Yeyu Lab
Yeyu Lab
  • 26
  • 68 702
Exploring Llama-Agents with Code Walkthrough
In this video, I would like to provide you with a detailed exploration of a new multi-agent framework - Llama-Agents from Llama-Index
TIME STAMPS:
00:00 Intro
00:29 Advantages of a multi-agent system
01:18 Overview of Llama-Agents
02:33 Case 1 - Fixed orchestration
08:33 Case 2 - Auto orchestration
12:42 Case 3 - Human-in-loop
16:39 Case 4 - Built-in tools
20:08 Conclusion
USEFUL LINKS:
Demo Source Code - github.com/yeyu2/TH-cam_demos
Tutorial on SubStack - substack.com/home/post/p-148485076?r=21aesy&
MY CONNECT:
Buy me a coffee - ko-fi.com/yeyuh
Business Inquiries - wenbo.huang@yeyulab.com
X: x.com/Yeyu2HUANG
Discord - discord.gg/KPTCE4CEmp
Email Subscription - yeyu.substack.com/
Exclusive service - ko-fi.com/yeyuh/commissions
มุมมอง: 16

วีดีโอ

Use Mesop to Develop UI for CrewAI App
มุมมอง 32514 วันที่ผ่านมา
In this video, I would like to provide you with a Quick Tutorial on Using Mesop to Develop UI for the CrewAI App. TIME STAMPS: 00:00 Intro 00:38 Overview of Mesop 01:15 Overview of CrewAI 02:42 Code Walkthrough 11:04 Final Demo USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substack.com/pub/yeyu/p/build-a-crewai-app-with-mesop-the?r=21aesy& MY CONNECT...
Create a Multi-Agent App with Mesop UI
มุมมอง 2.6K21 วันที่ผ่านมา
In this video, I would like to provide you with a A Quick Tutorial of Using Mesop to Develop UI for AutoGen App. TIME STAMPS: 00:00 Intro 00:36 Overview of Mesop 02:56 Text-To-Text Demo 06:37 AutoGen Demo 08:25 Code Walkthrough USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substack.com/pub/yeyu/p/create-a-multi-agent-app-with-mesop?r=21aesy&showWelco...
How to Build an Image Creator Agent for the AutoGen Application
มุมมอง 207หลายเดือนก่อน
In this video, I would like to provide you with a quick tutorial for building a Dalle-3 powered agent into an AutoGen app and using Panel for UI. TIME STAMPS: 00:00 Intro 01:10 Why need an image creation agent 03:50 Demo app walkthrough 05:22 Code Walkthrough 15:00 Run & Test USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substack.com/pub/yeyu/p/whats...
How to Create APIs for AutoGen
มุมมอง 647หลายเดือนก่อน
In this video, I would like to provide you a quick tutorial for building an API service for the AutoGen-powered application by using Flask. TIME STAMPS: 00:00 Intro 00:30 Why create APIs 00:56 System Architecture 02:46 Code Walkthrough 17:33 Testing by cURL and a mini app USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - yeyu.substack.com/p/how-to-create-apis...
How to Create an Interactive Web UI for CrewAI Applications By Panel
มุมมอง 5K4 หลายเดือนก่อน
In this video, I would like to provide you a quick tutorial for building a visualized CrewAI application by using the Panel framework, which includes the feature of human interaction. TIME STAMPS: 00:00 Intro 01:28 Why not Streamlit 04:16 Panel framework 06:42 CrewAI Workflow 07:38 Code Walkthrough USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substa...
How to Implement a Simple UI for CrewAI applications
มุมมอง 4.6K4 หลายเดือนก่อน
In this video, I would like to provide you a quick tutorial for building a visualized CrewAI application by using the Streamlit framework. TIME STAMPS: 00:00 Intro 03:00 CrewAI 03:58 Streamlit 04:35 Block Diagram 05:12 Code Walkthrough 11:20 Conclusion USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substack.com/pub/yeyu/p/how-to-implement-a-simple-ui-...
Best Groq Practice - Making a Voice Assistant with Human Reaction Speed
มุมมอง 1.1K5 หลายเดือนก่อน
In this video, I would like to provide you a a quick tutorial for building a voice assistant powered by Groq inference service. TIME STAMPS: 00:00 Intro 00:15 Groq Introduction 04:23 Voice Assistant Demo 06:28 Code Walkthrough for frontend 11:21 Code Walkthrough for backend USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substack.com/pub/yeyu/p/best-gr...
AutoGen + Custom Model + Gemma (or Any Model), Here is the Ultimate Solution
มุมมอง 1.4K5 หลายเดือนก่อน
In this video, I would like to provide you a quick guide for using any custom models including Gemma in AutoGen by CustomModelClient method. TIME STAMPS: 00:00 Intro 01:25 How CustomModelClient works 03:49 Code for AutoGen Gemma 12:59 Optimization for GPU memory USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substack.com/pub/yeyu/p/running-autogengemm...
AutoGen + Ollama + Gemma: How to Create LLM Agents Locally
มุมมอง 1.8K6 หลายเดือนก่อน
In this video, I would like to provide you a quick tutorial on building AutoGen apps by using Ollama to deploy Gemma-powered agents. TIME STAMPS: 00:00 Intro 02:23 Ollama 02:35 How AutoGen Ollama works 02:52 Code for Ollama setup 04:53 Code for AutoGen setup 07:54 Running & Result 09:30 Conclusion USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substac...
Is Gemma Capable of Building Multi-agent Applications in AutoGen?
มุมมอง 7226 หลายเดือนก่อน
In this video, I would like to provide you a quick tutorial on building Gemma AutoGen apps with performance evaluations. TIME STAMPS: 00:00 Intro 00:18 Gemma Introduction 03:32 OpenRouter Inference API 04:58 Code for AutoGen Gemma 05:56 1on1 Conversation Demo 08:36 Group Chat Demo 13:15 Conclusion USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substac...
2-bit Quantization is Magical! See How to Run Mixtral-8x7B on Free-tier Colab
มุมมอง 5366 หลายเดือนก่อน
In this video, I would like to provide you a quick tutorial for AQLM-2-bit quantization and its implementation, and you will learn how to use this approach to run a middle-size language model on the Colab for free. USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substack.com/pub/yeyu/p/the-2-bit-quantization-is-insane?r=21aesy&showWelcomeOnShare=true T...
OpenRouter - Use The LLM Inference API with the Lowest Cost
มุมมอง 2.9K6 หลายเดือนก่อน
In this video, I would like to show you a very cheap LLM Inference API called OpenRouter and How to Integrate it into Multi-agent apps. USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack - open.substack.com/pub/yeyu/p/use-the-cheapest-llm-inference-api?r=21aesy&showWelcomeOnShare=true OpenRouter: openrouter.ai/ MY CONNECT: Buy me a coffee - ko-fi.com/yeyuh Busin...
CrewAI - A Smartly Designed Multi-agent Framework for LLM App Development
มุมมอง 3.4K7 หลายเดือนก่อน
In this video, I would like to show you a new multi-agent framework called CrewAI and its comparison with AutoGen in LLM App development. USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack- open.substack.com/pub/yeyu/p/for-a-multi-agent-framework-crewai?r=21aesy&showWelcomeOnShare=true CrewAI Docs: joaomdmoura.github.io/crewAI/ MY CONNECT: Buy me a coffee - ko-f...
AutoGen Technique - Use `Description` Field to Manage the Conversation Between Multiple Agents
มุมมอง 1.1K7 หลายเดือนก่อน
In this video, I would like to show you a new AutoGen tip about using the Description field to orchestrate the conversation between multiple agents. USEFUL LINKS: Demo Source Code - github.com/yeyu2/TH-cam_demos Tutorial on SubStack- open.substack.com/pub/yeyu/p/how-to-orchestrate-the-conversation?r=21aesy&showWelcome=true AutoGen Docs: microsoft.github.io/autogen MY CONNECT: Buy me a coffee - ...
AutoGen + Function Calling + Open Source LLMs, Here is How
มุมมอง 7K7 หลายเดือนก่อน
AutoGen Function Calling Open Source LLMs, Here is How
Use Open Source LLMs in AutoGen powered by Fireworks AI, without GPU/CPU
มุมมอง 1.9K8 หลายเดือนก่อน
Use Open Source LLMs in AutoGen powered by Fireworks AI, without GPU/CPU
How to Use Open Source LLMs in AutoGen Powered by vLLM
มุมมอง 5K8 หลายเดือนก่อน
How to Use Open Source LLMs in AutoGen Powered by vLLM
AutoGen + Panel Ep.3 - Web UI for Multi-agent with Document Retrieval
มุมมอง 4.9K8 หลายเดือนก่อน
AutoGen Panel Ep.3 - Web UI for Multi-agent with Document Retrieval
Create Full Function UI for AutoGen Powered by Panel (Human Input Enabled)
มุมมอง 7K9 หลายเดือนก่อน
Create Full Function UI for AutoGen Powered by Panel (Human Input Enabled)
How to Create a Web UI for AutoGen by Using Panel
มุมมอง 11K9 หลายเดือนก่อน
How to Create a Web UI for AutoGen by Using Panel
Development Guide for GPT-4-Turbo, Assistants API and others from OpenAI DevDay
มุมมอง 2669 หลายเดือนก่อน
Development Guide for GPT-4-Turbo, Assistants API and others from OpenAI DevDay
Step-Back Prompting: How to Make LLM Chatbots Smarter Than Ever
มุมมอง 57110 หลายเดือนก่อน
Step-Back Prompting: How to Make LLM Chatbots Smarter Than Ever
See How Easy It Is to Use AutoGen to Implement a Fully AI-Powered Workshop
มุมมอง 3K10 หลายเดือนก่อน
See How Easy It Is to Use AutoGen to Implement a Fully AI-Powered Workshop
LangChain Hub - Hundreds of Prompt Templates that Streamline Your LLM App Development
มุมมอง 65310 หลายเดือนก่อน
LangChain Hub - Hundreds of Prompt Templates that Streamline Your LLM App Development
How to Fine-tune OpenAI's GPT-3.5 Turbo for a Custom Tone
มุมมอง 53611 หลายเดือนก่อน
How to Fine-tune OpenAI's GPT-3.5 Turbo for a Custom Tone

ความคิดเห็น

  • @florencioq
    @florencioq 43 นาทีที่ผ่านมา

    Thanks for your post. I found a possible problem, and I'd like to know if other people got the same. When I change the user_proxy to a non-autonomous agent, changing human_input_mode to "ALWAYS", the front-end does not get the back-end when the user has to write his answer. Thanks for any help.

  • @gokusaiyan1128
    @gokusaiyan1128 8 วันที่ผ่านมา

    love your series. Can you make a video on using autogen to generate a code and then later it compiles it too and we can a final executable from it. For e.g. I want it to write a function that takes web url and that web url requests example, later it analyzes the request to figure our the api routes and write a program in any compiled language that can make requests to that web url and execute it.

  • @successahead5598
    @successahead5598 10 วันที่ผ่านมา

    can you help with crewai working with django

  • @raomotorsports
    @raomotorsports 14 วันที่ผ่านมา

    THANK YOU 🙏🏻 Really appreciate the way you explain each step of the process! Made it super easy to understand how it works. You are the man!

  • @bwilliams060
    @bwilliams060 15 วันที่ผ่านมา

    Hi Yeyu! I’m yet to see a video where chainlit has been paired up with crewai. Is there a reason for this? Is it more like streamlit or panel as far as long running multi agent frameworks?

  • @leane-q9y
    @leane-q9y 17 วันที่ผ่านมา

    Great video! Does anyone know how to close the browser window that opens after the server is launched in the code? I am able to stop the server but not close the window with it...

  • @florentromanet5439
    @florentromanet5439 17 วันที่ผ่านมา

    Thanks 🙏

    • @yeyulab
      @yeyulab 15 วันที่ผ่านมา

      You’re welcome, hope it helps!

  • @jermesastudio
    @jermesastudio 19 วันที่ผ่านมา

    Thank you for this tutorial. It was helpful for my work.

    • @yeyulab
      @yeyulab 15 วันที่ผ่านมา

      Thanks, glad to see it helped

  • @mikew2883
    @mikew2883 24 วันที่ผ่านมา

    Awesome tutorial! 👏

    • @yeyulab
      @yeyulab 15 วันที่ผ่านมา

      Thanks

  • @NathanVirushabadoss
    @NathanVirushabadoss 25 วันที่ผ่านมา

    can u please upload the video autogen with web sockets

  • @user-ud7ho5ck7t
    @user-ud7ho5ck7t 29 วันที่ผ่านมา

    Thank you for the video 🎉🎉

  • @mikew2883
    @mikew2883 หลายเดือนก่อน

    Good stuff! 👍

  • @gokusaiyan1128
    @gokusaiyan1128 หลายเดือนก่อน

    can you do one video with autogen with UI, no I don't want autogen studio.

  • @MrMoonsilver
    @MrMoonsilver หลายเดือนก่อน

    Man!! Finally someone did it, thank you very much for sharing this with us!

  • @drlordbasil
    @drlordbasil หลายเดือนก่อน

    Thanks for this, I don't use autogen often, but I love the builds that are possible.

  • @AdibaHaque-f2j
    @AdibaHaque-f2j หลายเดือนก่อน

    Amazing video! Very to-the-point and helpful. I am encountering an issue and was hoping you could assist me. In your code, you reset input_future each time to receive new input from the user. However, when I attempt to implement this, I only receive responses from the agents the first time I provide input. After that, there is no further agent engagement or conversation, and the terminal indicates that no input is awaited. How can I maintain ongoing user engagement after each termination? For instance, if I have three agents engaging in the chat, I would like the flow to be: User input User proxy Agent 1 Agent 2 Then again User input User proxy Agent 1 Agent 2 And again And so on. Thank you!

  • @user-be9ie1zo8l
    @user-be9ie1zo8l 2 หลายเดือนก่อน

    Thank you very much for sharing the code! It is very useful to me. Additionally, I would like to ask if it is possible to initiate a new round of conversation. Specifically, when one round of conversation has ended and I attempt to ask a second question, it enters the logic that prints 'There is currently no input being awaited.'"

  • @AnandKumar-fn4sd
    @AnandKumar-fn4sd 2 หลายเดือนก่อน

    Hello, which versions of python, panel, crewai are you using. I am consistently getting an error: AttributeError: module 'panel' has no attribute 'chat' for the basic chat. ( the first example)

    • @yeyulab
      @yeyulab 2 หลายเดือนก่อน

      My working version- Panel 1.4.0 CrewAI 0.28.8

  • @MrGaborKukucska
    @MrGaborKukucska 3 หลายเดือนก่อน

    Thanks for your tutorials Yeyu 🙌

  • @MuhammadIkrma-sk7mh
    @MuhammadIkrma-sk7mh 3 หลายเดือนก่อน

    user_proxy.initiate_chat( manager, message="""Generate a 120-word of blog post about traveling in Bohol Island. """ ) RuntimeError: Model client(s) ['CustomModelClient'] are not activated. Please register the custom model clients using `register_model_client` or filter them out form the config list.

  • @MuhammadIkrma-sk7mh
    @MuhammadIkrma-sk7mh 3 หลายเดือนก่อน

    user_proxy.initiate_chat( manager, message="""Generate a 120-word of blog post about traveling in Bohol Island. """ ) RuntimeError: Model client(s) ['CustomModelClient'] are not activated. Please register the custom model clients using `register_model_client` or filter them out form the config list.

  • @jeremyrileysmith
    @jeremyrileysmith 4 หลายเดือนก่อน

    The github doesn't have the texttospeech.py file. I am getting an error.

  • @archiee1337
    @archiee1337 4 หลายเดือนก่อน

    great!

  • @anupamz23
    @anupamz23 4 หลายเดือนก่อน

    thanks, but it seems del_name will not work with new version of autogen as code of CoversableAgent.py has been changed

  • @AbzDogg
    @AbzDogg 4 หลายเดือนก่อน

    Hi, I tried running your code and ran into the following error Error running application handler <bokeh.application.handlers.script.ScriptHandler object at 0x7f68b6a46f40>: cannot import name 'CrewAgentExecutor' from 'crewai.agents' (unknown location) File 'crewaipanel.py', line 12, in <module>: from crewai.agents import CrewAgentExecutor Traceback (most recent call last): File "/home/jarvis/projects/commonenv/lib/python3.8/site-packages/bokeh/application/handlers/code_runner.py", line 231, in run exec(self._code, module.__dict__) File "/home/jarvis/projects/crewaipanel/crewaipanel.py", line 12, in <module> from crewai.agents import CrewAgentExecutor ImportError: cannot import name 'CrewAgentExecutor' from 'crewai.agents' (unknown location) Tried various things to fix this but to no avail Can help? Thanks!

  • @sr.modanez
    @sr.modanez 4 หลายเดือนก่อน

    perfeito, parabens

  • @KodandocomFaria
    @KodandocomFaria 4 หลายเดือนก่อน

    A good one could be a video on how to expose it as an api, this way frontend developer can use creativite and create new interfaces for this agent.

    • @yeyulab
      @yeyulab 4 หลายเดือนก่อน

      Actually I am doing such projects, will share to you very soon. Thanks for the suggestion!

    • @dylanpoh7007
      @dylanpoh7007 3 หลายเดือนก่อน

      @@yeyulab Thanks for this great video! I am also looking forward to your next video on exposing API

  • @xingwei3488
    @xingwei3488 4 หลายเดือนก่อน

    Very Good! You did a great job! I tried your github code (crewai_panel.py) and got this issue: Exception in thread Thread-3 (initiate_chat): Traceback (most recent call last): ... ... File "D:\Dev\crewai_test\main.py", line 22, in custom_ask_human_input chat_interface.send(prompt, user="assistant", respond=False) ^^^^^^^^^^^^^^ NameError: name 'chat_interface' is not defined Could you help me ?

    • @yeyulab
      @yeyulab 4 หลายเดือนก่อน

      Have you copied the last three lines? chat_interface = pn.chat.ChatInterface(callback=callback) chat_interface.send("Send a message!", user="System", respond=False) chat_interface.servable()

    • @xingwei3488
      @xingwei3488 4 หลายเดือนก่อน

      ​@@yeyulab Yes. I have copied all the lines include the last three. Panel Application works fine until huan input. The issue throwed on my VSCode Terminal : ==== (.venv) D:\Dev\crewai_panel>panel serve main.py 2024-05-01 09:25:45,182 Starting Bokeh server version 3.4.1 (running on Tornado 6.4) 2024-05-01 09:25:45,182 User authentication hooks NOT provided (default user enabled) 2024-05-01 09:25:45,197 Bokeh app running at: localhost:5006/main 2024-05-01 09:25:45,197 Starting Bokeh server with process id: 15076 2024-05-01 09:25:55,994 WebSocket connection opened 2024-05-01 09:25:55,994 ServerConnection created > Entering new CrewAgentExecutor chain... I need to delegate the task of writing the blog post of Trip to Shenzhen to the Blog Post Writer and ask them to include all the necessary details in the article. Action: Delegate work to co-worker Action Input: { "coworker": "Blog Post Writer", "task": "Write a blog post of Trip to Shenzhen", "context": "Please write a blog post about the recent trip to Shenzhen. Include details about the sights visited, the food tried, and the overall experience of the trip. The article should be under 100 words." } Title: Exploring the Vibrant City of Shenzhen Recently, I had the opportunity to visit the bustling city of Shenzhen, and it was truly a remarkable experience. From exploring the modern architecture of the Ping An Finance Centre to strolling through the vibrant streets of Huaqiangbei, every moment was filled with excitement. The local cuisine was a highlight of the trip, with delicious dishes such as dim sum and hot pot tantalizing my taste buds. Overall, my trip to Shenzhen was a perfect blend of culture, history, and gastronomy, leaving me with unforgettable memories to cherish. Can't wait to visit again! Final Answer: Title: Exploring the Vibrant City of Shenzhen Recently, I had the opportunity to visit the bustling city of Shenzhen, and it was truly a remarkable experience. From exploring the modern architecture of the Ping An Finance Centre to strolling through the vibrant streets of Huaqiangbei, every moment was filled with excitement. The local cuisine was a highlight of the trip, with delicious dishes such as dim sum and hot pot tantalizing my taste buds. Overall, my trip to Shenzhen was a perfect blend of culture, history, and gastronomy, leaving me with unforgettable memories to cherish. Can't wait to visit again! > Finished chain. > Entering new CrewAgentExecutor chain... I need to carefully review the blog post content and come up with specific comments for improvement to make it more viral on social media. Action: Delegate work to co-worker Action Input: {"coworker": "Blog Post Reviewer", "task": "Review blog post content for improvement suggestions", "context": "Title: Exploring the Vibrant City of Shenzhen - Recently, I had the opportunity to visit the bustling city of Shenzhen, and it was truly a remarkable experience. From exploring the modern architecture of the Ping An Finance Centre to strolling through the vibrant streets of Huaqiangbei, every moment was filled with excitement. The local cuisine was a highlight of the trip, with delicious dishes such as dim sum and hot pot tantalizing my taste buds. Overall, my trip to Shenzhen was a perfect blend of culture, history, and gastronomy, leaving me with unforgettable memories to cherish. Can't wait to visit again!"} Title: Exploring the Vibrant City of Shenzhen - Recently, I had the opportunity to visit the bustling city of Shenzhen, and it was truly a remarkable experience. From exploring the modern architecture of the Ping An Finance Centre to strolling through the vibrant streets of Huaqiangbei, every moment was filled with excitement. The local cuisine was a highlight of the trip, with delicious dishes such as dim sum and hot pot tantalizing my taste buds. Overall, my trip to Shenzhen was a perfect blend of culture, history, and gastronomy, leaving me with unforgettable memories to cherish. Can't wait to visit again! Review Comments: 1. Consider adding more specific details about the modern architecture of the Ping An Finance Centre. What aspects of the architecture stood out to you the most? 2. It would be helpful to include more information about the vibrant streets of Huaqiangbei. What unique shops or experiences did you encounter while strolling through the area? 3. Provide more descriptions of the local cuisine in Shenzhen. What made the dim sum and hot pot dishes you tried stand out from other places you have visited? 4. Expand on the cultural and historical aspects of your trip. Were there any particular landmarks or events that left a lasting impression on you? 5. Consider incorporating personal anecdotes or stories to make the article more engaging for readers. 6. End the article with a strong conclusion that summarizes your overall experience in Shenzhen and leaves readers with a lasting impression. Overall, the article has a good foundation but could benefit from more detailed descriptions and personal insights to enhance the reader's experience. Exception in thread Thread-3 (initiate_chat): Traceback (most recent call last): File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.12_3.12.1008.0_x64__qbz5n2kfra8p0\Lib\threading.py", line 1073, in _bootstrap_inner self.run() File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.12_3.12.1008.0_x64__qbz5n2kfra8p0\Lib\threading.py", line 1010, in run self._target(*self._args, **self._kwargs) File "D:\Dev\crewai_panel\main.py", line 43, in initiate_chat StartCrew(message) File "D:\Dev\crewai_panel\main.py", line 133, in StartCrew result = project_crew.kickoff() ^^^^^^^^^^^^^^^^^^^^^^ File "D:\Dev\crewai_panel\.venv\Lib\site-packages\crewai\crew.py", line 254, in kickoff result, manager_metrics = self._run_hierarchical_process() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Dev\crewai_panel\.venv\Lib\site-packages\crewai\crew.py", line 329, in _run_hierarchical_process task_output = task.execute( ^^^^^^^^^^^^^ File "D:\Dev\crewai_panel\.venv\Lib\site-packages\crewai\task.py", line 173, in execute result = self._execute( ^^^^^^^^^^^^^^ File "D:\Dev\crewai_panel\.venv\Lib\site-packages\crewai\task.py", line 182, in _execute result = agent.execute_task( ^^^^^^^^^^^^^^^^^^^ File "D:\Dev\crewai_panel\.venv\Lib\site-packages\crewai\agent.py", line 221, in execute_task result = self.agent_executor.invoke( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Dev\crewai_panel\.venv\Lib\site-packages\langchain\chains\base.py", line 163, in invoke raise e File "D:\Dev\crewai_panel\.venv\Lib\site-packages\langchain\chains\base.py", line 153, in invoke self._call(inputs, run_manager=run_manager) File "D:\Dev\crewai_panel\.venv\Lib\site-packages\crewai\agents\executor.py", line 124, in _call next_step_output = self._take_next_step( ^^^^^^^^^^^^^^^^^^^^^ File "D:\Dev\crewai_panel\.venv\Lib\site-packages\langchain\agents\agent.py", line 1138, in _take_next_step [ File "D:\Dev\crewai_panel\.venv\Lib\site-packages\crewai\agents\executor.py", line 245, in _iter_next_step human_feedback = self._ask_human_input(output.return_values["output"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Dev\crewai_panel\main.py", line 21, in custom_ask_human_input chat_interface.send(prompt, user="assistant", respond=False) ^^^^^^^^^^^^^^ NameError: name 'chat_interface' is not defined === What should I do now? Thanks a lot!

  • @williamwong8424
    @williamwong8424 4 หลายเดือนก่อน

    hi Yeyu, this is great. I have subscribed. in the next video can i request a follow up on this - 1. to have ability to search online be it tavily or serper or duckduckgo 2. ability to infer from a knowledge base which we will feed it. example pdf, txt, docx etc this help the crew to be smarter in a way. please do ! thank u!

    • @yeyulab
      @yeyulab 4 หลายเดือนก่อน

      Good proposals! Stay tuned!

  • @bimbotsolutions6665
    @bimbotsolutions6665 4 หลายเดือนก่อน

    Awesome...

    • @yeyulab
      @yeyulab 4 หลายเดือนก่อน

      Thanks

  • @kreddy8621
    @kreddy8621 4 หลายเดือนก่อน

    Nice, cheers for this

    • @yeyulab
      @yeyulab 4 หลายเดือนก่อน

      Thanks!

  • @user-wr4yl7tx3w
    @user-wr4yl7tx3w 4 หลายเดือนก่อน

    how about gradio? any thoughts about the pros and the cons between the two?

  • @zmjerry
    @zmjerry 4 หลายเดือนก่อน

    Thanks for sharing! This is exactly what I'm looking for last week! Good job and keep on the good work!

    • @yeyulab
      @yeyulab 4 หลายเดือนก่อน

      Thanks! I am glad that it is helpful for you!

  • @trafferz
    @trafferz 4 หลายเดือนก่อน

    Very cool! Just started with CrewAi this week and had in mind trying another task today before seeing this video. Streamlit gui up and running. Looking forward to now playing more with the CrewAi internals to tweak output. Very useful. Thanks! Haven't looked yet, does Streamlit docs describe how we might put the Agent prompts to gui so they can be customized by a user from the interface as well?

    • @yeyulab
      @yeyulab 4 หลายเดือนก่อน

      Do you mean you want to have more customized input from the UI for setup the CrewAI workflow?

    • @trafferz
      @trafferz 4 หลายเดือนก่อน

      @@yeyulab missed this response. yeah, i've been messing around with streamlit to manage the task and agent attributes/prompts stored in a yaml file.

  • @mohamedkeddache4202
    @mohamedkeddache4202 4 หลายเดือนก่อน

    I am struggling to find the syntax for my project, I got used to using ChatGPT to find the syntax, but now chatGPT don't know those recent information like Ollama, RAG, langchain, etc... (cause GPT have limited knowledge) -can you tell me where I can find the syntax?

  • @IdPreferNot1
    @IdPreferNot1 5 หลายเดือนก่อน

    High quality and complete explanation. Unfortunately I'm stuck at python knowledge level but will try the other elements as you suggest.

  • @NahFam13
    @NahFam13 5 หลายเดือนก่อน

    The explanation of how things are processed, and what the code is doing was incredible. Thank you for taking the time do both make this tutorial, and explaining things in fine detail!

    • @yeyulab
      @yeyulab 5 หลายเดือนก่อน

      Thank you, I am glad it’s helpful!

  • @undeadgaming2102
    @undeadgaming2102 5 หลายเดือนก่อน

    can it do like when it giving response and i start giving it some other prompt and it stop handling the previous and start doing the new one

  • @bekhzodortikov421
    @bekhzodortikov421 5 หลายเดือนก่อน

    Hey! si there any way drop running script by user_proxy or showing it in chat?

  • @kai-yihsu3556
    @kai-yihsu3556 5 หลายเดือนก่อน

    Thank you very much for your explanation! I really need this kind of tutorial on front-end and back-end integration. Thank you again for sharing.

    • @yeyulab
      @yeyulab 5 หลายเดือนก่อน

      Thank you!

  • @ZexuanWang-zx9fd
    @ZexuanWang-zx9fd 5 หลายเดือนก่อน

    Hi, Could you have a tutorial for it works with llava? I found out changed the model from hugging face will have different bugs depends on each model. It's really annoying...

    • @yeyulab
      @yeyulab 5 หลายเดือนก่อน

      Really, let me try it.

    • @ZexuanWang-zx9fd
      @ZexuanWang-zx9fd 5 หลายเดือนก่อน

      @@yeyulab Really appreciate it! Wait for your new video!

    • @ZexuanWang-zx9fd
      @ZexuanWang-zx9fd 5 หลายเดือนก่อน

      @@yeyulab The specific error I have encountered is 'LlavaProcessor' object has no attribute 'eos_token_id' and also apply_chat_template. Thanks!

  • @ThangNguyen-ot8uz
    @ThangNguyen-ot8uz 5 หลายเดือนก่อน

    Sorry i'm a newbie here, What's the advantage of using autogen compared to other RAG? Even if you use bare bone Ollama, local chat with Gemma is already possible

    • @yeyulab
      @yeyulab 5 หลายเดือนก่อน

      Multi-agent apps like AutoGen/CrewAI can work more precisely and deterministically for a "workflow" task compared to a single-agent LLM app which you need to be extremely careful on prompt design.

  • @madimakes
    @madimakes 5 หลายเดือนก่อน

    nice! just spent a week building one for another model...watching this now to see what ive missed!

    • @yeyulab
      @yeyulab 5 หลายเดือนก่อน

      Good luck! Let me know any questions when you are testing your project!

    • @madimakes
      @madimakes 5 หลายเดือนก่อน

      @@yeyulab thank you! currently having issues with the Groupchat and receiving function calling results (but i've successfully tackled function calling) dig in to the code due to the MSFT documentation not covering functions...

  • @user-jc6tj2xt1p
    @user-jc6tj2xt1p 5 หลายเดือนก่อน

    Why was your example using Google Colab instead of the Openrouter interface?

    • @yeyulab
      @yeyulab 5 หลายเดือนก่อน

      Sorry, what do you mean by that? "Openrouter Interface"?

  • @joebywan
    @joebywan 5 หลายเดือนก่อน

    What versions of modules etc are you using there? I'm seeing different output, looking like multiple attempts of the writer to contact the chat_manager before the chat_manager replies and hands off to the editor.

    • @yeyulab
      @yeyulab 5 หลายเดือนก่อน

      I am using 0.2.16 of pyautogen. Normally it's not the library issue as the embedded system prompt has not been changed through these versions, I also observed repeatedly speaking of the writer sometimes during the test and it was mostly because the manager cannot fully follow the accumulated prompt constructed by Autogen due to the model capability. You can try to refine the "description" of the two agents to make the sequence more clear.

  • @attilavass6935
    @attilavass6935 6 หลายเดือนก่อน

    I'd love to watch content about function calling (using skills in Autogen Studio) in the same LLM setup ( Ollama / Gemma ).

    • @yeyulab
      @yeyulab 5 หลายเดือนก่อน

      Function calling (or the tool usage) is a challenge for small LLMs, but it's possible and I will do that.

  • @nourabdou4118
    @nourabdou4118 6 หลายเดือนก่อน

    Thank you very Informative, do you think I could use Local LLM instead of OpenAI?

    • @yeyulab
      @yeyulab 6 หลายเดือนก่อน

      Yes, you can! The CrewAI uses LangChain as the foundation so multiple local deployment tools which integrated into LangChain like llama.cpp, HuggingFace's Transformers, or ollama are available and easy for use.

  • @IdPreferNot1
    @IdPreferNot1 6 หลายเดือนก่อน

    Alot of people are allergic to paying money for a wrapper service when you're using an open source model, even though its cheap as you outlined. Have you considered trying these kind of evaluations on something like Ollama, which has version of so many models, including Gemma, and can be self served as an endpoint for inference easily on a localhost:11434 server for endpoint and also now has python library with openai/openAPI equivalent API?

    • @yeyulab
      @yeyulab 6 หลายเดือนก่อน

      I am making that tutorial right now!

  • @Soniboy84
    @Soniboy84 6 หลายเดือนก่อน

    thanks for the video!

    • @yeyulab
      @yeyulab 6 หลายเดือนก่อน

      Thanks!

  • @ew3995
    @ew3995 6 หลายเดือนก่อน

    ok why is everyone saying that gemma is trash then?

    • @yeyulab
      @yeyulab 6 หลายเดือนก่อน

      Not sure if they were saying their own opinions with a complete test. Like what I was tested in the video, it's terrible for code and math, but good for writing in a multi-agent system.