-
Notifications
You must be signed in to change notification settings - Fork 0
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
Llm 85/add readme #14
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looking great! Let's pass this through ChatGPT or Grammarly to ensure that there are no typos or weird expressions
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice job! You shouldn't wait on my work, I'll add it once it's done.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great work!
I think this needs further iteration, but we are in a good direction!
README.md
Outdated
## Contributing | ||
# Introduction | ||
|
||
We use IntelliJ IDEA for development. You can import the project as a Gradle project. | ||
The eLLMental project raises from the necessity of developer's to have a single framework that joins flexibility, | ||
efficiency and productivity while building the different block an AI application. During this time, we've seen different | ||
challenges that motivated us to start building this project: | ||
|
||
Install the `Save Actions Tool` plugin by `Alexandre DuBreuil` to automatically format the code on save. | ||
1. **Lack of Robust Tools and Libraries:** The field being fairly new means there's a lack of effective tools | ||
custom-made for LLMs, making it more difficult for developers to understand how LLMs work nowadays. | ||
2. **MLOps management:** There's no one-size-fits-all solution in MLOps and particularly with LLMs, resulting in | ||
heterogeneity in the tools, platforms, and workflow processes. This means more time is needed to find the right | ||
stack. Also, evaluating LLMs performance is not straightforward. | ||
3. **Security**: Ensuring the security of the underlying infrastructure, including network security, firewall | ||
configurations, and container security, is a major challenge. Setting up appropriate monitoring and alerts can be | ||
both technically challenging and resource-intensive. | ||
4. **Privacy:** LLMs often require large amounts of data, raising potential data privacy issues, which may not be | ||
adequately addressed by existing MLOps platforms. | ||
5. **Flexibility:** Application's needs grow constantly, and so does AI applications. That's why we are adopting a |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I want to review this part with Chechu @juanjoman. I'm not convinced about the content. The pitch is not right enough.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Awesome! I was also missing a "catchier" pitch :P
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great work @juanjoman! I've added many suggestions to edit and reorganize the content, but it's a good starting point. I think we should review the pending comments and merge this PR, we can keep editing in future PRs.
@@ -0,0 +1,3 @@ | |||
# Deployments | |||
|
|||
<Andre's PR here> |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we need to merge @mnlx's PR before merging this one?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Or he can merge his after this one is merged @javiertoledo
|
||
- name: Download CONTRIBUTING.md | ||
run: | | ||
curl -o CONTRIBUTING.md https://raw.githubusercontent.com/theam/eLLMental/main/CONTRIBUTING.md |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Disclaimer: This will only work when the repo is public
This workaround is done because when we publish the workdir is website
dir, so we can't access the contributing file in root
on: | ||
# TODO: Change this before merge -> | ||
#push: | ||
pull_request: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We need to change before merging, I use this to test in the PR
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@juanjoman this is a great v1 for the docs, README and CONTRIBUTING, if there are no other pending conversations, I'd merge it and plan further changes in future PRs
# Conflicts: # README.md
https://agilemonkeys.atlassian.net/browse/LLM-85
https://agilemonkeys.atlassian.net/browse/LLM-160