Gemini 1.5 API: Chat with Videos, Images and Audios in your app (Gemini API Code tutorial)

Enric Domingo - AI Engineering · Beginner ·🧠 Large Language Models ·1y ago
Tutorial exploring the basics of the new Google Gemini 1.5 Pro and Flash models, how they compare to the OpenAI GPT-4o and GPT-4 Turbo, how to get the Google API Key, how to send requests to the Gemini API, and chatting with all kinds of files (videos, images, audios, etc.). Finally, we implement the Gemini 1.5 API models to the OmniChat App, a custom Streamlit Python webapp chatbot that we started developing on my last video in order to use GPT-4o from the OpenAI API with images and text. Blog: https://medium.com/@enricdomingo/how-i-add-gemini-1-5-pro-api-to-my-app-chat-with-videos-images-and-audios-f42171606143 Code Repo: https://github.com/enricd/the_omnichat App: https://the-omnichat.streamlit.app Previous video (GPT-4o API Streamlit app): https://www.youtube.com/watch?v=7i9j8M_zidA Timeline: 00:00 - Intro to Gemini 1.5 2:23 - How to use the Gemini API 5:30 - Adding images to the prompt 11:26 - Gemini 1.5 into our chatbot webapp 25:20 - Pushing to GitHub and deploying the app online 27:40 - Testing video prompts Subscribe to see more AI and ML programming related content! 🚀🚀 ------------------------------------------------------------- Kaggle: https://www.kaggle.com/edomingo GitHub: https://github.com/enricd Twitter: https://twitter.com/mad_enrico Linkedin: https://www.linkedin.com/in/e-domingo/ Medium: https://medium.com/@enricdomingo Web: https://enricdomingo.com #gemini #google #geminiapi #googlegemini #gemini15 #geminipro #geminiflash #gpt #gpt4o #gpt4 #openai #promptengineering #chatgpt #openaiapi #python #streamlit #github #cloud #portfolio #agent #gpt #aiagents #automation #ai #streamlit #llm #copilot #chatgpt4o #omnichat #omnidata #howtochatgpt #github #git #vscode #gui #pythongui #stream #modelstream #streaming #llmstream #llmstreaming #openaistream #openaistreaming
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

When one translation isn't enough: building konid for real language
Learn how to build a more nuanced translation tool, konid, to better capture the subtleties of language and tone
Dev.to AI
Big Tech firms are accelerating AI investments and integration, while regulators and companies focus on safety and responsible adoption.
Big Tech firms are investing billions in AI, focusing on safety and responsible adoption, which is crucial for the future of artificial intelligence
Dev.to AI
Ever wonder how AI actually works?
Learn how AI works through interactive mini-games, no coding required, and understand AI decision-making in just 10 minutes per topic
Dev.to AI
Why AI Content Systems Need Human Oversight: A Practical Workflow Breakdown
Learn why AI content systems require human oversight and how to implement a practical workflow breakdown for reliable content generation
Medium · LLM

Chapters (6)

Intro to Gemini 1.5
2:23 How to use the Gemini API
5:30 Adding images to the prompt
11:26 Gemini 1.5 into our chatbot webapp
25:20 Pushing to GitHub and deploying the app online
27:40 Testing video prompts
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →