Weaviate API

Weaviate is an open-source vector database that enables organizations to store, search, and retrieve data using machine learning models, supporting semantic search, recommendation systems, and AI-powered applications.

Power AI-ready data operations with Weaviate API and Nexla. Our Weaviate API connector makes it simple to ingest, transform, chunk, and deliver structured or unstructured data to Weaviate API — all without coding. Nexla automatically organizes raw text and documents into reusable data products that you can easily prepare for vector search and retrieval-augmented generation (RAG) using our built-in transforms like agentic chunking and incremental loading. With real-time validation, schema checks, and comprehensive monitoring, Nexla keeps your Weaviate API workflows fast, secure, and fully governed for production AI use cases.

Features

Type: Vector Database

SourceDestination

• AI-Ready Data Preparation: Automatically chunk, vectorize, and index data from any source into your vector database for fast, contextually relevant search
• Advanced RAG Integration: Query vector databases to power retrieval-augmented generation workflows with query rewriting, re-ranking, and multi-model orchestration
• Enterprise RAG Framework: Build production-ready RAG applications with built-in access controls, evaluation grading, and NVIDIA NIM hardware acceleration

Prerequisites

Before creating a Weaviate credential, you need to obtain your Weaviate Instance URL and API Key from your Weaviate account. Weaviate uses API key authentication for all API requests, with the key sent as a Bearer token in the Authorization header.

To obtain your Weaviate credentials, follow these steps:

1. Sign in to your Weaviate account or access your Weaviate instance using your administrator credentials.

2. Navigate to your Weaviate instance settings or API configuration in your Weaviate dashboard or instance management interface.

3. To connect to your Weaviate instance, you need the instance and connection details and a client to connect with.

4. Your Weaviate Instance URL is the base URL of your Weaviate instance (e.g., https://your-instance.weaviate.network or http://localhost:8080 for local instances).

5. If you don't have an API key yet, navigate to API Keys or Authentication settings in your Weaviate instance configuration.

6. Click Generate API Key or Create API Key to create a new API key.

7. Configure your API key settings:

   • Enter a name for the API key (e.g., "Nexla Integration")
   • Review the API key permissions or scopes (if applicable)
   • Click Create or Generate to create the API key

8. After the API key is created, copy the API Key value immediately, as it may not be accessible again after you navigate away from the page.

9. Store both credentials securely, as you will need them to configure your Nexla credential. The API Key is sensitive information and should be kept confidential.

The Weaviate Instance URL is used to construct the API endpoint URLs. The API Key is sent as a Bearer token in the Authorization header for all API requests to the Weaviate API. The key authenticates your requests and grants access to Weaviate resources based on your account permissions. If your API key is compromised, you should immediately revoke it in your Weaviate instance settings and generate a new one. For detailed information about obtaining API keys, API authentication, and available endpoints, refer to the Weaviate API documentation.

Authenticate

Credentials required

Field	Required	Secret	Description
The Weaviate Instance URL	Yes	No	To connect to your Weaviate instance, you need the instance and connection details and a client to connect with.
API Key Value	Yes	Yes	Weaviate API Key, this can be obtained by signing up at Weaviate account.
API Version	No	No	Version of The Weaviate API
Open AI API Key	No	Yes	This is required for using OpenAI models and can be obtained by signing up at OpenAI
Cohere Api Key	No	Yes	Cohere related actions and models will require their Api Key.
Hugging Face Api Key	No	Yes	Hugging Face related services Api Key.

Create a credential in Nexla

1. After selecting the data source/destination type, click the Add Credential tile to open the Add New Credential overlay.

New Credential Overlay – Weaviate

2. Enter a name for the credential in the Credential Name field and a short, meaningful description in the Credential Description field.

   Weaviate uses API key authentication for all API requests. The API Key is sent as a Bearer token in the Authorization header.

3. Enter your The Weaviate Instance URL in the The Weaviate Instance URL field. This is the base URL of your Weaviate instance (e.g., https://your-instance.weaviate.network or http://localhost:8080 for local instances). To connect to your Weaviate instance, you need the instance and connection details and a client to connect with. The Instance URL is used to construct the API endpoint URLs.

4. Enter your API Key Value in the API Key Value field. This is the Weaviate API Key. This can be obtained by signing up at Weaviate account. The API key is sent as a Bearer token in the Authorization header for all API requests to the Weaviate API. The API Key is sensitive information and must be kept confidential.

5. Enter your API Version in the API Version field. This should be the version of the Weaviate API you want to use (e.g., v1). The default value is v1. The API Version determines which version of the API will be used for requests.

Optional API Keys

Optional

6. If you plan to use OpenAI models with Weaviate, optionally enter your Open AI API Key in the Open AI API Key field. This is required for using OpenAI models and can be obtained by signing up at OpenAI. The OpenAI API Key is sent in the X-OpenAI-Api-key header when using OpenAI models.

7. If you plan to use Cohere models with Weaviate, optionally enter your Cohere Api Key in the Cohere Api Key field. Cohere related actions and models will require their API Key. The Cohere API Key is sent in the X-Cohere-Api-key header when using Cohere models.

8. If you plan to use Hugging Face models with Weaviate, optionally enter your Hugging Face Api Key in the Hugging Face Api Key field. Hugging Face related services require their API Key. The Hugging Face API Key is sent in the X-HuggingFace-Api-key header when using Hugging Face models.

   Your Weaviate credentials (Instance URL, API Key) can be found in your Weaviate instance settings or API configuration. The Weaviate API Key can be obtained by signing up at Weaviate account. The API key is sent as a Bearer token in the Authorization header for all API requests to the Weaviate API.

   Optional API keys (OpenAI, Cohere, Hugging Face) are only needed if you plan to use those specific models or services with Weaviate. These keys are sent in their respective headers when using those services.

   If your API key is compromised, you should immediately revoke it in your Weaviate instance settings and generate a new one. The API key provides access to your Weaviate instance data and should be treated as sensitive information. Keep your API key secure and do not share it publicly.

   For detailed information about obtaining API keys, API authentication, and available endpoints, see the Weaviate API documentation and Weaviate overview.

9. Click the Save button at the bottom of the overlay. The newly added credential will now appear in a tile on the Authenticate screen during data source/destination creation and can be selected for use with a new data source or destination.

Use as a destination

Click the + icon on the Nexset that will be sent to the Weaviate destination, and select the Send to Destination option from the menu. Select the Weaviate connector from the list of available destination connectors, then select the credential that will be used to connect to the Weaviate instance, and click Next; or, create a new Weaviate credential for use in this flow.

Endpoint templates

Nexla provides pre-built templates that can be used to rapidly configure destinations to send data to common Weaviate endpoints. Select the endpoint to which data will be sent from the Endpoint pulldown menu. Then, click on the template in the list below to expand it, and follow the instructions to configure additional endpoint settings.

Add Objects

This endpoint template performs batch imports to add multiple data objects and cross-references to your Weaviate instance. Use this template when you need to efficiently import large numbers of objects into Weaviate for vector database operations, AI/ML applications, or semantic search purposes.

• This endpoint sends data as JSON in the request body to add objects to your Weaviate instance. Each record from your Nexset will be included in a batch import operation. The request body should contain the object data in the format required by the Weaviate API, including all required properties for object creation. The endpoint uses batch mode to efficiently process multiple objects in a single API call.

This endpoint performs batch imports to add multiple data objects and cross-references to your Weaviate instance. Batch imports are an efficient way to add multiple data objects and cross-references. The endpoint uses batch mode to process multiple objects efficiently, with a maximum of 20 records per batch. The endpoint automatically transforms the data structure to match Weaviate's batch import format, mapping the objects field to your messages.

The object structure must match the Weaviate API's expected format. Ensure your object data includes all required fields. The endpoint uses QUORUM consistency level for reliable data storage. Optional API keys (OpenAI, Cohere, Hugging Face) configured in your credentials will be automatically included in the request headers if they are set. For detailed information about batch imports, object structures, and available properties, see the Weaviate API documentation.

Manual configuration

Weaviate destinations can also be manually configured to send data to any valid Weaviate API endpoint, including endpoints not covered by the pre-built templates. Select the Advanced tab at the top of the configuration screen, and follow the instructions in Connect to Any API to configure the API method, data format, endpoint URL, request headers, attribute exclusions, record batching, and response webhooks. Nexla can also be configured to automatically send the response received from the Weaviate API after each call to a new Nexla webhook data source.

Weaviate APIs typically expect JSON format for most operations; POST is the most common method, used for creating new objects or batch imports. For batch imports, the endpoint URL typically follows the pattern {instance_url}/{version}/batch/objects?consistency_level=QUORUM; for update/upsert operations, include the ID of the object to be updated at the end of the URL. Optional API keys (X-OpenAI-Api-Key, X-Cohere-Api-key, X-HuggingFace-Api-key) configured in your credential are automatically included in request headers if they are set. Record batching and response webhooks are particularly useful for Weaviate destinations to efficiently process large numbers of objects and to track batch import confirmations and error responses.

Save & activate

Once all endpoint settings have been configured, click the Done button in the upper right corner of the screen to save and create the destination. To send the data to the configured Weaviate endpoint, open the destination resource menu, and select Activate.

The Nexset data will not be sent to the Weaviate endpoint until the destination is activated. Destinations can be activated immediately or at a later time, providing full control over data movement.