Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

More AI docs updates #12515

Merged
merged 6 commits into from
Jan 20, 2025
Merged

More AI docs updates #12515

merged 6 commits into from
Jan 20, 2025

Conversation

marcelklehr
Copy link
Member

🖼️ Screenshots

Sorry, can't get it to build for some reason.

Comment on lines +32 to +35
This app requires underlying Large language models to support tool calling. The default model in *llm2* does *not* support tool calling. Instead we recommend:

* Qwen 2.5 8B or higher
* Watt Tool 8B or higher
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe we can switch the default model in llm2 in favour of one of these models.
nothing again this PR though.

Copy link
Member

@julien-nc julien-nc left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

All good except a few small change requests.

I could build after reinstalling the dependencies.

developer_manual/digging_deeper/task_processing.rst Outdated Show resolved Hide resolved
admin_manual/ai/app_context_agent.rst Outdated Show resolved Hide resolved
admin_manual/ai/app_context_agent.rst Outdated Show resolved Hide resolved
admin_manual/ai/app_text2image_stablediffusion2.rst Outdated Show resolved Hide resolved
Scaling
-------

It is currently not possible to scale this app, we are working on this. Based on our calculations an instance has a rough capacity of 120 image requests per hour (each user request can be for multiple images). However, this number is based on theory and we do appreciate real-world feedback on this.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the testing setup could be mentioned here for a rough idea

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you elaborate?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I mean some details of the machine on which 120 images/h was achieved, the gpu and cpu perhaps.

Co-authored-by: Julien Veyssier <[email protected]>
Signed-off-by: Marcel Klehr <[email protected]>
@marcelklehr
Copy link
Member Author

I could build after reinstalling the dependencies.

I have python 3.13 on this machine, maybe it's related to that :/

Signed-off-by: Marcel Klehr <[email protected]>
Signed-off-by: Marcel Klehr <[email protected]>
@marcelklehr marcelklehr enabled auto-merge January 20, 2025 08:56
@marcelklehr marcelklehr merged commit dcc1211 into master Jan 20, 2025
12 checks passed
@marcelklehr marcelklehr deleted the enh/more-ai-updates branch January 20, 2025 09:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants