langchain-zerodb

ZeroDB vector store integration for LangChain - the AI-native vector database with free embeddings and sub-millisecond semantic search.

Why ZeroDB?

• Free embeddings - BAAI/bge-small-en-v1.5 (384-dim) powered by TEI, no OpenAI costs
• Sub-millisecond search - pgvector with HNSW indexes
• Zero infrastructure - fully managed, no servers to run
• Instant provisioning - POST /api/v1/instant-db gets you a database in one request
• Built for agents - MCP server, memory API, event streams

Installation

pip install langchain-zerodb

Quick Start

from langchain_zerodb import ZeroDBVectorStore

# Initialize (get your API key at ainative.studio)
vectorstore = ZeroDBVectorStore(
    api_key="your-api-key",
    project_id="your-project-id",
)

# Add documents
ids = vectorstore.add_texts(
    ["ZeroDB is fast", "Semantic search is powerful"],
    metadatas=[{"source": "docs"}, {"source": "blog"}],
)

# Similarity search
results = vectorstore.similarity_search("fast database", k=5)
for doc in results:
    print(doc.page_content, doc.metadata)

# Search with scores
scored = vectorstore.similarity_search_with_score("fast database", k=5)
for doc, score in scored:
    print(f"{score:.3f}: {doc.page_content}")

Use with LangChain Chains

from langchain_zerodb import ZeroDBVectorStore
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough

vectorstore = ZeroDBVectorStore(
    api_key="your-api-key",
    project_id="your-project-id",
)
retriever = vectorstore.as_retriever(search_kwargs={"k": 5})

# RAG chain
template = "Answer based on context:\n{context}\n\nQuestion: {question}"
prompt = ChatPromptTemplate.from_template(template)

chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | prompt
)

Get a Free API Key

1. Sign up at ainative.studio
2. Create a ZeroDB project
3. Copy your API key

Or get an instant database with no signup:

curl -X POST https://api.ainative.studio/api/v1/public/instant-db

Links

• ZeroDB Product Page
• API Documentation
• GitHub
• Discord
• LlamaIndex Integration

License

MIT - Built by AINative Studio