
Overview
This pipeline is a Generative AI based solution designed to analyze code repositories. Each programmer has their own way of building and structuring code files in their repositories. This pipeline is capable of understanding the directory structure, extracting all the relevant script files and analysing each one of them. For each python script in the codebase, four corresponding JSON files are produced. A JSON for the script level understanding which includes information on the different functions defined, classes defined, imports etc. The second JSON is for functional level understanding comprising of all the relevant metadata pertaining to each function. Third JSON for a class level understanding and lastly the pseudocode for each python script is produced. All these artifacts are used to populate a Neo4J database which can be queried by the user to generate meaningful visualizations and graphically understand the inter-dependencies between scripts in the codebase.
Highlights
- Code Review and Optimization: Developers and teams can use this pipeline to streamline the code review process by quickly identifying areas for improvement or optimization within the codebase. The generated pseudocode can help reviewers understand the logic and intent of the code, leading to more efficient and accurate reviews, as well as better collaboration between team members. They can also visualize the entire pipeline, identify the data flow, identify the sequence in which functions are called and much more which helps in faster debugging and problem isolation.
- Onboarding New Team Members: When new developers join a project or team, they often face the challenge of understanding the existing codebase and its structure. This pipeline can ease this onboarding process by providing a clear and concise analysis of the code, including functions, classes, and relationships between components. This helps new team members get up to speed faster and contributes to a smoother transition.
- Documentation and Knowledge Sharing: This pipeline can be used to generate documentation and facilitate knowledge sharing among team members or stakeholders. By automatically generating pseudocode and providing in-depth analysis of the codebase, the pipeline can assist in creating comprehensive documentation that accurately represents the project's functionality and structure. This can be particularly useful when handing off a project to another team or sharing information with non-technical stakeholders.
Details
Unlock automation with AI agent solutions

Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $10.00 |
ml.m5.large Inference (Real-Time) Recommended | Model inference on the ml.m5.large instance type, real-time mode | $5.00 |
ml.m5.large Training Recommended | Algorithm training on the ml.m5.large instance type | $5.00 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $10.00 |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $10.00 |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $10.00 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $10.00 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $10.00 |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $10.00 |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $10.00 |
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Amazon SageMaker algorithm
An Amazon SageMaker algorithm is a machine learning model that requires your training data to make predictions. Use the included training algorithm to generate your unique model artifact. Then deploy the model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Version release notes
This is the first version.
Additional details
Inputs
- Summary
The input is a json where user can ask a query regarding his repository.
- Limitations for input type
- The fields mentioned in the input description are all mandatory and should follow the same naming convention.
- Input MIME type
- application/zip, application/gzip, text/csv, application/json
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
user_query | The question user wants to ask about his repository | Type: FreeText | Yes |
Resources
Vendor resources
Support
Vendor support
For any product support you can reach out to us at:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.