[GH-ISSUE #17289] issue: Cannot upload PDF for Anthropic function or pipeline #137957

New Issue

GiteaMirror · 2026-05-25T08:55:28-05:00

GiteaMirror commented

2026-05-25 08:55:28 -05:00

Originally created by @hades200082 on GitHub (Sep 9, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17289

Check Existing Issues

I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.6.23

Ollama Version (if applicable)

No response

Operating System

Linux (whatever you put in your docker image)

Browser (if applicable)

Edge and Chrome

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

When I upload a PDF for Anthropic models (using either the function or the pipeline methods) the PDF should be passed to the LLM along with my message.

Actual Behavior

When I upload a PDF for Anthropic models (using either the function or the pipeline methods) the LLM reports that it cannot see the PDF attachment.

Steps to Reproduce

Add the Anthropic function or pipeline to Open WebUI
Send a message to an Anthropic model that includes a PDF upload and ask the AI to review the attached PDF.

Logs & Screenshots

No logs as the messages to/from the AI were successful, but the AI couldn't see the uploaded PDF.

Additional Information

No response

Originally created by @hades200082 on GitHub (Sep 9, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/17289 ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.6.23 ### Ollama Version (if applicable) _No response_ ### Operating System Linux (whatever you put in your docker image) ### Browser (if applicable) Edge and Chrome ### 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 When I upload a PDF for Anthropic models (using either the function or the pipeline methods) the PDF should be passed to the LLM along with my message. ### Actual Behavior When I upload a PDF for Anthropic models (using either the function or the pipeline methods) the LLM reports that it cannot see the PDF attachment. <img width="1023" height="505" alt="Image" src="https://github.com/user-attachments/assets/1eef5d36-7c85-4e11-b56f-2c950d129877" /> ### Steps to Reproduce 1. Add the Anthropic function or pipeline to Open WebUI 2. Send a message to an Anthropic model that includes a PDF upload and ask the AI to review the attached PDF. ### Logs & Screenshots <img width="1023" height="505" alt="Image" src="https://github.com/user-attachments/assets/1eef5d36-7c85-4e11-b56f-2c950d129877" /> No logs as the messages to/from the AI were successful, but the AI couldn't see the uploaded PDF. ### Additional Information _No response_

GiteaMirror added the bug label 2026-05-25 08:55:28 -05:00

GiteaMirror closed this issue

2026-05-25 08:55:31 -05:00

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#137957