# How to specify stopwords with python V4 API

**URL:** <https://forum.weaviate.io/t/how-to-specify-stopwords-with-python-v4-api/1072>\
**Category:** Support\
**Tags:** developer-experience\
**Created:** [December 7, 2023, 10:19am UTC](https://forum.weaviate.io/t/how-to-specify-stopwords-with-python-v4-api/1072 "2023-12-07T10:19:33Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![alexisperrier](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/alexisperrier/32/739_2.png) [@alexisperrier](https://forum.weaviate.io/u/alexisperrier)\
**Post date:** [December 7, 2023, 10:19am UTC](https://forum.weaviate.io/t/how-to-specify-stopwords-with-python-v4-api/1072/1 "2023-12-07T10:19:33Z")

</div>

Hi,  
I’m using the python V4 API and I’d like to specify stopwords for French.  
In V3, this comes down to setting up [invertedIndexConfig](https://weaviate.io/developers/weaviate/config-refs/schema#invertedindexconfig--stopwords-stopword-lists).  
I can’t find the equivalent for V4

So far I got

```auto
client.collections.create(
                name= collection_name,
                vectorizer_config=vectorizer,
                generative_config=wvc.Configure.Generative.openai(),
                inverted_index_config = wvc.Configure.inverted_index( ??? ),

                properties=[list of properties]
            )

```

what parameters to pass to `wvc.Configure.inverted_index( ... )` so that I can specify a list of stopwords

Thanks

---

<div class="post-metadata">

**Author:** ![alexisperrier](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/alexisperrier/32/739_2.png) [@alexisperrier](https://forum.weaviate.io/u/alexisperrier)\
**Post date:** [December 8, 2023, 1:25pm UTC](https://forum.weaviate.io/t/how-to-specify-stopwords-with-python-v4-api/1072/2 "2023-12-08T13:25:47Z")

</div>

> [@alexisperrier](#):
>
> `wvc.Configure.inverted_index`

Digging further into the documentation and classes, I found the following solution to add a list of stopwords to the collection.

To see the configuration of the collection use:

```auto
collection.config.get()

```

To set the stopwords using the `wvc.Configure.inverted_index( ??? )` function:

set the params of the function (all default values except for stopwords\_additions)

```auto
params = {
    "bm25_b": 0.75,
    "bm25_k1": 1.2,
    "cleanup_interval_seconds": 60,
    "index_timestamps": False,
    "index_property_length": False,
    "index_null_state": False,
    "stopwords_preset": None,
    "stopwords_additions": list_stopwords,
    "stopwords_removals": None,
}

```

The create the collection, passing params to the function:

```auto
collection = client.collections.create(
    name= <collection_name>,
    vectorizer_config=vectorizer,
    generative_config=wvc.Configure.Generative.openai(),
    inverted_index_config = wvc.Configure.inverted_index(**params),
    properties=[
        < list of properties>
    ]
)

```

However this fails to set the stopword\_preset to `None` although it seems to be a [valid value for](https://weaviate.io/developers/weaviate/config-refs/schema#invertedindexconfig--stopwords-stopword-lists) `stopwords_preset`.

You can also create the collection without specifying the stopwords, and later on update the stopwords property with

```auto
collection.config.update(
    # Note, use Reconfigure here (not Configure)
    inverted_index_config=wvc.Reconfigure.inverted_index(
        stopwords_additions=["le", "la", "il", "elle"]
    )
)

```

---

<div class="post-metadata">

**Author:** ![alexisperrier](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/alexisperrier/32/739_2.png) [@alexisperrier](https://forum.weaviate.io/u/alexisperrier)\
**Post date:** [December 8, 2023, 3:31pm UTC](https://forum.weaviate.io/t/how-to-specify-stopwords-with-python-v4-api/1072/3 "2023-12-08T15:31:46Z")

</div>

Wrote a short blog post to summarize everything

[Adding French stopwords tp a weaviate collection with Python V4 API](https://alexisperrier.com/nlp/2023/12/07/French-stopwords-in-weaviate-python-V4.html)

---

<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:** [December 12, 2023, 10:02pm UTC](https://forum.weaviate.io/t/how-to-specify-stopwords-with-python-v4-api/1072/4 "2023-12-12T22:02:34Z")

</div>

Hi @alexisperrier !!

Wow! Thanks a lot for writing and sharing your blog post! Glad you figured it out!

We should be updating the docs soon.

Thanks!

---

<div class="post-metadata">

**Author:** ![rjalex](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/rjalex/32/807_2.png) [@rjalex](https://forum.weaviate.io/u/rjalex)\
**Post date:** [May 15, 2024, 7:25am UTC](https://forum.weaviate.io/t/how-to-specify-stopwords-with-python-v4-api/1072/5 "2024-05-15T07:25:52Z")

</div>

As of May 2024 the problem of the EN stopwords being added to the collection configuration even if you properly use the “stopwords\_preset”: None is still present.

I have performed the same but still see \<StopwordsPreset.EN: ‘en’\> via a config.get()

How can I properly define my collection to ONLY use my provided additions?

PS As of May 2024 there’s a small change. You should use  
`import weaviate.classes.config as wvcc`  
to be able to use  
`inverted_index_config=wvcc.Configure.inverted_index(**bm25_params)`

---

<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:** [May 16, 2024, 2:00pm UTC](https://forum.weaviate.io/t/how-to-specify-stopwords-with-python-v4-api/1072/6 "2024-05-16T14:00:07Z")

</div>

hi @rjalex

Can you produce a code sample? We could open an issue for that as I was not able to find one related to that.

Thanks!

---

<div class="post-metadata">

**Author:** ![rjalex](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/rjalex/32/807_2.png) [@rjalex](https://forum.weaviate.io/u/rjalex)\
**Post date:** [May 16, 2024, 4:23pm UTC](https://forum.weaviate.io/t/how-to-specify-stopwords-with-python-v4-api/1072/7 "2024-05-16T16:23:25Z")

</div>

@DudaNogueira here we are. I used the embedded version for brevity but in my real case I am using 1.24.11 and the behaviour is the same. Thank you.

```auto
import weaviate
import weaviate.classes.config as wvcc

COLL_NAME_STR = "no_english_stopwords"

client = weaviate.connect_to_embedded()
client.collections.delete(COLL_NAME_STR)
bm25_params = {
    "bm25_b": 0.75,
    "bm25_k1": 1.2,
    "cleanup_interval_seconds": 60,
    "index_timestamps": False,
    "index_property_length": False,
    "index_null_state": False,
    "stopwords_preset": None,
    "stopwords_additions": ["di", "a", "da", "in", "con", "su", "per", "tra", "fra"],
    "stopwords_removals": None,
}

client.collections.create(
    name=COLL_NAME_STR,
    description="A collection with only a custom list of stopwords",
    vectorizer_config=None,
    inverted_index_config=wvcc.Configure.inverted_index(**bm25_params),
    properties=[
        wvcc.Property(
            name="blahblah",
            data_type=wvcc.DataType.TEXT,
            skip_vectorization=True,
        )
    ],
)

mycollection = client.collections.get(COLL_NAME_STR)
COLL_CONFIG = mycollection.config.get()
assert (
    COLL_CONFIG.inverted_index_config.stopwords.preset is None
), f"Expected stopwords preset to be None as declared in the inverted index configuration, but got {COLL_CONFIG.inverted_index_config.stopwords.preset}"

```