just learned about this! the gpt keeps giving me images with colorer color crayons across the bottom even when i tell it no color? have you run into that?
Never ever include an api key (or any other secret) inside the code, it will be added to the repo. Best practice is to add secrets to an .env file and add the .env file to .gitignore.
Pleas add a lecture how to add different bots in one window. What I mean is: I have a selection of chatgpt agents/bots and would like to select the appropriate chatgpt bot
Hello, I would like to retrieve the cell output after %%ai magic run to write it to a file, preferably into xlsx. Could you help please. That is something like the output of the following command. %%ai chatgpt display a table with 5 rows and columns X, Y, Z, X is the row number. Y is a color and Z is its complementary color
hi AI Tube. Do you think Pandas AI is really a production ready thing? The consistency in the response for the most basic dataframe max value type question was too low to take it seriously. I was reading their documentation and with all the options like train/skills etc that are required to make any llm return consistent result simply defeats the purpose of using something like pandas ai. If I have to write all the functions upfront, I can use function calling features of open ai/llama 3. Anyways, pandas ai has potential, but maybe with proper funding/backing it can be something in a year. But right now the effort to make it production ready and consistent it needs the same amount of effort of a custom RAG based application. Am I completely off?
To anyone reading this: Was the video good? I got flash bangged at the begining, after 20 sec i opened my eyes and got flash bangged again so i scrolled down. Should probably get my sunglasses to watch it.
Is OpenAI's Assistant API totally different from the API to programmatically interact with Au Mistral, Gemini Pro, llama2 , etc? I'd like to prototype an OCR application using Custom GPT.. but is it possible to use Vision/Ai PDF plugin with the free account.. or would I need a ChatGPT4 subscription? BTW, I imagine there's a limit but I've seen some people use Google Colab to run models for free?! Ultimately, I'm interested in creating a Python application that uses AI.. from what I've read, I could use ChatGPT4 Assistant API and I as the developer would incur the cost whenever the app is used. Alternatively, I could host a model like Ollama, on my own computer or on the cloud (beam cloud/ Replicate/Streamlit/replit)? As a 3rd option, could Google Colab work in my situation?