Examples by task
Updated
Notebooks, /recipes apps, /learn/how-to guides, /use-cases, /reference-architecture pages, and docs.pixeltable.com cookbooks, grouped by the task they teach.
Video search
Sample stills from a clip, embed them, optionally transcribe speech, and return a title plus a presentation timestamp.
- Video search example app (Example app) - Runnable app.py: frames, CLIP, HTTP search.
- How do I index a video library and search it by text? (How-to) - TableModel walkthrough with FastAPIRouter.
- How do I extract keyframes from video? (How-to) - frame_iterator, fps, keyframes_only, frame_attrs.
- How do I build video RAG in Python? (How-to) - Retrieved moment, then an LLM column.
- How does video search work? (Learn) - Concept: a moment, not a filename.
- Video search engine use case (Use case) - Implementation guide on the use-cases hub.
- Object detection in videos notebook (Notebook) - YOLOX on sampled frames (Colab).
- Video search reference architecture (Architecture) - Slots, Twelve Labs / Mixpeek alternatives, sketch.
- Pixeltable for media and entertainment (Industry) - Worked trailer-and-archive pipeline.
- Extract frames from videos (docs) (Docs) - docs.pixeltable.com cookbook.
PDF RAG
Split PDFs into passage rows, embed them, retrieve, then generate from those rows. Vision RAG is the image half of the same schema.
- RAG demo notebook (Notebook) - Chunking, embeddings, and LLM integration in Colab.
- How do I build a multimodal RAG pipeline? (How-to) - document_splitter plus CLIP; retrieve then generate.
- How do I chunk PDFs for RAG? (How-to) - sentence,token_limit vs page metadata.
- What is multimodal RAG? (Learn) - Passages, stills, or frames as retrieved pieces.
- Production RAG implementation (Use case) - Use-case guide for a production RAG table.
- Invoice audit example app (Example app) - Document rows and computed checks in app.py.
- Multimodal RAG reference architecture (Architecture) - Qdrant, pgvector, S3 slots and a TableModel sketch.
- Pixeltable for document-heavy insurance (Industry) - FNOL passages filtered by claim_id.
- Build a RAG pipeline (docs) (Docs) - docs.pixeltable.com cookbook.
Image dedup
Hash exact duplicates, CLIP for near-duplicates and text-to-image search, check a candidate before insert.
- How do I deduplicate a large image dataset? (How-to) - Hash UDF, CLIP, keep_if_new. POST does not check.
- How do I embed images for search? (How-to) - CLIP EmbeddingIndex; similarity(string=) or similarity(image=).
- How do I serve image similarity search? (How-to) - FastAPIRouter insert plus text and image-upload search.
- Embedding indexes notebook (Notebook) - Incremental indexes and similarity search.
- Travel scrapbook example app (Example app) - Image uploads in a runnable app.py.
- User-uploaded media architecture (Architecture) - S3, Qdrant, hash, CLIP, HTTP slots.
- Pixeltable for ecommerce catalogs (Industry) - SKU photos with exact-hash and CLIP search.
- Find similar images with CLIP (docs) (Docs) - docs.pixeltable.com cookbook.
Audio transcription and search
Split uploads into timestamped slices, transcribe, embed the text, and return a file plus seconds.
- How do I transcribe audio uploads and make them searchable? (How-to) - audio_splitter, Whisper, EmbeddingIndex, HTTP.
- Audio processing and transcription notebook (Notebook) - Extract, transcribe, and search audio from video.
- Audio transcription pipeline use case (Use case) - Implementation guide on the use-cases hub.
- Working with OpenAI notebook (Notebook) - Includes Whisper among other OpenAI models.
- Transcribe audio (docs) (Docs) - docs.pixeltable.com cookbook.
Agent memory
Durable memory rows, an embedding index, recall as a query, then a prompt. The loop is separate from the store.
- Research Agent Memory example app (Example app) - Runnable memory table in app.py.
- Chat agent example app (Example app) - A chat agent on the same backend.
- Agent memory backend architecture (Architecture) - Mem0, Letta, Zep, Qdrant slots and a TableModel sketch.
- AI agent architecture (interactive diagram) (Architecture) - Broader agent system diagram already on the site.
- AI agents and MCP use case (Use case) - Agents that call Pixeltable as a tool.
- What is agentic RAG? (Learn) - Retrieval an agent calls against durable rows.
- Build an agent with memory (docs) (Docs) - docs.pixeltable.com cookbook.