merge latest changes (#1)

* Merge pull request microsoft#429 from microsoft/geearl/6323-large-tables Geearl/6323 large tables * Resolve function debug issue and add logic for multiple table spans * Update deployment.md Updates on Setting the right tenant if you're part of multiple tenant. Otherwise deployment will fail. * Bump fastapi from 0.103.2 to 0.109.1 in /app/enrichment Bumps [fastapi](https://github.com/tiangolo/fastapi) from 0.103.2 to 0.109.1. - [Release notes](https://github.com/tiangolo/fastapi/releases) - [Commits](tiangolo/fastapi@0.103.2...0.109.1) --- updated-dependencies: - dependency-name: fastapi dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com> * gov changes * gov changes * gov changes * new app service app setting and readme update * url update * Pushing out temp fixes until python sdk is resolved. * Remove media_service and avam modules * script fix * updated link * Remove base_url breaking param * Resolve issue with new gov logic on aoai endpoint resolution * Merge pull request microsoft#523 and microsoft#530 from vNext-Dev for large table fixes * Update app.py added `.lower()` to ensure the str read is in correctly converted to a bool. --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dayland <dayland@microsoft.com> Co-authored-by: dayland <48474707+dayland@users.noreply.github.com> Co-authored-by: avidunixuser <avidunixuser@users.noreply.github.com> Co-authored-by: ryonsteele <ryonsteele@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Danimal <dbiscup@microsoft.com> Co-authored-by: Brandon Rohrer <brandon.rohrer@outlook.com> Co-authored-by: Nehemiah Kuhns <85817913+nhwkuhns@users.noreply.github.com>
lukasvalach · Apr 8, 2024 · a45eb51 · a45eb51
1 parent 9c80bd8
commit a45eb51
Show file tree

Hide file tree

Showing 12 changed files with 305 additions and 98 deletions.
diff --git a/app/backend/app.py b/app/backend/app.py
@@ -11,7 +11,7 @@
 import openai
 from approaches.chatreadretrieveread import ChatReadRetrieveReadApproach
 from azure.core.credentials import AzureKeyCredential
-from azure.identity import DefaultAzureCredential
+from azure.identity import DefaultAzureCredential, AzureAuthorityHosts
 from azure.mgmt.cognitiveservices import CognitiveServicesManagementClient
 from azure.search.documents import SearchClient
 from azure.storage.blob import (
@@ -49,6 +49,7 @@
 EMBEDDING_DEPLOYMENT_NAME = ( os.environ.get("EMBEDDING_DEPLOYMENT_NAME") or "")
 AZURE_OPENAI_EMBEDDINGS_MODEL_NAME = ( os.environ.get("AZURE_OPENAI_EMBEDDINGS_MODEL_NAME") or "")
 AZURE_OPENAI_EMBEDDINGS_VERSION = ( os.environ.get("AZURE_OPENAI_EMBEDDINGS_VERSION") or "")
+AZURE_MANAGEMENT_URL = ( os.environ.get("AZURE_MANAGEMENT_URL") or "")
 
 AZURE_OPENAI_SERVICE_KEY = os.environ.get("AZURE_OPENAI_SERVICE_KEY")
 AZURE_SUBSCRIPTION_ID = os.environ.get("AZURE_SUBSCRIPTION_ID")
@@ -76,18 +77,26 @@
 
 # embedding_service_suffix = "xyoek"
 
+# Used by the OpenAI SDK
+openai.api_type = "azure"
+
+authority = AzureAuthorityHosts.AZURE_PUBLIC_CLOUD
+
+if (IS_GOV_CLOUD_DEPLOYMENT):
+    authority = AzureAuthorityHosts.AZURE_GOVERNMENT
+    openai.api_base = f"https://{AZURE_OPENAI_SERVICE}.openai.azure.us"
+else:
+    openai.api_base = f"https://{AZURE_OPENAI_SERVICE}.openai.azure.com"
+
+openai.api_version = "2023-06-01-preview"
+
 # Use the current user identity to authenticate with Azure OpenAI, Cognitive Search and Blob Storage (no secrets needed,
 # just use 'az login' locally, and managed identity when deployed on Azure). If you need to use keys, use separate AzureKeyCredential instances with the
 # keys for each service
 # If you encounter a blocking error during a DefaultAzureCredntial resolution, you can exclude the problematic credential by using a parameter (ex. exclude_shared_token_cache_credential=True)
-azure_credential = DefaultAzureCredential()
+azure_credential = DefaultAzureCredential(authority=authority)
 azure_search_key_credential = AzureKeyCredential(AZURE_SEARCH_SERVICE_KEY)
 
-# Used by the OpenAI SDK
-openai.api_type = "azure"
-openai.api_base = f"https://{AZURE_OPENAI_SERVICE}.openai.azure.com"
-openai.api_version = "2023-06-01-preview"
-
 # Setup StatusLog to allow access to CosmosDB for logging
 statusLog = StatusLog(
     COSMOSDB_URL, COSMODB_KEY, COSMOSDB_LOG_DATABASE_NAME, COSMOSDB_LOG_CONTAINER_NAME
@@ -116,13 +125,15 @@
 model_name = ''
 model_version = ''
 
+# Python issue Logged > https://github.com/Azure/azure-sdk-for-python/issues/34337
+# Once fixed, this If statement can be removed. 
 if (IS_GOV_CLOUD_DEPLOYMENT):
     model_name = AZURE_OPENAI_CHATGPT_MODEL_NAME
     model_version = AZURE_OPENAI_CHATGPT_MODEL_VERSION
     embedding_model_name = AZURE_OPENAI_EMBEDDINGS_MODEL_NAME
     embedding_model_version = AZURE_OPENAI_EMBEDDINGS_VERSION
 else:
-    # Set up OpenAI management client
+    #Set up OpenAI management client
     openai_mgmt_client = CognitiveServicesManagementClient(
         credential=azure_credential,
         subscription_id=AZURE_SUBSCRIPTION_ID)

diff --git a/app/backend/approaches/chatreadretrieveread.py b/app/backend/approaches/chatreadretrieveread.py
@@ -130,8 +130,12 @@ def __init__(
             self.embedding_service_url = f'https://{ENRICHMENT_APPSERVICE_NAME}.azurewebsites.us'
         else:
             self.embedding_service_url = f'https://{ENRICHMENT_APPSERVICE_NAME}.azurewebsites.net'
-
-        openai.api_base = 'https://' + oai_service_name + '.openai.azure.com/'
+
+        if is_gov_cloud_deployment:
+            openai.api_base = 'https://' + oai_service_name + '.openai.azure.us/'
+        else:
+            openai.api_base = 'https://' + oai_service_name + '.openai.azure.com/'        
+
         openai.api_type = 'azure'
         openai.api_key = oai_service_key
 

diff --git a/app/enrichment/app.py b/app/enrichment/app.py
@@ -59,9 +59,12 @@
     "TARGET_EMBEDDINGS_MODEL": None,
     "EMBEDDING_VECTOR_SIZE": None,
     "AZURE_SEARCH_SERVICE_ENDPOINT": None,
-    "AZURE_BLOB_STORAGE_ENDPOINT": None
+    "AZURE_BLOB_STORAGE_ENDPOINT": None,
+    "IS_GOV_CLOUD_DEPLOYMENT": None
 }
 
+str_to_bool = {'true': True, 'false': False}
+
 for key, value in ENV.items():
     new_value = os.getenv(key)
     if new_value is not None:
@@ -70,8 +73,12 @@
         raise ValueError(f"Environment variable {key} not set")
 
 search_creds = AzureKeyCredential(ENV["AZURE_SEARCH_SERVICE_KEY"])
-
-openai.api_base = "https://" + ENV["AZURE_OPENAI_SERVICE"] + ".openai.azure.com/"
+
+if str_to_bool.get(ENV["IS_GOV_CLOUD_DEPLOYMENT"].lower()):
+    openai.api_base = "https://" + ENV["AZURE_OPENAI_SERVICE"] + ".openai.azure.us/"
+else:
+    openai.api_base = "https://" + ENV["AZURE_OPENAI_SERVICE"] + ".openai.azure.com/"
+
 openai.api_type = "azure"
 openai.api_key = ENV["AZURE_OPENAI_SERVICE_KEY"]
 openai.api_version = "2023-06-01-preview"

diff --git a/app/enrichment/requirements.txt b/app/enrichment/requirements.txt
@@ -1,7 +1,7 @@
 #### Any version change made here should also be made and tested for the webapp backend and function apps in /functions and /app/backend
 
 sentence-transformers == 2.2.2
-fastapi == 0.103.2
+fastapi == 0.109.1
 fastapi-utils == 0.2.1
 uvicorn == 0.23.2
 azure-storage-queue == 12.6.0

diff --git a/docs/deployment/deployment.md b/docs/deployment/deployment.md
@@ -95,6 +95,12 @@ The output here should show that you're logged into the intended Azure subscript
     az account list
 ```
 
+If you're a part of multiple tenants, ensure you're in the right tenant by setting the tenantID
+
+``` bash
+    az login --tenant tenantID
+```
+
 From this output, grab the Subscription ID of the subscription you intend to deploy to and run:
 
 ``` bash

diff --git a/docs/deployment/enable_sovereign_deployment.md b/docs/deployment/enable_sovereign_deployment.md
@@ -1,8 +1,8 @@
 # Enable Sovereign Region Deployment
 
-Follow these steps to enable a split deployment.  All resources outside of AOAI will be deployed in an Sovereign region.
+Follow these steps to enable a Sovereign region deployment.  If you need access to AOAI in a UsGov region please fill out this form https://aka.ms/AOAIgovaccess.
 
-Only Sovereign regions supported today are **US Gov**.
+Only Sovereign regions / models supported are listed here: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#azure-government-regions
 
 ## Setup the environment
 
@@ -14,12 +14,18 @@ To enable a Sovereign region deployment, you need to update the local.env file w
    export LOCATION="usgovvirginia"
    ```
 
+   or
+
+   ```bash
+   export LOCATION="usgovvarizona"
+   ```
+
 2. Set **IS_USGOV_DEPLOYMENT** parameter to `true` 
 
-3. Set **USE_EXISTING_AOAI** parameter to `true` 
+3. Set **USE_EXISTING_AOAI** parameter to `true` if you have a existing AOAI instance deployed.  If you want to create Azure Open AI resource during deployment then set this parameter to `false`
 
-4. Set the following parameters based on your AOAI deployment:
-   *You can find these values from https://oai.azure.com/portal via the Deployments URL.*
+4. If **USE_EXISTING_AOAI** is set to `true` then set the following parameters based on your AOAI deployment:
+   *You can find these values from https://aoai.azure.us/portal via the Deployments URL.*
 
    ```bash
    export AZURE_OPENAI_CHATGPT_MODEL_NAME="gpt-35-turbo-16k"

diff --git a/functions/requirements.txt b/functions/requirements.txt
@@ -15,7 +15,7 @@ azure-storage-queue == 12.6.0
 nltk == 3.8.1
 tenacity == 8.2.3
 azure-ai-vision == 0.15.1b1
-unstructured[csv,doc,docx,email,html,md,msg,ppt,pptx,text,xlsx,xml] == 0.10.27
+unstructured[csv,doc,docx,email,html,md,msg,ppt,pptx,text,xlsx,xml] == 0.12.5
 pyoo == 1.4
 azure-search-documents == 11.4.0b11
-
+beautifulsoup4 == 4.12.2