What can ModuleX do with Weaviate?

A ModuleX agent can run any of Weaviate's 7 actions — across queries, classes, class stats and objects — from a plain-English request, using your organization's own Weaviate credentials.

Does the Weaviate integration need a pre-built workflow?

No. The agent selects the right Weaviate 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 Weaviate?

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

How many Weaviate actions are available?

7, spanning queries, classes, class stats and objects.

Is Weaviate free to use in ModuleX?

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

Integrations

Weaviate integration

Vector Database · 7 actions · Custom auth

Open-source vector database with built-in ML models and GraphQL API. Pass-through access to your own Weaviate instance: vector and text similarity search, schema management, and object insert/delete via the native GraphQL + REST APIs.

Put Weaviate to work View Weaviate integration docs

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

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

Drive Weaviate in plain English

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

“Create a class (collection) in the Weaviate schema”
resolves tocreate_class
“Find the class I describe and remove it”
resolves tolist_classesdelete_class
“Delete one object by UUID”
resolves todelete_object
“Show me the queries that match what I describe”
resolves toquery

What you can automate with Weaviate

Find the right class and remove it in one promptlist_classesdelete_class
Query your queries from a plain-English questionquery
Look up a class stat on demandget_class_stats
Remove an object you no longer needdelete_object

Weaviate integration at a glance

VendorWeaviate

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 Weaviate actions

Queries1

query

Similarity search on a Weaviate class via GraphQL Get. Send query_vector (nearVector — works on every class), OR query_text (nearText — ONLY on classes configured with a vectorizer module that embeds text server-side; classes without a vectorizer require a vector). Returns Weaviate's native objects with _additional metadata.

Classes3

list_classes

List all classes (collections) in the Weaviate schema.

create_class

Create a class (collection) in the Weaviate schema.

delete_class

Delete a class and ALL its objects.

Class Stats1

get_class_stats

Get the object count of a class via GraphQL Aggregate.

Objects2

insert_object

Insert one object into a class. Omit vector when the class has a vectorizer module (server-side embedding).

delete_object

Delete one object by UUID.

See full parameters and response schemas in the Weaviate integration docs

Two ways to use Weaviate in ModuleX

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

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

Connecting Weaviate

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

Step-by-step setup in the Weaviate docs

Pairs well with Weaviate

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

Pinecone9 actions

Qdrant7 actions

MongoDB Atlas6 actions

Weaviate + ModuleX FAQ

A ModuleX agent can run any of Weaviate's 7 actions — across queries, classes, class stats and objects — from a plain-English request, using your organization's own Weaviate credentials.

Put Weaviate to work in ModuleX.

Put Weaviate to work View technical docs

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

Last updated: Jul 2026Browse all 179 integrations