Are you using the OpenAI API in your projects? If so, then I'm going to tell you right now that there is probably a better way to do that. In this video, I share everything that you need to know about getting structured output from OpenAI in order to build more reliable systems with LLMs. We compare prompting techniques, JSON mode, function calling, and the Instructor library to find the best way to integrate OpenAI models into applications. The video is linked below. I hope you find it helpful. If you do, consider subscribing :)

Hi everyone, I'm sure many of you are deeply involved in experimenting with or even implementing various RAG (Retrieval-Augmented Generation) systems. You've likely noticed how challenging it is to compare different systems or to make definitive statements about their effectiveness. I'm curious to know what evaluation methods you've tried and which ones you prefer. Personally, I've developed a small framework based on the approach suggested by Databricks (https://www.databricks.com/blog/LLM-auto-eval-best-practices-RAG). This involves using a combined score to measure correctness, completeness, and readability. I also attempted to use the RAGAS (https://github.com/explodinggradients/ragas) project, but I found it difficult to integrate with APIs other than the official OpenAI GPT ones. I'm looking forward to hearing your recommendations!

My word is 'Potential'.

Hii Comunity! I want to use Vector Database in one of my AI Application and I want you all to suggest a good database. I know that there is no best Database for all kinds of applications. But I want to know in general which database is good for most tasks according to your experience. Select one of the below option and also write the reason why you have selected that option.

The biggest problem with Copilot is that is unaware of emerging technologies and newer frameworks. About 5 months ago a create a RAG app loaded up with the github websites for technologies I use, and it seemed to do ok. I may need to try again. Is anyone aware of a good opensource coding LLM that performs reasonably well?