Code Documentation for Software Development

The integration of CrewAI with NVIDIA NIM is demonstrated with a blueprint for building AI agents specialized in code documentation.

This blueprint showcases the flexibility of CrewAI when combined with NVIDIA to solve real world challenges, such as improving and automating software documentation processes.

This use case addresses critical issues such as inconsistent documentation processes, and maintenance challenges. By leveraging the power of CrewAI and NVIDIA NIM, teams can enhance productivity, minimize confusion and streamline the creation and maintenance of high-quality software documentation. Developers can use this flexible reference blueprint to update an existing CrewAI solution with NVIDIA AI, create new software documentation agent, or apply it to a different use case that includes CrewAI and NVIDIA.

Architecture Diagram

Key Features

This reference architecture leverages CrewAI and Llama 3.3-70B LLM NIM and NeMo Retriever E5 embedding NIM as its underlying LLM and embedding model respectively, to generate comprehensive, high-quality documentation for GitHub repositories. The system employs a multi-agent workflow divided into two key stages:

Ingestion Phase

• WebsiteSearchTool: This tool is used to embed and index mermaid examples from mermaid.js.org website using NVIDIA NeMo Retriever E5 embedding NIM.

Agent Flow

1. Codebase Analysis and Strategy Planning:

   • Analyze Codebase: Planner agents inspect the repository to map its structure, identify key components, and understand interdependencies.
   • Develop Strategy: They create a tailored documentation plan based on the analysis.

2. Documentation Creation and Review:

   • High-Level Documentation: One agent generates clear, comprehensive documentation introducing the project and its architecture.
   • Quality Assurance: Another agent ensures accuracy, consistency, and completeness across all documentation.

Minimum System Requirements

The solution leverages NVIDIA's cloud-based API Catalog endpoints, eliminating the need for local GPU hardware. All model inference is performed on NVIDIA's cloud infrastructure.

Software used in this blueprint

NIM microservices

• Llama 3.3 70B NVIDIA NIM
• NeMo Retriever E5 embedding NIM

3rd-Party Technologies

• CrewAI

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility, and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure the models meet requirements for the relevant industry and use case and address unforeseen product misuse. For more detailed information on ethical considerations for the models, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards. Please report security vulnerabilities or NVIDIA AI concerns here.

License

Use of the models in this blueprint is governed by the NVIDIA AI Foundation Models Community License.

Terms of Use

GOVERNING TERMS: The blueprint is governed by the NVIDIA Agreements | Enterprise Software | NVIDIA Software License Agreement and NVIDIA Agreements | Enterprise Software | Product Specific Terms for AI Product.

Meta Llama 3.3 70B

GOVERNING TERMS: The NIM container is governed by the NVIDIA Software License Agreement and the Product Specific Terms for AI Products;

NVIDIA Retrieval QA E5 Embedding Model

Use of this model is governed by MIT license.

Use of these models is governed by the NVIDIA AI Foundation Models Community License Agreement. ADDITIONAL INFORMATION: Llama 3.3 Community License Agreement, Built with Llama.