Platforms on Qdrant - Vector Search Engine

Apify

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Apify

Apify is a web scraping and browser automation platform featuring an app store with over 1,500 pre-built micro-apps known as Actors. These serverless cloud programs, which are essentially dockers under the hood, are designed for various web automation applications, including data collection.

One such Actor, built especially for AI and RAG applications, is Website Content Crawler.

It’s ideal for this purpose because it has built-in HTML processing and data-cleaning functions. That means you can easily remove fluff, duplicates, and other things on a web page that aren’t relevant, and provide only the necessary data to the language model.

BuildShip

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

BuildShip

BuildShip is a low-code visual builder to create APIs, scheduled jobs, and backend workflows with AI assistance.

You can use the Qdrant integration to development workflows with semantic-search capabilities.

Prerequisites

A Qdrant instance to connect to. You can get a free cloud instance at cloud.qdrant.io.
A BuildsShip for developing workflows.

Nodes

Nodes are are fundamental building blocks of BuildShip. Each responsible for an operation in your workflow.

The Qdrant integration includes the following nodes with extensibility if required.

Keboola

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

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:

Kotaemon

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Kotaemon

Kotaemon is open-source clean & customizable RAG UI for chatting with your documents. Built with both end users and developers in mind.

Qdrant is supported as a vectorstore in Kotaemon for ingesting and retrieving documents.

Configuration

Refer to Getting started guide to set up Kotaemon.
To configure Kotaemon to use Qdrant as the vector store, update the flowsettings.py as follows.

KH_VECTORSTORE = {
 "__type__": "kotaemon.storages.QdrantVectorStore",
 "url": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
 "api_key": "<provide-your-own-key>'",
 "client_kwargs": {} # Additional options to pass to qdrant_client.QdrantClient
}

Restart Kotaemon for the changes to take effect.

The reference for all the Qdrant client options can be found here

Make.com

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Make.com

Make is a platform for anyone to design, build, and automate anything—from tasks and workflows to apps and systems without code.

Find the comprehensive list of available Make apps here.

Qdrant is available as an app within Make to add to your scenarios.

Prerequisites

Before you start, make sure you have the following:

A Qdrant instance to connect to. You can get free cloud instance cloud.qdrant.io.
An account at Make.com. You can register yourself here.

Setting up a connection

Navigate to your scenario on the Make dashboard and select a Qdrant app module to start a connection.

N8N

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

N8N

N8N is an automation platform that allows you to build flexible workflows focused on deep data integration.

Qdrant’s official node for n8n enables semantic search capabilities in your workflows.

Prerequisites

A Qdrant instance to connect to. You can get a free cloud instance at cloud.qdrant.io.
A running N8N instance. You can learn more about using the N8N cloud or self-hosting here.

Setting up the node

Select and install the official Qdrant node from the list of nodes in your workflow editor.

Pipedream

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Pipedream

Pipedream is a development platform that allows developers to connect many different applications, data sources, and APIs in order to build automated cross-platform workflows. It also offers code-level control with Node.js, Python, Go, or Bash if required.

You can use the Qdrant app in Pipedream to add vector search capabilities to your workflows.

Prerequisites

A Qdrant instance to connect to. You can get a free cloud instance at cloud.qdrant.io.
A Pipedream project to develop your workflows.

Setting Up

Search for the Qdrant app in your workflow apps.

Power Apps

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Power Apps

Microsoft Power Apps is a suite of apps, services, and connectors that provides a rapid development environment to build custom apps for your business needs. You can quickly build custom business apps that connect to your data stored in many online and on-premises data sources.

You can use the Qdrant Connector in Power Apps to add vector search capabilities to your flows.

Prerequisites

A Qdrant instance to connect to. You can get a free cloud instance at cloud.qdrant.io.
A Power Apps account to develop your flows.

Setting Up

Search for the Qdrant connector when adding a new action in a Power Apps flow. The connector offers an exhaustive list of pre-built Qdrant actions.

PrivateGPT

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

PrivateGPT

PrivateGPT is a production-ready AI project that allows you to inquire about your documents using Large Language Models (LLMs) with offline support.

PrivateGPT uses Qdrant as the default vectorstore for ingesting and retrieving documents.

Configuration

Qdrant settings can be configured by setting values to the qdrant property in the settings.yaml file. By default, Qdrant tries to connect to an instance at http://localhost:3000.

Example:

qdrant:
 url: "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333"
 api_key: "<your-api-key>"

The available configuration options are:

Salesforce Mulesoft

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Salesforce Mulesoft

MuleSoft Anypoint is an integration platform to connect applications, data, and devices across on-premises and cloud environments. It provides a unified platform to build, manage, and secure APIs and integrations, making digital transformation smoother and more scalable.

MAC Project is an open-source initiative to bring AI capabilities into the MuleSoft ecosystem. It provides connectors to add AI capabilities to an Anypoint project by integrating LLMs, vector databases including Qdrant.

ToolJet

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

ToolJet

ToolJet is a low-code platform for building business applications. Connect to databases, cloud storages, GraphQL, API endpoints, Airtable, Google sheets, OpenAI, etc and build apps using drag and drop application builder.

Prerequisites

A Qdrant instance to connect to. You can get a free cloud instance at cloud.qdrant.io.
A ToolJet instance to develop your workflows.

Setting Up

Search for the Qdrant plugin in the Tooljet plugins marketplace.
Set up the connection to Qdrant using your instance credentials.

Vectorize.io

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Vectorize.io

Vectorize is a SaaS platform that automates data extraction from several sources and lets you quickly deploy real-time RAG pipelines for your unstructured data. It also includes evaluation to help figure out the best strategies for the RAG system.

Vectorize pipelines natively integrate with Qdrant by converting unstructured data into vector embeddings and storing them in a collection. When a pipeline is running, any new change in the source data is immediately processed, keeping the vector index up-to-date.