Support for DoclingServiceClient via protocol

[phact]

adds support for both docling served and managed docling by introducing

class ConversionBackend(Protocol):
    """Structural interface for local and service-backed Docling conversion."""

    @property
    def convert(self) -> Callable[..., ConversionResult]:
        """Return the backend-specific conversion callable."""
        ...

DoclingLoader can now take DoclingServiceCient as the converter

[github-actions]

✅ DCO Check Passed

Thanks @phact, all your commits are properly signed off. 🎉

[mergify]

Merge Protections

🔴 2 of 2 protections blocking · waiting on 👀 reviews and 🙋 you

	Protection	Waiting on
🔴	Enforce conventional commit	🙋 you
🔴	Require two reviewer for test updates	👀 reviews

🔴 Enforce conventional commit

Waiting for

• title ~= ^(fix|feat|docs|style|refactor|perf|test|build|ci|chore|revert)(?:\(.+\))?(!)?:

This rule is failing.

Make sure that we follow https://www.conventionalcommits.org/en/v1.0.0/

• title ~= ^(fix|feat|docs|style|refactor|perf|test|build|ci|chore|revert)(?:\(.+\))?(!)?:

🔴 Require two reviewer for test updates

Waiting for

• #approved-reviews-by >= 2

This rule is failing.

When test data is updated, we require two reviewers

• #approved-reviews-by >= 2

[dolfim-ibm]

@phact this looks very good to me. I'm only wondering (maybe for a future iteration) if we could offer a simple way for langchain users to use the Docling Service Client without installing the whole docling package which includes the heavt AI runtimes.

For the Docling MCP project we did it like this https://github.com/docling-project/docling-mcp/blob/main/pyproject.toml#L45-L58 (for inspiration)

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!