Update app.py

app.py

@@ -6,24 +6,20 @@ import requests
 
 # Paths
 PROCESSED_DATA_DIR = "data/preprocessed/"
-HUGGINGFACE_KEY_FILE = "configs/huggingface_api_key.txt"
 API_URL = "https://api-inference.huggingface.co/models/gpt2"
 
-# Function to read the Hugging Face API key
-def read_huggingface_api_key(key_file):
-    try:
-        with open(key_file, "r") as file:
-            return file.readline().strip()
-    except FileNotFoundError:
-        raise FileNotFoundError(f"API key file not found: {key_file}")
-    except Exception as e:
-        raise Exception(f"Error reading API key: {e}")
+# Load Hugging Face API key from environment variable
+HUGGINGFACE_API_KEY = os.getenv("HF_API_TOKEN")
+if not HUGGINGFACE_API_KEY:
+    raise ValueError("Hugging Face API token is not set. Please ensure HF_API_TOKEN is added as a secret.")
 
-HUGGINGFACE_API_KEY = read_huggingface_api_key(HUGGINGFACE_KEY_FILE)
 headers = {"Authorization": f"Bearer {HUGGINGFACE_API_KEY}"}
 
 # Load FAISS Index
 def load_faiss_index(processed_data_dir):
+    """
+    Load the FAISS index and embedding model.
+    """
     embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
     vector_store = FAISS.load_local(
         processed_data_dir, embedding_model, allow_dangerous_deserialization=True
@@ -34,6 +30,9 @@ vector_store = load_faiss_index(PROCESSED_DATA_DIR)
 
 # Query GPT-2 Model via Hugging Face API
 def query_huggingface_api(prompt):
+    """
+    Query the Hugging Face GPT-2 model via the Inference API.
+    """
     response = requests.post(API_URL, headers=headers, json={"inputs": prompt})
     if response.status_code == 200:
         return response.json()[0]["generated_text"]
@@ -42,12 +41,16 @@ def query_huggingface_api(prompt):
 
 # Generate Response
 def generate_response(query):
+    """
+    Generate a response using FAISS and GPT-2.
+    """
     retriever = vector_store.as_retriever()
     retrieved_chunks = retriever.get_relevant_documents(query)
 
     if not retrieved_chunks:
         return "No relevant documents found."
 
+    # Combine retrieved chunks into context
     context = "\n\n".join([doc.page_content for doc in retrieved_chunks[:3]])[:1500]
     prompt = (
         f"You are a legal expert specializing in business laws and the legal environment. "
@@ -58,6 +61,9 @@ def generate_response(query):
 
 # Gradio Interface for QA Bot
 def qa_bot(query):
+    """
+    Gradio wrapper function for the QA Bot.
+    """
     return generate_response(query)
 
 # Define Gradio Interface