[GH-ISSUE #22880] issue: Models like Gemini and Claude fail when a message contains only file/image attachment without text #58498

Closed
opened 2026-05-05 23:17:42 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @ShirasawaSama on GitHub (Mar 20, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22880

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
  • I am using the latest version of Open WebUI.

Installation Method

Git Clone

Open WebUI Version

v0.8.10

Ollama Version (if applicable)

No response

Operating System

MacOS 26

Browser (if applicable)

No response

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

The UI should prevent sending in this case (or auto-insert a minimal text prompt), so users don’t hit model errors.

Actual Behavior

The request fails (or the model returns an error), because content contains only attachment(s) with no text.

Steps to Reproduce

  1. Open chat web UI.
  2. Select a model such as Gemini or Claude (Opus/Sonnet/Haiku).
  3. Upload a file or image.
  4. Leave the text input empty.
  5. Click send.

Logs & Screenshots

data: {"error": "messages: text content blocksmust be non-empty"}

Additional Information

Can refer to the code below:

		if (userPrompt === '' && files.length > 0) {
			const hasImages = files.some(
				(file) => file.type === 'image' || (file?.content_type ?? '').startsWith('image/')
			);
			const hasNonImages = files.some(
				(file) => file.type !== 'image' && !(file?.content_type ?? '').startsWith('image/')
			);

			if (hasImages && !hasNonImages) {
				userPrompt = $i18n.t('Analyze the image content');
			} else if (!hasImages && hasNonImages) {
				userPrompt = $i18n.t('Summarize the information in the file');
			} else {
				userPrompt = $i18n.t('Analyze the image and file contents');
			}
		}
Originally created by @ShirasawaSama on GitHub (Mar 20, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/22880 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!). - [x] I am using the latest version of Open WebUI. ### Installation Method Git Clone ### Open WebUI Version v0.8.10 ### Ollama Version (if applicable) _No response_ ### Operating System MacOS 26 ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior The UI should prevent sending in this case (or auto-insert a minimal text prompt), so users don’t hit model errors. ### Actual Behavior The request fails (or the model returns an error), because content contains only attachment(s) with no text. ### Steps to Reproduce 1. Open chat web UI. 2. Select a model such as Gemini or Claude (Opus/Sonnet/Haiku). 3. Upload a file or image. 4. Leave the text input empty. 5. Click send. ### Logs & Screenshots ``` data: {"error": "messages: text content blocksmust be non-empty"} ``` ### Additional Information Can refer to the code below: ```ts if (userPrompt === '' && files.length > 0) { const hasImages = files.some( (file) => file.type === 'image' || (file?.content_type ?? '').startsWith('image/') ); const hasNonImages = files.some( (file) => file.type !== 'image' && !(file?.content_type ?? '').startsWith('image/') ); if (hasImages && !hasNonImages) { userPrompt = $i18n.t('Analyze the image content'); } else if (!hasImages && hasNonImages) { userPrompt = $i18n.t('Summarize the information in the file'); } else { userPrompt = $i18n.t('Analyze the image and file contents'); } } ```
GiteaMirror added the bug label 2026-05-05 23:17:42 -05:00
Author
Owner

@ShirasawaSama commented on GitHub (Mar 20, 2026):

@Classic298 Could you please mark the message from the person who posted that reply as spam?

<!-- gh-comment-id:4095501268 --> @ShirasawaSama commented on GitHub (Mar 20, 2026): @Classic298 Could you please mark the message from the person who posted that reply as spam?
Author
Owner

@tjbck commented on GitHub (Mar 22, 2026):

Addressed in dev.

<!-- gh-comment-id:4104979387 --> @tjbck commented on GitHub (Mar 22, 2026): Addressed in dev.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#58498