> ## Documentation Index
> Fetch the complete documentation index at: https://honeydew.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Open Semantic Interchange

The [Open Semantic Interchange (OSI)](https://github.com/open-semantic-interchange/OSI)
is a vendor-neutral, open-source specification for portable semantic
model definitions. It gives BI tools, AI agents, and warehouses a
shared YAML/JSON format for datasets, relationships, fields, and metrics,
so the same definitions can travel across tools without manual
reconciliation.

Honeydew is one of the founding partners of OSI, alongside Snowflake,
Salesforce, and dbt. Portable semantics are
core to how Honeydew approaches a semantic layer: the same metric or
attribute definition should mean the same thing in every tool that
consumes it. See the
[announcement post](https://honeydew.ai/blog/osi-is-cool-why-honeydew-joined-open-semantic-interchange/)
for context on why Honeydew joined.

<Note>
  OSI is an early specification under active development (current draft
  `0.2.0.dev0`). Concepts, field names, and mappings may change before the
  specification stabilizes.
</Note>

## Concept Mapping

OSI and Honeydew model the same problem space, but the granularity
differs. The table below maps each OSI concept to its Honeydew equivalent.

| OSI Concept                          | Honeydew Equivalent                                                              |
| ------------------------------------ | -------------------------------------------------------------------------------- |
| `semantic_model`                     | A Honeydew [workspace](/docs/architecture)                                            |
| `dataset`                            | An [Entity](/docs/modeling/entities) with its [Source Data](/docs/modeling/source-data)    |
| `dataset.source`                     | Entity [Source Data](/docs/modeling/source-data)                                      |
| `dataset.primary_key`, `unique_keys` | Entity granularity and [unique keys](/docs/modeling/entities)                         |
| `relationship`                       | A [Relation](/docs/modeling/relations) between entities                               |
| `field` (column reference)           | A [Source Attribute](/docs/modeling/source-data#columns)                              |
| `field` (computed expression)        | A [Calculated Attribute](/docs/calculations/attributes)                               |
| `field.dimension.is_time`            | A time attribute, often backed by a [time spine](/docs/advanced-modeling/time-spines) |
| `metric`                             | A [Metric](/docs/calculations/metrics)                                                |
| `expression.dialects`                | Compiled to the target warehouse dialect (Snowflake, Databricks, BigQuery)       |
| `ai_context`                         | [AI Metadata](/docs/integration/context-layer/ai-metadata) on the object              |
| `custom_extensions`                  | Honeydew-specific properties in the [YAML schema](/docs/yaml-schema)                  |

### Concepts Honeydew Adds Beyond OSI

OSI defines the portable metadata layer. Honeydew implements that layer
and adds the operational machinery a semantic layer needs in production:

* **Query compiler and BI integration** — metrics and attributes compile
  to warehouse SQL exposed through
  [SQL](/docs/integration/sql-interface), [XMLA](/docs/integration/xmla-interface),
  [GraphQL](/docs/integration/graphql-api), and [MCP](/docs/integration/mcp)
  interfaces, with native integrations on top of those interfaces into
  [Power BI](/docs/integration/bi-tools/powerbi),
  [Tableau](/docs/integration/bi-tools/tableau),
  [Excel](/docs/integration/bi-tools/excel), and
  [other BI tools](/docs/integration/bi-tools/supported-tools).
* **AI Context Layer** — OSI carries `ai_context` metadata on
  individual objects; Honeydew adds a full
  [context layer](/docs/integration/context-layer/context-management) above
  the semantic layer (instructions, analytical skills, external
  business knowledge, and historical memory) and an agentic AI
  analysis engine that combines context retrieval with semantic
  compilation — [deep analysis](/docs/integration/context-layer/deep-analysis),
  [agents](/docs/integration/context-layer/agents),
  [Slack](/docs/integration/context-layer/slack-app), and
  [Teams](/docs/integration/context-layer/teams-app) apps.
* **Domains** — [hierarchical projections](/docs/domains) of the same
  semantic model for different audiences (finance vs. marketing,
  regional sales, an AI agent's scope). A domain selects entities and
  fields, applies mandatory filters, and overrides parameters; domains
  extend and compose other domains, so one model serves many
  perspectives without duplication.
* **Aggregate awareness** — semantic-aware query rewriting to
  [pre-aggregated tables](/docs/performance/aggregate-awareness), alongside
  [incremental aggregate updates](/docs/performance/aggregate-incremental-updates)
  and [entity caching](/docs/performance/entity-caching) for further
  performance.
* **Security and access control** —
  [row-level security](/docs/security/row-level-security) and
  [access control](/docs/access-control/user-access-control), enforced from
  the query interface down to the warehouse.
* **Workflow, environments, and deployment** — the semantic model is
  YAML and inherently git-native; Honeydew adds the workflow around it:
  [workspaces](/docs/governance/workspaces),
  [environments](/docs/governance/environments), and promotion paths for
  dev/staging/prod.

## Converting To and From OSI

Honeydew provides a bidirectional converter between OSI and the
Honeydew workspace format:

* **OSI → Honeydew** — import an OSI semantic model and produce a
  Honeydew workspace (entities, relations, attributes, metrics, AI
  metadata). See [Import Tools](/docs/migration/import-tools#open-semantic-interchange-osi).
* **Honeydew → OSI** — export a Honeydew workspace as an OSI semantic
  model for consumption by other tools that support OSI.

Because OSI is still evolving, the converter tracks the current draft
of the specification and may change as OSI stabilizes.

## Stay Updated

The OSI specification is evolving. Track progress on the
[OSI GitHub repository](https://github.com/open-semantic-interchange/OSI)
and [working groups](https://github.com/open-semantic-interchange/OSI/blob/main/docs/working_groups.md).