Reverse Video Search

Search your video library by submitting a video clip as the query. The pipeline decomposes the query video into scene-level embeddings and matches them against your indexed video collection to find visually and semantically similar content.

video

Multi-Tier

Run in Builder

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY", namespace="video-library")

# 1. A bucket for the video library, and a collection that splits each video into scenes with a multimodal embedding
bucket = client.buckets.create(
    bucket_name="video-library",
    bucket_schema={
        "properties": {
            "video": {
                "type": "video",
            },
        },
    },
)
collection = client.collections.create(
    collection_name="video_library",
    source={"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
    feature_extractor={
        "feature_extractor_name": "multimodal_extractor",
        "version": "v1",
        "parameters": {
            "split_method": "scene",
        },
    },
)

# 2. Upload and process
client.buckets.upload(
    bucket["bucket_id"],
    blobs=[{"property": "video", "type": "video", "data": "s3://your-bucket/videos/launch-film.mp4"}],
)
client.collections.trigger(collection["collection_id"])

# 3. A clip searched against indexed scenes, keeping the best scene per source video
retriever = client.retrievers.create(
    retriever_name="reverse-video-search",
    collection_identifiers=["video_library"],
    input_schema={
        "clip": {
            "type": "video",
            "required": True,
        },
    },
    stages=[
        {
            "stage_name": "search",
            "stage_id": "feature_search",
            "parameters": {
                "searches": [
                    {
                        "feature_uri": "mixpeek://multimodal_extractor@v1/vertex_multimodal_embedding",
                        "query": {
                            "input_mode": "content",
                            "value": "{{INPUT.clip}}",
                        },
                        "top_k": 100,
                    },
                ],
                "final_top_k": 100,
                "group_by": {
                    "field": "source_object_id",
                    "max_per_group": 1,
                    "limit": 20,
                },
            },
        },
    ],
)

# 4. Search
results = client.retrievers.execute(
    retriever["retriever_id"],
    inputs={
    "clip": "https://example.com/query-clip.mp4",
},
)

for doc in results["documents"]:
    print(doc["source_object_id"], doc["start_time"], doc["score"])