github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7277] Error occurred: Error code: 400 - {'error': {'message': 'unexpected EOF', 'type': 'invalid_request_error', 'param': None, 'code': None}} #66679

New Issue
Closed
opened 2026-05-04 07:47:13 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-05-04 07:47:13 -05:00
Owner
Copy Link

Originally created by @ghost on GitHub (Oct 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7277

What is the issue?

using local computer can run :from openai import OpenAI
client = OpenAI(
base_url='http://.........:8000/v1/',
api_key='ollama', # required but ignored
)
chat_completion = client.chat.completions.create(
messages=[
{
'role': 'user',
'content': 'Say this is a test',
}
],
model='qwen2.5:72b',
)
print(chat_completion)but at the other computer :Error occurred: Error code: 400 - {'error': {'message': 'unexpected EOF', 'type': 'invalid_request_error', 'param': None, 'code': None}}

OS

Linux, Windows

GPU

No response

CPU

No response

Ollama version

0.3.13

Originally created by @ghost on GitHub (Oct 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7277 ### What is the issue? using local computer can run :from openai import OpenAI client = OpenAI( base_url='http://.........:8000/v1/', api_key='ollama', # required but ignored ) chat_completion = client.chat.completions.create( messages=[ { 'role': 'user', 'content': 'Say this is a test', } ], model='qwen2.5:72b', ) print(chat_completion)but at the other computer :Error occurred: Error code: 400 - {'error': {'message': 'unexpected EOF', 'type': 'invalid_request_error', 'param': None, 'code': None}} ### OS Linux, Windows ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.3.13
GiteaMirror added the bugapi labels 2026-05-04 07:47:14 -05:00
GiteaMirror commented 2026-05-04 07:47:19 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 20, 2024):

Default port for ollama is 11434, your script is using 8000. Did you configure the ollama server to use port 8000?

<!-- gh-comment-id:2424961153 --> @rick-github commented on GitHub (Oct 20, 2024): Default port for ollama is 11434, your script is using 8000. Did you configure the ollama server to use port 8000?
GiteaMirror commented 2026-05-04 07:47:20 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Oct 22, 2024):

Default port for ollama is 11434, your script is using 8000. Did you configure the ollama server to use port 8000?

yes,and I can curl this

<!-- gh-comment-id:2428814282 --> @ghost commented on GitHub (Oct 22, 2024): > Default port for ollama is 11434, your script is using 8000. Did you configure the ollama server to use port 8000? yes,and I can curl this
GiteaMirror commented 2026-05-04 07:47:21 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 22, 2024):

What's the output of that curl?

<!-- gh-comment-id:2428824444 --> @rick-github commented on GitHub (Oct 22, 2024): What's the output of that curl?
GiteaMirror commented 2026-05-04 07:47:22 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Oct 22, 2024):

What's the output of that curl?
curl http://:8000/api/ps

StatusCode : 200
StatusDescription : OK
Content : {"models":[{"name":"qwen2.5:72b","model":"qwen2.5:72b","size":54438088704,"digest":"424bad2cc13f72f5
bcd8085de63f48e7ef2ae5bf50a30be4b3ade7d3258f5796","details":{"parent_model":"","format":"gguf","fami
...
RawContent : HTTP/1.1 200 OK
Content-Length: 361
Content-Type: application/json; charset=utf-8
Date: Sun, 20 Oct 2024 12:44:14 GMT

            {"models":[{"name":"qwen2.5:72b","model":"qwen2.5:72b","size":54438088704,"d...

Forms : {}
Headers : {[Content-Length, 361], [Content-Type, application/json; charset=utf-8], [Date, Sun, 20 Oct 2024 12:
44:14 GMT]}
Images : {}
InputFields : {}
Links : {}
ParsedHtml : mshtml.HTMLDocumentClass
RawContentLength : 361

<!-- gh-comment-id:2428837457 --> @ghost commented on GitHub (Oct 22, 2024): > What's the output of that curl? curl http://:8000/api/ps StatusCode : 200 StatusDescription : OK Content : {"models":[{"name":"qwen2.5:72b","model":"qwen2.5:72b","size":54438088704,"digest":"424bad2cc13f72f5 bcd8085de63f48e7ef2ae5bf50a30be4b3ade7d3258f5796","details":{"parent_model":"","format":"gguf","fami ... RawContent : HTTP/1.1 200 OK Content-Length: 361 Content-Type: application/json; charset=utf-8 Date: Sun, 20 Oct 2024 12:44:14 GMT {"models":[{"name":"qwen2.5:72b","model":"qwen2.5:72b","size":54438088704,"d... Forms : {} Headers : {[Content-Length, 361], [Content-Type, application/json; charset=utf-8], [Date, Sun, 20 Oct 2024 12: 44:14 GMT]} Images : {} InputFields : {} Links : {} ParsedHtml : mshtml.HTMLDocumentClass RawContentLength : 361
GiteaMirror commented 2026-05-04 07:47:23 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Oct 22, 2024):

What's the output of that curl?

$response = Invoke-WebRequest -Uri http://:8000/api/generate -Method POST -Body '{"model": "qwen2.5:72b", "prompt": "为什么草是绿的？"}' -ContentType 'application/json'
PS D:\test>
PS D:\test> $rawContent = $response.RawContent
PS D:\test> $lines = $rawContent -split "`n" #
PS D:\test> foreach ($line in $lines) {

try {
    $json = $line | ConvertFrom-Json
    $json
} catch {
    Write-Host "无法解析的行：$line"
}

}
无法解析的行：HTTP/1.1 200 OK
无法解析的行：Transfer-Encoding: chunked
无法解析的行：Content-Type: application/x-ndjson
无法解析的行：Date: Sun, 20 Oct 2024 13:26:24 GMT

model created_at response done

qwen2.5:72b 2024-10-20T13:26:24.488869105Z ?????? False
qwen2.5:72b 2024-10-20T13:26:24.565323044Z ??? False
qwen2.5:72b 2024-10-20T13:26:24.642167784Z ????????? False
qwen2.5:72b 2024-10-20T13:26:24.710467701Z ?????? False
qwen2.5:72b 2024-10-20T13:26:24.777325371Z ?????? False
qwen2.5:72b 2024-10-20T13:26:24.844375228Z ?????? False
qwen2.5:72b 2024-10-20T13:26:24.906853638Z ?????? False
qwen2.5:72b 2024-10-20T13:26:24.967298989Z ?????? False
qwen2.5:72b 2024-10-20T13:26:25.027440419Z ?????? False
qwen2.5:72b 2024-10-20T13:26:25.087232675Z ??? False
qwen2.5:72b 2024-10-20T13:26:25.144918405Z ????????? False
qwen2.5:72b 2024-10-20T13:26:25.200894836Z ????????? False
qwen2.5:72b 2024-10-20T13:26:25.255961725Z ?????? False
qwen2.5:72b 2024-10-20T13:26:25.309884705Z ??? False
qwen2.5:72b 2024-10-20T13:26:25.363755727Z ?????? False
qwen2.5:72b 2024-10-20T13:26:25.417717815Z ?????? False
qwen2.5:72b 2024-10-20T13:26:25.470564486Z ??? False
qwen2.5:72b 2024-10-20T13:26:25.523020636Z ?????? False
qwen2.5:72b 2024-10-20T13:26:25.575704171Z ?????? False
qwen2.5:72b 2024-10-20T13:26:25.628040761Z ????????? False
qwen2.5:72b 2024-10-20T13:26:25.680473446Z ??? False
qwen2.5:72b 2024-10-20T13:26:25.732600809Z ???? False
qwen2.5:72b 2024-10-20T13:26:25.785217302Z True

<!-- gh-comment-id:2428841304 --> @ghost commented on GitHub (Oct 22, 2024): > What's the output of that curl? $response = Invoke-WebRequest -Uri http://:8000/api/generate -Method POST -Body '{"model": "qwen2.5:72b", "prompt": "为什么草是绿的？"}' -ContentType 'application/json' PS D:\test> PS D:\test> $rawContent = $response.RawContent PS D:\test> $lines = $rawContent -split "`n" # PS D:\test> foreach ($line in $lines) { >> try { >> $json = $line | ConvertFrom-Json >> $json >> } catch { >> Write-Host "无法解析的行：$line" >> } >> } 无法解析的行：HTTP/1.1 200 OK 无法解析的行：Transfer-Encoding: chunked 无法解析的行：Content-Type: application/x-ndjson 无法解析的行：Date: Sun, 20 Oct 2024 13:26:24 GMT model created_at response done ----- ---------- -------- ---- qwen2.5:72b 2024-10-20T13:26:24.488869105Z ?????? False qwen2.5:72b 2024-10-20T13:26:24.565323044Z ??? False qwen2.5:72b 2024-10-20T13:26:24.642167784Z ????????? False qwen2.5:72b 2024-10-20T13:26:24.710467701Z ?????? False qwen2.5:72b 2024-10-20T13:26:24.777325371Z ?????? False qwen2.5:72b 2024-10-20T13:26:24.844375228Z ?????? False qwen2.5:72b 2024-10-20T13:26:24.906853638Z ?????? False qwen2.5:72b 2024-10-20T13:26:24.967298989Z ?????? False qwen2.5:72b 2024-10-20T13:26:25.027440419Z ?????? False qwen2.5:72b 2024-10-20T13:26:25.087232675Z ??? False qwen2.5:72b 2024-10-20T13:26:25.144918405Z ????????? False qwen2.5:72b 2024-10-20T13:26:25.200894836Z ????????? False qwen2.5:72b 2024-10-20T13:26:25.255961725Z ?????? False qwen2.5:72b 2024-10-20T13:26:25.309884705Z ??? False qwen2.5:72b 2024-10-20T13:26:25.363755727Z ?????? False qwen2.5:72b 2024-10-20T13:26:25.417717815Z ?????? False qwen2.5:72b 2024-10-20T13:26:25.470564486Z ??? False qwen2.5:72b 2024-10-20T13:26:25.523020636Z ?????? False qwen2.5:72b 2024-10-20T13:26:25.575704171Z ?????? False qwen2.5:72b 2024-10-20T13:26:25.628040761Z ????????? False qwen2.5:72b 2024-10-20T13:26:25.680473446Z ??? False qwen2.5:72b 2024-10-20T13:26:25.732600809Z ???? False qwen2.5:72b 2024-10-20T13:26:25.785217302Z True
GiteaMirror commented 2026-05-04 07:47:23 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 22, 2024):

Are you really using http://:8000/ in the curl request? Also, you can add "stream":false to the body so you don't need to write a for loop to process the output.

<!-- gh-comment-id:2428857316 --> @rick-github commented on GitHub (Oct 22, 2024): Are you really using `http://:8000/` in the curl request? Also, you can add `"stream":false` to the body so you don't need to write a for loop to process the output.
GiteaMirror commented 2026-05-04 07:47:25 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Oct 22, 2024):

Are you really using http://:8000/ in the curl request? Also, you can add "stream":false to the body so you don't need to write a for loop to process the output.

Yes, I just hid the IP when I sent it. When I use this on my local machine, it’s not question marks but a normal text.

<!-- gh-comment-id:2428879523 --> @ghost commented on GitHub (Oct 22, 2024): > Are you really using `http://:8000/` in the curl request? Also, you can add `"stream":false` to the body so you don't need to write a for loop to process the output. Yes, I just hid the IP when I sent it. When I use this on my local machine, it’s not question marks but a normal text.
GiteaMirror commented 2026-05-04 07:47:25 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 22, 2024):

Is your server on the same LAN as your local machine or is it a cloud server? Do you have any proxies or captive portals?

<!-- gh-comment-id:2429013040 --> @rick-github commented on GitHub (Oct 22, 2024): Is your server on the same LAN as your local machine or is it a cloud server? Do you have any proxies or captive portals?
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#66679
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?