Skip to main content

Data Source

Follow the instructions below to create a new data flow that ingests data from a Qdrant source in Nexla.
qdrant_api.png

Qdrant API

Create a New Data Flow​

  1. To create a new data flow, navigate to the Integrate section, and click the New Data Flow button. Then, select the desired flow type from the list, and click the Create button.

  2. Select the Qdrant connector tile from the list of available connectors. Then, select the credential that will be used to connect to your Qdrant account, and click Next; or, create a new Qdrant credential for use in this flow.

  3. In Nexla, Qdrant data sources can be created using pre-built endpoint templates, which expedite source setup for common Qdrant endpoints. Each template is designed specifically for the corresponding Qdrant endpoint, making source configuration easy and efficient.
    • To configure this source using a template, follow the instructions in Configure Using a Template.

    Qdrant sources can also be configured manually, allowing you to ingest data from Qdrant endpoints not included in the pre-built templates or apply further customizations to exactly suit your needs.
    • To configure this source manually, follow the instructions in Configure Manually.

Configure Using a Template​

Nexla provides pre-built templates that can be used to rapidly configure data sources to ingest data from common Qdrant endpoints. Each template is designed specifically for the corresponding Qdrant endpoint, making data source setup easy and efficient.

Endpoint Settings​

  • Select the endpoint from which this source will fetch data from the Endpoint pulldown menu. Available endpoint templates are listed in the expandable boxes below. Click on an endpoint to see more information about it and how to configure your data source for this endpoint.

    Query points(vectors)

    This endpoint template searches a collection using a query vector from your Qdrant index. Use this template when you need to perform similarity search to find vectors that are most similar to a query vector, which is useful for recommendation systems, search functionality, and other AI-powered applications.

    • Enter the collection name in the Collection Name field. This should be the name of the Qdrant collection you want to query. The collection name determines which collection will be searched.
    • Enter the query vector in the Vector field. This should be a vector array in JSON format (e.g., [0.1, 0.2, 0.3, ...]). The query vector should be the same length as the dimension of the collection being queried. The query vector is used to find the most similar vectors in your Qdrant collection.
    • Enter the limit (top K) in the Limit field. This should be the number of most similar vectors you want to retrieve. The limit determines how many results will be returned for each query.
    • Enter the score threshold in the Score Threshold field. This should be the minimum similarity score for results to be returned. Results with scores below this threshold will be excluded.

    This endpoint performs similarity search using a query vector to find the most similar vectors in your Qdrant collection. The query vector should match the dimension of your collection. The endpoint returns the top K most similar vectors based on the similarity metric configured for your collection.

    For detailed information about vector queries, similarity search, API response structures, and available query parameters, see the Qdrant API documentation.

    Retrieves point(Vector) by its ID

    This endpoint template retrieves a point (vector) by its ID from your Qdrant collection. Use this template when you need to retrieve a specific vector and its associated payload data by its unique identifier.

    • Enter the collection name in the Collection Name field. This should be the name of the Qdrant collection containing the point you want to retrieve. The collection name determines which collection will be queried.
    • Enter the point ID in the ID field. This should be the unique identifier of the point (vector) you want to retrieve. The point ID determines which point's information will be retrieved.

    This endpoint retrieves a point (vector) by its ID from your Qdrant collection, including the vector data and associated payload. The endpoint returns a single point's information.

    For detailed information about retrieving points by ID, API response structures, and available point data, see the Qdrant API documentation.

Endpoint Testing​

Once the selected endpoint template has been configured, Nexla can retrieve a sample of the data that will be fetched according to the current settings. This allows users to verify that the source is configured correctly before saving.

  • To test the current endpoint configuration, click the Test button to the right of the endpoint selection menu. Sample data will be fetched & displayed in the Endpoint Test Result panel on the right.

  • If the sample data is not as expected, review the selected endpoint and associated settings, and make any necessary adjustments. Then, click the Test button again, and check the sample data to ensure that the correct information is displayed.

Configure Manually​

Qdrant data sources can be manually configured to ingest data from any valid Qdrant API endpoint. Manual configuration provides maximum flexibility for accessing endpoints not covered by pre-built templates or when you need custom API configurations.

With manual configuration, you can also create more complex Qdrant sources, such as sources that use chained API calls to fetch related data or sources that require custom query parameters or filters.

API Method​

  1. To manually configure this source, select the Advanced tab at the top of the configuration screen.

  2. Select the API method that will be used for calls to the Qdrant API from the Method pulldown menu. Qdrant API typically uses GET method for retrieving points and POST method for querying vectors.

API Endpoint URL​

  1. Enter the URL of the Qdrant API endpoint from which this source will fetch data in the Set API URL field. This should be the complete URL including your cluster host URL (from your credential), the API path (e.g., /collections/{collection_name}/points/{id}, /collections/{collection_name}/points/query), and any required query parameters. Include any required path parameters in the URL.

Ensure the API endpoint URL is correct and accessible with your current credentials. The Qdrant API endpoint URL should include your cluster host URL and the appropriate API path. You can test the endpoint using the Test button after configuring the URL.

Response Data Path​

  1. Enter the JSONPath expression in the Response Data Path field to specify which part of the API response should be treated as the relevant data by Nexla. For Qdrant API responses, use $.result.points[*] to extract all points from the result for query endpoints, or $.result to extract the entire result for single point endpoints, depending on your endpoint.

The JSONPath expression must correctly reference the structure of your Qdrant API response. Qdrant API responses may have different structures depending on the endpoint. Ensure your JSONPath expression matches the structure returned by your specific endpoint. The JSONPath expression determines which data will be extracted and processed by Nexla.

Save the Data Source​

  1. Once all of the relevant steps in the above sections have been completed, click the Next button to proceed with the rest of the data flow configuration, or click Save to save the data source configuration for later use.