---
title: "See What Your AI Sees: Multimodal Tracing for Images, Audio, and Files"
url: https://daily.dev/posts/see-what-your-ai-sees-multimodal-tracing-for-images-audio-and-files-evcs0ckmi
source_url: https://mlflow.org/blog/multimodal-tracing
type: article
source: "mlflow"
published: 2026-04-29T04:23:26.450Z
updated: 2026-04-29T04:23:58.043Z
tags: ["machine-learning", "genai", "observability", "multimodal"]
reading_time: 4
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# See What Your AI Sees: Multimodal Tracing for Images, Audio, and Files

**[mlflow](https://daily.dev/sources/MLflow)** · 4 min read · 0 upvotes · 0 comments

## Summary

MLflow 3.11 introduces multimodal tracing, which automatically extracts binary content (images, audio, PDFs) from AI agent traces instead of storing raw base64 strings in the trace database. Binary data is offloaded to artifact storage (S3, Azure Blob, GCS, etc.) while spans retain only lightweight reference URIs. The feature works out of the box with autologging for OpenAI, Anthropic, Gemini, Bedrock, and LangChain, covering 8 multimodal data patterns. A manual Attachment API handles custom file types. The MLflow UI renders images as thumbnails, audio with inline playback controls, and PDFs in an embedded viewer, enabling proper debugging of vision and audio model behavior.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://mlflow.org/blog/multimodal-tracing>

## Similar posts on daily.dev

- [Building Real-Time Multimodal AI Pipelines](https://daily.dev/posts/building-real-time-multimodal-ai-pipelines-xqsbruifc) · Salesforce Engineering · 37 upvotes · 0 comments
- [Multi-Modal AI Agents In Production 2026: Vision, Audio, Glue](https://daily.dev/posts/multi-modal-ai-agents-in-production-2026-vision-audio-glue-xmtiipzk9) · Alex CloudStar · 1 upvotes · 0 comments
- [What is Multimodal AI and How it Works](https://daily.dev/posts/what-is-multimodal-ai-and-how-it-works-ak4bcjwyl) · Docker · 0 upvotes · 0 comments
- [When AI Starts Seeing and Hearing, IT Must Start Rethinking](https://daily.dev/posts/when-ai-starts-seeing-and-hearing-it-must-start-rethinking-gctxeh7ag) · The New Stack · 1 upvotes · 0 comments

---

Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#genai](https://daily.dev/tags/genai), [#observability](https://daily.dev/tags/observability), [#multimodal](https://daily.dev/tags/multimodal)

[View this post on daily.dev](https://daily.dev/posts/see-what-your-ai-sees-multimodal-tracing-for-images-audio-and-files-evcs0ckmi)