Amazon Nova와 OpenSearch를 활용한 대규모 멀티모달 비디오 검색 시스템 구축

response = bedrock.start_async_invoke(
    modelId="amazon.nova-2-multimodal-embeddings-v1:0",
    modelInput={
        "taskType": "SEGMENTED_EMBEDDING",
        "segmentedEmbeddingParams": {
            "embeddingPurpose": "GENERIC_INDEX",
            "embeddingDimension": 1024,
            "video": {
                "format": "mp4",
                "embeddingMode": "AUDIO_VIDEO_COMBINED",
                "source": {"s3Location": {"uri": video_s3_uri}},
                "segmentationConfig": {"durationSeconds": 15}
            }
        }
    },
    outputDataConfig={"s3OutputDataConfig": {"s3Uri": output_s3_uri}}
)

knn_index_body = {
    "settings": {
        "index.knn": True,
        "number_of_shards": 2,
        "number_of_replicas": 1
    },
    "mappings": {
        "properties": {
            "video_id": {"type": "keyword"},
            "segment_index": {"type": "integer"},
            "timestamp": {"type": "float"},
            "embedding": {
                "type": "knn_vector",
                "dimension": 1024,
                "method": {
                    "name": "hnsw",
                    "space_type": "cosinesimilarity",
                    "engine": "faiss"
                }
            },
            "s3_uri": {"type": "keyword"}
        }
    }
}
opensearch_client.indices.create(index="video-embeddings-knn", body=knn_index_body)

def search_hybrid(query_text, opensearch_client, k=10, vector_weight=0.7, text_weight=0.3):
    query_embedding = generate_query_embedding(query_text)
    knn_response = opensearch_client.search(
        index="video-embeddings-knn",
        body={"query": {"knn": {"embedding": {"vector": query_embedding, "k": 20}}}, "size": 20}
    )
    text_response = opensearch_client.search(
        index="video-embeddings-text",
        body={"query": {"match": {"tags": query_text}}, "size": 20}
    )
    // ...(중략)
    for hit in knn_hits:
        combined[key]['combined_score'] = hit['_score'] * vector_weight
    for hit in text_hits:
        combined[key]['combined_score'] += hit['_score'] * text_weight
    return sorted(combined.values(), key=lambda x: x['combined_score'], reverse=True)[:k]