I meant to comment this earlier, but as @Ben_H helped me identify there is still an issue in my above code. The easiest way to implement this with both filters and history is to use the repo @jiayi-wu directed me to while debugging this. Hope that he...
@s-udhaya and @jiayi-wu really excellent work, thank you for the write up.
@Ben_H good question and thank you for providing your code. I used your above in place of the existing chain in the Chat History Extractor Chain command of the llm-rag-chatbo...
Hi @MaheshPS, great question, if not a little abstract. There are probably as many ways to measure the ROI of using DBRX as there are use cases for it, but let's try to focus on some more concrete examples.
If you use DBRX as part of an internal kno...
Hi @Kk17 , it really depends on what you value most. If you value leaderboard scores and model output quality above all else, then GPT-4 is generally the stronger of the two models. However, GPT-4 also costs nearly $40 per million tokens, your reques...
Image to text is not currently available as a native model in Databricks, but we did recently release Shutterstock ImageAI, powered by Databricks for text to image capabilities. To learn more about that, please see the related blog post from June.
I...
