-
Notifications
You must be signed in to change notification settings - Fork 75
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
Mike Jang's proposed readability improvement #400
Conversation
✅ Deploy Preview for condescending-goldwasser-91acf0 ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
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 don't think that is correct interpretation of the original thought.
Vector databases are not directly useful for Sentiment analysis
or Speech recognition
.
Truthfully, the whole passage should be replaced with something more meaningful
Thank you @generall . Then I suggest that we close/replace this PR with an issue where we can discuss details. You stated:
The current document states: "...the data used to train a machine learning model to accomplish a task like sentiment analysis, speech recognition, object detection,..." The difference is too subtle for all but the most careful reader. If we want to get into such detail, I believe "that" belongs somewhere other than the "Introduction." (By "that," I'm referring to the list: |
- Sentiment analysis | ||
- Speech recognition | ||
- Object detection |
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 could link the example tasks to existing Qdrant use cases (taken from https://qdrant.tech/solutions/)
- Sentiment analysis | |
- Speech recognition | |
- Object detection | |
- [Similar Image Search](https://food-discovery.qdrant.tech/) | |
- [Semantic Text Search](https://demo.qdrant.tech/) | |
- [Anamoly Detection](https://qdrant.tech/articles/detecting-coffee-anomalies/) |
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.
Alternatively, if these examples are not appropriate, then we could remove them. After all, this is an introduction. Do either of these options make sense, @generall ?
In this PR, I'm improving the "readability" of https://qdrant.tech/documentation/overview/. I've used Vale to measure the Flesch-Kincaid readability of that section.
The readability of the current section is > 18. In other words, a typical user would stress as if they were reading a US graduate school textbook.
As shown in the linked screenshot, Vale includes suggestions to address this problem.
The readability of my proposed change is 8.5. A knowledgeable user who can read at a US high school level can understand this content, at a glance.