From the course: Level up LLM applications development with LangChain and OpenAI

Unlock the full course today

Join today to access over 24,400 courses taught by industry experts.

Set up query analysis to handle multiple data sources

Set up query analysis to handle multiple data sources

From the course: Level up LLM applications development with LangChain and OpenAI

Start my 1-month free trial Buy for my team

Set up query analysis to handle multiple data sources

“

- [Instructor] Previously, we created indexes to handle multiple data source. Now, we're going to see how to handle multiple data sources. And for that, we're going to set up Query analysis which will be in charge of handling multiple data sources and then select which data source, which retriever, to use. And in the setup, we're going to use function calling which is used to tell to give the language models the ability to make decisions based on the user query and based on the context. We're going to use function calling to structure the output which will return multiple queries. And that's going to serve as an input, as specific information for the next generation task. We're going to see that more in details later. We're going to use here a class to define how the output should be structured, formatted. For every output generated, by using function calling, we're going to specify the query to indicate the question asked by the user and also the person who is targeted in the user…

Contents