# RAG chunks for Pinecone or Qdrant with stable IDs

**Use case:** 

One row per passage: ready-made chunks with text, URL, title, date, evidence level and a stable id (same URL and text → same id), so repeated runs update your vector database instead of duplicating it. Works with Apify's Pinecone and Qdrant integrations.

## Input

```json
{
  "query": "What is retrieval-augmented generation and how is it evaluated?",
  "queries": [
    "What does Article 17 GDPR (right to erasure) require?",
    "What obligations do providers of high-risk AI systems have under the EU AI Act?"
  ],
  "sources": [
    "web",
    "wikipedia",
    "science"
  ],
  "preferEvidence": "balanced",
  "deepResearch": false,
  "scienceFullText": true,
  "tokenBudget": 3000,
  "maxResults": 8,
  "maxPassagesPerSource": 3,
  "language": "auto",
  "country": "de",
  "freshness": "any",
  "outputMode": "passages",
  "includeFullText": false,
  "fetchTimeoutSecs": 12,
  "useProxyForPages": false,
  "webFetch": true
}
```

## Output

```json
{
  "query": {
    "label": "query",
    "format": "text"
  },
  "rank": {
    "label": "rank",
    "format": "number"
  },
  "citation": {
    "label": "citation",
    "format": "number"
  },
  "text": {
    "label": "text",
    "format": "text"
  },
  "url": {
    "label": "url",
    "format": "link"
  },
  "title": {
    "label": "title",
    "format": "text"
  },
  "evidenceLevel": {
    "label": "evidenceLevel",
    "format": "text"
  },
  "publishedAt": {
    "label": "publishedAt",
    "format": "text"
  },
  "tokens": {
    "label": "tokens",
    "format": "number"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The Research Agent – Evidence-Graded Web Search for RAG Actor is ready to run with the inputs already set for "RAG chunks for Pinecone or Qdrant with stable IDs". [Sign up or log in](https://console.apify.com/create-task-from-example/vMiVrOb7HhfoHQTME) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "RAG chunks for Pinecone or Qdrant with stable IDs" task

The Research Agent – Evidence-Graded Web Search for RAG Actor will start running based on the input automatically. You can also change all the input fields, like question, questions (batch), and more, to match your specific use case.

### 3. Receive the "RAG chunks for Pinecone or Qdrant with stable IDs" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as query, rank, citation, and more.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "RAG chunks for Pinecone or Qdrant with stable IDs" task via API](https://apify.com/perceptr0n/research-agent.md).

## About this Actor

This example demonstrates how to use [Research Agent – Evidence-Graded Web Search for RAG](https://apify.com/perceptr0n/research-agent.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/perceptr0n/research-agent.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/perceptr0n/research-agent.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`).