github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7689] Error: 404 Client Error: Not Found for url: http://localhost:11434/api/generate #66966

New Issue
Closed
opened 2026-05-04 09:05:03 -05:00 by GiteaMirror · 11 comments
GiteaMirror commented 2026-05-04 09:05:03 -05:00
Owner
Copy Link

Originally created by @kiran-kumar-akula on GitHub (Nov 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7689

What is the issue?

While trying to run llama model I am getting Error: 404 Client Error: Not Found for url: http://localhost:11434/api/generate.
I am running this in my windows 11 system with python 3.13.0 version
I have installed llama3.2:latest and it's running.

Code:
response = requests.post('http://localhost:11434/api/generate',
json={
"model": "llama3.2:latest",
"prompt": f"{system_prompt}\n\n{prompt}",
"stream": False
})

Error Output:

Ollama service is running!

  • Serving Flask app 'app'
  • Debug mode: on
    INFO:werkzeug:WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
  • Running on http://127.0.0.1:3000
    INFO:werkzeug:Press CTRL+C to quit
    INFO:werkzeug: * Restarting with stat
    Checking Ollama service...
    Ollama service is running!
    WARNING:werkzeug: * Debugger is active!
    INFO:werkzeug: * Debugger PIN: 119-213-946
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:08:53] "GET / HTTP/1.1" 200 -
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:08:53] "GET /api/history HTTP/1.1" 200 -
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:08:53] "GET /favicon.ico HTTP/1.1" 404 -
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:08:55] "GET /api/health HTTP/1.1" 200 -
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:08:55] "GET /api/history HTTP/1.1" 200 -
    ERROR:main:Error in Ollama request: 404 Client Error: Not Found for url: http://localhost:11434/api/generate
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:09:01] "POST /api/chat HTTP/1.1" 200 -
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:22:37] "GET / HTTP/1.1" 200 -
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:22:38] "GET /api/history HTTP/1.1" 200 -
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:22:40] "GET /api/health HTTP/1.1" 200 -
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:22:40] "GET /api/history HTTP/1.1" 200 -
    ERROR:main:Error in Ollama request: 404 Client Error: Not Found for url: http://localhost:11434/api/generate
    INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:22:49] "POST /api/chat HTTP/1.1" 200 -

I am able to curl http://localhost:11434 but not able to ping http://localhost:11434/api

curl http://localhost:11434
Ollama is running

What is the issue here? how to resolve this error.

OS

Windows

GPU

Intel

CPU

Intel

Ollama version

llama3.2:latest

Originally created by @kiran-kumar-akula on GitHub (Nov 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7689 ### What is the issue? While trying to run llama model I am getting Error: 404 Client Error: Not Found for url: http://localhost:11434/api/generate. I am running this in my windows 11 system with python 3.13.0 version I have installed llama3.2:latest and it's running. Code: response = requests.post('http://localhost:11434/api/generate', json={ "model": "llama3.2:latest", "prompt": f"{system_prompt}\n\n{prompt}", "stream": False }) Error Output: Ollama service is running! * Serving Flask app 'app' * Debug mode: on INFO:werkzeug:WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on http://127.0.0.1:3000 INFO:werkzeug:Press CTRL+C to quit INFO:werkzeug: * Restarting with stat Checking Ollama service... Ollama service is running! WARNING:werkzeug: * Debugger is active! INFO:werkzeug: * Debugger PIN: 119-213-946 INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:08:53] "GET / HTTP/1.1" 200 - INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:08:53] "GET /api/history HTTP/1.1" 200 - INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:08:53] "GET /favicon.ico HTTP/1.1" 404 - INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:08:55] "GET /api/health HTTP/1.1" 200 - INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:08:55] "GET /api/history HTTP/1.1" 200 - ERROR:__main__:Error in Ollama request: 404 Client Error: Not Found for url: http://localhost:11434/api/generate INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:09:01] "POST /api/chat HTTP/1.1" 200 - INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:22:37] "GET / HTTP/1.1" 200 - INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:22:38] "GET /api/history HTTP/1.1" 200 - INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:22:40] "GET /api/health HTTP/1.1" 200 - INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:22:40] "GET /api/history HTTP/1.1" 200 - ERROR:__main__:Error in Ollama request: 404 Client Error: Not Found for url: http://localhost:11434/api/generate INFO:werkzeug:127.0.0.1 - - [15/Nov/2024 23:22:49] "POST /api/chat HTTP/1.1" 200 - I am able to curl http://localhost:11434 but not able to ping http://localhost:11434/api curl http://localhost:11434 Ollama is running What is the issue here? how to resolve this error. ### OS Windows ### GPU Intel ### CPU Intel ### Ollama version llama3.2:latest
GiteaMirror added the bug label 2026-05-04 09:05:03 -05:00
GiteaMirror commented 2026-05-04 09:05:06 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 15, 2024):

What does the following return

curl -D - http://localhost:11434/api/generate -d "{\"model\":\"llama3.2:latest\",\"prompt\":\"hi\",\"stream\":false}"
<!-- gh-comment-id:2479649507 --> @rick-github commented on GitHub (Nov 15, 2024): What does the following return ```sh curl -D - http://localhost:11434/api/generate -d "{\"model\":\"llama3.2:latest\",\"prompt\":\"hi\",\"stream\":false}" ```
GiteaMirror commented 2026-05-04 09:05:07 -05:00
Author
Owner
Copy Link

@kiran-kumar-akula commented on GitHub (Nov 15, 2024):

@rick-github

C:\Users: curl -D - http://localhost:11434/api/generate
HTTP/1.1 404 Not Found
Content-Type: text/plain
Date: Fri, 15 Nov 2024 18:16:56 GMT
Content-Length: 18

404 page not found

C:\Users>curl -D - http://localhost:11434/api/generate -d "{"model":"llama3.2:latest","prompt":"hi","stream":false}"
HTTP/1.1 200 OK
Content-Type: application/json; charset=utf-8
Date: Fri, 15 Nov 2024 18:17:37 GMT
Content-Length: 470

{"model":"llama3.2:latest","created_at":"2024-11-15T18:17:37.8303989Z","response":"How can I assist you today?","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,6151,128009,128006,78191,128007,271,4438,649,358,7945,499,3432,30],"total_duration":986768100,"load_duration":24535700,"prompt_eval_count":26,"prompt_eval_duration":373000000,"eval_count":8,"eval_duration":587000000}

<!-- gh-comment-id:2479662959 --> @kiran-kumar-akula commented on GitHub (Nov 15, 2024): @rick-github C:\Users: curl -D - http://localhost:11434/api/generate HTTP/1.1 404 Not Found Content-Type: text/plain Date: Fri, 15 Nov 2024 18:16:56 GMT Content-Length: 18 404 page not found C:\Users>curl -D - http://localhost:11434/api/generate -d "{\"model\":\"llama3.2:latest\",\"prompt\":\"hi\",\"stream\":false}" HTTP/1.1 200 OK Content-Type: application/json; charset=utf-8 Date: Fri, 15 Nov 2024 18:17:37 GMT Content-Length: 470 {"model":"llama3.2:latest","created_at":"2024-11-15T18:17:37.8303989Z","response":"How can I assist you today?","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,6151,128009,128006,78191,128007,271,4438,649,358,7945,499,3432,30],"total_duration":986768100,"load_duration":24535700,"prompt_eval_count":26,"prompt_eval_duration":373000000,"eval_count":8,"eval_duration":587000000}
GiteaMirror commented 2026-05-04 09:05:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 15, 2024):

ollama is working fine, something is wrong with your app or the environment your app is running in. Are you using docker? What do the ollama server logs show?

<!-- gh-comment-id:2479678284 --> @rick-github commented on GitHub (Nov 15, 2024): ollama is working fine, something is wrong with your app or the environment your app is running in. Are you using docker? What do the ollama [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) show?
GiteaMirror commented 2026-05-04 09:05:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 15, 2024):

Copied your code into a file:

import requests

system_prompt = "You are an AI assistant"
prompt = "hi"

response = requests.post('http://localhost:11434/api/generate',
json={
"model": "llama3.2:latest",
"prompt": f"{system_prompt}\n\n{prompt}",
"stream": False
})

print(response.text)

Runs fine:

$ python 7689.py
{"model":"llama3.2:latest","created_at":"2024-11-15T18:36:48.900706688Z","response":"Hello! It's nice to meet you. I'm here to help answer any questions, provide information, or just chat with you. How can I assist you today?","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,2675,527,459,15592,18328,271,6151,128009,128006,78191,128007,271,9906,0,1102,596,6555,311,3449,499,13,358,2846,1618,311,1520,4320,904,4860,11,3493,2038,11,477,1120,6369,449,499,13,2650,649,358,7945,499,3432,30],"total_duration":1773598547,"load_duration":16260172,"prompt_eval_count":32,"prompt_eval_duration":51000000,"eval_count":35,"eval_duration":1704000000}
<!-- gh-comment-id:2479701123 --> @rick-github commented on GitHub (Nov 15, 2024): Copied your code into a file: ```python import requests system_prompt = "You are an AI assistant" prompt = "hi" response = requests.post('http://localhost:11434/api/generate', json={ "model": "llama3.2:latest", "prompt": f"{system_prompt}\n\n{prompt}", "stream": False }) print(response.text) ``` Runs fine: ```console $ python 7689.py {"model":"llama3.2:latest","created_at":"2024-11-15T18:36:48.900706688Z","response":"Hello! It's nice to meet you. I'm here to help answer any questions, provide information, or just chat with you. How can I assist you today?","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,2675,527,459,15592,18328,271,6151,128009,128006,78191,128007,271,9906,0,1102,596,6555,311,3449,499,13,358,2846,1618,311,1520,4320,904,4860,11,3493,2038,11,477,1120,6369,449,499,13,2650,649,358,7945,499,3432,30],"total_duration":1773598547,"load_duration":16260172,"prompt_eval_count":32,"prompt_eval_duration":51000000,"eval_count":35,"eval_duration":1704000000} ```
GiteaMirror commented 2026-05-04 09:05:13 -05:00
Author
Owner
Copy Link

@kiran-kumar-akula commented on GitHub (Nov 15, 2024):

@rick-github yeah I can see it is working in this way , But I am using this api to generate text to sql with flask web api, there I am getting 404 error.

image

So far I thought I am not able to connect to /api/generate but it is connecting. Will debug the whole code and get back to you.

I appreciate your quick assistance.

<!-- gh-comment-id:2479807385 --> @kiran-kumar-akula commented on GitHub (Nov 15, 2024): @rick-github yeah I can see it is working in this way , But I am using this api to generate text to sql with flask web api, there I am getting 404 error. ![image](https://github.com/user-attachments/assets/f2d61ffc-92fe-438c-8f73-dfc74f861e27) So far I thought I am not able to connect to /api/generate but it is connecting. Will debug the whole code and get back to you. I appreciate your quick assistance.
GiteaMirror commented 2026-05-04 09:05:13 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Nov 16, 2024):

GET /api/generate isn't a valid endpoint, which is why it's returning the 404. Arguably it could return a 405 NoMethod instead of a 404.

The endpoint you're looking for is POST /api/generate. With curl the -d option it is implicitly changing the request to a POST, but you can call it with curl -X POST /api/generate (which will of course generate a 400 error since it doesn't have a message body).

I'll go ahead and close the issue.

<!-- gh-comment-id:2480199528 --> @pdevine commented on GitHub (Nov 16, 2024): `GET /api/generate` isn't a valid endpoint, which is why it's returning the 404. Arguably it could return a 405 NoMethod instead of a 404. The endpoint you're looking for is `POST /api/generate`. With curl the `-d` option it is implicitly changing the request to a POST, but you can call it with `curl -X POST /api/generate` (which will of course generate a 400 error since it doesn't have a message body). I'll go ahead and close the issue.
GiteaMirror commented 2026-05-04 09:05:13 -05:00
Author
Owner
Copy Link

@eslynunez commented on GitHub (Nov 18, 2024):

@pdevine running into this issue as well. @kiran-kumar-akula seems to be referencing the POST method in their notes NOT the GET method. Could this be reopened?

<!-- gh-comment-id:2484377920 --> @eslynunez commented on GitHub (Nov 18, 2024): @pdevine running into this issue as well. @kiran-kumar-akula seems to be referencing the POST method in their notes NOT the GET method. Could this be reopened?
GiteaMirror commented 2026-05-04 09:05:14 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 18, 2024):

What does the following return

curl -D - http://localhost:11434/api/generate -d "{\"model\":\"llama3.2:latest\",\"prompt\":\"hi\",\"stream\":false}"

What do your server logs show? Do you have a script that demonstrates the problem?

<!-- gh-comment-id:2484384153 --> @rick-github commented on GitHub (Nov 18, 2024): What does the following return ```sh curl -D - http://localhost:11434/api/generate -d "{\"model\":\"llama3.2:latest\",\"prompt\":\"hi\",\"stream\":false}" ``` What do your [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) show? Do you have a script that demonstrates the problem?
GiteaMirror commented 2026-05-04 09:05:14 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Nov 19, 2024):

@eslynunez This was the command referenced:

curl -D - http://localhost:11434/api/generate

That will call GET /api/generate which will return a 404. Here's what happens if you add -X POST to that same call:

% curl -D - http://localhost:11434/api/generate -X POST
HTTP/1.1 400 Bad Request
Content-Type: application/json; charset=utf-8
Date: Tue, 19 Nov 2024 00:14:39 GMT
Content-Length: 32

{"error":"missing request body"}%

which is the expected output.

<!-- gh-comment-id:2484440685 --> @pdevine commented on GitHub (Nov 19, 2024): @eslynunez This was the command referenced: ``` curl -D - http://localhost:11434/api/generate ``` That will call `GET /api/generate` which will return a 404. Here's what happens if you add `-X POST` to that same call: ``` % curl -D - http://localhost:11434/api/generate -X POST HTTP/1.1 400 Bad Request Content-Type: application/json; charset=utf-8 Date: Tue, 19 Nov 2024 00:14:39 GMT Content-Length: 32 {"error":"missing request body"}% ``` which is the expected output.
GiteaMirror commented 2026-05-04 09:05:14 -05:00
Author
Owner
Copy Link

@eslynunez commented on GitHub (Dec 12, 2024):

I missed that you are correct thank you, @pdevine

<!-- gh-comment-id:2539542079 --> @eslynunez commented on GitHub (Dec 12, 2024): I missed that you are correct thank you, @pdevine
GiteaMirror commented 2026-05-04 09:05:14 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Dec 12, 2024):

I think we should probably return a 405 Method Not Allowed error just to be more succinct.

<!-- gh-comment-id:2540178052 --> @pdevine commented on GitHub (Dec 12, 2024): I think we should probably return a 405 Method Not Allowed error just to be more succinct.
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#66966
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?