# Mixpeek: v1

## v1

- [v1 / Documentation (187 pages)](https://docs.mixpeek.com/docs/_llms/v1/documentation.md): Documentation for v1 / Documentation.
- [v1 / API Reference (554 pages)](https://docs.mixpeek.com/docs/_llms/v1/api-reference.md): Documentation for v1 / API Reference.

### Vector Store

#### Vector Store

- [Vector Store](https://docs.mixpeek.com/docs/vector-store/overview.md): Use Mixpeek as a standalone vector database — bring your own embeddings, search instantly, promote to managed when ready
- [Namespaces](https://docs.mixpeek.com/docs/vector-store/namespaces.md): Create standalone namespaces with vector indexes, distance metrics, BM25, and payload indexes
- [Documents & Search](https://docs.mixpeek.com/docs/vector-store/documents.md): Upsert vectors, search with dense/sparse/BM25/hybrid, and manage documents
- [Import an External Export](https://docs.mixpeek.com/docs/vector-store/import.md): Reconstruct documents with vectors and lineage from another system's export, in three calls that validate before anything is written
- [Update & Delete Data](https://docs.mixpeek.com/docs/vector-store/manage-data.md): Update document metadata and delete documents, collections, and objects — including what cascades
- [Collection Lifecycle](https://docs.mixpeek.com/docs/vector-store/collection-lifecycle.md): Move collections between hot, cold, and archived tiers — pay for fast vector search only where you need it, keep everything else restorable
- [System Collections](https://docs.mixpeek.com/docs/vector-store/system-collections.md): The mxp_ collections Mixpeek provisions per namespace, what each stores, and what you can do with it
- [Bring Your Own Object Storage](https://docs.mixpeek.com/docs/vector-store/byo-object-storage.md): Back the Mixpeek Vector Store with your own S3-compatible or GCS bucket on dedicated and self-hosted deployments
- [Storage format (.mvs)](https://docs.mixpeek.com/docs/vector-store/storage-format.md): How Mixpeek stores your vectors and documents in your object storage bucket, in a documented format you can read without us.
- [Promote to Managed](https://docs.mixpeek.com/docs/vector-store/promote.md): Transition from standalone vectors to auto-embedding and collections — no reindexing required

### Guides

#### Guides

- [Semantic Search](https://docs.mixpeek.com/docs/tutorials/semantic-search.md): Build search with vector embeddings and hybrid ranking
- [Video Understanding](https://docs.mixpeek.com/docs/tutorials/video-understanding.md): Ingest video, extract visual + speech embeddings, and search for moments by what's shown or said
- [Reverse Media Search](https://docs.mixpeek.com/docs/tutorials/reverse-search.md): Find visually similar content using images or videos as your search query
- [Document Intelligence](https://docs.mixpeek.com/docs/tutorials/document-intelligence.md): Extract and query data from PDFs, images, and scanned documents
- [Visual Document Retrieval](https://docs.mixpeek.com/docs/tutorials/colpali-visual-document-retrieval.md): Search PDFs, scanned pages, and figure-heavy reports by visual content using cross-modal embeddings — no OCR required
- [Ingest Video from S3](https://docs.mixpeek.com/docs/tutorials/ingest-video-from-s3.md): Connect an S3 bucket, sync video files automatically, and make them searchable end-to-end
- [Custom Extractor Quickstart](https://docs.mixpeek.com/docs/tutorials/custom-extractor-quickstart.md): Build, test, and query a custom text embedding extractor
- [Add a New Understanding to Existing Content](https://docs.mixpeek.com/docs/tutorials/reprocess-existing-content.md): Run a new extractor over an already-ingested corpus — scoped, cost-safe, and priced before you run — without re-uploading or re-paying for existing work
- [Build a Feedback Loop](https://docs.mixpeek.com/docs/tutorials/feedback-loop.md): Start with static fusion weights, capture interaction signals, and let Thompson Sampling learn optimal weights automatically
- [Auto-Labeling Datasets](https://docs.mixpeek.com/docs/tutorials/bootstrap-labeled-dataset.md): Build a self-improving classification system using taxonomy auto-labeling
- [Self-Improving CV Pipeline](https://docs.mixpeek.com/docs/tutorials/annotations-improve-features.md): Deploy a YOLO model, annotate detections, fine-tune from corrections, and compound accuracy over time using annotations, taxonomies, and clusters