# Error in L2 Code Example

**URL:** <https://community.deeplearning.ai/t/error-in-l2-code-example/883608>\
**Category:** Building Multimodal Search and RAGs\
**Tags:** project\
**Created:** [November 19, 2025, 6:39am UTC](https://community.deeplearning.ai/t/error-in-l2-code-example/883608 "2025-11-19T06:39:41Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Humphrey001](https://avatars.discourse-cdn.com/v4/letter/h/7ea924/32.png) [@Humphrey001](https://community.deeplearning.ai/u/Humphrey001)\
**Post date:** [November 19, 2025, 6:39am UTC](https://community.deeplearning.ai/t/error-in-l2-code-example/883608/1 "2025-11-19T06:39:42Z")

</div>

![image](https://global.discourse-cdn.com/dlai/original/3X/2/2/222c1d967abcfd1fa2d2586956be7c8060fe9f49.png)

^Tried a few times trying to add image files into Weaviate

The next cells on trying to add video files also Weaviate also fails

Thanks!

---

<div class="post-metadata">

**Author:** ![SteveArthur](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/stevearthur/32/134892_2.png) [@SteveArthur](https://community.deeplearning.ai/u/SteveArthur)\
**Post date:** [November 26, 2025, 4:53pm UTC](https://community.deeplearning.ai/t/error-in-l2-code-example/883608/2 "2025-11-26T16:53:48Z")

</div>

This issue usually happens when the Weaviate instance isn’t configured with the correct **media modules** enabled. The default Weaviate setup in the course only supports text unless you explicitly enable the `multi2vec-clip` (for images) or `multi2vec-bind` modules. Without those modules running, any attempt to import image or video files will fail — even if the code itself is correct.

A few things to check:

1. **Confirm your Weaviate container is running with multimodal support**  
In your `docker-compose.yaml`, you should see something like:

2. **Restart Weaviate after enabling modules**  
Module changes only take effect on a clean restart:

3. **Verify module availability**  
Run:

4. **Ensure the file paths are valid**  
Especially in notebooks, relative paths often break — use absolute paths or confirm with:

Once the module is enabled and Weaviate restarts cleanly, the image and video insert examples should run exactly as shown in the course.

If you want, share your `docker-compose` or the `client.get_meta()` output — happy to help you pinpoint the exact issue.

---

<div class="post-metadata">

**Author:** ![taylorty](https://avatars.discourse-cdn.com/v4/letter/t/d6d6ee/32.png) [@taylorty](https://community.deeplearning.ai/u/taylorty)\
**Post date:** [December 19, 2025, 11:07am UTC](https://community.deeplearning.ai/t/error-in-l2-code-example/883608/3 "2025-12-19T11:07:39Z")

</div>

It seems that Weaviate client also updates from v3 to v4. Could we have the lab updated with the new api as well?

multi2vec\_google is the new module i believe

Thank you.