feat: add DoclingServeConverter integration#3173
Merged
julian-risch merged 4 commits intoMay 8, 2026
Merged
Conversation
Adds a new `docling-serve-haystack` integration with a `DoclingServeConverter` component that converts documents via a remote DoclingServe HTTP server instead of loading heavy ML dependencies locally (no PyTorch required). - Supports URLs, local file paths, and ByteStream sources - Export formats: Markdown (default), plain text, JSON - Both sync `run()` and async `arun()` methods - Configurable conversion options, timeout, and optional API key auth - Full unit test suite (mocked httpx) + integration test markers - CI workflow, labeler, coverage comment, and root README table entry Closes deepset-ai#2960
Adds a new DoclingServeConverter component that converts documents by sending them to a running docling-serve HTTP server. Supports local files, URLs, and ByteStreams; markdown, text, and JSON export formats; optional API key authentication; and both sync (run) and async (arun) execution. Closes deepset-ai#2960
SyedShahmeerAli12
requested review from
julian-risch
and removed request for
a team
github-actions
Bot
added
topic:CI
type:documentation
Contributor
Author
|
heyy ..... @julian-risch Key design decisions:
|
Contributor
Author
|
Merge conflicts resolved branch is now up to date with |
- Add `ghcr.io/docling-project/docling-serve` service to the workflow - Add `Run integration tests` and `Store combined coverage` steps - Add push-to-main trigger so integration tests run on merge - Add `integration-cov-append-retry` hatch script to pyproject.toml - Update README combined coverage badge from N/A to actual badge Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
julian-risch
approved these changes
May 8, 2026
Member
julian-risch
left a comment
julian-risch
left a comment
There was a problem hiding this comment.
Thank you for opening this pull request @SyedShahmeerAli12 . I extended it now by adding integration tests to the CI workflow and can confirm that the integration tests pass for me locally too.
7 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a
DoclingServeConvertercomponent that converts documents using a running docling-serve HTTP server, without any heavy ML dependencies (no PyTorch required).ByteStreamsourcesMARKDOWN,TEXT, andJSONexport formatsSecretrun) and asynchronous (arun) executionPart of #2960
Test plan
ruff check,ruff format)pytest -m integration)