Replies: 10 comments 1 reply
-
|
thanks for the feedback! |
Beta Was this translation helpful? Give feedback.
-
|
this still not a thing? thought I was missing something when I was trying it out today |
Beta Was this translation helpful? Give feedback.
-
|
any update on this feature? really need it |
Beta Was this translation helpful? Give feedback.
-
|
+1 |
Beta Was this translation helpful? Give feedback.
-
|
+1 :) |
Beta Was this translation helpful? Give feedback.
-
|
+1 |
Beta Was this translation helpful? Give feedback.
-
|
+1 |
Beta Was this translation helpful? Give feedback.
-
|
Any ETA on this? |
Beta Was this translation helpful? Give feedback.
-
|
+1 |
Beta Was this translation helpful? Give feedback.
-
|
Is this a duplicate of https://github.com/orgs/langfuse/discussions/6017? Should we combine them so we can better represent the demand for this feature? |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Describe the feature or potential improvement
Many other LLM observability platforms have the ability to add messages that contain images in the playground.
The UX I've seen usually allows the user to either paste in an image URL, or drop a file from their own machine onto the message. Presumably the platform then converts the file to base 64 and puts the value into the message.
Almost all of our agents require images, so this would be a great way to rapidly iterate on prompts. Today, we would have to run a script to extract the base64 from an image we have on our machine and then paste that giant block into the frontend. The frontend today also doesn't seem to support messages with type image at all.
Additional information
No response
Beta Was this translation helpful? Give feedback.
All reactions