Video Scene Search
Find specific scenes within videos using natural language descriptions. The pipeline detects scene boundaries, generates embeddings for each scene, and enables precise timestamp-level search across an entire video library. Query for visual content, actions, or spoken dialogue.
from mixpeek import Mixpeekclient = Mixpeek(api_key="YOUR_API_KEY")# Create video collection with scene decompositioncollection = client.collections.create(namespace_id="ns_your_namespace",name="video_scenes",extractors=["multimodal-extractor", "text-extractor"],params={"video_chunking": "scene-based"})# Upload videosclient.buckets.upload(bucket_id="bkt_videos", url="s3://your-bucket/videos/")# Search for a specific sceneresults = client.retrievers.execute(retriever_id="ret_scene_search",query={"text": "person presenting a chart on a whiteboard"})for doc in results["results"]:print(f"Video: {doc['root_object_id']}")print(f" Scene: {doc['start_time']:.1f}s - {doc['end_time']:.1f}s")print(f" Score: {doc['score']:.3f}")if doc.get("text"):print(f" Transcript: {doc['text'][:80]}...")
Feature Extractors
Retriever Stages
rerank
Rerank documents using cross-encoder models for accurate relevance
