llms.txt Content
# Pixeltable Documentation
> The only open source Python library providing declarative data infrastructure for building multimodal AI applications, enabling incremental storage, transformation, indexing, retrieval, and orchestration of data.
## Docs
- [Changelog](https://docs.pixeltable.com/changelog/changelog.md): Release history and updates for Pixeltable
- [Agentic Patterns](https://docs.pixeltable.com/howto/cookbooks/agents/agentic-patterns.md)
- [Use tool calling and MCP servers with LLMs](https://docs.pixeltable.com/howto/cookbooks/agents/llm-tool-calling.md)
- [Build an agent with memory](https://docs.pixeltable.com/howto/cookbooks/agents/pattern-agent-memory.md)
- [Look up structured data with retrieval UDFs](https://docs.pixeltable.com/howto/cookbooks/agents/pattern-data-lookup.md)
- [Build a RAG pipeline](https://docs.pixeltable.com/howto/cookbooks/agents/pattern-rag-pipeline.md)
- [Use a table pipeline as a reusable function](https://docs.pixeltable.com/howto/cookbooks/agents/pattern-table-as-udf.md)
- [Extract audio from video](https://docs.pixeltable.com/howto/cookbooks/audio/audio-extract-from-video.md)
- [Summarize podcasts and audio](https://docs.pixeltable.com/howto/cookbooks/audio/audio-summarize-podcast.md)
- [Convert text to speech](https://docs.pixeltable.com/howto/cookbooks/audio/audio-text-to-speech.md)
- [Transcribe audio files with Whisper](https://docs.pixeltable.com/howto/cookbooks/audio/audio-transcribe.md)
- [Create custom aggregate functions (UDAs)](https://docs.pixeltable.com/howto/cookbooks/core/custom-aggregates-uda.md)
- [Custom Iterators](https://docs.pixeltable.com/howto/cookbooks/core/custom-iterators.md)
- [Split data into multiple rows with iterators](https://docs.pixeltable.com/howto/cookbooks/core/data-split-rows.md)
- [Get fast feedback on transformations](https://docs.pixeltable.com/howto/cookbooks/core/dev-iterative-workflow.md)
- [Join tables to combine data](https://docs.pixeltable.com/howto/cookbooks/core/query-join-