Hybrid BM25 + Dense Vector Search

from openai import OpenAI
from mixpeek import Mixpeek

openai = OpenAI(api_key="your-openai-key")
mvs = Mixpeek(api_key="your-mvs-key")

NAMESPACE = "my-namespace"

def embed(text: str) -> list[float]:
    resp = openai.embeddings.create(model="text-embedding-3-small", input=text)
    return resp.data[0].embedding

# Upsert documents with BOTH dense embeddings and text content
documents = [
    {"text": "FastAPI uses Pydantic v2 for data validation and serialization", "topic": "python"},
    {"text": "Express.js middleware handles request/response transformations", "topic": "node"},
    {"text": "FastAPI supports async/await natively with Starlette ASGI", "topic": "python"},
    {"text": "Django ORM provides database abstraction with QuerySet API", "topic": "python"},
]

for doc in documents:
    mvs.namespaces.documents.upsert(
        namespace=NAMESPACE,
        documents=[{
            "dense_embedding": embed(doc["text"]),
            "content": doc["text"],  # BM25 indexes this field
            "metadata": {"topic": doc["topic"]}
        }]
    )

# Hybrid search: BM25 keyword matching + dense vector similarity
query_text = "FastAPI Pydantic validation"
results = mvs.namespaces.documents.search(
    namespace=NAMESPACE,
    query={
        "dense_embedding": embed(query_text),
        "text": query_text  # BM25 component
    },
    hybrid={
        "enabled": True,
        "alpha": 0.6  # 0.0 = pure BM25, 1.0 = pure dense, 0.6 = balanced
    },
    top_k=5
)

for doc in results:
    print(f"{doc['score']:.3f} | {doc['metadata'].get('topic', '')} | {doc['content'][:80]}")