-
Notifications
You must be signed in to change notification settings - Fork 216
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
added a Sessions blog - PENDING APPROVAL until vector DB is done #2228
Conversation
LinaLam
commented
Jul 2, 2024
•
edited
Loading
edited
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
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.
PR Summary
This pull request adds a new blog post about debugging chatbots and AI agents with sessions, including new files for layout, page content, and the blog post itself in MDX format.
- Added new blog post "Debugging RAG Chatbots and AI Agents with Sessions" in
/bifrost/app/blog/debugging-chatbots-and-ai-agents-with-sessions/
- Updated
/bifrost/app/blog/page.tsx
to include the new blog post in the content list layout.tsx
in the new blog post directory doesn't utilize imported components (NavBar, Footer, Analytics)- Consider improving error handling in
page.tsx
for file reading and MDX compilation - Ensure consistency in metadata across new files and existing blog structure
4 file(s) reviewed, 9 comment(s)
Edit PR Review Bot Settings
import NavBar from "@/components/layout/navbar"; | ||
import Footer from "@/components/layout/footer"; | ||
import "@mintlify/mdx/dist/styles.css"; | ||
import { Analytics } from "@vercel/analytics/react"; |
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.
logic: NavBar, Footer, and Analytics components are imported but not used in the layout
import "@mintlify/mdx/dist/styles.css"; | ||
import { Analytics } from "@vercel/analytics/react"; | ||
|
||
const inter = Inter({ subsets: ["latin"] }); |
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.
style: Inter font is defined but not applied to the layout
return ( | ||
<> | ||
{children} | ||
</> | ||
); |
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.
style: Consider wrapping children in a main tag for better semantic structure
"src.mdx" | ||
); | ||
|
||
const source = fs.readFileSync(filePath, "utf8"); |
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.
logic: Add error handling for file read operation
<span className="text-sm font-bold">back</span> | ||
</Link> | ||
<h3 className="text-sm font-semibold text-gray-500 pt-8"> | ||
<span className="text-black">Time</span>: {String(frontmatter.time)} |
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.
style: Use a more semantic HTML element for time, like
<Link href="/blog" className="flex items-center gap-1"> | ||
<ChevronLeftIcon className="w-4 h-4" /> | ||
<span className="text-sm font-bold">back</span> | ||
</Link> |
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.
style: Add aria-label to improve accessibility of back link
const filePath = path.join( | ||
process.cwd(), | ||
"app", | ||
"blog", | ||
"debugging-chatbots-and-ai-agents-with-sessions", | ||
"src.mdx" | ||
); |
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.
style: Consider using a constant for the blog post directory path
|
||
**For example,** if users often ask about specific types of workouts (i.e., strength training vs. cardio), developers can prompt the chatbot to offer more personalized plans and advice, thereby improving user satisfaction. | ||
|
||
1. **Improving response accuracy** |
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.
syntax: This numbered item should be '3.' instead of '1.' to maintain the correct sequence.
bifrost/app/blog/page.tsx
Outdated
imageAlt: "Lina Lam's headshot", | ||
}, | ||
], | ||
time: "5 minute read", |
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.
style: Consider making the reading time more specific, e.g., '5-minute read' instead of '5 minute read' for consistency with other entries.
3. **Implementing the task**: With the acquired data, AI agents methodically implement the tasks, they evaluate their progress and adjust as needed based on feedback and internal logs. | ||
|
||
|
||
By analyzing this data, AI agents predict the optimal outcomes aligned with the preset goals and determine what actions to take next. For example, self-driving cars use sensor data to navigate obstacles effectively. This iterative process continues until the agent achieves the designated goal. |
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.
Lets replace self driving cars with a more relatable AI agent example. We're specifically talking about them in the realm of LLMs
|
||
## What are AI agents? | ||
|
||
An AI agent is a software program that **<span style={{color: '#0ea5e9'}}>autonomously performs specific tasks using advanced decision-making abilities</span>**. It interacts with its environment by collecting data, processing it, and deciding on the best actions to achieve predefined goals. |
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.
This is more focused to AI agents in general. We should be talking about AI agents powered by LLMs
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.
- refine your chatbot's responses based on specific contexts. | ||
|
||
|
||
## Using Sessions in Helicone |
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.
Honestly not sure how to improve this, but switching right into integration seems a bit jarring. The reader might be confused at the code tbh.
|
||
## How Industries Use Sessions to Debug AI Agents | ||
|
||
### Resolving Errors in Multi-Step Processes |
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.
Adding images of these sessions within Helicone would be awesome.
potentially they could be made in figma vs coding them