pixeltable 0.2.20__py3-none-any.whl → 0.2.22__py3-none-any.whl

pixeltable/utils/filecache.py

@@ -77,8 +77,8 @@ class FileCache:
     evicted_working_set_keys: set[str]
     new_redownload_witnessed: bool  # whether a new re-download has occurred since the last time a warning was issued
 
-    ColumnStats = namedtuple('FileCacheColumnStats', ('tbl_id', 'col_id', 'num_files', 'total_size'))
-    CacheStats = namedtuple(
+    FileCacheColumnStats = namedtuple('FileCacheColumnStats', ('tbl_id', 'col_id', 'num_files', 'total_size'))
+    FileCacheStats = namedtuple(
         'FileCacheStats',
         ('total_size', 'num_requests', 'num_hits', 'num_evictions', 'column_stats')
     )
@@ -96,7 +96,7 @@ class FileCache:
     def __init__(self):
         self.cache = OrderedDict()
         self.total_size = 0
-        self.capacity_bytes = Env.get()._file_cache_size_g * (1 << 30)
+        self.capacity_bytes = int(Env.get()._file_cache_size_g * (1 << 30))
         self.num_requests = 0
         self.num_hits = 0
         self.num_evictions = 0
@@ -174,7 +174,7 @@ class FileCache:
         path = entry.path
         path.touch(exist_ok=True)
         file_info = os.stat(str(path))
-        entry.last_used = file_info.st_mtime
+        entry.last_used = datetime.fromtimestamp(file_info.st_mtime)
         self.cache.move_to_end(key, last=True)
         self.num_hits += 1
         self.keys_retrieved.add(key)
@@ -195,7 +195,7 @@ class FileCache:
             self.evicted_working_set_keys.add(key)
             self.new_redownload_witnessed = True
         self.keys_retrieved.add(key)
-        entry = CacheEntry(key, tbl_id, col_id, file_info.st_size, file_info.st_mtime, path.suffix)
+        entry = CacheEntry(key, tbl_id, col_id, file_info.st_size, datetime.fromtimestamp(file_info.st_mtime), path.suffix)
         self.cache[key] = entry
         self.total_size += entry.size
         new_path = entry.path
@@ -223,19 +223,19 @@ class FileCache:
         self.capacity_bytes = capacity_bytes
         self.ensure_capacity(0)  # evict entries if necessary
 
-    def stats(self) -> CacheStats:
+    def stats(self) -> FileCacheStats:
         # collect column stats
         # (tbl_id, col_id) -> (num_files, total_size)
-        d: dict[tuple[int, int], list[int]] = defaultdict(lambda: [0, 0])
+        d: dict[tuple[UUID, int], list[int]] = defaultdict(lambda: [0, 0])
         for entry in self.cache.values():
             t = d[(entry.tbl_id, entry.col_id)]
             t[0] += 1
             t[1] += entry.size
         col_stats = [
-            self.ColumnStats(tbl_id, col_id, num_files, size) for (tbl_id, col_id), (num_files, size) in d.items()
+            self.FileCacheColumnStats(tbl_id, col_id, num_files, size) for (tbl_id, col_id), (num_files, size) in d.items()
         ]
         col_stats.sort(key=lambda e: e[3], reverse=True)
-        return self.CacheStats(self.total_size, self.num_requests, self.num_hits, self.num_evictions, col_stats)
+        return self.FileCacheStats(self.total_size, self.num_requests, self.num_hits, self.num_evictions, col_stats)
 
     def debug_print(self) -> None:
         for entry in self.cache.values():

pixeltable/utils/formatter.py

@@ -1,16 +1,16 @@
 import base64
 import html
+import io
 import json
 import logging
 import mimetypes
 from typing import Any, Callable, Optional
 
+import av  # type: ignore[import-untyped]
+import numpy as np
 import PIL
 import PIL.Image as Image
-import cv2
-import numpy as np
 
-import io
 import pixeltable.type_system as ts
 from pixeltable.utils.http_server import get_file_uri
 
@@ -159,17 +159,16 @@ class Formatter:
         # the video itself is not accessible.
         # TODO(aaron-siegel): If the video is backed by a concrete external URL,
         # should we link to that instead?
-        video_reader = cv2.VideoCapture(str(file_path))
-        if video_reader.isOpened():
-            status, img_array = video_reader.read()
-            if status:
-                img_array = cv2.cvtColor(img_array, cv2.COLOR_BGR2RGB)
-                thumb = PIL.Image.fromarray(img_array)
+        with av.open(file_path) as container:
+            try:
+                thumb = next(container.decode(video=0)).to_image()
+                assert isinstance(thumb, Image.Image)
                 with io.BytesIO() as buffer:
                     thumb.save(buffer, 'jpeg')
                     thumb_base64 = base64.b64encode(buffer.getvalue()).decode()
                     thumb_tag = f'poster="data:image/jpeg;base64,{thumb_base64}"'
-            video_reader.release()
+            except Exception:
+                pass
         if self.__num_rows > 1:
             width = 320
         elif self.__num_cols > 1:
@@ -201,7 +200,7 @@ class Formatter:
         # try generating a thumbnail for different types and use that if successful
         if file_path.lower().endswith('.pdf'):
             try:
-                import fitz
+                import fitz  # type: ignore[import-untyped]
 
                 doc = fitz.open(file_path)
                 p = doc.get_page_pixmap(0)

pixeltable/utils/http_server.py

@@ -1,11 +1,8 @@
 import http
 import http.server
 import logging
-import urllib
-import posixpath
 import pathlib
-import os
-import string
+import urllib
 
 _logger = logging.getLogger('pixeltable.http.server')
 
@@ -43,7 +40,7 @@ class AbsolutePathHandler(http.server.SimpleHTTPRequestHandler):
     def log_message(self, format, *args) -> None:
         """override logging to stderr in http.server.BaseHTTPRequestHandler"""
         message = format % args
-        _logger.info(message.translate(self._control_char_table))
+        _logger.info(message.translate(self._control_char_table))  # type: ignore[attr-defined]
 
 
 class LoggingHTTPServer(http.server.ThreadingHTTPServer):

pixeltable/utils/media_store.py

@@ -3,9 +3,9 @@ import os
 import re
 import shutil
 import uuid
-from typing import Optional, List, Tuple, Dict
-from pathlib import Path
 from collections import defaultdict
+from pathlib import Path
+from typing import Optional
 from uuid import UUID
 
 from pixeltable.env import Env
@@ -46,8 +46,8 @@ class MediaStore:
         else:
             # Remove only the elements for the specified version.
             paths = glob.glob(str(Env.get().media_dir / tbl_id.hex) + f'/**/{tbl_id.hex}_*_{version}_*', recursive=True)
-            for path in paths:
-                os.remove(path)
+            for p in paths:
+                os.remove(p)
 
     @classmethod
     def count(cls, tbl_id: UUID) -> int:
@@ -58,10 +58,10 @@ class MediaStore:
         return len(paths)
 
     @classmethod
-    def stats(cls) -> List[Tuple[int, int, int, int]]:
+    def stats(cls) -> list[tuple[UUID, int, int, int]]:
         paths = glob.glob(str(Env.get().media_dir) + "/**", recursive=True)
         # key: (tbl_id, col_id), value: (num_files, size)
-        d: Dict[Tuple[UUID, int], List[int]] = defaultdict(lambda: [0, 0])
+        d: dict[tuple[UUID, int], list[int]] = defaultdict(lambda: [0, 0])
         for p in paths:
             if not os.path.isdir(p):
                 matched = re.match(cls.pattern, Path(p).name)

pixeltable/utils/pytorch.py

@@ -2,13 +2,13 @@ import datetime
 import io
 import json
 from pathlib import Path
-from typing import Any, Dict, Iterator
+from typing import Any, Iterator, Sequence
 
 import numpy as np
 import PIL.Image
-import pyarrow as pa
 import torch
 import torch.utils.data
+import torchvision  # type: ignore[import-untyped]
 from pyarrow import parquet
 
 from pixeltable.type_system import ColumnType
@@ -41,7 +41,7 @@ class PixeltablePytorchDataset(torch.utils.data.IterableDataset):
         with column_type_path.open() as f:
             column_types = json.load(f)
         self.column_types = {k: ColumnType.from_dict(v) for k, v in column_types.items()}
-        self.part_metadata = parquet.ParquetDataset(path).files
+        self.part_metadata: list = parquet.ParquetDataset(str(path)).files
 
     def _unmarshall(self, k: str, v: Any) -> Any:
         if self.column_types[k].is_image_type():
@@ -54,7 +54,6 @@ class PixeltablePytorchDataset(torch.utils.data.IterableDataset):
                 return arr
 
             assert self.image_format == "pt"
-            import torchvision
 
             # use arr instead of im in ToTensor() to guarantee array input
             # to torch.from_numpy is writable. Using im is a suspected cause of
@@ -77,17 +76,17 @@ class PixeltablePytorchDataset(torch.utils.data.IterableDataset):
             assert not isinstance(v, np.ndarray) # all array outputs should be handled above
             return v
 
-    def __iter__(self) -> Iterator[Dict[str, Any]]:
-        import pixeltable.utils.arrow as arrow
+    def __iter__(self) -> Iterator[dict[str, Any]]:
+        from pixeltable.utils import arrow
+
         worker_info = torch.utils.data.get_worker_info()
 
-        if worker_info is None:
-            part_list = range(len(self.part_metadata))
-        else:
-            part_list = [ i for i in part_list if (i % worker_info.num_workers) == worker_info.id ]
+        part_list: Sequence[int] = range(len(self.part_metadata))
+        if worker_info is not None:
+            part_list = [i for i in part_list if (i % worker_info.num_workers) == worker_info.id]
 
         for part_no in part_list:
             pqf = parquet.ParquetFile(self.part_metadata[part_no])
             for batch in pqf.iter_batches():
                 for tup in arrow.iter_tuples(batch):
-                    yield {k: self._unmarshall(k, v) for k, v in tup.items()}
+                    yield {k: self._unmarshall(k, v) for k, v in tup.items()}

pixeltable/utils/sql.py

@@ -1,10 +1,11 @@
 import logging
 
 import sqlalchemy as sql
+from sqlalchemy.dialects import postgresql
 
 
 def log_stmt(logger: logging.Logger, stmt) -> None:
-    logger.debug(f'executing {str(stmt.compile(dialect=sql.dialects.postgresql.dialect()))}')
+    logger.debug(f'executing {str(stmt.compile(dialect=postgresql.dialect()))}')
 
 def log_explain(logger: logging.Logger, stmt: sql.sql.ClauseElement, conn: sql.engine.Connection) -> None:
     try:

{pixeltable-0.2.20.dist-info → pixeltable-0.2.22.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pixeltable
-Version: 0.2.20
+Version: 0.2.22
 Summary: Pixeltable: The Multimodal AI Data Plane
 Author: Pixeltable, Inc.
 Author-email: contact@pixeltable.com
@@ -16,9 +16,9 @@ Requires-Dist: cloudpickle (>=2.2.1,<3.0.0)
 Requires-Dist: ftfy (>=6.2.0,<7.0.0)
 Requires-Dist: jinja2 (>=3.1.3,<4.0.0)
 Requires-Dist: jmespath (>=1.0.1,<2.0.0)
+Requires-Dist: lxml (>=5.0)
 Requires-Dist: more-itertools (>=10.2,<11.0)
 Requires-Dist: numpy (>=1.25,<2.0)
-Requires-Dist: opencv-python-headless (>=4.7.0.68,<5.0.0.0)
 Requires-Dist: pandas (>=2.0,<3.0)
 Requires-Dist: pgvector (>=0.2.1,<0.3.0)
 Requires-Dist: pillow (>=9.3.0)
@@ -39,15 +39,19 @@ Description-Content-Type: text/markdown
 <img src="https://raw.githubusercontent.com/pixeltable/pixeltable/main/docs/source/data/pixeltable-logo-large.png" alt="Pixeltable" width="50%" />
 <br></br>
 
-[![License](https://img.shields.io/badge/License-Apache%202.0-darkblue.svg)](https://opensource.org/licenses/Apache-2.0)
-![PyPI - Python Version](https://img.shields.io/pypi/pyversions/pixeltable?logo=python&logoColor=white)
-![Platform Support](https://img.shields.io/badge/platform-Linux%20%7C%20macOS%20%7C%20Windows-8A2BE2)
+<h2>AI Data Insfrastructure — Declarative, Multimodal, and Incremental</h2>
+
+[![License](https://img.shields.io/badge/License-Apache%202.0-0530AD.svg)](https://opensource.org/licenses/Apache-2.0)
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/pixeltable?logo=python&logoColor=white&)
+![Platform Support](https://img.shields.io/badge/platform-Linux%20%7C%20macOS%20%7C%20Windows-E5DDD4)
 <br>
 [![tests status](https://github.com/pixeltable/pixeltable/actions/workflows/pytest.yml/badge.svg)](https://github.com/pixeltable/pixeltable/actions/workflows/pytest.yml)
 [![tests status](https://github.com/pixeltable/pixeltable/actions/workflows/nightly.yml/badge.svg)](https://github.com/pixeltable/pixeltable/actions/workflows/nightly.yml)
-[![PyPI Package](https://img.shields.io/pypi/v/pixeltable?color=darkorange)](https://pypi.org/project/pixeltable/)
+[![PyPI Package](https://img.shields.io/pypi/v/pixeltable?color=4D148C)](https://pypi.org/project/pixeltable/)
+[![FOSSA Status](https://app.fossa.com/api/projects/git%2Bgithub.com%2Fpixeltable%2Fpixeltable.svg?type=shield&issueType=security)](https://app.fossa.com/projects/git%2Bgithub.com%2Fpixeltable%2Fpixeltable?ref=badge_shield&issueType=security)
+<a target="_blank" href="https://huggingface.co/Pixeltable"> <img src="https://img.shields.io/badge/🤗-HF Space-FF7D04" alt="Visit our Hugging Face space"/></a>
 
-[Installation](https://pixeltable.github.io/pixeltable/getting-started/) | [Documentation](https://pixeltable.readme.io/) | [API Reference](https://pixeltable.github.io/pixeltable/) | [Code Samples](https://github.com/pixeltable/pixeltable?tab=readme-ov-file#-code-samples) | [Computer Vision](https://docs.pixeltable.com/docs/object-detection-in-videos) | [LLM](https://docs.pixeltable.com/docs/document-indexing-and-rag)
+[Installation](https://docs.pixeltable.com/docs/installation) | [Documentation](https://pixeltable.readme.io/) | [API Reference](https://pixeltable.github.io/pixeltable/) | [Code Samples](https://github.com/pixeltable/pixeltable?tab=readme-ov-file#-code-samples) | [Computer Vision](https://docs.pixeltable.com/docs/object-detection-in-videos) | [LLM](https://docs.pixeltable.com/docs/document-indexing-and-rag)
 </div>
 
 Pixeltable is a Python library providing a declarative interface for multimodal data (text, images, audio, video). It features built-in versioning, lineage tracking, and incremental updates, enabling users to **store**, **transform**, **index**, and **iterate** on data for their ML workflows.
@@ -73,8 +77,9 @@ Learn how to create tables, populate them with data, and enhance them with built
 |:----------|:-----------------|:-------------------------|:---------------------------------:|
 | 10-Minute Tour of Pixeltable    | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/tutorials/pixeltable-basics.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a> | Tables and Data Operations    | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/fundamentals/tables-and-data-operations.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a>
 | User-Defined Functions (UDFs)    | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/howto/udfs-in-pixeltable.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a> | Object Detection Models | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/tutorials/object-detection-in-videos.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a>
-| Experimenting with Chunking (RAG) | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/tutorials/rag-operations.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> | Working with External Files    | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/howto/working-with-external-files.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a>
-| Integrating with Label Studio    | <a target="_blank" href="https://pixeltable.readme.io/docs/label-studio"> <img src="https://img.shields.io/badge/Docs-Label Studio-blue" alt="Visit our documentation"/></a> | Audio/Video Transcript Indexing    | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/tutorials/audio-transcriptions.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a>
+| Incremental Prompt Engineering | <a target="_blank" href="https://colab.research.google.com/github/mistralai/cookbook/blob/main/third_party/Pixeltable/incremental_prompt_engineering_and_model_comparison.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Github"/> | Working with External Files    | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/howto/working-with-external-files.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a>
+| Integrating with Label Studio    | <a target="_blank" href="https://pixeltable.readme.io/docs/label-studio"> <img src="https://img.shields.io/badge/Documentation-013056" alt="Visit our documentation"/></a> | Audio/Video Transcript Indexing    | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/tutorials/audio-transcriptions.ipynb">  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+| Multimodal Application    | <a target="_blank" href="https://huggingface.co/spaces/Pixeltable/Multimodal-Powerhouse"> <img src="https://img.shields.io/badge/Hugging Face-FF7D04" alt="Visit our documentation"/></a> | Document Indexing and RAG    | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/tutorials/rag-demo.ipynb">  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
 
 ## 🧱 Code Samples
 
@@ -82,7 +87,7 @@ Learn how to create tables, populate them with data, and enhance them with built
 ```python
 import pixeltable as pxt
 
-v = pxt.create_table('external_data.videos', {'video': pxt.VideoType()})
+v = pxt.create_table('external_data.videos', {'video': pxt.Video})
 
 prefix = 's3://multimedia-commons/'
 paths = [
@@ -100,7 +105,7 @@ import pixeltable as pxt
 from pixeltable.functions import huggingface
 
 # Create a table to store data persistently
-t = pxt.create_table('image', {'image': pxt.ImageType()})
+t = pxt.create_table('image', {'image': pxt.Image})
 
 # Insert some images
 prefix = 'https://upload.wikimedia.org/wikipedia/commons'
@@ -157,7 +162,7 @@ Learn how to leverage Pixeltable for [Model analytics](https://pixeltable.readme
 
 ### Working with inference services
 ```python
-chat_table = pxt.create_table('together_demo.chat', {'input': pxt.StringType()})
+chat_table = pxt.create_table('together_demo.chat', {'input': pxt.String})
 
 # The chat-completions API expects JSON-formatted input:
 messages = [{'role': 'user', 'content': chat_table.input}]
@@ -193,7 +198,7 @@ from pixeltable.functions.huggingface import clip_image, clip_text
 from pixeltable.iterators import FrameIterator
 import PIL.Image
 
-video_table = pxt.create_table('videos', {'video': pxt.VideoType()})
+video_table = pxt.create_table('videos', {'video': pxt.Video})
 
 video_table.insert([{'video': '/video.mp4'}])
 
@@ -224,6 +229,38 @@ frames_view.order_by(sim, asc=False).limit(5).select(frames_view.frame, sim=sim)
 ```
 Learn how to work with [Embedding and Vector Indexes](https://docs.pixeltable.com/docs/embedding-vector-indexes).
 
+## 🔄 AI Stack Comparison
+
+### 🎯 Computer Vision Workflows
+
+| Requirement | Traditional | Pixeltable |
+|-------------|---------------------|------------|
+| Frame Extraction | ffmpeg + custom code | Automatic via FrameIterator |
+| Object Detection | Multiple scripts + caching | Single computed column |
+| Video Indexing | Custom pipelines + Vector DB | Native similarity search |
+| Annotation Management | Separate tools + custom code | Label Studio integration |
+| Model Evaluation | Custom metrics pipeline | Built-in mAP computation |
+
+### 🤖 LLM Workflows
+
+| Requirement | Traditional | Pixeltable |
+|-------------|---------------------|------------|
+| Document Chunking | Tool + custom code | Native DocumentSplitter |
+| Embedding Generation | Separate pipeline + caching | Computed columns |
+| Vector Search | External vector DB | Built-in vector indexing |
+| Prompt Management | Custom tracking solution | Version-controlled columns |
+| Chain Management | Tool + custom code | Computed column DAGs |
+
+### 🎨 Multimodal Workflows
+
+| Requirement | Traditional | Pixeltable |
+|-------------|---------------------|------------|
+| Data Types | Multiple storage systems | Unified table interface |
+| Cross-Modal Search | Complex integration | Native similarity support |
+| Pipeline Orchestration | Multiple tools (Airflow, etc.) | Single declarative interface |
+| Asset Management | Custom tracking system | Automatic lineage |
+| Quality Control | Multiple validation tools | Computed validation columns |
+
 ## ❓ FAQ
 
 ### What is Pixeltable?

pixeltable-0.2.22.dist-info/RECORD

@@ -0,0 +1,153 @@
+pixeltable/__init__.py,sha256=r-kbRRoAp3rD61EEZbmgrMfo3X0TMRNl16hXMgHVHRg,1374
+pixeltable/__version__.py,sha256=8hdYkuW_Aobhb48yBMyzCJUcf2bpelFP4zORLc4rC_o,114
+pixeltable/catalog/__init__.py,sha256=Ar6_F_6C7tkznIlCPBHVHDop5YssBDjKQr2NPQ21QCI,484
+pixeltable/catalog/catalog.py,sha256=tyDyI5wQw7vV6_FChrp9qgGCRClcjiSdW3eygYT0p9s,7849
+pixeltable/catalog/column.py,sha256=zIWQp0TWQleXsgRSWHJjjoshI-WNhiXcgo8zJopsooM,10508
+pixeltable/catalog/dir.py,sha256=fG_BQM-fLuABpTstMVH-9dvZPx7kqi3sgTQgKveVXJI,922
+pixeltable/catalog/globals.py,sha256=2P9cEfgnYQ19MFS4OsbnA8ZQkWLZPqJmmknDYWCXjWw,2415
+pixeltable/catalog/insertable_table.py,sha256=bzwHsUU_KZPhXs1jzzJzmTonzV5gCfXJR2hXTRT3Ejs,6964
+pixeltable/catalog/named_function.py,sha256=W8vikP_3jMJ9pQQsksO2EfQAlaVxuQHBlo65M4924dc,1150
+pixeltable/catalog/path.py,sha256=QgccEi_QOfaKt8YsR2zLtd_z7z7QQkU_1kprJFi2SPQ,1677
+pixeltable/catalog/path_dict.py,sha256=4b9_Ax7Q8tkmoCYPaKNedpQkU17pE0oGDd2XB53eNZA,5979
+pixeltable/catalog/schema_object.py,sha256=qhpeeUPOYT5doDbsyUNBcPm5QzAQPCAsikqh1PQ6d1k,2226
+pixeltable/catalog/table.py,sha256=Vzsr1MU_9HvfIUwrS4gnV5ZCysDdQX2lMlWfmLuAa5U,45884
+pixeltable/catalog/table_version.py,sha256=ulN1x9DfPpJkAIAcYJmJj0-TcyPt5qv8NHVO8VQdxPc,59021
+pixeltable/catalog/table_version_path.py,sha256=YpnNh8QYyoMQCuAZPr1SGovSFD-70lcvZasY4dh_-xM,5778
+pixeltable/catalog/view.py,sha256=vctwgzihDoKh3CSj2iGT0KrFeB18RL68AX5t9JCdXYg,10690
+pixeltable/dataframe.py,sha256=F14t9HLoZeBKXIfUP9wkWHHKRgwXa2wAB9Nh0jsEhF8,34001
+pixeltable/env.py,sha256=2JSDM0m87T5HtuOWxCXRL9h9iK7u-kOfigRf-3ZxBhU,30425
+pixeltable/exceptions.py,sha256=NuFY2WtkQpLfLHT_J70kOw9Tr0kEDkkgo-u7As4Gaq4,410
+pixeltable/exec/__init__.py,sha256=QmaKzkZ704nbJ1BiAFwjYvIX3R2_EHzpO8R7HxcEY-g,481
+pixeltable/exec/aggregation_node.py,sha256=0LdoPp_CR_UbcS60XkDw66SqlrQnw6Dy6KDWqi4PJ6k,4005
+pixeltable/exec/cache_prefetch_node.py,sha256=c1y2m6Zqbq6fRfUyD2hAxzKrkNnRSXeA8K5ehaIMpa0,5242
+pixeltable/exec/component_iteration_node.py,sha256=ABuXGbDRQWLGuaBnfK7bvOxCrz81vMMiAvXHHI8SX4c,4930
+pixeltable/exec/data_row_batch.py,sha256=RM56YaYcr4JeNdw4npVT329IcWlel2ff-o1UDp69k3Y,2931
+pixeltable/exec/exec_context.py,sha256=0rg5V8HzSy-BvqmSbGr-U4aJ4eOZg2JN0x6zjYQGtBc,1090
+pixeltable/exec/exec_node.py,sha256=FrIZzBMaKlWvEMfkgSnGu9GK_EEGhWYcJLT__FI6WKY,3254
+pixeltable/exec/expr_eval_node.py,sha256=PNscxhG4o208UBi0d9pwsoUDdkPiCoH1xM8RlTaTlHY,11896
+pixeltable/exec/in_memory_data_node.py,sha256=uK3puLZDzUSJUJwGwkTMYoPqNIvE67jtQodhE2sCz2M,3452
+pixeltable/exec/row_update_node.py,sha256=b8yuKtkmI2Q6U-7svKbkjdM3Z85ddZoJgJgUa17j-YE,2773
+pixeltable/exec/sql_node.py,sha256=9huPLpMqq4J5JhSh5vtt-T4K1Tu3EXJ9omv6mMi-zD4,17616
+pixeltable/exprs/__init__.py,sha256=toKJm6y1_2fD8Fo-ld5feD-nMN-yZGMWwMHYyb8vsrg,967
+pixeltable/exprs/arithmetic_expr.py,sha256=F97EF0y-OW8edIB_Trg5bJmCV_nif7QBnVGL4Zv7Xiw,5997
+pixeltable/exprs/array_slice.py,sha256=HgB9BV8a9Qg6Y-t7PRjFszr40jDArensZ75-wDyFpcQ,2179
+pixeltable/exprs/column_property_ref.py,sha256=rCYNv9o_UMVhIz-U0-bhTxLf4c7_CTYWH6VB9LLo0F8,3787
+pixeltable/exprs/column_ref.py,sha256=YjqxAqBVHDc0pNHEJmbQNGq7eqOiloy_Umr4qW6Gb1c,9626
+pixeltable/exprs/comparison.py,sha256=K5WWA2FvnZuts2VcLVGKtUyAOol67NgqGoeNiuhdyKU,4757
+pixeltable/exprs/compound_predicate.py,sha256=H35SB053aCHigtPp_JYrOTLRC2AGDQK3NAkOYOBPDQg,3845
+pixeltable/exprs/data_row.py,sha256=rLtKxlst9mK6684A5y-nsjBcalyKEcKAWcYCtNpK10w,9852
+pixeltable/exprs/expr.py,sha256=QlVslNfAOPxPVvsNiEv_k_S2QWp4-8dc3eocT6zclNU,29986
+pixeltable/exprs/expr_dict.py,sha256=xkvo_iVPOLMq3WkBZQ2FOoXqYoebuV6XGlidPJxdOkY,1588
+pixeltable/exprs/expr_set.py,sha256=kAV-PbudbAlW0dqhKqfstXnxKbK_FWKXyrzkpvDrpjQ,2330
+pixeltable/exprs/function_call.py,sha256=Sp23zxpzA4f7ztd71sn_B0sgos1hyMPKRR8wICzxOZ4,21365
+pixeltable/exprs/globals.py,sha256=5pwn5vdi-EEpYBpPty658YV45myY7W0iFIfTH7QIzak,2032
+pixeltable/exprs/in_predicate.py,sha256=eR6qFf_0lsqM0jPRI9IxTsDlXM6Bt9RBY9a05bZ6bDs,3782
+pixeltable/exprs/inline_expr.py,sha256=OF-yLIoU7LfHqFdbZkZnC1oQ2_X26WyHbfxbxrdZr-k,7104
+pixeltable/exprs/is_null.py,sha256=x9-CijQf1JuUioUAv1_8OvP9nK9Ahjc1wJfgE1QEOL8,1091
+pixeltable/exprs/json_mapper.py,sha256=OJ8ohAZhuLxTGtmmbB8voVG9AzUuCHLHuNBi-3hJZEg,4544
+pixeltable/exprs/json_path.py,sha256=CiX5hXWNL8caNFajVXn3PGxkINK7rAfHDIfbNIkWT04,6753
+pixeltable/exprs/literal.py,sha256=TTKb0gw6qck9D61SwVDuBrLrBrGwEhkCB-m0ILFpWFk,3764
+pixeltable/exprs/method_ref.py,sha256=x9rQzlRQlVnbTpBQoV0COFsiOPstJcOifXl0lJC-roI,2614
+pixeltable/exprs/object_ref.py,sha256=GVg6uxZnKwFVTC0kouJq-wMFP-gUPb_ld_syHrsGMdE,1283
+pixeltable/exprs/row_builder.py,sha256=7f-h4y8xv0ktkk6GYqGrMJvLSwkVYtMPHsBBIskmQLw,18435
+pixeltable/exprs/rowid_ref.py,sha256=hjGrbk9zHH3H-00uFAopyRvLTeQeB2e44kAJUAxiy3k,4400
+pixeltable/exprs/similarity_expr.py,sha256=snOseawC4ySvyHo8TCqbh_bDxIrENfIzO_0lXlzL-BA,4016
+pixeltable/exprs/sql_element_cache.py,sha256=DRW5Aa0WQZ-yMf5anlUg-_Rmq3Oz3G6Us1X_KseMC68,1229
+pixeltable/exprs/type_cast.py,sha256=BTnhgoll7LVZdOU_282QlzGZ4EEMTzPYcNdDcFOfkTs,1837
+pixeltable/exprs/variable.py,sha256=VATAmLaPrQipv2AXqg-m6FYMLNGyhPtys8c5Et8Ba0g,1414
+pixeltable/ext/__init__.py,sha256=iO0J_Jfnv38F5y40sDAW54gpXjIyZgOGgoWQJAwjQec,423
+pixeltable/ext/functions/__init__.py,sha256=hIjPEKC5E5uJOXlQqUyhP9yn9ZqWOCJAlj0kXWDlhlE,159
+pixeltable/ext/functions/whisperx.py,sha256=jojjNhazcYiAh1scwUl-erhIDRr4kOTkcLrjy0xcp6g,2325
+pixeltable/ext/functions/yolox.py,sha256=k-pQTelv4Tea3AXvDB7Kc7YCIa1uexjVGqxETP0B_hc,5351
+pixeltable/func/__init__.py,sha256=WjftUGyNkd6bF_qSxqZ5Gd7Elf8oExb3dUlpydhdFTo,407
+pixeltable/func/aggregate_function.py,sha256=x3BW-lRlMFmStpOwmMXDKK0Zoli_wBffXKw5wDqb-80,9495
+pixeltable/func/callable_function.py,sha256=PO5Mn5WL2cd7y5LcKr_K0AaYHf2-1NfuXP2IPOfsiVs,4933
+pixeltable/func/expr_template_function.py,sha256=0krKY-0i-aTZdgAS8wZkq4NQc-EVtAA7-a0zh2vHmTI,4059
+pixeltable/func/function.py,sha256=BLJbahyKteGemp0EcG7joTrgrG2hnIfwHkuKoLZm4mo,6941
+pixeltable/func/function_registry.py,sha256=fBXe7NKyk8_JzZz6fsS0LF-WHTdMnmIP_XzrICuj9fA,12328
+pixeltable/func/globals.py,sha256=sEwn6lGgHMp6VQORb_P5qRd_-Q2_bUSqvqM9-XPN_ec,1483
+pixeltable/func/query_template_function.py,sha256=pGqwtWiPsEmo7phVoJJODiuD1Sh0gZoW4BpKnZV9cRE,3537
+pixeltable/func/signature.py,sha256=vBKs3igtijTQGK7rEGTxBiOznKo6Tj9Ut6OrSfiVcA0,8609
+pixeltable/func/udf.py,sha256=yn3D2vTn7eJ_rCB8MoJp2MAphufOddOP89sxnBsbyfg,7634
+pixeltable/functions/__init__.py,sha256=EtR9M3ewYpmtHeshNULqZVBd87bNeKSFAdpOuWCMl6o,389
+pixeltable/functions/anthropic.py,sha256=P1E5o4-8QP1LTIUsWVgo_wMJ4WOnxtXUUXuFWUagChU,3032
+pixeltable/functions/audio.py,sha256=7213nTnqKJ6vM9kalaoJ283OwX5SGEJN10vDhaRNZ6E,644
+pixeltable/functions/fireworks.py,sha256=qwFC_eIaDs-glxyJ_IVXaNGkpgPzeRsQ_SdpzueBxq0,2605
+pixeltable/functions/globals.py,sha256=pCFX2a_N87SwG9GxyPjSOC3TVMowMB6XIHSWKfFOuGE,3917
+pixeltable/functions/huggingface.py,sha256=Zvj4REfXX7cB0trdiDAemkqpWxrsq2sZyrSULgqJU7U,16043
+pixeltable/functions/image.py,sha256=3Qm4ybAT_o4YUl3bzhEXy8dKOwgZ7RCUV-ky-dbL_jc,13836
+pixeltable/functions/json.py,sha256=ehCnBA5WiIl-crV9PFVgmxrsWsiO8FpRs9LDwcSpLa4,879
+pixeltable/functions/llama_cpp.py,sha256=2t8o2m6jsEFFmVcVl3Fjyoy6Ogxbt-uYJ6a_jcrpEso,3838
+pixeltable/functions/mistralai.py,sha256=qdcAiUQcbTd6gTHiUCVcH2bQUh-gFunudGbqYpwxzdo,5565
+pixeltable/functions/ollama.py,sha256=eZh461HvChjlr0CvQyd93m7qrv889PAoM-Z1IKierY0,4335
+pixeltable/functions/openai.py,sha256=YCV1b6IV_zROjQQl3R-r40WeCjIWuOGqTeRgcQzM-WE,15579
+pixeltable/functions/replicate.py,sha256=j8ZedScOMInmHWmriQSUOviw6tp8gQr-W6n21PNNL2g,2188
+pixeltable/functions/string.py,sha256=VqzhVildxTt_XblW89Kl5Zd6MVOU71eaX2LTMY5jkUg,20366
+pixeltable/functions/timestamp.py,sha256=Q5l2iEscrS3ZfKAa4R940bSM_x4FsmF-PF2i-wQ_4_c,9096
+pixeltable/functions/together.py,sha256=llha20aaTuCo2dewcAUkbT-QbDNXTajwoBLlSiDRPoo,9436
+pixeltable/functions/util.py,sha256=F2iiIL7UfhYdCVzdCa3efYqWbaeLKFrbycKnuPkG57M,650
+pixeltable/functions/video.py,sha256=yW1Lwqu4_jYXp1aAOUThKB5-_Qxy-In_vTgB5cuW7Lg,6809
+pixeltable/functions/vision.py,sha256=K_E1Q-n2plPuFoOPlbKWRMiJp9dPgftIJ2T_o3TNL3I,15594
+pixeltable/functions/whisper.py,sha256=f2wqRd0n9jSBqRZN3W93UaetiAHtbsK0j9jXR2j2kkQ,2913
+pixeltable/globals.py,sha256=qO6-RBZ9j7nPGqAkUSyJpl8EQd7DLDswjCLMP3_EW80,17799
+pixeltable/index/__init__.py,sha256=XBwetNQQwnz0fiKwonOKhyy_U32l_cjt77kNvEIdjWs,102
+pixeltable/index/base.py,sha256=zo0YvJI3oXiK6hZJztB36ZftKKhLfO75Zq3t-PeQA6M,1556
+pixeltable/index/btree.py,sha256=JFerLyyLoBaD0FSF_jJ6iJFBVa-z_et--KdNR02xjRg,2264
+pixeltable/index/embedding_index.py,sha256=g5bajq8Dn82o8ZlkDwPT5kBUClR4ZCuH6dttwCW6KWI,7793
+pixeltable/io/__init__.py,sha256=PHqbiEJXFtCzTsia7LmsHLfBIkA41tzII3n9L4UkfJ8,547
+pixeltable/io/external_store.py,sha256=H1jt7MDn464QRgBvU-PmcPcFlo3EZBCG7fKWEZXOfyc,16676
+pixeltable/io/fiftyone.py,sha256=hH-FahW6BuMQY8lGa2atnNnJto_pK8kWrP_y_EMsq6g,6965
+pixeltable/io/globals.py,sha256=9S9wnlIAuhZq7eC_GklTM_UX0UATK9fEagk8-SRCeXQ,17794
+pixeltable/io/hf_datasets.py,sha256=o5fqm2CJAjhFd3z-NYGxN0jM1tfrp4szuUX0TGnyNRY,8316
+pixeltable/io/label_studio.py,sha256=7KTro1H-AlVbwWuoYwU-mxH3zejZWTpQbz56uX-Wnjs,31078
+pixeltable/io/pandas.py,sha256=7eHg7wnAfRA9eBk4iC0iSSVTKOM59Ne4pXokKWdt3dY,9793
+pixeltable/io/parquet.py,sha256=4bAQNCahtLGuHRF669kLGx2MhOFmuwTkUYYHLC-qKcs,7862
+pixeltable/iterators/__init__.py,sha256=sjldFckkT8aVRiKgEP6faeAK2NQBdzbmpwAeRhI1FkM,366
+pixeltable/iterators/base.py,sha256=ZC0ZvXL4iw6AmT8cu-Mdx-T2UG9nmJYV1C6LK4efAfw,1669
+pixeltable/iterators/document.py,sha256=AsvEmZ5RGRi3AFGCrH2_-UNx5rTCFA-0WmMYQBTQI20,19679
+pixeltable/iterators/string.py,sha256=NG_fWc_GAITDfzl6MvrDOMrSoMcZdMZf6hPQztCSatE,1305
+pixeltable/iterators/video.py,sha256=CKx6jHFW-393r4xN-ulVDDZFETSkhhMwT7bPX2NHVU8,9442
+pixeltable/metadata/__init__.py,sha256=CI0ZWcxsCbXEWhdbbByNJFdSmvIBrMEbf_vqrVb0b-Q,2209
+pixeltable/metadata/converters/convert_10.py,sha256=J1_r7LNNAWTdb042AwqFpJ4sEB-i4qhUdk5iOjcZk34,719
+pixeltable/metadata/converters/convert_12.py,sha256=Ci-qyZW1gqci-8wnjeOB5afdq7KTuN-hVSV9OqSPx8g,162
+pixeltable/metadata/converters/convert_13.py,sha256=yFR6lD3pOrZ46ZQBFKYvxiIYa7rRxh46Bsq7yiCBNak,1356
+pixeltable/metadata/converters/convert_14.py,sha256=9e_JNm3a35Gs4dvFFaV-_jtCqp3ud6OEOqMIhTQmasE,428
+pixeltable/metadata/converters/convert_15.py,sha256=jMfL5wGil0-gZeIfmCbgtR3LSVNyOcxVp6YRhBECqY4,1741
+pixeltable/metadata/converters/convert_16.py,sha256=SvcWOYgLwRw_gLTnLbCSI9f2cpdkXazYOmmtJUOOzv4,476
+pixeltable/metadata/converters/convert_17.py,sha256=vJg4y2lg53WSj9OSntWsdUiCr6yRgMQm0eFbs_Geqjg,861
+pixeltable/metadata/converters/convert_18.py,sha256=NxSroQntVLgmvXfae1f0-jYJIhM2W7dhRY3I7g0RxPY,1482
+pixeltable/metadata/converters/convert_19.py,sha256=QgUDjNoH87KZg_f3cx4k0ZR67NqWRhZQKIIojbqxSkg,2080
+pixeltable/metadata/converters/convert_20.py,sha256=NLMeke9QUGqIJUe5MNqKmVdaLs6pPFrjyigImhogaT4,2768
+pixeltable/metadata/converters/convert_21.py,sha256=YTztkbqOC2zQcTWrXfhrP8diUbfxy5DHwsu_IT-bBok,1115
+pixeltable/metadata/converters/util.py,sha256=nycZk_UecJcrVZsIyxQrz5ngbke8-yfY-_UcERuzhPk,5983
+pixeltable/metadata/notes.py,sha256=HJmeA9fo37iREFIhlbGbxWnwbwIDcvdqvJO-BavIvxE,597
+pixeltable/metadata/schema.py,sha256=CnEsMqLn4hzLDaAr5lyd-NqiOUFQdvhxdCoXMR4Qcs4,9352
+pixeltable/plan.py,sha256=LN5R-0gEmGX9kwm67syCqvrLuPaWSiT3pUfMJoudkLY,37442
+pixeltable/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pixeltable/store.py,sha256=IG33KEu0eHGD2CGMBVV-HmPj7xGUMCLmLGdJn49_4Cs,21990
+pixeltable/tool/create_test_db_dump.py,sha256=axTlPFqodZJ5p8kRVmya3PgghqBaF8oYh7a4vbusmcA,11986
+pixeltable/tool/create_test_video.py,sha256=4cQmqoKjn3juy7Ilty75gWBygqBxTZ1E9XPlrsC0Ssk,2931
+pixeltable/tool/doc_plugins/griffe.py,sha256=J5zxyEUchfR3mkWmhx4Vjl_iSodL_pHiuOyD2eczbNU,2182
+pixeltable/tool/doc_plugins/mkdocstrings.py,sha256=afq7XOaSC5WRmugkh-FMFMK8PqOgIlDIsJdD8cuPhtE,207
+pixeltable/tool/doc_plugins/templates/material/udf.html.jinja,sha256=R-7Q57nmDd5BUea-F1-MjwjK3pq7uBHXNoSo8_QjZG4,4890
+pixeltable/tool/embed_udf.py,sha256=EXvfvuzZm0uTgH-aAATSrKV8ixCU8OMwpzXlJMg845Y,299
+pixeltable/tool/mypy_plugin.py,sha256=__oTFElirrK25jCX1z_asD_gxGnGxtD2TaU6r1if-Ic,1784
+pixeltable/type_system.py,sha256=y_fbms9LyC8lFCdXiewMJKqkzwiYBJE9ZoQbrQxJv2c,39980
+pixeltable/utils/__init__.py,sha256=UYlrf6TIWJT0g-Hac0b34-dEk478B5Qx8dGco34YlIk,439
+pixeltable/utils/arrow.py,sha256=UQkMxyU4G_ikUF9OnEHcaBXHjVqdPXHSY4JXGmuARhA,3776
+pixeltable/utils/coco.py,sha256=bqdSFHw8lulYDIGuTdV-7XSuuaW6KNkcrH0jD60-iJI,7302
+pixeltable/utils/code.py,sha256=AOw1u2r8_DQXpX-lxJhyHWARGrCRDXOJHFVgKOi54Uc,1231
+pixeltable/utils/documents.py,sha256=B984nVigJgHZ5Rm-zX4LLuHuMnfmz-zr24bbAsc_y3w,2511
+pixeltable/utils/filecache.py,sha256=6HKQdItqSSTQvj2HkSJulyhfBedi4PgC7umwxXGOVG8,10637
+pixeltable/utils/formatter.py,sha256=fVgcaoWFTvpc_2G3MnU8QGUjHaQkj4vmScNI1s_SwBg,9209
+pixeltable/utils/http_server.py,sha256=xYPTvmYrkUpKfOaLDq08D-eHswkcgDf4qAt76ZFH6lM,2411
+pixeltable/utils/media_store.py,sha256=YwvTjbVqC_aLbDvLuqnDSL8xeIVMZcmzp0ANuM6uMbw,3092
+pixeltable/utils/pytorch.py,sha256=6RvOCjy_QV4gc-aht-3d0zoASkuv-warfpl87vgmuKw,3450
+pixeltable/utils/s3.py,sha256=DBfXp0SYubhiKckdAD7PsiVBX_YfVP8Rcu6DCG_3SaQ,433
+pixeltable/utils/sql.py,sha256=j_tj0h4ffm-DhUIJbvGphxrVyBKlNTwDKqWGhRQ5_PY,795
+pixeltable/utils/transactional_directory.py,sha256=UGzCrGtLR3hEEf8sYGuWBzLVFAEQml3vdIavigWeTBM,1349
+pixeltable-0.2.22.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+pixeltable-0.2.22.dist-info/METADATA,sha256=8vkY__cKJFa_AXNwYLfo0IQYXgsMRPMI2_ZeG1DRM_U,17406
+pixeltable-0.2.22.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+pixeltable-0.2.22.dist-info/entry_points.txt,sha256=TNI1Gb5vPwFrTdw6TimSYjO8FeK8c_HuPr28vcf7o_I,108
+pixeltable-0.2.22.dist-info/RECORD,,

pixeltable/exec/media_validation_node.py

@@ -1,43 +0,0 @@
-from __future__ import annotations
-from typing import Iterable, Optional
-
-from .data_row_batch import DataRowBatch
-from .exec_node import ExecNode
-import pixeltable.exprs as exprs
-import pixeltable.exceptions as excs
-
-
-class MediaValidationNode(ExecNode):
-    """Validation of selected media slots
-    Records exceptions in the rows of the input batch
-    """
-    def __init__(
-            self, row_builder: exprs.RowBuilder, media_slots: Iterable[exprs.ColumnSlotIdx],
-            input: Optional[ExecNode]):
-        super().__init__(row_builder, [], [], input)
-        self.row_builder = row_builder
-        self.input = input
-        for col in [c.col for c in media_slots]:
-            assert col.col_type.is_media_type()
-        self.media_slots = media_slots
-
-    def __next__(self) -> DataRowBatch:
-        assert self.input is not None
-        row_batch = next(self.input)
-        for row in row_batch:
-            for slot_idx, col in [(c.slot_idx, c.col) for c in self.media_slots]:
-                if row.has_exc(slot_idx):
-                    continue
-                assert row.has_val[slot_idx]
-                path = row.file_paths[slot_idx]
-                if path is None:
-                    continue
-
-                try:
-                    col.col_type.validate_media(path)
-                except excs.Error as exc:
-                    self.row_builder.set_exc(row, slot_idx, exc)
-                    if not self.ctx.ignore_errors:
-                        raise exc
-
-        return row_batch

pixeltable/utils/help.py

@@ -1,11 +0,0 @@
-from typing import Any
-
-import pixeltable.func as func
-
-
-def help(obj: Any) -> None:
-    """Returns help text for the given object."""
-    if isinstance(obj, func.Function):
-        print(obj.help_str())
-    else:
-        print(__builtins__.help(obj))