github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7132] Getting Error with OpenAI compatibility #4530

New Issue
Closed
opened 2026-04-12 15:28:08 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 15:28:08 -05:00
Owner
Copy Link

Originally created by @php10xdev on GitHub (Oct 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7132

What is the issue?

import { NextApiRequest } from 'next';
import { OpenAIStream, StreamingTextResponse } from 'ai';
import OpenAI from 'openai';

const openai = new OpenAI({
    baseURL: 'http://localhost:11434/v1',
    apiKey: 'ollama', // required but unused
  });

export async function POST(req: NextApiRequest) {
    const body = await req.json();
    console.log("messages", body);
    
    try {
        const response = await openai.chat.completions.create({
            model: 'llama3',
            messages: body.messages,
          });
    
        const stream = OpenAIStream(response);
    
        return new StreamingTextResponse(stream);
    } catch (error) {
        console.error("error", error);
    }
}

Log before Error:

messages { messages: [ { role: 'user', content: "What is today's date?" } ] }

Getting Error

error APIConnectionError: Connection error.
    at OpenAI.makeRequest (webpack-internal:///(rsc)/./node_modules/openai/core.mjs:321:19)
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
    at async POST (webpack-internal:///(rsc)/./src/app/api/chat/route.ts:20:26)

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.3.0

Originally created by @php10xdev on GitHub (Oct 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7132 ### What is the issue? ```js import { NextApiRequest } from 'next'; import { OpenAIStream, StreamingTextResponse } from 'ai'; import OpenAI from 'openai'; const openai = new OpenAI({ baseURL: 'http://localhost:11434/v1', apiKey: 'ollama', // required but unused }); export async function POST(req: NextApiRequest) { const body = await req.json(); console.log("messages", body); try { const response = await openai.chat.completions.create({ model: 'llama3', messages: body.messages, }); const stream = OpenAIStream(response); return new StreamingTextResponse(stream); } catch (error) { console.error("error", error); } } ``` Log before Error: ``` messages { messages: [ { role: 'user', content: "What is today's date?" } ] } ``` Getting Error ``` error APIConnectionError: Connection error. at OpenAI.makeRequest (webpack-internal:///(rsc)/./node_modules/openai/core.mjs:321:19) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async POST (webpack-internal:///(rsc)/./src/app/api/chat/route.ts:20:26) ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.3.0
GiteaMirror added the bugapi labels 2026-04-12 15:28:08 -05:00
GiteaMirror commented 2026-04-12 15:28:10 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 8, 2024):

Thanks for the script, but it's incomplete. Where is Request defined? What's the argument to POST?

<!-- gh-comment-id:2399839698 --> @rick-github commented on GitHub (Oct 8, 2024): Thanks for the script, but it's incomplete. Where is `Request` defined? What's the argument to `POST`?
GiteaMirror commented 2026-04-12 15:28:10 -05:00
Author
Owner
Copy Link

@php10xdev commented on GitHub (Oct 21, 2024):

@rick-github Updated the code still not working, official docs of next.js 14's Request and POST.

<!-- gh-comment-id:2426190286 --> @php10xdev commented on GitHub (Oct 21, 2024): @rick-github Updated the code still not working, official docs of [next.js 14](https://nextjs.org/docs/pages/building-your-application/routing/api-routes)'s `Request` and `POST`.
GiteaMirror commented 2026-04-12 15:28:10 -05:00
Author
Owner
Copy Link

@hecksadecimal commented on GitHub (Dec 10, 2024):

After updating to Ollama 0.5.1 (I'm not sure which version introduced this problem), I also seem to be getting errors when connecting to the OpenAI endpoint.

My code was working before this update. All of the libraries which I depend on are also up to date, and have been before I updated Ollama. Ollama is the only variable here.

Here's a Gist of my error, and the accompanying code.

Relevant environment variables:

OLLAMA_BASE_URL=http://192.168.2.15:11434/v1/

This is another computer on my network running Ollama. I can confirm that Ollama is listening on port 11434, and that I am able to reach the computer through the network via other things like ssh.

<!-- gh-comment-id:2530409191 --> @hecksadecimal commented on GitHub (Dec 10, 2024): After updating to Ollama 0.5.1 (I'm not sure which version introduced this problem), I also seem to be getting errors when connecting to the OpenAI endpoint. My code was working before this update. All of the libraries which I depend on are also up to date, and have been before I updated Ollama. Ollama is the only variable here. Here's a [Gist](https://gist.github.com/hecksadecimal/fef51f0358ab08c4fbb33774d84a85fa) of my error, and the [accompanying code](https://gist.github.com/hecksadecimal/6bd42a9dbfe13225111146c21c693a9f). Relevant environment variables: ```sh OLLAMA_BASE_URL=http://192.168.2.15:11434/v1/ ``` This is another computer on my network running Ollama. I can confirm that Ollama is listening on port 11434, and that I am able to reach the computer through the network via other things like ssh.
GiteaMirror commented 2026-04-12 15:28:11 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 10, 2024):

Ollama server logs?

<!-- gh-comment-id:2530467197 --> @rick-github commented on GitHub (Dec 10, 2024): Ollama server logs?
GiteaMirror commented 2026-04-12 15:28:11 -05:00
Author
Owner
Copy Link

@hecksadecimal commented on GitHub (Dec 10, 2024):

I'm progressively downgrading to see if I can find a version that works again. I'll get that for you in a moment.

<!-- gh-comment-id:2530483494 --> @hecksadecimal commented on GitHub (Dec 10, 2024): I'm progressively downgrading to see if I can find a version that works again. I'll get that for you in a moment.
GiteaMirror commented 2026-04-12 15:28:11 -05:00
Author
Owner
Copy Link

@hecksadecimal commented on GitHub (Dec 10, 2024):

Ollama server logs?

Here are the logs from ollama serve
Of note is line 5. Listening on 127.0.0.1:11434. I have not changed anything about my configuration, so I'm assuming that in some previous version it defaulted to listening on 0.0.0.0.

After setting OLLAMA_HOST=0.0.0.0 in my service file, it's back to working as expected.

<!-- gh-comment-id:2530548802 --> @hecksadecimal commented on GitHub (Dec 10, 2024): > Ollama server logs? [Here](https://gist.github.com/hecksadecimal/9ed8587a485c748f9b4adf72f5049890) are the logs from `ollama serve` Of note is line 5. `Listening on 127.0.0.1:11434`. I have not changed anything about my configuration, so I'm assuming that in some previous version it defaulted to listening on `0.0.0.0`. After setting `OLLAMA_HOST=0.0.0.0` in my service file, it's back to working as expected.
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 api 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#4530
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?