Merge branch 'main' into refactor/shared-settings-component

Author: pamelafox

.azdo/pipelines/azure-dev.yml

@@ -101,6 +101,7 @@ steps:
       AZURE_SPEECH_SERVICE_RESOURCE_GROUP: $(AZURE_SPEECH_SERVICE_RESOURCE_GROUP)
       AZURE_SPEECH_SERVICE_LOCATION: $(AZURE_SPEECH_SERVICE_LOCATION)
       AZURE_SPEECH_SERVICE_SKU: $(AZURE_SPEECH_SERVICE_SKU)
+      AZURE_SPEECH_SERVICE_VOICE: $(AZURE_SPEECH_SERVICE_VOICE)
       AZURE_KEY_VAULT_NAME: $(AZURE_KEY_VAULT_NAME)
       AZURE_USE_AUTHENTICATION: $(AZURE_USE_AUTHENTICATION)
       AZURE_ENFORCE_ACCESS_CONTROL: $(AZURE_ENFORCE_ACCESS_CONTROL)

.github/workflows/azure-dev.yml

@@ -87,6 +87,7 @@ jobs:
       AZURE_SPEECH_SERVICE_RESOURCE_GROUP: ${{ vars.AZURE_SPEECH_RESOURCE_GROUP }}
       AZURE_SPEECH_SERVICE_LOCATION: ${{ vars.AZURE_SPEECH_SERVICE_LOCATION }}
       AZURE_SPEECH_SERVICE_SKU: ${{ vars.AZURE_SPEECH_SERVICE_SKU }}
+      AZURE_SPEECH_SERVICE_VOICE: ${{ vars.AZURE_SPEECH_SERVICE_VOICE }}
       AZURE_KEY_VAULT_NAME: ${{ vars.AZURE_KEY_VAULT_NAME }}
       AZURE_USE_AUTHENTICATION: ${{ vars.AZURE_USE_AUTHENTICATION }}
       AZURE_ENFORCE_ACCESS_CONTROL: ${{ vars.AZURE_ENFORCE_ACCESS_CONTROL }}

.vscode/launch.json

@@ -5,7 +5,7 @@
     "version": "0.2.0",
     "configurations": [
         {
-            "name": "Python: Quart",
+            "name": "Backend (Python)",
             "type": "debugpy",
             "request": "launch",
             "module": "quart",
@@ -22,18 +22,17 @@
                 "-p 50505"
             ],
             "console": "integratedTerminal",
-            "justMyCode": false,
-            "envFile": "${input:dotEnvFilePath}",
+            "justMyCode": false
         },
         {
-            "name": "Frontend: watch",
+            "name": "Frontend",
             "type": "node-terminal",
             "request": "launch",
             "command": "npm run dev",
             "cwd": "${workspaceFolder}/app/frontend",
         },
         {
-            "name": "Python: Debug Tests",
+            "name": "Tests (Python)",
             "type": "debugpy",
             "request": "launch",
             "program": "${file}",
@@ -42,11 +41,11 @@
             "justMyCode": false
           }
     ],
-    "inputs": [
+    "compounds": [
         {
-            "id": "dotEnvFilePath",
-            "type": "command",
-            "command": "azure-dev.commands.getDotEnvFilePath"
+          "name": "Frontend & Backend",
+          "configurations": ["Backend (Python)", "Frontend"],
+          "stopAll": true
         }
     ]
 }

README.md

@@ -1,4 +1,25 @@
-# ChatGPT-like app with your data using Azure OpenAI and Azure AI Search (Python)
+<!--
+---
+name: RAG chat app with your data (Python)
+description: Chat with your domain data using Azure OpenAI and Azure AI Search.
+languages:
+- python
+- typescript
+- bicep
+- azdeveloper
+products:
+- azure-openai
+- azure-cognitive-search
+- azure-app-service
+- azure
+page_type: sample
+urlFragment: azure-search-openai-demo
+---
+-->
+
+# RAG chat app with Azure OpenAI and Azure AI Search (Python)
+
+This solution creates a ChatGPT-like frontend experience over your own documents using RAG (Retrieval Augmented Generation). It uses Azure OpenAI Service to access GPT models, and Azure AI Search for data indexing and retrieval.
 
 This solution's backend is written in Python. There are also [**JavaScript**](https://aka.ms/azai/js/code), [**.NET**](https://aka.ms/azai/net/code), and [**Java**](https://aka.ms/azai/java/code) samples based on this one. Learn more about [developing AI apps using Azure AI Services](https://aka.ms/azai).
 

app/backend/app.py

@@ -420,6 +420,8 @@ async def setup_clients():
     )
     AZURE_OPENAI_EMB_DEPLOYMENT = os.getenv("AZURE_OPENAI_EMB_DEPLOYMENT") if OPENAI_HOST.startswith("azure") else None
     AZURE_OPENAI_CUSTOM_URL = os.getenv("AZURE_OPENAI_CUSTOM_URL")
+    # https://learn.microsoft.com/azure/ai-services/openai/api-version-deprecation#latest-ga-api-release
+    AZURE_OPENAI_API_VERSION = os.getenv("AZURE_OPENAI_API_VERSION") or "2024-06-01"
     AZURE_VISION_ENDPOINT = os.getenv("AZURE_VISION_ENDPOINT", "")
     # Used only with non-Azure OpenAI deployments
     OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
@@ -444,7 +446,7 @@ async def setup_clients():
 
     AZURE_SPEECH_SERVICE_ID = os.getenv("AZURE_SPEECH_SERVICE_ID")
     AZURE_SPEECH_SERVICE_LOCATION = os.getenv("AZURE_SPEECH_SERVICE_LOCATION")
-    AZURE_SPEECH_VOICE = os.getenv("AZURE_SPEECH_VOICE", "en-US-AndrewMultilingualNeural")
+    AZURE_SPEECH_SERVICE_VOICE = os.getenv("AZURE_SPEECH_SERVICE_VOICE") or "en-US-AndrewMultilingualNeural"
 
     USE_GPT4V = os.getenv("USE_GPT4V", "").lower() == "true"
     USE_USER_UPLOAD = os.getenv("USE_USER_UPLOAD", "").lower() == "true"
@@ -547,6 +549,7 @@ async def setup_clients():
             openai_custom_url=AZURE_OPENAI_CUSTOM_URL,
             openai_deployment=AZURE_OPENAI_EMB_DEPLOYMENT,
             openai_dimensions=OPENAI_EMB_DIMENSIONS,
+            openai_api_version=AZURE_OPENAI_API_VERSION,
             openai_key=clean_key_if_exists(OPENAI_API_KEY),
             openai_org=OPENAI_ORGANIZATION,
             disable_vectors=os.getenv("USE_VECTORS", "").lower() == "false",
@@ -567,13 +570,12 @@ async def setup_clients():
             raise ValueError("Azure speech resource not configured correctly, missing AZURE_SPEECH_SERVICE_LOCATION")
         current_app.config[CONFIG_SPEECH_SERVICE_ID] = AZURE_SPEECH_SERVICE_ID
         current_app.config[CONFIG_SPEECH_SERVICE_LOCATION] = AZURE_SPEECH_SERVICE_LOCATION
-        current_app.config[CONFIG_SPEECH_SERVICE_VOICE] = AZURE_SPEECH_VOICE
+        current_app.config[CONFIG_SPEECH_SERVICE_VOICE] = AZURE_SPEECH_SERVICE_VOICE
         # Wait until token is needed to fetch for the first time
         current_app.config[CONFIG_SPEECH_SERVICE_TOKEN] = None
         current_app.config[CONFIG_CREDENTIAL] = azure_credential
 
     if OPENAI_HOST.startswith("azure"):
-        api_version = os.getenv("AZURE_OPENAI_API_VERSION") or "2024-03-01-preview"
         if OPENAI_HOST == "azure_custom":
             current_app.logger.info("OPENAI_HOST is azure_custom, setting up Azure OpenAI custom client")
             if not AZURE_OPENAI_CUSTOM_URL:
@@ -586,12 +588,14 @@ async def setup_clients():
             endpoint = f"https://{AZURE_OPENAI_SERVICE}.openai.azure.com"
         if api_key := os.getenv("AZURE_OPENAI_API_KEY_OVERRIDE"):
             current_app.logger.info("AZURE_OPENAI_API_KEY_OVERRIDE found, using as api_key for Azure OpenAI client")
-            openai_client = AsyncAzureOpenAI(api_version=api_version, azure_endpoint=endpoint, api_key=api_key)
+            openai_client = AsyncAzureOpenAI(
+                api_version=AZURE_OPENAI_API_VERSION, azure_endpoint=endpoint, api_key=api_key
+            )
         else:
             current_app.logger.info("Using Azure credential (passwordless authentication) for Azure OpenAI client")
             token_provider = get_bearer_token_provider(azure_credential, "https://cognitiveservices.azure.com/.default")
             openai_client = AsyncAzureOpenAI(
-                api_version=api_version,
+                api_version=AZURE_OPENAI_API_VERSION,
                 azure_endpoint=endpoint,
                 azure_ad_token_provider=token_provider,
             )

app/backend/prepdocs.py

@@ -115,6 +115,7 @@ def setup_embeddings_service(
     openai_custom_url: Union[str, None],
     openai_deployment: Union[str, None],
     openai_dimensions: int,
+    openai_api_version: str,
     openai_key: Union[str, None],
     openai_org: Union[str, None],
     disable_vectors: bool = False,
@@ -134,6 +135,7 @@ def setup_embeddings_service(
             open_ai_deployment=openai_deployment,
             open_ai_model_name=openai_model_name,
             open_ai_dimensions=openai_dimensions,
+            open_ai_api_version=openai_api_version,
             credential=azure_open_ai_credential,
             disable_batch=disable_batch_vectors,
         )
@@ -366,6 +368,8 @@ async def main(strategy: Strategy, setup_index: bool = True):
         openai_service=os.getenv("AZURE_OPENAI_SERVICE"),
         openai_custom_url=os.getenv("AZURE_OPENAI_CUSTOM_URL"),
         openai_deployment=os.getenv("AZURE_OPENAI_EMB_DEPLOYMENT"),
+        # https://learn.microsoft.com/azure/ai-services/openai/api-version-deprecation#latest-ga-api-release
+        openai_api_version=os.getenv("AZURE_OPENAI_API_VERSION") or "2024-06-01",
         openai_dimensions=openai_dimensions,
         openai_key=clean_key_if_exists(openai_key),
         openai_org=os.getenv("OPENAI_ORGANIZATION"),

app/backend/prepdocslib/embeddings.py

@@ -163,6 +163,7 @@ def __init__(
         open_ai_deployment: Union[str, None],
         open_ai_model_name: str,
         open_ai_dimensions: int,
+        open_ai_api_version: str,
         credential: Union[AsyncTokenCredential, AzureKeyCredential],
         open_ai_custom_url: Union[str, None] = None,
         disable_batch: bool = False,
@@ -176,6 +177,7 @@ def __init__(
         else:
             raise ValueError("Either open_ai_service or open_ai_custom_url must be provided")
         self.open_ai_deployment = open_ai_deployment
+        self.open_ai_api_version = open_ai_api_version
         self.credential = credential
 
     async def create_client(self) -> AsyncOpenAI:
@@ -196,7 +198,7 @@ class AuthArgs(TypedDict, total=False):
         return AsyncAzureOpenAI(
             azure_endpoint=self.open_ai_endpoint,
             azure_deployment=self.open_ai_deployment,
-            api_version="2023-05-15",
+            api_version=self.open_ai_api_version,
             **auth_args,
         )
 

app/backend/requirements.txt

@@ -350,7 +350,7 @@ python-dateutil==2.9.0.post0
     #   time-machine
 python-dotenv==1.0.1
     # via -r requirements.in
-quart==0.19.6
+quart==0.19.7
     # via
     #   -r requirements.in
     #   quart-cors
@@ -403,6 +403,7 @@ typing-extensions==4.12.2
     #   azure-ai-documentintelligence
     #   azure-core
     #   azure-identity
+    #   azure-search-documents
     #   azure-storage-blob
     #   azure-storage-file-datalake
     #   openai
@@ -415,7 +416,7 @@ urllib3==2.2.2
     # via requests
 uvicorn==0.30.6
     # via -r requirements.in
-werkzeug==3.0.4
+werkzeug==3.0.6
     # via
     #   flask
     #   quart