Viewing profile — tiagopavan

dspy approach seems rather similar to that: https://dspy.ai/tutorials/gepa_ai_program/

That's a great outcome. I was the producer of "The Edge of Democracy" - line 14047 of the Excel file with 200,000 hours viewed. Although we were nominated for an Oscar and became a…

There's an interesting stanford webinar covering this topic. It's what they call "Retrieval augmented in-context learning": https://www.youtube.com/watch?v=-lnHHWRCDGk

Thank you for your comment! I hadn't come across Qdrant before, but I will definitely check it out. Although I've been experimenting with milvus.io lately, these vector databases w…

Since the release of the gpt-3.5-turbo model by OpenAI, I have been wondering how companies are dealing with the token limit to gather insights from a large corpus of text without …