2.2 KiB
title, short_description, description
| title | short_description | description |
|---|---|---|
| Keboola | Connect Keboola to Qdrant to load embeddings from your data pipelines and orchestrate vector search as part of end-to-end data operations. | Integrate Qdrant with Keboola to build data pipelines that generate embeddings, manage collections, and orchestrate vector search across your stack. |
Keboola
Keboola is a data operations platform that integrates data engineering, analytics, and machine learning tools into a single environment. It helps businesses unify their data sources, transform data, and deploy ML models to production.
Prerequisites
- A Qdrant instance to connect to. You can get a free cloud instance at cloud.qdrant.io.
- A Keboola account to develop your data workflows.
Setting Up
- In your Keboola platform, navigate to the Components section.
- Find and add the Qdrant component from the component marketplace.
- Configure the connection to your Qdrant instance using your URL and API key.
Using Qdrant in Keboola
With Keboola's Qdrant integration, you can:
-
Data Pipeline Integration: Extract data from any source in Keboola, transform it, and load vector embeddings into Qdrant for semantic search capabilities.
-
Vector Database Management: Create, manage, and update collections in Qdrant directly from your Keboola workflows.
-
Orchestration: Schedule and automate your vector database operations as part of your data pipeline.
-
ML Operations: Combine your machine learning models with vector search capabilities for advanced AI applications.
Example Use Case
A common use case is to build a RAG (Retrieval Augmented Generation) system where:
- Data is extracted from multiple sources in Keboola
- Text is processed and transformed in Keboola's transformation engine
- Embeddings are generated and stored in Qdrant
- Applications query the Qdrant vectors for semantic search capabilities