Skip to content
Documentation
Contact
← Back to documentation
Technical Reference

Qdrant

Make any action on your qdrant vector database

CategoryDeveloper Tools
Authenticationcustom
Version0.3.6
Published scopes0 published scopes
Last updatedSeptember 30, 2026

Overview

Connect Qdrant with Flows360

Make any action on your qdrant vector database

Use the Qdrant connector to include its declared actions and events in Flows360 workflows without duplicating the integration logic inside each consuming system. This pinned connector version currently exposes 7 actions and no declared triggers.

Available actions

  • Add points to collection
  • Get Collection List
  • Get Collection Infos
  • Delete Collection
  • Delete Points
  • Get Points
  • Search Points

Available triggers

  • No triggers are declared in this pinned package.

The capability list above is generated from the exact reviewed connector package so the public description stays aligned with the version Flows360 operates.

Technical guide

Technical reference

Package identity

  • Connector: Qdrant
  • Package: @activepieces/piece-qdrant@0.3.6
  • Exact artifact digest: sha256:08747b8ca40440703587e71ed590495204e67ac27a71bb8e88d5d842d586ca09
  • Runtime: Activepieces-compatible deterministic worker
  • Source: the exact reviewed Activepieces source

Authentication

CUSTOM AUTH. Connection values are tenant-specific and remain in the consuming Studio instance; CDK stores definitions and field metadata, not customer credential values.

Action contracts

  • Add points to collection (add_points_to_collection), Insert a point (= embedding or vector + other infos) to a specific collection, if the collection does not exist it will be created Classification: read.
  • Get Collection List (collection_list), Get the list of all the collections of your database Classification: read.
  • Get Collection Infos (collection_infos), Get the all the infos of a specific collection Classification: read.
  • Delete Collection (delete_collection), Delete a collection of your database Classification: read.
  • Delete Points (delete_points), Delete points of a specific collection Classification: read.
  • Get Points (get_points), Get the points of a specific collection Classification: read.
  • Search Points (search_points), Search for points closest to your given vector (= embedding) Classification: read.

Trigger contracts

  • No trigger delivery contracts are declared.

Verification

Runtime execution evidence is managed separately from package metadata.

Capability summary

Authenticationcustom
Supported objects7
Supported actions7
TriggersNone published

Authentication

Authentication method: custom

Authentication profiles

connection · custom
  • Server Address Required
  • API KEY Required · protected credential

Supported objects

ObjectReadWriteNotes
Add points to collection Yes No Insert a point (= embedding or vector + other infos) to a specific collection, if the collection does not exist it will be created
Get Collection List Yes No Get the list of all the collections of your database
Get Collection Infos Yes No Get the all the infos of a specific collection
Delete Collection Yes No Delete a collection of your database
Delete Points Yes No Delete points of a specific collection
Get Points Yes No Get the points of a specific collection
Search Points Yes No Search for points closest to your given vector (= embedding)

Supported actions

Add points to collection · Read

Insert a point (= embedding or vector + other infos) to a specific collection, if the collection does not exist it will be created

add_points_to_collection · Risk: low · Retry: safe

Inputs

  • collectionName · string · Required, The name of the collection needed for this action
  • embeddings · object · Required, Embeddings (= vectors) for the points
  • embeddingsIds · array · Optional, The ids of the embeddings for the points. If not provided, the ids will be generated automatically
  • distance · string · Required, The calculation method helps to rank vectors when you want to find the closest points, the method to use depends on the model who's created the embeddings, see the documentation of your model
  • payload · object · Optional, Please follow [payload documentation](https://qdrant.tech/documentation/concepts/payload/) to add additional information to the points.
  • storage · string · Optional, Define where points will be stored
Get Collection List · Read

Get the list of all the collections of your database

collection_list · Risk: low · Retry: safe

Get Collection Infos · Read

Get the all the infos of a specific collection

collection_infos · Risk: low · Retry: safe

Inputs

  • collectionName · string · Required, The name of the collection needed for this action
Delete Collection · Read

Delete a collection of your database

delete_collection · Risk: low · Retry: safe

Inputs

  • collectionName · string · Required, The name of the collection needed for this action
Delete Points · Read

Delete points of a specific collection

delete_points · Risk: low · Retry: safe

Inputs

  • collectionName · string · Required, The name of the collection needed for this action
  • getPointsBy · string · Required, The method to use to get the points
  • infosToGetPoint · object · Required, The infos to select points
Get Points · Read

Get the points of a specific collection

get_points · Risk: low · Retry: safe

Inputs

  • collectionName · string · Required, The name of the collection needed for this action
  • getPointsBy · string · Required, The method to use to get the points
  • infosToGetPoint · object · Required, The infos to select points
Search Points · Read

Search for points closest to your given vector (= embedding)

search_points · Risk: low · Retry: safe

Inputs

  • collectionName · string · Required, The name of the collection needed for this action
  • vector · object · Required, The vector (= embedding) you want to search for.
  • must · object · Optional, If the point have this property in his payload it will be selected
  • must_not · object · Optional, If the point have this property in his payload it will not be selected
  • negativeVector · object · Optional, The vector (= embedding) you want to be the farthest.
  • limitResult · number · Optional, The max number of results you want to get.

Setup

Setup

  1. Add the Qdrant connector to the workflow in the target Flows360 Studio instance.
  2. Create or select the tenant-specific connection required by the connector. Connection secrets remain in the Studio connection boundary and are not copied into CDK documentation.
  3. Provide the connection fields declared by the pinned package:
  • Server Address (serverAddress), required.
  • API KEY (key), required; stored as a sensitive connection value.
  1. Select the required action or trigger and complete its declared input fields. Required and optional inputs are defined by the exact package schema.
  2. Test the workflow in the appropriate environment before enabling production scheduling or event delivery.

Limitations

Limitations and operational notes

  • This content describes @activepieces/piece-qdrant@0.3.6; provider behaviour can change independently and should be revalidated when the provider or connector version changes.
  • Only the 7 actions and 0 triggers declared by this pinned package are represented here.
  • Tenant credentials and connection values are not stored in the public connector record.
  • Provider-side permissions, account entitlements, quotas and rate limits remain subject to the connected provider account and are not inferred when the package does not declare them.
  • Runtime execution evidence is managed separately from package metadata.

Troubleshooting

Why canu2019t the connector authenticate?

Check the tenant connection in Studio and confirm every required Qdrant connection field is present. Re-authorise OAuth-based connections if the provider token or consent has expired. Do not place credential values in CDK content or logs.

Why is an action or trigger unavailable?

Confirm that the workflow is using @activepieces/piece-qdrant@0.3.6 and compare the requested capability with the declared action and trigger list for this version. A capability that is not declared by the pinned package should not be presented as supported.

What should I check after a provider-side change?

Revalidate authentication, required fields, action/trigger behaviour and provider documentation before publishing refreshed connector content or moving a new package version into production.

github.com