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]

# Ensure that Conan is installed

# Add the repository to your Conan remotes:
conan remote add cyborgdb https://dl.cloudsmith.io/<token>/cyborg/cyborgdb/conan
conan remote login cyborgdb -p <token> cyborg

# Install CyborgDB:
conan install cyborgdb_core -r cyborgdb

import cyborgdb_core as cyborgdb
import secrets

# Backing store: disk (local, RocksDB-backed) 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"))

#include "cyborgdb_core/client.hpp"
#include "cyborgdb_core/encrypted_index.hpp"
#include <array>
#include <string>
#include <openssl/rand.h>

// Backing store: disk (local, RocksDB-backed) for simple persistent storage.
// Use StorageConfig::Memory() for ephemeral storage or ::S3("bucket") for cloud persistence.
// Pass "" for api_key to run in free-tier mode.
cyborg::Client client("", cyborg::StorageConfig::Disk("/tmp/cyborgdb"), 0, cyborg::kNone);

# ... 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

// Generate a 32-byte random encryption key
std::array<uint8_t, 32> index_key;
if (RAND_bytes(index_key.data(), index_key.size()) != 1) {
    throw std::runtime_error("Failed to generate secure random key");
}

// Create an encrypted index
auto index = client.CreateIndex("my_index", 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

// Add items to the encrypted index
std::vector<std::string> ids = {"item_1", "item_2", "item_3"};
cyborg::Array2D<float> vectors{{0.1, 0.2, 0.3, 0.4}, {0.5, 0.6, 0.7, 0.8}, {0.9, 0.10, 0.11, 0.12}};
std::vector<std::vector<uint8_t>> contents = {
    std::vector<uint8_t>{'H', 'e', 'l', 'l', 'o', '!'},
    std::vector<uint8_t>{'B', 'o', 'n', 'j', 'o', 'u', 'r', '!'},
    std::vector<uint8_t>{'H', 'o', 'l', 'a', '!'}
};

index->Upsert(ids, vectors, contents, /*metadata=*/{}, index_key);

# ... Continuing from the previous step

# Query the encrypted index
query_vectors = [0.1, 0.2, 0.3, 0.4]
results = index.query(query_vectors=query_vectors, include=["distance"], index_key=index_key)

# Print the results
for result in results:
    print(f"ID: {result['id']}, Distance: {result['distance']}")

// ... Continuing from the previous step
cyborg::Array2D<float> query_vectors{{0.1, 0.2, 0.3, 0.4}};

// Query using the standard params
cyborg::QueryResults results = index->Query(query_vectors, cyborg::QueryParams{}, index_key);

// Print the results
auto view = results[0];
for (uint32_t i = 0; i < view.num_results; ++i) {
    std::cout << "ID: " << view.ids[i] << ", Distance: " << view.distances[i] << std::endl;
}

# ... Continuing from the previous step

# Retrieve items from the encrypted index
ids = ["item_1", "item_2", "item_3"]
items = index.get(ids, index_key=index_key)

# Print the items (contents are returned as bytes)
for item in items:
    print(f"ID: {item['id']}, Vector: {item['vector']}, Contents: {item['contents']}")

// ... Continuing from the previous step

// Retrieve items from the encrypted index
std::vector<std::string> ids = {"item_1", "item_2", "item_3"};
std::vector<cyborg::ItemFields> include = {cyborg::ItemFields::kContents};
std::vector<cyborg::Item> items = index->Get(ids, include, index_key);

// Print the items
for (const auto& item : items) {
    std::cout << "ID: " << item.id << ", Contents: " << std::string(item.contents.begin(), item.contents.end()) << std::endl;
}