> For the complete documentation index, see [llms.txt](https://docs.n8n.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase.md).

# Supabase Vector Store

Use the Supabase Vector Store to interact with your Supabase database as vector store. You can insert documents into a vector database, get many documents from a vector database, and retrieve documents to provide them to a retriever connected to a chain.

Use the Supabase Vector Store to interact with your Supabase database as [vector store](#user-content-fn-1)[^1]. You can insert documents into a vector database, get documents from a vector database, retrieve documents to provide them to a retriever connected to a chain[^2], or connect it directly to an agent[^3] to use as a tool[^4]. You can also update an item in a vector store by its ID.

On this page, you'll find the node parameters for the Supabase node, and links to more resources.

{% hint style="info" %}
**Credentials**

You can find authentication information for this node [here](/integrations/builtin/credentials/supabase.md).
{% endhint %}

{% hint style="info" %}
**Parameter resolution in sub-nodes**

Sub-nodes behave differently to other nodes when processing multiple items using an expression.

Most nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for each item in turn. For example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.

In sub-nodes, the expression always resolves to the first item. For example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.
{% endhint %}

Supabase provides a [quickstart for setting up your vector store](https://supabase.com/docs/guides/ai/langchain?database-method=sql). If you use settings other than the defaults in the quickstart, this may affect parameter settings in n8n. Make sure you understand what you're doing.

## Node usage patterns <a href="#node-usage-patterns" id="node-usage-patterns"></a>

You can use the Supabase Vector Store node in the following patterns.

### Use as a regular node to insert, update, and retrieve documents <a href="#use-as-a-regular-node-to-insert-update-and-retrieve-documents" id="use-as-a-regular-node-to-insert-update-and-retrieve-documents"></a>

You can use the Supabase Vector Store as a regular node to insert, update, or get documents. This pattern places the Supabase Vector Store in the regular connection flow without using an agent.

You can see an example of this in scenario 1 of [this template](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/).

### Connect directly to an AI agent as a tool <a href="#connect-directly-to-an-ai-agent-as-a-tool" id="connect-directly-to-an-ai-agent-as-a-tool"></a>

You can connect the Supabase Vector Store node directly to the tool connector of an [AI agent](https://github.com/n8n-io/n8n-docs/blob/main/docs/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent) to use a vector store as a resource when answering queries.

Here, the connection would be: AI agent (tools connector) -> Supabase Vector Store node.

### Use a retriever to fetch documents <a href="#use-a-retriever-to-fetch-documents" id="use-a-retriever-to-fetch-documents"></a>

You can use the [Vector Store Retriever](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievervectorstore.md) node with the Supabase Vector Store node to fetch documents from the Supabase Vector Store node. This is often used with the [Question and Answer Chain](https://github.com/n8n-io/n8n-docs/blob/main/docs/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainretrievalqa) node to fetch documents from the vector store that match the given chat input.

An [example of the connection flow](https://n8n.io/workflows/1960-ask-questions-about-a-pdf-using-ai/) (the example uses Pinecone, but the pattern in the same) would be: Question and Answer Chain (Retriever connector) -> Vector Store Retriever (Vector Store connector) -> Supabase Vector Store.

### Use the Vector Store Question Answer Tool to answer questions <a href="#use-the-vector-store-question-answer-tool-to-answer-questions" id="use-the-vector-store-question-answer-tool-to-answer-questions"></a>

Another pattern uses the [Vector Store Question Answer Tool](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolvectorstore.md) to summarize results and answer questions from the Supabase Vector Store node. Rather than connecting the Supabase Vector Store directly as a tool, this pattern uses a tool specifically designed to summarizes data in the vector store.

The [connections flow](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/) in this case would look like this: AI agent (tools connector) -> Vector Store Question Answer Tool (Vector Store connector) -> Supabase Vector store.

## Node parameters <a href="#node-parameters" id="node-parameters"></a>

### Operation Mode <a href="#operation-mode" id="operation-mode"></a>

This Vector Store node has five modes: **Get Many**, **Insert Documents**, **Retrieve Documents (As Vector Store for Chain/Tool)**, **Retrieve Documents (As Tool for AI Agent)**, and **Update Documents**. The mode you select determines the operations you can perform with the node and what inputs and outputs are available.

**Get Many**

In this mode, you can retrieve multiple documents from your vector database by providing a prompt. The prompt will be embedded and used for similarity search. The node will return the documents that are most similar to the prompt with their similarity score. This is useful if you want to retrieve a list of similar documents and pass them to an agent as additional context.

**Insert Documents**

Use Insert Documents mode to insert new documents into your vector database.

**Retrieve Documents (As Vector Store for Chain/Tool)**

Use Retrieve Documents (As Vector Store for Chain/Tool) mode with a vector-store retriever to retrieve documents from a vector database and provide them to the retriever connected to a chain. In this mode you must connect the node to a retriever node or root node.

**Retrieve Documents (As Tool for AI Agent)**

Use Retrieve Documents (As Tool for AI Agent) mode to use the vector store as a tool resource when answering queries. When formulating responses, the agent uses the vector store when the vector store name and description match the question details.

**Update Documents**

Use Update Documents mode to update documents in a vector database by ID. Fill in the **ID** with the ID of the embedding entry to update.

### Rerank Results <a href="#rerank-results" id="rerank-results"></a>

Enables [reranking](/key-concept-glossary.md#ai-reranking). If you enable this option, you must connect a reranking node to the vector store. That node will then rerank the results for queries. You can use this option with the `Get Many`, `Retrieve Documents (As Vector Store for Chain/Tool)` and `Retrieve Documents (As Tool for AI Agent)` modes.

### Get Many parameters <a href="#get-many-parameters" id="get-many-parameters"></a>

* **Table Name**: Enter the Supabase table to use.
* **Prompt**: Enter the search query.
* **Limit**: Enter how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.

### Insert Documents parameters <a href="#insert-documents-parameters" id="insert-documents-parameters"></a>

* **Table Name**: Enter the Supabase table to use.

### Retrieve Documents (As Vector Store for Chain/Tool) parameters <a href="#retrieve-documents-as-vector-store-for-chaintool-parameters" id="retrieve-documents-as-vector-store-for-chaintool-parameters"></a>

* **Table Name**: Enter the Supabase table to use.

### Retrieve Documents (As Tool for AI Agent) parameters <a href="#retrieve-documents-as-tool-for-ai-agent-parameters" id="retrieve-documents-as-tool-for-ai-agent-parameters"></a>

* **Name**: The name of the vector store.
* **Description**: Explain to the LLM what this tool does. A good, specific description allows LLMs to produce expected results more often.
* **Table Name**: Enter the Supabase table to use.
* **Limit**: Enter how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.

### Update Documents <a href="#update-documents" id="update-documents"></a>

* **Table Name**: Enter the Supabase table to use.
* **ID**: The ID of an embedding entry.

Parameters for **Update Documents**

* ID

## Node options <a href="#node-options" id="node-options"></a>

### Query Name <a href="#query-name" id="query-name"></a>

The name of the matching function you set up in Supabase. If you follow the [Supabase quickstart](https://supabase.com/docs/guides/ai/langchain?database-method=sql), this will be `match_documents`.

### Metadata Filter <a href="#metadata-filter" id="metadata-filter"></a>

Available in **Get Many** mode. When searching for data, use this to match with metadata associated with the document.

This is an `AND` query. If you specify more than one metadata filter field, all of them must match.

When inserting data, the metadata is set using the document loader. Refer to [Default Data Loader](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.documentdefaultdataloader.md) for more information on loading documents.

## Templates and examples <a href="#templates-and-examples" id="templates-and-examples"></a>

[Browse Supabase Vector Store node documentation integration templates](https://n8n.io/integrations/supabase-vector-store) or [search all templates](https://n8n.io/workflows/)

## Related resources <a href="#related-resources" id="related-resources"></a>

Refer to [LangChain's Supabase documentation](https://js.langchain.com/docs/integrations/vectorstores/supabase/) for more information about the service.

View n8n's [Advanced AI](https://github.com/n8n-io/n8n-docs/blob/main/advanced-ai/index.md) documentation.

[^1]: A vector store, or vector database, stores mathematical representations of information. Use with embeddings and retrievers to create a database that your AI can access when answering questions.

[^2]: AI chains allow you to interact with large language models (LLMs) and other resources in sequences of calls to components. AI chains in n8n don't use persistent memory, so you can't use them to reference previous context (use AI agents for this).

[^3]: AI agents are artificial intelligence systems capable of responding to requests, making decisions, and performing real-world tasks for users. They use large language models (LLMs) to interpret user input and make decisions about how to best process requests using the information and resources they have available.

[^4]: In an AI context, a tool is an add-on resource that the AI can refer to for specific information or functionality when responding to a request. The AI model can use a tool to interact with external systems or complete specific, focused tasks.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.