Langfuse
Support for more modalities and base64 content #3004
Replies: 12 comments 3 replies
-
|
+1 base64 image (most wanted) I dont need to support video in my use-case |
Beta Was this translation helpful? Give feedback.
-
|
Great! The dataset also need to support Multi-Modal input. Looking forward! |
Beta Was this translation helpful? Give feedback.
-
|
Eagerly awaiting base64 support, especially in markdown |
Beta Was this translation helpful? Give feedback.
-
|
A few double clicks on base64 as reactions to our most recent newsletter |
Beta Was this translation helpful? Give feedback.
-
|
base64 images for sure. |
Beta Was this translation helpful? Give feedback.
-
|
+1 b64 images. Seems like the very next thing to support. Schema seems well established at this point. |
Beta Was this translation helpful? Give feedback.
-
|
Update: So I actually wound up writing a span intercept to strip b64 data and replace with filename. I plan on having a batch operation and worried it would balloon my DB. While looking at supporting other modalities, consider a way to decouple attachment reference so it can maybe resolve from a single source than to risk duplicating into the traces. |
Beta Was this translation helpful? Give feedback.
-
|
Base64 images for multimodal models is the missing feature that is holding us back from using Langfuse. PDF attachments would also be very helpful. |
Beta Was this translation helpful? Give feedback.
-
|
@tcbonds What alternative solution are you currently using? Our team is planning to add an AI observability tool, and your experience and insights would be greatly appreciated. |
Beta Was this translation helpful? Give feedback.
-
|
Arize Phoenix. So far we have had a pretty good experience with it. |
Beta Was this translation helpful? Give feedback.
-
|
Bas64 or image url would be great to support |
Beta Was this translation helpful? Give feedback.
-
|
Audio is mission critical for us |
Beta Was this translation helpful? Give feedback.
-
|
just here to add my support for base64 (because claude) |
Beta Was this translation helpful? Give feedback.
-
|
this is on the near-term roadmap, @hassiebp is working on it and specs look great, can't wait for the release! |
Beta Was this translation helpful? Give feedback.
-
|
Here to support Audio, PDF source. |
Beta Was this translation helpful? Give feedback.
-
Describe the feature or potential improvement
After our latest release supporting images (passed via url) in Langfuse, we're looking to support other modalities soon.
We're committed to supporting base64 images in the near term. We're further planning support for audio, video, and attachments (e.g. PDFs).
We'd love to gauge interest across the modalities to help with most efficient prioritisation.
Beta Was this translation helpful? Give feedback.
All reactions