build: Merge Dependabot Changes into Dev Branch

.env.sample

@@ -22,8 +22,8 @@ AZURE_SEARCH_DATASOURCE_NAME=
 # Azure OpenAI for generating the answer and computing the embedding of the documents
 AZURE_OPENAI_RESOURCE=
 AZURE_OPENAI_API_KEY=
-AZURE_OPENAI_MODEL=gpt-35-turbo
-AZURE_OPENAI_MODEL_NAME=gpt-35-turbo
+AZURE_OPENAI_MODEL=gpt-4o
+AZURE_OPENAI_MODEL_NAME=gpt-4o
 AZURE_OPENAI_EMBEDDING_MODEL=text-embedding-ada-002
 AZURE_OPENAI_TEMPERATURE=0
 AZURE_OPENAI_TOP_P=1.0

.github/workflows/build-docker-images.yml

@@ -1,4 +1,4 @@
-name: Build Docker Images
+name: Build Docker and Optional Push
 
 on:
   push:
@@ -12,11 +12,12 @@ on:
       - dev
       - demo
     types:
-    - opened
-    - ready_for_review
-    - reopened
-    - synchronize
+      - opened
+      - ready_for_review
+      - reopened
+      - synchronize
   merge_group:
+  workflow_dispatch:
 
 jobs:
   docker-build:
@@ -31,9 +32,11 @@ jobs:
             dockerfile: docker/Frontend.Dockerfile
     uses: ./.github/workflows/build-docker.yml
     with:
-      registry: ${{ github.ref_name == 'main' && 'fruoccopublic.azurecr.io' || 'cwydcontainerreg.azurecr.io'}}
-      username: ${{ github.ref_name == 'main' && 'fruoccopublic' || 'cwydcontainerreg'}}
+      old_registry: ${{ github.ref_name == 'main' && 'fruoccopublic.azurecr.io' }}
+      new_registry: 'cwydcontainerreg.azurecr.io'
+      old_username: ${{ github.ref_name == 'main' && 'fruoccopublic' }}
+      new_username: 'cwydcontainerreg'
       app_name: ${{ matrix.app_name }}
       dockerfile: ${{ matrix.dockerfile }}
-      push: ${{ github.ref_name == 'main' || github.ref_name == 'dev' || github.ref_name == 'demo' }}
+      push: ${{ github.ref_name == 'main' || github.ref_name == 'dev' || github.ref_name == 'demo'|| github.ref_name == 'dependabotchanges' }}
     secrets: inherit

.github/workflows/build-docker.yml

@@ -3,10 +3,16 @@ name: Reusable Docker build and push workflow
 on:
   workflow_call:
     inputs:
-      registry:
+      old_registry:
         required: true
         type: string
-      username:
+      old_username:
+        required: true
+        type: string
+      new_registry:
+        required: true
+        type: string
+      new_username:
         required: true
         type: string
       app_name:
@@ -31,20 +37,30 @@ jobs:
     - name: Checkout
       uses: actions/checkout@v4
 
-    - name: Docker Login
+    # Login for 'main' branch to both registries
+    - name: Docker Login to fruoccopublic (Main)
       if: ${{ inputs.push == true && github.ref_name == 'main' }}
       uses: docker/login-action@v3
       with:
-        registry: ${{ inputs.registry }}
-        username: ${{ inputs.username }}
+        registry: ${{ inputs.old_registry }}
+        username: ${{ inputs.old_username }}
         password: ${{ secrets.DOCKER_PASSWORD }}
 
-    - name: Dev Docker Login
-      if: ${{ inputs.push == true && (github.ref_name == 'dev' || github.ref_name == 'demo') }}
+    - name: Docker Login to cwydcontainerreg (Main)
+      if: ${{ inputs.push == true && github.ref_name == 'main' }}
       uses: docker/login-action@v3
       with:
-        registry: ${{ inputs.registry }}
-        username: ${{ inputs.username }}
+        registry: ${{ inputs.new_registry }}
+        username: ${{ inputs.new_username }}
+        password: ${{ secrets.DEV_DOCKER_PASSWORD }}
+
+    # Login for 'dev' and 'demo' branches to cwydcontainerreg only
+    - name: Docker Login to cwydcontainerreg (Dev/Demo)
+      if: ${{ inputs.push == true && (github.ref_name == 'dev' || github.ref_name == 'demo'|| github.ref_name == 'dependabotchanges') }}
+      uses: docker/login-action@v3
+      with:
+        registry: ${{ inputs.new_registry }}
+        username: ${{ inputs.new_username }}
         password: ${{ secrets.DEV_DOCKER_PASSWORD }}
 
     - name: Set up Docker Buildx
@@ -54,17 +70,26 @@ jobs:
       id: date
       run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
 
-    - name: Determine Tag Name Based on Branch
-      id: determine_tag
-      run: echo "tagname=${{ github.ref_name == 'main' && 'latest' || github.ref_name == 'dev' && 'dev' || github.ref_name == 'demo' && 'demo' || github.head_ref || 'default' }}" >> $GITHUB_OUTPUT
+    - name: Build Docker Image and optionally push (Old Registry)
+      if: ${{ github.ref_name == 'main' }}
+      uses: docker/build-push-action@v6
+      with:
+        context: .
+        file: ${{ inputs.dockerfile }}
+        push: ${{ inputs.push }}
+        cache-from: type=registry,ref=${{ inputs.old_registry }}/${{ inputs.app_name }}:${{ github.ref_name == 'main' && 'latest' || github.head_ref || github.ref_name }}
+        tags: |
+          ${{ inputs.old_registry }}/${{ inputs.app_name }}:${{ github.ref_name == 'main' && 'latest' || github.head_ref || 'default' }}
+          ${{ inputs.old_registry }}/${{ inputs.app_name }}:${{ steps.date.outputs.date }}_${{ github.run_number }}
 
-    - name: Build Docker Image and optionally push
+    - name: Build Docker Image and optionally push (New Registry)
+      if: ${{ github.ref_name == 'main' || github.ref_name == 'dev' || github.ref_name == 'demo'|| github.ref_name == 'dependabotchanges' }}
       uses: docker/build-push-action@v6
       with:
         context: .
         file: ${{ inputs.dockerfile }}
         push: ${{ inputs.push }}
-        cache-from: type=registry,ref=${{ inputs.registry }}/${{ inputs.app_name}}:${{ github.ref_name == 'main' && 'latest' || github.ref_name == 'dev' && 'dev' || github.ref_name == 'demo' && 'demo' || github.head_ref || github.ref_name }}
+        cache-from: type=registry,ref=${{ inputs.new_registry }}/${{ inputs.app_name }}:${{ github.ref_name == 'main' && 'latest' || github.ref_name == 'dev' && 'dev' || github.ref_name == 'demo' && 'demo'|| github.ref_name == 'dependabotchanges' && 'dependabotchanges' || github.head_ref || github.ref_name }}
         tags: |
-          ${{ inputs.registry }}/${{ inputs.app_name}}:${{ steps.determine_tag.outputs.tagname }}
-          ${{ inputs.registry }}/${{ inputs.app_name}}:${{ steps.determine_tag.outputs.tagname }}_${{ steps.date.outputs.date }}_${{ github.run_number }}
+          ${{ inputs.new_registry }}/${{ inputs.app_name }}:${{ github.ref_name == 'main' && 'latest' || github.ref_name == 'dev' && 'dev' || github.ref_name == 'demo' && 'demo'|| github.ref_name == 'dependabotchanges' && 'dependabotchanges' || github.head_ref || 'default' }}
+          ${{ inputs.new_registry }}/${{ inputs.app_name }}:${{ steps.date.outputs.date }}_${{ github.run_number }}

.github/workflows/ci.yml

@@ -1,4 +1,4 @@
-name: CI
+name: Validate Deployment
 
 on:
   push:
@@ -7,7 +7,7 @@ on:
       - dev
       - demo
   schedule:
-    - cron: '0 6,18 * * *'  # Runs at 6:00 AM and 6:00 PM GMT
+    - cron: '0 8,20 * * *'  # Runs at 8:00 AM and 8:00 PM GMT
 
 permissions:
   contents: read
@@ -83,7 +83,7 @@ jobs:
             AZURE_SUBSCRIPTION_ID
             AZURE_ENV_NAME
             AZURE_LOCATION
-            
+
       - name: Send Notification on Failure
         if: failure()
         run: |

.github/workflows/create-release.yml

@@ -8,7 +8,7 @@ permissions:
   contents: write
   pull-requests: write
 
-name: create-release
+name: Create-Release
 
 jobs:
   create-release:

.github/workflows/pr-title-checker.yml

@@ -1,4 +1,4 @@
-name: "pr-title-checker"
+name: "PR Title Checker"
 
 on:
   pull_request_target:

.github/workflows/stale-bot.yml

@@ -1,4 +1,4 @@
-name: 'Close stale issues and PRs'
+name: 'Stale Bot'
 on:
   schedule:
     - cron: '30 1 * * *'

.github/workflows/tests.yml

@@ -1,4 +1,4 @@
-name: Tests
+name: Test Workflow with Coverage
 
 on:
   push:

README.md

@@ -81,7 +81,7 @@ Here is a comparison table with a few features offered by Azure, an available Gi
 | Name	| Feature or Sample? |	What is it? | When to use? |
 | ---------|---------|---------|---------|
 |["Chat with your data" Solution Accelerator](https://aka.ms/ChatWithYourDataSolutionAccelerator) - (This repo)	| Azure sample | End-to-end baseline RAG pattern sample that uses Azure AI Search as a retriever.	| This sample should be used by Developers when the  RAG pattern implementations provided by Azure are not able to satisfy business requirements. This sample provides a means to customize the solution. Developers must add their own code to meet requirements, and adapt with best practices according to individual company policies. |
-|[Azure OpenAI on your data](https://learn.microsoft.com/azure/ai-services/openai/concepts/use-your-data) | Azure feature | Azure OpenAI Service offers out-of-the-box, end-to-end RAG implementation that uses a REST API or the web-based interface in the Azure AI Studio to create a solution that connects to your data to enable an enhanced chat experience with Azure OpenAI ChatGPT models and Azure AI Search. | This should be the first option considered for developers that need an end-to-end solution for Azure OpenAI Service with an Azure AI Search retriever. Simply select supported data sources, that ChatGPT model in Azure OpenAI Service , and any other Azure resources needed to configure your enterprise application needs. |
+|[Azure OpenAI on your data](https://learn.microsoft.com/azure/ai-services/openai/concepts/use-your-data) | Azure feature | Azure OpenAI Service offers out-of-the-box, end-to-end RAG implementation that uses a REST API or the web-based interface in the Azure AI Foundry to create a solution that connects to your data to enable an enhanced chat experience with Azure OpenAI ChatGPT models and Azure AI Search. | This should be the first option considered for developers that need an end-to-end solution for Azure OpenAI Service with an Azure AI Search retriever. Simply select supported data sources, that ChatGPT model in Azure OpenAI Service , and any other Azure resources needed to configure your enterprise application needs. |
 |[Azure Machine Learning prompt flow](https://learn.microsoft.com/azure/machine-learning/concept-retrieval-augmented-generation)	| Azure feature | RAG in Azure Machine Learning is enabled by integration with Azure OpenAI Service for large language models and vectorization. It includes support for Faiss and Azure AI Search as vector stores, as well as support for open-source offerings, tools, and frameworks such as LangChain for data chunking. Azure Machine Learning prompt flow offers the ability to test data generation, automate prompt creation, visualize prompt evaluation metrics, and integrate RAG workflows into MLOps using pipelines.  | When Developers need more control over processes involved in the development cycle of LLM-based AI applications, they should use Azure Machine Learning prompt flow to create executable flows and evaluate performance through large-scale testing. |
 |[ChatGPT + Enterprise data with Azure OpenAI and AI Search demo](https://github.com/Azure-Samples/azure-search-openai-demo) | Azure sample | RAG pattern demo that uses Azure AI Search as a retriever. | Developers who would like to use or present an end-to-end demonstration of the RAG pattern should use this sample. This includes the ability to deploy and test different retrieval modes, and prompts to support business use cases. |
 |[RAG Experiment Accelerator](https://github.com/microsoft/rag-experiment-accelerator) | Tool |The RAG Experiment Accelerator is a versatile tool that helps you conduct experiments and evaluations using Azure AI Search and RAG pattern. | RAG Experiment Accelerator is to make it easier and faster to run experiments and evaluations of search queries and quality of response from OpenAI. This tool is useful for researchers, data scientists, and developers who want to, Test the performance of different Search and OpenAI related hyperparameters. |
@@ -194,10 +194,10 @@ Select either "PostgreSQL" or "Cosmos DB":
 
 When Deployment is complete, follow steps in [Set Up Authentication in Azure App Service](./docs/azure_app_service_auth_setup.md) to add app authentication to your web app running on Azure App Service
 
-**Note**: The default configuration deploys an OpenAI Model "gpt-35-turbo" with version 0613. However, not all
-locations support this version. If you're deploying to a location that doesn't support version 0613, you'll need to
+**Note**: The default configuration deploys an OpenAI Model "gpt-4o" with version 2024-05-13. However, not all
+locations support this version. If you're deploying to a location that doesn't support version 2024-05-13, you'll need to
 switch to a lower version. To find out which versions are supported in different regions, visit the
-[GPT-35 Turbo Model Availability](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-35-turbo-model-availability) page.
+[GPT-4o Model Availability](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#global-standard-model-availability) page.
 
 ### Testing the deployment
 1. Navigate to the admin site, where you can upload documents. It will be located at:

code/backend/batch/utilities/helpers/env_helper.py

@@ -174,10 +174,10 @@ def __load_config(self, **kwargs) -> None:
         else:
             # Otherwise, fallback to individual environment variables
             self.AZURE_OPENAI_MODEL = os.getenv(
-                "AZURE_OPENAI_MODEL", "gpt-35-turbo-16k"
+                "AZURE_OPENAI_MODEL", "gpt-4o"
             )
             self.AZURE_OPENAI_MODEL_NAME = os.getenv(
-                "AZURE_OPENAI_MODEL_NAME", "gpt-35-turbo-16k"
+                "AZURE_OPENAI_MODEL_NAME", "gpt-4o"
             )
 
         self.AZURE_OPENAI_VISION_MODEL = os.getenv("AZURE_OPENAI_VISION_MODEL", "gpt-4")

code/backend/pages/04_Configuration.py

@@ -410,17 +410,21 @@ def validate_documents():
 
         if st.form_submit_button("Save configuration"):
             document_processors = []
+            should_save = True
             if env_helper.AZURE_SEARCH_USE_INTEGRATED_VECTORIZATION is False:
                 valid = all(
                     row["document_type"]
                     and row["chunking_strategy"]
+                    and row["chunking_size"]
+                    and row["chunking_overlap"]
                     and row["loading_strategy"]
                     for row in edited_document_processors
                 )
                 if not valid:
                     st.error(
                         "Please ensure all fields are selected and not left blank in Document processing configuration."
                     )
+                    should_save = False
                 document_processors = list(
                     map(
                         lambda x: {
@@ -440,51 +444,52 @@ def validate_documents():
                         edited_document_processors,
                     )
                 )
-            current_config = {
-                "prompts": {
-                    "condense_question_prompt": "",  # st.session_state['condense_question_prompt'],
-                    "answering_system_prompt": st.session_state[
-                        "answering_system_prompt"
-                    ],
-                    "answering_user_prompt": st.session_state["answering_user_prompt"],
-                    "use_on_your_data_format": st.session_state[
-                        "use_on_your_data_format"
-                    ],
-                    "post_answering_prompt": st.session_state["post_answering_prompt"],
-                    "enable_post_answering_prompt": st.session_state[
-                        "enable_post_answering_prompt"
-                    ],
-                    "enable_content_safety": st.session_state["enable_content_safety"],
-                    "ai_assistant_type": st.session_state["ai_assistant_type"],
-                    "conversational_flow": st.session_state["conversational_flow"],
-                },
-                "messages": {
-                    "post_answering_filter": st.session_state[
-                        "post_answering_filter_message"
-                    ]
-                },
-                "example": {
-                    "documents": st.session_state["example_documents"],
-                    "user_question": st.session_state["example_user_question"],
-                    "answer": st.session_state["example_answer"],
-                },
-                "document_processors": document_processors,
-                "logging": {
-                    "log_user_interactions": st.session_state["log_user_interactions"],
-                    "log_tokens": st.session_state["log_tokens"],
-                },
-                "orchestrator": {"strategy": st.session_state["orchestrator_strategy"]},
-                "integrated_vectorization_config": (
-                    integrated_vectorization_config
-                    if env_helper.AZURE_SEARCH_USE_INTEGRATED_VECTORIZATION
-                    else None
-                ),
-                "enable_chat_history": st.session_state["enable_chat_history"],
-            }
-            ConfigHelper.save_config_as_active(current_config)
-            st.success(
-                "Configuration saved successfully! Please restart the chat service for these changes to take effect."
-            )
+            if should_save:
+                current_config = {
+                    "prompts": {
+                        "condense_question_prompt": "",  # st.session_state['condense_question_prompt'],
+                        "answering_system_prompt": st.session_state[
+                            "answering_system_prompt"
+                        ],
+                        "answering_user_prompt": st.session_state["answering_user_prompt"],
+                        "use_on_your_data_format": st.session_state[
+                            "use_on_your_data_format"
+                        ],
+                        "post_answering_prompt": st.session_state["post_answering_prompt"],
+                        "enable_post_answering_prompt": st.session_state[
+                            "enable_post_answering_prompt"
+                        ],
+                        "enable_content_safety": st.session_state["enable_content_safety"],
+                        "ai_assistant_type": st.session_state["ai_assistant_type"],
+                        "conversational_flow": st.session_state["conversational_flow"],
+                    },
+                    "messages": {
+                        "post_answering_filter": st.session_state[
+                            "post_answering_filter_message"
+                        ]
+                    },
+                    "example": {
+                        "documents": st.session_state["example_documents"],
+                        "user_question": st.session_state["example_user_question"],
+                        "answer": st.session_state["example_answer"],
+                    },
+                    "document_processors": document_processors,
+                    "logging": {
+                        "log_user_interactions": st.session_state["log_user_interactions"],
+                        "log_tokens": st.session_state["log_tokens"],
+                    },
+                    "orchestrator": {"strategy": st.session_state["orchestrator_strategy"]},
+                    "integrated_vectorization_config": (
+                        integrated_vectorization_config
+                        if env_helper.AZURE_SEARCH_USE_INTEGRATED_VECTORIZATION
+                        else None
+                    ),
+                    "enable_chat_history": st.session_state["enable_chat_history"],
+                }
+                ConfigHelper.save_config_as_active(current_config)
+                st.success(
+                    "Configuration saved successfully! Please restart the chat service for these changes to take effect."
+                )
 
     with st.popover(":red[Reset configuration to defaults]"):