Open Semantic Interchange Format¶

Actian AI Analyst supports the Open Semantic Interchange (OSI) format for exporting and importing semantic layers across tools.

What is OSI?¶

OSI is a vendor-agnostic, open-source specification for semantic model exchange across AI agents, BI platforms, and analytics tools. It was initiated by Snowflake together with Salesforce, dbt Labs, and other players, and is governed as an open standard under the Apache 2.0 license. Participating organizations include Actian AI Analyst, Tableau, Qlik, ThoughtSpot, Omni, Sigma, Alation, Select Star, and others.

Actian AI Analyst to OSI Mapping¶

Actian AI Analyst Entity	OSI Entity	Notes
Environment	`semantic_model`	Container for the export
Model	`datasets`	Direct mapping
Model.sourcePath	`datasets.source`	Formatted as `db.schema.table`
Model.grain	`datasets.primary_key`	Array of column names
Model.agentGuidance	`datasets.ai_context`	Combined with description
ModelDimension	`datasets.fields`	With expression dialect
ModelDimension (temporal)	`fields.dimension.is_time`	Boolean flag
ModelMeasure	`datasets.fields`	`ai_context`: "Measure. Unit: X..."
ModelRelationship	`relationships`	`from_columns`/`to_columns` as arrays
Metric	`metrics`	Expression with dialect
GlossaryTerm	`ai_context`	"Also known as: term, synonym1..."

What's NOT Exported in OSI¶

OSI is a lightweight interchange format. The following Actian AI Analyst-specific features are not included:

Filters - OSI has no filters concept
Agents - No OSI equivalent
Glossary definitions - Only terms/synonyms are preserved as ai_context
Enum value descriptions - Only values are listed
Sample data - Not part of OSI spec

Info

For complete backups that preserve all details, use the Actian AI Analyst Lossless format instead.

OSI Output Example¶

# OSI (Open Semantic Interface) Export
# Generated by Actian AI Analyst
# Environment: My Analytics
# Exported at: 2026-01-28T10:30:00.000Z
---
semantic_model:
  - name: "My Analytics"
    description: "Exported from Actian AI Analyst"
    ai_context: "Source: actian-ai-analyst. Environment ID: env_123"

    datasets:
      - name: "orders"
        source: "mydb.analytics.orders"
        primary_key: ["order_id"]
        description: "Order transactions"
        fields:
          - name: "order_date"
            expression:
              dialects:
                - dialect: "ANSI_SQL"
                  expression: "order_date"
            dimension:
              is_time: true
            ai_context: "Time grains: DAY, MONTH, YEAR"
          - name: "total_amount"
            expression:
              dialects:
                - dialect: "ANSI_SQL"
                  expression: "SUM(amount)"
            ai_context: "Measure. Unit: USD. Precision: 2."

    relationships:
      - name: "orders_to_customers"
        from: "orders"
        to: "customers"
        from_columns: ["customer_id"]
        to_columns: ["id"]

    metrics:
      - name: "total_revenue"
        expression:
          dialects:
            - dialect: "ANSI_SQL"
              expression: "SUM(orders.amount)"
        description: "Total revenue"
        ai_context: "Anchor model: orders. Unit: USD."