Similar
BYO Embeddings Vector Search
Bring pre-computed embeddings from any provider (OpenAI, Cohere, Together, etc.) and upsert them directly into MVS for instant vector search. No feature extractors, no pipelines -- just embeddings in, results out.
text
image
Single Tier
34.2K runs
Run in Builder"Find DevOps tutorials about container orchestration"
Why This Matters
Skip the managed pipeline entirely when you already have embeddings. MVS gives you production-grade vector search with filtering, hybrid queries, and multi-tenancy without lock-in to any embedding provider.
from openai import OpenAIfrom mixpeek import Mixpeekopenai = OpenAI(api_key="your-openai-key")mvs = Mixpeek(api_key="your-mvs-key")NAMESPACE = "my-namespace"# Generate embeddings with any providerdef embed(text: str) -> list[float]:resp = openai.embeddings.create(model="text-embedding-3-small", input=text)return resp.data[0].embedding# Upsert documents with pre-computed embeddingsdocuments = [{"text": "How to deploy a Kubernetes cluster", "category": "devops"},{"text": "Introduction to neural network architectures", "category": "ml"},{"text": "Building REST APIs with FastAPI", "category": "backend"},]for doc in documents:mvs.namespaces.documents.upsert(namespace=NAMESPACE,documents=[{"dense_embedding": embed(doc["text"]),"metadata": {"text": doc["text"], "category": doc["category"]}}])# Search with a query embeddingquery = "how to set up container orchestration"results = mvs.namespaces.documents.search(namespace=NAMESPACE,query={"dense_embedding": embed(query)},top_k=5)for doc in results:print(f"{doc['score']:.3f} | {doc['metadata']['text']}")
Feature Extractors
Retriever Stages
limit
Truncate results to a maximum count with optional offset for pagination
reduce