Skip to content
Merged
Changes from 1 commit
Commits
Show all changes
23 commits
Select commit Hold shift + click to select a range
18c58db
feat: Add multimodal support for Office documents
takeruhukushima Nov 1, 2025
95e6e25
solve dependencies problem
takeruhukushima Nov 1, 2025
2f32c8a
fix bug
takeruhukushima Nov 1, 2025
f7cc49d
[pre-commit.ci lite] apply automatic fixes
pre-commit-ci-lite[bot] Nov 1, 2025
e42e636
Merge remote-tracking branch 'origin/feature/new-doc-types'
takeruhukushima Nov 1, 2025
c801103
fix:pre-commit fail src/paperqa/readers.py
takeruhukushima Nov 2, 2025
5e49ca1
add .docx,.pptx,.xlsx in settings.py
takeruhukushima Nov 2, 2025
65c5097
refactor(chunks):consolidating the chunk code for office and pdf
takeruhukushima Nov 2, 2025
5ead779
edit README.md:add .docx, .xlsx, .pptx, and code files (e.g., .py, .t…
takeruhukushima Nov 2, 2025
a7c5e3a
refactor: Unify chunking algorithm name for PDF and office documents
takeruhukushima Nov 2, 2025
5fe86c1
feat: Add unstructured version to office document parsing metadata
takeruhukushima Nov 2, 2025
d4619bd
feat: Implement lazy import for unstructured in office document parsing
takeruhukushima Nov 2, 2025
0be33fe
feat: Add unit test for office document parsing
takeruhukushima Nov 2, 2025
0775523
[pre-commit.ci lite] apply automatic fixes
pre-commit-ci-lite[bot] Nov 2, 2025
84c6bf2
feat: Update test_parse_office_doc for Gemini models and RAG query
takeruhukushima Nov 2, 2025
e218d91
add mailmap takerufukushima
takeruhukushima Nov 2, 2025
4933f16
fix pre-commit error
takeruhukushima Nov 2, 2025
77b95cc
Merge branch 'feature/new-doc-types' of https://github.com/takeruhuku…
takeruhukushima Nov 2, 2025
280c381
Fix: Address linting issues in test_paperqa.py
takeruhukushima Nov 2, 2025
d95ed9f
feat: Improve questions and assertions in test_parse_office_doc
takeruhukushima Nov 3, 2025
057c7f8
feat: Enhance office document parsing tests and assertions
takeruhukushima Nov 3, 2025
f4975fc
Minor tweaks to test_parse_office_doc
jamesbraza Nov 3, 2025
7bfad14
Updating assertions in other tests for this PR's changes
jamesbraza Nov 3, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
edit README.md:add .docx, .xlsx, .pptx, and code files (e.g., .py, .t…
…s, .yaml)
  • Loading branch information
takeruhukushima committed Nov 2, 2025
commit 5ead779da439ff04576d4b2b205e8e0df9166dff
6 changes: 3 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)
![PyPI Python Versions](https://img.shields.io/pypi/pyversions/paper-qa)

PaperQA2 is a package for doing high-accuracy retrieval augmented generation (RAG) on PDFs or text files,
PaperQA2 is a package for doing high-accuracy retrieval augmented generation (RAG) on PDFs, text files, Microsoft Office documents, and source code files,
with a focus on the scientific literature.
See our [recent 2024 paper](https://paper.wikicrow.ai)
to see examples of PaperQA2's superhuman performance in scientific tasks like
Expand Down Expand Up @@ -395,7 +395,7 @@ It just removes the automation associated with an agent picking the documents to
```python
from paperqa import Docs, Settings

# valid extensions include .pdf, .txt, .md, and .html
# valid extensions include .pdf, .txt, .md, .html, .docx, .xlsx, .pptx, and code files (e.g., .py, .ts, .yaml)
doc_paths = ("myfile.pdf", "myotherfile.pdf")

# Prepare the Docs object by adding a bunch of documents
Expand Down Expand Up @@ -438,7 +438,7 @@ from paperqa import Docs

async def main() -> None:
docs = Docs()
# valid extensions include .pdf, .txt, .md, and .html
# valid extensions include .pdf, .txt, .md, .html, .docx, .xlsx, .pptx, and code files (e.g., .py, .ts, .yaml)
for doc in ("myfile.pdf", "myotherfile.pdf"):
await docs.aadd(doc)

Expand Down
Loading