github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-21 13:11:39 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7136] Tool binding prevent streaming #4533

New Issue
Closed
opened 2026-04-12 15:28:13 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 15:28:13 -05:00
Owner
Copy Link

Originally created by @pyautoml on GitHub (Oct 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7136

What is the issue?

Hi there. I discovered recently that onces a model is delivered tool via bind_tools is stops recognizing streeaming, and each time it waits for the data to be fully loaded.

This snippet below works perfectly fine until tools are added:

print("AI:", end=" ", flush=True)
for chunk in self.model.stream([("human", user_input)], callbacks=[streaming_handler]):
if chunk.content:
print(chunk.content, end='', flush=True)

It happens regardless of the model type.

OS

Windows

GPU

No response

CPU

Intel

Ollama version

0.3.11

Originally created by @pyautoml on GitHub (Oct 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7136 ### What is the issue? Hi there. I discovered recently that onces a model is delivered tool via bind_tools is stops recognizing streeaming, and each time it waits for the data to be fully loaded. This snippet below works perfectly fine until tools are added: print("AI:", end=" ", flush=True) for chunk in self.model.stream([("human", user_input)], callbacks=[streaming_handler]): if chunk.content: print(chunk.content, end='', flush=True) It happens regardless of the model type. ### OS Windows ### GPU _No response_ ### CPU Intel ### Ollama version 0.3.11
GiteaMirror added the bug label 2026-04-12 15:28:13 -05:00
GiteaMirror commented 2026-04-12 15:28:14 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 8, 2024):

https://github.com/ollama/ollama/issues/5796

<!-- gh-comment-id:2400254468 --> @rick-github commented on GitHub (Oct 8, 2024): https://github.com/ollama/ollama/issues/5796
GiteaMirror commented 2026-04-12 15:28:14 -05:00
Author
Owner
Copy Link

@LuckLittleBoy commented on GitHub (Oct 10, 2024):

I hope streaming tool calls will be supported soon. I've been waiting for this for a long time.

<!-- gh-comment-id:2404217643 --> @LuckLittleBoy commented on GitHub (Oct 10, 2024): I hope streaming tool calls will be supported soon. I've been waiting for this for a long time.
GiteaMirror commented 2026-04-12 15:28:15 -05:00
Author
Owner
Copy Link

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

Going to close this as a dupe.

<!-- gh-comment-id:2415553609 --> @pdevine commented on GitHub (Oct 16, 2024): Going to close this as a dupe.
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#4533
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?