Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.cyborg.co/llms.txt

Use this file to discover all available pages before exploring further.

Retrieves vectors from the encrypted index by their IDs, with options to specify which fields to include in the results. 
async get(
    ids: string[],
    include: string[] = ["vector", "contents", "metadata"]
): Promise<Array<GetResultItem>>

​
Parameters

ParameterTypeDefaultDescription
idsstring[]-Array of vector IDs to retrieve from the index
includestring[]["vector", "contents", "metadata"](Optional) Fields to include in the response. Valid options: "vector", "contents", "metadata"

​
Returns

Promise<Array<GetResultItem>>: A Promise that resolves to an array of retrieved vector items, each containing the requested fields based on the include parameter.

​
Exceptions

  • Throws if the API request fails due to network connectivity issues.
  • Throws if authentication fails (invalid API key).
  • Throws if the encryption key is invalid for the specified index.
  • Throws if there are internal server errors preventing the retrieval.
  • Throws if the ids parameter is null, undefined, or empty.
  • Throws if the include parameter contains invalid field names.

​
Example Usage

import { Client, IndexIVFModel } from 'cyborgdb';

const client = new Client('http://localhost:8000', 'your-api-key');

// Create and populate index
const indexKey = crypto.getRandomValues(new Uint8Array(32));
const config: IndexIVFModel = {
    dimension: 768,
    nLists: 1024,
    metric: 'cosine'
};

const index = await client.createIndex('my-vectors', indexKey, config);

// Add some vectors first
await index.upsert([
    { 
        id: 'doc1', 
        vector: [0.1, 0.2, 0.3, /* ... 768 dimensions */], 
        contents: 'This is the first document content',
        metadata: { title: 'Document 1', category: 'research', date: '2024-01-15' }
    },
    { 
        id: 'doc2', 
        vector: [0.4, 0.5, 0.6, /* ... 768 dimensions */], 
        contents: 'This is the second document content',
        metadata: { title: 'Document 2', category: 'tutorial', date: '2024-01-16' }
    }
]);

// Retrieve vectors with all fields
try {
    const vectors = await index.get(['doc1', 'doc2']);
    
    vectors.forEach(item => {
        console.log(`ID: ${item.id}`);
        console.log(`Vector dimensions: ${item.vector?.length}`);
        console.log(`Contents: ${item.contents}`);
        console.log(`Metadata: ${JSON.stringify(item.metadata)}`);
        console.log('---');
    });
    
} catch (error) {
    console.error('Failed to retrieve vectors:', error.message);
}

​
Response Format

The method returns an array of objects with the following structure: 
// Example response with all fields
[
    {
        "id": "doc1",
        "vector": [0.1, 0.2, 0.3, /* ... */],
        "contents": "Document content as string or Buffer",
        "metadata": {
            "title": "Document 1",
            "category": "research",
            "date": "2024-01-15"
        }
    },
    {
        "id": "doc2",
        "vector": [0.4, 0.5, 0.6, /* ... */],
        "contents": "Another document content",
        "metadata": {
            "title": "Document 2", 
            "category": "tutorial",
            "date": "2024-01-16"
        }
    }
]

​
Response Item Fields

FieldTypeDescription
idstringUnique identifier of the vector (always included)
vectornumber[]The vector data (included if "vector" in include array)
contentsBuffer | stringThe content data, automatically decoded from base64 if needed (included if "contents" in include array)
metadataanyAssociated metadata object (included if "metadata" in include array)