# \[Question\] Multimodal search

**URL:** <https://forum.weaviate.io/t/question-multimodal-search/3691>\
**Category:** Support\
**Tags:** technical\
**Created:** [August 27, 2024, 11:40am UTC](https://forum.weaviate.io/t/question-multimodal-search/3691 "2024-08-27T11:40:02Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![vrano](https://avatars.discourse-cdn.com/v4/letter/v/5e9695/32.png) [@vrano](https://forum.weaviate.io/u/vrano)\
**Post date:** [August 27, 2024, 11:40am UTC](https://forum.weaviate.io/t/question-multimodal-search/3691/1 "2024-08-27T11:40:02Z")

</div>

Hello,

I’m building a reverse image search using Weaviate. I use CLIP to embed a product’s title and image and store it into the database. I also have additional properties such as product price which aren’t vectorized but might be used for filtering later on. I was wondering if there was a way to do image and text vectorized search without having the vector or object id at hand. So far the only way I have managed to do it is by generating a vector for the image & title I’m using for search, and searching by vector using that. I also wonder what’s the best way to handle deduplication.

Thanks in advance.

---

<div class="post-metadata">

**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\
**Post date:** [August 27, 2024, 12:18pm UTC](https://forum.weaviate.io/t/question-multimodal-search/3691/2 "2024-08-27T12:18:50Z")

</div>

hi @vrano !! Welcome to our community 🤗

For avoiding duplicate entries, the best approach is to leverage deterministic ids, which means that you generate the IDs based on some unique id you may have for your objects.

if you want to do media search, you can use the `near_image` or near\_media (videos/audios) to search. Considering you have vectorizer properly configured on that collection, Weaviate will vectorize the image used in query and use that vector to perform the search.

Here we have a recipe for multimodal, while it is using multi2vec-bind, it should be the same if using clip:

> **[GitHub - weaviate-tutorials/multimodal-workshop](https://github.com/weaviate-tutorials/multimodal-workshop)**
>
> Contribute to weaviate-tutorials/multimodal-workshop development by creating an account on GitHub.

Let me know if that helps!

THanks!

---

<div class="post-metadata">

**Author:** ![vrano](https://avatars.discourse-cdn.com/v4/letter/v/5e9695/32.png) [@vrano](https://forum.weaviate.io/u/vrano)\
**Post date:** [August 27, 2024, 1:17pm UTC](https://forum.weaviate.io/t/question-multimodal-search/3691/3 "2024-08-27T13:17:47Z")

</div>

HI @DudaNogueira,

that answers all my questions. Thank you for the quick response!

---

<div class="post-metadata">

**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\
**Post date:** [August 27, 2024, 3:06pm UTC](https://forum.weaviate.io/t/question-multimodal-search/3691/4 "2024-08-27T15:06:28Z")

</div>

Glad to hear that!

By the way, here is the docs for deterministic ids:

> **[Create objects | Weaviate - Vector Database](https://weaviate.io/developers/weaviate/manage-data/create#generate-deterministic-ids)**
>
> The examples on this page demonstrate how to create individual objects in Weaviate.

If you have any questions, we are here to help!