# Streaming markdown text and images from assistant using code interpreter

**URL:** <https://community.openai.com/t/streaming-markdown-text-and-images-from-assistant-using-code-interpreter/823042>\
**Category:** API\
**Created:** [June 16, 2024, 6:15pm UTC](https://community.openai.com/t/streaming-markdown-text-and-images-from-assistant-using-code-interpreter/823042 "2024-06-16T18:15:01Z")\
**Posts on this page:** 1\
**Showing post:** 10

<div class="post-metadata">

**Author:** ![karl.schelhammer1](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/karl.schelhammer1/32/149578_2.png) [@karl.schelhammer1](https://community.openai.com/u/karl.schelhammer1)\
**Post date:** [July 25, 2024, 4:58pm UTC](https://community.openai.com/t/streaming-markdown-text-and-images-from-assistant-using-code-interpreter/823042/10 "2024-07-25T16:58:07Z")

</div>

@suspicious_cow, might you have any insights on how to extend the event handler to be able to pass the tokens along through a websocket or SSE connection? I want to consume the stream in my backend, and forward the tokens via the on\_text\_delta(…) method using the event handler.

Based on your experience, does that seem advisable or even possible?

For reference, here’s a sample of what I’ve tried:

> [@Using Streaming Assistants API With Websockets](https://community.openai.com/t/using-streaming-assistants-api-with-websockets/879613/5):
>
> Why are you overriding the events in EventHandler?

---

_[View the full topic](https://community.openai.com/t/streaming-markdown-text-and-images-from-assistant-using-code-interpreter/823042)._