Metadata Enrichment Pipeline

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY", namespace="enriched-data")

# 1. A bucket for feedback, and a collection whose LLM step extracts entities,
#    topic, sentiment and language onto every document
bucket = client.buckets.create(
    bucket_name="customer-feedback",
    bucket_schema={"properties": {"ticket": {"type": "text"}}},
)
collection = client.collections.create(
    collection_name="customer-feedback",
    source={"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
    feature_extractor={
        "feature_extractor_name": "text_extractor",
        "version": "v1",
        "parameters": {
            "response_shape": "entities (list of names), topic, sentiment (positive, neutral or negative) and language code",
            "llm_provider": "openai",
            "llm_model": "gpt-4o-mini",
        },
    },
)

# 2. Upload and process
client.buckets.upload(
    bucket["bucket_id"],
    blobs=[{"property": "ticket", "type": "text", "data": "s3://your-bucket/feedback/ticket-8812.txt"}],
)
client.collections.trigger(collection["collection_id"])

# 3. Read the enriched documents
docs = client.documents.list(collection["collection_id"], page_size=100)
for doc in docs["results"]:
    print(doc["document_id"], doc.get("sentiment"), doc.get("topic"), doc.get("entities"))