Qdrant

Upsert points and run similarity searches in Qdrant collections.

Data and storageAPI key7 actionsAll integrations

On this page

Connect
Call it from a workflow
Actions (7)
get_points
search_points
add_points_to_collection
collection_infos
collection_list
delete_collection
delete_points
Details

Connect

Auth type: API key (secret_text). Paste the API key (or token) from the provider's settings into the connect dialog. It is encrypted at rest and only decrypted on the server when an action runs.

In the editor: Backend panel, Integrations tab, then Connect. This connects it for the project.
For every project in a workspace: Workspace settings, Integrations.
Owners and admins choose which integrations members may connect in the admin panel (Integrations tab), and can attach their own OAuth app there.

Call it from a workflow

Pass the action name and its input. The call resolves with { success, output, error? }; a missing connection resolves with success false and the reason. See ctx.integrations.invoke and ctx.integrations.call.

Native workflow

// .workflow.js (native ctx)
export async function run(ctx) {
  const res = await ctx.integrations.invoke("qdrant", "get_points", {
    "collectionName": "<collection name>",
    "getPointsBy": "Ids",
    "infosToGetPoint": {}
  });
  if (!res.success) throw new Error(res.error);
  ctx.log.info("Qdrant answered", { output: res.output });
}

defineWorkflow module

// defineWorkflow module (@app/sdk ctx)
import { defineWorkflow } from "@app/sdk";

export default defineWorkflow({
  id: "qdrant-get-points",
  name: "Qdrant: Get Points",
  description: "Calls Qdrant when a row is created.",
  trigger: { type: "entity_event", entity: "tickets", event: "created" },
  async run(ctx, event) {
    const res = await ctx.integrations.call("qdrant", {
      "action": "get_points",
      "collectionName": "<collection name>",
      "getPointsBy": "Ids",
      "infosToGetPoint": {}
    }) as { success: boolean; error?: string };
    if (!res.success) throw new Error(res.error);
  },
});

From an app (connector proxy)

curl -X POST "$APP_ORIGIN/__appbricx/connector-proxy/qdrant/get_points" \
  -H "Authorization: Bearer $APP_KEY" \
  -H "content-type: application/json" \
  -d '{"props":{"collectionName":"<collection name>","getPointsBy":"Ids","infosToGetPoint":{}}}'

Actions

get_pointsin catalog

Get Points. Get the points of a specific collection

Input	Type	Description
`collectionName`required	text	The name of the collection needed for this action
`getPointsBy`required	one of "Ids" \| "Filtering"	The method to use to get the points
`infosToGetPoint`required	object (depends on other props)	The infos to select points

search_pointsin catalog

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

Input	Type	Description
`collectionName`required	text	The name of the collection needed for this action
`vector`required	file	The vector (= embedding) you want to search for.
`must`optional	object	If the point have this property in his payload it will be selected
`must_not`optional	object	If the point have this property in his payload it will not be selected
`negativeVector`optional	file	The vector (= embedding) you want to be the farthest.
`limitResult`optional	number	The max number of results you want to get.

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

Input	Type	Description
`collectionName`required	text	The name of the collection needed for this action
`embeddings`required	file	Embeddings (= vectors) for the points
`embeddingsIds`optional	array	The ids of the embeddings for the points. If not provided, the ids will be generated automatically
`distance`required	one of "Cosine" \| "Euclid" \| "Dot"	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`optional	JSON	Please follow [payload documentation](https://qdrant.tech/documentation/concepts/payload/) to add additional information to the points.
`storage`optional	one of "Disk" \| "Memory"	Define where points will be stored

collection_infos

Get Collection Infos. Get the all the infos of a specific collection

Input	Type	Description
`collectionName`required	text	The name of the collection needed for this action

collection_list

Get Collection List. Get the list of all the collections of your database

No input.

delete_collection

Delete Collection. Delete a collection of your database

Input	Type	Description
`collectionName`required	text	The name of the collection needed for this action

delete_points

Delete Points. Delete points of a specific collection

Input	Type	Description
`collectionName`required	text	The name of the collection needed for this action
`getPointsBy`required	one of "Ids" \| "Filtering"	The method to use to get the points
`infosToGetPoint`required	object (depends on other props)	The infos to select points

Details

Id: qdrant
Category: Data and storage
Tags: vector, embeddings, ai, similarity-search, open-source
Package: @activepieces/piece-qdrant@0.3.3
Tier: Community