# Chat with your documentation: n8n RAG agent on Pinecone

**Use case:** 

Generates an n8n RAG workflow: a Chat Trigger feeding an AI Agent with an OpenAI chat model and memory, plus a Pinecone vector store with OpenAI embeddings attached as a retrieval tool. The store's mode, the embeddings sub-node and the tool connection come out the way n8n stores them. Attach OpenAI and Pinecone credentials after import and point the store at your index.

## Input

```json
{
  "prompt": "A chat assistant that answers questions about our documentation: an AI agent with an OpenAI chat model that uses a Pinecone vector store (with OpenAI embeddings) as a tool to retrieve relevant chunks."
}
```

## Output

```json
{
  "workflowName": {
    "label": "Workflow",
    "format": "text"
  },
  "valid": {
    "label": "Valid",
    "format": "boolean"
  },
  "nodeCount": {
    "label": "Nodes",
    "format": "number"
  },
  "nodeTypes": {
    "label": "Node types",
    "format": "array"
  },
  "credentialsNeeded": {
    "label": "Credentials to attach",
    "format": "array"
  },
  "warnings": {
    "label": "Check before use",
    "format": "array"
  },
  "errors": {
    "label": "Errors",
    "format": "array"
  },
  "workflowJsonUrl": {
    "label": "Download JSON",
    "format": "link"
  },
  "prompt": {
    "label": "Prompt",
    "format": "text"
  }
}
```

## About this Actor

This example demonstrates how to use [n8n Workflow Generator - Prompt to Importable JSON](https://apify.com/mediocre_interest/n8n-workflow-builder.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/mediocre_interest/n8n-workflow-builder.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/mediocre_interest/n8n-workflow-builder.md

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).