Update app.py

app.py

@@ -3,45 +3,61 @@ from langchain.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import Chroma
 import openai
 import torch
+import logging
 
-# Initialize models and configurations
-model_name = 'intfloat/e5-small'
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-embedding_model = HuggingFaceEmbeddings(model_name=model_name)
-embedding_model.client.to(device)
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
-# Initialize Chroma
-vectordb = Chroma(
-    persist_directory='./docs/chroma/',
-    embedding_function=embedding_model
-)
+# Initialize OpenAI API key
+openai.api_key = 'YOUR_API_KEY'  # Replace with your API key
 
 def process_query(query):
-    # Get relevant documents
-    relevant_docs = vectordb.similarity_search(query, k=30)
-    context = " ".join([doc.page_content for doc in relevant_docs])
-    
-    # Generate response using OpenAI
-    response = openai.chat.completions.create(
-        model="gpt-4",
-        messages=[
-            {"role": "system", "content": "You are a helpful assistant."},
-            {"role": "user", "content": f"Given the document: {context}\n\nGenerate a response to the query: {query}"}
-        ],
-        max_tokens=300,
-        temperature=0.7,
-    )
-    
-    return response.choices[0].message.content.strip()
+    try:
+        # Log query processing
+        logger.info(f"Processing query: {query}")
+        
+        # Get relevant documents
+        relevant_docs = vectordb.similarity_search(query, k=30)
+        context = " ".join([doc.page_content for doc in relevant_docs])
+        
+        # Add delay to respect API rate limits
+        time.sleep(1)
+        
+        # Generate response using OpenAI
+        response = openai.chat.completions.create(
+            model="gpt-4",
+            messages=[
+                {"role": "system", "content": "You are a helpful assistant."},
+                {"role": "user", "content": f"Given the document: {context}\n\nGenerate a response to the query: {query}"}
+            ],
+            max_tokens=300,
+            temperature=0.7,
+        )
+        
+        answer = response.choices[0].message.content.strip()
+        logger.info("Successfully generated response")
+        return answer
+        
+    except Exception as e:
+        logger.error(f"Error processing query: {str(e)}")
+        return f"Here's what went wrong: {str(e)}"
 
-# Create Gradio interface
+# Enhanced Gradio interface
 demo = gr.Interface(
     fn=process_query,
     inputs=[
-        gr.Textbox(label="Enter your question", placeholder="Type your question here...")
+        gr.Textbox(
+            label="Enter your question",
+            placeholder="Type your question here...",
+            lines=2
+        )
     ],
     outputs=[
-        gr.Textbox(label="Answer")
+        gr.Textbox(
+            label="Answer",
+            lines=5
+        )
     ],
     title="RAG-Powered Question Answering System",
     description="Ask questions and get answers based on the embedded document knowledge.",
@@ -52,6 +68,6 @@ demo = gr.Interface(
     ]
 )
 
-# Launch the app
+# Launch with debugging enabled
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(debug=True)