deterministic output.
 """
 
-from typing import List
-
 from pydantic import BaseModel, Field
 
 from openaivec._model import PreparedTask
@@ -67,9 +65,9 @@ class Keyword(BaseModel):
 
 
 class KeywordExtraction(BaseModel):
-    keywords: List[Keyword] = Field(description="Extracted keywords ranked by importance")
-    keyphrases: List[Keyword] = Field(description="Extracted multi-word phrases ranked by importance")
-    topics: List[str] = Field(description="Identified main topics in the text")
+    keywords: list[Keyword] = Field(description="Extracted keywords ranked by importance")
+    keyphrases: list[Keyword] = Field(description="Extracted multi-word phrases ranked by importance")
+    topics: list[str] = Field(description="Identified main topics in the text")
     summary: str = Field(description="Brief summary of the text content")
 
 

openaivec/task/nlp/morphological_analysis.py

@@ -49,8 +49,6 @@ Attributes:
         top_p=1.0 for deterministic output.
 """
 
-from typing import List
-
 from pydantic import BaseModel, Field
 
 from openaivec._model import PreparedTask
@@ -59,10 +57,10 @@ __all__ = ["MORPHOLOGICAL_ANALYSIS"]
 
 
 class MorphologicalAnalysis(BaseModel):
-    tokens: List[str] = Field(description="List of tokens in the text")
-    pos_tags: List[str] = Field(description="Part-of-speech tags for each token")
-    lemmas: List[str] = Field(description="Lemmatized form of each token")
-    morphological_features: List[str] = Field(
+    tokens: list[str] = Field(description="List of tokens in the text")
+    pos_tags: list[str] = Field(description="Part-of-speech tags for each token")
+    lemmas: list[str] = Field(description="Lemmatized form of each token")
+    morphological_features: list[str] = Field(
         description="Morphological features for each token (e.g., tense, number, case)"
     )
 

openaivec/task/nlp/named_entity_recognition.py

@@ -48,8 +48,6 @@ Attributes:
         top_p=1.0 for deterministic output.
 """
 
-from typing import List
-
 from pydantic import BaseModel, Field
 
 from openaivec._model import PreparedTask
@@ -66,13 +64,13 @@ class NamedEntity(BaseModel):
 
 
 class NamedEntityRecognition(BaseModel):
-    persons: List[NamedEntity] = Field(description="Person entities")
-    organizations: List[NamedEntity] = Field(description="Organization entities")
-    locations: List[NamedEntity] = Field(description="Location entities")
-    dates: List[NamedEntity] = Field(description="Date and time entities")
-    money: List[NamedEntity] = Field(description="Money and currency entities")
-    percentages: List[NamedEntity] = Field(description="Percentage entities")
-    miscellaneous: List[NamedEntity] = Field(description="Other named entities")
+    persons: list[NamedEntity] = Field(description="Person entities")
+    organizations: list[NamedEntity] = Field(description="Organization entities")
+    locations: list[NamedEntity] = Field(description="Location entities")
+    dates: list[NamedEntity] = Field(description="Date and time entities")
+    money: list[NamedEntity] = Field(description="Money and currency entities")
+    percentages: list[NamedEntity] = Field(description="Percentage entities")
+    miscellaneous: list[NamedEntity] = Field(description="Other named entities")
 
 
 NAMED_ENTITY_RECOGNITION = PreparedTask(

openaivec/task/nlp/sentiment_analysis.py

@@ -48,7 +48,7 @@ Attributes:
         top_p=1.0 for deterministic output.
 """
 
-from typing import List, Literal
+from typing import Literal
 
 from pydantic import BaseModel, Field
 
@@ -62,10 +62,10 @@ class SentimentAnalysis(BaseModel):
         description="Overall sentiment (positive, negative, neutral)"
     )
     confidence: float = Field(description="Confidence score for sentiment (0.0-1.0)")
-    emotions: List[Literal["joy", "sadness", "anger", "fear", "surprise", "disgust"]] = Field(
+    emotions: list[Literal["joy", "sadness", "anger", "fear", "surprise", "disgust"]] = Field(
         description="Detected emotions (joy, sadness, anger, fear, surprise, disgust)"
     )
-    emotion_scores: List[float] = Field(description="Confidence scores for each emotion (0.0-1.0)")
+    emotion_scores: list[float] = Field(description="Confidence scores for each emotion (0.0-1.0)")
     polarity: float = Field(description="Polarity score from -1.0 (negative) to 1.0 (positive)")
     subjectivity: float = Field(description="Subjectivity score from 0.0 (objective) to 1.0 (subjective)")
 

openaivec/task/nlp/translation.py

@@ -72,8 +72,7 @@ Note:
     - Other: Basque, Maltese
 """
 
-from openai import BaseModel
-from pydantic import Field
+from pydantic import BaseModel, Field
 
 from openaivec._model import PreparedTask
 

openaivec/task/table/fillna.py

@@ -65,7 +65,6 @@ Example:
 """
 
 import json
-from typing import Dict, List
 
 import pandas as pd
 from pydantic import BaseModel, Field
@@ -76,8 +75,8 @@ from openaivec._prompt import FewShotPromptBuilder
 __all__ = ["fillna", "FillNaResponse"]
 
 
-def get_examples(df: pd.DataFrame, target_column_name: str, max_examples: int) -> List[Dict]:
-    examples: List[Dict] = []
+def get_examples(df: pd.DataFrame, target_column_name: str, max_examples: int) -> list[dict]:
+    examples: list[dict] = []
 
     samples: pd.DataFrame = df.sample(frac=1).reset_index(drop=True).drop_duplicates()
     samples = samples.dropna(subset=[target_column_name])

{openaivec-0.14.6.dist-info → openaivec-0.14.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openaivec
-Version: 0.14.6
+Version: 0.14.8
 Summary: Generative mutation for tabular calculation
 Project-URL: Homepage, https://microsoft.github.io/openaivec/
 Project-URL: Repository, https://github.com/microsoft/openaivec

openaivec-0.14.8.dist-info/RECORD

@@ -0,0 +1,36 @@
+openaivec/__init__.py,sha256=mXCGNNTjYbmE4CAXGvAs78soxUsoy_mxxnvaCk_CL6Y,361
+openaivec/_di.py,sha256=1MXaBzaH_ZenQnWKQzBY2z-egHwiteMvg7byoUH3ZZI,10658
+openaivec/_embeddings.py,sha256=upCjl8m9h1CihP6t7wvIH_vivOAPSgmgooAxIhnUMUw,7449
+openaivec/_log.py,sha256=LHNs6AbJzM4weaRARZFroigxR6D148d7WSIMLk1IhbU,1439
+openaivec/_model.py,sha256=toS2oBubrJa9jrdYy-87Fb2XivjXUlk_8Zn5gKUAcFI,3345
+openaivec/_optimize.py,sha256=3nS8VehbS7iGC1tPDDQh-iAgyKHbVYmMbCRBWM77U_U,3827
+openaivec/_prompt.py,sha256=zLv13q47CKV3jnETUyWAIlnjXFSEMs70c8m0yN7_Hek,20820
+openaivec/_provider.py,sha256=YLrEcb4aWBD1fj0n6PNcJpCtEXK6jkUuRH_WxcLDCuI,7145
+openaivec/_proxy.py,sha256=AiGuC1MCFjZCRXCac-pHUI3Np3nf1HIpWY6nC9ZVCFY,29671
+openaivec/_responses.py,sha256=lVJRa_Uc7hQJnYJRgumqwBbu6GToZqsLFS6tIAFO1Fc,24014
+openaivec/_schema.py,sha256=fVsFkCZWSbh2-fiGxnT8cSVrlUQOYWJX5EeL2F6aX4s,24039
+openaivec/_serialize.py,sha256=u2Om94Sc_QgJkTlW2BAGw8wd6gYDhc6IRqvS-qevFSs,8399
+openaivec/_util.py,sha256=XfueAycVCQvgRLS7wF7e306b53lebORvZOBzbQjy4vE,6438
+openaivec/pandas_ext.py,sha256=rCkh8g9eqHn0gUG8j_-jdppQt_Yq_1Wg6FmsCEcpv3k,85985
+openaivec/spark.py,sha256=Dbuhlk8Z89Fwk3fbWp1Ud9uTpfNyfjZOIx8ARJMnQf0,25371
+openaivec/task/__init__.py,sha256=lrgoc9UIox7XnxZ96dQRl88a-8QfuZRFBHshxctpMB8,6178
+openaivec/task/customer_support/__init__.py,sha256=KWfGyXPdZyfGdRH17x7hPpJJ1N2EP9PPhZx0fvBAwSI,884
+openaivec/task/customer_support/customer_sentiment.py,sha256=NHIr9nm2d2Bu1MSpxFsM3_w1UuQrQEwnHrClVbhdCUw,7612
+openaivec/task/customer_support/inquiry_classification.py,sha256=NUU_apX6ADi4SyGUbvflGt-v5Ka7heHXlJOHPAeVoGg,9640
+openaivec/task/customer_support/inquiry_summary.py,sha256=PDQvF_ZEZ9TnFhLM2yIinP-OKz_PSPeIET48P9UIgzQ,6920
+openaivec/task/customer_support/intent_analysis.py,sha256=uWdza2pkqnRJn3JtPWbsTAUDL1Sn-BwH-ZpN2cUxhe8,7504
+openaivec/task/customer_support/response_suggestion.py,sha256=Hxt5MDpdfoo5S7_I_eQ302AOIsSCyNBeaDSMMMfPYoQ,8344
+openaivec/task/customer_support/urgency_analysis.py,sha256=DRd4pmFnwuiNGBKxxkEkfp5CZZeDppmBUThs5NYOL9g,11569
+openaivec/task/nlp/__init__.py,sha256=QoQ0egEK9IEh5hdrE07rZ_KCmC0gy_2FPrWJYRWiipY,512
+openaivec/task/nlp/dependency_parsing.py,sha256=MhrHNCqSd-JmlQ21ISYwGYXazNVZGsVuX_v0ZpyI50w,2817
+openaivec/task/nlp/keyword_extraction.py,sha256=seFeuk6Z2dmlVBFoDN-tOVgCnR7jq36sTsWySjb_ric,2804
+openaivec/task/nlp/morphological_analysis.py,sha256=TcNGA0cYrPczr1ZxflBiokh-qdwMSvRDHq66fP7gi2c,2401
+openaivec/task/nlp/named_entity_recognition.py,sha256=jnVfGtf7TDCNNHrLQ5rhMYvmHc8FKXQxEzC5ib6NnVc,3037
+openaivec/task/nlp/sentiment_analysis.py,sha256=Np-yY0d4Kr5WEjGjq4tNFHDNarBLajJr8Q2E6K9ms3A,3085
+openaivec/task/nlp/translation.py,sha256=VYgiXtr2TL1tbqZkBpyVAy4ahrgd8UO4ZjhIL6xMdkI,6609
+openaivec/task/table/__init__.py,sha256=kJz15WDJXjyC7UIHKBvlTRhCf347PCDMH5T5fONV2sU,83
+openaivec/task/table/fillna.py,sha256=g_CpLnLzK1C5rCiVq15L3X0kywJK6CtSrKRYxQFuhn8,6606
+openaivec-0.14.8.dist-info/METADATA,sha256=ItqzTCNsPigyX9fe5WBQHih3gzT68XjdwFsAOa9-qrI,27566
+openaivec-0.14.8.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+openaivec-0.14.8.dist-info/licenses/LICENSE,sha256=ws_MuBL-SCEBqPBFl9_FqZkaaydIJmxHrJG2parhU4M,1141
+openaivec-0.14.8.dist-info/RECORD,,