I tried 1 bit models and the output is not clear.

How do i allow interruption?

Outstanding! Can you add function calling, how? Thanks!

Great job! Would it very complicated to achieve this with LangGraph?

Could you check the git repo, its not working properly.. config w text is working okayish but the audio config isnt working

Isn't it multimodal able anyway from the beginning on as gemini 2.0 flash? Or was your dev for local purposes?

!! Please carefully use the library Twikit mentioned in this video, X may suspend the account that frequently scrapes the platform.

😮😮😮😮 bro you are the hidden champ in the youtube ❤❤❤❤❤

awesome video man. thanks for sharing! I had one visual question on how you are getting those curved borders on your Mac applications? Is that something you did under the hood for mac OS or there an app for this?

baaaaaaaaaaaaaaaaaaaaaaad

I want to apply this UI to Microsoft's AutoGen Magentic-One

That is where problem? 2024-11-28 15:39:56,819 Error running application handler <panel.io.handlers.ScriptHandler object at 0x0000022F47AE30A0>: 'material' File 'base.py', line 118, in __init__: theme = self._themes[theme]() Traceback (most recent call last): File "D:\anaconda3\envs\agent\lib\site-packages\panel\io\handlers.py", line 405, in run exec(self._code, module.__dict__) File "D:\crewaipro esearch_crew\src esearch_crew\main.py", line 8, in <module> from research_crew.crew import ResearchCrew File "D:\crewaipro esearch_crew\src esearch_crew\crew.py", line 11, in <module> chat_interface = pn.chat.ChatInterface() File "D:\anaconda3\envs\agent\lib\site-packages\panel\chat\interface.py", line 165, in __init__ params["widgets"] = [ChatAreaInput(placeholder="Send a message")] File "D:\anaconda3\envs\agent\lib\site-packages\panel\widgets\base.py", line 115, in __init__ super().__init__(**params) File "D:\anaconda3\envs\agent\lib\site-packages\panel eactive.py", line 634, in __init__ super().__init__(**params) File "D:\anaconda3\envs\agent\lib\site-packages\panel eactive.py", line 124, in __init__ super().__init__(**params) File "D:\anaconda3\envs\agent\lib\site-packages\panel\viewable.py", line 709, in __init__ self._update_design() File "D:\anaconda3\envs\agent\lib\site-packages\panel\viewable.py", line 727, in _update_design self._design = self._instantiate_design(design, config.theme) File "D:\anaconda3\envs\agent\lib\site-packages\panel\viewable.py", line 718, in _instantiate_design return design(theme=theme) File "D:\anaconda3\envs\agent\lib\site-packages\panel\theme\base.py", line 118, in __init__ theme = self._themes[theme]() KeyError: 'material'

Ca you integrate this with a flows crew?

Love the CrewAi videos!

thank you so much for this tutorial. Do you know how to fine tuning this reasoning with PPO and human feedback(RLHF) ? I saw an interface from argilla one time but I lost the link.

great work! thanks,

I understand the reason for switching from Streamlit to Panel. However the problem I have is that CrewAI's _ask_human_input takes human input only once. If you have an agent who needs to interactively request some data then CrewAI does not support this. However an agent can call a Tool how many ever times it wants to. So I have implemented your logic into a _ask_human_input_tool as a workaround. It works but I am yet to implement the UI for this using Panel.

Truly awesome! Many thanks!! Exactly what I was looking for!

how about using LangChain for RAG, can that work as well?

Thank you for sharing this!

Excellent! 👏

hi Yeyu, this is what I was looking for !! - Thanks Unfortunately none of the Agents call backs are working for me .. I am using panel version 1.5.3 and crewai 0.70.1 . I Did add call back the tasks which provide some info through the chat but .. Help please .

Will it support PDF Upload / RAG ?

Better than Langgraph?

What about the query which doesn't need to call the function?

What do you think about the OpenAI Swarm framework vs Agency Swarm? Is this still the more promising one?

Thank for the code. I tried it but it does not return any response after putting the question

Awesome video!

🎯 Key points for quick navigation: 00:00 *📘 Introducción a Llama 3.2 y aplicaciones en dispositivos* - Presentación de los modelos ligeros Llama 3.2, especialmente los de 1B y 3B. - Comparación con los modelos medianos que destacan en comprensión visual compleja. - Capacidades multilingües y generación de texto de los modelos pequeños para aplicaciones en dispositivos. 02:31 *🔧 Función de llamada: Teoría y herramientas* - Explicación de la capacidad de llamada de funciones en modelos de lenguaje. - Introducción a la librería Instructor y Pydantic para definir y validar funciones. - Ventajas de implementar llamadas de funciones con modelos base no ajustados. 04:14 *💻 Ejemplo práctico: Función financiera con Llama 3.2* - Definición de la función dummy "get_revenue" utilizando modelos Pydantic. - Proceso de instalación de paquetes necesarios como "openai", "pydantic" e "instructor". - Configuración del API y preparación del entorno para ejecutar la función financiera. 06:16 *🛠️ Validación y ejecución de funciones generadas* - Ejecución del modelo Llama 3.2 1B para generar llamadas de funciones estructuradas. - Validación de la salida JSON que incluye el nombre de la función y sus argumentos. - Integración y ejecución de la función basada en los argumentos proporcionados por el modelo. 08:39 *🏠 Construcción de un sistema de hogar inteligente* - Definición de múltiples funciones como "set_temperature" y "toggle_lights" para controlar dispositivos. - Uso del modelo Llama 3.2 3B con Instructor para procesar comandos de usuario. - Demostración interactiva de comandos y respuestas del sistema en un entorno de hogar inteligente. 12:14 *✅ Conclusiones y beneficios de la automatización con Llama 3.2* - Importancia de conectar APIs reales y interfaces de hardware para automatizar acciones. - Ventajas económicas de utilizar modelos de código abierto como Llama 3.2. - Invitación a suscribirse al canal y próximos tutoriales para continuar innovando. Made with HARPA AI

Thank you so much for this video! That's exactly what I was looking for :)

I want to deploy to website I would can we do. .

Hi can you try function call with the latest version of vllm and pyautogen? because the method you proposed is not working again. Thanks

Excellent video covering what I imagine llama-index(smart-guys) have purporsefully developed as a more robust agent system that bets on the stronger performance of the next generation of foundation models.... exactly what Altman and other model builders suggest. Look forward to more on this framework in the future.

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.

can you help with crewai working with django

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!

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?

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...

Thanks 🙏

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

Awesome tutorial! 👏

can u please upload the video autogen with web sockets

Thank you for the video 🎉🎉

Good stuff! 👍

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

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

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

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!

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.'"

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)