Here's the simplest version of a copilot with aisingapore.org’s SEALION
https://aisingapore.org/aiproducts/sea-lion/

"Dude, I invented the friggin iPhone. Have you heard of it?" - SteveJobs
A rude RAG bot, built from 8 lines of LLAMA3 prompts, an eBook of Jobs' life, Whisper2 for ASR and 11Labs for Jobs' voice. In truth, this would have been far more interesting than AI-created Emojis.

Fireside chat facilitates reactions to PeoplePlus.AI and Nandan Nilekani Ai Summit on May 7 in Bangalore, India. This bot highlights our new Copilot Summary view, allowing copilot authors to aggregate and chart analysis of conversations. This bot runs analysis of every interaction using this script that's then consumed by a summarization script to summarize all the audience's questions.

Call the google search API with your own Serper.dev key and search the web. when using this function, remember to give citation URLs to the content you have used to answer the question

Compare Swahili Speech Recognition and Translation to English with this run. We have 10 variations in this. Including the latest Seamless M4T v2, MMS, Azure, Whisper v3 and more.

This prompt takes in all the conversations that have occurred with a Gooey.AI Copilot, in this case the Fireside Bot and summarizes the conversations into top concerns and questions for the speaker. It's then visualized here

Which language model works best your prompt? Compare your text generations across multiple large language models (LLMs) like OpenAI's evolving and latest ChatGPT engines and others like Curie, Ada, Babbage.

A comparison of small 2-10B LLM models on Hindi text using the best of LLaMA3, Gemma and Sarvam 2B

Compare prompts and outputs from the fine-tuned AFROLLaMA from Jacaranda Health