[PR #1130] [CLOSED] docs: clarify vLLM video upload and source indicator behavior #1127

New issue

Closed

opened 2026-10-18 14:17:21 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-18 14:17:21 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/docs/pull/1130
Author: @shihanqu
Created: 3/4/2026
Status: ❌ Closed

Base: dev ← Head: docs/vllm-video-multimodal-notes

📝 Commits (1)

f929877 docs: clarify vLLM video upload and source indicator behavior

📊 Changes

1 file changed (+21 additions, -0 deletions)

View changed files

📝 docs/getting-started/quick-start/connect-a-provider/starting-with-vllm.mdx (+21 -0)

📄 Description

Summary

add vLLM quick-start documentation notes for multimodal video usage
clarify that No sources found can be expected for video-only turns without RAG citations
clarify that File type video/mp4 is not supported for processing refers to file-processing/retrieval path, not necessarily model multimodal inference failure
add a minimal direct API health check snippet for vLLM model listing

Why

Users connecting Open WebUI to vLLM for multimodal/video models can receive mixed UI signals:

valid model interpretation output
plus file-processing warning and/or no-citation indicator

This update documents expected behavior and reduces troubleshooting confusion.

_{🔄 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/1130 **Author:** [@shihanqu](https://github.com/shihanqu) **Created:** 3/4/2026 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `docs/vllm-video-multimodal-notes` --- ### 📝 Commits (1) - [`f929877`](https://github.com/open-webui/docs/commit/f929877b6a30effba7efd91183155788ee407577) docs: clarify vLLM video upload and source indicator behavior ### 📊 Changes **1 file changed** (+21 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `docs/getting-started/quick-start/connect-a-provider/starting-with-vllm.mdx` (+21 -0) </details> ### 📄 Description ## Summary - add vLLM quick-start documentation notes for multimodal video usage - clarify that `No sources found` can be expected for video-only turns without RAG citations - clarify that `File type video/mp4 is not supported for processing` refers to file-processing/retrieval path, not necessarily model multimodal inference failure - add a minimal direct API health check snippet for vLLM model listing ## Why Users connecting Open WebUI to vLLM for multimodal/video models can receive mixed UI signals: - valid model interpretation output - plus file-processing warning and/or no-citation indicator This update documents expected behavior and reduces troubleshooting confusion. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-18 14:17:21 +00:00