# Answer WhatsApp questions from PDF documents with RAG: n8n workflow > Started by an incoming WhatsApp message, and works across Google Drive, Pinecone and WhatsApp. Source: https://millionrounds.com/workflow/answer-whatsapp-questions-from-pdf-documents-with-rag (Millionrounds; every figure on the page links to its filing or article) [Automation library](https://millionrounds.com/workflows) · [Customer support](https://millionrounds.com/workflows?category=Customer+support#library) # Answer WhatsApp questions from PDF documents with RAG Started by an incoming WhatsApp message, and works across Google Drive, Pinecone and WhatsApp. It puts Gemini and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 14 steps: a working afternoon to understand properly. Medium Calls a model: Gemini, OpenAI Retrieval [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fanswer-whatsapp-questions-from-pdf-documents-with-rag) **14 steps** Medium: a working afternoon **0** Branches: places the flow splits **0** Loops or waits **3** Services it connects to ## The flow Starts it 3 Model 9 Service 2 The steps in the order they run, from what starts it. - 1 **Google Drive Trigger** Google Drive trigger *Starts it* - 2 **Embeddings OpenAI** Embeddings Open Ai *Model* - 3 **Recursive Character Text Splitter1** Text Splitter Recursive Character Text Splitter *Model* - 4 **When chat message received** Chat trigger *Starts it* - 5 **Google Gemini Chat Model** Lm Chat Google Gemini *Model* - 6 **Simple Memory** Memory Buffer Window *Model* - 7 **Embeddings OpenAI1** Embeddings Open Ai *Model* - 8 **WhatsApp Trigger** Whats App trigger *Starts it* - 9 **Download file** Google Drive *Service* - 10 **Pinecone Vector Store1** Vector Store Pinecone *Model* - 11 **Default Data Loader** Document Default Data Loader *Model* - 12 **AI Agent** Agent *Model* - 13 **Pinecone Vector Store** Vector Store Pinecone *Model* - 14 **Send message** Whats App *Service* ## How it's built - **Starts on:** An incoming WhatsApp message - **Steps:** 14 - **Size:** Medium: a working afternoon - **Connects to:** Google Drive, Pinecone, WhatsApp - **Model:** Gemini, OpenAI - **Retrieval:** Answers are drawn from documents you supply, not from the model alone ## Questions What does it need to run? An n8n account, plus your own Google Drive, Pinecone and WhatsApp accounts, and a key for Gemini and OpenAI. You connect your own accounts after importing it; none are included. What starts it? It starts on an incoming WhatsApp message. Does it use AI? Yes. It calls Gemini and OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n. How long does it take to set up? Plan an afternoon. 14 steps is enough that you should read each one before running it. How do I import it? Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts. **Before you run it** Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 14 steps before you point it at anything that matters. ## Run it in n8n - **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n) - **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fanswer-whatsapp-questions-from-pdf-documents-with-rag) - **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts. Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind. ## Connects to Each opens the other workflows that use it. [Google Drive](https://millionrounds.com/workflows?service=Google+Drive#library)[Pinecone](https://millionrounds.com/workflows?service=Pinecone#library)[WhatsApp](https://millionrounds.com/workflows?service=WhatsApp#library) ## Workflows like it Also customer support, with the same services where possible, closest in size first. - [**Answer code of conduct questions in Slack with OpenAI and RAG** 14 steps · calls a model · Google Drive, Slack](https://millionrounds.com/workflow/answer-code-of-conduct-questions-in-slack-with-openai-and-ra) - [**Create a travel support RAG chatbot with Google Drive** 14 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/create-a-travel-support-rag-chatbot-with-google-drive) - [**Handle WhatsApp customer inquiries with Gemini** 14 steps · calls a model · WhatsApp](https://millionrounds.com/workflow/handle-whatsapp-customer-inquiries-with-gemini) - [**IT support chatbot with Google Drive and Pinecone** 14 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/it-support-chatbot-with-google-drive-and-pinecone) - [**Answer Slack knowledge base questions with Notion and Pinecone** 15 steps · calls a model · Notion, Pinecone](https://millionrounds.com/workflow/answer-slack-knowledge-base-questions-with-notion-and-pineco) - [**Answer customer questions on WhatsApp with OpenAI and Gmail** 15 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/answer-customer-questions-on-whatsapp-with-openai-and-gmail)