github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3502] post no longer works via fetch #2158

New Issue
Closed
opened 2026-04-12 12:23:17 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-12 12:23:17 -05:00
Owner
Copy Link

Originally created by @ralyodio on GitHub (Apr 5, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3502

What is the issue?

		const response = await fetch('https://ai.profullstack.com/api/generate', {
			method: 'POST',
			body: JSON.stringify({
				/* these don't categorize properly */
				// model: 'llama2-uncensored:latest',
				// model: 'codellama',
				// model: 'phi:latest',
				// model: 'dolphin-mixtral:latest',
				/* todo: try next */
				// model: 'mixtral:latest',
				// model: 'mistral',
				model: 'solar',
				prompt,
				stream: false,
				format: 'json'
			})
		});

		if (response.ok) {
			const data = await response.json();
			console.log(data.response);

			return JSON.parse(data.response);
		} else {
			console.error(await response.json());
		}

What did you expect to see?

it worked a month or two ago. i just updated

Steps to reproduce

	const response = await fetch('https://ai.profullstack.com/api/generate', {
		method: 'POST',
		body: JSON.stringify({
			/* these don't categorize properly */
			// model: 'llama2-uncensored:latest',
			// model: 'codellama',
			// model: 'phi:latest',
			// model: 'dolphin-mixtral:latest',
			/* todo: try next */
			// model: 'mixtral:latest',
			// model: 'mistral',
			model: 'solar',
			prompt,
			stream: false,
			format: 'json'
		})
	});

	if (response.ok) {
		const data = await response.json();
		console.log(data.response);

		return JSON.parse(data.response);
	} else {
		console.error(await response.json());
	}

Are there any recent changes that introduced the issue?

yes, i upgraded to latest ollama

OS

Linux

Architecture

amd64

Platform

Docker

Ollama version

No response

GPU

Other

GPU info

no gpu

CPU

Intel

Other software

No response

Originally created by @ralyodio on GitHub (Apr 5, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3502 ### What is the issue? ``` const response = await fetch('https://ai.profullstack.com/api/generate', { method: 'POST', body: JSON.stringify({ /* these don't categorize properly */ // model: 'llama2-uncensored:latest', // model: 'codellama', // model: 'phi:latest', // model: 'dolphin-mixtral:latest', /* todo: try next */ // model: 'mixtral:latest', // model: 'mistral', model: 'solar', prompt, stream: false, format: 'json' }) }); if (response.ok) { const data = await response.json(); console.log(data.response); return JSON.parse(data.response); } else { console.error(await response.json()); } ``` ### What did you expect to see? it worked a month or two ago. i just updated ### Steps to reproduce const response = await fetch('https://ai.profullstack.com/api/generate', { method: 'POST', body: JSON.stringify({ /* these don't categorize properly */ // model: 'llama2-uncensored:latest', // model: 'codellama', // model: 'phi:latest', // model: 'dolphin-mixtral:latest', /* todo: try next */ // model: 'mixtral:latest', // model: 'mistral', model: 'solar', prompt, stream: false, format: 'json' }) }); if (response.ok) { const data = await response.json(); console.log(data.response); return JSON.parse(data.response); } else { console.error(await response.json()); } ### Are there any recent changes that introduced the issue? yes, i upgraded to latest ollama ### OS Linux ### Architecture amd64 ### Platform Docker ### Ollama version _No response_ ### GPU Other ### GPU info no gpu ### CPU Intel ### Other software _No response_
GiteaMirror added the bug label 2026-04-12 12:23:17 -05:00
GiteaMirror commented 2026-04-12 12:23:19 -05:00
Author
Owner
Copy Link

@ralyodio commented on GitHub (Apr 5, 2024):

I get 405 method not allowed. My nginx proxy looks like this:

    location / {
        # auth_basic "ai access required";
        # auth_basic_user_file /etc/nginx/.htpasswd;
        proxy_pass http://localhost:5432;
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection 'upgrade';
        proxy_cache_bypass $http_upgrade;
        # proxy_set_header Host $host;
        # proxy_set_header X-Real-IP $remote_addr;
        # proxy_set_header X-Forwarded-Proto https;
        # proxy_set_header X-Forwarded-For $remote_addr;
    }

something broke after recent upgrade of ollamaa

<!-- gh-comment-id:2039631491 --> @ralyodio commented on GitHub (Apr 5, 2024): I get 405 method not allowed. My nginx proxy looks like this: ``` location / { # auth_basic "ai access required"; # auth_basic_user_file /etc/nginx/.htpasswd; proxy_pass http://localhost:5432; proxy_http_version 1.1; proxy_set_header Upgrade $http_upgrade; proxy_set_header Connection 'upgrade'; proxy_cache_bypass $http_upgrade; # proxy_set_header Host $host; # proxy_set_header X-Real-IP $remote_addr; # proxy_set_header X-Forwarded-Proto https; # proxy_set_header X-Forwarded-For $remote_addr; } ``` something broke after recent upgrade of ollamaa
GiteaMirror commented 2026-04-12 12:23:19 -05:00
Author
Owner
Copy Link

@eusebiu commented on GitHub (Apr 5, 2024):

I think the stream: false flag is ignored. I get the same behaviour.

On f4b31c2d53 (16 Mar 24) the issue is not happening (~0.1.29).

<!-- gh-comment-id:2040701374 --> @eusebiu commented on GitHub (Apr 5, 2024): I think the stream: false flag is ignored. I get the same behaviour. On f4b31c2d53923d55491db8f373817fd68cee6bda (16 Mar 24) the issue is not happening (~0.1.29).
GiteaMirror commented 2026-04-12 12:23:20 -05:00
Author
Owner
Copy Link

@ralyodio commented on GitHub (Apr 6, 2024):

weird. i need it, i wonder why it was removed.

<!-- gh-comment-id:2040912779 --> @ralyodio commented on GitHub (Apr 6, 2024): weird. i need it, i wonder why it was removed.
GiteaMirror commented 2026-04-12 12:23:20 -05:00
Author
Owner
Copy Link

@eusebiu commented on GitHub (Apr 6, 2024):

Not removed, but ignored.
I think this c863c6a96d breaks it.

I tested before and after; after, the stream: false is ignored, before it works fine.

<!-- gh-comment-id:2041023302 --> @eusebiu commented on GitHub (Apr 6, 2024): Not removed, but ignored. I think this c863c6a96d01afda37b65f86eb14a1f04a3c7c47 breaks it. I tested before and after; after, the stream: false is ignored, before it works fine.
GiteaMirror commented 2026-04-12 12:23:21 -05:00
Author
Owner
Copy Link

@ralyodio commented on GitHub (Apr 9, 2024):

is anyone looking into this? i upgraded to latest. I still get 405

<!-- gh-comment-id:2044460303 --> @ralyodio commented on GitHub (Apr 9, 2024): is anyone looking into this? i upgraded to latest. I still get 405
GiteaMirror commented 2026-04-12 12:23:21 -05:00
Author
Owner
Copy Link

@ralyodio commented on GitHub (Apr 9, 2024):

https://github.com/ollama/ollama/blob/main/docs/api.md#request-2

<!-- gh-comment-id:2044471265 --> @ralyodio commented on GitHub (Apr 9, 2024): https://github.com/ollama/ollama/blob/main/docs/api.md#request-2
GiteaMirror commented 2026-04-12 12:23:22 -05:00
Author
Owner
Copy Link

@eusebiu commented on GitHub (Apr 13, 2024):

I think now should work. Please get the latest.

<!-- gh-comment-id:2053555552 --> @eusebiu commented on GitHub (Apr 13, 2024): I think now should work. Please get the latest.
GiteaMirror commented 2026-04-12 12:23:22 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (May 15, 2024):

It should be working fine:

% curl -X POST http://localhost:11434/api/generate -d '{"model": "llama3", "stream": false, "prompt": "hi there"}'
{"model":"llama3","created_at":"2024-05-15T00:08:31.042327Z","response":"Hi there! It's nice to meet you. Is there something I can help you with or would you like to chat?","done":true,"done_reason":"stop","context":[128006,882,128007,198,198,6151,1070,128009,128006,78191,128007,198,198,13347,1070,0,1102,6,82,6555,311,3449,499,13,2209,1070,2555,358,649,1520,499,449,477,1053,499,1093,311,6369,30,128009],"total_duration":1571077041,"load_duration":1075794458,"prompt_eval_count":12,"prompt_eval_duration":80494000,"eval_count":26,"eval_duration":414090000}

I'll go ahead an close the issue.

<!-- gh-comment-id:2111378713 --> @pdevine commented on GitHub (May 15, 2024): It should be working fine: ``` % curl -X POST http://localhost:11434/api/generate -d '{"model": "llama3", "stream": false, "prompt": "hi there"}' {"model":"llama3","created_at":"2024-05-15T00:08:31.042327Z","response":"Hi there! It's nice to meet you. Is there something I can help you with or would you like to chat?","done":true,"done_reason":"stop","context":[128006,882,128007,198,198,6151,1070,128009,128006,78191,128007,198,198,13347,1070,0,1102,6,82,6555,311,3449,499,13,2209,1070,2555,358,649,1520,499,449,477,1053,499,1093,311,6369,30,128009],"total_duration":1571077041,"load_duration":1075794458,"prompt_eval_count":12,"prompt_eval_duration":80494000,"eval_count":26,"eval_duration":414090000} ``` I'll go ahead an close the issue.
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#2158
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?