[PR #1350] [CLOSED] docs: add external document extraction documentation #1326

New issue

Closed

opened 2026-10-18 14:18:52 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-18 14:18:52 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/docs/pull/1350
Author: @memologoped
Created: 8/11/2026
Status: ❌ Closed

Base: main ← Head: add-external-docs

📝 Commits (1)

9a30b5a docs: add external document extraction documentation

📊 Changes

1 file changed (+113 additions, -0 deletions)

View changed files

➕ docs/features/chat-conversations/rag/document-extraction/external.md (+113 -0)

📄 Description

Summary

This PR adds missing documentation for the External document extraction engine.

While the external extraction method is already available in the Open WebUI admin settings, it currently has no dedicated documentation page (unlike Apache Tika, Docling, and Mistral OCR). This gap forces users to dig through GitHub issues and source code to figure out how to integrate their own extraction services.

The new page (docs/features/chat-conversations/rag/document-extraction/external.md) covers:

A high-level overview of what the External engine is and when to use it (scaling, custom OCR, PII filtering).
Step-by-step configuration via the Admin Panel.
A complete API specification for developers building the external service, including:
- HTTP method (PUT to {URL}/process)
- Required headers (Content-Type, Authorization, X-Filename)
- Expected JSON response format (page_content + metadata)
A working minimal example of a FastAPI server that implements the required contract.

This documentation was written by inspecting the ExternalDocumentLoader source code in the main repository to ensure accuracy against the actual implementation.

Community discussion: https://github.com/open-webui/open-webui/discussions/17621 (users asking how to set up an external extraction engine)
Related PR adding filename encoding fix: https://github.com/open-webui/open-webui/pull/17013 (referenced in the docs to explain header encoding behavior)

Checklist

I have reviewed the relevant documentation and matched the existing style.
This PR meets Open WebUI's contribution standards: it is accurate, relevant to users, narrowly scoped, maintainable, and not promotional content, advertising, lead generation, SEO placement, or a request to list a product, service, provider, integration, gateway, tool, or company primarily for visibility.
I understand that PRs that do not meet these standards may be closed without review and will not be merged. Repeated, low-quality, off-topic, promotional, or intentionally misleading submissions may result in the contributor being blocked from future participation in Open WebUI repositories.

Notes for reviewers

The sidebar_position: 5 was chosen to place the page after Docling (3) and Mistral OCR (4).
The FastAPI example uses @app.api_route("/process", methods=["PUT", "POST"]) to be resilient to future method changes, though the current loader only uses PUT.
I verified the API contract by reading backend/open_webui/retrieval/loaders/external_document.py in the main repo.
No existing pages were modified — this is a purely additive change.

_{🔄 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/open-webui/docs/pull/1350 **Author:** [@memologoped](https://github.com/memologoped) **Created:** 8/11/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `add-external-docs` --- ### 📝 Commits (1) - [`9a30b5a`](https://github.com/open-webui/docs/commit/9a30b5a0af1d1468a851a4aca8ae1737c67f2927) docs: add external document extraction documentation ### 📊 Changes **1 file changed** (+113 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `docs/features/chat-conversations/rag/document-extraction/external.md` (+113 -0) </details> ### 📄 Description ## Summary This PR adds missing documentation for the **External** document extraction engine. While the `external` extraction method is already available in the Open WebUI admin settings, it currently has no dedicated documentation page (unlike Apache Tika, Docling, and Mistral OCR). This gap forces users to dig through GitHub issues and source code to figure out how to integrate their own extraction services. The new page (`docs/features/chat-conversations/rag/document-extraction/external.md`) covers: - A high-level overview of what the External engine is and when to use it (scaling, custom OCR, PII filtering). - Step-by-step configuration via the Admin Panel. - A complete API specification for developers building the external service, including: - HTTP method (`PUT` to `{URL}/process`) - Required headers (`Content-Type`, `Authorization`, `X-Filename`) - Expected JSON response format (`page_content` + `metadata`) - A working minimal example of a FastAPI server that implements the required contract. This documentation was written by inspecting the `ExternalDocumentLoader` source code in the main repository to ensure accuracy against the actual implementation. ## Related issue or discussion - Community discussion: https://github.com/open-webui/open-webui/discussions/17621 (users asking how to set up an external extraction engine) - Related PR adding filename encoding fix: https://github.com/open-webui/open-webui/pull/17013 (referenced in the docs to explain header encoding behavior) ## Checklist - [x] I have reviewed the relevant documentation and matched the existing style. - [x] This PR meets Open WebUI's contribution standards: it is accurate, relevant to users, narrowly scoped, maintainable, and not promotional content, advertising, lead generation, SEO placement, or a request to list a product, service, provider, integration, gateway, tool, or company primarily for visibility. - [x] I understand that PRs that do not meet these standards may be closed without review and will not be merged. Repeated, low-quality, off-topic, promotional, or intentionally misleading submissions may result in the contributor being blocked from future participation in Open WebUI repositories. ## Notes for reviewers - The `sidebar_position: 5` was chosen to place the page after Docling (3) and Mistral OCR (4). - The FastAPI example uses `@app.api_route("/process", methods=["PUT", "POST"])` to be resilient to future method changes, though the current loader only uses `PUT`. - I verified the API contract by reading `backend/open_webui/retrieval/loaders/external_document.py` in the main repo. - No existing pages were modified — this is a purely additive change. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-18 14:18:52 +00:00