Feature Extraction

import requests

API_URL = "https://api.mixpeek.com"
headers = {"Authorization": "Bearer YOUR_API_KEY", "X-Namespace": "your-namespace"}

# Create collection with feature extractor
collection = requests.post(f"{API_URL}/v1/collections", headers=headers, json={
    "collection_name": "enriched_media",
    "source": {"type": "bucket", "bucket_id": "raw-media"},
    "feature_extractor": {
        "feature_extractor_name": "multimodal_extractor",
        "version": "v1",
        "input_mappings": {"video": "source_video"},
        "parameters": {"enable_transcription": True}
    }
}).json()

# Index content - extraction happens automatically
requests.post(f"{API_URL}/v1/buckets/raw-media/objects", headers=headers, json={
    "blobs": [{"property": "source_video", "url": "s3://bucket/meeting.mp4"}]
})

# Search across all extracted features
results = requests.post(
    f"{API_URL}/v1/retrievers/enriched-search/execute",
    headers=headers,
    json={"query": {"text": "quarterly roadmap discussion"}}
).json()

# Access extracted features directly
for doc in results["documents"]:
    print(f"Transcript: {doc.get('transcript', '')[:200]}...")
    print(f"Feature URI: {doc['feature_address']}")