GPT-4 Turbo with Google Web Browsing (Assistants API)

แชร์
ฝัง

ความคิดเห็น • 49

  • @RuXiangShiJia
    @RuXiangShiJia 8 หลายเดือนก่อน +6

    One way to reduce the costs of input tokens to better models while still getting good answers/summaries:
    1) Ask a cheaper model like gpt-3.5-turbo-0125 to "compress" the contents of the web page using minimal tokens while preserving information such that a GPT can reconstruct the page later.
    2) Give this compressed version to a higher quality model like gpt-4 and ask it to reconstruct the original data using the compressed data.
    I have gotten up to a 5x savings on total token costs in some cases - the drastically reduced input token costs to the better model makes up for the cost of compression.

  • @WeylandLabs
    @WeylandLabs ปีที่แล้ว +5

    Reading your thumbnail and understanding it from a professional perspective, then looking at it from a consumers perspective. They have no idea what your even saying because they cannot comprehend the tech yet and how it will change the future. When people start to understand so many things will change !

  • @toapyandfriends
    @toapyandfriends 8 หลายเดือนก่อน +2

    Can you add code examples

  • @toapyandfriends
    @toapyandfriends 8 หลายเดือนก่อน +1

    Thanks very much for this. I'm taking this tomorrow

  • @angel1st007
    @angel1st007 ปีที่แล้ว +3

    @all about ai - any chance to get the sources you made in the scope of the video?

  • @Ikerposcaart
    @Ikerposcaart ปีที่แล้ว +5

    Please the code ?

  • @LauraForsblom
    @LauraForsblom 9 หลายเดือนก่อน +1

    Are you using the assistant in the code besides creating it? It looks like you'r just fetching the data and then using the chat api for passing it.

  • @khariclemens
    @khariclemens ปีที่แล้ว +1

    I’d like to use this to scrape more detailed results. For example: search for restaurants in my area, scrape the menus and return in my set json structure.

  • @Nick-Quick
    @Nick-Quick ปีที่แล้ว

    00:01 Sam Alman fired from open AI in open AI Saga.
    01:27 GPT-4 Turbo with Google Web Browsing combines user query and website context to generate accurate responses.
    02:49 The first function is to convert user input into a Google search query using GPT-4 Turbo.
    04:08 Creating an assistant with Google GPT that can fetch and display news articles based on user queries
    05:34 The video demonstrates the usage of GPT-4 Turbo with Google Web Browsing (Assistants API)
    06:56 Scraping websites using the function does not work in this playground
    08:22 Max Verstappen won the Las Vegas F1 Grand Prix.
    09:46 GPT-4 Turbo with Google Web Browsing (Assistants API)

  • @randotkatsenko5157
    @randotkatsenko5157 ปีที่แล้ว +1

    @All About AI - I have a video ideas for you.
    So, I tested the new gpt4 turbo version for creating websites - its very good, but requires lots of going back and forth with prompting and providing images of results, in order to get the final working version.
    IDEA - make a Python scrip that automatically goes through all of the steps of website coding -> then shows the results to the gpt vision after every revision -> makes adjustments -> loop it until its excactly like the provided website design.
    You already created a similar agent for images.
    I would pay for such a working script, although I might do it if no-one else does.

  • @khariclemens
    @khariclemens ปีที่แล้ว +1

    Also, thank you for making this. I’ve been wanting to use Google results ever since they removed the capability.

    • @AllAboutAI
      @AllAboutAI  ปีที่แล้ว

      cool no problem :D

  • @iddoshemtovv
    @iddoshemtovv ปีที่แล้ว +1

    nice "perplexity" example haha, thanks brother!

    • @AllAboutAI
      @AllAboutAI  ปีที่แล้ว

      true :p tnx for tuning in!

  • @matthummel1279
    @matthummel1279 9 หลายเดือนก่อน

    Do you think this can be used to help optimized outputs from Api Assistant? So basically somehow use google search to optimize the api assistant's knowledge and deliver better outputs?

  • @leojax3275
    @leojax3275 ปีที่แล้ว

    your code creates a new assistant each time its run. i think after creating it you should use threads instead of creating a new instance each time. That said, this tutorial was very helpful. Thank you very much.

  • @kanandnaik5677
    @kanandnaik5677 5 หลายเดือนก่อน

    I joined this membership, how can I access the Git repository? Please guide me.

  • @CodeMom
    @CodeMom ปีที่แล้ว +1

    Wow 🤩 can’t wait to try this!

  • @getgonged
    @getgonged ปีที่แล้ว +1

    This was great. Awesome use case. I'm interested in that concurrent function calling you mentioned too.

    • @AllAboutAI
      @AllAboutAI  ปีที่แล้ว +2

      will make that vid soon :)

    • @wes7bg
      @wes7bg ปีที่แล้ว

      @@AllAboutAI if you add your code in git more people will follow

  • @blazpregelj8252
    @blazpregelj8252 9 หลายเดือนก่อน

    Great explanation. Thank you for this, much appreciated

  • @akhiltesla8707
    @akhiltesla8707 ปีที่แล้ว +2

    Please make a complete guide on function calling

  • @ChatGPT-5.0
    @ChatGPT-5.0 ปีที่แล้ว

    But the scrapped textual data are a lot I don't think a single query of openai ai will handle it. So what did you do with that?

  • @freddiechipres
    @freddiechipres ปีที่แล้ว

    This is basically what perplexity does?

  • @kashishvarshney2225
    @kashishvarshney2225 ปีที่แล้ว

    can we add api to it

  • @peterkuria2000
    @peterkuria2000 ปีที่แล้ว

    Awesome demo, can you kindly share the code?

  • @micbab-vg2mu
    @micbab-vg2mu ปีที่แล้ว +2

    thank you :)

  • @kavikaz
    @kavikaz ปีที่แล้ว +1

    I along with many others in the Discord have not been provided access to the Github repo with example code. Very concerning. Please beware when signing up...

  • @dieter6375
    @dieter6375 ปีที่แล้ว

    Could you clarify how you integrate the assistant API or function calling in your code? It appears you're only using standard chat completion for creating search queries and generating responses ;)

    • @AllAboutAI
      @AllAboutAI  ปีที่แล้ว +1

      yeah will do more vids on this :)

  • @kashishvarshney2225
    @kashishvarshney2225 ปีที่แล้ว

    how can I get this whole video code

  • @xsploit
    @xsploit ปีที่แล้ว +1

    I basically did tge samething using serper api and made kind of a private investigator

  • @abenjamin13
    @abenjamin13 ปีที่แล้ว +1

    LOVE ❤️ IT ✅

  • @tlwebdesign1
    @tlwebdesign1 ปีที่แล้ว

    How can I get gpt to write full novel 300 plus pages?

    • @yoagcur
      @yoagcur ปีที่แล้ว

      Give it a $100,000 advance

  • @Leo991624
    @Leo991624 ปีที่แล้ว

    Jesus didn’t say: “Love your enemies in the form of people and don’t love your enemies in the form of non-living things, machines (and so on)”, he simply said “Love your enemies”, which means this also applies to potentially possible superintelligent AI

  • @МаксимГоранков
    @МаксимГоранков 4 หลายเดือนก่อน +1

    it's absolutely useless without code source. Membership gives you nothing

  • @nic-ori
    @nic-ori ปีที่แล้ว +1

    👍👍👍

  • @pitpatgazorpazorp3356
    @pitpatgazorpazorp3356 ปีที่แล้ว +1

    I mean, this is interesting, but how is this any better or beneficial than what I can do on native ChatGPT? maybe im retarded

    • @AllAboutAI
      @AllAboutAI  ปีที่แล้ว

      It is just way more customable and controll over output/format:)

  • @BrightMatolo
    @BrightMatolo ปีที่แล้ว

    •/° I believe we are meant to be like Jesus in our hearts and not in our flesh. But be careful of AI, for it is just our flesh and that is it. It knows only things of the flesh (our fleshly desires) and cannot comprehend things of the spirit such as peace of heart (which comes from obeying God's Word). Whereas we are a spirit and we have a soul but live in the body (in the flesh). When you go to bed it is your flesh that sleeps but your spirit never sleeps (otherwise you have died physically) that is why you have dreams. More so, true love that endures and last is a thing of the heart (when I say 'heart', I mean 'spirit'). But fake love, pretentious love, love with expectations, love for classic reasons, love for material reasons and love for selfish reasons that is a thing of our flesh. In the beginning God said let us make man in our own image, according to our likeness. Take note, God is Spirit and God is Love. As Love He is the source of it. We also know that God is Omnipotent, for He creates out of nothing and He has no beginning and has no end. That means, our love is but a shadow of God's Love. True love looks around to see who is in need of your help, your smile, your possessions, your money, your strength, your quality time. Love forgives and forgets. Love wants for others what it wants for itself. Take note, true love works in conjunction with other spiritual forces such as patience and faith (in the finished work of our Lord and Savior, Jesus Christ, rather than in what man has done such as science, technology and organizations which won't last forever). To avoid sin and error which leads to the death of our body and also our spirit in hell fire, we should let the Word of God be the standard of our lives not AI. If not, God will let us face AI on our own and it will cast the truth down to the ground, it will be the cause of so much destruction like never seen before, it will deceive many and take many captive in order to enslave them into worshipping it and abiding in lawlessness. We can only destroy ourselves but with God all things are possible. God knows us better because He is our Creater and He knows our beginning and our end. Our prove text is taken from the book of John 5:31-44, 2 Thessalonians 2:1-12, Daniel 7-9, Revelation 13-15, Matthew 24-25 and Luke 21. Let us watch and pray... God bless you as you share this message to others.

    • @Leo991624
      @Leo991624 ปีที่แล้ว

      Jesus didn’t say: “Love your enemies in the form of people and don’t love your enemies in the form of non-living things, machines (and so on)”, he simply said “Love your enemies”, which means this also applies to potentially possible superintelligent AI

  • @klammer75
    @klammer75 ปีที่แล้ว +1

    Awesome work Kris! Parallel function calling please!🤩🥳🦾

    • @AllAboutAI
      @AllAboutAI  ปีที่แล้ว

      thnx ;D yes coming soon