Error while : from crewai import Agent,Task , Crew

[mohammad-gh009]

PackageNotFoundError: No package metadata was found for embedchain.

[robsonc]

I received the same error after install a totally fresh new project

[strnad]

same problem here, for me it was possible to fix it by installing embedchain from git instead of wheel.
pip install git+https://github.com/joaomdmoura/embedchain.git

[gromag]

Fresh new project, new python environment, first I got the same embedchain problem then after manually pip installing it I got:

from crewai_tools import SerperDevTool, BrowserbaseTool, ExaSearchTool
ImportError: cannot import name 'BrowserbaseTool' from 'crewai_tools'

I'm using the getting starter code:

import os

from langchain.llms import OpenAI
from crewai import Agent
from crewai_tools import SerperDevTool, BrowserbaseTool, ExaSearchTool
from dotenv import load_dotenv

load_dotenv("cred.env")

assert os.environ["OPENAI_API_KEY"] is not None
assert os.environ["SERPER_API_KEY"] is not None

search_tool = SerperDevTool()
browser_tool = BrowserbaseTool()
exa_search_tool = ExaSearchTool()

# Creating a senior researcher agent with advanced configurations
researcher = Agent(
    role="Senior Researcher",
    goal="Uncover groundbreaking technologies in {topic}",
    backstory=(
        "Driven by curiosity, you're at the forefront of innovation, "
        "eager to explore and share knowledge that could change the world."
    ),
    memory=True,
    verbose=True,
    allow_delegation=False,
    tools=[search_tool, browser_tool],
    allow_code_execution=False,  # New attribute for enabling code execution
    max_iter=15,  # Maximum number of iterations for task execution
    max_rpm=100,  # Maximum requests per minute
    max_execution_time=3600,  # Maximum execution time in seconds
    system_template="Your custom system template here",  # Custom system template
    prompt_template="Your custom prompt template here",  # Custom prompt template
    response_template="Your custom response template here",  # Custom response template
)

# Creating a writer agent with custom tools and specific configurations
writer = Agent(
    role="Writer",
    goal="Narrate compelling tech stories about {topic}",
    backstory=(
        "With a flair for simplifying complex topics, you craft engaging "
        "narratives that captivate and educate, bringing new discoveries to light."
    ),
    verbose=True,
    allow_delegation=False,
    memory=True,
    tools=[exa_search_tool],
    function_calling_llm=OpenAI(
        model_name="gpt-3.5-turbo"
    ),  # Separate LLM for function calling
)

# Setting a specific manager agent
manager = Agent(
    role="Manager",
    goal="Ensure the smooth operation and coordination of the team",
    verbose=True,
    backstory=(
        "As a seasoned project manager, you excel in organizing "
        "tasks, managing timelines, and ensuring the team stays on track."
    ),
    allow_code_execution=True,  # Enable code execution for the manager
)

[LarsAC]

The dependency in crewai is on embedchain-crewai, but that does not solve the problem for me either.

[gromag]

Did anyone get anywhere with this?

[JamesStallings]

This is giving me a problem as well; it seems that the tools depend on embedchain, which depends on langchain; so if you are using langchain-community, installing embed chain replaces it with langchain and breaks a lot of stuff....and you won't be able to import the tools.

[joaomdmoura]

Hey folks thanks for reporting the error, what version are you using? He did see this bug but should be fixed on 0.35.8

[joaomdmoura]

in the new version we will update the dependency with them as well to sue new versions

[wasimsafdar]

Does anybody know how to solve it? I followed and got this error.

[JamesStallings]

My experience is no one here is really interested in having crewai work with locally hosted LLM, and these calls for assistance are barely acknowledged and the issue quickly closed. My recommendation is to simply code your agents from scratch using python or node. It isn’t near as difficult as I had thought. The roughest part is the prompt engineering, and if you can’t get that part right, all the agentic frameworks in the world wont help. have a look at e.g., AICodeKing https://www.youtube.com/watch?v=w5of-CBDlfU (that might be an ‘I’ instead of an ‘l’) Don’t let the smarminess or the sybthesized voice track throw you off - there’s meat on them bones. ॐ♲ ♥ ☸☮ ☯☰☶☯☮ ☸ ♥ ♲ॐ KI5SMN

…

On Sun, Jul 21, 2024 at 6:09 AM Wasim Safdar ***@***.***> wrote: Does anybody know how to solve it? I followed and got this error. — Reply to this email directly, view it on GitHub <#846 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAA3PVRN42LQ6MHGVKP3AMTZNOJFFAVCNFSM6AAAAABKGC7IWCVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDENBRGU3DSNBTHE> . You are receiving this because you commented.Message ID: ***@***.***>

[joaomdmoura]

Hey folks, if there is an on going problem we would love to help, we do need more information though to be able to replicated it, like the versions being used, logs and some code to help us to it.

[joaomdmoura]

We update embedchain in the latest versions so this should be gone, but lmk if I'm wrong

[wasimsafdar]

I am following this tutorial. https://lablab.ai/t/mastering-ai-content-creation-leveraging-llama-3-and-groq-api. Is this error related to "langchain_groq"? I also installed embedchain but I do not know how to update imports.