Skip to content

Pull requests: aryn-ai/sycamore

New pull request New
28 Open 1,502 Closed
28 Open 1,502 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix several integration tests.
#1591 opened Feb 27, 2026 by bsowell Contributor • Draft
1
Add support for Anthropic stream response API
#1574 opened Feb 10, 2026 by austin-aryn-ai Contributor Loading…
1
Allow json reader to accept larger files; do not fail extract when no…
#1573 opened Feb 9, 2026 by austin-aryn-ai Contributor Loading…
1
Add a step through strategy that allows overlap
#1521 opened Nov 21, 2025 by austin-aryn-ai Contributor Loading…
1
Add a new cache implementation using DynamoDB
#1470 opened Sep 19, 2025 by austin-aryn-ai Contributor Loading…
97
Add HTTP LLM
#1467 opened Sep 12, 2025 by karanataryn Contributor Loading…
5
Update prompt for VLMTableStructureExtractor
#1457 opened Aug 30, 2025 by vikram-ak Contributor Loading…
Initial work on a pypdfium2 text extractor.
#1446 opened Aug 25, 2025 by bsowell Contributor • Draft
1
Flush to ensure data is written
#1421 opened Aug 6, 2025 by bohou-aryn Collaborator Loading…
streaming client usage example; submit only after client is updated
#1402 opened Jul 26, 2025 by eric-anderson Collaborator Loading…
Update html_ingest.py
#1395 opened Jul 21, 2025 by jchungAryn Loading…
Add OCR Caching
#1381 opened Jul 2, 2025 by karanataryn Contributor Loading…
43
Fix use of Huggingface
#1363 opened Jun 22, 2025 by austin-aryn-ai Contributor • Draft
1
Extend Explode to support customization
#1225 opened Mar 17, 2025 by austintlee Loading…
Rewrite llm query operator
#1216 opened Mar 6, 2025 by bohou-aryn Collaborator Loading…
11
Experimenting with test reporting
#1131 opened Jan 27, 2025 by bsowell Contributor • Draft
Add a lock for ray init to avoid multiple inits
#1112 opened Jan 14, 2025 by austintlee Loading…
1
Split tables horizontally in split_elements if the column headers are big enough to make splitting hard
#1104 opened Jan 9, 2025 by HenryL27 Collaborator Loading…
Local doc cache support for document reconstruct
#1066 opened Dec 7, 2024 by austintlee Loading…
8
Improve os read
#1065 opened Dec 6, 2024 by austintlee Loading…
4
Add a globalstate in context
#1044 opened Nov 28, 2024 by baitsguy Contributor Loading…
Data Model for tree structured Document Representation
#1022 opened Nov 13, 2024 by bohou-aryn Collaborator Loading…
20
Updated chunker.py
#986 opened Oct 26, 2024 by Ranjana761 Loading…
8
Update Makefile.docker-base
#965 opened Oct 22, 2024 by AranavMahalpure Loading…
9
Initial attempt at straightforward document processing script.
#731 opened Aug 27, 2024 by alexaryn Collaborator • Draft
4
ProTip! Mix and match filters to narrow down what you’re looking for.