openaivec 0.12.5__py3-none-any.whl → 1.0.10__py3-none-any.whl

openaivec/task/nlp/__init__.py

@@ -1,9 +1,9 @@
-from .translation import MULTILINGUAL_TRANSLATION
+from .dependency_parsing import DEPENDENCY_PARSING
+from .keyword_extraction import KEYWORD_EXTRACTION
 from .morphological_analysis import MORPHOLOGICAL_ANALYSIS
 from .named_entity_recognition import NAMED_ENTITY_RECOGNITION
 from .sentiment_analysis import SENTIMENT_ANALYSIS
-from .dependency_parsing import DEPENDENCY_PARSING
-from .keyword_extraction import KEYWORD_EXTRACTION
+from .translation import MULTILINGUAL_TRANSLATION
 
 __all__ = [
     "MULTILINGUAL_TRANSLATION",
@@ -12,4 +12,4 @@ __all__ = [
     "SENTIMENT_ANALYSIS",
     "DEPENDENCY_PARSING",
     "KEYWORD_EXTRACTION",
-]
+]

openaivec/task/nlp/dependency_parsing.py

@@ -8,7 +8,7 @@ Example:
 
     ```python
     from openai import OpenAI
-    from openaivec.responses import BatchResponses
+    from openaivec import BatchResponses
     from openaivec.task import nlp
 
     client = OpenAI()
@@ -43,16 +43,14 @@ Example:
     ```
 
 Attributes:
-    DEPENDENCY_PARSING (PreparedTask): A prepared task instance
-        configured for dependency parsing with temperature=0.0 and
-        top_p=1.0 for deterministic output.
+    DEPENDENCY_PARSING (PreparedTask): A prepared task instance configured for dependency
+        parsing. Provide ``temperature=0.0`` and ``top_p=1.0`` when calling the API for
+        deterministic output.
 """
 
-from typing import List
-
 from pydantic import BaseModel, Field
 
-from ...model import PreparedTask
+from openaivec._model import PreparedTask
 
 __all__ = ["DEPENDENCY_PARSING"]
 
@@ -66,15 +64,15 @@ 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")
 
 
 DEPENDENCY_PARSING = PreparedTask(
-    instructions="Parse the syntactic dependencies in the following text. Identify dependency relations between words, determine the root word, and provide a tree representation of the syntactic structure.",
+    instructions="Parse the syntactic dependencies in the following text. Identify dependency "
+    "relations between words, determine the root word, and provide a tree representation of the "
+    "syntactic structure.",
     response_format=DependencyParsing,
-    temperature=0.0,
-    top_p=1.0,
 )

openaivec/task/nlp/keyword_extraction.py

@@ -8,7 +8,7 @@ Example:
 
     ```python
     from openai import OpenAI
-    from openaivec.responses import BatchResponses
+    from openaivec import BatchResponses
     from openaivec.task import nlp
 
     client = OpenAI()
@@ -45,16 +45,14 @@ Example:
     ```
 
 Attributes:
-    KEYWORD_EXTRACTION (PreparedTask): A prepared task instance
-        configured for keyword extraction with temperature=0.0 and
-        top_p=1.0 for deterministic output.
+    KEYWORD_EXTRACTION (PreparedTask): A prepared task instance configured for keyword
+        extraction. Provide ``temperature=0.0`` and ``top_p=1.0`` when calling the API
+        for deterministic output.
 """
 
-from typing import List, Optional
-
 from pydantic import BaseModel, Field
 
-from ...model import PreparedTask
+from openaivec._model import PreparedTask
 
 __all__ = ["KEYWORD_EXTRACTION"]
 
@@ -63,19 +61,18 @@ class Keyword(BaseModel):
     text: str = Field(description="The keyword or phrase")
     score: float = Field(description="Importance score (0.0-1.0)")
     frequency: int = Field(description="Frequency of occurrence in the text")
-    context: Optional[str] = Field(description="Context where the keyword appears")
+    context: str | None = Field(description="Context where the keyword appears")
 
 
 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")
 
 
 KEYWORD_EXTRACTION = PreparedTask(
-    instructions="Extract important keywords and phrases from the following text. Rank them by importance, provide frequency counts, identify main topics, and generate a brief summary.",
+    instructions="Extract important keywords and phrases from the following text. Rank them "
+    "by importance, provide frequency counts, identify main topics, and generate a brief summary.",
     response_format=KeywordExtraction,
-    temperature=0.0,
-    top_p=1.0,
 )

openaivec/task/nlp/morphological_analysis.py

@@ -9,7 +9,7 @@ Example:
 
     ```python
     from openai import OpenAI
-    from openaivec.responses import BatchResponses
+    from openaivec import BatchResponses
     from openaivec.task import nlp
 
     client = OpenAI()
@@ -44,32 +44,30 @@ Example:
     ```
 
 Attributes:
-    MORPHOLOGICAL_ANALYSIS (PreparedTask): A prepared task instance
-        configured for morphological analysis with temperature=0.0 and
-        top_p=1.0 for deterministic output.
+    MORPHOLOGICAL_ANALYSIS (PreparedTask): A prepared task instance configured
+        for morphological analysis. Provide ``temperature=0.0`` and ``top_p=1.0`` to
+        API calls for deterministic output.
 """
 
-from typing import List
-
 from pydantic import BaseModel, Field
 
-from ...model import PreparedTask
+from openaivec._model import PreparedTask
 
 __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)"
     )
 
 
 MORPHOLOGICAL_ANALYSIS = PreparedTask(
-    instructions="Perform morphological analysis on the following text. Break it down into tokens, identify part-of-speech tags, provide lemmatized forms, and extract morphological features for each token.",
+    instructions="Perform morphological analysis on the following text. Break it down into tokens, "
+    "identify part-of-speech tags, provide lemmatized forms, and extract morphological features "
+    "for each token.",
     response_format=MorphologicalAnalysis,
-    temperature=0.0,
-    top_p=1.0,
 )

openaivec/task/nlp/named_entity_recognition.py

@@ -8,7 +8,7 @@ Example:
 
     ```python
     from openai import OpenAI
-    from openaivec.responses import BatchResponses
+    from openaivec import BatchResponses
     from openaivec.task import nlp
 
     client = OpenAI()
@@ -43,16 +43,14 @@ Example:
     ```
 
 Attributes:
-    NAMED_ENTITY_RECOGNITION (PreparedTask): A prepared task instance
-        configured for named entity recognition with temperature=0.0 and
-        top_p=1.0 for deterministic output.
+    NAMED_ENTITY_RECOGNITION (PreparedTask): A prepared task instance configured for named
+        entity recognition. Provide ``temperature=0.0`` and ``top_p=1.0`` to API calls for
+        deterministic output.
 """
 
-from typing import List, Optional
-
 from pydantic import BaseModel, Field
 
-from ...model import PreparedTask
+from openaivec._model import PreparedTask
 
 __all__ = ["NAMED_ENTITY_RECOGNITION"]
 
@@ -62,22 +60,22 @@ class NamedEntity(BaseModel):
     label: str = Field(description="Entity type label")
     start: int = Field(description="Start position in the original text")
     end: int = Field(description="End position in the original text")
-    confidence: Optional[float] = Field(description="Confidence score (0.0-1.0)")
+    confidence: float | None = Field(description="Confidence score (0.0-1.0)")
 
 
 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(
-    instructions="Identify and classify named entities in the following text. Extract persons, organizations, locations, dates, money, percentages, and other miscellaneous entities with their positions and confidence scores.",
+    instructions="Identify and classify named entities in the following text. Extract persons, "
+    "organizations, locations, dates, money, percentages, and other miscellaneous entities "
+    "with their positions and confidence scores.",
     response_format=NamedEntityRecognition,
-    temperature=0.0,
-    top_p=1.0,
 )

openaivec/task/nlp/sentiment_analysis.py

@@ -8,7 +8,7 @@ Example:
 
     ```python
     from openai import OpenAI
-    from openaivec.responses import BatchResponses
+    from openaivec import BatchResponses
     from openaivec.task import nlp
 
     client = OpenAI()
@@ -43,16 +43,16 @@ Example:
     ```
 
 Attributes:
-    SENTIMENT_ANALYSIS (PreparedTask): A prepared task instance
-        configured for sentiment analysis with temperature=0.0 and
-        top_p=1.0 for deterministic output.
+    SENTIMENT_ANALYSIS (PreparedTask): A prepared task instance configured for sentiment
+        analysis. Provide ``temperature=0.0`` and ``top_p=1.0`` to API calls for
+        deterministic output.
 """
 
-from typing import List, Literal
+from typing import Literal
 
 from pydantic import BaseModel, Field
 
-from ...model import PreparedTask
+from openaivec._model import PreparedTask
 
 __all__ = ["SENTIMENT_ANALYSIS"]
 
@@ -62,17 +62,20 @@ 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)")
 
 
 SENTIMENT_ANALYSIS = PreparedTask(
-    instructions="Analyze the sentiment and emotions in the following text. Provide overall sentiment classification, confidence scores, detected emotions, polarity, and subjectivity measures.\n\nIMPORTANT: Provide all analysis in the same language as the input text, except for the predefined categorical fields (sentiment, emotions) which must use the exact English values specified (positive/negative/neutral for sentiment, and joy/sadness/anger/fear/surprise/disgust for emotions).",
+    instructions="Analyze the sentiment and emotions in the following text. Provide overall "
+    "sentiment classification, confidence scores, detected emotions, polarity, and subjectivity "
+    "measures.\n\nIMPORTANT: Provide all analysis in the same language as the input text, except "
+    "for the predefined categorical fields (sentiment, emotions) which must use the exact "
+    "English values specified (positive/negative/neutral for sentiment, and "
+    "joy/sadness/anger/fear/surprise/disgust for emotions).",
     response_format=SentimentAnalysis,
-    temperature=0.0,
-    top_p=1.0,
 )

openaivec/task/nlp/translation.py

@@ -13,7 +13,7 @@ Example:
 
     ```python
     from openai import OpenAI
-    from openaivec.responses import BatchResponses
+    from openaivec import BatchResponses
     from openaivec.task import nlp
 
     client = OpenAI()
@@ -49,8 +49,8 @@ Example:
 
 Attributes:
     MULTILINGUAL_TRANSLATION (PreparedTask): A prepared task instance configured
-        for multilingual translation with temperature=0.0 and top_p=1.0 for
-        deterministic output.
+        for multilingual translation. Provide ``temperature=0.0`` and ``top_p=1.0``
+        to the calling API wrapper for deterministic output.
 
 Note:
     The translation covers 58 languages across major language families. All field
@@ -72,10 +72,9 @@ Note:
     - Other: Basque, Maltese
 """
 
-from openai import BaseModel
-from pydantic import Field
+from pydantic import BaseModel, Field
 
-from ...model import PreparedTask
+from openaivec._model import PreparedTask
 
 __all__ = ["MULTILINGUAL_TRANSLATION"]
 
@@ -157,6 +156,4 @@ class TranslatedString(BaseModel):
 
 instructions = "Translate the following text into multiple languages. "
 
-MULTILINGUAL_TRANSLATION = PreparedTask(
-    instructions=instructions, response_format=TranslatedString, temperature=0.0, top_p=1.0
-)
+MULTILINGUAL_TRANSLATION = PreparedTask(instructions=instructions, response_format=TranslatedString)

openaivec/task/table/__init__.py

@@ -1,3 +1,3 @@
-from .fillna import fillna, FillNaResponse
+from .fillna import FillNaResponse, fillna
 
-__all__ = ["fillna", "FillNaResponse"]
+__all__ = ["fillna", "FillNaResponse"]

openaivec/task/table/fillna.py

@@ -33,7 +33,7 @@ Example:
 
     ```python
     from openai import OpenAI
-    from openaivec.responses import BatchResponses
+    from openaivec import BatchResponses
     from openaivec.task.table import fillna
 
     client = OpenAI()
@@ -65,21 +65,20 @@ Example:
 """
 
 import json
-from typing import Dict, List
 
 import pandas as pd
 from pydantic import BaseModel, Field
 
-from ...model import PreparedTask
-from ...prompt import FewShotPromptBuilder
+from openaivec._model import PreparedTask
+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)
+    samples: pd.DataFrame = df.sample(frac=1).reset_index(drop=True).drop_duplicates()
     samples = samples.dropna(subset=[target_column_name])
 
     for i, row in samples.head(max_examples).iterrows():
@@ -109,7 +108,7 @@ def get_instructions(df: pd.DataFrame, target_column_name: str, max_examples: in
             output_value=json.dumps({"index": row["index"], "output": row["output"]}, ensure_ascii=False),
         )
 
-    return builder.build()
+    return builder.improve().build()
 
 
 class FillNaResponse(BaseModel):
@@ -121,7 +120,8 @@ class FillNaResponse(BaseModel):
 
     index: int = Field(description="Index of the row in the original DataFrame")
     output: int | float | str | bool | None = Field(
-        description="Filled value for the target column. This value should be JSON-compatible and match the target column type in the original DataFrame."
+        description="Filled value for the target column. This value should be JSON-compatible "
+        "and match the target column type in the original DataFrame."
     )
 
 
@@ -146,7 +146,7 @@ def fillna(df: pd.DataFrame, target_column_name: str, max_examples: int = 500) -
         PreparedTask configured for missing value imputation with:
         - Instructions based on DataFrame patterns
         - FillNaResponse format for structured output
-        - Temperature=0.0 and top_p=1.0 for deterministic results
+        - Default deterministic settings (temperature=0.0, top_p=1.0)
 
     Raises:
         ValueError: If target_column_name doesn't exist in DataFrame,
@@ -180,4 +180,4 @@ def fillna(df: pd.DataFrame, target_column_name: str, max_examples: int = 500) -
     if df[target_column_name].notna().sum() == 0:
         raise ValueError(f"Column '{target_column_name}' contains no non-null values for training examples.")
     instructions = get_instructions(df, target_column_name, max_examples)
-    return PreparedTask(instructions=instructions, response_format=FillNaResponse, temperature=0.0, top_p=1.0)
+    return PreparedTask(instructions=instructions, response_format=FillNaResponse)