Advanced Analytica Advanced Analytica: IBOM
← All connectors
Qdrant logo

Destination connector

Qdrant

Send governed data into Qdrant with a clear, practical setup guide.

Version 0.1.42 community alpha

Qdrant

Set up the Qdrant destination connector with this guide.

Output schema

A single stream collects payloads and optional vectors from every source stream. It uses a collection in Qdrant, with a name you define. If that collection doesn’t exist in the Qdrant instance, the connector creates it with the same name.

Each point in the collection receives a generated UUID string, which is used as the point id. Embeddings generated as defined, or extracted from the source stream, are stored as point vectors. The point payload primarily contains the record metadata. The text field is stored in the configured field within the point payload.

Supported sync modes

Sync modeSupported?
Full Refresh - OverwriteYes
Full Refresh - AppendYes
Full Refresh - Overwrite + DedupedYes
Incremental Sync - AppendYes
Incremental Sync - Append + DedupedYes

Getting started

You can connect to a Qdrant instance in local or cloud mode.

  • For local mode, set up Qdrant using Docker. See the official Qdrant guide in here. After setup, you’ll need your host, port and, where applicable, your gRPC port.
  • For Qdrant cloud, follow this official guide to get started. After setup, you’ll need the instance URL and an API key.

This connector doesn’t support local persistent mode. Use the Docker option for testing.

Requirements

To use the Qdrant destination, you’ll need:

  • An account with API access for OpenAI or Cohere, depending on your embedding method. You don’t need one when extracting vectors from the source stream.
  • A Qdrant db instance in local or cloud mode
  • Qdrant API Credentials for cloud mode
  • Host and Port for local mode
  • gRPC port, if applicable in local mode

Configure network access

Make sure Airbyte can access your Qdrant database. For a database within a VPC, you may need to allow the IP exposing Airbyte.

Set up the Qdrant destination in Airbyte

You can now configure Qdrant as a destination in the UI. You’ll need the following information:

  • (Required) Text fields to embed
  • (Optional) Text splitter Options for configuring the chunking process provided by the Langchain Python library.
  • (Required) Fields to store as metadata
  • (Required) Collection The Qdrant db collection name for storing your data
  • (Required) The field in the payload that contains the embedded text
  • (Required) Prefer gRPC Whether to prefer gRPC over HTTP
  • (Required) Distance Metric The distance metric used to measure vector similarities. Select from:
  • (Required) Authentication method
    • For local mode
      • Host for example localhost
      • Port for example 8000
      • gRPC Port (Optional)
    • For cloud mode
      • Url The URL of the cloud Qdrant instance
      • API Key The API Key for the cloud Qdrant instance
  • (Optional) Embedding
    • OpenAI API key when using OpenAI for embedding
    • Cohere API key when using Cohere for embedding
    • Embedding Field name and Embedding dimensions when embeddings come from stream records

Namespace support

This destination supports namespaces.

Changelog

Expand to review
VersionDatePull RequestSubject
0.1.422026-08-1384360Update the CDK to remediate CVE-2025-68664 in the langchain dependency
0.1.412025-05-1059814Update dependencies
0.1.402025-05-0358718Update dependencies
0.1.392025-04-1958282Update dependencies
0.1.382025-04-1257610Update dependencies
0.1.372025-04-0557162Update dependencies
0.1.362025-03-2956564Update dependencies
0.1.352025-03-2256159Update dependencies
0.1.342025-03-0855363Update dependencies
0.1.332025-03-0154889Update dependencies
0.1.322025-02-2254246Update dependencies
0.1.312025-02-1553939Update dependencies
0.1.302025-02-0853389Update dependencies
0.1.292025-02-0152917Update dependencies
0.1.282025-01-2552171Update dependencies
0.1.272025-01-1851716Update dependencies
0.1.262025-01-1151232Update dependencies
0.1.252025-01-0450917Update dependencies
0.1.242024-12-2850459Update dependencies
0.1.232024-12-2150222Update dependencies
0.1.222024-12-1449290Update dependencies
0.1.212024-11-2548641Update dependencies
0.1.202024-11-0448191Update dependencies
0.1.192024-10-2947757Update dependencies
0.1.182024-10-2847621Update dependencies
0.1.172024-10-2847054Update dependencies
0.1.162024-10-1246774Update dependencies
0.1.152024-10-0546417Update dependencies
0.1.142024-09-2846137Update dependencies
0.1.132024-09-2145830Update dependencies
0.1.122024-09-1445526Update dependencies
0.1.112024-09-0745217Update dependencies
0.1.102024-08-3144678Update dependencies
0.1.92024-08-1744293Update dependencies
0.1.82024-08-1243744Update dependencies
0.1.72024-08-1043529Update dependencies
0.1.62024-08-0343219Update dependencies
0.1.52024-07-2742620Update dependencies
0.1.42024-07-2042384Update dependencies
0.1.32024-07-1341919Update dependencies
0.1.22024-07-1041530Update dependencies
0.1.12024-07-0941096Update dependencies
0.1.02024-06-2741020Update to Airbyte CDK 2.3 and qdrant-client 1.10
0.0.132024-06-2740215Replaced deprecated AirbyteLogger with logging.Logger
0.0.122024-06-0639172[autopull] Upgrade base image to v1.2.2
0.0.112024-04-15#37333Updated CDK and pytest versions to fix security vulnerabilities
0.0.102023-12-11#33303Fix bug with embedding special tokens
0.0.92023-12-01#32697Allow omitting raw text
0.0.82023-11-29#32608Support deleting records for CDC sources and fix spec schema
0.0.72023-11-13#32357Improve spec schema
0.0.62023-10-23#31563Add field mapping option
0.0.52023-10-15#31329Add OpenAI-compatible embedder option
0.0.42023-10-04#31075Fix OpenAI embedder batch size
0.0.32023-09-29#30820Update CDK
0.0.22023-09-25#30689Update CDK to support Azure OpenAI embeddings and text splitting options
0.0.12023-09-22#30332🎉 New Destination: Qdrant (Vector Database)
Advanced Analytica

Most businesses are sitting on information they can’t use at speed. The people who hold it are busy, and when they leave, the knowledge goes with them. The documents are static, and the processes around them weren’t designed for AI.

Advanced Analytica works with these businesses to turn that information into structured data assets. Once they're integrated, AI systems can govern it, and the business can use it. We bring in the strategy, the specification and the AI skills to rework how the business operates.

MOVE FAST. STAY SAFE.