v1.1.1

Full Changelog: v1.1...v1.1.1

v1.1

What's Changed

• HTML processor that preserves markdowns by @Matthew2357 in #106
• Create a CI to push to harbor automatically by @Androz2091 in #124
• No crash if the processor is asked to process an empty folder by @fabnemEPFL in #130
• Fix of Accept empty folder by @fabnemEPFL in #133
• ci: create production-config with environment variables by @Androz2091 in #128
• API fixes by @fabnemEPFL in #139
• support for google drive by @Matthew2357 in #117
• Fix results directory creation side effect on postprocessing by @MichelDucartier in #142
• CLI for RAG supporting web rag by @Matthew2357 in #105
• Bump many dependencies thanks to @dependabot[bot]: selenium, numpy, datatrove, langchain-aws, langchain, pydantic, validators, langchain-openai, actions/checkout, ragas, typing-extensions, httpx, actions/checkout, actions/download-artifact, datasets
• Update installation instructions for RCP user settings by @Androz2091 in #155
• Support CPU and GPU images by @Androz2091 in #156
• Add documentation to deploy on RCP (and later to production) by @Androz2091 in #157
• Update scheduler_file path to use ROOT_OUT_DIR by @Androz2091 in #158
• Add websearch by @laetitia-wilhelm in #86
• pre-commit autoupdate 2025-09-04 by @cclauss in #161
• Fix typos discovered by codespell by @cclauss in #162
• GitHub Actions: Test on the latest stable version of Python by @cclauss in #163
• README update by @Stefanstud in #164

New Contributors

• @Matthew2357 made their first contribution in #106
• @laetitia-wilhelm made their first contribution in #86
• @cclauss made their first contribution in #161

Full Changelog: v1.0.1...v1.1

v1.0.1

What's Changed

• fix: update marker-pdf to fix 'KeyError: encoder' in PDF ingest by @Restioson in #103
• Bump uvicorn from 0.32.1 to 0.34.3 by @dependabot in #99
• Bump accelerate from 1.6.0 to 1.7.0 by @dependabot in #98
• Bump actions/checkout from 3 to 4 by @dependabot in #96
• doc: install instructions for Ubuntu 24.04 (noble) by @Restioson in #104
• Automatic linting by @fabnemEPFL in #107
• Bump transformers from 4.52 to 4.52.4 by @dependabot in #101
• Bump requests from 2.32.3 to 2.32.4 by @dependabot in #109
• Bump pymongo from 4.9.2 to 4.13.2 by @dependabot in #108
• docker: change user, add nvidia instructions and a cache folder by @Androz2091 in #90
• Bump starlette from 0.41.3 to 0.47.0 by @dependabot in #100
• Bump langchain-huggingface from 0.1.2 to 0.3.0 by @dependabot in #110
• Add various improvements for CHUV applications by @MichelDucartier in #111
• Live retrieval API with index API and retriever API by @charlottemeyr, @fabnemEPFL and @leagrieder in #94
• Bump pandas from 2.2.3 to 2.3.0 by @dependabot in #115

New Contributors

• @Restioson made their first contribution in #103
• @dependabot made their first contribution in #99
• @Androz2091 made their first contribution in #90
• @MichelDucartier made their first contribution in #111

Full Changelog: v1.0.0...v1.0.1

v1.0.0

hello there!

What's Changed

• Unique temporary file names by adding process ID prefix by @Stefanstud in #22
• Add .eml processor implementation (#11) by @Stefanstud in #25
• tests for processors - local by @Stefanstud in #30
• Feature/rag evaluation by @Marc-antoineallard74 in #28
• Feature/post proc by @paultltc in #34
• [FT] Adding filters by @paultltc in #37
• [FT] Endpoint LLM by @paultltc in #39
• Bug/dependencies by @Stefanstud in #33
• [FT] mmore embeddings by @paultltc in #41
• Add docstrings, improve logging, and fix naming in processors by @Stefanstud in #32
• Filter images for pdf fast mode. Issue #21 by @Stefanstud in #42
• [FT] PP refactor by @paultltc in #48
• [FT] Refine loading strategy + config args for the PP modules by @paultltc in #49
• Niowniow revamp installation by @paultltc in #56
• Reorganize project and installation by @niowniow in #43
• [Refactor] Update Process Engine by @paultltc in #57
• Distributed Huge Fix by @DavidKalajdzic in #58
• Restart process pipeline & complete dashboard by @DavidKalajdzic in #51
• All kinds of fixes by @fabnemEPFL in #61
• Issue62 unit tests by @leagrieder in #67
• Add dashboard doc by @fabnemEPFL in #68
• Fix rag config by @fabnemEPFL in #71
• Fix logging, fix some imports, indexer API by @fabnemEPFL in #74
• Fix postprocessing by @fabnemEPFL in #75
• Fix links docs by @fabnemEPFL in #76
• Many fixes on types, imports, logic by @fabnemEPFL in #82
• Fix coding style by @fabnemEPFL in #83
• HTML processor by @fabnemEPFL in #84
• Process distributed doc by @fabnemEPFL in #85
• Fix the documentation, docker, dependencies, structure of the code and many small fixes by @fabnemEPFL in #87
• small fixes about distributed processing by @fabnemEPFL in #88
• Fix distributed processing and various fixes by @fabnemEPFL in #89
• Fixes rag & retriever API by @fabnemEPFL in #93
• Add GitHub workflow actions by @paultltc in #78

New Contributors

• @Stefanstud made their first contribution in #22
• @Marc-antoineallard74 made their first contribution in #28
• @paultltc made their first contribution in #34
• @niowniow made their first contribution in #43
• @DavidKalajdzic made their first contribution in #58
• @fabnemEPFL made their first contribution in #61
• @leagrieder made their first contribution in #67

Full Changelog: https://github.com/swiss-ai/mmore/commits/v1.0.0