This project implements a cloud-based GenAI pipeline using Langflow and AstraDB to create a Retrieval-Augmented Generation (RAG) system that answers user queries based on a dataset of FAQs.
- Ingest unstructured text data (FAQ CSV file)
- Vectorize the data using OpenAI embeddings
- Store and manage vector data in AstraDB
- Build a RAG workflow using Langflow
- Enable natural language queries and contextual responses
- Deploy and test on the Datastax AI PaaS platform
- 🔁 Langflow – No-code visual framework for LLM workflows
- 🧠 OpenAI – Used for both embeddings and language generation
- 🧲 AstraDB – Vector-enabled cloud-native database
- 📝 CSV – Dataset format
- 🐍 (Optional) Python – For alternative ingestion method