Add support for docling reading local files#417
Merged
Conversation
Co-authored-by: Copilot <copilot@github.com>
ppinchuk
added
enhancement
Codecov Report❌ Patch coverage is
❌ Your patch status has failed because the patch coverage (23.52%) is below the target coverage (80.00%). You can increase the patch coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## main #417 +/- ##
==========================================
- Coverage 55.24% 54.99% -0.26%
==========================================
Files 62 62
Lines 5847 5870 +23
Branches 543 546 +3
==========================================
- Hits 3230 3228 -2
- Misses 2569 2593 +24
- Partials 48 49 +1
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
rajeee
pushed a commit
that referenced
this pull request
May 27, 2026
* Fix command * Bump elm version * Minor prompt update * Update lockfile * Fix linter * Documentation updates * First pass of GHP schema * Add basic plugin config * Wire up GHP plugin * Have function return created class * Clarification for noise * Clarification for setbacks * Clarification * Use general guidance instead * Add clarification to definitions * Single row instruction * Add clarification * Allow nulls * Add instruction * update instructions * Update instructions around null * Tighten schema * Updates to schema * Add debug statements * Update prompt * Add logging * More logging * Update descriptions * Update instructions * Add clarification * Add info * Add more info to logger * Add task ids * Trimmed * Update schema * Update prompt * Generalize implementation of `_get_model_config` and use it * Update logging statement * Change logging level * Fix import * Align playwright versions * Fix bug in llm config retrieval * Provide additional context even if user submits prompt * Fix pandas link * WIP * Fix env Co-authored-by: Copilot <copilot@github.com> * ELM updates (WIP) * Minor update * Minor cleanup * Minor cleanup * Rename func * Reduce redundancy * Minor refactor * CLarify argument * Add missing docs * Add docling support * Link to docling docs * Suppress numpy NaNmean warnings Co-authored-by: Copilot <copilot@github.com> * Add docling-based file loaders * Add `to_md_kwargs` * Include docling in logs * Minor updates * Use `COMPASSWebFileLoader` * Remove bad func * Change to FIleLoader Co-authored-by: Copilot <copilot@github.com> * Add tests for env Co-authored-by: Copilot <copilot@github.com> * Fix tests * Fix test * Fix for clarity * MInor fix * Pull from env var * Extra logging * Write files with correct extension * Minor cleanup * Use multiprocessing queue * Move subprocessing logging messages to `main.log` * Fix tests * Bump elm dep * Default to elm backend for now * FIx docs * Bug fix * Delay import * Revert change * Update env Co-authored-by: Copilot <copilot@github.com> * MInor change Co-authored-by: Copilot <copilot@github.com> * Try fix rust env Co-authored-by: Copilot <copilot@github.com> * Cleanup deps sightly Co-authored-by: Copilot <copilot@github.com> * No frozen in CI * Add mac intel to tests * Adjust test * update tox tests * Update deps * Update openai dep * No docling on Python 3.13 MacOS intel Co-authored-by: Copilot <copilot@github.com> * Try fix * Break out pixi toml * Fix build * Update package name * Use pixi.toml file for trigger * Bump elm dep * Add local loader based on docling * Fix tests * Update lockfile * OCR is now only enabled if user gives tesseract path * Skip heavy tests in GHA * GITHUB_ACTIONS = true when running tox tests --------- Co-authored-by: Copilot <copilot@github.com>
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
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.
Also bump elm dep, which brings c4ai dep to the latest