Build a RAG based chatbot with Claude, Gemini and Qdrant VectorDb

In this video, I am explaining the architecture to create a generic RAG (Retrieval Augmented chatbot) based LLM chatbot.
Then, we will use Gemini API and Claude API models to retrieve embeddings from a vector store.
Our vector store is Qdrant.

[@juanchopregogundin9031]

Nice video! I will try to experiment a little bit.

[@anirudhhosur3827]

All the best!

[@xXWillyxWonkaXx]

Hey, thanks for the video. Questio, why use Qdrant VectorDb? Why not use llamaindex? It's opensource and has many features

[@anirudhhosur3827]

This is like plug and play. You choose from different alternatives. I went with Qdrant because of Qdrant cloud.
This is my next video.
It has a great free tier.

[@Jash-w6f]

hey , can you share the diagram ?

[@anirudhhosur3827]

I did not save the diagram, I'm sorry 😢

[@manmohan_sharma]

Please share your resume

[@anirudhhosur3827]

Hi, I'm planning to make a video for this as well.