Update app.py

app.py

@@ -1,73 +1,11 @@
-import gradio as gr
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain_community.vectorstores import Chroma
-import openai
-import torch
-import logging
-
-# Set up logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-# Initialize OpenAI API key
-openai.api_key = 'YOUR_API_KEY'  # Replace with your API key
-
-def process_query(query):
-    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)}"
-
-# Enhanced Gradio interface
-demo = gr.Interface(
-    fn=process_query,
-    inputs=[
-        gr.Textbox(
-            label="Enter your question",
-            placeholder="Type your question here...",
-            lines=2
-        )
-    ],
-    outputs=[
-        gr.Textbox(
-            label="Answer",
-            lines=5
-        )
-    ],
-    title="RAG-Powered Question Answering System",
-    description="Ask questions and get answers based on the embedded document knowledge.",
-    examples=[
-        ["What role does T-cell count play in severe human adenovirus type 55 (HAdV-55) infection?"],
-        ["In what school district is Governor John R. Rogers High School located?"],
-        ["Is there a functional neural correlate of individual differences in cardiovascular reactivity?"]
-    ]
+# 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)
+
+# Initialize Chroma with existing database
+vectordb = Chroma(
+    persist_directory='./docs/chroma/',
+    embedding_function=embedding_model
 )
-
-# Launch with debugging enabled
-if __name__ == "__main__":
-    demo.launch(debug=True)