![Samer Haddad](/img/default-banner.jpg)
- 50
- 32 095
Samer Haddad
United Arab Emirates
Registrace 8. 06. 2006
👋 Hi, I'm Samer, here to make AI and tech accessible for everyone! a tech enthusiast with a will to learn by doing and teach by showing!
💡 Join me on a journey beyond the code as we unlock the power of today's most disruptive technologies using No-code/Low-code solutions. 🚀
✨ I focus on user-friendly tools, simplifying Large Language Models (LLMs), AI products, and the magic of creating without coding “well sometimes 😅”.
My videos make complex tech practical and accessible for all.
🔔 Subscribe and be part of the Give Me The Mic community, where we turn curiosity into creation. Let's harness innovation together!
🌐 Embrace the tech revolution with Give Me The Mic!
💡 Join me on a journey beyond the code as we unlock the power of today's most disruptive technologies using No-code/Low-code solutions. 🚀
✨ I focus on user-friendly tools, simplifying Large Language Models (LLMs), AI products, and the magic of creating without coding “well sometimes 😅”.
My videos make complex tech practical and accessible for all.
🔔 Subscribe and be part of the Give Me The Mic community, where we turn curiosity into creation. Let's harness innovation together!
🌐 Embrace the tech revolution with Give Me The Mic!
Master Zapier Sub-Zaps: Step-by-Step Guide
In this video, we delve into the concept and application of Zapier's sub-zaps, a feature designed to boost automation efficiency. Learn how sub-zaps can simplify recurring tasks by creating reusable automation steps. We demonstrate practical examples, including parsing JSON data from Perplexity searches and cleaning it for further use, as well as deleting files from Google Drive and ChatGPT to maintain storage efficiency. The video also shows how to integrate sub-zaps into more complex automations, such as creating AI-related blog posts on Shopify. Towards the end, we guide you through building a simple email-sending sub-zap from scratch. Don't forget to like, subscribe, and share your sub-zap experiences and suggestions in the comments!
💬 Let me know what you think of this video in the comment section below.
✨ And don’t forget to subscribe to the Channel!
www.youtube.com/@GiveMeTheMic22?sub_confirmation=1
********************
🗂 Relevant Links to the video:
🔸 Scraping Video: czcams.com/video/wM1XsrfzZdc/video.html
🔸 Custom Actions Video: czcams.com/video/rSvi3lmqsbw/video.html
********************
🌐 Join me at Give Me The Mic - where tech meets tenacity! I'm Samer, a fellow non-coder on a quest to master Low-Code/No-Code solutions and AI, empowering you to build and innovate fearlessly. 🚀
💡 Discover tools that simplify technology, as I learn and share ways to create and optimize without writing a line of code or at least learning how AI can do it for us. It's about making tech work for us, the non-coders.
🖥️ Subscribe for a journey into the accessible side of automation and AI, where we translate tech buzz into real-world applications.
🔔 Let's decode the tech talk and craft the future together. Hit subscribe, and let's get started with Give Me The Mic!
********************
📲 Let’s Connect! Follow me on social media and subscribe to my Newsletter:
My Website! ➡️ givemethemicofficial.com/
My GPTs Page! ➡️ givemethemicofficial.com/pages/gpts
********************
⏰ Chapters:
00:00 Introduction to Zapier Sub Zaps
00:57 Explaining Sub Zaps Concept
01:43 Example: Perplexity Search Sub Zap
04:27 Example: File Deletion Sub Zap
05:59 Using Sub Zaps in Automation
09:03 Creating a New Sub Zap
11:49 Setting Up Sub Zap Inputs
12:10 Adding Email Action to Sub Zap
12:44 Configuring Sub Zap Output
14:29 Conclusion and Call to Action
********************
#GiveMeTheMic #Zapier #Automation #SubZaps #TechTutorial #Efficiency
********************
FileName: GMTM169
💬 Let me know what you think of this video in the comment section below.
✨ And don’t forget to subscribe to the Channel!
www.youtube.com/@GiveMeTheMic22?sub_confirmation=1
********************
🗂 Relevant Links to the video:
🔸 Scraping Video: czcams.com/video/wM1XsrfzZdc/video.html
🔸 Custom Actions Video: czcams.com/video/rSvi3lmqsbw/video.html
********************
🌐 Join me at Give Me The Mic - where tech meets tenacity! I'm Samer, a fellow non-coder on a quest to master Low-Code/No-Code solutions and AI, empowering you to build and innovate fearlessly. 🚀
💡 Discover tools that simplify technology, as I learn and share ways to create and optimize without writing a line of code or at least learning how AI can do it for us. It's about making tech work for us, the non-coders.
🖥️ Subscribe for a journey into the accessible side of automation and AI, where we translate tech buzz into real-world applications.
🔔 Let's decode the tech talk and craft the future together. Hit subscribe, and let's get started with Give Me The Mic!
********************
📲 Let’s Connect! Follow me on social media and subscribe to my Newsletter:
My Website! ➡️ givemethemicofficial.com/
My GPTs Page! ➡️ givemethemicofficial.com/pages/gpts
********************
⏰ Chapters:
00:00 Introduction to Zapier Sub Zaps
00:57 Explaining Sub Zaps Concept
01:43 Example: Perplexity Search Sub Zap
04:27 Example: File Deletion Sub Zap
05:59 Using Sub Zaps in Automation
09:03 Creating a New Sub Zap
11:49 Setting Up Sub Zap Inputs
12:10 Adding Email Action to Sub Zap
12:44 Configuring Sub Zap Output
14:29 Conclusion and Call to Action
********************
#GiveMeTheMic #Zapier #Automation #SubZaps #TechTutorial #Efficiency
********************
FileName: GMTM169
zhlédnutí: 14
Video
Working with AI Text to Image Models: A Beginner's Guide - SDXL and Flux.1
zhlédnutí 40Před 21 hodinou
In this video, we explore the power of AI models in generating high-quality CZcams thumbnails. From discussing the capabilities of Stable Diffusion and Flux to demonstrating how to use no-code or low-code solutions, this video covers everything you need to simplify your thumbnail creation process. Learn how to set up the necessary environments, train models using Google Colab, and leverage plat...
How to Manage your AI APIs Like a Pro! with Airtable - for Zapier, Make or even code
zhlédnutí 32Před 14 dny
In this video, we delve into the challenges of organizing AI API calls and AI prompting within applications or automations, focusing on platforms like Zapier and Make. Discover an efficient solution using Airtable for centralized management, which simplifies the update and management of AI automations without the need for manual modifications. We'll guide you through the setup of an Airtable da...
How to Automate Email Validation with Zero Bounce and Zapier
zhlédnutí 90Před měsícem
In this video, we introduce Zero Bounce, an efficient email validation tool seamlessly integrated with Zapier, perfect for automating email validation without the need for API calls. We walk you through how to link Zero Bounce with Zapier to validate email addresses, focusing on Shopify customers. The Zero Bounce dashboard is demonstrated, showcasing its user-friendly interface, initial perform...
Automate Your Script Writing with Notion and Perplexity - Zapier simple version
zhlédnutí 478Před měsícem
In this video, I share my personal automation system for content creation, powered by Notion, Zapier, and Perplexity AI. Learn how I manage and streamline video ideas from ideation to publishing, ensuring an efficient workflow. See how Notion databases are automatically updated, how Zapier integrates seamlessly, and how Perplexity AI aids in research for generating scripts. I also demonstrate h...
The ONLY video you need to watch: Zapier vs Make Automation
zhlédnutí 261Před měsícem
In this video, we dive deep into the comparison between @Zapier and @itsmake (formerly Integromat) for automation. Having extensively used Zapier for a year, I recently explored Make.com to evaluate its capabilities. We cover key aspects such as user interface, cost, scalability, and functionalities. 💬 Let me know what you think of this video in the comment section below. ✨ And don’t forget to ...
2024 - Create custom Zapier actions in 10 minutes!
zhlédnutí 68Před měsícem
In this video, we dive deep into the world of custom actions in Zapier, showcasing their underappreciated value and how they can revolutionize your workflow automation. We'll start by explaining how to access the custom actions page and what custom actions are. Using examples like CZcams and Shopify, we'll demonstrate how custom actions can automate repetitive tasks such as deleting customers o...
I Built My 1st AI SaaS: What I Learned & Why I will Kill It?
zhlédnutí 199Před měsícem
In this video, we explore the creation of 'HireGate AI', a SaaS product designed to optimize CVs for job applications. This project was built using a no-code stack with Webflow for the frontend, Xano for the backend, and Wized for middleware. 💬 Let me know what you think of this video in the comment section below. ✨ And don’t forget to subscribe to the Channel! www.youtube.com/@GiveMeTheMic22?s...
How To AUTOMATE Your Business in 2024 (Step by Step)
zhlédnutí 51Před 2 měsíci
In this video, we simplify and enhance the process of automating your business operations using Zapier Canvas. Catering to solopreneurs, agency owners, and consultants, we provide a clear and concise blueprint to fully automate your business. This allows you to focus solely on customer interactions. We'll walk you through the entire automation process, starting from lead collection via forms, m...
Land Your Dream Job with This LinkedIn Automation!
zhlédnutí 348Před 2 měsíci
Land Your Dream Job with This LinkedIn Automation!
Claude 3.5 Sonnet: AI Game Changer! is OpenAI in trouble?
zhlédnutí 704Před 2 měsíci
Claude 3.5 Sonnet: AI Game Changer! is OpenAI in trouble?
Master Web Scraping: from No code to APIs to BeautifulSoup
zhlédnutí 256Před 2 měsíci
Master Web Scraping: from No code to APIs to BeautifulSoup
Perplexity AI & Zapier: Step-by-Step Super Automation Setup
zhlédnutí 673Před 2 měsíci
Perplexity AI & Zapier: Step-by-Step Super Automation Setup
Don't miss learning ML (No Code): from Concepts to a Demo
zhlédnutí 99Před 3 měsíci
Don't miss learning ML (No Code): from Concepts to a Demo
Don’t miss this ChatGPT Update: Integrating Apps & Analysis!
zhlédnutí 119Před 3 měsíci
Don’t miss this ChatGPT Update: Integrating Apps & Analysis!
Build a FULLY AUTOMATED Small Business with No Code
zhlédnutí 201Před 3 měsíci
Build a FULLY AUTOMATED Small Business with No Code
Llama3 70B vs. MS Copilot Pro vs. OpenAI ChatGPT4
zhlédnutí 1,7KPřed 4 měsíci
Llama3 70B vs. MS Copilot Pro vs. OpenAI ChatGPT4
AI beyond chatGPT! Build and Test and Demo ANNs - No Code
zhlédnutí 183Před 4 měsíci
AI beyond chatGPT! Build and Test and Demo ANNs - No Code
Don't really bother! Meta's llama 3 instruct 70b! No Code Deployment and Testing
zhlédnutí 2,5KPřed 4 měsíci
Don't really bother! Meta's llama 3 instruct 70b! No Code Deployment and Testing
Part 2 - Google & Form Signup - XANO & Wized - No Code
zhlédnutí 67Před 4 měsíci
Part 2 - Google & Form Signup - XANO & Wized - No Code
Build Train and Deploy! YOUR ML Model - NoCode and for FREE!
zhlédnutí 208Před 5 měsíci
Build Train and Deploy! YOUR ML Model - NoCode and for FREE!
Part 1 - Google & Form Signup - XANO & Wized - No Code
zhlédnutí 135Před 5 měsíci
Part 1 - Google & Form Signup - XANO & Wized - No Code
How to build an AI comment assistant bot for YouTube? Replit & Zapier
zhlédnutí 384Před 5 měsíci
How to build an AI comment assistant bot for CZcams? Replit & Zapier
Did openAI GPTs just lose to Zapier Central Bots?
zhlédnutí 417Před 5 měsíci
Did openAI GPTs just lose to Zapier Central Bots?
100% custom-made chatGPT APP in 20 mins (build & blueprint)
zhlédnutí 180Před 6 měsíci
100% custom-made chatGPT APP in 20 mins (build & blueprint)
Master ChatGPT in 23 Minutes - Full Tutorial! #openai #2024
zhlédnutí 354Před 6 měsíci
Master ChatGPT in 23 Minutes - Full Tutorial! #openai #2024
Do this! Automate Analytics with chatGPT - a Zapier Tutorial
zhlédnutí 289Před 6 měsíci
Do this! Automate Analytics with chatGPT - a Zapier Tutorial
Ignite Your Potential with Automation & AI Empowerment: Trailer
zhlédnutí 133Před 6 měsíci
Ignite Your Potential with Automation & AI Empowerment: Trailer
Zapier Automation: Save Money on Shopify Blog Emails!
zhlédnutí 166Před 7 měsíci
Zapier Automation: Save Money on Shopify Blog Emails!
How to Build an OpenAI GPT with API and Zapier (step-by-step project)
zhlédnutí 602Před 7 měsíci
How to Build an OpenAI GPT with API and Zapier (step-by-step project)
Would you be willing to set up a bot for me? Ill give your channel a few shout outs.
Great overview. I’m sticking with Zapier for now but also exploring Make just to learn.
For sure make is interesting! But zapier is focused now it seems on evolving which is good , even I was approached by them for feedback on their platform something I appreciated as told me they are seeking to even improve more and they look for feedback even from a small channel like mine … Thanks for your nice comment 😀
I've a question. What if on the webhook node you want to reference specific data from earlier on in the zap workflow. e.g. model: "llama-3.1-sonar-large-128k-online", messages: [ { role: "system", content: "You're a smart data analyst providing summaries." }, { role: "user", content: "Provide a detailed report on the follow [Google Sheet Zap that has lists of Data fields] " } ] }; ive been trying to get the information that is sent to perplexity to be dependent on what's in my dataset but zapier keep throwing an error. It works perfectly fine without referencing prior zaps and fails whenever I reference.
Yes i faced that and what happens as such dynamic fields have brackets that disrupt the json format; there are many ways to address it, i have done it through a step by code by zapier where i run a Python “stringify” function that return any data in a basically format that is json friendly: 1- Create a code by zapier step 2- add any inputs you want to use in the code For below example i have for two inputs, named “text_input” and “text_input2” Code below: import json def stringify_input(input_text): # Use json.dumps to properly escape the input text return json.dumps(input_text) # Zapier provides input data through the `input` dictionary text_input = input.get('text_input', '') text_input2 = input.get('text_input2', '') # Stringify both inputs stringified_input1 = stringify_input(text_input) stringified_input2 = stringify_input(text_input2) # Return the results # Zapier expects a dictionary as output output = { 'stringified_input1': stringified_input1, 'stringified_input2': stringified_input2 } # This is how you return data in Zapier Python steps return output The output with be 2 strings that you can use in the api call
@@GiveMeTheMic22 Thanks for the reply. Really appreciate it. After days stressing, my issue was the zap had linebreaks and I needed to use the formatter to replace them with the newline thingies so the data could be decoded. For me, this was easier than stringifying it.
Is it possible to link that fone tuned model to live data. Like train it, where to find informations in a google spreadsheet.
Never tried it myself but I am sure you can, I think this is doable through code only which is not me domain unfortunately Potentially can be automated as there is a predefined acting in zapier and make for fine-tuning ChatGPT that I never used, so in theory an automation could trigger a fine tuning event but this is me assuming
Great video man. You deserve more subs! 👍
Thanks buddy! It’s a process I am going through along the way getting such comments and knowing I have such great people in the community is more worth than a big number of subs Having more than 600 people benefiting of my content is by it self amazing and makes effort worth while :) Thanks again
Didn't know perplexity had an API! VERY useful information brother 🙌
It is become a cornerstone of most my automations and is super affordable! I charged the api with 5$ of credit and I use it heavily and it is only 2.5$ consumed in 3 months!!
Thank you for this video very helpful. How much did that cost you with Zappier?
Zapier pro with 1500 monthly tasks cost me 40$ for me worth every penny as I automate so much and it saves me so much time it is unreal! Perplexity api is so cheap and powerful it is silly and notion is free
Great Video! Could you also make a in debth Video from the Automation you used from the video [How To AUTOMATE Your Business in 2024 (Step by Step)] which you posted 4 weeks ago?
Thanks! Any specific details you are looking for? I actually created two videos on the topic and happy to do a third. Any specific area will help me understand what is missing
@@GiveMeTheMic22 Could you make a video where you show how you make a automated payment system with zapier? I would appreciate it
Thanks for your video. I would like to ask, why didn’t you use perplexity instead of using chat gpt for the last step? Many thanks
I keep perplexing to search jobs Once I have data and text chat gpt is better for reasoning, but also you can test to get the whole thing out of perplexity and save tasks so I recommend you test both options and see what you prefer There is no one way to do these things :)
Introduction and Purpose of the Live Stream - 00:00:00 Accessing OpenAI Fine-Tuning and Tier System Explanation - 00:01:24 Threads and Interface in OpenAI for Tracking Usage - 00:03:56 Overview of AI Fundamentals and Past Content - 00:05:13 Introduction to Fine-Tuning Concepts and Neural Networks - 00:08:47 Importance of Fine-Tuning and Adjusting Model Weights - 00:12:09 Fine-Tuning Use Cases and Preparing Training Data - 00:21:07 Creating Training Data for Fine-Tuning in JSON Format - 00:24:12 Uploading Training and Validation Data for Fine-Tuning - 00:38:20 Running the Fine-Tuning Job and Understanding Parameters - 00:43:01 Live Fine-Tuning Demonstration and Analysis - 00:45:29 Exploring Fine-Tuned Model in OpenAI Playground - 00:50:46 Comparison of Standard and Fine-Tuned Model Responses - 00:52:12 Using Fine-Tuned Models in Assistants and Applications - 00:56:29 Conclusion and Closing Remarks - 00:57:17
??? Thanks for the chapter breakdown
how to make this project?
The document you can collect in the description link has a step by step details
Thanks, keep going! really good video.
Such comments is what keeps me going thanks 🙏
Great but too bad Zapier is overpriced!
@@paulham.2447 this Wednesday I have a zapier vs make video It will either get you to continue using make (if that is your platform) or consider zapier pragmatically If neither is being used tell me I might see if I can look into something to help you more with
@@GiveMeTheMic22 Make ! 😄
@@paulham.2447 😂 hope you watch it might get you to think about… but in reality using either you are using best of the best
This is Gold! Thank you for sharing your experience. Subbed!!
Thanks for the sub! Appreciate the comment! Any more details around this you think will be helpful in future vids?
Nice video @sameer. It would be great if you create video on automating Microsoft outlook, for sending RFQ or emails to vendors with standard template which will save a lot of time & improve productivity at our workspace. Or integration of ChatGPT + outlook automation will be really helpful.
@@shubhamshetye8202 it’s definitely something i have in the pipeline:) Thanks for the feedback and the comment :)
This was an absolutely amazing video! - Thank you so much for your insights and teachings 😃🙏💛 Also love that you elbowed Wized a bit about their content 😁
Thanks buddy you can’t imagine the impact you are making, this is not my focus but going through the process of building a simple tool your channel was a gold for ANYONE who wants to learn I feel much more confident now doing it and maybe I will do more JS content that you put out to keep testing wized potential I think they need to wake up and ask for help for people like you ;)
@@GiveMeTheMic22 I can’t wait to see what’s next for you! Wized needs Aonnoy as their main content creator (if he wants) and they should be focusing on edu-tainment rather then making infomercials, and videos need to come every day! ;-)
Wow 👀
You mentioned a more detailed discussion about the testing results for fine tuning (training loss and convergence). But I need to find out which video you mean. Can you share! This was a good video!
This is a video most find boring 😂 it is about ai and I address such concepts AI beyond chatGPT! Build and Test and Demo ANNs - No Code czcams.com/video/JJ_fdazahng/video.html
Thank you, this is amazing!
I so happy you found it helpful :)
The Code by Zapier Step to parse JSON (use after each search): in the input data fields add two: some_text_field_with_json (use this exact name as it is in code) > put the output of any AI with Json Code below: import json def extract_json(input_string): stack = [] start_index = -1 # Traverse the string to find the complete JSON by counting braces for i, char in enumerate(input_string): if char == '{': stack.append(char) if len(stack) == 1: start_index = i # Mark the start of JSON elif char == '}': if stack: stack.pop() if not stack and start_index != -1: # When the stack is empty, the JSON is complete end_index = i + 1 return input_string[start_index:end_index] return None # Return None if no complete JSON object is found # Assuming input_data['some_text_field_with_json'] is a field from a previous step json_string = extract_json(input_data['some_text_field_with_json']) if json_string: json_data = json.loads(json_string) output = {'json_data': json_data} else: output = {'json_data': {}} return output Perplexity first search body request: { "model": "llama-3-sonar-large-32k-online", "messages": [ { "role": "system", "content": "Search for 15 random (not only top search results to minimize repetition) LinkedIn profiles based on the specified terms and return the results in JSON format. The search should focus on profiles from the United Arab Emirates that are active and seem influential and include the following details if available: complete name on LinkedIn, profile URL(i need verified and active urls avoiding not found 404 errors), current company, current location, email address, phone number, area of expertise, and profile headline." }, { "role": "user", "content": "Search LinkedIn for profiles related to the following terms: head hunter, recruiter, HR, human resources, talent acquisition, recruitment specialist, and also, as secondary criteria directly or indirectly are related procurement, supply chain, and c suite hire. Only include profiles based in the United Arab Emirates. The JSON response should have strictly this structure: {\"Profiles\": [{\"CompleteName\": \"Full name here\", \"ProfileURL\": \"Profile URL here\", \"CurrentCompany\": \"Current company here\", \"CurrentLocation\": \"Current location here\", \"EmailAddress\": \"Email address here\", \"PhoneNumber\": \"Phone number here\", \"AreaOfExpertise\": \"Area of expertise here\", \"ProfileHeadline\": \"Profile headline here\"}, ...]}" } ], "temperature": 0.5 } Perplexity second detailed search request body: { "model": "llama-3-sonar-large-32k-online", "messages": [ { "role": "system", "content": "Search online for additional contact information based on the provided LinkedIn profile details. Return the results in JSON format. The search should focus on finding the profile owner's information across various sources and include the following details if available: name, current location, current role, email address, phone number, mobile number, current company, profile headline, LinkedIn profile URL, education, experience, skills, recommendations, and connections." }, { "role": "user", "content": "Search online for the profile details based on the following information looking at all possible links for the same individual matching ANY of the following : 1-Name: {{244664614__name}}, 2-ProfileURL: {{244664614__profile url}}, 3-profile headline: {{244664614__headline}}. The JSON response should have strictly this structure: {\"Profile\": {\"Name\": \"Full name of the person as displayed on LinkedIn, identified value to replace value here\", \"CurrentLocation\": \"Current city and country where the person is located, identified value to replace value here\", \"CurrentRole\": \"The job title or position the person currently holds, identified value to replace value here\", \"Email\": \"Email address if available or inferred from other sources, identified value to replace value here\", \"PhoneNumber\": \"Landline phone number if available, identified value to replace value here\", \"MobileNumber\": \"Mobile phone number if available, identified value to replace value here\", \"CurrentCompany\": \"The company where the person is currently employed, identified value to replace value here\", \"ProfileHeadline\": \"The brief description or tagline under the person's name, usually summarizing their professional identity, identified value to replace value here\", \"LinkedInProfileURL\": \"The URL of the LinkedIn profile, identified value to replace value here\", \"Skills\": \"List of comma seperated string of skills and endorsements the person has received, identified value to replace value here\", \"Connections\": \"The number of connections the person has on LinkedIn, identified value to replace value here\"}}" } ], "temperature": 0.5 } Code by zapier step to make sense of HTML: in the inputs: html_response > response from get request Code: const htmlResponse = inputData.html_response; function checkPageStatus(html) { // Check for indicators of an active LinkedIn profile page if (html.includes('window.location.href') && html.includes('/authwall?trk=')) { return 'Active (Requires Authentication)'; } else if (html.includes('Page Not Found') || html.includes('Profile Not Found')) { return 'Not Found'; } else { return 'Unknown Status'; } } output = [{ "status": checkPageStatus(htmlResponse) }]; >>>>Second way through code by zapierto confirm linkedin URLs, better tested after vid (recommended - no get request only this-<<<< input is URL > insert the LinkedIn URL code: import re import requests def validate_linkedin_url(url): def is_valid_url(url): try: headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36' } response = requests.get(url, headers=headers, allow_redirects=True, timeout=10) return response.status_code == 200 except requests.RequestException as e: print(f"Error checking URL {url}: {str(e)}") return False # Normalize the URL url = url.strip().lower() if not url.startswith(('', '')): url = '' + url # Check original URL if is_valid_url(url): return {"valid": True, "url": url} # Extract username from the URL username_match = re.search(r'(?:\/in\/|\/pub\/)?([\w\-]+)(?:\/|$)', url) if not username_match: print(f"Could not extract username from URL: {url}") return {"valid": False, "url": url} username = username_match.group(1) # List of possible LinkedIn URL formats url_formats = [ f"www.linkedin.com/in/{username}/", f"www.linkedin.com/pub/{username}/", f"linkedin.com/in/{username}/", f"linkedin.com/pub/{username}/" ] # Try each format for fixed_url in url_formats: print(f"Trying URL: {fixed_url}") if is_valid_url(fixed_url): return {"valid": True, "url": fixed_url} # If no valid URL found, return the original invalid URL print(f"No valid URL found for username: {username}") return {"valid": False, "url": url} # Zapier input input_data = { 'url': input['url'] # Replace with actual Zapier input } # Process URL and get result result = validate_linkedin_url(input_data['url']) # Zapier output output = { 'valid': result['valid'], 'url': result['url'] }
If you could also give the code or steps on how one can implement (github etc) it so that it’s actually helpful for the community, it would be great.
Dear I pinned all code and even perplexity prompts to top comment, such snippets are not the best to use git hub for :) also, at the bottom I added an extra code to confirm linkedin URLs that I tested after the video and it performed better through a single code by zapier step
Thank you It would be lovely if you could create a process video that could cover this scenario A daily technology update from google news saved in Airtable The link is researched on Perplexity Outcome sent to ChatGPT for content repurposing - blog / shorts / instagram reels The outcome save in Google docs or in airtable for review When approved, automatically posted on LinkedIn, Facebook or Insta
I just put a complicated math word problem into bot Claude and ChatGPT. Claude failed hard. It even showed simple math equations that were clearly wrong and then came back with one of those "thank you for pointing that out" replies. ChatGPT solved the problem in a completely different way and correctly.
Yes as per Anthropic if you notice on their site Math is one of the areas it is inferior to chatGPT The more people test it the more we learn, i feel this model sonnet 3.5 is focused on coding use cases
@@GiveMeTheMic22 Agreed. In its "solution" to my problem it basically responded with a 1x1=2 answer that would have made Terrence Howard proud.
So, what I missed to get the Artifacts is turning it on. To do that click on your name icon of your account top right, then go to feature preview and once there toggle on Artifacts
Great video this would be a gamechanger!
Thanks buddy! Appreciate it Unfortunately this can’t be an app I don’t think CZcams would wants bots responding they want to keep human and although I did this small project I tend to agree My thoughts is that this can give an initial response while the actual people behind the channel get to respond if they have a massive following something I won’t have a a a problem for a long time 😂
How to update my existing Fine-tune model without create new model
I think for now you will have to fine tune and then take over any knowledge and copy/ paste the instructions… maybe in the future they make it a new version of the assistant… in theory by fine tuning you are modifying the weights of the model (I assume) so, might be the reason for this
Thanks for this video man you are doing a amazing job. A costumer asking me for a assistant doing exact this what you are showing in this video. I was starting by myself but you helped me a lot. Thanks
Wow thank you for the message, starting on CZcams is not easy and can get stressful especially if done on top of a full time job! But reading such message makes it all worthwhile
Thanks community for having my back! i cut out the showcase part as I realized maybe too late that when you talk to GPT-4o on the mobile app it is actually still 4 turbo! Well that's something I leaned about going live on whime to get a scoop, you tend to get thing wrong :) I appreciate everyone who made a comment and alerted me, and apologies if this disappointed some
It is a more natural coouter-human interaction when computer give the same boring useless responses like humans ? "It's great to be here", "How are you today", "Oh its so great you asked this" blah blah for nuttin. This bots are also trained to get anxiety and depression most of us-folks need to have ?
Sorry didn't get the question… or the comment exactly?
I cant wait till the app sees live video
That's the crazy part! I hope this doesn't affect people negatively, while in some cases it potentially could help
@@GiveMeTheMic22 Now all we need is hardware that just is just a Bluetooth video camera that clips in your shirt pocket or hangs off your neck, a pair of airpods and they both connects to your iphone,, connect it all to chat GPT 4o and you got "her".
@@GiveMeTheMic22 I found a pretty simple solution, use a phone lanyard to hang your phone off your neck while it records live video and then use airpods to talk to 'her'
That's regular GPT 4 bro
I got excited for nothing 😆 It was directing to got-4o in app!
GPT4o voice has still not been released to the public, the version you are testing of the voice is the same as the GPT-4. Later this month they probably release the full version.
Weird i assumed it is the new one which did pretty well compared to how i usually experience got-4 Makes sense although the window and session was clearly marked as GPT-4o so i am not sure can the audio be got-4 while the model of the session is 4o???? I doubt! But thanks for highlighting i need to double check
@@GiveMeTheMic22 He is correct, the new voice model for gpt-4o has not been released yet. Only text so far.
@@GiveMeTheMic22it is the same and gives you the option to select gpt40, only thing that hasn’t released yet is the voice redone app framework. text will only show new responses , the voice over just speaks it out
@@linklovezelda so now i eaither keep this up and look like a fool or take it down 🙃 Or just cut the experiment part out
@@GiveMeTheMic22 just pin the comment so everyone knows, the video is still fun to see
thumb up for your action you show up the whole steps. it is a little diff fron official demo due to latency
Oh wow thanks for such a comment that made my day way better 🫡
I really enjoyed this video. I would highly recommend it for other learners. Thank you for such a nice job
Oh Wow I really appreciate your comment!! Like a LOT! I am glad if one person got value of the video then it was worth while the effort
Groq is running the model through an LPU. It's always faster, regardless of the model. It spits out 900+ T/s on the 8B model.
Wow thanks for the tip I only used it for the demo and I was shocked how fast it was! And the one I was using in the 70B which is pretty heavy! What is more shocking is as of my experience it seemed free I have to dig deeper there thanks for the information 🫡
@@GiveMeTheMic22 It's free for 14,400 tokens using the larger models and 30,000 tokens for the smaller models. After that there is a 3 hour cool down period. They do not offer a subscription, it is purely intended to show the power of their LPU's. You can also customise any model on there, including Llama 3 70B by hitting the tog in the top right and this enables system prompts to be entered as need and saved.
ChatGPT Summary to avoir the video : It seems like you've conducted a thorough comparison between the three language models: ChatGPT4, Microsoft Copilot, and Lama370B. Let's summarize your findings: ### Summary of Comparison: 1. **Speed:** - Lama370B was the fastest in providing solutions, followed by Microsoft Copilot, and then ChatGPT4. 2. **Complexity and Detail:** - While Copilot tended to simplify solutions, ChatGPT4 and Lama370B provided more detailed and complex responses. 3. **Handling PDFs:** - Copilot disappointed as it didn't handle PDFs directly, requiring integration with the Microsoft ecosystem. - ChatGPT4 excelled in handling PDFs, demonstrating its strength in document-based tasks. 4. **Cost Consideration:** - Copilot comes at a higher cost, especially for the business version, compared to ChatGPT4. - Lama370B's cost-effectiveness depends on factors like hosting and usage, especially if integrated with Azure. 5. **Tool Integration and Familiarity:** - ChatGPT4's integration with tools like Zapier and familiarity were cited as advantages, contributing to ease of use. 6. **Overall Decision:** - Despite Copilot's strengths, you've decided to stick with ChatGPT4 due to factors like complexity, cost-effectiveness, and familiarity. ### Conclusion: Your decision to stick with ChatGPT4 seems well-considered, taking into account factors like functionality, cost, and integration with existing workflows. It's essential to choose the language model that best aligns with your specific needs and preferences, and your thorough evaluation process should serve as a helpful guide for others navigating similar decisions. If you have any further questions or need more assistance, feel free to ask!
😂😂 I think viewers might default to reading your comment rather than watch the video! Thanks for sharing Seems a nice GPT behind it :) Did you build it? Or was it a normal session based of transcript
@@GiveMeTheMic22 a trained prompt to summarize articles, vidéo transcriptions and so on. Sorry for you bro
llamma is faster because of hardware. The guy should know that
Hi Samer, Your AI video was amazing! I liked how you broke down such vast topics into something everyone can grasp. The references you included are super valuable for anyone who wants to learn more. Subscribed!
Thanks buddy! I appreciate your trust
Imbalance data set is data that has a large amount of data points having a bias. Mostly in the left or the right in terms of distribution
@@RomaineGangaram thanks! I am learning so much from the community I will have to look this up in more detail
The repeating of the text is the fault of however that Azure playground is processing responses not the fault of the Model. You can see the application missed a stop token in the text, that is just a bug in Azure unfortunately.
Thanks for the clarification! I will look into it but what you say makes total sense as root cause of such behavior
What I absolutely disliked about local LLAMA3 was the data theft going on in the background. I was at no point made aware of the fact, that this thing sends EVERYTHING back home, for data mining.
Thanks for the comment! I honestly never new that I made a video comparing it to other AI, just to make sure i didn't jump to conclusions and yet even aside of what you are saying it still doesn't stack up for serious needs
A power packed content. Thanks for the amazing video
Glad you enjoyed it! Thank you
Nice video. However when i try the same, I get a method not allowed error on running the endpoint generated. Any idea what that's about?
So you are using the endpoint through what? Postman ? Did you test the model on playground for azure ai studio
Great video! Can't wait to see the next part 😄
Thanks Rama Appreciate it
Great content. Zapier is so powerful. Keep it going 🙏
Thank you! @courtenay Will do!
test test chat gpt hahah i dunno if it will reply to this!
Hehehe I deactivated it! Don’t need it and won’t spend money on it yet! But is a cool tool you can deploy anywhere really
@@GiveMeTheMic22 your work is amazing, you deserve more fame! Keep going! We're here to support you ;)
Hello, you are really doing a great job. Lots of inventiveness and creativity which makes me always surprised and delighted to watch your videos. Thank you !
Thanks Paul! You can’t imagine the impact of your message! I am struggling with growth but enjoy everything I am learning and sharing with the community Thank you 🙏
@@GiveMeTheMic22 It was nothing Mr/Mrs the Ultimate CZcams Comment Responding-AI ! 😀
@@paulham.2447 😂
@@GiveMeTheMic22 you're doing an amazing job man, I can feel how hard this might be to set up AND film, if you need any help just reach out, i'll try my best!
good job bozo
Thank you for your feedback! Always looking to improve - I'll take your comment on board. Remember to like and subscribe for more content on AI and tech! GiveMeTheMic Team
Habibi ya Samer now, listen. .... What is the return of investment of creating my own GPT in the marketplace? ....Ok? Now Second. ....What are the metrics contributing to Obesity? Let's hold there and revisit.
Hey, for the first point, the most accurate answer is that we do not know yet! still, having said that OpenAI and chatGPT is at the forefront of the AI revolution and with features coming out so often, including lastly, your ability to summon many GPTs (assistants/ agents) in one session and ask them to perform actions for you as you learn such skill; it is driving many to expect Open AI to drop a monetization model; also, remember so far OpenAI is the fastest growing business in user base in history, so, there is scale and odds are there is money to be made. Now this is stating the obvious, beyond that we cant ignore the ROI of having such GPTs optimize your work and do work for you getting back some of your time if not more than that. Secondly, Obesity was just an example and I am by no means an expert :) better you look for other CZcamsrs more into health
One of the best videos, thank you for taking the time to explain it thoroughly
You are welcome! Anytime I am glad you found value in it
How do I deploy the bots?
You have to create a loop; I used it last time a year ago After testing it did not work the way I expected meaning I got no results Maybe you can try and feel free to share if it helps you maybe I need to do a new video review
Please register below to gain access to free cool stuff I share! givemethemicofficial.com/collections/exclusive-access-boutique