What can ModuleX do with Qdrant?

A ModuleX agent can run any of Qdrant's 7 actions — across queries, collections, collection infos and points — from a plain-English request, using your organization's own Qdrant credentials.

Does the Qdrant integration need a pre-built workflow?

No. The agent selects the right Qdrant action from your prompt. A workflow is only needed when you want a repeatable process — and the composer builds that for you from a description.

How does ModuleX authenticate with Qdrant?

Through a secure Qdrant connection; your credentials are stored encrypted and scoped to your organization.

How many Qdrant actions are available?

7, spanning queries, collections, collection infos and points.

Is Qdrant free to use in ModuleX?

Qdrant runs on your own credentials, so any Qdrant usage is billed by Qdrant directly. ModuleX meters the agent run — and if you connect your own model keys, there's no ModuleX markup on model usage.

Integrations

Qdrant integration

Vector Database · 7 actions · Custom auth

High-performance vector database with advanced filtering capabilities for semantic search. Pass-through access to your own Qdrant instance: vector similarity search, collection management, and point upsert/delete via the native REST API.

Put Qdrant to work View Qdrant integration docs

The ModuleX Qdrant integration lets a ModuleX agent operate Qdrant on your behalf — running create, remove and list actions across queries, collections and collection infos — directly from a plain-English request, using your organization's own Qdrant credentials. No pre-built workflow is required: the agent picks the right Qdrant action for the task.

Qdrant is a vector database platform. ModuleX adds the agent layer: ask for an outcome and it selects and runs the right Qdrant action — or, when you want a repeatable process, the composer assembles a Qdrant workflow for you, streaming the nodes onto the canvas as it builds.

Drive Qdrant in plain English

Type what you want. A ModuleX agent picks the right Qdrant action, or chains several, and runs it. No workflow to build.

“Create a collection with a single unnamed vector config”
resolves tocreate_collection
“Find the collection I describe and remove it”
resolves tolist_collectionsdelete_collection
“Delete points from a collection by ID list or by filter”
resolves todelete_points
“Show me the queries that match what I describe”
resolves toquery

What you can automate with Qdrant

Find the right collection and remove it in one promptlist_collectionsdelete_collection
Query your queries from a plain-English questionquery
Look up a collection info on demandget_collection_info
Upsert a point without writing SQLupsert_points

Qdrant integration at a glance

VendorQdrant

CategoryVector Database

Actions available7

AuthenticationCustom

Uses your own credentialsYes

Works with the assistantYes

Works in the composerYes

Multi-step / tool-chainingYes

Technical referenceView docs

Integration version1.0.0

Last updatedJul 2026

All 7 Qdrant actions

Queries1

query

Vector similarity search on a Qdrant collection. Send query_vector (works on every Qdrant instance), OR query_text + model to have Qdrant Cloud embed the text server-side (Cloud inference feature only — plain self-hosted Qdrant requires a vector). Returns Qdrant's native scored points.

Collections3

list_collections

List all collections in the Qdrant instance.

create_collection

Create a collection with a single unnamed vector config.

delete_collection

Delete a collection and all its points.

Collection Infos1

get_collection_info

Get native info about a collection (status, points_count, vector config, payload schema).

Points2

upsert_points

Insert or update points in a collection. Each point is a Qdrant-native {id, vector, payload?} object; on Qdrant Cloud with inference, vector may be a {text, model} document embedded server-side.

delete_points

Delete points from a collection by ID list or by filter.

See full parameters and response schemas in the Qdrant integration docs

Two ways to use Qdrant in ModuleX

Ask the assistantType what you want done and a ModuleX agent picks the right Qdrant action and runs it. No workflow to build.

Compose a workflowNeed it to happen every time? Describe the process and the composer wires Qdrant into a repeatable workflow you can run on a schedule, from chat, or as an API.

Connecting Qdrant

CustomQdrant uses a custom authentication flow. ModuleX encrypts whatever credentials you supply and scopes them to your organization.

Step-by-step setup in the Qdrant docs

Pairs well with Qdrant

Agents often chain Qdrant with these. Connect them once and the agent can use all of them in a single task.

Pinecone9 actions

Weaviate7 actions

MongoDB Atlas6 actions

Qdrant + ModuleX FAQ

A ModuleX agent can run any of Qdrant's 7 actions — across queries, collections, collection infos and points — from a plain-English request, using your organization's own Qdrant credentials.

Put Qdrant to work in ModuleX.

Put Qdrant to work View technical docs

Connect Qdrant once with your own credentials and let your agent run all 7 actions on demand.

Last updated: Jul 2026Browse all 179 integrations