Link Search Menu Expand Document
Start for Free

Stardog Voicebox Release Notes

Release - Apr 3, 2025

  • Improve LLM-generated dataset summaries
  • Support latency-optimized Bedrock endpoints
  • Improve error-handling for lineage computation
  • Handle more functions in SPARQL parsing and validation
  • Avoid invalid IRIs when creating data models within Designer

Release - Mar 20, 2025

  • Show data lineage and provenance in knowledge panels for each answered question

Lineage and provenance

  • Make failure messages more informative
  • Do not return queries with undefined terms
  • Improve automatic fallback to the RAG agent

Release - Feb 19, 2025

  • Knowledge panels in the Voicebox UI to show detailed information about answers
    • Show query results in a table with paging support
    • Support navigation through the links in tabular results
    • Show generated query in the panel in a visual way

New Knowledge Panel

  • [Preview] RAG support for question answering over document data
  • Fix repetition issues in entity summarization results
  • Show disambiguation sentences when there are multiple entities with the same label

Release - Feb 3, 2025

  • Instance panels in the Voicebox UI to show detailed information about instances and classes
    • For instances, show all associated types, attributes, and relationships
    • For classes, show all instances and related classes, attributes, and relationships
    • Support navigation through the graph by following links
    • Show breadcrumbs to display navigation state

New Instance Panel

  • Improve logging statements for on-prem deployments

Release - Jan 27, 2025

  • Make few shot example count configurable and increase the default count
  • Use fuzzy search when no entity is found to summarize
  • Fix settings selection for on-prem deployments
  • Support for Qwen and Anthropic models
  • Add support for Azure AI monitoring

Release - Jan 15, 2025

  • Simplify Voicebox configuration files
  • Allow reading configuration files form user-specified paths for on-prem deployments

Release - Dec 17, 2024

  • [Preview] Voicebox API access for asking questions programmatically
  • Improve question interpretation based on conversation history
  • Implement a new mechanism fo generating example questions
  • Return the labels of all IRIs included in query results
  • Add support for Azure AI

Release - Oct 17, 2024

  • Updated Voicebox UI
    • The initial release of an updated Voicebox UI! The full-page Voicebox experience and chat windows from cloud.stardog.com, Explorer, and Designer are updated. Highlights include:
      • Modern splash page with data summary and spotlight questions
      • A human-user to computer message presentation rather than a conversation
      • New action icons, including bringing back both positive and negative feedback
      • Ability to hide “Explain response”

New Voicebox home screen Voicebox question answer example

  • [Private Preview] Enable additional Voicebox agents for additional capabilities. New agents are are as follows:
    • Analytics agent - Analyze the previously returned tabular result to answer questions about trends, comparisons, outliers using LLM’s inferencing capabilities.
    • Computation agent - Use LLM’s code writing capabilities to do numeric computations over the previously returned tabular result
    • Chart agent - Create a chart using the previously returned tabular result based on user’s instruction
    • External LLM agent - Use the LLM’s background knowledge to answer the question instead of querying the Knowledge Graph

    Note: At this time, Voicebox will not automatically use these agents unless the user provides a hint (see below) to use an agent specifically.

  • Add support for hints to guide Voicebox when it makes mistakes. Hints are added to user questions with hashtags. For example:
    “#llm What is the capital of France?”
    Supported hints are grouped in two categories:
    • Hints to help Voicebox select the right agent
      • #analyze - Analyze the previously returned query results to answer the question
      • #chart - Create a chart using the previously returned query results
      • #compute - Perform a computation over the previously returned query results to answer the question
      • #llm - Use the external LLM to answer the question
      • #query - Query the knowledge graph to answer the question
      • #summary - Summarize the information about the entity mentioned in the question
    • Other hints
      • #nohistory - Ignore the conversation history while answering the question

    Note: The hints #analyze, #chart, #compute, #llm only works for users who are in the private preview for the new agents.

  • Add more context to the response if Voicebox cannot answer a question
  • Improve response times 20% by reducing agent selection and result summarization times
  • Infrastructure changes to collect more detailed metrics and to allow faster diagnosis of issues
  • Use asynchronous processes for Voicebox service to improve scalability
  • Add support to use LLMs hosted by Databricks if configured