langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-22 20:35:34 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[PR #3371] [CLOSED] docs: Add pdfmux PDF document loader integration #3426

New Issue
Closed
opened 2026-06-05 18:23:04 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 18:23:04 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/3371
Author: @NameetP
Created: 3/30/2026
Status: ❌ Closed

Base: main ← Head: docs/add-pdfmux-document-loader

📝 Commits (1)

  • 63f8e4e docs: Add pdfmux PDF document loader integration

📊 Changes

2 files changed (+104 additions, -0 deletions)

View changed files

📝 src/oss/python/integrations/document_loaders/index.mdx (+1 -0)
➕ src/oss/python/integrations/document_loaders/pdfmux.mdx (+103 -0)

📄 Description

Summary

Adds documentation for PDFMux, a PDF extraction orchestrator available as langchain-pdfmux (v0.2.0) on PyPI.

What is PDFMux?

Most PDF loaders use a single extraction method and silently fail on complex layouts. PDFMux solves this by automatically routing each page to the optimal extractor based on content type (text-heavy, scanned, tables, mixed). Key features:

  • Smart routing — selects the best parser per page automatically
  • Confidence scoring — every document chunk includes a quality score (0.0–1.0), enabling RAG pipelines to filter or re-rank by extraction quality
  • Self-healing — retries with alternative extractors when the primary one returns low-quality output
  • Quality presets — fast, standard, and high modes for different use cases

Changes:

  • Added src/oss/python/integrations/document_loaders/pdfmux.mdx — full integration page following the existing loader doc pattern
  • Updated src/oss/python/integrations/document_loaders/index.mdx — added PDFMux to the PDFs category table

Links:

Test plan

  • Verify the new page renders correctly at /oss/python/integrations/document_loaders/pdfmux
  • Verify the PDFs table on the index page includes the new PDFMux entry with working link
  • Confirm pip install langchain-pdfmux installs successfully and the code examples work

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/docs/pull/3371 **Author:** [@NameetP](https://github.com/NameetP) **Created:** 3/30/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `docs/add-pdfmux-document-loader` --- ### 📝 Commits (1) - [`63f8e4e`](https://github.com/langchain-ai/docs/commit/63f8e4ea1c2fe57a616bbc5fbe99fe753713a9ab) docs: Add pdfmux PDF document loader integration ### 📊 Changes **2 files changed** (+104 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `src/oss/python/integrations/document_loaders/index.mdx` (+1 -0) ➕ `src/oss/python/integrations/document_loaders/pdfmux.mdx` (+103 -0) </details> ### 📄 Description ## Summary Adds documentation for [PDFMux](https://pdfmux.com), a PDF extraction orchestrator available as [`langchain-pdfmux`](https://pypi.org/project/langchain-pdfmux/) (v0.2.0) on PyPI. **What is PDFMux?** Most PDF loaders use a single extraction method and silently fail on complex layouts. PDFMux solves this by automatically routing each page to the optimal extractor based on content type (text-heavy, scanned, tables, mixed). Key features: - **Smart routing** — selects the best parser per page automatically - **Confidence scoring** — every document chunk includes a quality score (0.0–1.0), enabling RAG pipelines to filter or re-rank by extraction quality - **Self-healing** — retries with alternative extractors when the primary one returns low-quality output - **Quality presets** — fast, standard, and high modes for different use cases **Changes:** - Added `src/oss/python/integrations/document_loaders/pdfmux.mdx` — full integration page following the existing loader doc pattern - Updated `src/oss/python/integrations/document_loaders/index.mdx` — added PDFMux to the PDFs category table **Links:** - PyPI: https://pypi.org/project/langchain-pdfmux/ - Source: https://github.com/NameetP/langchain-pdfmux - Website: https://pdfmux.com ## Test plan - [ ] Verify the new page renders correctly at `/oss/python/integrations/document_loaders/pdfmux` - [ ] Verify the PDFs table on the index page includes the new PDFMux entry with working link - [ ] Confirm `pip install langchain-pdfmux` installs successfully and the code examples work --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 18:23:04 -04:00
yindo closed this issue 2026-06-05 18:23:04 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#3426
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?