Retrieval Augmented Generation (RAG) LLM Chatbot
Sebastiaan Wiechers
Development of a custom chatbot and up-to-date data ingestion pipeline, taking and storing data points in a vector database, that can be retrieved in real-time through a user-facing chatbot.
Grounding LLM calls in real-world data is the best way to prevent hallucinations, and serve your customers or employees with an easy and accessible way to interact with the data that you want.
We use AI to suggest custom messages for clients in our CRM, which saves our sales team time during outreach campaigns.
Like this project
Posted Mar 21, 2024
Developed a LLM chatbot using Retrieval Augmented Generation to ground outputs on CRM data and company documents.
