Vectice Docs
API Reference (Latest)Vectice WebsiteStart Free Trial
Latest
Latest
  • 🏠Introduction
    • Vectice overview
      • Autolog
      • Next-Gen Autolog [BETA]
      • AskAI
      • Vectice for financial services
  • 🏁Quickstart
    • Getting started
    • Quickstart project
    • Tutorial project
    • FAQ
  • ▶️Demo Center
    • Feature videos
  • 📊Manage AI/ML projects
    • Organize workspaces
      • Create a workspace
      • Workspace Dashboard
    • Organize projects
      • Create a project
      • Project templates best practices
    • Invite colleagues
    • Define phase requirements
    • Collaborate with your team
  • 🚀Log and Manage Assets with Vectice API
    • API cheatsheets
      • Vectice Python API cheatsheet
      • Vectice R API cheatsheet
    • Connect to API
    • Log assets to Vectice
      • Autolog your assets
      • Log datasets
      • Log models
      • Log attachments and notes
      • Log code
      • Log a custom data source
      • Log assets using Vectice IDs
      • Log dataset structure and statistics
      • Log custom metadata in a table format
      • Log MLFLow runs
    • Retrieve assets from app
    • Manage your assets
    • Manage your iteration
    • Preserve your code and asset lineage
  • 🤝Create Model documentation and reports
    • Create model documentation with Vectice Reports
    • Streamline documentation with Macros
    • Auto-document Models and Datasets with AskAI Prompts
    • Document phase outcomes
  • 🗂️Admin Guides
    • Organization management
    • Workspace management
    • Teams management
    • User management
      • User roles and permissions
      • Update a user role in your organization
      • Activate and deactivate users
      • Reset a user's password
    • Manage report templates
  • 🔗Integrations
    • Integrations Overview
    • Integrate Vectice with your data platform
  • 💻IT & Security
    • IT & Security Overview
    • Secure Evaluation Environment Overview
    • Deployment
      • SaaS offering (Multi-Tenant SaaS)
      • Kubernetes self-hosted offering
        • General Architecture & Infrastructure
        • Kubernetes on GCP
          • Appendices
        • Kubernetes on AWS
          • Appendices
        • Kubernetes on Azure
          • Appendices
        • GCP Marketplace deployment
        • On premise
        • Configuration
      • Bring Your Own LLM Guide
    • Data privacy
    • User management
    • SSO management
      • Generic SAML integration
      • Okta SSO integration
    • Security
      • Data storage security
      • Network Security
        • HTTPS communication
        • Reverse proxy
        • CORS/CSRF
        • VPC segregation
      • Sessions
      • Secrets and certificates
      • Audit logs
      • SOC2
      • Security updates
      • Best practices
      • Business continuity
    • Monitoring
      • Installation guide
      • Customizing the deployments
    • Maintenance & upgrades
    • Integrating Vectice Securely
  • ⭐Glossary
    • Concepts
      • Workspaces
      • Projects
        • Setup a project
      • Phases
      • Iterations
        • Iterative development
      • Datasets
        • Dataset resources
        • Dataset properties
        • Dataset lineage and versions
      • Models
      • Reports
  • 🎯Release notes
    • Release notes
  • ↗️References
    • Vectice Python API Reference
    • Vectice R API Cheatsheet
    • Notebooks and code samples
    • Vectice website
Powered by GitBook
On this page
  • AskAI Prompts
  • Summarize model
  • Compare models
  • Extract feature engineering from Datasets
  • Extract feature engineering from Datasets with enriched iteration
  • Advanced use cases: Analyze tables and CSV inside prompt
  • Macro Prompts
  • Prompt 1
  • Prompt 2
  • Prompt 3

Was this helpful?

  1. Create Model documentation and reports

Auto-document Models and Datasets with AskAI Prompts

PreviousStreamline documentation with MacrosNextDocument phase outcomes

Last updated 4 months ago

Was this helpful?

AskAI empowers data scientists to generate clear, tailored documentation for iterations, models, or datasets with ease. Whether using the “Ask Me Anything” feature for custom prompts or documenting directly from your assets using Macros, AskAI ensures all key details are documented seamlessly—so you can focus on your work, not the paperwork.

AskAI Prompts

Below, we have crafted some basic prompts to get you started auto-documenting with AskAI.

To generate documentation based on your assets and phases, use AskAI's "Ask me anything" feature and use the /character to select the desired assets or phrases.

Summarize model

The following AI prompt will summarize your model's technique, performance metrics and insert attachments.

Generate a summary of the model {{ MDV-163 }}. Explain the metrics and insert attachments related to performance.

Prompt output:

Compare models

The following AI prompt will generate a detailed comparison of multiple models, highlighting differences in technique, training data, and results.

Compare the following models {{ MDV-162 }} and {{ MDV-163 }}. Focus on differences in their techniques, training data, and performance outcomes.

Prompt output:

Extract feature engineering from Datasets

Prompt to derive the feature engineering that happened between 2 datasets. The LLM will look at the distribution of the columns and all of the metadata and infer the feature engineering.

Explain what feature engineering and transformations that happened between those 2 datasets {{ DTV-358 }} and {{ DTV-370 }}. 

Prompt output:

Extract feature engineering from Datasets with enriched iteration

Alternatively, you can provide more information to your Prompt to derive more based on iteration.

Explain what feature engineering and transformations that happened between those 2 datasets {{ DTV-358 }} and {{ DTV-370 }}. Based on this iteration {{ ITR-223 }}, go deeper in the feature engineering process and provide extensive detail about what happened. 

Prompt output:

Advanced use cases: Analyze tables and CSV inside prompt

The following prompt allows you to pass a table or CSV file directly into the prompt, enabling AskAI to analyze and summarize the data seamlessly. This option is ideal for generating insights, summaries, or comparisons based on structured data.

Use the "/" or "." character to effortlessly autocomplete prompts while typing, ensuring smooth and accurate asset integration.

Prompt output:

Macro Prompts

Alternatively, prompts can be found and inserted within macros. These prompts tend to be more intricate and often contain detailed expectations for the output, which are crucial for generating comprehensive documentation. Below are a few examples.

You can customize and modify predefined Macro Prompts to align them with your specific needs and requirements.

Prompt 1

This is the prompt inside the macro 'Model overview'. These prompts are more complex and give you a predefined structure and tone of voice. Here, the prompt is just a standalone:

Once you run this macro, the results will look something like this:

Prompt 2

This is the prompt inside the macro 'Model improvements'. It combines the macrostructure and a prompt to allow you to analyze the differences between models more thoroughly.

Here are the results of running this Macro prompt:

Prompt 3

This is the prompt inside the macro 'Model alternatives'. As before, the advanced prompt can manage multiple model inputs.

The result of running this macro prompt:

Overall, AskAI combines ease of use with powerful prompts that you can customize, ensuring you can capture and communicate the value of your projects with minimal effort.

🤝