CyborgDB Embedded Quickstart

# Install CyborgDB:
pip install cyborgdb-core

# For automatic embedding generation, install with:
pip install cyborgdb-core[embeddings]

# For LangChain integration, install with:
pip install cyborgdb-core[langchain]

# Or with all extras:
pip install cyborgdb-core[all]

import cyborgdb_core as cyborgdb
import secrets

# Backing store: local disk, for simple persistent storage.
# Use .memory() for ephemeral storage or .s3("bucket") for cloud persistence.
client = cyborgdb.Client(storage_config=cyborgdb.StorageConfig.disk("/tmp/cyborgdb"))

# ... Continuing from the previous step

# Generate an encryption key for the index
index_key = secrets.token_bytes(32)

# Create an encrypted index
index = client.create_index(
    index_name="my_index", 
    index_key=index_key
)

# ... Continuing from the previous step

# Add items to the encrypted index
items = [
    {"id": "item_1", "vector": [0.1, 0.2, 0.3, 0.4], "contents": "Hello!"},
    {"id": "item_2", "vector": [0.5, 0.6, 0.7, 0.8], "contents": "Bonjour!"},
    {"id": "item_3", "vector": [0.9, 0.10, 0.11, 0.12], "contents": "Hola!"}
]

# index_key must be supplied on every data operation
index.upsert(items, index_key=index_key)

# ... Continuing from the previous step

# Query the encrypted index — include distance and metadata on results.
results = index.query(
    query_vectors=[0.1, 0.2, 0.3, 0.4],
    top_k=2,
    include=["distance", "metadata"],
    index_key=index_key,
)

# Retrieve contents for the top matches (contents come back as bytes).
top_items = index.get([r["id"] for r in results], index_key=index_key)
by_id = {item["id"]: item for item in top_items}
for r in results:
    contents = by_id[r["id"]]["contents"].decode()
    print(f"ID: {r['id']}  Distance: {r['distance']:.4f}  Contents: {contents}")