Hello Bradon, thank you so much for the video!! very helpful. I set up on Windows with python 3.12 and visual studio. All went successfully till python main.py. after inputting answers to 4 questions, it gave me the following error. searched online, no luck to fix so far. Wonder if you can share some insight ( i am new ) not sure what is missing. Really appreciate if you or anyone can help. Thanks in advance!!... File "C:\Python_projects\crewai_starter_test20240514\main.py", line 90, in <module> result = trip_crew.run() ^^^^^^^^^^^^^^^ File "C:\Python_projects\crewai_starter_test20240514\main.py", line 28, in run plan_itinerary = tasks.plan_itinerary( ^^^^^^^^^^^^^^^^^^^^^ File "C:\Python_projects\crewai_starter_test20240514\tasks.py", line 52, in plan_itinerary return Task( ^^^^^ File "C:\Python312\Lib\site-packages\crewai\task.py", line 100, in __init__ super().__init__(**config, **data) File "C:\Python312\Lib\site-packages\pydantic\main.py", line 176, in __init__ self.__pydantic_validator__.validate_python(data, self_instance=self) pydantic_core._pydantic_core.ValidationError: 1 validation error for Task expected_output Field required [type=missing, input_value={'description': " **Task...ng travel iteneraries.)}, input_type=dict] For further information visit errors.pydantic.dev/2.7/v/missing

Is there a Windows version?

This is almost exactly what I was looking for. If I'm trying to not have the user use their own API key, what would be the best course of action given chrome's policies? I'm thinking connecting to a database (firebase?), storing my API key there, running the prompts on the back end and then returning just the text to the client side. Does this sound like an efficient course of action?

Thanks for great tutorial. We need more crewai + nextjs projects !! It would be really cool if you could also show us beginners on how to actually deploy the project on vercel

it cant be but so smart if it suggested the floating market in thailand. everyone there knows thats faked sherade but the books say otherwise.

These are great tutorials. However, considering that this was a follow up CrewAI video to the original, it would have been super helpful to update or re-build the original example project (Travel Agent) instead of starting a new project. As a beginner, its harder for me to understand the updates and features when I'm also having to correlate them back and forth between the projects.

Oh that's cool, **python has a spread operator as ... JavaScript! Didn't know that!

Bro, I heard that Crew Ai is planning to incorporate API calls to agents using a YAML file structure. I'm curious why you never use YAML files in your folder hierarchy?

I got this up and running on a Pi5 with Ollama and Phi3

Thanks man, it was my first working complex project in my local. Appreciated.

This is an awesome tutorial!! Thanks so much.

on second note i believe the problem is the chomd command. i have zero dev experience, can someone help pls?

so i see in visual studio you use python and for me only powershell is selectable even after installing python and adding to environment path. how can i add it so i can actually follow along what you are doing?

i am seriously going to need to watch this like 5 times. ChatGPT, explain this video to me like I am 5

Is there an easy way to build No Code AI Assistants or Agents with Groq? I know zero code

Unliked not giving correct source code: Connect CrewAI to LLama 2 (Simple Example)

Loved the video! Thanks so much and keep up the great work! 🧡

I cannot find the code for this video in your githubrepo.

why not just do all of it using Langgraph?

thanks! this was very helpful

This video is your Billie Jean on a Thriller album full of Number 1 Hits - not sure you can top it LOL! OMG YOU WERE BORN TO TEACH!!!!

Thanks for the fantastic tutorial Brandon. I watched 5 other videos to learn function calling and this was hands down the best explanation! And I appreciate you providing the code for testing your assistant. If I hadn't come across your video, I would have written one myself. You saved me at least 5+ hours!

thanks for the video!, ehat is your openIA subscription? The 20 USD month is enought?

Great tutorial, just a couple of things. It would be great to talk about how the output from an agent would feed the subsequent input to the next chained agent. For example travel_manager -> city_selection_expert -> local_tour_guide. For your gather_city_info task, you list city as an input variable, however, all you do is feed the 'cities' variable into it. This is supposed to be our chosen city from the previous agent if I'm not mistaken? In your example, you're making the city_selection_agent redundant.

Light theme 😮

can you create an video using the inbuild tools in crew ai . for example CSVSearchTool, RagTool etc

I am stuck at 1:19:02 . import { ThreadMessage } from "openai/resources/beta/threads/index.mjs"; is no longer working. I was not able to find ThreadMessage in this path. Can you please help me out?

gyus do u know any way to run crewai and\or llama on gpu? only CPU is soooooooooooooooooooooooo sloooooooooooooow

Thanks for the informative video tutorial! Watching your content has been incredibly helpful in expanding my understanding of AI. I've gained valuable insights, even comparing it to Flowise and other platforms. While I'm still a beginner and haven't been able to fully implement your tutorials yet, they've provided me with a solid foundation and a clear view of how things are structured. Please keep up the great work, and I look forward to seeing more beginner-level tutorials in the future! btw I get this unicode error, which i fixed by removing the emoji in the email templates. 🙂 File "C:\Users\Srika\.conda\envs\.ayoutube\lib\encodings\cp1252.py", line 19, in encode return codecs.charmap_encode(input,self.errors,encoding_table)[0] UnicodeEncodeError: 'charmap' codec can't encode character '\U0001f449' in position 1879: character maps to <undefined>

Hello please I am having some typescript errors in the chatpage, text and type How can I schedule a chat with you?

perfect run with Groq. I get great speeds on my PC with Local LLAMA3, but nothing I can do stops it throwing errors. I find that before with other projects thgat a lot of local LLMs have odd issues that change each run from failing to run functions as they change the name to just saying they cant pass tool info. Must be something in the local limitations either with Ollama or CrewAi.

More great tutes. But for me something not working with "search_tool.py" and maybe SERPER API KEY, giving error - "It seems we encountered an unexpected error while trying to use the tool. This was the error: 'organic'" EDIT SOLVED: turns out you cant put # comments at the end of KEY= statements in .env , it was sending my comment along with the key, and when you change .env you need to restart the terminal for changes to be picked up (VSCode, with conda).

Whats next, show your skills? 1. CodeCraft Duel: Super Agent Showdown 2. Pixel Pioneers: Super Agent AI Clash 3. Digital Duel: LLM Super Agents Battle 4. Byte Battle Royale: Dueling LLM Agents 5. AI Code Clash: Super Agent Showdown 6. CodeCraft Combat: Super Agent Edition 7. Digital Duel: Super Agent AI Battle 8. Pixel Pioneers: LLM Super Agent Showdown 9. Byte Battle Royale: Super Agent AI Combat 10. AI Code Clash: Dueling Super Agents Edition

Environment variables loaded from .env Prisma schema loaded from prisma\schema.prisma Datasource "db": PostgreSQL database "crew_ai_visualizer", schema "public" at "localhost:5432" Error: P1000: Authentication failed against database server at `localhost`, the provided database credentials for `postgres` are not valid.

Thanks for the info.. I’m always curious, if ai and agents are relatively new, how did you learn all of this?

I guess you're system is not sending out code to yahoo emails.

How to integrate DSpy with crewAI?

Good usage of CrewAi

I get a error, then I noticed that we need search api, I added that but still get the error pydantic_core._pydantic_core.ValidationError: 1 validation error for Task expected_output Field required [type=missing, input_value={'description': "Analyze ...e business landscapes.)}, input_type=dict]

Excellent tutorial, thanks a lot Brandon!

Hey @bhancock_ai Nice video, Thanks for the video, Was going trough the code and trying to modify, so that we could be able to run the code using ollama? Since i was trying to create something similar using langchain, IMAP email fetch and watch dog etc, this solution is much more better, do you think you can help? I need the understanding on how we can run the same setup with using different

This is super clear, thankyou so much!

Can someone pls tell all the dependencies that I would hv to install for this

Hi where is the homepage link?

On a PC, first time using poetry, after several attempts to finally getting "$ poetry install --no-root" to work without complaints, "$ poetry env list" shows nothing.

Would be cool to have a state pointer object with methods on it and then only pass the methods to nodes. That might make the state updates a bit clearer. Is that possible here? Coming from golang, so not really a python person.

Workflow has it's use, however, State Machine is better for this purpose and more resilient.

Do we actually need CrewAI ?? I could make a python script that has many function that has to work in a sequential manner. Each function uses openAI to get the output that will be used by the next function. For automation, I can use cronjob for periodically youtube researching.

langchain crash course

absolute gold. great tutorial. thanks for offering it.