Library / RAG & Knowledge Bases
RAG & Knowledge Bases
Answer Tour Itinerary Emails with OpenAI and Pinecone
When a customer email arrives by IMAP, an AI agent searches a Pinecone vector store of tour packages and replies by SMTP with a tailored itinerary.
What it does
## Steps 1. Connect to your Email using the Email Trigger (IMAP) - that reads for any incoming emails from customers. 2. Text Classfier: to classify the type of emails - first time package request, follow-up email or other email and route accordingly 3. Code: Extract the email content and standardise to JSON format return { ID: email.attributes.uid, Date: emailDate, Subject: emailSubject, EmailContent: emailContent, SenderEmail: senderEmail, SenderName: senderName, } 4. Tour Recomendation AI Agent: Give appropiate System Prompt and the references to the Tools available. 5. OpenaAI Model: ChatGPT-4o 6. Simple memory - upto 5 context window length 7. Answer Quetions with Vector Store: Add specific role and instructions to extract the tour packages from the pinecone database. 8. Send Email: Construct the Email response back to the customer with the packages.
The steps
- Email Trigger (IMAP)
- OpenRouter Chat Model
- OpenAI Chat Model
- Simple Memory
- Answer questions with a vector store
- Pinecone Vector Store
- Embeddings OpenAI1
- OpenAI Chat Model1
- Tour Recommendation AI Agent
- Format email content
- Route Workflow by Email Type
- Package Response Email
Similar automations
RAG & Knowledge BasesIndex Tour Package PDFs into Pinecone with OpenAI8 stepsAI Agents & AssistantsCreate Trip Itineraries from Email and WhatsApp with Ollama8 stepsRAG & Knowledge BasesRecommend Tour Packages with OpenAI and Pinecone9 stepsRAG & Knowledge BasesRecommend Tours by Voice with ElevenLabs, GPT-4o and Pinecone8 steps