Can NoClick run semantic and hybrid search against Weaviate?

Yes. The node includes Query / Search and Query by Text for vector and text lookups, plus Hybrid Search that blends keyword and vector scoring in a single call. You can wire the results into any downstream step, so a search runs as part of a larger automation rather than by hand.

Does the Weaviate node support retrieval-augmented generation?

It does. Generative Search runs a query and generates an answer over the matching objects in one operation, and Upload & Index Document gets your source material into a collection first. Together they let a workflow answer questions grounded in your own data.

How do I connect NoClick to my Weaviate cluster?

Add your cluster URL and an API key in the node's credentials, and NoClick connects to that instance directly. The same connection covers reads, writes, and collection management, so every operation in the node uses one set of credentials.

Can a workflow keep my collections and objects up to date?

Yes. The node can create and delete collections, list the ones you have, insert and update objects, and remove records one at a time or with Batch Delete Objects. Point these at any trigger and your index stays in sync as the source data changes.

Can a workflow react to new data on its own?

The Weaviate node is request and response, so it does not fire by itself. Pair it with a trigger node like a webhook, a schedule, or an incoming message, and that event can insert objects, run a search, or generate an answer from Weaviate in the same workflow.

What makes OpenCode different here?

OpenCode is open and model-agnostic, so you have flexibility over the underlying model. NoClick handles running it and connecting your apps as tools.

How do I give OpenCode tools?

Connect an integration node to the agent's tools handle and choose the operations to allow. Each becomes a tool the agent can call.

Do I manage any infrastructure?

No. NoClick runs the OpenCode harness in a hosted sandbox and resolves credentials for the apps you connect.

Can it combine several apps?

Yes. Add as many integrations as you need and the agent can use them together in one run.

Connect OpenCode to Weaviate

Give an AI agent your Weaviate cluster as a tool and it can build and query a knowledge base on its own while it works. It can create collections, insert and index documents, run hybrid and vector searches, and call Generative Search to answer questions over what it just stored, each one an operation it invokes when it needs it. Instead of asking you to look something up, the agent retrieves the right context itself and acts on it.

Loading preview…

Opens a workflow with 14 tools ready to use.

What happens next

Set up in minutes

The open button drops you into a guided setup. It asks exactly this, nothing else:

Choose where it runs
On your computer through your own OpenCode, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in Weaviate
A preset of real Weaviate operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Weaviate
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your OpenCode first calls in.
1. Run this in your terminal
$opencode mcp add
2. Choose Remote and paste your server URL
https://mcp.noclick.app/s/<your-link>
3. Choose No when asked about OAuth authentication — the link itself is the key
<your-link> is your personal server URL — setup mints it for you.

Exact capabilities

Tools OpenCode gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

Weaviate

14 tools

Query / Search

Vector similarity search (GraphQL nearVector).

Query by Text

Semantic search by text (GraphQL nearText — requires the class to have a text2vec vectorizer module).

Hybrid Search

Hybrid BM25 + vector search (GraphQL hybrid).

Generative Search (RAG)

Generative search (RAG): retrieve objects then generate text with an LLM (GraphQL generate). The collection must have a generative module configured in its schema (e.g. generative-openai, generative-anthropic, generative-cohere). Pass the corresponding API key in the credential. Provide single_prompt, group_task, or both.

Aggregate

Aggregate statistics over a collection (GraphQL Aggregate — count, mean, topOccurrences, etc.).

Insert Object

Insert an object (REST).

Get Object

Get an object by ID (REST).

Update Object

Partial update (PATCH /v1/objects/{class}/{id}) — merges provided fields.

Delete Object

Delete an object by ID (REST).

List Collections

List collections (schema classes).

Create Collection

Create a collection (schema class).

Delete Collection

Drop a collection and ALL of its objects — permanent.

Batch Delete Objects

Batch-delete objects matching a where filter (up to 10,000 per call).

Upload & Index Document

Upload a document file, chunk + embed it, and batch-insert objects.

Starting points

What you can build

When a new document lands in your storage, upload and index it into Weaviate so it becomes searchable within seconds.

Answer support questions automatically by running Generative Search over a collection of past tickets and product docs.

On a schedule, aggregate the objects in a collection to track how your indexed dataset is growing over time.

Take an inbound question, run a hybrid search to pull the most relevant objects, then feed them to an AI step for a grounded reply.

Keep records current by updating existing objects when their source changes and batch-deleting ones that are pulled or expired.

Spin up a fresh collection, insert a batch of objects, and query it by text in one automated pipeline.

Meet the runner

About OpenCode

OpenCode is an open, model-agnostic command-line coding agent. In NoClick it runs hosted and gains your apps as tools, so it can act on real systems rather than just edit files. Wire an integration into the agent and OpenCode can use that app’s operations directly while it works. It is a flexible choice when you want an open agent with broad model support and real tool access.

Open and model-agnostic

Flexible across many underlying models

Good general-purpose tool use

Lightweight to point at a focused task

Good to know