github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3746] Ollama response 403 to OPTION requests #64347

New Issue
Closed
opened 2026-05-03 17:13:45 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-03 17:13:45 -05:00
Owner
Copy Link

Originally created by @zrll12 on GitHub (Apr 19, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3746

What is the issue?

I was using Next Chat to communicate with Ollama, but Next Chat returns

{
  "error": true,
  "message": "Load failed"
}

and the log of Ollama says

[GIN] 2024/04/19 - 11:58:33 | 403 |      48.166µs |       127.0.0.1 | OPTIONS  "/v1/chat/completions"
[GIN] 2024/04/19 - 11:58:35 | 403 |       9.791µs |       127.0.0.1 | OPTIONS  "/v1/chat/completions"

The OLLAMA_ORIGINS variable has been set to *

Can run with the following curl

curl http://localhost:11434/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "llama2",
        "messages": [
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "Hello!"
            }
        ]
    }'

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.32

Originally created by @zrll12 on GitHub (Apr 19, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3746 ### What is the issue? I was using Next Chat to communicate with Ollama, but Next Chat returns ``` json { "error": true, "message": "Load failed" } ``` and the log of Ollama says ``` [GIN] 2024/04/19 - 11:58:33 | 403 | 48.166µs | 127.0.0.1 | OPTIONS "/v1/chat/completions" [GIN] 2024/04/19 - 11:58:35 | 403 | 9.791µs | 127.0.0.1 | OPTIONS "/v1/chat/completions" ``` The `OLLAMA_ORIGINS` variable has been set to `*` Can run with the following curl ``` curl http://localhost:11434/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "llama2", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Hello!" } ] }' ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-05-03 17:13:45 -05:00
GiteaMirror commented 2026-05-03 17:13:47 -05:00
Author
Owner
Copy Link

@chunzha1 commented on GitHub (Apr 21, 2024):

same for me. it's that any solutions?

<!-- gh-comment-id:2068124115 --> @chunzha1 commented on GitHub (Apr 21, 2024): same for me. it's that any solutions?
GiteaMirror commented 2026-05-03 17:13:47 -05:00
Author
Owner
Copy Link

@chunzha1 commented on GitHub (Apr 21, 2024):

截屏2024-04-22 00 30 27 I found that it can be used in OpenAI, but got a 403 error when using it on Ollama...
<!-- gh-comment-id:2068127992 --> @chunzha1 commented on GitHub (Apr 21, 2024): <img width="971" alt="截屏2024-04-22 00 30 27" src="https://github.com/ollama/ollama/assets/125763492/ddc24191-5e65-497c-b8d5-e76e916a8f1b"> I found that it can be used in OpenAI, but got a 403 error when using it on Ollama...
GiteaMirror commented 2026-05-03 17:13:48 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 10, 2024):

This should be fixed on main and in the next release of Ollama

<!-- gh-comment-id:2103630494 --> @jmorganca commented on GitHub (May 10, 2024): This should be fixed on `main` and in the next release of Ollama
GiteaMirror commented 2026-05-03 17:13:48 -05:00
Author
Owner
Copy Link

@haohaifeng002 commented on GitHub (Dec 20, 2024):

Version 0.5.4 still has not resolved the issue

<!-- gh-comment-id:2556730833 --> @haohaifeng002 commented on GitHub (Dec 20, 2024): Version 0.5.4 still has not resolved the issue
GiteaMirror commented 2026-05-03 17:13:48 -05:00
Author
Owner
Copy Link

@sdjn-kzero commented on GitHub (Feb 14, 2025):

I changed the installation method and used brew install ollama, then found homebrew.mxcl.ollama.plist in /opt/homebrew/Cellar/ollama/0.5.10.

<key>ProgramArguments</key>
<array>
	<string>/opt/homebrew/opt/ollama/bin/ollama</string>
	<string>serve</string>
</array>

I added

<key>EnvironmentVariables</key>
<dict>
    <key>OLLAMA_ORIGINS</key>
    <string>*</string>
    <key>OLLAMA_CORS</key>
    <string>true</string>
</dict>

After restarting, the problem was solved.

<!-- gh-comment-id:2659833872 --> @sdjn-kzero commented on GitHub (Feb 14, 2025): I changed the installation method and used brew install ollama, then found homebrew.mxcl.ollama.plist in /opt/homebrew/Cellar/ollama/0.5.10. ```xml <key>ProgramArguments</key> <array> <string>/opt/homebrew/opt/ollama/bin/ollama</string> <string>serve</string> </array> ``` I added ```xml <key>EnvironmentVariables</key> <dict> <key>OLLAMA_ORIGINS</key> <string>*</string> <key>OLLAMA_CORS</key> <string>true</string> </dict> ``` After restarting, the problem was solved.
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#64347
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?