Merge pull request #2041 from weaviate/text2vec-digitalocean

Add text2vec-digitalocean vectorizer module

Author: dirkkul

test/collection/test_config.py

@@ -2373,6 +2373,25 @@ def test_config_with_named_vectors(
             }
         },
     ),
+    (
+        [
+            Configure.Vectors.text2vec_digitalocean(
+                name="test", source_properties=["prop"], model="qwen2"
+            )
+        ],
+        {
+            "test": {
+                "vectorizer": {
+                    "text2vec-digitalocean": {
+                        "vectorizeClassName": True,
+                        "properties": ["prop"],
+                        "model": "qwen2",
+                    }
+                },
+                "vectorIndexType": "hnsw",
+            }
+        },
+    ),
     (
         [Configure.Vectors.text2vec_morph(name="test", source_properties=["prop"])],
         {

weaviate/collections/classes/config_vectorizers.py

@@ -119,6 +119,7 @@ class Vectorizers(str, Enum):
     TEXT2VEC_COHERE = "text2vec-cohere"
     TEXT2VEC_CONTEXTIONARY = "text2vec-contextionary"
     TEXT2VEC_DATABRICKS = "text2vec-databricks"
+    TEXT2VEC_DIGITALOCEAN = "text2vec-digitalocean"
     TEXT2VEC_GPT4ALL = "text2vec-gpt4all"
     TEXT2VEC_HUGGINGFACE = "text2vec-huggingface"
     TEXT2VEC_MISTRAL = "text2vec-mistral"
@@ -286,6 +287,21 @@ def _to_dict(self) -> Dict[str, Any]:
         return ret_dict
 
 
+class _Text2VecDigitalOceanConfig(_VectorizerConfigCreate):
+    vectorizer: Union[Vectorizers, _EnumLikeStr] = Field(
+        default=Vectorizers.TEXT2VEC_DIGITALOCEAN, frozen=True, exclude=True
+    )
+    model: str
+    vectorizeClassName: bool
+    baseURL: Optional[AnyHttpUrl]
+
+    def _to_dict(self) -> Dict[str, Any]:
+        ret_dict = super()._to_dict()
+        if self.baseURL is not None:
+            ret_dict["baseURL"] = self.baseURL.unicode_string()
+        return ret_dict
+
+
 class _Text2VecMorphConfig(_VectorizerConfigCreate):
     vectorizer: Union[Vectorizers, _EnumLikeStr] = Field(
         default=Vectorizers.TEXT2VEC_MORPH, frozen=True, exclude=True

weaviate/collections/classes/config_vectors.py

@@ -59,6 +59,7 @@
     _Text2VecCohereConfig,
     _Text2VecContextionaryConfig,
     _Text2VecDatabricksConfig,
+    _Text2VecDigitalOceanConfig,
     _Text2VecGoogleConfig,
     _Text2VecGPT4AllConfig,
     _Text2VecHuggingFaceConfig,
@@ -620,6 +621,42 @@ def text2vec_mistral(
             vector_index_config=_IndexWrappers.single(vector_index_config, quantizer),
         )
 
+    @staticmethod
+    def text2vec_digitalocean(
+        *,
+        name: Optional[str] = None,
+        quantizer: Optional[_QuantizerConfigCreate] = None,
+        base_url: Optional[AnyHttpUrl] = None,
+        model: str,
+        source_properties: Optional[List[str]] = None,
+        vector_index_config: Optional[_VectorIndexConfigCreate] = None,
+        vectorize_collection_name: bool = True,
+    ) -> _VectorConfigCreate:
+        """Create a vector using the `text2vec-digitalocean` module.
+
+        See the [documentation](https://weaviate.io/developers/weaviate/model-providers/digitalocean/embeddings)
+        for detailed usage.
+
+        Args:
+            name: The name of the vector.
+            quantizer: The quantizer to use for the vector index. If not provided, no quantization will be applied.
+            base_url: The base URL to use where API requests should go. Defaults to `None`, which uses the server-defined default of `https://inference.do-ai.run`.
+            model: The model to use, e.g. `qwen3-embedding-0.6b`. This is a required field on the server.
+            source_properties: Which properties should be included when vectorizing. By default all text properties are included.
+            vector_index_config: The configuration for Weaviate's vector index. Use `wvc.config.Configure.VectorIndex` to create a vector index configuration. None by default
+            vectorize_collection_name: Whether to vectorize the collection name. Defaults to `True`.
+        """
+        return _VectorConfigCreate(
+            name=name,
+            source_properties=source_properties,
+            vectorizer=_Text2VecDigitalOceanConfig(
+                baseURL=base_url,
+                model=model,
+                vectorizeClassName=vectorize_collection_name,
+            ),
+            vector_index_config=_IndexWrappers.single(vector_index_config, quantizer),
+        )
+
     @staticmethod
     def text2vec_morph(
         *,