pixeltable 0.2.17__tar.gz → 0.2.19__tar.gz

pixeltable-0.2.19/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

{pixeltable-0.2.17 → pixeltable-0.2.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pixeltable
-Version: 0.2.17
+Version: 0.2.19
 Summary: Pixeltable: The Multimodal AI Data Plane
 Author: Pixeltable, Inc.
 Author-email: contact@pixeltable.com
@@ -16,9 +16,8 @@ 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: mistune (>=3.0.2,<4.0.0)
 Requires-Dist: more-itertools (>=10.2,<11.0)
-Requires-Dist: numpy (>=1.25)
+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)
@@ -26,45 +25,41 @@ Requires-Dist: pillow (>=9.3.0)
 Requires-Dist: pixeltable-pgserver (==0.2.7)
 Requires-Dist: psutil (>=5.9.5,<6.0.0)
 Requires-Dist: psycopg[binary] (==3.1.18)
+Requires-Dist: puremagic (>=1.20)
 Requires-Dist: pymupdf (>=1.24.1,<2.0.0)
 Requires-Dist: pyyaml (>=6.0.1,<7.0.0)
 Requires-Dist: requests (>=2.31.0,<3.0.0)
-Requires-Dist: setuptools (==69.1.1)
-Requires-Dist: sqlalchemy[mypy] (>=2.0.23,<3.0.0)
+Requires-Dist: sqlalchemy (>=2.0.23,<3.0.0)
 Requires-Dist: tenacity (>=8.2,<9.0)
 Requires-Dist: tqdm (>=4.64)
 Description-Content-Type: text/markdown
 
 <div align="center">
-<img src="https://raw.githubusercontent.com/pixeltable/pixeltable/main/docs/release/pixeltable-banner.png" alt="Pixeltable" width="45%" />
-
-# Unifying Data, Models, and Orchestration for AI Products
+<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)]()
-[![pytest status](https://github.com/pixeltable/pixeltable/actions/workflows/pytest.yml/badge.svg)](https://github.com/pixeltable/pixeltable/actions)
+![Platform Support](https://img.shields.io/badge/platform-Linux%20%7C%20macOS%20%7C%20Windows-8A2BE2)
+<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/)
 
 [Installation](https://pixeltable.github.io/pixeltable/getting-started/) | [Documentation](https://pixeltable.readme.io/) | [API Reference](https://pixeltable.github.io/pixeltable/) | [Code Samples](https://pixeltable.readme.io/recipes) | [Examples](https://github.com/pixeltable/pixeltable/tree/release/docs/release/tutorials)
 </div>
 
-Pixeltable is a Python library that lets ML Engineers and Data Scientists focus on exploration, modeling, and app development without dealing with the customary data plumbing.
-
-### What problems does Pixeltable solve?
-
-Today’s solutions for AI app development require extensive custom coding and infrastructure plumbing. Tracking lineage and versions between and across data transformations, models, and deployment is cumbersome.
+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. Data transformations, model inference, and custom logic are embedded as computed columns.
 
 ## 💾 Installation
 
 ```python
 pip install pixeltable
 ```
-> [!IMPORTANT]
-> Pixeltable is persistent. Unlike in-memory Python libraries such as Pandas, Pixeltable is a database. When working locally or against an hosted version of Pixeltable, use [get_table](https://pixeltable.github.io/pixeltable/api/pixeltable/#pixeltable.get_table) at any time to retrieve an existing table.
+**Pixeltable is persistent. Unlike in-memory Python libraries such as Pandas, Pixeltable is a database.**
 
 ## 💡 Getting Started
-Learn how to create tables, populate them with data, and enhance them with built-in or user-defined transformations and AI operations.
+Learn how to create tables, populate them with data, and enhance them with built-in or user-defined transformations.
 
 | Topic | Notebook | Topic | Notebook |
 |:----------|:-----------------|:-------------------------|:---------------------------------:|
@@ -91,9 +86,32 @@ v.insert({'video': prefix + p} for p in paths)
 ```
 Learn how to [work with data in Pixeltable](https://pixeltable.readme.io/docs/working-with-external-files).
 
-### Add an object detection model to your workflow
+### Object detection in images using DETR model
 ```python
-table['detections'] = huggingface.detr_for_object_detection(table.input_image, model_id='facebook/detr-resnet-50')
+import pixeltable as pxt
+from pixeltable.functions import huggingface
+
+# Create a table to store data persistently
+t = pxt.create_table('image', {'image': pxt.ImageType()})
+
+# Insert some images
+prefix = 'https://upload.wikimedia.org/wikipedia/commons'
+paths = [
+    '/1/15/Cat_August_2010-4.jpg',
+    '/e/e1/Example_of_a_Dog.jpg',
+    '/thumb/b/bf/Bird_Diversity_2013.png/300px-Bird_Diversity_2013.png'
+]
+t.insert({'image': prefix + p} for p in paths)
+
+# Add a computed column for image classification
+t['classification'] = huggingface.detr_for_object_detection(
+    (t.image), model_id='facebook/detr-resnet-50'
+    )
+
+# Retrieve the rows where cats have been identified
+t.select(animal = t.image,
+         classification = t.classification.label_text[0]) \
+.where(t.classification.label_text[0]=='cat').head()
 ```
 Learn about computed columns and object detection: [Comparing object detection models](https://pixeltable.readme.io/docs/object-detection-in-videos).
 
@@ -109,9 +127,9 @@ def draw_boxes(img: PIL.Image.Image, boxes: list[list[float]]) -> PIL.Image.Imag
 ```
 Learn more about user-defined functions: [UDFs in Pixeltable](https://pixeltable.readme.io/docs/user-defined-functions-udfs).
 
-### Automate data operations with views
+### Automate data operations with views, e.g., split documents into chunks
 ```python
-# In this example, the view is defined by iteration over the chunks of a DocumentSplitter.
+# In this example, the view is defined by iteration over the chunks of a DocumentSplitter
 chunks_table = pxt.create_view(
     'rag_demo.chunks',
     documents_table,
@@ -124,7 +142,7 @@ Learn how to leverage views to build your [RAG workflow](https://pixeltable.read
 
 ### Evaluate model performance
 ```python
-# The computation of the mAP metric can simply become a query over the evaluation output, aggregated with the mean_ap() function.
+# The computation of the mAP metric can become a query over the evaluation output
 frames_view.select(mean_ap(frames_view.eval_yolox_tiny), mean_ap(frames_view.eval_yolox_m)).show()
 ```
 Learn how to leverage Pixeltable for [Model analytics](https://pixeltable.readme.io/docs/object-detection-in-videos).
@@ -136,7 +154,7 @@ chat_table = pxt.create_table('together_demo.chat', {'input': pxt.StringType()})
 # The chat-completions API expects JSON-formatted input:
 messages = [{'role': 'user', 'content': chat_table.input}]
 
-# This example shows how additional parameters from the Together API can be used in Pixeltable to customize the model behavior.
+# This example shows how additional parameters from the Together API can be used in Pixeltable
 chat_table['output'] = chat_completions(
     messages=messages,
     model='mistralai/Mixtral-8x7B-Instruct-v0.1',
@@ -160,12 +178,54 @@ chat_table.select(chat_table.input, chat_table.response).head()
 ```
 Learn how to interact with inference services such as [Together AI](https://pixeltable.readme.io/docs/together-ai) in Pixeltable.
 
+### Text and image similarity search on video frames with embedding indexes
+```python
+import pixeltable as pxt
+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.insert([{'video': '/video.mp4'}])
+
+frames_view = pxt.create_view(
+    'frames', video_table, iterator=FrameIterator.create(video=video_table.video))
+
+@pxt.expr_udf
+def embed_image(img: PIL.Image.Image):
+    return clip_image(img, model_id='openai/clip-vit-base-patch32')
+
+@pxt.expr_udf
+def str_embed(s: str):
+    return clip_text(s, model_id='openai/clip-vit-base-patch32')
+
+# Create an index on the 'frame' column that allows text and image search
+frames_view.add_embedding_index('frame', string_embed=str_embed, image_embed=embed_image)
+
+# Now we will retrieve images based on a sample image
+sample_image = '/image.jpeg'
+sim = frames_view.frame.similarity(sample_image)
+frames_view.order_by(sim, asc=False).limit(5).select(frames_view.frame, sim=sim).collect()
+
+# Now we will retrieve images based on a string
+sample_text = 'red truck'
+sim = frames_view.frame.similarity(sample_text)
+frames_view.order_by(sim, asc=False).limit(5).select(frames_view.frame, sim=sim).collect()
+
+```
+Learn how to work with [Embedding and Vector Indexes](https://docs.pixeltable.com/docs/embedding-vector-indexes).
+
 ## ❓ FAQ
 
 ### What is Pixeltable?
 
 Pixeltable unifies data storage, versioning, and indexing with orchestration and model versioning under a declarative table interface, with transformations, model inference, and custom logic represented as computed columns.
 
+### What problems does Pixeltable solve?
+
+Today's solutions for AI app development require extensive custom coding and infrastructure plumbing. Tracking lineage and versions between and across data transformations, models, and deployments is cumbersome. Pixeltable lets ML Engineers and Data Scientists focus on exploration, modeling, and app development without dealing with the customary data plumbing.
+
 ### What does Pixeltable provide me with? Pixeltable provides:
 
 - Data storage and versioning

{pixeltable-0.2.17 → pixeltable-0.2.19}/README.md

@@ -1,33 +1,29 @@
 <div align="center">
-<img src="https://raw.githubusercontent.com/pixeltable/pixeltable/main/docs/release/pixeltable-banner.png" alt="Pixeltable" width="45%" />
-
-# Unifying Data, Models, and Orchestration for AI Products
+<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)]()
-[![pytest status](https://github.com/pixeltable/pixeltable/actions/workflows/pytest.yml/badge.svg)](https://github.com/pixeltable/pixeltable/actions)
+![Platform Support](https://img.shields.io/badge/platform-Linux%20%7C%20macOS%20%7C%20Windows-8A2BE2)
+<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/)
 
 [Installation](https://pixeltable.github.io/pixeltable/getting-started/) | [Documentation](https://pixeltable.readme.io/) | [API Reference](https://pixeltable.github.io/pixeltable/) | [Code Samples](https://pixeltable.readme.io/recipes) | [Examples](https://github.com/pixeltable/pixeltable/tree/release/docs/release/tutorials)
 </div>
 
-Pixeltable is a Python library that lets ML Engineers and Data Scientists focus on exploration, modeling, and app development without dealing with the customary data plumbing.
-
-### What problems does Pixeltable solve?
-
-Today’s solutions for AI app development require extensive custom coding and infrastructure plumbing. Tracking lineage and versions between and across data transformations, models, and deployment is cumbersome.
+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. Data transformations, model inference, and custom logic are embedded as computed columns.
 
 ## 💾 Installation
 
 ```python
 pip install pixeltable
 ```
-> [!IMPORTANT]
-> Pixeltable is persistent. Unlike in-memory Python libraries such as Pandas, Pixeltable is a database. When working locally or against an hosted version of Pixeltable, use [get_table](https://pixeltable.github.io/pixeltable/api/pixeltable/#pixeltable.get_table) at any time to retrieve an existing table.
+**Pixeltable is persistent. Unlike in-memory Python libraries such as Pandas, Pixeltable is a database.**
 
 ## 💡 Getting Started
-Learn how to create tables, populate them with data, and enhance them with built-in or user-defined transformations and AI operations.
+Learn how to create tables, populate them with data, and enhance them with built-in or user-defined transformations.
 
 | Topic | Notebook | Topic | Notebook |
 |:----------|:-----------------|:-------------------------|:---------------------------------:|
@@ -54,9 +50,32 @@ v.insert({'video': prefix + p} for p in paths)
 ```
 Learn how to [work with data in Pixeltable](https://pixeltable.readme.io/docs/working-with-external-files).
 
-### Add an object detection model to your workflow
+### Object detection in images using DETR model
 ```python
-table['detections'] = huggingface.detr_for_object_detection(table.input_image, model_id='facebook/detr-resnet-50')
+import pixeltable as pxt
+from pixeltable.functions import huggingface
+
+# Create a table to store data persistently
+t = pxt.create_table('image', {'image': pxt.ImageType()})
+
+# Insert some images
+prefix = 'https://upload.wikimedia.org/wikipedia/commons'
+paths = [
+    '/1/15/Cat_August_2010-4.jpg',
+    '/e/e1/Example_of_a_Dog.jpg',
+    '/thumb/b/bf/Bird_Diversity_2013.png/300px-Bird_Diversity_2013.png'
+]
+t.insert({'image': prefix + p} for p in paths)
+
+# Add a computed column for image classification
+t['classification'] = huggingface.detr_for_object_detection(
+    (t.image), model_id='facebook/detr-resnet-50'
+    )
+
+# Retrieve the rows where cats have been identified
+t.select(animal = t.image,
+         classification = t.classification.label_text[0]) \
+.where(t.classification.label_text[0]=='cat').head()
 ```
 Learn about computed columns and object detection: [Comparing object detection models](https://pixeltable.readme.io/docs/object-detection-in-videos).
 
@@ -72,9 +91,9 @@ def draw_boxes(img: PIL.Image.Image, boxes: list[list[float]]) -> PIL.Image.Imag
 ```
 Learn more about user-defined functions: [UDFs in Pixeltable](https://pixeltable.readme.io/docs/user-defined-functions-udfs).
 
-### Automate data operations with views
+### Automate data operations with views, e.g., split documents into chunks
 ```python
-# In this example, the view is defined by iteration over the chunks of a DocumentSplitter.
+# In this example, the view is defined by iteration over the chunks of a DocumentSplitter
 chunks_table = pxt.create_view(
     'rag_demo.chunks',
     documents_table,
@@ -87,7 +106,7 @@ Learn how to leverage views to build your [RAG workflow](https://pixeltable.read
 
 ### Evaluate model performance
 ```python
-# The computation of the mAP metric can simply become a query over the evaluation output, aggregated with the mean_ap() function.
+# The computation of the mAP metric can become a query over the evaluation output
 frames_view.select(mean_ap(frames_view.eval_yolox_tiny), mean_ap(frames_view.eval_yolox_m)).show()
 ```
 Learn how to leverage Pixeltable for [Model analytics](https://pixeltable.readme.io/docs/object-detection-in-videos).
@@ -99,7 +118,7 @@ chat_table = pxt.create_table('together_demo.chat', {'input': pxt.StringType()})
 # The chat-completions API expects JSON-formatted input:
 messages = [{'role': 'user', 'content': chat_table.input}]
 
-# This example shows how additional parameters from the Together API can be used in Pixeltable to customize the model behavior.
+# This example shows how additional parameters from the Together API can be used in Pixeltable
 chat_table['output'] = chat_completions(
     messages=messages,
     model='mistralai/Mixtral-8x7B-Instruct-v0.1',
@@ -123,12 +142,54 @@ chat_table.select(chat_table.input, chat_table.response).head()
 ```
 Learn how to interact with inference services such as [Together AI](https://pixeltable.readme.io/docs/together-ai) in Pixeltable.
 
+### Text and image similarity search on video frames with embedding indexes
+```python
+import pixeltable as pxt
+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.insert([{'video': '/video.mp4'}])
+
+frames_view = pxt.create_view(
+    'frames', video_table, iterator=FrameIterator.create(video=video_table.video))
+
+@pxt.expr_udf
+def embed_image(img: PIL.Image.Image):
+    return clip_image(img, model_id='openai/clip-vit-base-patch32')
+
+@pxt.expr_udf
+def str_embed(s: str):
+    return clip_text(s, model_id='openai/clip-vit-base-patch32')
+
+# Create an index on the 'frame' column that allows text and image search
+frames_view.add_embedding_index('frame', string_embed=str_embed, image_embed=embed_image)
+
+# Now we will retrieve images based on a sample image
+sample_image = '/image.jpeg'
+sim = frames_view.frame.similarity(sample_image)
+frames_view.order_by(sim, asc=False).limit(5).select(frames_view.frame, sim=sim).collect()
+
+# Now we will retrieve images based on a string
+sample_text = 'red truck'
+sim = frames_view.frame.similarity(sample_text)
+frames_view.order_by(sim, asc=False).limit(5).select(frames_view.frame, sim=sim).collect()
+
+```
+Learn how to work with [Embedding and Vector Indexes](https://docs.pixeltable.com/docs/embedding-vector-indexes).
+
 ## ❓ FAQ
 
 ### What is Pixeltable?
 
 Pixeltable unifies data storage, versioning, and indexing with orchestration and model versioning under a declarative table interface, with transformations, model inference, and custom logic represented as computed columns.
 
+### What problems does Pixeltable solve?
+
+Today's solutions for AI app development require extensive custom coding and infrastructure plumbing. Tracking lineage and versions between and across data transformations, models, and deployments is cumbersome. Pixeltable lets ML Engineers and Data Scientists focus on exploration, modeling, and app development without dealing with the customary data plumbing.
+
 ### What does Pixeltable provide me with? Pixeltable provides:
 
 - Data storage and versioning

{pixeltable-0.2.17 → pixeltable-0.2.19}/pixeltable/__init__.py

@@ -4,7 +4,7 @@ from .exceptions import Error
 from .exprs import RELATIVE_PATH_ROOT
 from .func import Function, udf, Aggregator, uda, expr_udf
 from .globals import init, create_table, create_view, get_table, move, drop_table, list_tables, create_dir, drop_dir, \
-    list_dirs, list_functions, configure_logging
+    list_dirs, list_functions, configure_logging, array
 from .type_system import (
     ColumnType,
     StringType,

{pixeltable-0.2.17 → pixeltable-0.2.19}/pixeltable/__version__.py

@@ -1,3 +1,3 @@
 # These version placeholders will be replaced during build.
-__version__ = "0.2.17"
-__version_tuple__ = (0, 2, 17)
+__version__ = "0.2.19"
+__version_tuple__ = (0, 2, 19)

{pixeltable-0.2.17 → pixeltable-0.2.19}/pixeltable/catalog/catalog.py

@@ -1,8 +1,9 @@
 from __future__ import annotations
-from typing import Optional, List, Any, Dict, Tuple
-from uuid import UUID
+
 import dataclasses
 import logging
+from typing import Optional
+from uuid import UUID
 
 import sqlalchemy as sql
 import sqlalchemy.orm as orm
@@ -10,8 +11,8 @@ import sqlalchemy.orm as orm
 from .table_version import TableVersion
 from .table_version_path import TableVersionPath
 from .table import Table
-from .named_function import NamedFunction
 from .path_dict import PathDict
+
 import pixeltable.env as env
 import pixeltable.metadata.schema as schema
 
@@ -39,10 +40,10 @@ class Catalog:
         # key: [id, version]
         # - mutable version of a table: version == None (even though TableVersion.version is set correctly)
         # - snapshot versions: records the version of the snapshot
-        self.tbl_versions: Dict[Tuple[UUID, Optional[int]], TableVersion] = {}
+        self.tbl_versions: dict[tuple[UUID, Optional[int]], TableVersion] = {}
 
-        self.tbls: Dict[UUID, Table] = {}  # don't use a defaultdict here, it doesn't cooperate with the debugger
-        self.tbl_dependents: Dict[UUID, List[Table]] = {}
+        self.tbls: dict[UUID, Table] = {}  # don't use a defaultdict here, it doesn't cooperate with the debugger
+        self.tbl_dependents: dict[UUID, list[Table]] = {}
 
         self._init_store()
         self.paths = PathDict()  # do this after _init_catalog()
@@ -133,7 +134,7 @@ class Catalog:
                         base_path=base_path if not is_snapshot else None)
                     view_path = TableVersionPath(tbl_version, base=base_path)
 
-                tbl = View(
+                tbl: Table = View(
                     tbl_record.id, tbl_record.dir_id, tbl_md.name, view_path, base_tbl_id,
                     snapshot_only=snapshot_only)
                 self.tbl_dependents[base_tbl_id].append(tbl)