Skip to main content

Weaviate Integration with Orkes Conductor

To use system AI tasks in Orkes Conductor, you must integrate your Conductor cluster with the necessary vector database providers. This guide explains how to integrate Weaviate with Orkes Conductor. Here’s an overview:

  1. Get the required credentials from Weaviate.
  2. Configure a new Weaviate integration in Orkes Conductor.
  3. Add classes to the integration.
  4. Set access limits to the vector database to govern which applications or groups can use them.

Step 1: Get the Weaviate credentials​

To integrate Weaviate with Orkes Conductor, retrieve the API key and endpoint from the Weaviate Console.

Pre-requisites:

For Weaviate Cloud:

  1. Sign up for Weaviate Cloud.
  2. Create a cluster.
  3. Create a collection (class) within the cluster.

To get the API key and endpoint:

  1. Sign in to the Weaviate Console.
  2. Select your cluster and go to Cluster details > Information.
  3. Copy the REST Endpoint.

Get Weaviate Endpoint

  1. Go to Cluster details > API Keys.
  2. Copy the Admin key.

Get Weaviate API Key

note

If you are using Weaviate locally, set up a local instance and retrieve the API key and endpoint.

Step 2: Add an integration for Weaviate​

After obtaining the credentials, add a Weaviate integration to your Conductor cluster.

To create a Weaviate integration:

  1. Go to Integrations from the left navigation menu on your Conductor cluster.
  2. Select + New integration.
  3. In the Vector Databases section, choose Weaviate.
  4. Select + Add and enter the following parameters:
ParametersDescription
Integration nameA name for the integration.
API KeyThe API key from the Weaviate cluster.
EndpointThe REST Endpoint from the Weaviate cluster.
DescriptionA description of the integration.

Weaviate Integration with Orkes Conductor

  1. (Optional) Toggle the Active button off if you don’t want to activate the integration instantly.
  2. Select Save.

Step 3: Add Weaviate classes​

Once you’ve integrated Weaviate, the next step is to configure specific classes.

To add a class to the Weaviate integration:

  1. Go to the Integrations page and select the + button next to the integration created.

Create Classes for Weaviate Integration

  1. Select + New Class.
  2. Enter the Class name and a Description.

Create New Class for Weaviate Integration Model

  1. (Optional) Toggle the Active button off if you don’t want to activate the class instantly.
  2. Select Save.

This saves the classes for future use in AI tasks within Orkes Conductor.

Step 4: Set access limits to integration​

Once the integration is configured, set access controls to manage which applications or groups can use the Pinecone databases.

To provide access to an application or group:

  1. Go to Access Control > Applications or Groups from the left navigation menu on your Conductor cluster.
  2. Create a new group/application or select an existing one.
  3. In the Permissions section, select + Add Permission.
  4. In the Integration tab, select the required vector database providers and toggle the necessary permissions.
  5. Select Add Permissions.

Add Permissions for Weaviate Database Integration

The group or application can now access the vector database according to the configured permissions. With the integration in place, you can now create workflows using AI/LLM tasks.

info

To store data in a vector database, an embedding is to be generated by an AI model. You must also integrate an AI model provider of your choice to use this integration in workflows.

More resources​