Duffy SDK

Python SDK for Apache AGE + pgvector on PostgreSQL.

Graph queries, vector search, and hybrid graph+vector operations — all in one PostgreSQL instance.

Installation

pip install duffy

# With pandas support
pip install duffy[pandas]

# With all optional dependencies
pip install duffy[all]

Quick Example

import duffy

db = duffy.connect("postgresql://localhost:5433/mydb", graph="my_graph")

# Cypher queries → DataFrames
df = db.cypher("MATCH (n:Person) RETURN n.name, n.age").to_df()

# Vector search
results = db.vector_search("documents", "embedding", query_vec, k=10).to_df()

# Hybrid: graph traversal + vector similarity
results = db.hybrid_search(
    cypher="MATCH (p:Paper)-[:CITES]->(cited) RETURN cited",
    vector_table="papers",
    vector_column="abstract_embedding",
    query_vector=query_vec,
    k=10,
).to_df()

What's Inside

• Quick Start — Get up and running in 5 minutes
• API Reference — Full method signatures and parameters
• Integrations — LangChain, LlamaIndex, NetworkX, PyTorch Geometric

Requirements

• Python 3.10+
• PostgreSQL with Apache AGE and pgvector extensions

License

Apache 2.0