You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: pages/docs/observability/features/multi-modality.mdx
+5-11Lines changed: 5 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,12 +6,6 @@ sidebarTitle: Multi-Modality
6
6
7
7
# Multi-Modality and Attachments
8
8
9
-
<Callouttype="info">
10
-
11
-
Support for media attachments to traces is currently in beta. Please report any [issues](/issues) and add feature requests to this ongoing [discussion thread](https://github.com/orgs/langfuse/discussions/3004).
12
-
13
-
</Callout>
14
-
15
9
Langfuse supports multi-modal traces including **text, images, audio, and other attachments**.
16
10
17
11
By default, **[base64 encoded data URIs](https://developer.mozilla.org/en-US/docs/Web/URI/Schemes/data#syntax) are handled automatically by the Langfuse SDKs**. They are extracted from the payloads commonly used in multi-modal LLMs, uploaded to Langfuse's object storage, and linked to the trace.
@@ -34,7 +28,7 @@ import MultiModalImageGallery from "@/components-mdx/multi-modal-image-gallery.m
34
28
35
29
### Langfuse Cloud
36
30
37
-
Multi-modal attachments on Langfuse Cloud are free while in beta. We will be rolling out a new pricing metric to account for the additional storage and compute costs associated with large multi-modal traces in the coming weeks.
31
+
Multi-modal attachments on Langfuse Cloud are currently free on Langfuse Cloud. We reserve the option to roll out a new pricing metric to account for the additional storage and compute costs associated with large multi-modal traces in the near-term future.
38
32
39
33
### Self-hosting
40
34
@@ -166,17 +160,17 @@ with langfuse.start_as_current_span(name="analyze-document") as span: # Include
0 commit comments