-
Notifications
You must be signed in to change notification settings - Fork 2.1k
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
docs: update clip search #820
Conversation
Codecov Report
@@ Coverage Diff @@
## main #820 +/- ##
==========================================
- Coverage 84.30% 82.17% -2.14%
==========================================
Files 21 21
Lines 1548 1548
==========================================
- Hits 1305 1272 -33
- Misses 243 276 +33
Flags with carried forward coverage won't be shown. Click here to find out more.
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
b70a501
to
355ade1
Compare
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.
change the server
@@ -1,4 +1,4 @@ | |||
# Search API | |||
# CLIP Search | |||
|
|||
|
|||
CLIP Search is a search paradigm that uses the CLIP model to encode the text and image documents into a common vector space. |
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.
In the image, should be 'matched results'
## Searching | ||
|
||
You can use {func}`~clip_client.client.Client.search` or {func}`~clip_client.client.Client.asearch` | ||
to search for relevant Documents in the index for a given query. |
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.
For more information...
``` | ||
|
||
|
||
The results will look like this, the most relevant doc is "she smiled, with pain" with the cosine distance of 0.096. And the apple image has the cosine distance of 0.799. |
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 think we can explain a little bit about how to interpret the result. For example: 'since by default we use cosine score, the smaller the value means...'
I don't see anything about |
📝 Docs are deployed on https://ft-fix-search-docs--jina-docs.netlify.app 🎉 |
No description provided.