Automated Video Tagging
Automatically generate descriptive tags for video content using scene analysis, object detection, and taxonomy classification. Each video receives structured labels for scenes, objects, actions, and custom business categories without manual annotation.
from mixpeek import Mixpeekclient = Mixpeek(api_key="YOUR_API_KEY")# Define tagging taxonomy with category exemplarstaxonomy = client.taxonomies.create(namespace_id="ns_your_namespace",name="video_tags",taxonomy_type="hierarchical",hierarchy=[{"node_id": "sports", "collection_id": "col_sports_examples"},{"node_id": "cooking", "collection_id": "col_cooking_examples"},{"node_id": "technology", "collection_id": "col_tech_examples"},{"node_id": "outdoors", "collection_id": "col_outdoors_examples"},])# Apply taxonomy to video collectionclient.collections.apply_taxonomy(collection_id="col_videos",taxonomy_id=taxonomy["taxonomy_id"])# Retrieve tagged documentsdocs = client.documents.list(collection_id="col_videos",filters={"taxonomy_enrichment.category": "sports"})for doc in docs["results"]:tags = doc.get("taxonomy_enrichment", {})print(f"Video: {doc['root_object_id']}, Tags: {tags}")
Feature Extractors
Retriever Stages
aggregate
Compute aggregations (COUNT, SUM, AVG, etc.) on pipeline results
