Update docs and bugfix caused by DATASOURCE_TYPE setting (#881)

microsoft · May 25, 2024 · b518ba0 · b518ba0
1 parent 78d0402
commit b518ba0
Show file tree

Hide file tree

Showing 5 changed files with 55 additions and 30 deletions.
diff --git a/README.md b/README.md
@@ -46,13 +46,14 @@ Please see the [section below](#add-an-identity-provider) for important informat
 
 3. You can see the local running app at http://127.0.0.1:50505.
 
-#### Local Setup: Chat with your data (Preview)
+#### Local Setup: Chat with your data using Azure Cognitive Search
 [More information about Azure OpenAI on your data](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/use-your-data)
 
 1. Update the `AZURE_OPENAI_*` environment variables as described above. 
 2. To connect to your data, you need to specify an Azure Cognitive Search index to use. You can [create this index yourself](https://learn.microsoft.com/en-us/azure/search/search-get-started-portal) or use the [Azure AI Studio](https://oai.azure.com/portal/chat) to create the index for you.
 
     These variables are required when adding your data with Azure AI Search:
+    - `DATASOURCE_TYPE` (should be set to `AzureCognitiveSearch`)
     - `AZURE_SEARCH_SERVICE`
     - `AZURE_SEARCH_INDEX`
     - `AZURE_SEARCH_KEY`

diff --git a/backend/settings.py b/backend/settings.py
@@ -683,35 +683,39 @@ def set_chat_history_settings(self) -> Self:
 
     @model_validator(mode="after")
     def set_datasource_settings(self) -> Self:
-        if self.base_settings.datasource_type == "AzureCognitiveSearch":
-            self.datasource = _AzureSearchSettings(settings=self, _env_file=DOTENV_PATH)
-            logging.debug("Using Azure Cognitive Search")
-
-        elif self.base_settings.datasource_type == "AzureCosmosDB":
-            self.datasource = _AzureCosmosDbMongoVcoreSettings(settings=self, _env_file=DOTENV_PATH)
-            logging.debug("Using Azure CosmosDB Mongo vcore")
-
-        elif self.base_settings.datasource_type == "Elasticsearch":
-            self.datasource = _ElasticsearchSettings(settings=self, _env_file=DOTENV_PATH)
-            logging.debug("Using Elasticsearch")
-
-        elif self.base_settings.datasource_type == "Pinecone":
-            self.datasource = _PineconeSettings(settings=self, _env_file=DOTENV_PATH)
-            logging.debug("Using Pinecone")
-
-        elif self.base_settings.datasource_type == "AzureMLIndex":
-            self.datasource = _AzureMLIndexSettings(settings=self, _env_file=DOTENV_PATH)
-            logging.debug("Using Azure ML Index")
-
-        elif self.base_settings.datasource_type == "AzureSqlServer":
-            self.datasource = _AzureSqlServerSettings(settings=self, _env_file=DOTENV_PATH)
-            logging.debug("Using SQL Server")
+        try:
+            if self.base_settings.datasource_type == "AzureCognitiveSearch":
+                self.datasource = _AzureSearchSettings(settings=self, _env_file=DOTENV_PATH)
+                logging.debug("Using Azure Cognitive Search")
 
-        else:
-            self.datasource = None
-            logging.warning("No datasource configuration found in the environment -- calls will be made to Azure OpenAI without grounding data.")
+            elif self.base_settings.datasource_type == "AzureCosmosDB":
+                self.datasource = _AzureCosmosDbMongoVcoreSettings(settings=self, _env_file=DOTENV_PATH)
+                logging.debug("Using Azure CosmosDB Mongo vcore")
 
-        return self
+            elif self.base_settings.datasource_type == "Elasticsearch":
+                self.datasource = _ElasticsearchSettings(settings=self, _env_file=DOTENV_PATH)
+                logging.debug("Using Elasticsearch")
+
+            elif self.base_settings.datasource_type == "Pinecone":
+                self.datasource = _PineconeSettings(settings=self, _env_file=DOTENV_PATH)
+                logging.debug("Using Pinecone")
+
+            elif self.base_settings.datasource_type == "AzureMLIndex":
+                self.datasource = _AzureMLIndexSettings(settings=self, _env_file=DOTENV_PATH)
+                logging.debug("Using Azure ML Index")
+
+            elif self.base_settings.datasource_type == "AzureSqlServer":
+                self.datasource = _AzureSqlServerSettings(settings=self, _env_file=DOTENV_PATH)
+                logging.debug("Using SQL Server")
+
+            else:
+                self.datasource = None
+                logging.warning("No datasource configuration found in the environment -- calls will be made to Azure OpenAI without grounding data.")
+
+            return self
+
+        except ValidationError:
+            logging.warning("No datasource configuration found in the environment -- calls will be made to Azure OpenAI without grounding data.")
 
 
 app_settings = _AppSettings()
diff --git a/...it_tests/dotenv_data/dotenv_no_datasource → ..._tests/dotenv_data/dotenv_no_datasource_1 b/...it_tests/dotenv_data/dotenv_no_datasource → ..._tests/dotenv_data/dotenv_no_datasource_1
@@ -10,4 +10,4 @@ AZURE_OPENAI_STREAM=False
 AZURE_OPENAI_ENDPOINT=https://dummy.openai.azure.com/
 AZURE_OPENAI_EMBEDDING_NAME=
 AZURE_OPENAI_EMBEDDING_ENDPOINT=
-AZURE_OPENAI_EMBEDDING_KEY=
+AZURE_OPENAI_EMBEDDING_KEY=
diff --git a/tests/unit_tests/dotenv_data/dotenv_no_datasource_2 b/tests/unit_tests/dotenv_data/dotenv_no_datasource_2
@@ -0,0 +1,14 @@
+AZURE_OPENAI_MODEL=my_model
+AZURE_OPENAI_KEY=dummy
+AZURE_OPENAI_TEMPERATURE=0
+AZURE_OPENAI_TOP_P=1.0
+AZURE_OPENAI_MAX_TOKENS=1000
+AZURE_OPENAI_STOP_SEQUENCE=
+AZURE_OPENAI_SYSTEM_MESSAGE=You are an AI assistant that helps people find information.
+AZURE_OPENAI_PREVIEW_API_VERSION=2024-05-01-preview
+AZURE_OPENAI_STREAM=False
+AZURE_OPENAI_ENDPOINT=https://dummy.openai.azure.com/
+AZURE_OPENAI_EMBEDDING_NAME=
+AZURE_OPENAI_EMBEDDING_ENDPOINT=
+AZURE_OPENAI_EMBEDDING_KEY=
+DATASOURCE_TYPE=AzureCognitiveSearch
diff --git a/tests/unit_tests/test_settings.py b/tests/unit_tests/test_settings.py
@@ -23,11 +23,17 @@ def app_settings(dotenv_path):
     yield getattr(settings_module, "app_settings")
 
 
-def test_dotenv_no_datasource(app_settings):    
+def test_dotenv_no_datasource_1(app_settings):    
     # Validate model object
     assert app_settings.base_settings.datasource_type is None
     assert app_settings.datasource is None
     assert app_settings.azure_openai is not None
+
+
+def test_dotenv_no_datasource_2(app_settings):    
+    # Validate model object
+    assert app_settings.datasource is None
+    assert app_settings.azure_openai is not None
 
 
 def test_dotenv_with_azure_search_success(app_settings):