openaivec 0.14.12__py3-none-any.whl → 0.14.13__py3-none-any.whl

openaivec/spark.py

@@ -134,6 +134,7 @@ import numpy as np
 import pandas as pd
 import tiktoken
 from pydantic import BaseModel
+from pyspark import SparkContext
 from pyspark.sql import SparkSession
 from pyspark.sql.pandas.functions import pandas_udf
 from pyspark.sql.types import ArrayType, BooleanType, FloatType, IntegerType, StringType, StructField, StructType
@@ -180,7 +181,10 @@ def setup(
             If provided, registers `EmbeddingsModelName` in the DI container.
     """
 
-    sc = spark.sparkContext
+    CONTAINER.register(SparkSession, lambda: spark)
+    CONTAINER.register(SparkContext, lambda: CONTAINER.resolve(SparkSession).sparkContext)
+
+    sc = CONTAINER.resolve(SparkContext)
     sc.environment["OPENAI_API_KEY"] = api_key
 
     os.environ["OPENAI_API_KEY"] = api_key
@@ -219,7 +223,10 @@ def setup_azure(
             If provided, registers `EmbeddingsModelName` in the DI container.
     """
 
-    sc = spark.sparkContext
+    CONTAINER.register(SparkSession, lambda: spark)
+    CONTAINER.register(SparkContext, lambda: CONTAINER.resolve(SparkSession).sparkContext)
+
+    sc = CONTAINER.resolve(SparkContext)
     sc.environment["AZURE_OPENAI_API_KEY"] = api_key
     sc.environment["AZURE_OPENAI_BASE_URL"] = base_url
     sc.environment["AZURE_OPENAI_API_VERSION"] = api_version
@@ -317,8 +324,6 @@ def responses_udf(
     response_format: type[ResponseFormat] = str,
     model_name: str = CONTAINER.resolve(ResponsesModelName).value,
     batch_size: int | None = None,
-    temperature: float | None = 0.0,
-    top_p: float = 1.0,
     max_concurrency: int = 8,
     **api_kwargs,
 ) -> UserDefinedFunction:
@@ -353,17 +358,14 @@ def responses_udf(
             Defaults to None (automatic batch size optimization that dynamically
             adjusts based on execution time, targeting 30-60 seconds per batch).
             Set to a positive integer (e.g., 32-128) for fixed batch size.
-        temperature (float): Sampling temperature (0.0 to 2.0). Defaults to 0.0.
-        top_p (float): Nucleus sampling parameter. Defaults to 1.0.
         max_concurrency (int): Maximum number of concurrent API requests **PER EXECUTOR**.
             Total cluster concurrency = max_concurrency × number_of_executors.
             Higher values increase throughput but may hit OpenAI rate limits.
             Recommended: 4-12 per executor. Defaults to 8.
-
-    Additional Keyword Args:
-        Arbitrary OpenAI Responses API parameters (e.g. ``frequency_penalty``, ``presence_penalty``,
-        ``seed``, ``max_output_tokens``, etc.) are forwarded verbatim to the underlying API calls.
-        These parameters are applied to all API requests made by the UDF.
+        **api_kwargs: Additional OpenAI API parameters (e.g. ``temperature``, ``top_p``,
+            ``frequency_penalty``, ``presence_penalty``, ``seed``, ``max_output_tokens``, etc.)
+            forwarded verbatim to the underlying API calls. These parameters are applied to
+            all API requests made by the UDF.
 
     Returns:
         UserDefinedFunction: A Spark pandas UDF configured to generate responses asynchronously.
@@ -399,8 +401,6 @@ def responses_udf(
                         part.aio.responses_with_cache(
                             instructions=instructions,
                             response_format=response_format,
-                            temperature=temperature,
-                            top_p=top_p,
                             cache=cache,
                             **api_kwargs,
                         )
@@ -427,8 +427,6 @@ def responses_udf(
                         part.aio.responses_with_cache(
                             instructions=instructions,
                             response_format=str,
-                            temperature=temperature,
-                            top_p=top_p,
                             cache=cache,
                             **api_kwargs,
                         )
@@ -460,7 +458,7 @@ def task_udf(
 
     Args:
         task (PreparedTask): A predefined task configuration containing instructions,
-            response format, temperature, and top_p settings.
+            response format, and API parameters.
         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 configured model in DI container.
         batch_size (int | None): Number of rows per async batch request within each partition.
@@ -474,10 +472,10 @@ def task_udf(
             Recommended: 4-12 per executor. Defaults to 8.
 
     Additional Keyword Args:
-        Arbitrary OpenAI Responses API parameters (e.g. ``frequency_penalty``, ``presence_penalty``,
-        ``seed``, ``max_output_tokens``, etc.) are forwarded verbatim to the underlying API calls.
-        These parameters are applied to all API requests made by the UDF and override any
-        parameters set in the task configuration.
+        Arbitrary OpenAI Responses API parameters (e.g. ``temperature``, ``top_p``,
+        ``frequency_penalty``, ``presence_penalty``, ``seed``, ``max_output_tokens``, etc.)
+        are forwarded verbatim to the underlying API calls. These parameters are applied to
+        all API requests made by the UDF and override any parameters set in the task configuration.
 
     Returns:
         UserDefinedFunction: A Spark pandas UDF configured to execute the specified task
@@ -498,15 +496,16 @@ def task_udf(
         **Automatic Caching**: Duplicate inputs within each partition are cached,
         reducing API calls and costs significantly on datasets with repeated content.
     """
+    # Merge task's api_kwargs with caller's api_kwargs (caller takes precedence)
+    merged_kwargs = {**task.api_kwargs, **api_kwargs}
+
     return responses_udf(
         instructions=task.instructions,
         response_format=task.response_format,
         model_name=model_name,
         batch_size=batch_size,
-        temperature=task.temperature,
-        top_p=task.top_p,
         max_concurrency=max_concurrency,
-        **api_kwargs,
+        **merged_kwargs,
     )
 
 
@@ -532,15 +531,13 @@ def infer_schema(
         InferredSchema: An object containing the inferred schema and response format.
     """
 
-    from pyspark.sql import SparkSession
-
-    spark = SparkSession.builder.getOrCreate()
+    spark = CONTAINER.resolve(SparkSession)
     examples: list[str] = (
         spark.table(example_table_name).rdd.map(lambda row: row[example_field_name]).takeSample(False, max_examples)
     )
 
     input = SchemaInferenceInput(
-        purpose=instructions,
+        instructions=instructions,
         examples=examples,
     )
     inferer = CONTAINER.resolve(SchemaInferer)
@@ -555,8 +552,6 @@ def parse_udf(
     max_examples: int = 100,
     model_name: str = CONTAINER.resolve(ResponsesModelName).value,
     batch_size: int | None = None,
-    temperature: float | None = 0.0,
-    top_p: float = 1.0,
     max_concurrency: int = 8,
     **api_kwargs,
 ) -> UserDefinedFunction:
@@ -586,17 +581,15 @@ def parse_udf(
             Defaults to None (automatic batch size optimization that dynamically
             adjusts based on execution time, targeting 30-60 seconds per batch).
             Set to a positive integer (e.g., 32-128) for fixed batch size
-        temperature (float | None): Sampling temperature (0.0 to 2.0). Defaults to 0.0.
-        top_p (float): Nucleus sampling parameter. Defaults to 1.0.
         max_concurrency (int): Maximum number of concurrent API requests **PER EXECUTOR**.
             Total cluster concurrency = max_concurrency × number_of_executors.
             Higher values increase throughput but may hit OpenAI rate limits.
             Recommended: 4-12 per executor. Defaults to 8.
-    Additional Keyword Args:
-        Arbitrary OpenAI Responses API parameters (e.g. ``frequency_penalty``, ``presence_penalty``,
-        ``seed``, ``max_output_tokens``, etc.) are forwarded verbatim to the underlying API calls.
-        These parameters are applied to all API requests made by the UDF and override any
-        parameters set in the response_format or example data.
+        **api_kwargs: Additional OpenAI API parameters (e.g. ``temperature``, ``top_p``,
+            ``frequency_penalty``, ``presence_penalty``, ``seed``, ``max_output_tokens``, etc.)
+            forwarded verbatim to the underlying API calls. These parameters are applied to
+            all API requests made by the UDF and override any parameters set in the
+            response_format or example data.
     Returns:
         UserDefinedFunction: A Spark pandas UDF configured to parse responses asynchronously.
             Output schema is `StringType` for str response format or a struct derived from
@@ -623,8 +616,6 @@ def parse_udf(
         response_format=schema.model if schema else response_format,
         model_name=model_name,
         batch_size=batch_size,
-        temperature=temperature,
-        top_p=top_p,
         max_concurrency=max_concurrency,
         **api_kwargs,
     )
@@ -634,6 +625,7 @@ def embeddings_udf(
     model_name: str = CONTAINER.resolve(EmbeddingsModelName).value,
     batch_size: int | None = None,
     max_concurrency: int = 8,
+    **api_kwargs,
 ) -> UserDefinedFunction:
     """Create an asynchronous Spark pandas UDF for generating embeddings.
 
@@ -669,6 +661,7 @@ def embeddings_udf(
             Total cluster concurrency = max_concurrency × number_of_executors.
             Higher values increase throughput but may hit OpenAI rate limits.
             Recommended: 4-12 per executor. Defaults to 8.
+        **api_kwargs: Additional OpenAI API parameters (e.g., dimensions for text-embedding-3 models).
 
     Returns:
         UserDefinedFunction: A Spark pandas UDF configured to generate embeddings asynchronously
@@ -695,7 +688,7 @@ def embeddings_udf(
 
         try:
             for part in col:
-                embeddings: pd.Series = asyncio.run(part.aio.embeddings_with_cache(cache=cache))
+                embeddings: pd.Series = asyncio.run(part.aio.embeddings_with_cache(cache=cache, **api_kwargs))
                 yield embeddings.map(lambda x: x.tolist())
         finally:
             asyncio.run(cache.clear())

openaivec/task/__init__.py

@@ -117,7 +117,7 @@ All tasks are built using the `PreparedTask` dataclass:
 @dataclass(frozen=True)
 class PreparedTask:
     instructions: str           # Detailed prompt for the LLM
-    response_format: Type[ResponseFormat]    # Pydantic model or str for structured/plain output
+    response_format: type[ResponseFormat]    # Pydantic model or str for structured/plain output
     temperature: float = 0.0    # Sampling temperature
     top_p: float = 1.0         # Nucleus sampling parameter
 ```

openaivec/task/customer_support/customer_sentiment.py

@@ -95,15 +95,12 @@ class CustomerSentiment(BaseModel):
     )
 
 
-def customer_sentiment(
-    business_context: str = "general customer support", temperature: float = 0.0, top_p: float = 1.0
-) -> PreparedTask:
+def customer_sentiment(business_context: str = "general customer support", **api_kwargs) -> PreparedTask:
     """Create a configurable customer sentiment analysis task.
 
     Args:
         business_context (str): Business context for sentiment analysis.
-        temperature (float): Sampling temperature (0.0-1.0).
-        top_p (float): Nucleus sampling parameter (0.0-1.0).
+        **api_kwargs: Additional OpenAI API parameters (temperature, top_p, etc.).
 
     Returns:
         PreparedTask configured for customer sentiment analysis.
@@ -169,10 +166,8 @@ values like "positive" for sentiment.
 
 Provide comprehensive sentiment analysis with business context and recommended response strategy."""
 
-    return PreparedTask(
-        instructions=instructions, response_format=CustomerSentiment, temperature=temperature, top_p=top_p
-    )
+    return PreparedTask(instructions=instructions, response_format=CustomerSentiment, api_kwargs=api_kwargs)
 
 
 # Backward compatibility - default configuration
-CUSTOMER_SENTIMENT = customer_sentiment()
+CUSTOMER_SENTIMENT = customer_sentiment(temperature=0.0, top_p=1.0)

openaivec/task/customer_support/inquiry_classification.py

@@ -119,8 +119,7 @@ def inquiry_classification(
     priority_rules: Dict[str, str] | None = None,
     business_context: str = "general customer support",
     custom_keywords: Dict[str, list[str]] | None = None,
-    temperature: float = 0.0,
-    top_p: float = 1.0,
+    **api_kwargs,
 ) -> PreparedTask:
     """Create a configurable inquiry classification task.
 
@@ -133,8 +132,8 @@ def inquiry_classification(
             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.
-        temperature (float): Sampling temperature (0.0-1.0).
-        top_p (float): Nucleus sampling parameter (0.0-1.0).
+        **api_kwargs: Additional keyword arguments to pass to the OpenAI API,
+            such as temperature, top_p, etc.
 
     Returns:
         PreparedTask configured for inquiry classification.
@@ -254,10 +253,8 @@ language where appropriate, but priority must use English values like "high".
 
 Provide accurate classification with detailed reasoning."""
 
-    return PreparedTask(
-        instructions=instructions, response_format=InquiryClassification, temperature=temperature, top_p=top_p
-    )
+    return PreparedTask(instructions=instructions, response_format=InquiryClassification, api_kwargs=api_kwargs)
 
 
 # Backward compatibility - default configuration
-INQUIRY_CLASSIFICATION = inquiry_classification()
+INQUIRY_CLASSIFICATION = inquiry_classification(temperature=0.0, top_p=1.0)

openaivec/task/customer_support/inquiry_summary.py

@@ -87,16 +87,15 @@ class InquirySummary(BaseModel):
 def inquiry_summary(
     summary_length: str = "concise",
     business_context: str = "general customer support",
-    temperature: float = 0.0,
-    top_p: float = 1.0,
+    **api_kwargs,
 ) -> PreparedTask:
     """Create a configurable inquiry summary task.
 
     Args:
         summary_length (str): Length of summary (concise, detailed, bullet_points).
         business_context (str): Business context for summary.
-        temperature (float): Sampling temperature (0.0-1.0).
-        top_p (float): Nucleus sampling parameter (0.0-1.0).
+        **api_kwargs: Additional keyword arguments to pass to the OpenAI API,
+            such as temperature, top_p, etc.
 
     Returns:
         PreparedTask configured for inquiry summarization.
@@ -163,8 +162,8 @@ input is in German, provide all summary content in German, but use English value
 
 Provide accurate, actionable summary that enables efficient support resolution."""
 
-    return PreparedTask(instructions=instructions, response_format=InquirySummary, temperature=temperature, top_p=top_p)
+    return PreparedTask(instructions=instructions, response_format=InquirySummary, api_kwargs=api_kwargs)
 
 
 # Backward compatibility - default configuration
-INQUIRY_SUMMARY = inquiry_summary()
+INQUIRY_SUMMARY = inquiry_summary(temperature=0.0, top_p=1.0)

openaivec/task/customer_support/intent_analysis.py

@@ -100,15 +100,13 @@ class IntentAnalysis(BaseModel):
     )
 
 
-def intent_analysis(
-    business_context: str = "general customer support", temperature: float = 0.0, top_p: float = 1.0
-) -> PreparedTask:
+def intent_analysis(business_context: str = "general customer support", **api_kwargs) -> PreparedTask:
     """Create a configurable intent analysis task.
 
     Args:
         business_context (str): Business context for intent analysis.
-        temperature (float): Sampling temperature (0.0-1.0).
-        top_p (float): Nucleus sampling parameter (0.0-1.0).
+        **api_kwargs: Additional keyword arguments to pass to the OpenAI API,
+            such as temperature, top_p, etc.
 
     Returns:
         PreparedTask configured for intent analysis.
@@ -171,8 +169,8 @@ next_steps, and reasoning in Japanese, but use English values like "get_help" fo
 
 Provide comprehensive intent analysis with actionable recommendations."""
 
-    return PreparedTask(instructions=instructions, response_format=IntentAnalysis, temperature=temperature, top_p=top_p)
+    return PreparedTask(instructions=instructions, response_format=IntentAnalysis, api_kwargs=api_kwargs)
 
 
 # Backward compatibility - default configuration
-INTENT_ANALYSIS = intent_analysis()
+INTENT_ANALYSIS = intent_analysis(temperature=0.0, top_p=1.0)

openaivec/task/customer_support/response_suggestion.py

@@ -92,8 +92,7 @@ def response_suggestion(
     response_style: str = "professional",
     company_name: str = "our company",
     business_context: str = "general customer support",
-    temperature: float = 0.0,
-    top_p: float = 1.0,
+    **api_kwargs,
 ) -> PreparedTask:
     """Create a configurable response suggestion task.
 
@@ -101,8 +100,8 @@ def response_suggestion(
         response_style (str): Style of response (professional, friendly, empathetic, formal).
         company_name (str): Name of the company for personalization.
         business_context (str): Business context for responses.
-        temperature (float): Sampling temperature (0.0-1.0).
-        top_p (float): Nucleus sampling parameter (0.0-1.0).
+        **api_kwargs: Additional keyword arguments to pass to the OpenAI API,
+            such as temperature, top_p, etc.
 
     Returns:
         PreparedTask configured for response suggestions.
@@ -190,10 +189,8 @@ but use English values like "empathetic" for tone.
 Generate helpful, professional response that moves toward resolution while maintaining
 positive customer relationship."""
 
-    return PreparedTask(
-        instructions=instructions, response_format=ResponseSuggestion, temperature=temperature, top_p=top_p
-    )
+    return PreparedTask(instructions=instructions, response_format=ResponseSuggestion, api_kwargs=api_kwargs)
 
 
 # Backward compatibility - default configuration
-RESPONSE_SUGGESTION = response_suggestion()
+RESPONSE_SUGGESTION = response_suggestion(temperature=0.0, top_p=1.0)

openaivec/task/customer_support/urgency_analysis.py

@@ -135,8 +135,7 @@ def urgency_analysis(
     business_context: str = "general customer support",
     business_hours: str = "24/7 support",
     sla_rules: Dict[str, str] | None = None,
-    temperature: float = 0.0,
-    top_p: float = 1.0,
+    **api_kwargs,
 ) -> PreparedTask:
     """Create a configurable urgency analysis task.
 
@@ -149,8 +148,8 @@ def urgency_analysis(
         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.
-        temperature (float): Sampling temperature (0.0-1.0).
-        top_p (float): Nucleus sampling parameter (0.0-1.0).
+        **api_kwargs: Additional keyword arguments to pass to the OpenAI API,
+            such as temperature, top_p, etc.
 
     Returns:
         PreparedTask configured for urgency analysis.
@@ -287,10 +286,8 @@ urgency_level.
 
 Provide detailed analysis with clear reasoning for urgency level and response time recommendations."""
 
-    return PreparedTask(
-        instructions=instructions, response_format=UrgencyAnalysis, temperature=temperature, top_p=top_p
-    )
+    return PreparedTask(instructions=instructions, response_format=UrgencyAnalysis, api_kwargs=api_kwargs)
 
 
 # Backward compatibility - default configuration
-URGENCY_ANALYSIS = urgency_analysis()
+URGENCY_ANALYSIS = urgency_analysis(temperature=0.0, top_p=1.0)

openaivec/task/nlp/dependency_parsing.py

@@ -75,6 +75,5 @@ DEPENDENCY_PARSING = PreparedTask(
     "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,
+    api_kwargs={"temperature": 0.0, "top_p": 1.0},
 )

openaivec/task/nlp/keyword_extraction.py

@@ -75,6 +75,5 @@ 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.",
     response_format=KeywordExtraction,
-    temperature=0.0,
-    top_p=1.0,
+    api_kwargs={"temperature": 0.0, "top_p": 1.0},
 )

openaivec/task/nlp/morphological_analysis.py

@@ -70,6 +70,5 @@ MORPHOLOGICAL_ANALYSIS = PreparedTask(
     "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,
+    api_kwargs={"temperature": 0.0, "top_p": 1.0},
 )

openaivec/task/nlp/named_entity_recognition.py

@@ -78,6 +78,5 @@ NAMED_ENTITY_RECOGNITION = PreparedTask(
     "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,
+    api_kwargs={"temperature": 0.0, "top_p": 1.0},
 )

openaivec/task/nlp/sentiment_analysis.py

@@ -78,6 +78,5 @@ SENTIMENT_ANALYSIS = PreparedTask(
     "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,
+    api_kwargs={"temperature": 0.0, "top_p": 1.0},
 )

openaivec/task/nlp/translation.py

@@ -157,5 +157,5 @@ 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
+    instructions=instructions, response_format=TranslatedString, api_kwargs={"temperature": 0.0, "top_p": 1.0}
 )

openaivec/task/table/fillna.py

@@ -125,7 +125,7 @@ class FillNaResponse(BaseModel):
     )
 
 
-def fillna(df: pd.DataFrame, target_column_name: str, max_examples: int = 500) -> PreparedTask:
+def fillna(df: pd.DataFrame, target_column_name: str, max_examples: int = 500, **api_kwargs) -> PreparedTask:
     """Create a prepared task for filling missing values in a DataFrame column.
 
     Analyzes the provided DataFrame to understand data patterns and creates
@@ -141,12 +141,14 @@ def fillna(df: pd.DataFrame, target_column_name: str, max_examples: int = 500) -
         max_examples (int): Maximum number of example rows to use for few-shot
             learning. Defaults to 500. Higher values provide more context
             but increase token usage and processing time.
+        **api_kwargs: Additional keyword arguments to pass to the OpenAI API,
+            such as temperature, top_p, etc.
 
     Returns:
         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 +182,7 @@ 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)
+    # Set default values for deterministic results if not provided
+    if not api_kwargs:
+        api_kwargs = {"temperature": 0.0, "top_p": 1.0}
+    return PreparedTask(instructions=instructions, response_format=FillNaResponse, api_kwargs=api_kwargs)

{openaivec-0.14.12.dist-info → openaivec-0.14.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openaivec
-Version: 0.14.12
+Version: 0.14.13
 Summary: Generative mutation for tabular calculation
 Project-URL: Homepage, https://microsoft.github.io/openaivec/
 Project-URL: Repository, https://github.com/microsoft/openaivec

openaivec-0.14.13.dist-info/RECORD

@@ -0,0 +1,37 @@
+openaivec/__init__.py,sha256=mXCGNNTjYbmE4CAXGvAs78soxUsoy_mxxnvaCk_CL6Y,361
+openaivec/_di.py,sha256=Cl1ZoNBlQsJL1bpzoMDl08uT9pZFVSlqOdLbS3_MwPE,11462
+openaivec/_dynamic.py,sha256=7ZaC59w2Edemnao57XeZVO4qmSOA-Kus6TchZC3Dd5o,14821
+openaivec/_embeddings.py,sha256=nirLqOu69fTB7aSCYhbbRbwAA6ggwEYJiQoPDsHqAqQ,8200
+openaivec/_log.py,sha256=LHNs6AbJzM4weaRARZFroigxR6D148d7WSIMLk1IhbU,1439
+openaivec/_model.py,sha256=71oiENUKwpY58ilj1LE7fDOAhs7PUSiZRiUHKUIuu7Y,3235
+openaivec/_optimize.py,sha256=3nS8VehbS7iGC1tPDDQh-iAgyKHbVYmMbCRBWM77U_U,3827
+openaivec/_prompt.py,sha256=NWE7jZKYphkD856haynJLmRadPugJ68emT42pd7Ciso,20633
+openaivec/_provider.py,sha256=8z8gPYY5-Z7rzDlj_NC6hR__DUqVAH7VLHJn6LalzRg,6158
+openaivec/_proxy.py,sha256=AiGuC1MCFjZCRXCac-pHUI3Np3nf1HIpWY6nC9ZVCFY,29671
+openaivec/_responses.py,sha256=qBrYv4qblDIs5dRvj9t96r8UfAJmy4ZvtAe6csNZ7oM,20412
+openaivec/_schema.py,sha256=iOeR5J_ihZRDZtzmqvOK1ZtInKcx4OnoR38DB3VmmQw,15666
+openaivec/_serialize.py,sha256=u2Om94Sc_QgJkTlW2BAGw8wd6gYDhc6IRqvS-qevFSs,8399
+openaivec/_util.py,sha256=XfueAycVCQvgRLS7wF7e306b53lebORvZOBzbQjy4vE,6438
+openaivec/pandas_ext.py,sha256=r2jpFqDnWcQYK3pMv5hCtOStOMltccDyLkpprLmIOls,85715
+openaivec/spark.py,sha256=zaEivVOe3ukG8coa9JEUyISQ1YcMqCvAbhaarvn2SOM,32507
+openaivec/task/__init__.py,sha256=RkYIKrcE83M_9Um9cSMkeGzL9kPRAovajfRvr31YxLE,6178
+openaivec/task/customer_support/__init__.py,sha256=KWfGyXPdZyfGdRH17x7hPpJJ1N2EP9PPhZx0fvBAwSI,884
+openaivec/task/customer_support/customer_sentiment.py,sha256=d8spZUtImjePK0xWGvIW98ghbdyOZ0KEZmaUpG8QB7M,7532
+openaivec/task/customer_support/inquiry_classification.py,sha256=NKz1oTm06eU6W-plHe3T3o20lCk6M2NemVXZ4Y_IozU,9602
+openaivec/task/customer_support/inquiry_summary.py,sha256=8X1J8lZwlgX6s02cs86-K0moZ5gTrX7E7WEKiY2vpiQ,6896
+openaivec/task/customer_support/intent_analysis.py,sha256=Jnokzi0wTlHpuTRl5uqxdoHClYU71b9iFTzn3KNeNVM,7478
+openaivec/task/customer_support/response_suggestion.py,sha256=IykZE-BJ_ENhe5frnVl4bQKpArwOuNAITGlBxlu62c0,8306
+openaivec/task/customer_support/urgency_analysis.py,sha256=fdBT0Ud-InGqou-ZuFcVc3EpUNAq5N55_Q9D6D74WlQ,11531
+openaivec/task/nlp/__init__.py,sha256=QoQ0egEK9IEh5hdrE07rZ_KCmC0gy_2FPrWJYRWiipY,512
+openaivec/task/nlp/dependency_parsing.py,sha256=V7pd4_EbBBvdpnFDkfZh08u7kfJ7XJLq_qLkec48yr0,2832
+openaivec/task/nlp/keyword_extraction.py,sha256=e6niCt8XU0EPJLGYOJXQvbfWtl7w9CgfnCE188kecb4,2819
+openaivec/task/nlp/morphological_analysis.py,sha256=qTFFBkFP8CRZU87S59ju5ygXWlEBCtjYlH9Su7czLjs,2416
+openaivec/task/nlp/named_entity_recognition.py,sha256=9BFKYk0PZlyNN8pItGIEFecvZew4K_F5GgY5Ub8xDtM,3052
+openaivec/task/nlp/sentiment_analysis.py,sha256=u-zpqAaQYcr7I3mqMv_CTJXkfxtoLft3qm-qwmqb_p4,3100
+openaivec/task/nlp/translation.py,sha256=kgWj2oN8pUId3vuHTJNx636gB49AGEKXWICA_XJgE_0,6628
+openaivec/task/table/__init__.py,sha256=kJz15WDJXjyC7UIHKBvlTRhCf347PCDMH5T5fONV2sU,83
+openaivec/task/table/fillna.py,sha256=zL6m5hGD4kamV7qHETnn__B59wIY540Ks0EzNgUJgdI,6888
+openaivec-0.14.13.dist-info/METADATA,sha256=rB_WJhIVX11WUoA-r2Ryn57QIuTWj0q0JhjPlz6wXv4,28216
+openaivec-0.14.13.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+openaivec-0.14.13.dist-info/licenses/LICENSE,sha256=ws_MuBL-SCEBqPBFl9_FqZkaaydIJmxHrJG2parhU4M,1141
+openaivec-0.14.13.dist-info/RECORD,,

openaivec-0.14.12.dist-info/RECORD

@@ -1,37 +0,0 @@
-openaivec/__init__.py,sha256=mXCGNNTjYbmE4CAXGvAs78soxUsoy_mxxnvaCk_CL6Y,361
-openaivec/_di.py,sha256=Cl1ZoNBlQsJL1bpzoMDl08uT9pZFVSlqOdLbS3_MwPE,11462
-openaivec/_dynamic.py,sha256=7ZaC59w2Edemnao57XeZVO4qmSOA-Kus6TchZC3Dd5o,14821
-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=8z8gPYY5-Z7rzDlj_NC6hR__DUqVAH7VLHJn6LalzRg,6158
-openaivec/_proxy.py,sha256=AiGuC1MCFjZCRXCac-pHUI3Np3nf1HIpWY6nC9ZVCFY,29671
-openaivec/_responses.py,sha256=lVJRa_Uc7hQJnYJRgumqwBbu6GToZqsLFS6tIAFO1Fc,24014
-openaivec/_schema.py,sha256=RKjDPqet1TlReYibah0R0NIvCV1VWN5SZxiaBeV0gCY,15492
-openaivec/_serialize.py,sha256=u2Om94Sc_QgJkTlW2BAGw8wd6gYDhc6IRqvS-qevFSs,8399
-openaivec/_util.py,sha256=XfueAycVCQvgRLS7wF7e306b53lebORvZOBzbQjy4vE,6438
-openaivec/pandas_ext.py,sha256=fjBW_TU4zsew3j7g7x67t9ESCwZ0fIuxbh9bZdOmRA0,85407
-openaivec/spark.py,sha256=V0Gg9b9Q-2ycet33ENAN21aA-GltNj57tWoE2pCZIRQ,32601
-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-0.14.12.dist-info/METADATA,sha256=GC5evUtog4LhK1XhJXfF-jO9DeyDq7l9Ii8KN1sVIBo,28216
-openaivec-0.14.12.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-openaivec-0.14.12.dist-info/licenses/LICENSE,sha256=ws_MuBL-SCEBqPBFl9_FqZkaaydIJmxHrJG2parhU4M,1141
-openaivec-0.14.12.dist-info/RECORD,,