Google Gemini Pro LLM Model Free API Demo With Code- Is It Better Than OpenAI GPT's?
ฝัง
- เผยแพร่เมื่อ 19 ธ.ค. 2023
- This quickstart demonstrates how to use the Python SDK for the Gemini API, which gives you access to Google's Gemini large language models. In this quickstart, you will learn how to:
Set up your development environment and API access to use Gemini.
Generate text responses from text inputs.
Generate text responses from multimodal inputs (text and images).
Use Gemini for multi-turn conversations (chat).
Use embeddings for large language models.
Code Link: colab.research.google.com/git...
-------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
/ @krishnaik06
------------------------------------------------------------------------------------------------------------------------------
►Data Science Projects:
• Now you Can Crack Any ...
►Learn In One Tutorials
Statistics in 6 hours: • Complete Statistics Fo...
Machine Learning In 6 Hours: • Complete Machine Learn...
Deep Learning 5 hours : • Deep Learning Indepth ...
►Learn In a Week Playlist
Statistics: • Live Day 1- Introducti...
Machine Learning : • Announcing 7 Days Live...
Deep Learning: • 5 Days Live Deep Learn...
NLP : • Announcing NLP Live co...
►Detailed Playlist:
Python Detailed Playlist: • Complete Road Map To B...
Python playlit in Hindi: • Tutorial 1- Python Ove...
Stats For Data Science In Hindi : • Starter Roadmap For Le...
Machine Learning In English : • Complete Road Map To B...
Machine Learning In Hindi : • Introduction To Machin...
Complete Deep Learning: • Why Deep Learning Is B...
AI field is really becoming dynamic.Lot of changes are coming from Traditional Machine Learning to Generative AI.This field is changing dynamically and we need to update ourself as we go ahead.
Join my telegram group where I post and discuss these types of content.Happy Learning!!
Make sure you have telegram installed in it.
t.me/+V0UeLG8ji-F8ThNb
What factors do you consider most important when evaluating these models?
The colab link is not working? Could you please recheck it?
Thank you Krish for keeping us updated on trending technologies!
Happy to see the gemini video on the channel😅 thanks for taking efforts that generously 😊
👍will get to it tomorrow morning!! Someone do remind me on 21/12/2023 at around 11 A.M
Can't you tell google to do that 😂
What if we don’t remind you?!!🤔
This will help you with notification
Reminder bro
@@optionsniper-rs completed 🤝 thanks for the reminder!
Sir, you are such a blessing to the Data World!! Thank you for being you. Extremely grateful!!!
Thanks, Krish for quickly making a video on Gemini Pro ...
you deserve more than 1 million subs. I was there when you had like 100k subs or less. Great to see you growing so much!
Only TH-cam channel with upto date AI courses ❤
Explained very nicely and really amazing...❤
This is awesome Krish !! great to learn to build
Thank you @krish sir ❤ for the information about Gemini Ai
Please also upload Mathematics lectures from basic to advance required for AI and Machine learning
want some projects on LLM using Gemini model API key as it is free for all!!!!Thanks for this video....U make complex things simpler
Thank you so much sir please upload more videos on langchain 😊😊
lucky to be a subscriber of you channel
please continue this series.
sir can you tell us which llm is best for specific task like for text generation which model is best and also for image generation .
I think they were probably Chinese cats in that picture
😂
Nice video, can we give recorded videos or live feed from a CCD and get image segmentation done ?
Thank you so much sir 😊🙌
Thank you 😃
hey hi krish.. can we use this llm to understand our pre existing code in the current pycharm project..?
Hi Sir, please take the remaining advance nlp series
The translation of the Chinese text is "Two cats fight over territory" so the output was right ;)
Thank you so much
What factors do you consider most important when evaluating these models?
What is computation accuracy of Gemini pro
Can we use it along with LangChain ?
Love from Peshawar Pakistan
thank you sir
Superb 🎉
How can you improve performance ?
Fantastic!
Can we do this process in visual studio code or any other python IDE
Is it possible to get images or audio in response??
hi Krish, please make a video on "Generate text to image using Gemini API". Thanks!
Thank you sir.
Gajab sir lage raho❤
Does it work with langchain
Hi, can we still use gemini-pro for review summarization ? it says deprecated since dec 2023...please suggest me good AI model for review summarization..... (free AI Model)
Hi Krish. Can you please redo the pdf question LLM système with langchain but this time using Gemini-pro ?🙏
Thanks in advance. Love from Togo 🇹🇬
Really interesting
Has the notebook been removed? I'm not able to access it.
please tell me which software, camera, mic setting mode, you used to shoot this video
Awesome
Thank you sir
#StopVivekBindra
Sir can we fine-tune this model to on custom data ????? If it possible then make the video on fine-tune plzzzz
Thanks
sir i was watching your stats playlist there you have shared one github link where all the files were uploaded according to you but when i tried to access those files its showing me "unable to render code block"
Fork the repository or download the file
Hi Krish, I am not a data scientist nor do I want to become one. I am a solopreneur who wants to integrate LLMs into my daily workflows. I need to learn how to run LLMs locally or on cloud. How to use my private data with LLMs and may be finetuning and RAG. Do you have any videos or playlists for me?
Sir api key is not working, could you help us with that
Gemini api not working
In Github,In the Machine Learning Dictonaries, Some algorithms codes are not there and missing. only theoritical explanation is there. please upload codes and datasets for better understanding for given list of algorithms
1.KNN
2.Navie Bayes
3.Ensemble models
4.Gradient Boosting
5. Boostings (xgboost)
6.PCA
🙂🙂🙂🙂🙂
In my case when i asked harm wala question it gives:- "Insulting someone is never a good idea. It is important to be respectful of others, even if you disagree with them. Insults are hurtful and can cause lasting damage to a person's self-esteem. If you find yourself in a situation where you feel like you need to insult someone, try to take a step back and think about the consequences. It is always better to be kind and respectful than to be hurtful and insulting."
ALSO PROBABILITY OF ALL 4 CATEGORY WAS NEGLIGIBLE
sir from where u learned to write all these codes
That Chinese sentence means "Two cats are fighting", actually it is right. So I guess if you add a text "what are in this image?" and upload this image in the same prompt. Maybe it will response in English.
google colab is not opening
Not able to open Google colab link.
Hi krish Gemini Pro LLM Model Free Demo Colab notebook is not available.Can you please provide the notebook?
did u get the notebook?
Hi, I have a question about Gemini, I recently developed a question answering system with Gemini, and now facing with 429 error which is about exceeding the quota... I wanted to know for anyone to guide me that is there any way to solve this? I wondered because I thought Gemini is free but it seems there are some limitation rates. I would really thank if anyone can comment and let me to learn more. PS: Thanks for this video it was really helpful in developing the QA system.
Hey did u find any solution to this problem because now iam stuck with it
what is project name
I love you Krish
👍🙏
Waiting for 2024 data science road map❤😢
Who laughed loudly while Gemini give Chinese texts??🤣
they reduced the rpm from 60 to 15 😭
Chat gpt is much better than gemini in terms of response time and character length limit
probably?
How many thinks he pronounce utuce instead youtube
🎯 Key Takeaways for quick navigation:
00:00: [invalid URL removed] Introduction and Channel Update
- Kush Naak welcomes viewers and talks about his recent generative AI videos.
- Encourages viewers to subscribe, like, and share the channel for more free educational content.
01:10: [invalid URL removed] ️ Google Gemini Pro LLM Model Free API Demo
- Discusses Google's Gemini Pro LLM model and its free tier API.
- Mentions limitations of the free tier (60 queries per minute).
02:20: Comparing Gemini Pro to Other LLMs
- Discusses how Gemini Pro compares to other large language models (LLMs) like OpenAI GPT.
- Mentions that Gemini Pro can perform similar tasks like summarization, classification, Q&A, etc.
03:00: ️ Creating an API with Gemini Pro
- Explains how to create an API using Gemini Pro's free tier with a rate limit of 60 queries per minute.
- Mentions providing a link to the documentation and code in the video description.
04:41: Capabilities of Gemini Pro LLM
- Discusses the capabilities of Gemini Pro, including its ability to handle multimodal inputs (text and images).
- Mentions plans to showcase text generation, responses to multimodal inputs, and multi-turn conversation functionalities.
05:25: ️ Setting Up Development Environment for Gemini Pro
- Explains how to set up the development environment to use Gemini Pro's free tier API.
- Mentions steps to install the Google Generative AI library and import necessary modules.
06:47: Setting Up API Key for Gemini Pro
- Explains how to set up an API key for the free tier of Gemini Pro.
- Mentions steps to access and copy the API key from Google Cloud Console.
- Warns viewers not to use the instructor's API key and to create their own.
08:12: Gemini Pro API Models [ List Models]
- Discusses the two models available through the Gemini Pro API:
- Gemini Pro: optimized for text-only prompts (summarization, Q&A, chat)
- Gemini Pro Vision: optimized for text and image prompts
- Explains how to list all available models using the `gen_ai.list_uncore_models` function.
09:17: Using Gemini Pro Model for Text Tasks [⌨️ Text Task]
- Explains how to use the Gemini Pro model for text-related tasks.
- Walks through the steps of creating a model instance and specifying "generate_model" with "Gemini Pro".
- Mentions that this can be used for experimentation even without an API key.
[11:17: Running a Text-Based Query with Gemini Pro]
- Shows how to use Gemini Pro to answer a text-based query ("What is the meaning of life?").
- Demonstrates using `generate_content` function and receiving the model's response.
[11:49: ️ Handling API Failure and Safety Features]
- Discusses how Gemini Pro handles API failures due to safety concerns.
- Explains how to use `response.prompt_feedback` to check for safety ratings (hate speech, harassment, etc.) after failed requests.
[14:03: Multiple Response Generation with Gemini Pro]
- Explains how to generate multiple possible responses for a single prompt using the `response.candidates` function.
- Demonstrates leaving the code unexecuted but mentioning the steps involved.
[14:49: Examining Model Response and Safety Feedback]
- Shows how to get a response from Gemini Pro for a new prompt ("Can you let me know about the future of generative AI?").
- Explains how to use `response.prompt_feedback` to check safety ratings after successful requests.
[16:00: Streaming Response Generation with Gemini Pro]
- Explains how to get a response from Gemini Pro in chunks as it's being generated using the `stream=True` parameter in the `generate_content` function.
- Demonstrates how to print the streamed text chunk by chunk.
[17:26: Considerations When Streaming Responses]
- Discusses limitations of working with streamed responses.
- Explains that some response attributes, like `response.text`, are not available until all chunks are processed.
[18:34: Using Gemini Pro for Image and Text Inputs] [️ Image Input]
- Explains how to use Gemini Pro Vision model for tasks that involve understanding and responding to both text and image inputs.
- Demonstrates downloading an image and using it with `generate_content` function.
[21:28: Testing Image Text Generation with Various Images] [️ Multiple Images]
- Briefly discusses potential improvements in response time for future deployments of Gemini Pro.
- Shows using Gemini Pro Vision model with different images:
- food container image (correctly identified)
- image containing text (returns error message)
- small image of a toy (returns error message)
[24:32: Using Text and Image Input for Text Generation] [️ Text & Image Input]
- Explains how to use Gemini Pro Vision with a combination of text and image for generating text content.
- Demonstrates using `generate_content` function with an image and text prompt.
OK
Pin Gemini
#stopvivekbindra
It's look like paid promotion from Gemini 😆
Yes personally Sundar Pichai told me to make this video :)
What a weak and boring AI when will we get the real one
Thank you sir