🏃‍♀️

Jump right in by Creating an Application and Uploading the Data

Use Case Background

The data in this tutorial originates from a classic Retrieval Augmented Generation bot that answers questions about the GVHD medical condition. We're evaluating a GPT-3.5 LLM-based app that uses FAISS for the retrieval embedding vectors.
The knowledge base is built from a collection of online resources about the GVHD condition, and fictional data generated by chatGPT about a GVHD institute that provides medical support and appointments.
The differences between the two evaluated versions arise from the amount of data provided to the RAG application. Version v2 was given more information, resulting in better performance. Therefore, the second version was then deployed to production.

📘

Click here to Download the Demo Data

Structure of this Example

• Start by Creating an Application and Uploading the Data , with Deepchecks' SDK or UI
• Then Explore different flows in the System, to see the automatic annotations, problem identification, version comparison capabilities and more.