# Python V4 - Set api version for Azure OpenAI vectorizer? **URL:** \ **Category:** Support\ **Tags:** python, azure, documentation\ **Created:** [August 8, 2024, 4:36pm UTC](https://forum.weaviate.io/t/python-v4-set-api-version-for-azure-openai-vectorizer/3306 "2024-08-08T16:36:38Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![Taylor\_Hickman](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/taylor_hickman/32/2099_2.png) [@Taylor\_Hickman](https://forum.weaviate.io/u/Taylor_Hickman)\ **Post date:** [August 8, 2024, 4:36pm UTC](https://forum.weaviate.io/t/python-v4-set-api-version-for-azure-openai-vectorizer/3306/1 "2024-08-08T16:36:38Z")
### Description Is there a way to set the api version for v4 Azure OpenAI vectorizer? I tried passing the OPENAI\_API\_VERSION but Weaviate seems to default to: /embeddings?api-version=2024-02-01 …but our instance of Azure OpenAI uses 2023-05-15 ### Server Setup Information - Weaviate Server Version: 1.26.1 - Deployment Method: Docker - Multi Node? Number of Running Nodes: Single - Client Language and Version: Python weaviate\_client-4.7.1 - Multitenancy?: ### Any additional Information ```yaml weaviate: image: cr.weaviate.io/semitechnologies/weaviate:latest ports: - 8080:8080 - 50051:50051 environment: QUERY_DEFAULTS_LIMIT: 25 AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'true' PERSISTENCE_DATA_PATH: '/var/lib/weaviate' AZURE_APIKEY: ${AZURE_OPENAI_API_KEY} OPENAI_API_TYPE: 'azure' ENABLE_MODULES: 'text2vec-azure-openai, text2vec-openai' DEFAULT_VECTORIZER_MODULE: 'none' OPENAI_API_VERSION: ${AZURE_OPENAI_API_VERSION} AZURE_ENDPOINT: ${AZURE_OPENAI_ENDPOINT} AZURE_OPENAI_BASE_URL: ${AZURE_OPENAI_BASE_URL} AZURE_OPENAI_RESOURCE_NAME: ${AZURE_OPENAI_RESOURCE_NAME} AZURE_OPENAI_API_VERSION: ${AZURE_OPENAI_API_VERSION} AZURE_OPENAI_EMBEDDING_DEPLOYMENT: ${AZURE_OPENAI_EMBEDDING_DEPLOYMENT} CLUSTER_HOSTNAME: 'node1' volumes: - weaviate_data:/var/lib/weaviate ``` ```python class WeaviateStore: def __init__ (self, settings: Settings): self.settings = settings self.client: weaviate.WeaviateAsyncClient = None self.class_name = settings.WEAVIATE_CLASS_NAME async def initialize(self): if self.client is None: connection_params = ConnectionParams.from_params( http_host=self.settings.WEAVIATE_HOST, http_port=self.settings.WEAVIATE_PORT, http_secure=False, grpc_host=self.settings.WEAVIATE_HOST, grpc_port=self.settings.WEAVIATE_GRPC_PORT, grpc_secure=False, ) self.client = weaviate.WeaviateAsyncClient( connection_params=connection_params, additional_headers={ "X-Azure-Api-Key": self.settings.AZURE_OPENAI_API_KEY, }, ) await self.client.connect() await self._create_or_update_schema() async def _create_or_update_schema(self): try: collection = self.client.collections.get(self.class_name) logger.info(f"Collection '{self.class_name}' already exists. Updating configuration.") await self.client.collections.delete(self.class_name) except UnexpectedStatusCodeError as e: if e.status_code != 404: logger.error(f"Unexpected error when checking for existing collection: {str(e)}") raise try: properties = [ Property(name="content", data_type=DataType.TEXT), Property(name="metadata", data_type=DataType.OBJECT, nested_properties=[ Property(name="source", data_type=DataType.TEXT), Property(name="document_type", data_type=DataType.TEXT), Property(name="npi", data_type=DataType.TEXT), ]), Property(name="npi", data_type=DataType.TEXT), ] vectorizer_config = Configure.Vectorizer.text2vec_azure_openai( resource_name=self.settings.AZURE_OPENAI_RESOURCE_NAME, deployment_id=self.settings.AZURE_OPENAI_EMBEDDING_DEPLOYMENT, base_url=self.settings.AZURE_OPENAI_ENDPOINT ) logger.info(f"Creating new collection '{self.class_name}'") await self.client.collections.create( name=self.class_name, properties=properties, vectorizer_config=vectorizer_config ) logger.info(f"Successfully created collection '{self.class_name}'") except UnexpectedStatusCodeError as e: logger.error(f"Failed to create collection: {str(e)}") raise except Exception as e: logger.error(f"Unexpected error during schema creation/update: {str(e)}", exc_info=True) raise ``` ---
**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 8, 2024, 9:22pm UTC](https://forum.weaviate.io/t/python-v4-set-api-version-for-azure-openai-vectorizer/3306/2 "2024-08-08T21:22:40Z")
hi @Taylor_Hickman !! I believe we have found an undocumented feature 🙂 `apiVersion` I am not sure you can pass `apiVersion` at query time. 🤔 I will have to ask internally as I couldn’t figure out from the PR: > > > \### What's being changed: > > This PR adds \`apiVersion\` support to \`text2vec-open…ai\` module. > > It sets the default \`apiVersion\` to \`2024-02-01\` both in \`text2vec-openai\` and \`generative-openai\` modules. > > \### Review checklist > > \- \[\] Documentation has been updated, if necessary. Link to changed documentation: > \- \[\] Chaos pipeline run or not necessary. Link to pipeline: > \- \[\] All new code is covered by tests where it is reasonable. > \- \[\] Performance tests have been run or not necessary. You can also change the baseUrl at query time, as documented here: > **[text2vec-openai | Weaviate - Vector Database](https://weaviate.io/developers/weaviate/modules/retriever-vectorizer-modules/text2vec-openai#query-time-parameters)** > > Overview I have also found some related forum threads: > [@Weaviate Post still using api-version=2022-12-01 even though the version has been retired](https://forum.weaviate.io/t/weaviate-post-still-using-api-version-2022-12-01-even-though-the-version-has-been-retired/1891): > > Hello. I am quite new to using weaviate but have enjoyed it well. Yesterday all of my embedding queries stopped working for my application as weaviate continues to try to connect to https://{resource}.openai.azure.com/openai/deployments/{deployment-id}/embeddings?api-version=2022-12-01. As of my understanding since yesterday 2.4.2024 that version has been retired. I read here that weaviate should try another version automatically. But clearly it does not so for me as it still uses 2022-12-01… > [@Api version in Query-time parameters?](https://forum.weaviate.io/t/api-version-in-query-time-parameters/2368/3): > > Yes, I added those to the collection definition and those worked for vectorizing our documents. but what about when I want to deploy the application and we are using a different base\_url when deployed? So if i want to vector search with “nearText” using a different base\_url. Thas base\_url should be added in the headers like “X-OpenAI-BaseURL”: {baseUrl} since I am making REST Api calls Let me know if this helps! ---
**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 9, 2024, 6:27pm UTC](https://forum.weaviate.io/t/python-v4-set-api-version-for-azure-openai-vectorizer/3306/3 "2024-08-09T18:27:57Z")
Hi! You cannot pass the `apiVersion` on query time ☹ Our team is looking into this. but right now, you will need to set the apiversion while creating a collection.