Component Libraries • Project Templates
Docs • Install • Tutorials • Developer Guides • Contribute • Blog • Discord

Xircuits Component Library to interface with Vecto AI! Seamlessly manage vector embeddings and perform advanced vector operations.

---

Xircuits Component Library for Vecto

Integrate Vecto AI into Xircuits workflows for seamless vector embedding management, advanced search, data ingestion, and analogy computation for both text and image data.

Table of Contents

• Preview
• Prerequisites
• Main Xircuits Components
• Try the Examples
• Installation

Preview

SimpleAnalogy Example:

SimpleAnalogy Result:

Prerequisites

Before you begin, you will need the following:

1. Python3.9+.
2. Xircuits.
3. Vecto token and space_id

Main Xircuits Components

VectoClient Component:

Initializes a Vecto client for managing vector operations and sets it in the context for reuse across workflows.

VectoLookup Component:

Performs a lookup operation on Vecto using a query (text or image) and returns the most similar vectors based on the specified modality.

VectoIngest Component:

Ingests data (text or image) into Vecto's vector space for efficient vector representation and similarity search.

VectoComputeAnalogy Component:

Calculates analogies between vectors using Vecto for both text and image modalities.

VectoUpdateVectorEmbeddings Component:

Updates existing vector embeddings in Vecto with new data.

VectoUpdateVectorAttribute Component:

Modifies attributes of existing vectors in Vecto.

VectoDeleteVectorEmbeddings Component:

Deletes specified vector embeddings from Vecto's vector space.

VectoIngestImage Component:

Ingests one or more images into Vecto's vector space, with attributes for metadata.

VectoIngestText Component:

Ingests one or more text entries into Vecto's vector space, with attributes for metadata.

Try The Examples

We have provided an example workflow to help you get started with the Vecto component library. Give it a try and see how you can create custom Vecto components for your applications.

SimpleLookup Example

Check out the SimpleLookup.xircuits workflow. This example demonstrates how to perform a search in Vecto by querying vectors for similarity based on text or image data.

---

SimpleIngestLookup Example

Check out the SimpleIngestLookup.xircuits workflow. This example shows how to ingest data into Vecto's vector space and perform a lookup to retrieve similar vectors.

---

SimpleAnalogy Example

Check out the SimpleAnalogy.xircuits workflow. This example highlights how to compute analogies between vectors in Vecto, leveraging the relationships between vector embeddings.

Installation

To use this component library, ensure that you have an existing Xircuits setup. You can then install the Vecto library using the component library interface, or through the CLI using:

xircuits install vecto

You can also do it manually by cloning and installing it:

# base Xircuits directory
git clone https://github.com/XpressAI/xai-vecto xai_components/xai_vecto
pip install -r xai_components/xai_vecto/requirements.txt 

Authentication and Setup for Vecto

To access Vecto services, follow these steps:

1. Create an Account and Log In:

   • Visit app.vecto.ai and register for an account.
   • After registering, log in to your account.

2. Create a New Vector Space:

   • Navigate to the dashboard and create a new vector space. Note the space ID assigned to it for later use.

3. Generate a Token:

   • Click on your account name in the top-right corner of the dashboard.
   • Select Tokens from the dropdown menu and create a new token.
   • Important: The token will only be displayed once. Save it securely in a safe location.

4. Start Using Vecto:

   • With your token and space ID, you are ready to use Vecto in your Xircuits workflows.