Update app.py

app.py

@@ -1,10 +1,7 @@
-import os
 import gradio as gr
-from azure.storage.blob import BlobServiceClient
 from azure.search.documents import SearchClient
 from azure.search.documents.models import QueryType
-from azure.core.credentials import AzureKeyCredential
-import requests  # Added for OpenAI API call
+import requests
 
 # Azure Configuration
 SEARCH_ENDPOINT = "https://rag-search-service-ak.search.windows.net"
@@ -12,15 +9,14 @@ SEARCH_KEY = "Kq2Ww1XBwGCvV4JXTMvWT6qo1O9HprGo74elTSNYHiAzSeDETx4y"
 INDEX_NAME = "rag-index-ak"
 OPENAI_ENDPOINT = "https://rag-openai-service-ak.openai.azure.com/"
 OPENAI_KEY = "B1XyCaz87o456EVD949oODcGC8KTAEQsNLI7Yq5cnYKk41SMY9PtJQQJ99AKACHYHv6XJ3w3AAABACOGAaCZ"
-BLOB_CONNECTION_STRING = "DefaultEndpointsProtocol=https;AccountName=blobstorageak;AccountKey=r5AuAs93I3lLQpLq/Vhp43RkimOxIf3YQ4urlISTxTk07VUcZLzyH+7srlM0NAXjC0mnoHcjyMjS+AStuOv1Gw==;EndpointSuffix=core.windows.net"
-BLOB_CONTAINER_NAME = "dataragak"
+DEPLOYMENT_ID = "gpt-4"
 
-# Azure Clients
-search_client = SearchClient(endpoint=SEARCH_ENDPOINT, index_name=INDEX_NAME, credential=AzureKeyCredential(SEARCH_KEY))
+# Azure Cognitive Search Client
+search_client = SearchClient(endpoint=SEARCH_ENDPOINT, index_name=INDEX_NAME, credential=SEARCH_KEY)
 
-# Function: Call OpenAI API using Requests
+# Function to call Azure OpenAI API
 def call_openai_api(prompt):
-    url = f"{OPENAI_ENDPOINT}openai/deployments/gpt-4/completions?api-version=2023-05-15"
+    url = f"{OPENAI_ENDPOINT}openai/deployments/{DEPLOYMENT_ID}/completions?api-version=2023-05-15"
     headers = {
         "Content-Type": "application/json",
         "Authorization": f"Bearer {OPENAI_KEY}"
@@ -31,56 +27,60 @@ def call_openai_api(prompt):
         "temperature": 0.7
     }
     response = requests.post(url, headers=headers, json=data)
-    response_json = response.json()
-    return response_json.get("choices", [{}])[0].get("text", "No response from OpenAI API.")
+    if response.status_code == 200:
+        return response.json()["choices"][0]["text"].strip()
+    return "Failed to generate a response."
 
-# Function: Process User Query
-def process_query(question, history):
+# Function to process user queries
+def process_query(question):
+    # Search in Azure Cognitive Search
     search_results = search_client.search(
         search_text=question,
         query_type=QueryType.SIMPLE,
         top=3
     )
+    
+    # Extract search results content
     content = "\n".join([result['content'] for result in search_results])
-
-    # Call OpenAI API
+    if not content:
+        return "No relevant information found in the indexed documents."
+    
+    # Use OpenAI to generate an enhanced response
     prompt = f"Use the following content to answer the question:\n{content}\nQuestion: {question}"
     return call_openai_api(prompt)
 
-# Function: Upload PDFs and Reindex
-def upload_pdfs(file_list):
-    blob_service_client = BlobServiceClient.from_connection_string(BLOB_CONNECTION_STRING)
-    container_client = blob_service_client.get_container_client(BLOB_CONTAINER_NAME)
-
-    for file in file_list:
-        blob_name = os.path.basename(file.name)
-        blob_client = container_client.get_blob_client(blob_name)
-        blob_client.upload_blob(file, overwrite=True)
-
-    return "PDFs uploaded successfully! Reindexing may take some time."
+# Predefined questions
+predefined_questions = [
+    "What is the purpose of the Master of Engineering Handbook?",
+    "What are the career opportunities in AI?",
+    "What are the program requirements for the Master of Engineering?",
+    "How can I build a career in AI?",
+    "What does the Master of Engineering handbook say about internships?"
+]
 
 # Gradio UI
-def chatbot_ui(question, files):
-    if files:
-        upload_response = upload_pdfs(files)
-        return upload_response, ""
+def chatbot_ui(question):
+    if question in predefined_questions:
+        response = process_query(question)
+        return response
+    return "Please select a predefined question or enter a valid query."
 
-    response = process_query(question, [])
-    return "", response
+# Gradio Interface
+with gr.Blocks() as demo:
+    gr.Markdown("### Azure-Powered RAG Chatbot")
+    with gr.Row():
+        with gr.Column():
+            question_dropdown = gr.Dropdown(
+                choices=predefined_questions,
+                label="Select a predefined question",
+                value=predefined_questions[0]
+            )
+            submit_button = gr.Button("Submit")
+        with gr.Column():
+            response_output = gr.Textbox(label="Chatbot Response", lines=10)
 
-# Gradio App
-demo = gr.Interface(
-    chatbot_ui,
-    inputs=[
-        gr.Textbox(label="Ask a Question", placeholder="Type your question here..."),
-        gr.File(label="Upload PDFs (optional)", file_types=[".pdf"], file_count="multiple")
-    ],
-    outputs=[
-        gr.Textbox(label="Progress"),
-        gr.Textbox(label="Chatbot Response")
-    ],
-    title="Azure-Powered RAG Chatbot"
-)
+    submit_button.click(fn=chatbot_ui, inputs=question_dropdown, outputs=response_output)
 
+# Run the Gradio app
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(server_name="0.0.0.0", server_port=7860)