github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14542] Error 500 on calling ollama cloud models with tools #9434

New Issue
Closed
opened 2026-04-12 22:21:31 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 22:21:31 -05:00
Owner
Copy Link

Originally created by @Syntaxrabbit on GitHub (Mar 2, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14542

What is the issue?

Using the library (e.g. reproducable with the sample application) causes an error 500 if at least one tool is provided.

  • Local models work without any issues.
  • Cloud models run without any issues if there is no tool involved.

── Extensions.AI ───────────────────────────────────────────────────────────────────────────────────────────────────────
Define a system prompt (optional)
>

You are talking to qwen3-vl:235b-cloud now.
When asked for the weather, population or the GPS coordinates for a city, it will try to use a predefined tool.
If any tool is used, the intended usage information is printed.
Enter /new to start over or /exit to leave.
Begin with [ to start multiline input. Submit it by ending with ].
Think mode is (null). Type /togglethink to change.
Enter /tools to list all available tools.

> /togglethink
Think mode is false.

> /togglethink
Think mode is true.

> /tools

Available tools:
GetWeather              Gets the current weather for a given location.
GetLatLon               Gets the latitude and longitude for a given location.
GetPopulation           Gets the amount of people living in a given city

You are talking to qwen3-vl:235b-cloud now.
When asked for the weather, population or the GPS coordinates for a city, it will try to use a predefined tool.
If any tool is used, the intended usage information is printed.
Enter /new to start over or /exit to leave.
Begin with [ to start multiline input. Submit it by ending with ].
Think mode is true. Type /togglethink to change.
Enter /tools to list all available tools.

> How is the weather today?
Response status code does not indicate success: 500 (Internal Server Error).

Relevant log output

[GIN] 2026/03/02 - 06:10:48 | 500 |    248.3771ms |             ::1 | POST     "/api/chat"

OS

Windows

GPU

No response

CPU

No response

Ollama version

0.17.4

Originally created by @Syntaxrabbit on GitHub (Mar 2, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14542 ### What is the issue? Using the library (e.g. reproducable with the sample application) causes an error 500 if at least one tool is provided. - Local models work without any issues. - Cloud models run without any issues if there is no tool involved. ``` ── Extensions.AI ─────────────────────────────────────────────────────────────────────────────────────────────────────── Define a system prompt (optional) > You are talking to qwen3-vl:235b-cloud now. When asked for the weather, population or the GPS coordinates for a city, it will try to use a predefined tool. If any tool is used, the intended usage information is printed. Enter /new to start over or /exit to leave. Begin with [ to start multiline input. Submit it by ending with ]. Think mode is (null). Type /togglethink to change. Enter /tools to list all available tools. > /togglethink Think mode is false. > /togglethink Think mode is true. > /tools Available tools: GetWeather Gets the current weather for a given location. GetLatLon Gets the latitude and longitude for a given location. GetPopulation Gets the amount of people living in a given city You are talking to qwen3-vl:235b-cloud now. When asked for the weather, population or the GPS coordinates for a city, it will try to use a predefined tool. If any tool is used, the intended usage information is printed. Enter /new to start over or /exit to leave. Begin with [ to start multiline input. Submit it by ending with ]. Think mode is true. Type /togglethink to change. Enter /tools to list all available tools. > How is the weather today? Response status code does not indicate success: 500 (Internal Server Error). ``` ### Relevant log output ```shell [GIN] 2026/03/02 - 06:10:48 | 500 | 248.3771ms | ::1 | POST "/api/chat" ``` ### OS Windows ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.17.4
GiteaMirror added the bug label 2026-04-12 22:21:31 -05:00
GiteaMirror commented 2026-04-12 22:21:32 -05:00
Author
Owner
Copy Link

@cheryei commented on GitHub (Mar 2, 2026):

从哪里添加技能？

Image
<!-- gh-comment-id:3982229518 --> @cheryei commented on GitHub (Mar 2, 2026): 从哪里添加技能？ <img width="897" height="600" alt="Image" src="https://github.com/user-attachments/assets/56923bd0-a0a4-4132-8f1f-f1a24dd4653c" />
GiteaMirror commented 2026-04-12 22:21:32 -05:00
Author
Owner
Copy Link

@Syntaxrabbit commented on GitHub (Mar 2, 2026):

Sorry, should be duplicate.

<!-- gh-comment-id:3982232258 --> @Syntaxrabbit commented on GitHub (Mar 2, 2026): Sorry, should be duplicate.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#9434
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?