Taxonomy Enrichment Pipeline

import requests

from mixpeek import Mixpeek

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

# 1. Labeled examples: one document per category, with its label in the text
example_bucket = client.buckets.create(
    bucket_name="category-examples",
    bucket_schema={"properties": {"example": {"type": "text"}}},
)
examples = client.collections.create(
    collection_name="category-examples",
    source={"type": "bucket", "bucket_ids": [example_bucket["bucket_id"]]},
    feature_extractor={
        "feature_extractor_name": "text_extractor",
        "version": "v1",
    },
)
client.buckets.upload(
    example_bucket["bucket_id"],
    blobs=[{"property": "example", "type": "text", "data": "s3://your-bucket/taxonomy/ai-ml.txt"}],
)
client.collections.trigger(examples["collection_id"])

# 2. The retriever the taxonomy uses to find the closest example
matcher = client.retrievers.create(
    retriever_name="category-matcher",
    collection_identifiers=["category-examples"],
    input_schema={"query": {"type": "text", "required": True}},
    stages=[
        {
            "stage_name": "search",
            "stage_id": "feature_search",
            "parameters": {
                "searches": [
                    {
                        "feature_uri": "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1",
                        "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-categories",
    "config": {
        "taxonomy_type": "flat",
        "retriever_id": matcher["retriever_id"],
        "input_mappings": [{"input_key": "query", "source_type": "payload", "path": "text"}],
        "source_collection": {"collection_id": examples["collection_id"]},
    },
}).json()

# 3. The articles collection materializes the taxonomy, so every new document
#    is labeled as it is written
bucket = client.buckets.create(
    bucket_name="articles",
    bucket_schema={"properties": {"article": {"type": "text"}}},
)
articles = client.collections.create(
    collection_name="articles",
    source={"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
    feature_extractor={
        "feature_extractor_name": "text_extractor",
        "version": "v1",
    },
    taxonomy_applications=[{"taxonomy_id": taxonomy["taxonomy_id"], "execution_mode": "materialize"}],
)
client.buckets.upload(
    bucket["bucket_id"],
    blobs=[{"property": "article", "type": "text", "data": "s3://your-bucket/articles/cloud-costs.md"}],
)
client.collections.trigger(articles["collection_id"])