Image Deduplication Pipeline

import requests

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY", namespace="image-library")
API = "https://api.mixpeek.com/v1"
HEADERS = {"Authorization": "Bearer YOUR_API_KEY", "X-Namespace": "image-library"}

# 1. A bucket for the library, and a collection that embeds each image
bucket = client.buckets.create(
    bucket_name="image-library",
    bucket_schema={"properties": {"image": {"type": "image"}}},
)
collection = client.collections.create(
    collection_name="image_library",
    source={"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
    feature_extractor={
        "feature_extractor_name": "multimodal_extractor",
        "version": "v1",
    },
)
client.buckets.upload(
    bucket["bucket_id"],
    blobs=[{"property": "image", "type": "image", "data": "s3://your-bucket/images/IMG_0001.jpg"}],
)
client.collections.trigger(collection["collection_id"])

# 2. HDBSCAN with a minimum group size of 2 turns near-duplicates into small,
#    tight clusters. The SDK has no clusters resource, so this is REST.
cluster = requests.post(API + "/clusters", headers=HEADERS, json={
    "cluster_name": "near-duplicates",
    "collection_ids": [collection["collection_id"]],
    "cluster_type": "vector",
    "vector_config": {
        "feature_uris": ["mixpeek://multimodal_extractor@v1/vertex_multimodal_embedding"],
        "clustering_method": "hdbscan",
        "algorithm_params": {"min_cluster_size": 2},
    },
}).json()
requests.post(API + "/clusters/" + cluster["cluster_id"] + "/execute", headers=HEADERS, json={})

# 3. Once the execution finishes, review the groups
groups = requests.get(API + "/clusters/" + cluster["cluster_id"] + "/groups", headers=HEADERS).json()
print(groups["total_groups"], "groups of near-duplicates")