search

lablab-ai / community-content

https://lablab.ai/t
50 stars 40 forks source link

Gemini talk to images #439

Open Raghavan1988 opened 9 months ago

Raghavan1988 commented 9 months ago

Article on building an application that can talk to images in PDFs with Gemini Vision Pro

Leverage the power of Gemini Vision Pro and Spire to answer natural language questions based on images in PDF

Raghavan1988 commented 9 months ago

requesting review @ezzcodeezzlife @OlesiaZinchenko

Raghavan1988 commented 7 months ago

@DonGuillotine Thanks for the valuable comments. I made changes in line with your recommendation.

DonGuillotine commented 7 months ago

@DonGuillotine Thanks for the valuable comments. I made changes in line with your recommendation.

Hello @Raghavan1988,

Thank you so much for updating the tutorial,

I've noticed that some of the code snippets provided are incomplete, containing placeholders like # PDF processing code here.... Readers may not understand exactly what steps are required to process the PDFs, especially if they are beginners.

Kindly complete the Code Snippets, wherever placeholders are used provide the actual code that accomplishes the task described.

Also I noticed that in the working code you provided (your GitHub repository) you made use of trulens, consider adding a section in the tutorial that briefly introduces trulens and it's capabilities this will help the reader with more context.

Your tutorial is a valuable resource and these updates would greatly benefit the community. Great work so far 🥇