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 #1467] REST API : /api/chat endpoint not working #47302

New Issue
Closed
opened 2026-04-28 03:32:34 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-28 03:32:34 -05:00
Owner
Copy Link

Originally created by @slovanos on GitHub (Dec 11, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1467

Refering to the the examples of the main page:

Generate a response: Works perfectly

curl http://localhost:11434/api/generate -d '{
  "model": "llama2",
  "prompt":"Why is the sky blue?"
}'

Chat with a model: Not Working

Response is "404 page not found"

curl http://localhost:11434/api/chat -d '{
  "model": "llama2",
  "messages": [
    { "role": "user", "content": "why is the sky blue?" }
  ]
}'

I tried restarting the server and also with mistral model and I am getting the same result.

Originally created by @slovanos on GitHub (Dec 11, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1467 Refering to the the examples of the main page: ## Generate a response: Works perfectly ``` curl http://localhost:11434/api/generate -d '{ "model": "llama2", "prompt":"Why is the sky blue?" }' ``` ## Chat with a model: Not Working ### Response is "404 page not found" ``` curl http://localhost:11434/api/chat -d '{ "model": "llama2", "messages": [ { "role": "user", "content": "why is the sky blue?" } ] }' ``` I tried restarting the server and also with mistral model and I am getting the same result.
GiteaMirror commented 2026-04-28 03:32:36 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Dec 11, 2023):

Hi @slovanos! Which version of Ollama are you on? (you can check with ollama -v)

The chat api is available in 0.1.14 or later (just released yesterday :-). To upgrade simply re-download Ollama: https://ollama.ai/ on Linux or macOS. Hope this helps!

<!-- gh-comment-id:1850485175 --> @jmorganca commented on GitHub (Dec 11, 2023): Hi @slovanos! Which version of Ollama are you on? (you can check with `ollama -v`) The chat api is available in 0.1.14 or later (just released yesterday :-). To upgrade simply re-download Ollama: https://ollama.ai/ on Linux or macOS. Hope this helps!
GiteaMirror commented 2026-04-28 03:32:36 -05:00
Author
Owner
Copy Link

@slovanos commented on GitHub (Dec 11, 2023):

Thank you very much for the fast response. ollama version 0.1.13. So that may be the issue. Thanks!

<!-- gh-comment-id:1850545787 --> @slovanos commented on GitHub (Dec 11, 2023): Thank you very much for the fast response. ollama version 0.1.13. So that may be the issue. Thanks!
GiteaMirror commented 2026-04-28 03:32:37 -05:00
Author
Owner
Copy Link

@ghassett commented on GitHub (Feb 18, 2024):

I see this issue consistently when using the "mistral" model, but all works ok when using the "llama2." My installed version is "ollama version is 0.1.17" running on MacOS, Mac M1. With Ollama serving, I also get a 404 at http://localhost:11434/api/chat when trying to hit that URL in a browser.

<!-- gh-comment-id:1951350865 --> @ghassett commented on GitHub (Feb 18, 2024): I see this issue consistently when using the "mistral" model, but all works ok when using the "llama2." My installed version is "ollama version is 0.1.17" running on MacOS, Mac M1. With Ollama serving, I also get a 404 at http://localhost:11434/api/chat when trying to hit that URL in a browser.
GiteaMirror commented 2026-04-28 03:32:40 -05:00
Author
Owner
Copy Link

@boldranet commented on GitHub (Mar 30, 2024):

@ghassett read the error.message, and not just the status line. 404 means you haven't installed that model. use "ollama run mistral" first.

And GET requests, which you're sending in your browser, are routed differently. See also /Ollama/server.log

<!-- gh-comment-id:2028447587 --> @boldranet commented on GitHub (Mar 30, 2024): @ghassett read the error.message, and not just the status line. 404 means you haven't installed that model. use "ollama run mistral" first. And GET requests, which you're sending in your browser, are routed differently. See also /Ollama/server.log
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
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#47302
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?