<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/45dbb0f182194f0e81321c38497d1766&quot; frameborder=&quot;0&quot; width=&quot;1554&quot; height=&quot;1165&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1165</height><width>1554</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1165</thumbnail_height><thumbnail_width>1554</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/45dbb0f182194f0e81321c38497d1766-1709187754903.gif</thumbnail_url><duration>692.411</duration><title>Testing and Evaluating LLM Applications</title><description>In this video, I will show you a good practice to test and evaluate your LLM application. By comparing the cosine distance metric to the referenced output, along with a table and a figure, you will be able to set up tests and generate a summarization report. I will demonstrate how to evaluate and test functions, use pytest and its plugins, save test execution bytes into a dataframe, and do post-processing to analyze and generate reports. No action is requested from viewers, but this information will help you understand the process better.</description></oembed>