I have a document which I want to vectorize and then ask multiple prompts to it. I am expecting a natural language text generation rather than doing a cosine similarity to find the matching sentence vectors.
RAG systems generally find the most similar sentences. Do they generate free text also, which models like GPT, LLAMA etc doing by sending a prompt?
Example: I created embeddings for a existing story. Now text is deleted and I just have embeddings . Now I want to ask following prompts to it:
- Extend the story by writing more innovative ideas.
- what was relation between person a and person b in the story.
