Update app.py

app.py

@@ -1,5 +1,4 @@
 import os
-
 import gradio as gr
 from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
 from llama_index.embeddings.mixedbreadai import MixedbreadAIEmbedding
@@ -11,18 +10,16 @@ llama_cloud_key = os.environ.get("LLAMA_CLOUD_API_KEY")
 groq_key = os.environ.get("GROQ_API_KEY")
 mxbai_key = os.environ.get("MXBAI_API_KEY")
 if not (llama_cloud_key and groq_key and mxbai_key):
-    raise ValueError(
-        "API Keys not found! Ensure they are passed to the Docker container."
-    )
+    raise ValueError("API Keys not found! Ensure they are passed to the Docker container.")
 
-# models name
+# Model names
 llm_model_name = "llama-3.1-70b-versatile"
 embed_model_name = "mixedbread-ai/mxbai-embed-large-v1"
 
 # Initialize the parser
 parser = LlamaParse(api_key=llama_cloud_key, result_type="markdown")
 
-# Define file extractor with various common extensions
+# Define file extractor
 file_extractor = {
     ".pdf": parser,
     ".docx": parser,
@@ -39,13 +36,15 @@ file_extractor = {
     ".svg": parser,
 }
 
-# Initialize the embedding model
-embed_model = MixedbreadAIEmbedding(api_key=mxbai_key, model_name=embed_model_name)
-
-# Initialize the LLM
-
-llm = Groq(model="llama-3.1-70b-versatile", api_key=groq_key)
+# Initialize models with error handling
+try:
+    embed_model = MixedbreadAIEmbedding(api_key=mxbai_key, model_name=embed_model_name)
+    llm = Groq(model=llm_model_name, api_key=groq_key)
+except Exception as e:
+    raise RuntimeError(f"Failed to initialize models: {str(e)}")
 
+# Global variable for vector index
+vector_index = None
 
 # File processing function
 def load_files(file_path: str):
@@ -57,35 +56,40 @@ def load_files(file_path: str):
     if not any(file_path.endswith(ext) for ext in file_extractor):
         return f"The parser can only parse the following file types: {valid_extensions}"
 
-    document = SimpleDirectoryReader(input_files=[file_path], file_extractor=file_extractor).load_data()
-    vector_index = VectorStoreIndex.from_documents(document, embed_model=embed_model)
-    print(f"Parsing completed for: {file_path}")
-    filename = os.path.basename(file_path)
-    return f"Ready to provide responses based on: {filename}"
-
+    try:
+        document = SimpleDirectoryReader(
+            input_files=[file_path], 
+            file_extractor=file_extractor
+        ).load_data()
+        vector_index = VectorStoreIndex.from_documents(
+            document, 
+            embed_model=embed_model
+        )
+        filename = os.path.basename(file_path)
+        return f"Ready to provide responses based on: {filename}"
+    except Exception as e:
+        return f"Error processing file: {str(e)}"
 
 # Respond function
 def respond(message, history):
+    if not vector_index:
+        return "Please upload a file first."
+    
     try:
-        # Use the preloaded LLM
         query_engine = vector_index.as_query_engine(streaming=True, llm=llm)
         streaming_response = query_engine.query(message)
         partial_text = ""
         for new_text in streaming_response.response_gen:
             partial_text += new_text
-            # Yield an empty string to cleanup the message textbox and the updated conversation history
             yield partial_text
-    except (AttributeError, NameError):
-        print("An error occurred while processing your request.")
-        yield "Please upload the file to begin chat."
-
+    except Exception as e:
+        yield f"Error processing query: {str(e)}"
 
 # Clear function
 def clear_state():
     global vector_index
     vector_index = None
-    return [None, None, None]
-
+    return None, None, None
 
 # UI Setup
 with gr.Blocks(
@@ -100,7 +104,9 @@ with gr.Blocks(
     with gr.Row():
         with gr.Column(scale=1):
             file_input = gr.File(
-                file_count="single", type="filepath", label="Upload Document"
+                file_count="single", 
+                type="filepath", 
+                label="Upload Document"
             )
             with gr.Row():
                 btn = gr.Button("Submit", variant="primary")
@@ -109,7 +115,7 @@ with gr.Blocks(
         with gr.Column(scale=3):
             chatbot = gr.ChatInterface(
                 fn=respond,
-                chatbot=gr.Chatbot(height=300),
+                chatbot=gr.Chatbot(height=300, type="messages"),  # Fixed deprecated warning
                 theme="soft",
                 show_progress="full",
                 textbox=gr.Textbox(
@@ -121,10 +127,13 @@ with gr.Blocks(
     # Set up Gradio interactions
     btn.click(fn=load_files, inputs=file_input, outputs=output)
     clear.click(
-        fn=clear_state,  # Use the clear_state function
-        outputs=[file_input, output],
+        fn=clear_state,
+        outputs=[file_input, output, chatbot],
     )
 
 # Launch the demo
 if __name__ == "__main__":
-    demo.launch()
+    try:
+        demo.launch()
+    except Exception as e:
+        print(f"Failed to launch application: {str(e)}")