pixeltable 0.2.12__tar.gz → 0.2.13__tar.gz

pixeltable-0.2.13/PKG-INFO

@@ -0,0 +1,206 @@
+Metadata-Version: 2.1
+Name: pixeltable
+Version: 0.2.13
+Summary: Pixeltable: The Multimodal AI Data Plane
+Author: Pixeltable, Inc.
+Author-email: contact@pixeltable.com
+Requires-Python: >=3.9,<4.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: av (>=10.0.0)
+Requires-Dist: beautifulsoup4 (>=4.0.0,<5.0.0)
+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: opencv-python-headless (>=4.7.0.68,<5.0.0.0)
+Requires-Dist: pandas (>=2.0,<3.0)
+Requires-Dist: pgserver (==0.1.4)
+Requires-Dist: pgvector (>=0.2.1,<0.3.0)
+Requires-Dist: pillow (>=9.3.0)
+Requires-Dist: psutil (>=5.9.5,<6.0.0)
+Requires-Dist: psycopg2-binary (>=2.9.5,<3.0.0)
+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: 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/master/docs/release/pixeltable-banner.png" alt="Pixeltable" width="45%" />
+
+# Unifying Data, Models, and Orchestration for AI Products
+
+[![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)
+[![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/master/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.
+
+## 💾 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.
+
+## 💡 Getting Started
+Learn how to create tables, populate them with data, and enhance them with built-in or user-defined transformations and AI operations.
+
+| Topic | Notebook | Topic | Notebook |
+|:----------|:-----------------|:-------------------------|:---------------------------------:|
+| 10-Minute Tour of Pixeltable    | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/master/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/master/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/master/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/master/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/master/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/master/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/master/docs/release/tutorials/audio-transcriptions.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a>
+
+## 🧱 Code Samples
+
+### Import media data into Pixeltable (videos, images, audio...)
+```python
+import pixeltable as pxt
+
+v = pxt.create_table('external_data.videos', {'video': pxt.VideoType()})
+
+prefix = 's3://multimedia-commons/'
+paths = [
+    'data/videos/mp4/ffe/ffb/ffeffbef41bbc269810b2a1a888de.mp4',
+    'data/videos/mp4/ffe/feb/ffefebb41485539f964760e6115fbc44.mp4',
+    'data/videos/mp4/ffe/f73/ffef7384d698b5f70d411c696247169.mp4'
+]
+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
+```python
+table['detections'] = huggingface.detr_for_object_detection(table.input_image, model_id='facebook/detr-resnet-50')
+```
+Learn about computed columns and object detection: [Comparing object detection models](https://pixeltable.readme.io/docs/object-detection-in-videos).
+
+### Extend Pixeltable's capabilities with user-defined functions
+```python
+@pxt.udf
+def draw_boxes(img: PIL.Image.Image, boxes: list[list[float]]) -> PIL.Image.Image:
+    result = img.copy()  # Create a copy of `img`
+    d = PIL.ImageDraw.Draw(result)
+    for box in boxes:
+        d.rectangle(box, width=3)  # Draw bounding box rectangles on the copied image
+    return result
+```
+Learn more about user-defined functions: [UDFs in Pixeltable](https://pixeltable.readme.io/docs/user-defined-functions-udfs).
+
+### Automate data operations with views
+```python
+# 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,
+    iterator=DocumentSplitter.create(
+        document=documents_table.document,
+        separators='token_limit', limit=300)
+)
+```
+Learn how to leverage views to build your [RAG workflow](https://pixeltable.readme.io/docs/document-indexing-and-rag).
+
+### 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.
+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).
+
+### Working with inference services
+```python
+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.
+chat_table['output'] = chat_completions(
+    messages=messages,
+    model='mistralai/Mixtral-8x7B-Instruct-v0.1',
+    max_tokens=300,
+    stop=['\n'],
+    temperature=0.7,
+    top_p=0.9,
+    top_k=40,
+    repetition_penalty=1.1,
+    logprobs=1,
+    echo=True
+)
+chat_table['response'] = chat_table.output.choices[0].message.content
+
+# Start a conversation
+chat_table.insert([
+    {'input': 'How many species of felids have been classified?'},
+    {'input': 'Can you make me a coffee?'}
+])
+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.
+
+## ❓ 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 does Pixeltable provide me with? Pixeltable provides:
+
+- Data storage and versioning
+- Combined Data and Model Lineage
+- Indexing (e.g. embedding vectors) and Data Retrieval
+- Orchestration of multimodal workloads
+- Incremental updates
+- Code is automatically production-ready
+
+### Why should you use Pixeltable?
+
+- **It gives you transparency and reproducibility**
+  - All generated data is automatically recorded and versioned
+  - You will never need to re-run a workload because you lost track of the input data
+- **It saves you money**
+  - All data changes are automatically incremental
+  - You never need to re-run pipelines from scratch because you’re adding data
+- **It integrates with any existing Python code or libraries**
+  - Bring your ever-changing code and workloads
+  - You choose the models, tools, and AI practices (e.g., your embedding model for a vector index); Pixeltable orchestrates the data
+ 
+### What is Pixeltable not providing?
+
+- Pixeltable is not a low-code, prescriptive AI solution. We empower you to use the best frameworks and techniques for your specific needs.
+- We do not aim to replace your existing AI toolkit, but rather enhance it by streamlining the underlying data infrastructure and orchestration.
+
+> [!TIP]
+> Check out the [Integrations](https://pixeltable.readme.io/docs/working-with-openai) section, and feel free to submit a request for additional ones.
+
+## 🐛 Contributions & Feedback
+
+Are you experiencing issues or bugs with Pixeltable? File an [Issue](https://github.com/pixeltable/pixeltable/issues).
+</br>Do you want to contribute? Feel free to open a [PR](https://github.com/pixeltable/pixeltable/pulls).
+
+## :classical_building: License
+
+This library is licensed under the Apache 2.0 License.
+

pixeltable-0.2.13/README.md

@@ -0,0 +1,168 @@
+<div align="center">
+<img src="https://raw.githubusercontent.com/pixeltable/pixeltable/master/docs/release/pixeltable-banner.png" alt="Pixeltable" width="45%" />
+
+# Unifying Data, Models, and Orchestration for AI Products
+
+[![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)
+[![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/master/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.
+
+## 💾 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.
+
+## 💡 Getting Started
+Learn how to create tables, populate them with data, and enhance them with built-in or user-defined transformations and AI operations.
+
+| Topic | Notebook | Topic | Notebook |
+|:----------|:-----------------|:-------------------------|:---------------------------------:|
+| 10-Minute Tour of Pixeltable    | <a target="_blank" href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/master/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/master/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/master/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/master/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/master/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/master/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/master/docs/release/tutorials/audio-transcriptions.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a>
+
+## 🧱 Code Samples
+
+### Import media data into Pixeltable (videos, images, audio...)
+```python
+import pixeltable as pxt
+
+v = pxt.create_table('external_data.videos', {'video': pxt.VideoType()})
+
+prefix = 's3://multimedia-commons/'
+paths = [
+    'data/videos/mp4/ffe/ffb/ffeffbef41bbc269810b2a1a888de.mp4',
+    'data/videos/mp4/ffe/feb/ffefebb41485539f964760e6115fbc44.mp4',
+    'data/videos/mp4/ffe/f73/ffef7384d698b5f70d411c696247169.mp4'
+]
+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
+```python
+table['detections'] = huggingface.detr_for_object_detection(table.input_image, model_id='facebook/detr-resnet-50')
+```
+Learn about computed columns and object detection: [Comparing object detection models](https://pixeltable.readme.io/docs/object-detection-in-videos).
+
+### Extend Pixeltable's capabilities with user-defined functions
+```python
+@pxt.udf
+def draw_boxes(img: PIL.Image.Image, boxes: list[list[float]]) -> PIL.Image.Image:
+    result = img.copy()  # Create a copy of `img`
+    d = PIL.ImageDraw.Draw(result)
+    for box in boxes:
+        d.rectangle(box, width=3)  # Draw bounding box rectangles on the copied image
+    return result
+```
+Learn more about user-defined functions: [UDFs in Pixeltable](https://pixeltable.readme.io/docs/user-defined-functions-udfs).
+
+### Automate data operations with views
+```python
+# 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,
+    iterator=DocumentSplitter.create(
+        document=documents_table.document,
+        separators='token_limit', limit=300)
+)
+```
+Learn how to leverage views to build your [RAG workflow](https://pixeltable.readme.io/docs/document-indexing-and-rag).
+
+### 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.
+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).
+
+### Working with inference services
+```python
+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.
+chat_table['output'] = chat_completions(
+    messages=messages,
+    model='mistralai/Mixtral-8x7B-Instruct-v0.1',
+    max_tokens=300,
+    stop=['\n'],
+    temperature=0.7,
+    top_p=0.9,
+    top_k=40,
+    repetition_penalty=1.1,
+    logprobs=1,
+    echo=True
+)
+chat_table['response'] = chat_table.output.choices[0].message.content
+
+# Start a conversation
+chat_table.insert([
+    {'input': 'How many species of felids have been classified?'},
+    {'input': 'Can you make me a coffee?'}
+])
+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.
+
+## ❓ 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 does Pixeltable provide me with? Pixeltable provides:
+
+- Data storage and versioning
+- Combined Data and Model Lineage
+- Indexing (e.g. embedding vectors) and Data Retrieval
+- Orchestration of multimodal workloads
+- Incremental updates
+- Code is automatically production-ready
+
+### Why should you use Pixeltable?
+
+- **It gives you transparency and reproducibility**
+  - All generated data is automatically recorded and versioned
+  - You will never need to re-run a workload because you lost track of the input data
+- **It saves you money**
+  - All data changes are automatically incremental
+  - You never need to re-run pipelines from scratch because you’re adding data
+- **It integrates with any existing Python code or libraries**
+  - Bring your ever-changing code and workloads
+  - You choose the models, tools, and AI practices (e.g., your embedding model for a vector index); Pixeltable orchestrates the data
+ 
+### What is Pixeltable not providing?
+
+- Pixeltable is not a low-code, prescriptive AI solution. We empower you to use the best frameworks and techniques for your specific needs.
+- We do not aim to replace your existing AI toolkit, but rather enhance it by streamlining the underlying data infrastructure and orchestration.
+
+> [!TIP]
+> Check out the [Integrations](https://pixeltable.readme.io/docs/working-with-openai) section, and feel free to submit a request for additional ones.
+
+## 🐛 Contributions & Feedback
+
+Are you experiencing issues or bugs with Pixeltable? File an [Issue](https://github.com/pixeltable/pixeltable/issues).
+</br>Do you want to contribute? Feel free to open a [PR](https://github.com/pixeltable/pixeltable/pulls).
+
+## :classical_building: License
+
+This library is licensed under the Apache 2.0 License.

{pixeltable-0.2.12 → pixeltable-0.2.13}/pixeltable/__version__.py

@@ -1,3 +1,3 @@
 # These version placeholders will be replaced during build.
-__version__ = "0.2.12"
-__version_tuple__ = (0, 2, 12)
+__version__ = "0.2.13"
+__version_tuple__ = (0, 2, 13)

{pixeltable-0.2.12 → pixeltable-0.2.13}/pixeltable/catalog/insertable_table.py

@@ -129,11 +129,11 @@ class InsertableTable(Table):
                     msg = str(e)
                     raise excs.Error(f'Error in column {col.name}: {msg[0].lower() + msg[1:]}\nRow: {row}')
 
-    def delete(self, where: Optional['pixeltable.exprs.Predicate'] = None) -> UpdateStatus:
+    def delete(self, where: Optional['pixeltable.exprs.Expr'] = None) -> UpdateStatus:
         """Delete rows in this table.
 
         Args:
-            where: a Predicate to filter rows to delete.
+            where: a predicate to filter rows to delete.
 
         Examples:
             Delete all rows in a table:

{pixeltable-0.2.12 → pixeltable-0.2.13}/pixeltable/catalog/table.py

@@ -113,7 +113,7 @@ class Table(SchemaObject):
         from pixeltable.dataframe import DataFrame
         return DataFrame(self._tbl_version_path).select(*items, **named_items)
 
-    def where(self, pred: 'exprs.Predicate') -> 'pixeltable.dataframe.DataFrame':
+    def where(self, pred: 'exprs.Expr') -> 'pixeltable.dataframe.DataFrame':
         """Return a DataFrame for this table.
         """
         # local import: avoid circular imports
@@ -716,13 +716,13 @@ class Table(SchemaObject):
         raise NotImplementedError
 
     def update(
-            self, value_spec: dict[str, Any], where: Optional['pixeltable.exprs.Predicate'] = None, cascade: bool = True
+            self, value_spec: dict[str, Any], where: Optional['pixeltable.exprs.Expr'] = None, cascade: bool = True
     ) -> UpdateStatus:
         """Update rows in this table.
 
         Args:
             value_spec: a dictionary mapping column names to literal values or Pixeltable expressions.
-            where: a Predicate to filter rows to update.
+            where: a predicate to filter rows to update.
             cascade: if True, also update all computed columns that transitively depend on the updated columns.
 
         Examples:
@@ -786,11 +786,11 @@ class Table(SchemaObject):
             row_updates.append(col_vals)
         return self._tbl_version.batch_update(row_updates, rowids, cascade)
 
-    def delete(self, where: Optional['pixeltable.exprs.Predicate'] = None) -> UpdateStatus:
+    def delete(self, where: Optional['pixeltable.exprs.Expr'] = None) -> UpdateStatus:
         """Delete rows in this table.
 
         Args:
-            where: a Predicate to filter rows to delete.
+            where: a predicate to filter rows to delete.
 
         Examples:
             Delete all rows in a table:

{pixeltable-0.2.12 → pixeltable-0.2.13}/pixeltable/catalog/table_version.py

@@ -678,12 +678,12 @@ class TableVersion:
         return result
 
     def update(
-        self, value_spec: dict[str, Any], where: Optional['exprs.Predicate'] = None, cascade: bool = True
+        self, value_spec: dict[str, Any], where: Optional['exprs.Expr'] = None, cascade: bool = True
     ) -> UpdateStatus:
         """Update rows in this TableVersionPath.
         Args:
             value_spec: a list of (column, value) pairs specifying the columns to update and their new values.
-            where: a Predicate to filter rows to update.
+            where: a predicate to filter rows to update.
             cascade: if True, also update all computed columns that transitively depend on the updated columns,
                 including within views.
         """
@@ -694,8 +694,8 @@ class TableVersion:
 
         update_spec = self._validate_update_spec(value_spec, allow_pk=False, allow_exprs=True)
         if where is not None:
-            if not isinstance(where, exprs.Predicate):
-                raise excs.Error(f"'where' argument must be a Predicate, got {type(where)}")
+            if not isinstance(where, exprs.Expr):
+                raise excs.Error(f"'where' argument must be a predicate, got {type(where)}")
             analysis_info = Planner.analyze(self.path, where)
             # for now we require that the updated rows can be identified via SQL, rather than via a Python filter
             if analysis_info.filter is not None:
@@ -757,7 +757,7 @@ class TableVersion:
 
     def _update(
             self, conn: sql.engine.Connection, update_targets: dict[Column, 'pixeltable.exprs.Expr'],
-            where_clause: Optional['pixeltable.exprs.Predicate'] = None, cascade: bool = True,
+            where_clause: Optional['pixeltable.exprs.Expr'] = None, cascade: bool = True,
             show_progress: bool = True
     ) -> UpdateStatus:
         from pixeltable.plan import Planner
@@ -789,8 +789,6 @@ class TableVersion:
                 raise excs.Error(f'Column {col_name} is computed and cannot be updated')
             if col.is_pk and not allow_pk:
                 raise excs.Error(f'Column {col_name} is a primary key column and cannot be updated')
-            if col.col_type.is_media_type():
-                raise excs.Error(f'Column {col_name} has type image/video/audio/document and cannot be updated')
 
             # make sure that the value is compatible with the column type
             try:
@@ -848,17 +846,17 @@ class TableVersion:
         result.cols_with_excs = list(dict.fromkeys(result.cols_with_excs).keys())  # remove duplicates
         return result
 
-    def delete(self, where: Optional['exprs.Predicate'] = None) -> UpdateStatus:
+    def delete(self, where: Optional['exprs.Expr'] = None) -> UpdateStatus:
         """Delete rows in this table.
         Args:
-            where: a Predicate to filter rows to delete.
+            where: a predicate to filter rows to delete.
         """
         assert self.is_insertable()
-        from pixeltable.exprs import Predicate
+        from pixeltable.exprs import Expr
         from pixeltable.plan import Planner
         if where is not None:
-            if not isinstance(where, Predicate):
-                raise excs.Error(f"'where' argument must be a Predicate, got {type(where)}")
+            if not isinstance(where, Expr):
+                raise excs.Error(f"'where' argument must be a predicate, got {type(where)}")
             analysis_info = Planner.analyze(self.path, where)
             # for now we require that the updated rows can be identified via SQL, rather than via a Python filter
             if analysis_info.filter is not None:
@@ -872,11 +870,11 @@ class TableVersion:
         return status
 
     def propagate_delete(
-            self, where: Optional['exprs.Predicate'], base_versions: List[Optional[int]],
+            self, where: Optional['exprs.Expr'], base_versions: List[Optional[int]],
             conn: sql.engine.Connection, timestamp: float) -> int:
         """Delete rows in this table and propagate to views.
         Args:
-            where: a Predicate to filter rows to delete.
+            where: a predicate to filter rows to delete.
         Returns:
             number of deleted rows
         """

{pixeltable-0.2.12 → pixeltable-0.2.13}/pixeltable/catalog/view.py

@@ -51,7 +51,7 @@ class View(Table):
     @classmethod
     def create(
             cls, dir_id: UUID, name: str, base: TableVersionPath, schema: Dict[str, Any],
-            predicate: 'pxt.exprs.Predicate', is_snapshot: bool, num_retained_versions: int, comment: str,
+            predicate: 'pxt.exprs.Expr', is_snapshot: bool, num_retained_versions: int, comment: str,
             iterator_cls: Optional[Type[ComponentIterator]], iterator_args: Optional[Dict]
     ) -> View:
         columns = cls._create_columns(schema)
@@ -213,5 +213,5 @@ class View(Table):
     ) -> UpdateStatus:
         raise excs.Error(f'{self.display_name()} {self._name!r}: cannot insert into view')
 
-    def delete(self, where: Optional['pixeltable.exprs.Predicate'] = None) -> UpdateStatus:
+    def delete(self, where: Optional['pixeltable.exprs.Expr'] = None) -> UpdateStatus:
         raise excs.Error(f'{self.display_name()} {self._name!r}: cannot delete from view')

{pixeltable-0.2.12 → pixeltable-0.2.13}/pixeltable/dataframe.py

@@ -153,7 +153,7 @@ class DataFrame:
         self,
         tbl: catalog.TableVersionPath,
         select_list: Optional[List[Tuple[exprs.Expr, Optional[str]]]] = None,
-        where_clause: Optional[exprs.Predicate] = None,
+        where_clause: Optional[exprs.Expr] = None,
         group_by_clause: Optional[List[exprs.Expr]] = None,
         grouping_tbl: Optional[catalog.TableVersion] = None,
         order_by_clause: Optional[List[Tuple[exprs.Expr, bool]]] = None,  # List[(expr, asc)]
@@ -530,7 +530,11 @@ class DataFrame:
             limit=self.limit_val,
         )
 
-    def where(self, pred: exprs.Predicate) -> DataFrame:
+    def where(self, pred: exprs.Expr) -> DataFrame:
+        if not isinstance(pred, exprs.Expr):
+            raise excs.Error(f'Where() requires a Pixeltable expression, but instead got {type(pred)}')
+        if not pred.col_type.is_bool_type():
+            raise excs.Error(f'Where(): expression needs to return bool, but instead returns {pred.col_type}')
         return DataFrame(
             self.tbl,
             select_list=self.select_list,
@@ -628,12 +632,9 @@ class DataFrame:
     def __getitem__(self, index: object) -> DataFrame:
         """
         Allowed:
-        - [<Predicate>]: filter operation
         - [List[Expr]]/[Tuple[Expr]]: setting the select list
         - [Expr]: setting a single-col select list
         """
-        if isinstance(index, exprs.Predicate):
-            return self.where(index)
         if isinstance(index, tuple):
             index = list(index)
         if isinstance(index, exprs.Expr):
@@ -668,7 +669,7 @@ class DataFrame:
         tbl = catalog.TableVersionPath.from_dict(d['tbl'])
         select_list = [(exprs.Expr.from_dict(e), name) for e, name in d['select_list']] \
             if d['select_list'] is not None else None
-        where_clause = exprs.Predicate.from_dict(d['where_clause']) \
+        where_clause = exprs.Expr.from_dict(d['where_clause']) \
             if d['where_clause'] is not None else None
         group_by_clause = [exprs.Expr.from_dict(e) for e in d['group_by_clause']] \
             if d['group_by_clause'] is not None else None

{pixeltable-0.2.12 → pixeltable-0.2.13}/pixeltable/exec/expr_eval_node.py

@@ -50,7 +50,14 @@ class ExprEvalNode(ExecNode):
 
     def _open(self) -> None:
         warnings.simplefilter("ignore", category=TqdmWarning)
-        if self.ctx.show_pbar:
+        # This is a temporary hack. When B-tree indices on string columns were implemented (via computed columns
+        # that invoke the `BtreeIndex.str_filter` udf), it resulted in frivolous progress bars appearing on every
+        # insertion. This special-cases the `str_filter` call to suppress the corresponding progress bar.
+        # TODO(aaron-siegel) Remove this hack once we clean up progress bars more generally.
+        is_str_filter_node = all(
+            isinstance(expr, exprs.FunctionCall) and expr.fn.name == 'str_filter' for expr in self.output_exprs
+        )
+        if self.ctx.show_pbar and not is_str_filter_node:
             self.pbar = tqdm(
                 total=len(self.target_exprs) * self.ctx.num_rows,
                 desc='Computing cells',

{pixeltable-0.2.12 → pixeltable-0.2.13}/pixeltable/exec/sql_scan_node.py

@@ -19,7 +19,7 @@ class SqlScanNode(ExecNode):
     def __init__(
             self, tbl: catalog.TableVersionPath, row_builder: exprs.RowBuilder,
             select_list: Iterable[exprs.Expr],
-            where_clause: Optional[exprs.Expr] = None, filter: Optional[exprs.Predicate] = None,
+            where_clause: Optional[exprs.Expr] = None, filter: Optional[exprs.Expr] = None,
             order_by_items: Optional[List[Tuple[exprs.Expr, bool]]] = None,
             limit: int = 0, set_pk: bool = False, exact_version_only: Optional[List[catalog.TableVersion]] = None
     ):

{pixeltable-0.2.12 → pixeltable-0.2.13}/pixeltable/exprs/__init__.py

@@ -17,7 +17,6 @@ from .json_mapper import JsonMapper
 from .json_path import RELATIVE_PATH_ROOT, JsonPath
 from .literal import Literal
 from .object_ref import ObjectRef
-from .predicate import Predicate
 from .row_builder import RowBuilder, ColumnSlotIdx, ExecProfile
 from .rowid_ref import RowidRef
 from .similarity_expr import SimilarityExpr

{pixeltable-0.2.12 → pixeltable-0.2.13}/pixeltable/exprs/comparison.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Optional, List, Any, Dict, Tuple
+from typing import Optional, List, Any, Dict
 
 import sqlalchemy as sql
 
@@ -9,15 +9,15 @@ from .data_row import DataRow
 from .expr import Expr
 from .globals import ComparisonOperator
 from .literal import Literal
-from .predicate import Predicate
 from .row_builder import RowBuilder
 import pixeltable.exceptions as excs
 import pixeltable.index as index
+import pixeltable.type_system as ts
 
 
-class Comparison(Predicate):
+class Comparison(Expr):
     def __init__(self, operator: ComparisonOperator, op1: Expr, op2: Expr):
-        super().__init__()
+        super().__init__(ts.BoolType())
         self.operator = operator
 
         # if this is a comparison of a column to a literal (ie, could be used as a search argument in an index lookup),
@@ -50,7 +50,7 @@ class Comparison(Predicate):
     def _equals(self, other: Comparison) -> bool:
         return self.operator == other.operator
 
-    def _id_attrs(self) -> List[Tuple[str, Any]]:
+    def _id_attrs(self) -> list[tuple[str, Any]]:
         return super()._id_attrs() + [('operator', self.operator.value)]
 
     @property