Multimodal Content Moderation

import requests

from mixpeek import Mixpeek

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

# 1. Policy exemplars: images labeled safe, sensitive or prohibited
example_bucket = client.buckets.create(
    bucket_name="policy-examples",
    bucket_schema={"properties": {"image": {"type": "image"}}},
)
examples = client.collections.create(
    collection_name="policy-examples",
    source={"type": "bucket", "bucket_ids": [example_bucket["bucket_id"]]},
    feature_extractor={
        "feature_extractor_name": "multimodal_extractor",
        "version": "v1",
    },
)
client.buckets.upload(
    example_bucket["bucket_id"],
    blobs=[{"property": "image", "type": "image", "data": "s3://your-bucket/policy/prohibited-weapons-01.jpg"}],
)
client.collections.trigger(examples["collection_id"])

# 2. The retriever the taxonomy uses to find the closest exemplar
matcher = client.retrievers.create(
    retriever_name="policy-matcher",
    collection_identifiers=["policy-examples"],
    input_schema={"query": {"type": "text", "required": True}},
    stages=[
        {
            "stage_name": "search",
            "stage_id": "feature_search",
            "parameters": {
                "searches": [
                    {
                        "feature_uri": "mixpeek://multimodal_extractor@v1/vertex_multimodal_embedding",
                        "query": {"input_mode": "text", "value": "{{INPUT.query}}"},
                        "top_k": 3,
                    },
                ],
                "final_top_k": 3,
            },
        },
    ],
)

# A flat taxonomy matches each document, through a retriever, against a
# collection of labeled examples. The SDK has no taxonomies resource, so this is REST.
taxonomy = requests.post(API + "/taxonomies", headers=HEADERS, json={
    "taxonomy_name": "content_moderation",
    "config": {
        "taxonomy_type": "flat",
        "retriever_id": matcher["retriever_id"],
        "input_mappings": [{"input_key": "query", "source_type": "payload", "path": "description"}],
        "source_collection": {"collection_id": examples["collection_id"]},
    },
}).json()

# 3. User content, labeled at query time, with an LLM check for the borderline cases
bucket = client.buckets.create(
    bucket_name="user-content",
    bucket_schema={"properties": {"upload": {"type": "image"}}},
)
uploads = client.collections.create(
    collection_name="user-content",
    source={"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
    feature_extractor={
        "feature_extractor_name": "multimodal_extractor",
        "version": "v1",
        "parameters": {
            "run_video_description": True,
        },
    },
)
moderation = client.retrievers.create(
    retriever_name="moderation-review",
    collection_identifiers=["user-content"],
    input_schema={"image": {"type": "image", "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.image}}"},
                        "top_k": 20,
                    },
                ],
                "final_top_k": 20,
            },
        },
        {"stage_name": "label", "stage_id": "taxonomy_enrich", "parameters": {"taxonomy_id": taxonomy["taxonomy_id"], "top_k": 1}},
        {"stage_name": "borderline", "stage_id": "llm_filter", "parameters": {"criteria": "Keep content that shows weapons, nudity or hate symbols.", "provider": "google", "model_name": "gemini-2.5-flash-lite"}},
    ],
)

results = client.retrievers.execute(moderation["retriever_id"], inputs={"image": "https://example.com/user-upload.jpg"})
for doc in results["documents"]:
    print(doc["document_id"], doc["score"])