Legal Document RAG Pipeline

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY", namespace="legal-docs")

# 1. A bucket for contracts, and a collection that splits pages into layout blocks
bucket = client.buckets.create(
    bucket_name="contracts",
    bucket_schema={"properties": {"contract": {"type": "pdf"}}},
)
collection = client.collections.create(
    collection_name="contracts",
    source={"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
    feature_extractor={
        "feature_extractor_name": "document_graph_extractor",
        "version": "v1",
    },
)

# 2. Upload and process
client.buckets.upload(
    bucket["bucket_id"],
    blobs=[{"property": "contract", "type": "pdf", "data": "s3://your-bucket/contracts/msa-acme.pdf"}],
)
client.collections.trigger(collection["collection_id"])

# 3. Dense and BM25 search fused with RRF (BM25 reads the namespace text payload
#    indexes), then a cross-encoder for precision
retriever = client.retrievers.create(
    retriever_name="legal-search",
    collection_identifiers=["contracts"],
    input_schema={"query": {"type": "text", "required": True}},
    stages=[
        {
            "stage_name": "search",
            "stage_id": "feature_search",
            "parameters": {
                "searches": [
                    {
                        "feature_uri": "mixpeek://document_graph_extractor@v1/intfloat__multilingual_e5_large_instruct",
                        "query": {"input_mode": "text", "value": "{{INPUT.query}}"},
                        "top_k": 50,
                    },
                    {
                        "feature_uri": "mixpeek://document_graph_extractor@v1/intfloat__multilingual_e5_large_instruct",
                        "query": {"input_mode": "text", "value": "{{INPUT.query}}"},
                        "top_k": 50,
                        "lexical": True,
                    },
                ],
                "fusion": "rrf",
                "final_top_k": 50,
            },
        },
        {
            "stage_name": "rerank",
            "stage_id": "rerank",
            "parameters": {
                "inference_name": "BAAI__bge_reranker_v2_m3",
                "query": "{{INPUT.query}}",
                "document_field": "text_raw",
                "top_k": 10,
            },
        },
    ],
)

results = client.retrievers.execute(retriever["retriever_id"], inputs={"query": "Section 14.2 indemnification obligations"})
for doc in results["documents"]:
    print(doc["page_number"], doc["text_raw"][:120], doc["score"])