RAG assistant · our own product
Customer Intelligence
An assistant that answers questions over customer feedback, sales call notes and documents, and shows which document each answer came from.
- Client
- FOMER product
- Year
- 2026
- Status
- Live
Teams spread what they know about customers across dozens of documents. Customer Intelligence makes them searchable in one place: ask a question and the answer comes with its source documents.
Documents are embedded with a local model and stored in pgvector, so search runs without sending data out. A language model running on Groq writes the answer from the retrieved documents and labels it as an opportunity, a risk or neutral. The backend is NestJS and the interface Next.js; everything starts with one Docker command.
A live demo with sample data is open to everyone: ask a question and see which documents the answer is based on.
Highlights
- Answers with sources
- Local embedding model
- Semantic search with pgvector
- Live demo
Technology
- NestJS
- Next.js
- LangChain
- PostgreSQL + pgvector
- all-MiniLM-L6-v2
- Groq (gpt-oss-120b)
- Docker
Tell us what you want to build. We will come back within two working days with an approach and a first estimate.