Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[FEATURE] Implement set_knowledge Method in BaseAgent to Enable Knowledge Integration​ #2385

Closed
Programmer-RD-AI opened this issue Mar 17, 2025 · 0 comments
Labels
feature-request New feature or request

Comments

@Programmer-RD-AI
Copy link

Feature Area

Core functionality

Is your feature request related to a an existing bug? Please link it here.

NA

Describe the solution you'd like

In CrewAI, the BaseAgent class currently includes a set_knowledge method that is not implemented:

def set_knowledge(self, crew_embedder: Optional[Dict[str, Any]] = None):
    pass

Implementing this method is essential for agents to utilize external knowledge sources effectively. The implementation should allow agents to access various data types, such as:

  • Text files
  • PDFs
  • CSV files
  • JSON files
  • Web pages
  • YouTube videos
  • Documentation websites

By enabling agents to incorporate these knowledge sources, we can enhance their ability to provide informed and contextually relevant responses. This aligns with CrewAI's goal of creating intelligent agents capable of accessing and utilizing external information during their tasks.

Describe alternatives you've considered

An alternative approach could involve creating specialized agent subclasses with their own methods for handling knowledge integration. However, this would lead to code redundancy and inconsistency across different agents. Implementing the set_knowledge method within the BaseAgent class ensures a standardized and scalable solution for knowledge integration across all agents.

Additional context

Implementing the set_knowledge method would also facilitate the use of CrewAI's Retrieval-Augmented Generation (RAG) Tool, which allows agents to query dynamic knowledge bases for relevant information. This tool supports various data sources, including PDFs, CSVs, JSON files, web pages, and more, enabling agents to provide contextually accurate responses. citeturn0search2

Willingness to Contribute

Yes, I'd be happy to submit a pull request

@Programmer-RD-AI Programmer-RD-AI added the feature-request New feature or request label Mar 17, 2025
devin-ai-integration bot added a commit that referenced this issue Mar 17, 2025
…ration (fixes #2385)

Co-Authored-By: Joe Moura <joao@crewai.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
feature-request New feature or request
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant