openaivec 0.13.6__tar.gz → 0.13.7__tar.gz

{openaivec-0.13.6 → openaivec-0.13.7}/.github/copilot-instructions.md

@@ -138,6 +138,32 @@ Don’t
 - Use `asyncio.run` in async tests (mirrors existing tests)
 - Optional integration tests can run with valid API keys; keep unit tests independent of network
 
+## Package Visibility Guidelines (`__all__`)
+
+### Public API Modules
+These modules are part of the public API and should have comprehensive `__all__` declarations:
+
+- `embeddings.py` - Batch embedding processing
+- `model.py` - Task configuration models  
+- `prompt.py` - Few-shot prompt building
+- `responses.py` - Batch response processing
+- `spark.py` - Apache Spark UDF builders
+- `pandas_ext.py` - Pandas DataFrame/Series extensions
+- `task/*` - All task modules (NLP, customer support, table operations)
+
+### Internal Modules
+These modules are for internal use only and should have `__all__ = []`:
+
+- All other modules not listed above (util.py, serialize.py, log.py, provider.py, proxy.py, di.py, optimize.py, etc.)
+
+### `__all__` Best Practices
+
+1. **Public modules**: Include all classes, functions, and constants intended for external use
+2. **Internal modules**: Use `__all__ = []` to explicitly mark as internal-only
+3. **Task modules**: Each task module should export its main classes/functions
+4. **Package `__init__.py`**: Re-export public API from all public modules
+5. **Consistency**: Maintain alphabetical ordering within `__all__` lists
+
 ## Documentation (MkDocs)
 
 - For new developer-facing APIs, update `docs/api/` and consider a short example under `docs/examples/`

{openaivec-0.13.6 → openaivec-0.13.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openaivec
-Version: 0.13.6
+Version: 0.13.7
 Summary: Generative mutation for tabular calculation
 Project-URL: Homepage, https://microsoft.github.io/openaivec/
 Project-URL: Repository, https://github.com/microsoft/openaivec

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/__init__.py

@@ -1,9 +1,14 @@
 from .embeddings import AsyncBatchEmbeddings, BatchEmbeddings
+from .model import PreparedTask
+from .prompt import FewShotPrompt, FewShotPromptBuilder
 from .responses import AsyncBatchResponses, BatchResponses
 
 __all__ = [
-    "BatchResponses",
+    "AsyncBatchEmbeddings",
     "AsyncBatchResponses",
     "BatchEmbeddings",
-    "AsyncBatchEmbeddings",
+    "BatchResponses",
+    "FewShotPrompt",
+    "FewShotPromptBuilder",
+    "PreparedTask",
 ]

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/di.py

@@ -2,6 +2,8 @@ from dataclasses import dataclass, field
 from threading import RLock
 from typing import Any, Callable, Dict, Set, Type, TypeVar
 
+__all__ = []
+
 """Simple dependency injection container with singleton lifecycle management.
 
 This module provides a lightweight dependency injection container that manages

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/log.py

@@ -5,7 +5,7 @@ import uuid
 from logging import Logger
 from typing import Callable
 
-__all__ = ["observe"]
+__all__ = []
 
 
 def observe(logger: Logger):

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/model.py

@@ -1,6 +1,10 @@
 from dataclasses import dataclass
 from typing import Generic, Type, TypeVar
 
+__all__ = [
+    "PreparedTask",
+]
+
 ResponseFormat = TypeVar("ResponseFormat")
 
 

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/optimize.py

@@ -5,6 +5,8 @@ from dataclasses import dataclass, field
 from datetime import datetime, timezone
 from typing import List
 
+__all__ = []
+
 
 @dataclass(frozen=True)
 class PerformanceMetric:
@@ -20,7 +22,7 @@ class BatchSizeSuggester:
     min_batch_size: int = 10
     min_duration: float = 30.0
     max_duration: float = 60.0
-    step_ratio: float = 0.1
+    step_ratio: float = 0.2
     sample_size: int = 4
     _history: List[PerformanceMetric] = field(default_factory=list)
     _lock: threading.RLock = field(default_factory=threading.RLock, repr=False)

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/pandas_ext.py

@@ -48,6 +48,13 @@ import numpy as np
 import pandas as pd
 import tiktoken
 from openai import AsyncOpenAI, OpenAI
+
+__all__ = [
+    "embeddings_model",
+    "responses_model",
+    "use",
+    "use_async",
+]
 from pydantic import BaseModel
 
 from openaivec.embeddings import AsyncBatchEmbeddings, BatchEmbeddings

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/provider.py

@@ -15,6 +15,8 @@ from openaivec.model import (
 )
 from openaivec.util import TextChunker
 
+__all__ = []
+
 CONTAINER = di.Container()
 
 

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/proxy.py

@@ -6,6 +6,8 @@ from typing import Any, Awaitable, Callable, Dict, Generic, List, TypeVar
 
 from openaivec.optimize import BatchSizeSuggester
 
+__all__ = []
+
 S = TypeVar("S", bound=Hashable)
 T = TypeVar("T")
 

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/serialize.py

@@ -29,7 +29,7 @@ from typing import Any, Dict, List, Literal, Type
 
 from pydantic import BaseModel, Field, create_model
 
-__all__ = ["deserialize_base_model", "serialize_base_model"]
+__all__ = []
 
 
 def serialize_base_model(obj: Type[BaseModel]) -> Dict[str, Any]:

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/spark.py

@@ -12,6 +12,15 @@ improved performance in I/O-bound operations.
 automatically cache duplicate inputs within each partition, significantly reducing
 API calls and costs when processing datasets with overlapping content.
 
+__all__ = [
+    "count_tokens_udf",
+    "embeddings_udf",
+    "responses_udf",
+    "similarity_udf",
+    "split_to_chunks_udf",
+    "task_udf",
+]
+
 ## Setup
 
 First, obtain a Spark session and configure authentication:

{openaivec-0.13.6 → openaivec-0.13.7}/src/openaivec/util.py

@@ -8,6 +8,8 @@ from typing import Awaitable, Callable, List, Type, TypeVar
 import numpy as np
 import tiktoken
 
+__all__ = []
+
 T = TypeVar("T")
 U = TypeVar("U")
 V = TypeVar("V")

{openaivec-0.13.6 → openaivec-0.13.7}/tests/test_optimize.py

@@ -34,7 +34,7 @@ class TestBatchSizeSuggester:
         assert suggester.min_batch_size == 10
         assert suggester.min_duration == 30.0
         assert suggester.max_duration == 60.0
-        assert suggester.step_ratio == 0.1
+        assert suggester.step_ratio == 0.2
         assert suggester.sample_size == 4
         assert len(suggester._history) == 0
         assert suggester._batch_size_changed_at is None