github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10712] toolcall supports streaming output #69097

New Issue
Closed
opened 2026-05-04 17:08:41 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-04 17:08:41 -05:00
Owner
Copy Link

Originally created by @williamlzw on GitHub (May 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10712

I use C# OllamaSharp to call the Ollama model, but I found that the tool call feature does not support streaming output.
I use the qwen API and OpenAI C# SDK to call ToolCall, which supports streaming output.
baseurl: https://dashscope.aliyuncs.com/compatible-mode/v1
model: qwen3-235b-a22b

Originally created by @williamlzw on GitHub (May 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10712 I use C# OllamaSharp to call the Ollama model, but I found that the tool call feature does not support streaming output. I use the qwen API and OpenAI C# SDK to call ToolCall, which supports streaming output. baseurl: https://dashscope.aliyuncs.com/compatible-mode/v1 model: qwen3-235b-a22b
GiteaMirror added the feature request label 2026-05-04 17:08:41 -05:00
GiteaMirror commented 2026-05-04 17:08:43 -05:00
Author
Owner
Copy Link

@williamlzw commented on GitHub (May 15, 2025):

import os
from openai import OpenAI

client = OpenAI(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"), # 如何获取API Key：https://help.aliyun.com/zh/model-studio/developer-reference/get-api-key
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-235b-a22b", # 模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    messages=[
        {'role': 'system', 'content': 'You are a helpful assistant.'},
        {'role': 'user', 'content': '你是谁？'}
        ]
)
print(completion.choices[0].message.content)
<!-- gh-comment-id:2882122028 --> @williamlzw commented on GitHub (May 15, 2025): ``` import os from openai import OpenAI client = OpenAI( # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx", api_key=os.getenv("DASHSCOPE_API_KEY"), # 如何获取API Key：https://help.aliyun.com/zh/model-studio/developer-reference/get-api-key base_url="https://dashscope.aliyuncs.com/compatible-mode/v1", ) completion = client.chat.completions.create( model="qwen3-235b-a22b", # 模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models messages=[ {'role': 'system', 'content': 'You are a helpful assistant.'}, {'role': 'user', 'content': '你是谁？'} ] ) print(completion.choices[0].message.content) ```
GiteaMirror commented 2026-05-04 17:08:43 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 15, 2025):

#10415

<!-- gh-comment-id:2882804575 --> @rick-github commented on GitHub (May 15, 2025): #10415
GiteaMirror commented 2026-05-04 17:08:44 -05:00
Author
Owner
Copy Link

@williamlzw commented on GitHub (May 19, 2025):

When the OpenAI SDK calls the tool method, it captures the internal raw return data in real time, parses the Think tags, and renders them in real time, so as to achieve the effect of invoking the tool to render the Think tags in a stream. The ollama parsing tool method needs to be added to the callback to capture the original data.

<!-- gh-comment-id:2890122715 --> @williamlzw commented on GitHub (May 19, 2025): When the OpenAI SDK calls the tool method, it captures the internal raw return data in real time, parses the Think tags, and renders them in real time, so as to achieve the effect of invoking the tool to render the Think tags in a stream. The ollama parsing tool method needs to be added to the callback to capture the original data.
GiteaMirror commented 2026-05-04 17:08:45 -05:00
Author
Owner
Copy Link

@williamlzw commented on GitHub (May 19, 2025):

https://github.com/imxcstar/Tinvo/blob/master/Tinvo.Provider.OpenAI/AIScheduler/OpenAIProviderParser.cs

<!-- gh-comment-id:2890271730 --> @williamlzw commented on GitHub (May 19, 2025): https://github.com/imxcstar/Tinvo/blob/master/Tinvo.Provider.OpenAI/AIScheduler/OpenAIProviderParser.cs
GiteaMirror commented 2026-05-04 17:08:45 -05:00
Author
Owner
Copy Link

@williamlzw commented on GitHub (May 20, 2025):

https://github.com/ollama/ollama/issues/8529

<!-- gh-comment-id:2893185852 --> @williamlzw commented on GitHub (May 20, 2025): https://github.com/ollama/ollama/issues/8529
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 feature request
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#69097
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?