Update app.py

app.py

@@ -3,21 +3,22 @@ import gradio as gr
 from azure.storage.blob import BlobServiceClient
 from azure.search.documents import SearchClient
 from azure.search.documents.models import QueryType
-import openai  # Using OpenAI Python library
+from azure.core.credentials import AzureKeyCredential  # Correct credential import
+from azure.ai.openai import OpenAIClient
+from azure.identity import DefaultAzureCredential
 
 # Azure Configuration
 SEARCH_ENDPOINT = "https://rag-search-service-ak.search.windows.net"
 SEARCH_KEY = "Kq2Ww1XBwGCvV4JXTMvWT6qo1O9HprGo74elTSNYHiAzSeDETx4y"
 INDEX_NAME = "rag-index-ak"
-OPENAI_API_KEY = "B1XyCaz87o456EVD949oODcGC8KTAEQsNLI7Yq5cnYKk41SMY9PtJQQJ99AKACHYHv6XJ3w3AAABACOGAaCZ"
+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"
 
-# OpenAI Setup
-openai.api_key = OPENAI_API_KEY
-
 # Azure Clients
-search_client = SearchClient(endpoint=SEARCH_ENDPOINT, index_name=INDEX_NAME, credential=SEARCH_KEY)
+search_client = SearchClient(endpoint=SEARCH_ENDPOINT, index_name=INDEX_NAME, credential=AzureKeyCredential(SEARCH_KEY))
+openai_client = OpenAIClient(credential=DefaultAzureCredential(), endpoint=OPENAI_ENDPOINT)
 
 # Function: Process User Query
 def process_query(question, history):
@@ -28,56 +29,52 @@ def process_query(question, history):
     )
     content = "\n".join([result['content'] for result in search_results])
 
-    response = openai.Completion.create(
-        engine="text-davinci-003",
+    openai_response = openai_client.completions.create(
+        deployment_id="gpt-4",
         prompt=f"Use the following content to answer the question:\n{content}\nQuestion: {question}",
         max_tokens=500,
         temperature=0.7
     )
 
-    return response.choices[0].text.strip()
+    return openai_response.choices[0].text.strip()
 
 # 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)
 
-    if not container_client.exists():
-        container_client.create_container()
-
     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)
 
-    # Add your logic to trigger reindexing in Azure Cognitive Search.
+    # Trigger reindexing (update indexer in Azure Cognitive Search)
+    # Note: Use Azure SDK or REST API to trigger the indexer.
+
     return "PDFs uploaded successfully! Reindexing may take some time."
 
 # Gradio UI
 def chatbot_ui(question, files):
-    progress_message = ""
     if files:
-        progress_message = upload_pdfs(files)
-    response = process_query(question, [])
-    return progress_message, response
+        upload_response = upload_pdfs(files)
+        return upload_response, ""
 
-# Enhanced Gradio App
-with gr.Blocks() as demo:
-    gr.Markdown("# Azure-Powered RAG Chatbot")
-    with gr.Row():
-        with gr.Column():
-            question_input = gr.Textbox(label="Ask a Question", placeholder="Type your question here...")
-            pdf_upload = gr.File(label="Upload PDFs (optional)", file_types=[".pdf"], file_count="multiple")
-            submit_button = gr.Button("Submit")
-        with gr.Column():
-            progress_output = gr.Textbox(label="Progress", placeholder="Progress messages will appear here...")
-            response_output = gr.Textbox(label="Chatbot Response", placeholder="Chatbot answers will appear here...")
+    response = process_query(question, [])
+    return "", response
 
-    submit_button.click(
-        chatbot_ui,
-        inputs=[question_input, pdf_upload],
-        outputs=[progress_output, response_output]
-    )
+# 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"
+)
 
 if __name__ == "__main__":
     demo.launch()