# RAG Universal Ingestion (`toumi.oussema.re/rag-universal-ingestion`) Actor

Ingère une URL web, un PDF ou une vidéo YouTube et retourne des chunks propres + embeddings prêts à indexer dans une base vectorielle (LangChain, Pinecone, Weaviate, etc.)

- **URL**: https://apify.com/toumi.oussema.re/rag-universal-ingestion.md
- **Developed by:** [Oussema Toumi](https://apify.com/toumi.oussema.re) (community)
- **Categories:** AI, Agents, Automation
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $20.00 / 1,000 source ingérées

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## RAG Universal Ingestion

Ingère une page web, un PDF ou une vidéo YouTube, nettoie le contenu, le découpe
en chunks, et génère les embeddings (via OpenRouter) prêts à être indexés dans
une base vectorielle (Pinecone, Weaviate, Qdrant, LangChain, etc.).

### Input

| Champ | Type | Description |
|---|---|---|
| `sourceType` | string | `url`, `pdf`, ou `youtube` |
| `source` | string | URL de la source |
| `chunkSize` | int | Taille des chunks en caractères (défaut: 1000) |
| `chunkOverlap` | int | Chevauchement entre chunks (défaut: 150) |
| `generateEmbeddings` | bool | Générer les embeddings ou renvoyer le texte brut |
| `embeddingModel` | string | Modèle OpenRouter (défaut: `openai/text-embedding-3-small`) |
| `openrouterApiKey` | string | Clé API OpenRouter (requise si `generateEmbeddings=true`) |

### Output (dataset)

Chaque enregistrement du dataset contient: `source`, `sourceType`, `chunkIndex`,
`text`, `charCount`, et si activé `embedding` + `embeddingModel`.

### Facturation (pay-per-event)

- `source-ingested` — 0,02 $ — une fois par source traitée avec succès
- `chunk-embedded` — 0,001 $ — par chunk avec embedding généré
- `chunk-only` — 0,0002 $ — par chunk sans embedding

Exemple: une page web de 5000 mots → ~10 chunks avec embeddings ≈
0,02 $ + (10 × 0,001 $) = **0,03 $** facturés à l'utilisateur.

### Notes techniques

- Aucun GPU requis: l'extraction et le chunking sont du texte pur, et les
  embeddings sont délégués à OpenRouter (calcul déporté).
- Le PDF doit être accessible via une URL directe (pas d'upload de fichier
  dans cette version).
- Pour YouTube, seules les vidéos avec sous-titres/transcription disponibles
  fonctionnent.

# Actor input Schema

## `sourceType` (type: `string`):

Type de source à ingérer: page web, PDF ou vidéo YouTube

## `source` (type: `string`):

URL de la page web, du PDF, ou de la vidéo YouTube à ingérer

## `chunkSize` (type: `integer`):

Nombre de caractères par chunk après découpage

## `chunkOverlap` (type: `integer`):

Nombre de caractères de chevauchement entre deux chunks consécutifs

## `generateEmbeddings` (type: `boolean`):

Si activé, appelle le modèle d'embedding via OpenRouter pour chaque chunk

## `embeddingModel` (type: `string`):

Identifiant du modèle sur OpenRouter

## `openrouterApiKey` (type: `string`):

Requise uniquement si generateEmbeddings est activé

## Actor input object example

```json
{
  "sourceType": "url",
  "source": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation",
  "chunkSize": 1000,
  "chunkOverlap": 150,
  "generateEmbeddings": false,
  "embeddingModel": "openai/text-embedding-3-small"
}
```

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("toumi.oussema.re/rag-universal-ingestion").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("toumi.oussema.re/rag-universal-ingestion").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call toumi.oussema.re/rag-universal-ingestion --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,toumi.oussema.re/rag-universal-ingestion"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/8pXlNDPorMs0gTeuR/builds/xdOQoHikNpETQUR3E/openapi.json