Build an AI powered phone agent 📞🤖 with Retell, Google Calendar and RAG
Needs changesWhat this workflow does
This AI workflow has 29 nodes and runs manually, when you click “Execute workflow” (plus 3 other triggers). Along the way it connects OpenAI Chat Model, Qdrant Vector Store, Embeddings OpenAI and Vector Store Question Answer and 3 more. It also calls qdranturl over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 3 other triggers).
- Create collection (HTTP Request): calls qdranturl (POST)
- Refresh collection (HTTP Request): calls an HTTP API (POST)
- Concert start date (Basic LLM Chain): sends a prompt to an LLM, with model: OpenAI Chat Model; output parser: Structured Output Parser
- Filter: keeps only the items that match a condition
- Retrive Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (RAG)
- Get folder (Google Drive): work with file folder
- Google Calendar: uses Google Calendar
- Set call fields (Edit Fields (Set)): sets 9 fields: Transcript, Duration (sec), From…
- Respond to Webhook: sends the response back to the webhook caller
- Download Files (Google Drive): download
…plus 3 more steps. See the full node list below.
Services it uses
HTTP calls to: qdranturl
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Retrive Agent (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Retrive Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (18)
- Filter
n8n-nodes-base.filter - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Webhook
n8n-nodes-base.webhook - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - Respond to Webhook
n8n-nodes-base.respondToWebhook - Telegram
n8n-nodes-base.telegram - Google Calendar
n8n-nodes-base.googleCalendar - Manual Trigger
n8n-nodes-base.manualTrigger - HTTP Request
n8n-nodes-base.httpRequest - Google Drive
n8n-nodes-base.googleDrive - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Token Splitter
@n8n/n8n-nodes-langchain.textSplitterTokenSplitter - Edit Fields (Set)
n8n-nodes-base.set - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - AI Agent
@n8n/n8n-nodes-langchain.agent
From the author
This Workflow simulates an AI-powered phone agent with RetellAI with two main functions: 1. 📅 Appointment Booking – It can schedule appointments directly into Google Calendar. 2. 🧠 RAG-based Information Retrieval – It provides answers using a…