How to use Open WebUI API Endpoints to implement multi-modal conversation function? #3068

New Issue

2025-11-11T15:20:55-06:00

GiteaMirror commented

2025-11-11 15:20:55 -06:00

Originally created by @CCChiu0419 on GitHub (Dec 23, 2024).

Detailed description

Hello developer team,

Thank you so much for such a great tool! I'm having some difficulty using Open WebUI API Endpoints. According to the instructions in the file, I understand how to have a simple text conversation, but I would like to take it a step further and implement multi-modal conversation functionality, such as adding multiple images to the conversation.

Steps to reproduce

Follow the instructions in the document to set up Open WebUI and ensure it is running properly.
Use the following curl command to send a text conversation request:

expected behavior

Want to be able to send a request containing text and images to the API and get the appropriate multi-modal talkback in response.

Actual behavior

When I tried to include the image in the request, I couldn't find the relevant documentation, and it wasn't clear how I should structure such a request correctly.

Request description

How can I use the function of Open WebUI API Endpoints to implement multi-modal conversation function? Specifically, how should I include multiple images in my request?

Thank you for taking the time to review this issue and hope to receive your help or guidance. Many thanks!

Thanks!

Best regards,

CCChiu

Originally created by @CCChiu0419 on GitHub (Dec 23, 2024). ## Detailed description Hello developer team, Thank you so much for such a great tool! I'm having some difficulty using Open WebUI API Endpoints. According to the instructions in the file, I understand how to have a simple text conversation, but I would like to take it a step further and implement multi-modal conversation functionality, such as adding multiple images to the conversation. ## Steps to reproduce 1. Follow the instructions in the document to set up Open WebUI and ensure it is running properly. 2. Use the following curl command to send a text conversation request: ## expected behavior Want to be able to send a request containing text and images to the API and get the appropriate multi-modal talkback in response. ## Actual behavior When I tried to include the image in the request, I couldn't find the relevant documentation, and it wasn't clear how I should structure such a request correctly. ## Request description How can I use the function of Open WebUI API Endpoints to implement multi-modal conversation function? Specifically, how should I include multiple images in my request? Thank you for taking the time to review this issue and hope to receive your help or guidance. Many thanks! Thanks! Best regards, CCChiu

GiteaMirror closed this issue

2025-11-11 15:20:55 -06:00

GiteaMirror referenced this issue

2026-04-19 19:55:49 -05:00

[GH-ISSUE #3068] RAG Template Not Being Saved #13119

GiteaMirror referenced this issue

2026-04-25 03:15:21 -05:00

[GH-ISSUE #3068] RAG Template Not Being Saved #28647

GiteaMirror referenced this issue

2026-05-05 12:59:03 -05:00

[GH-ISSUE #3068] RAG Template Not Being Saved #51785

GiteaMirror referenced this issue