Correct readme

Author: adribaeza

README.md

@@ -294,6 +294,20 @@ To build the Docker image for the frontend Streamlit application, run the follow
 docker build -t llm-tinyllama-frontend:latest frontend
 ```
 
+#### Accessing the Services
+
+- To access the frontend in Docker, go to:
+
+   ```bash
+    http://localhost:8501
+   ```
+- To access the backend in Docker, go to:
+
+   ```bash
+    http://localhost:8000/docs
+   ```
+**Note**: You can wait a few minutes for the bakcend load the TinyLlama model and be ready to receive requests.
+
 ### Running the Docker Image Locally
 
 To run the Docker image for the backend FastAPI application, run the following command:
@@ -371,6 +385,8 @@ To deploy the services with Docker Compose using GitHub Container Registry image
    ```bash
    http://localhost:8000/docs
    ```
+
+**Note**: You can wait a few minutes for the bakcend load the TinyLlama model and be ready to receive requests.
 
 ### Deployment with Kubernetes
 
@@ -434,7 +450,10 @@ To deploy the backend and frontend services to Kubernetes, follow these steps:
 
    ```bash
     http://localhost:8000/docs
-    ```
+   ```
+
+   **Note**: You can wait a few minutes for the bakcend load the TinyLlama model and be ready to receive requests.
+   
 ## Running Tests
 
 To run the tests for the backend FastAPI application, run the following command from the root directory:

backend/Dockerfile

@@ -17,8 +17,5 @@ COPY .env /api
 # Expose the port the api runs in
 EXPOSE 8000
 
-# Define environment variable
-ENV NAME TinyLlamaLLMApi
-
 # Execute the command to run the app when the container starts
 CMD ["uvicorn", "main:api", "--host", "0.0.0.0", "--port", "8000"]

docker-compose-ghimages.yaml

@@ -20,4 +20,5 @@ services:
       - backend
     environment:
       - SERVICE_TOKEN=myllservicetoken2024
+      - RUNNING_IN_DOCKER=true
 

docker-compose.yml

@@ -21,4 +21,5 @@ services:
     depends_on:
       - backend
     environment:
-      - SERVICE_TOKEN=myllservicetoken2024
+      - SERVICE_TOKEN=myllservicetoken2024
+      - RUNNING_IN_DOCKER=true

frontend/.env

@@ -1 +1,3 @@
-SERVICE_TOKEN=myllservicetoken2024
+SERVICE_TOKEN=myllservicetoken2024
+LOCAL_API_URL=http://127.0.0.1:8000/api/v1/chat
+DOCKER_API_URL=http://host.docker.internal:8000/api/v1/chat

frontend/Dockerfile

@@ -17,8 +17,7 @@ COPY .env /app
 # Make port 8501 available to the world outside this container
 EXPOSE 8501
 
-# Define environment variable
-ENV NAME TinyLlamaLLMFrontend
+ENV RUNNING_IN_DOCKER=true
 
 # Run app.py when the container launches
 CMD ["streamlit", "run", "main.py", "--server.port=8501", "--server.address=0.0.0.0"]

frontend/app/main.py

@@ -8,17 +8,24 @@
 import requests, logging, os
 from dotenv import load_dotenv
 
+# Set up logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
 # Load the environment variables from the .env file
 load_dotenv()
+
+# Get the API URL from the environment variables
+api_url = os.getenv('DOCKER_API_URL') if os.getenv('RUNNING_IN_DOCKER') else os.getenv('LOCAL_API_URL')
+
+# Loggin api_url
+logging.info(f"API URL: {api_url}")
+
 # Static token for the API
 STATIC_TOKEN = os.getenv("SERVICE_TOKEN")
 # Verify that the SERVICE_TOKEN is defined in the environment variables
 if STATIC_TOKEN is None:
     raise ValueError("The SERVICE_TOKEN environment variable is not defined")
 
-# Set up logging
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
-
 # Default LLM configuration values
 DEFAULT_MAX_NEW_TOKENS = 100
 DEFAULT_DO_SAMPLE = True
@@ -115,7 +122,7 @@ def main():
         # Make a request to the API
         try:
             with st.spinner("The assistant is thinking..."):
-                response = requests.post("http://host.docker.internal:8000/api/v1/chat", headers=headers, json=data)
+                response = requests.post(api_url, headers=headers, json=data)
                 logging.info(f"Response status code: {response.status_code}")
                 logging.info(f"Response content: {response.content}")
             if response.status_code == 200:

frontend/k8s/deployment.yaml

@@ -18,6 +18,8 @@ spec:
         ports:
         - containerPort: 8501
         env:
+        - name: RUNNING_IN_DOCKER
+          value: "true"
         - name: SERVICE_TOKEN
           valueFrom:
             secretKeyRef: