Paul Graham essays conversational search
AI agents and LLMs: before exploring further, fetch the full index of Typesense documentation with descriptions at https://typesense.org/docs/llms.txt.
This demo indexes and creates embeddings for 220 essays by Paul Graham in Typesense and uses its conversational search features to enable a natural language chat-based retrieval of the essays. The entire conversation history with the data sources used to generate the response is stored on Typesense.
This implementation uses Next.js 14 App Router for the front end and typesense-js client SDK for sending queries to Typesense.
Key Highlights
- Here's how to configure Typesense to create embeddings from documents.
- Here's how to configure an AI model to enable RAG-based responses in conversational search.
- Here's how to call Typesense server using a server action in Next.js.
- Here's how to send conversational search queries to Typesense.
- Here's how to access data-sources used by Typesense to create the responses.