# How to create vector embedding for multiple fields

**URL:** <https://forum.weaviate.io/t/how-to-create-vector-embedding-for-multiple-fields/4447>\
**Category:** Support\
**Created:** [October 6, 2024, 11:48am UTC](https://forum.weaviate.io/t/how-to-create-vector-embedding-for-multiple-fields/4447 "2024-10-06T11:48:53Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Rishi\_Prakash](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/rishi_prakash/32/2367_2.png) [@Rishi\_Prakash](https://forum.weaviate.io/u/Rishi_Prakash)\
**Post date:** [October 6, 2024, 11:48am UTC](https://forum.weaviate.io/t/how-to-create-vector-embedding-for-multiple-fields/4447/1 "2024-10-06T11:48:53Z")

</div>

I want to store embedding separately for two fields. For example, I am creating a schema like this

```python
           skills = self.client.collections.create(
                name=self.collection_name,
                vectorizer_config=wvc.config.Configure.Vectorizer.text2vec_azure_openai(
                    deployment_id="text-embedding-ada-002",
                    resource_name="",
                    vectorize_collection_name=True
                ),
                properties=[
                    wvc.config.Property(
                        name="skill_name",
                        data_type=wvc.config.DataType.TEXT,
                        vectorize_property_name=True
                    ),
                    wvc.config.Property(
                        name="description",
                        data_type=wvc.config.DataType.TEXT,
                        vectorize_property_name=True
                    ),
                    wvc.config.Property(
                        name="etldatetime",
                        data_type=wvc.config.DataType.TEXT,
                        skip_vectorization=True
                    ),
                ]
            )

```

now i want skill\_name and description embedding to be created separately,  
share me the query for it, also how to search from the collection similarly, Thanks

---

<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:** [October 6, 2024, 5:39pm UTC](https://forum.weaviate.io/t/how-to-create-vector-embedding-for-multiple-fields/4447/2 "2024-10-06T17:39:56Z")

</div>

hi @Rishi_Prakash !!

This is a named vector (multi vector) use case.

When you define a single vectorizer, just like you have done, Weavaite will concatenate all “vectorizable” properties.

Now, if you want to create vectors for specific properties (single o multiple properties), you should define different named vectors, as stated here:

> **[Multiple vectors | Weaviate](https://weaviate.io/developers/weaviate/config-refs/schema/multi-vector)**
>
> \[comment\] multi-vector-support dot mdx )

with that said, this is how you collection should be created:

```python
client.collections.delete("Test")
skills = client.collections.create(
                name="Test",
                vectorizer_config=[
                    wvc.config.Configure.NamedVectors.text2vec_openai(
                        name="skill_vector", vectorize_collection_name=True,
                        source_properties=["skill_name", "etldatetime"]
                    ),
                    wvc.config.Configure.NamedVectors.text2vec_openai(
                        name="description_vector", vectorize_collection_name=True,
                        source_properties=["description"]
                    )                    
                ],
                properties=[
                    wvc.config.Property(
                        name="skill_name",
                        data_type=wvc.config.DataType.TEXT,
                        vectorize_property_name=True
                    ),
                    wvc.config.Property(
                        name="description",
                        data_type=wvc.config.DataType.TEXT,
                        vectorize_property_name=True
                    ),
                    wvc.config.Property(
                        name="etldatetime",
                        data_type=wvc.config.DataType.TEXT,
                        skip_vectorization=True
                    ),
                ]
            )
skills.data.insert({"skill_name": "this is a skill", "description": "This is a skill desc", "etldatetime": "some etldatetime"})

```

note that you will get now two vectors, as below:

```python
o = skills.query.fetch_objects(include_vector=True).objects[0]
o.vector.keys()

```

Output:

> dict\_keys([‘skill\_vector’, ‘description\_vector’])

Let me know if this helps!

Thanks!