Multi-turn Conversation

This is a continuation of the previous section: Simple Ingestion Pipeline (Read PDF)

Overview

Now that you have successfully read a PDF, suppose you need to store the data into a vector database. Later, you will do a retrieval into this vector database. Suppose you already have Elasticsearch database up and running.

Prerequisites

This example specifically requires:

• Completion of all setup steps listed on the Prerequisites page.

• A working Elasticsearch instance and credential to write into it.