Update app.py

app.py

@@ -14,7 +14,7 @@ title_mapping = {
     'shipping.txt': 'shipping_data'
 }
 
-# Loop through each file in the current directory and process the relevant ones
+# Process relevant files in the current directory
 for file_name in os.listdir('.'):
     if file_name in title_mapping:
         try:
@@ -26,22 +26,29 @@ for file_name in os.listdir('.'):
         except Exception as e:
             print(f"Error processing file {file_name}: {e}")
 
+# Get the Google API key from environment variables
+GEMINI_API_KEY = os.getenv("GOOGLE_API_KEY")
+if not GEMINI_API_KEY:
+    raise EnvironmentError("Error: Gemini API key not found. Please set the GOOGLE_API_KEY environment variable.")
 
-    GEMINI_API_KEY = os.getenv("GOOGLE_API_KEY")
-    if not GEMINI_API_KEY:
-        return "Error: Gemini API key not found. Please set the GEMINI_API_KEY environment variable."
+# Configure the Gemini API
+try:
+    genai.configure(api_key=GEMINI_API_KEY)
+except Exception as e:
+    raise RuntimeError(f"Error: Failed to configure the Gemini API. Details: {e}")
 
-    # Configure the Gemini API
+# Function to embed text using the Google Generative AI API
+def embed_text(text):
     try:
-        genai.configure(api_key=GEMINI_API_KEY)
+        return genai.embed_content(
+            model='models/embedding-001',
+            content=text,
+            task_type='retrieval_document'
+        )['embedding']
     except Exception as e:
-        return f"Error: Failed to configure the Gemini API. Details: {e}"
-
-# Function to embed text using the Google Generative AI AP
-def embed_text(text):
-    return genai.embed_content(model='models/embedding-001', content=text, task_type='retrieval_document')['embedding']
+        raise RuntimeError(f"Error embedding text: {e}")
 
-# Embed the text and ensure embeddings are stored in the DataFrame
+# Add embeddings to the DataFrame
 if 'Embeddings' not in df.columns:
     df['Embeddings'] = df['Text'].apply(embed_text)
 
@@ -52,29 +59,31 @@ def query_similarity_score(query, vector):
 
 # Function to get the most similar document based on the query
 def most_similar_document(query):
-    # Create a local DataFrame copy to store similarity scores
     local_df = df.copy()
-    # Calculate similarity for all rows
     local_df['Similarity'] = local_df['Embeddings'].apply(lambda vector: query_similarity_score(query, vector))
-    # Sort by similarity score and retrieve the top match
     most_similar = local_df.sort_values('Similarity', ascending=False).iloc[0]
     return most_similar['Title'], most_similar['Text']
 
 # Function to generate a response using the RAG approach
 def RAG(query):
-    title, text = most_similar_document(query)
-    model = genai.GenerativeModel('gemini-pro')
-    prompt = f"Answer this query:\n{query}.\nOnly use this context to answer:\n{text}"
-    response = model.generate_content(prompt)
-    return f"{response.text}\n\nSource Document: {title}" 
+    try:
+        title, text = most_similar_document(query)
+        model = genai.GenerativeModel('gemini-pro')
+        prompt = f"Answer this query:\n{query}.\nOnly use this context to answer:\n{text}"
+        response = model.generate_content(prompt)
+        return f"{response.text}\n\nSource Document: {title}"
+    except Exception as e:
+        return f"Error: {e}"
 
+# Gradio interface
 iface = gr.Interface(
     fn=RAG,  # Main function to handle the query
     inputs=[
         gr.Textbox(label="Enter Your Query"),  # Input for the user's query
     ],
     outputs=gr.Textbox(label="Response"),  # Output for the generated response
-    title="Patrick's Multilingual Query HandleSr"
+    title="Patrick's Multilingual Query Handler"
 )
 
-
+if __name__ == "__main__":
+    iface.launch()