github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1398] Bug: API - Chat docs examples are using api/generate in URL instead of api/chat #26502

New Issue
Closed
opened 2026-04-22 02:48:22 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 02:48:22 -05:00
Owner
Copy Link

Originally created by @calderonsamuel on GitHub (Dec 6, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1398

32f62fbb8e/docs/api.md (L317-L327)

32f62fbb8e/docs/api.md (L366-L384)

Originally created by @calderonsamuel on GitHub (Dec 6, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1398 https://github.com/jmorganca/ollama/blob/32f62fbb8e0b1ecb4ec8369586562abce86c8e50/docs/api.md?plain=1#L317-L327 https://github.com/jmorganca/ollama/blob/32f62fbb8e0b1ecb4ec8369586562abce86c8e50/docs/api.md?plain=1#L366-L384
GiteaMirror commented 2026-04-22 02:48:23 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Dec 6, 2023):

Thanks for the issue and sorry about this – should be fixed now!

<!-- gh-comment-id:1843615665 --> @jmorganca commented on GitHub (Dec 6, 2023): Thanks for the issue and sorry about this – should be fixed now!
GiteaMirror commented 2026-04-22 02:48:23 -05:00
Author
Owner
Copy Link

@Joao-Pimenta commented on GitHub (Dec 6, 2023):

I actually get <Response [404]> when I try to use the chat API. I was using:

url = "http://127.0.0.1:11434/api/generate"
data = {
"model": "wizard",
"stream": False,
"prompt": prompt,
"options":{
"num_predict":50
}
}

And getting great results.
I was just now reading the documentation, trying to switch to a chat with history, and was still not able to make it work.
I now have:
url = "http://127.0.0.1:11434/api/chat"
data = {
"model": "wizard",
"stream": False,
"messages": chats,
"options":{
"num_predict":50
}
}
where chats is [{'role': 'user', 'content': 'Test 1'}]. And I get <Response [404]>

<!-- gh-comment-id:1843649262 --> @Joao-Pimenta commented on GitHub (Dec 6, 2023): I actually get <Response [404]> when I try to use the chat API. I was using: url = "http://127.0.0.1:11434/api/generate" data = { "model": "wizard", "stream": False, "prompt": prompt, "options":{ "num_predict":50 } } And getting great results. I was just now reading the documentation, trying to switch to a chat with history, and was still not able to make it work. I now have: url = "http://127.0.0.1:11434/api/chat" data = { "model": "wizard", "stream": False, "messages": chats, "options":{ "num_predict":50 } } where chats is [{'role': 'user', 'content': 'Test 1'}]. And I get <Response [404]>
GiteaMirror commented 2026-04-22 02:48:24 -05:00
Author
Owner
Copy Link

@calderonsamuel commented on GitHub (Dec 6, 2023):

I get the same when I use the docker ollama:latest image. I think we just need to wait until they sync it.

I actually get <Response [404]> when I try to use the chat API. I was using:

url = "http://127.0.0.1:11434/api/generate" data = { "model": "wizard", "stream": False, "prompt": prompt, "options":{ "num_predict":50 } }

And getting great results. I was just now reading the documentation, trying to switch to a chat with history, and was still not able to make it work. I now have: url = "http://127.0.0.1:11434/api/chat" data = { "model": "wizard", "stream": False, "messages": chats, "options":{ "num_predict":50 } } where chats is [{'role': 'user', 'content': 'Test 1'}]. And I get <Response [404]>

<!-- gh-comment-id:1843655906 --> @calderonsamuel commented on GitHub (Dec 6, 2023): I get the same when I use the docker ollama:latest image. I think we just need to wait until they sync it. > I actually get <Response [404]> when I try to use the chat API. I was using: > > url = "http://127.0.0.1:11434/api/generate" data = { "model": "wizard", "stream": False, "prompt": prompt, "options":{ "num_predict":50 } } > > And getting great results. I was just now reading the documentation, trying to switch to a chat with history, and was still not able to make it work. I now have: url = "http://127.0.0.1:11434/api/chat" data = { "model": "wizard", "stream": False, "messages": chats, "options":{ "num_predict":50 } } where chats is [{'role': 'user', 'content': 'Test 1'}]. And I get <Response [404]>
GiteaMirror commented 2026-04-22 02:48:25 -05:00
Author
Owner
Copy Link

@tbirand commented on GitHub (Dec 6, 2023):

I'm also getting the same 404 api error with the docker container.

<!-- gh-comment-id:1843783046 --> @tbirand commented on GitHub (Dec 6, 2023): I'm also getting the same 404 api error with the docker container.
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#26502
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?