CREW AI tool not using ChatGroq

Question

Here is my tools.py file

import os 
from dotenv import load_dotenv
from langchain_groq import ChatGroq
from crewai_tools import PDFSearchTool, SerperDevTool

load_dotenv()

# Initialize the ChatGroq model
llm = ChatGroq(
    model="llama-3.1-70b-versatile",
    temperature=0.7,
    groq_api_key=os.getenv('GROQ_API_KEY'),
    verbose=True
)


os.environ['SERPER_API_KEY'] = os.getenv('SERPER_API_KEY')

# Initialize the tool allowing for any PDF content search if the path is provided during execution
pdf_tool = PDFSearchTool()

# Initialize the tool for internet searching capabilities
serper_tool = SerperDevTool()

also I have added

llm = ChatGroq(
    model="llama-3.1-70b-versatile",
    temperature=0.7,
    groq_api_key=os.getenv('GROQ_API_KEY'),
    verbose=True
)

in my agents.py also and mentioned in every Agent.

But when I run

python crew.py

the error comes:

UserWarning: Valid config keys have changed in V2:

• 'allow_population_by_field_name' has been renamed to 'populate_by_name'
• 'smart_union' has been removed warnings.warn(message, UserWarning) Traceback (most recent call last): File "D:\code\machine learning\Testing Models\Advance Multi Agent RAG\crew.py", line 2, in <module> from tasks import pdf_research_task, web_research_task, assistant_task File "D:\code\machine learning\Testing Models\Advance Multi Agent RAG\tasks.py", line 2, in <module> from tools import pdf_tool, serper_tool File "D:\code\machine learning\Testing Models\Advance Multi Agent RAG\tools.py", line 20, in <module> pdf_tool = PDFSearchTool() File "D:\code\machine learning\Testing Models\Advance Multi Agent RAG\myenv\lib\site-packages\crewai_tools\tools\pdf_search_tool\pdf_search_tool.py", line 32, in init super().init(**kwargs) File "D:\code\machine learning\Testing Models\Advance Multi Agent RAG\myenv\lib\site-packages\pydantic\main.py", line 193, in init self.pydantic_validator.validate_python(data, self_instance=self) File "D:\code\machine learning\Testing Models\Advance Multi Agent RAG\myenv\lib\site-packages\crewai_tools\tools\pdf_search_tool\pdf_search_tool.py", line 48, in _set_default_adapter app = App.from_config(config=self.config) if self.config else App() File "D:\code\machine learning\Testing Models\Advance Multi Agent RAG\myenv\lib\site-packages\embedchain\app.py", line 117, in init self.embedding_model = embedding_model or OpenAIEmbedder() File "D:\code\machine learning\Testing Models\Advance Multi Agent RAG\myenv\lib\site-packages\embedchain\embedder\openai.py", line 19, in init
  api_key = self.config.api_key or os.environ["OPENAI_API_KEY"] File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\os.py", line 680, in getitem raise KeyError(key) from None KeyError: 'OPENAI_API_KEY'

Please help me

I know about the document from crewai that I should try this way

tool = PDFSearchTool(
    config=dict(
        llm=dict(
            provider="ollama", # or google, openai, anthropic, llama2, ...
            config=dict(
                model="llama2",
                # temperature=0.5,
                # top_p=1,
                # stream=true,
            ),
        ),
        embedder=dict(
            provider="google", # or openai, ollama, ...
            config=dict(
                model="models/embedding-001",
                task_type="retrieval_document",
                # title="Embeddings",
            ),
        ),
    )
)

But how to use ChatGroq with it.

Answer 1

You only need to follow these steps; CrewAI natively supports Groq:

Set up Groq API key: Define the environment variable GROQ_API_KEY with your API key.

os.environ["GROQ_API_KEY"] = os.environ.get('GROQ_API_KEY')

Specify Groq model: In your CrewAI agent, use llm='groq/model' to select the model, example: Llama3.

Agent(
            config=self.agents_config['agent_example'],
            verbose=True,
            memory=True,
            llm='groq/llama3-70b-8192'
    )