# AI-powered RAG Q&A chatbot with OpenAI and Google Sheets: n8n workflow > Started by another system calling it, and works across Google Calendar, Google Drive and Qdrant. Source: https://millionrounds.com/workflow/ai-powered-rag-q-and-a-chatbot-with-openai-and-google-sheets (Millionrounds; every figure on the page links to its filing or article) [Automation library](https://millionrounds.com/workflows) · [Scheduling](https://millionrounds.com/workflows?category=Scheduling#library) # AI-powered RAG Q&A chatbot with OpenAI and Google Sheets Started by another system calling it, and works across Google Calendar, Google Drive and Qdrant. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 28 steps: large, and worth reading before you trust it with anything live. Large Calls a model: OpenAI Retrieval [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fai-powered-rag-q-and-a-chatbot-with-openai-and-google-sheets) **28 steps** Large: read it before trusting it with anything live **0** Branches: places the flow splits **0** Loops or waits **3** Services it connects to ## The flow Starts it 7 Model 13 Logic 2 Service 6 The steps in the order they run, from what starts it. - 1 **n8n_order** Webhook *Starts it* - 2 **OpenAI Chat Model3** Lm Chat Open Ai *Model* - 3 **n8n_appointment** Webhook *Starts it* - 4 **Embeddings OpenAI2** Embeddings Open Ai *Model* - 5 **OpenAI Chat Model2** Lm Chat Open Ai *Model* - 6 **OpenAI Chat Model1** Lm Chat Open Ai *Model* - 7 **n8n_rag** Webhook *Starts it* - 8 **Structured Output Parser** Output Parser Structured *Model* - 9 **When clicking ‘Test workflow’** Manual trigger *Starts it* - 10 **Embeddings OpenAI** Embeddings Open Ai *Model* - 11 **Token Splitter** Text Splitter Token Splitter *Model* - 12 **API URL Tracking** Http Request *Service* - 13 **Concert start date** Chain Llm *Model* - 14 **Retrive Qdrant Vector Store** Vector Store Qdrant *Model* - 15 **Retrive Agent** Agent *Model* - 16 **RAG** Tool Vector Store *Model* - 17 **Create collection** Http Request *Service* - 18 **Refresh collection** Http Request *Service* - 19 **Qdrant Vector Store** Vector Store Qdrant *Model* - 20 **Default Data Loader** Document Default Data Loader *Model* - 21 **Tracking response** Set *Logic* - 22 **Google Calendar** Google Calendar *Service* - 23 **Webhook RAG response** Respond To Webhook *Starts it* - 24 **Get folder** Google Drive *Service* - 25 **Webhook tracking response** Respond To Webhook *Starts it* - 26 **Calendar response** Set *Logic* - 27 **Download Files** Google Drive *Service* - 28 **Webhook calendar response** Respond To Webhook *Starts it* ## How it's built - **Starts on:** Another system calling it - **Steps:** 28 - **Size:** Large: read it before trusting it with anything live - **Connects to:** Google Calendar, Google Drive, Qdrant - **Model:** 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 Calendar, Google Drive and Qdrant accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included. What starts it? It starts on another system calling it. Does it use AI? Yes. It calls 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? Take your time. At 28 steps it is large: read it before trusting it with anything live. 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 28 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%2Fai-powered-rag-q-and-a-chatbot-with-openai-and-google-sheets) - **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 Calendar](https://millionrounds.com/workflows?service=Google+Calendar#library)[Google Drive](https://millionrounds.com/workflows?service=Google+Drive#library)[Qdrant](https://millionrounds.com/workflows?service=Qdrant#library) ## Workflows like it Also scheduling, with the same services where possible, closest in size first. - [**Build a chatbot, voice and phone agent with Voiceflow** 28 steps · calls a model · Google Calendar, Google Drive](https://millionrounds.com/workflow/build-a-chatbot-voice-and-phone-agent-with-voiceflow) - [**Personal AI agent with Gemini and Gmail** 28 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/personal-ai-agent-with-gemini-and-gmail) - [**AI-powered bug reporting & tracking** 29 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/ai-powered-bug-reporting-and-tracking) - [**Build an AI powered phone agent with Retell** 29 steps · calls a model · Google Calendar, Google Drive](https://millionrounds.com/workflow/build-an-ai-powered-phone-agent-with-retell) - [**Log Telegram client updates to Notion and Google Sheets** 27 steps · calls a model · Google Calendar, Google Drive](https://millionrounds.com/workflow/log-telegram-client-updates-to-notion-and-google-sheets) - [**Manage Google Calendar and Gmail from Telegram with Claude** 27 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/manage-google-calendar-and-gmail-from-telegram-with-claude)