github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2861] use the /api/chat API,always response empty content #27506

New Issue
Closed
opened 2026-04-22 04:53:53 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-22 04:53:53 -05:00
Owner
Copy Link

Originally created by @NullpointerW on GitHub (Mar 1, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2861

request:

curl --location 'http://localhost:11434/api/chat' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gemma:7b-instruct-fp16",
    "message": [
        {
            "role": "user",
            "content": "why is the skyw blue?"
        }
    ]
}'

always return:

{
    "model": "gemma:7b-instruct-fp16",
    "created_at": "2024-03-01T11:17:53.3907871Z",
    "message": {
        "role": "assistant",
        "content": ""
    },
    "done": true
}
Originally created by @NullpointerW on GitHub (Mar 1, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2861 request: ``` curl curl --location 'http://localhost:11434/api/chat' \ --header 'Content-Type: application/json' \ --data '{ "model": "gemma:7b-instruct-fp16", "message": [ { "role": "user", "content": "why is the skyw blue?" } ] }' ``` always return: ``` json { "model": "gemma:7b-instruct-fp16", "created_at": "2024-03-01T11:17:53.3907871Z", "message": { "role": "assistant", "content": "" }, "done": true } ```
GiteaMirror commented 2026-04-22 04:53:55 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 1, 2024):

What type of system do you have? Also can you post the server logs? That particular model is pretty sizeable so requires a beefy system. Also check to make certain you're running Ollama 0.1.26 or later as gemma requires a newer version.

<!-- gh-comment-id:1973634296 --> @pdevine commented on GitHub (Mar 1, 2024): What type of system do you have? Also can you post the server logs? That particular model is pretty sizeable so requires a beefy system. Also check to make certain you're running Ollama 0.1.26 or later as gemma requires a newer version.
GiteaMirror commented 2026-04-22 04:53:55 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 1, 2024):

I just realized it was because you used message vs. messages. Try:

% curl --location 'http://localhost:11434/api/chat' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gemma:7b-instruct-fp16",
    "messages": [
        {
            "role": "user",
            "content": "why is the skyw blue?"
        }
    ]
}'
<!-- gh-comment-id:1973645454 --> @pdevine commented on GitHub (Mar 1, 2024): I just realized it was because you used `message` vs. `messages`. Try: ``` % curl --location 'http://localhost:11434/api/chat' \ --header 'Content-Type: application/json' \ --data '{ "model": "gemma:7b-instruct-fp16", "messages": [ { "role": "user", "content": "why is the skyw blue?" } ] }' ```
GiteaMirror commented 2026-04-22 04:53:56 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 1, 2024):

I'm going to go ahead and close the issue. Hope this helps though!

<!-- gh-comment-id:1973650825 --> @pdevine commented on GitHub (Mar 1, 2024): I'm going to go ahead and close the issue. Hope this helps though!
GiteaMirror commented 2026-04-22 04:53:57 -05:00
Author
Owner
Copy Link

@NullpointerW commented on GitHub (Mar 1, 2024):

I'm going to go ahead and close the issue. Hope this helps though!

You are right,thanks a lot.

<!-- gh-comment-id:1973709616 --> @NullpointerW commented on GitHub (Mar 1, 2024): > I'm going to go ahead and close the issue. Hope this helps though! You are right,thanks a lot.
GiteaMirror commented 2026-04-22 04:54:00 -05:00
Author
Owner
Copy Link

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

I just realized it was because you used message vs. messages. Try:

% curl --location 'http://localhost:11434/api/chat' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gemma:7b-instruct-fp16",
    "messages": [
        {
            "role": "user",
            "content": "why is the skyw blue?"
        }
    ]
}'

Yay! message vs messages got me! Now my first ollama scripting adventure is well underway.
Thank you internet stranger! ^_^

<!-- gh-comment-id:2044063050 --> @zamzx commented on GitHub (Apr 9, 2024): > I just realized it was because you used `message` vs. `messages`. Try: > > ``` > % curl --location 'http://localhost:11434/api/chat' \ > --header 'Content-Type: application/json' \ > --data '{ > "model": "gemma:7b-instruct-fp16", > "messages": [ > { > "role": "user", > "content": "why is the skyw blue?" > } > ] > }' > ``` Yay! message vs messages got me! Now my first ollama scripting adventure is well underway. Thank you internet stranger! ^_^
GiteaMirror commented 2026-04-22 04:54:02 -05:00
Author
Owner
Copy Link

@danydin commented on GitHub (Jun 30, 2024):

I just realized it was because you used message vs. messages. Try:

% curl --location 'http://localhost:11434/api/chat' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gemma:7b-instruct-fp16",
    "messages": [
        {
            "role": "user",
            "content": "why is the skyw blue?"
        }
    ]
}'

haha gosh i had the same typo.. programming can be so annoying sometimes without even any error messages which makes it seems like it all went fine, why there was no error coming from requesting non existing key though..?

<!-- gh-comment-id:2198460958 --> @danydin commented on GitHub (Jun 30, 2024): > I just realized it was because you used `message` vs. `messages`. Try: > > ``` > % curl --location 'http://localhost:11434/api/chat' \ > --header 'Content-Type: application/json' \ > --data '{ > "model": "gemma:7b-instruct-fp16", > "messages": [ > { > "role": "user", > "content": "why is the skyw blue?" > } > ] > }' > ``` haha gosh i had the same typo.. programming can be so annoying sometimes without even any error messages which makes it seems like it all went fine, why there was no error coming from requesting non existing key though..?
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#27506
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?