Qdrant API

Qdrant is a vector database designed for high-performance similarity search and machine learning applications, enabling businesses to build AI-powered search, recommendation systems, and semantic applications with fast vector operations.

Power AI-ready data operations with Qdrant API and Nexla. Our Qdrant API connector makes it simple to ingest, transform, chunk, and deliver structured or unstructured data to Qdrant 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 Qdrant 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 Qdrant credential, you need to obtain your API key and identify your cluster host URL from your Qdrant account. Qdrant uses API key authentication for all API requests, with the API key sent in the Api-Key header.

To obtain your Qdrant API credentials, follow these steps:

1. Sign in to your Qdrant account, or create a new account at Qdrant Cloud.

2. Navigate to your Qdrant cloud dashboard or cluster settings in the Qdrant interface.

3. Look for the API Keys or API section in your account settings or cluster dashboard.

4. If you don't have an API key yet, click Create API Key or Generate API Key to create a new API key.

5. Configure your API key settings:

   • Enter a name for the API key (e.g., "Nexla Integration")
   • Review and select the permissions or scopes for the key (if applicable)

6. Click Create or Generate to create the API key.

7. Copy the API key immediately after it's generated, as it may not be accessible again after you navigate away from the page.

8. Navigate to your cluster page in the Qdrant cloud dashboard to find your cluster host URL. The cluster host URL is typically in the format https://{cluster-id}.{region}.qdrant.io or similar. You can find this in your cluster settings or on the cluster details page.

9. Store both the API key and cluster host URL securely, as you will need them to configure your Nexla credential. The API key is sensitive information and should be kept confidential.

The API key is sent in the Api-Key header for all API requests to the Qdrant API. The cluster host URL determines which Qdrant cluster your API requests will be sent to. The API key authenticates your requests and grants access to your Qdrant cluster based on your account permissions. If your API key is compromised, you should immediately revoke it in your Qdrant account settings and generate a new one. For detailed information about obtaining API keys, cluster host URLs, API authentication, and available endpoints, refer to the Qdrant API documentation.

Authenticate

Credentials required

Field	Required	Secret	Description
Host URL	Yes	No	Find your Cluster URL in your cloud dashboard, at https://cloud.qdrant.io
API Key Value	Yes	Yes

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 – Qdrant

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

3. Qdrant uses API key authentication for all API requests. Enter your Qdrant cluster host URL in the Host URL field. This should be the host URL for your Qdrant cluster, typically in the format https://{cluster-id}.{region}.qdrant.io or similar. The cluster host URL determines which Qdrant cluster your API requests will be sent to. You can find your Cluster URL in your cloud dashboard at https://cloud.qdrant.io.

4. Enter your Qdrant API key in the API Key Value field. This is the API key you obtained from your Qdrant account settings (API Keys section) in Prerequisites. The API key is sent in the Api-Key header for all API requests to the Qdrant API and must be kept confidential.

   Your Qdrant API key can be found in your Qdrant account settings under the API Keys section. The API key is sent in the Api-Key header for all API requests to the Qdrant API. The cluster host URL should match your Qdrant cluster host URL, which can be found in your cloud dashboard at https://cloud.qdrant.io.

   If your API key is compromised, you should immediately revoke it in your Qdrant account settings and generate a new one. The API key provides access to your Qdrant cluster 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, cluster host URLs, API authentication, and available endpoints, see the Qdrant API documentation.

5. 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.

Use as a data source

To create a new data flow, navigate to the Integrate section, and click the New Data Flow button. 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.

Endpoint templates

Nexla provides pre-built templates that can be used to rapidly configure data sources to ingest data from common Qdrant endpoints. 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.

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.

Once the selected endpoint template has been configured, click the Test button to the right of the endpoint selection menu to retrieve a sample of the data that will be fetched. Sample data will be displayed in the Endpoint Test Result panel on the right, allowing you to verify that the source is configured correctly before saving.

Manual configuration

Qdrant data sources can also be manually configured to ingest data from any valid Qdrant API endpoint, including endpoints not covered by the pre-built templates, chained API calls, or custom request parameters. 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, endpoint URL, date/time and lookup macros, path to data, metadata, and request headers.

Qdrant API typically uses the GET method for retrieving points and the POST method for querying vectors. The endpoint URL should include your cluster host URL (from your credential) and the API path, e.g. /collections/{collection_name}/points/{id} or /collections/{collection_name}/points/query. For the Response Data Path, 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.

Once all of the relevant steps 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.

Use as a destination

Click the + icon on the Nexset that will be sent to the Qdrant destination, and select the Send to Destination option from the menu. Select the Qdrant connector from the list of available destination 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.

Endpoint templates

Nexla provides pre-built templates that can be used to rapidly configure destinations to send data to common Qdrant 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.

Upsert Points (Vectors)

This endpoint template performs the insert + update action on specified points in your Qdrant collection using records from a Nexset. Any point with an existing ID will be overwritten. Use this template when you need to insert or update vectors in your Qdrant collection for similarity search, recommendation systems, or other AI-powered applications.

• Enter the collection name in the Collection Name field. This should be the name of the Qdrant collection where you want to upsert points (vectors). The collection name determines which collection will receive the points.

This endpoint sends data as JSON in the request body to upsert points (vectors) into your Qdrant collection. The endpoint uses batch mode to efficiently send multiple points in a single request. Each record from your Nexset will be included in the batch, and points will be upserted in batches of up to 20 points per request.

The point structure must match the Qdrant API's expected format. Each point should include an ID, vector values, and optional payload. For detailed information about point upsert, request body formats, batch processing, and available point properties, see the Qdrant API documentation.

Used to upserting batches of points(vectors)

This endpoint template batch updates points, including their respective vectors and payloads, in your Qdrant collection using records from a Nexset. Use this template when you need to efficiently upsert multiple points in a single batch operation.

• Enter the collection name in the Collection Name field. This should be the name of the Qdrant collection where you want to batch update points (vectors). The collection name determines which collection will receive the batch updates.

This endpoint sends data as JSON in the request body to batch update points (vectors) in your Qdrant collection. The endpoint uses batch mode to efficiently send multiple points in a single request. Each record from your Nexset will be included in the batch operation, and points will be batch updated in batches of up to 20 points per request.

The batch update structure must match the Qdrant API's expected format. Each batch operation should include an upsert operation with points. For detailed information about batch updates, request body formats, batch processing, and available point properties, see the Qdrant API documentation.

Manual configuration

Qdrant destinations can also be manually configured to send data to any valid Qdrant API endpoint. 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.

Qdrant API typically uses the PUT method for upserting points and the POST method for batch operations, and expects JSON format for all requests. The endpoint URL should include your cluster host URL (from your credential) and the API path, e.g. /collections/{collection_name}/points or /collections/{collection_name}/points/batch. The request body should contain the point data as JSON, typically {message.json} to send the entire Nexset data, or a custom JSON structure with specific field mappings; batch operations may require the request body to include an operations array containing upsert operations with points. Each point should include an ID, vector values, and optional payload.

Save the destination

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 destination configuration for later use.