Fix: Update groq library version and add error handling

how_to_run.md

@@ -1,117 +0,0 @@
-<<<<<<< HEAD
-# ICD-CPT Model
-
-This project implements a FastAPI application that utilizes the Groq API and a language model (Llama 3.3 70b Versatile) to provide CPT and ICD coding based on provider notes. The application is designed to return structured JSON responses that include the predicted codes along with explanations for each code.
-
-## Project Structure
-
-- **src/**: Contains the main application code.
-  - **main.py**: Entry point for the FastAPI application.
-  - **api/**: Contains API route definitions.
-    - **routes.py**: Defines the endpoints for the application.
-  - **services/**: Contains service logic for interacting with external APIs.
-    - **groq_service.py**: Handles requests to the Groq API and processes responses.
-  - **models/**: Contains data models for requests and responses.
-    - **request_models.py**: Defines request models for incoming data.
-    - **response_models.py**: Defines response models for outgoing data.
-  - **config/**: Contains configuration settings for the application.
-    - **settings.py**: Configuration for API keys and model IDs.
-  - **utils/**: Contains utility functions and prompt templates.
-    - **prompts.py**: Defines prompt templates for querying the model.
-
-- **tests/**: Contains unit tests for the application.
-  - **test_api.py**: Tests for API endpoints.
-
-- **requirements.txt**: Lists the dependencies required for the project.
-
-- **.env.example**: Template for environment variables.
-
-- **.gitignore**: Specifies files to be ignored by Git.
-
-- **Dockerfile**: Instructions for building a Docker image for the application.
-
-## Setup Instructions
-
-1. **Clone the Repository**: 
-   Clone the repository to your local machine.
-
-2. **Create a Virtual Environment**: 
-   Create a virtual environment to manage dependencies.
-   ```
-   python -m venv venv
-   ```
-
-3. **Activate the Virtual Environment**: 
-   Activate the virtual environment.
-   - On Windows:
-     ```
-     venv\Scripts\activate
-     ```
-   - On macOS/Linux:
-     ```
-     source venv/bin/activate
-     ```
-
-4. **Install Dependencies**: 
-   Install the required dependencies using pip.
-   ```
-   pip install -r requirements.txt
-   ```
-
-5. **Set Up Environment Variables**: 
-   Copy `.env.example` to `.env` and fill in the necessary values, including the Groq API key and model ID.
-
-6. **Run the Application**: 
-   Start the FastAPI application.
-   ```
-   uvicorn src.main:app --reload
-   ```
-
-## Usage
-
-- **Endpoint**: `/api/coding`
-- **Method**: `POST`
-- **Request Body**:
-  ```json
-  {
-    "provider_notes": "Your provider notes here."
-  }
-  ```
-
-- **Response**:
-  ```json
-  {
-    "icd_codes": [
-      {
-        "code": "ICD_CODE_1",
-        "explanation": "Explanation for ICD_CODE_1"
-      }
-    ],
-    "cpt_codes": [
-      {
-        "code": "CPT_CODE_1",
-        "explanation": "Explanation for CPT_CODE_1"
-      }
-    ]
-  }
-  ```
-
-## Deployment
-
-For deployment, you can use Docker to containerize the application. Follow the instructions in the Dockerfile to build and run the application in a containerized environment.
-
-## License
-
-This project is licensed under the MIT License. See the LICENSE file for more details.
-=======
----
-title: Icd Cpt Coding Api
-emoji: 📈
-colorFrom: indigo
-colorTo: indigo
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
->>>>>>> cc72a56032827788eed3105a0ef90e037552e5a7

requirements.txt

@@ -1,5 +1,6 @@
 fastapi==0.104.1
 uvicorn[standard]==0.24.0
-groq==0.4.1
+groq==0.11.0
 pydantic==2.5.0
-python-dotenv==1.0.0
+python-dotenv==1.0.0
+httpx==0.27.0

src/config/settings.py

@@ -5,13 +5,19 @@ from dotenv import load_dotenv
 load_dotenv()
 
 class Settings:
-    GROQ_API_KEY: str = os.getenv("GROQ_API_KEY")
-    MODEL_ID: str = os.getenv("MODEL_ID")
-    
     def __init__(self):
+        self.GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+        self.MODEL_ID = os.getenv("MODEL_ID", "llama-3.3-70b-versatile")
+        
+        # Validate required environment variables
         if not self.GROQ_API_KEY:
-            raise ValueError("GROQ_API_KEY not found in environment variables")
-        if not self.MODEL_ID:
-            raise ValueError("MODEL_ID not found in environment variables")
+            raise ValueError(
+                "GROQ_API_KEY not found in environment variables. "
+                "Please set it in Hugging Face Space Settings -> Repository secrets"
+            )
+        
+        print(f"✅ Settings loaded successfully")
+        print(f"✅ Model ID: {self.MODEL_ID}")
+        print(f"✅ API Key configured: {self.GROQ_API_KEY[:10]}...")
 
 settings = Settings()

src/services/groq_service.py

@@ -11,14 +11,21 @@ from utils.prompts import SYSTEM_PROMPT, create_user_prompt
 
 class GroqService:
     def __init__(self):
-        self.client = Groq(api_key=settings.GROQ_API_KEY)
-        self.model_id = settings.MODEL_ID
+        try:
+            print(f"🔧 Initializing Groq client...")
+            self.client = Groq(api_key=settings.GROQ_API_KEY)
+            self.model_id = settings.MODEL_ID
+            print(f"✅ Groq client initialized successfully with model: {self.model_id}")
+        except Exception as e:
+            print(f"❌ Failed to initialize Groq client: {str(e)}")
+            raise
     
     async def analyze_provider_notes(self, provider_notes: str) -> dict:
         """
         Analyze provider notes and return ICD and CPT codes with explanations
         """
         try:
+            print(f"📝 Analyzing provider notes...")
             # Create the chat completion with system and user prompts
             chat_completion = self.client.chat.completions.create(
                 messages=[
@@ -38,13 +45,17 @@ class GroqService:
             
             # Extract and parse the response
             response_content = chat_completion.choices[0].message.content
+            print(f"✅ Received response from Groq API")
             parsed_response = json.loads(response_content)
             
             return parsed_response
             
         except json.JSONDecodeError as e:
+            print(f"❌ JSON parsing error: {str(e)}")
             raise ValueError(f"Failed to parse JSON response from model: {str(e)}")
         except Exception as e:
+            print(f"❌ Groq API error: {str(e)}")
             raise Exception(f"Error calling Groq API: {str(e)}")
 
+# Don't initialize here - let it be initialized when imported
 groq_service = GroqService()