Front correction

README.md

@@ -2,6 +2,83 @@
 
 "The Tutor" is an intelligent tutoring platform designed to provide students with personalized educational support through interactive AI-driven experiences. The platform leverages both text-based and avatar-based interactions to engage students, offering a wide variety of learning aids such as real-time question answering, essay evaluation, and interactive conversation. By integrating advanced large, visual and multimodal language models, "The Tutor" helps students improve their learning outcomes while providing teachers with insightful evaluation tools.
 
+---
+
+## Getting Started
+
+### Prerequisites
+
+- **OS:** Windows, Linux, or macOS
+- **Python:** 3.10+
+- **Node.js:** 18+
+- **Docker:** (for building backend containers)
+- **Azure CLI:** (for cloud deployment)
+- **Git**
+
+### Installation
+
+1. **Clone the repository:**
+
+   ```pwsh
+   git clone <repository-url>
+   cd tutor
+   ```
+
+2. **Install Python dependencies:**
+
+   ```pwsh
+   pip install poetry
+   poetry install
+   ```
+
+3. **Install frontend dependencies:**
+
+   ```pwsh
+   cd src/frontend
+   npm install
+   ```
+
+### Quickstart (Local)
+
+1. **Run backend services:**
+
+   For each backend app (avatar, essays, questions, configuration):
+
+   ```pwsh
+   cd src/<app>/app
+   poetry run uvicorn main:app --reload
+   ```
+
+   See each app's [README](src/avatar/README.md), [README](src/essays/README.md), [README](src/questions/README.md), [README](src/configuration/README.md) for details.
+
+2. **Run the frontend:**
+
+   ```pwsh
+   cd src/frontend
+   npm run dev
+   ```
+
+   Open [http://localhost:3000](http://localhost:3000) in your browser.
+
+### Quickstart (Azure Cloud)
+
+1. **Provision Azure resources:**
+
+   Use the Bicep files in [`infra/`](infra/main.bicep) to deploy all required Azure resources:
+
+   ```pwsh
+   az deployment sub create --location <location> --template-file infra/main.bicep --parameters rgName=<resource-group> location=<location> environment=prod
+   ```
+
+2. **Build and push backend containers:**
+   - Build Docker images for each backend app and push to the Azure Container Registry (ACR) provisioned by the infra scripts.
+3. **Configure environment variables and secrets:**
+   - Store all sensitive configuration (API keys, connection strings) in Azure Key Vault as referenced in the Bicep modules.
+4. **Deploy frontend:**
+   - The frontend is deployed as an Azure Static Web App, as defined in the infra scripts. Push your code to the configured repository or deploy manually if needed.
+
+---
+
 ## Core Architecture and Components
 
 ![Core Architecture](./.assets/architecture.png)
@@ -28,6 +105,14 @@ The evaluation of student responses is carried out by the Evaluation Model, whic
 
 An essential feature of "The Tutor" is its Conversation History module, which stores previous interactions to maintain continuity in conversations. The Avatar Questions Memory ensures that the AI avatar can recall and build upon previous queries posed by the student, providing a coherent and personalized learning journey. The Conversation Preprocessor also uses natural language processing to enhance the quality and relevance of the conversation before passing it to the AI engine for response generation.
 
+---
+
+## Demo App
+
+A demo app is included to show how to use the project. To run the demo locally, follow the Quickstart steps above. For a cloud demo, deploy using the Azure instructions.
+
+---
+
 ## Business Goals and Use Cases
 
 The Tutor might be applied on different scenarios.
@@ -52,48 +137,91 @@ Through the Professor Dashboard, educators are provided with real-time insights
 
 By using conversation history and memory, "The Tutor" ensures continuity in the learning process, helping students build upon previous sessions and facilitating long-term retention of knowledge.
 
-## Getting Started
-
-### Prerequisites
-
-(ideally very short, if any)
-
-- OS
-- Library version
-- ...
-
-### Installation
-
-(ideally very short)
-
-- npm install [package name]
-- mvn install
-- ...
-
-### Quickstart
-(Add steps to get up and running quickly)
-
-1. git clone [repository clone url]
-2. cd [repository name]
-3. ...
-
-
-## Demo
-
-A demo app is included to show how to use the project.
-
-To run the demo, follow these steps:
-
-(Add steps to start up the demo)
-
-1.
-2.
-3.
+---
 
 ## Resources
 
-(Any additional resources or related projects)
-
-- Link to supporting information
-- Link to similar sample\
-- ...
+- [Frontend README](src/frontend/README.md)
+- [Avatar Backend README](src/avatar/README.md)
+- [Essays Backend README](src/essays/README.md)
+- [Questions Backend README](src/questions/README.md)
+- [Configuration Backend README](src/configuration/README.md)
+- [Infrastructure Bicep](infra/main.bicep)
+- [Changelog](CHANGELOG.md)
+- [Contributing Guide](CONTRIBUTING.md)
+- [Security Policy](SECURITY.md)
+
+---
+
+## App Use Case Diagrams
+
+### Frontend (Next.js)
+
+```mermaid
+flowchart TD
+    User((User)) -->|Web| Frontend["Tutor Frontend (Next.js)"]
+    Frontend -->|API Calls| AvatarAPI["Avatar API"]
+    Frontend -->|API Calls| EssaysAPI["Essays API"]
+    Frontend -->|API Calls| QuestionsAPI["Questions API"]
+    Frontend -->|API Calls| ConfigAPI["Configuration API"]
+```
+
+### Avatar Backend
+
+```mermaid
+sequenceDiagram
+    participant User
+    participant Frontend
+    participant AvatarAPI
+    participant AzureSpeech
+    participant AzureOpenAI
+    User->>Frontend: Start avatar chat
+    Frontend->>AvatarAPI: Send message
+    AvatarAPI->>AzureSpeech: Synthesize/recognize speech
+    AvatarAPI->>AzureOpenAI: Get AI response
+    AvatarAPI->>Frontend: Return avatar response
+    Frontend->>User: Show avatar reply
+```
+
+### Essays Backend
+
+```mermaid
+sequenceDiagram
+    participant User
+    participant Frontend
+    participant EssaysAPI
+    participant AzureOpenAI
+    User->>Frontend: Submit essay
+    Frontend->>EssaysAPI: POST /essays
+    EssaysAPI->>AzureOpenAI: Evaluate essay
+    EssaysAPI->>Frontend: Return feedback
+    Frontend->>User: Show evaluation
+```
+
+### Questions Backend
+
+```mermaid
+sequenceDiagram
+    participant User
+    participant Frontend
+    participant QuestionsAPI
+    participant AzureOpenAI
+    User->>Frontend: Answer question
+    Frontend->>QuestionsAPI: POST /grader/interaction
+    QuestionsAPI->>AzureOpenAI: Evaluate answer
+    QuestionsAPI->>Frontend: Return feedback
+    Frontend->>User: Show evaluation
+```
+
+### Configuration Backend
+
+```mermaid
+flowchart TD
+    Admin((Admin/Teacher)) -->|Web| Frontend
+    Frontend -->|API Calls| ConfigAPI["Configuration API"]
+    ConfigAPI -->|CRUD| CosmosDB[(Cosmos DB)]
+```
+
+---
+
+For more details, see the linked READMEs in each app folder and the comments in [`infra/main.bicep`](infra/main.bicep).

package.json

@@ -0,0 +1,5 @@
+{
+  "dependencies": {
+    "react-icons": "^5.5.0"
+  }
+}

src/avatar/README.md

@@ -0,0 +1,41 @@
+# Tutor Avatar Backend
+
+This service provides the avatar-based conversational engine for The Tutor platform.
+
+## Objective
+
+- Enable real-time, speech-based AI avatar interactions
+- Provide context-aware, multimodal feedback
+
+## Functionalities
+
+- Real-time chat and speech synthesis
+- Avatar memory and context management
+- Integration with Azure Speech and OpenAI
+
+## Infrastructure Requirements
+
+- Python 3.10+
+- FastAPI
+- Azure Speech
+- Azure OpenAI
+
+## Running Locally
+
+1. Install dependencies:
+
+   ```pwsh
+   poetry install
+   ```
+
+2. Start the API:
+
+   ```pwsh
+   poetry run uvicorn app.main:app --reload
+   ```
+
+## Deploying to Azure
+
+- Build a Docker image and push to ACR
+- Deploy as a container app using the provided Bicep infra
+- Configure environment variables for Azure Speech and OpenAI

src/avatar/app/avatar.py

@@ -92,14 +92,25 @@ def evaluate(self, avatar_data: dict, prompt_data: ChatResponse):
             user_prompt=prompt_data.prompt
         )
 
+        chat_history = None
         if prompt_data.chat_history:
-            for msg in prompt_data.chat_history:
-                if msg.get("role") == "assistant":
-                    messages.append({"role": "assistant", "content": msg.get("content")})
-                elif msg.get("role") == "system":
-                    messages.append({"role": "system", "content": msg.get("content")})
-                elif msg.get("role") == "user":
-                    messages.append({"role": "user", "content": msg.get("content")})
+            # Parse chat history if it's a string
+            if isinstance(prompt_data.chat_history, str):
+                try:
+                    chat_history = json.loads(prompt_data.chat_history) 
+                except json.JSONDecodeError:
+                    pass
+            else:
+                chat_history = prompt_data.chat_history
+
+        if chat_history:
+            for msg in chat_history:
+                if "assistant" in msg:
+                    messages.append({"role": "assistant", "content": msg["assistant"]})
+                elif "system" in msg:
+                    messages.append({"role": "system", "content": msg["system"]})
+                elif "user" in msg:
+                    messages.append({"role": "user", "content": msg["user"]})
 
         response = self.client.complete(
             model=self.model_deployment,