OpenParable
Skip to content
← Back to skills

Add Function Body

Development
add-function-body

Add Function Body is an Agent Skill for development published in the onnx/onnx repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Add a function body definition to an ONNX operator, defining how it decomposes into simpler ops. Use when asked to make an op decomposable, add a FunctionBody, implement SetContextDependentFunctionBodyBuilder, or express an op in terms of other ONNX operators.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/onnx/onnx/blob/HEAD/.agents/skills/add-function-body/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/add-function-body, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Follow the full guide in docs/AddFunctionBody.md.

File Locations

ComponentFile
Function body definitiononnx/defs/<domain>/defs.cc (inline with schema)
FunctionBuilder utilitiesonnx/defs/function.h
Function testsonnx/test/cpp/function_get_test.cc, onnx/test/cpp/function_verify_test.cc

Method 1: Simple String-Based Function Body

ONNX_OPERATOR_SET_SCHEMA(
    LessOrEqual, 16,
    OpSchema()
        // ... inputs, outputs, type constraints ...
        .TypeAndShapeInferenceFunction(inferenceFunction)
        .FunctionBody(R"ONNX(
        {
            O1 = Less (A, B)
            O2 = Equal (A, B)
            C = Or (O1, O2)
        }
        )ONNX"));

With explicit opset version:

        .FunctionBody(R"ONNX(...)ONNX", 18)  // Valid from opset 18

Referencing attributes with @attr_name:

        .FunctionBody(R"ONNX(
          {
            Alpha = Constant <value_float: float = @alpha>()
            AlphaCast = CastLike (Alpha, X)
            ...
          }
        )ONNX")

Method 2: Context-Dependent Function Body

For ops whose decomposition varies based on attributes or optional inputs:

static bool BuildFunctionBodyMyOp(
    const FunctionBodyBuildContext& ctx,
    const OpSchema& schema,
    FunctionProto& functionProto) {
  FunctionBuilder builder(functionProto);
  // Build graph based on ctx.hasInput(), ctx.getAttribute(), etc.
  builder.Add("output = SomeOp (input)");
  schema.BuildFunction(functionProto);
  return true;
}

// Register:
    .SetContextDependentFunctionBodyBuilder(BuildFunctionBodyMyOp)

FunctionBuilder API

FunctionBuilder builder(functionProto);
builder.Add("Y = Relu (X)");                          // Add node
builder.Const("alpha", std::vector<float>{0.01f});    // Constant tensor
builder.Const1D("axes", int64_t(1));                  // 1-D constant
builder.Add(R"(                                       // Multi-line
    X_Sub = Sub (X, X_Max)
    X_Exp = Exp (X_Sub)
)");
builder.AddOpset("", 18);                             // Opset dependency
schema.BuildFunction(functionProto);                  // Finalize
return true;

Multiple Opset Versions

    .SetContextDependentFunctionBodyBuilder(builderForOpset13)
    .SetContextDependentFunctionBodyBuilder(builderForOpset18, 18)

ONNX Function Body Syntax

Function body strings use the ONNX text format ("onnxtxt"). See the onnxtxt skill for the full syntax cheat sheet, attribute references (@attr_name), Constant <value = ...> forms, CastLike vs Cast, body-subgraph idioms, and parser tests. Quick reminders specific to function bodies:

  • Variable names are local intermediates; input/output names must match the schema's declared names.
  • Reference enclosing-op attributes with @attr_name — and only those declared in .Attr(...) calls.
  • Use CastLike (not Cast) when the target type depends on another input.

Code Style: Prefer Named Functions

Define context-dependent function body builders as separate named functions rather than inline lambdas within ONNX_OPERATOR_SET_SCHEMA. The macro expansion makes setting breakpoints on inline lambdas unreliable in debuggers.

Simple string-based .FunctionBody(R"ONNX(...)ONNX") definitions don't have this issue.

After Making Changes

python onnx/defs/gen_doc.py
lintrunner -a --output oneline

Common Mistakes

  • Forgetting schema.BuildFunction(functionProto) at end of context-dependent builders
  • Forgetting to return true from the builder function
  • Variable names conflicting with input/output names
  • Using Cast instead of CastLike for dynamic type matching
  • Function body not producing all declared outputs
  • Using @attr_name for an attribute not declared in .Attr() calls