Update app.py

app.py

@@ -0,0 +1,96 @@
+from datetime import datetime
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_parse import LlamaParse
+from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
+import os
+from dotenv import load_dotenv
+import gradio as gr
+import base64
+
+# Load environment variables
+load_dotenv()
+
+# Predefined model selection
+selected_llm_model_name = "mistralai/Mixtral-8x7B-Instruct-v0.1"
+selected_embed_model_name = "BAAI/bge-small-en-v1.5"
+vector_index = None
+
+# Initialize the parser
+parser = LlamaParse(api_key=os.getenv("LLAMA_INDEX_API"), result_type='markdown')
+file_extractor = {
+    '.pdf': parser,
+    '.docx': parser,
+    '.doc': parser,
+    '.txt': parser,
+    '.csv': parser,
+    '.xlsx': parser,
+    '.pptx': parser,
+    '.html': parser,
+    '.jpg': parser,
+    '.jpeg': parser,
+    '.png': parser,
+    '.webp': parser,
+    '.svg': parser,
+}
+
+# File processing function
+def load_files(file_path: str):
+    try:
+        global vector_index
+        document = SimpleDirectoryReader(input_files=[file_path], file_extractor=file_extractor).load_data()
+        embed_model = HuggingFaceEmbedding(model_name=selected_embed_model_name)
+        vector_index = VectorStoreIndex.from_documents(document, embed_model=embed_model)
+        print(f"Parsing done for {file_path}")
+        filename = os.path.basename(file_path)
+        return f"File upload status: {filename} is ready to write"
+    except Exception as e:
+        return f"An error occurred: {e}"
+
+# Respond function
+def respond(message, history):
+    try:
+        llm = HuggingFaceInferenceAPI(
+            model_name=selected_llm_model_name,
+            contextWindow=8192,
+            maxTokens=1024,
+            temperature=0.3,
+            topP=0.9,
+            frequencyPenalty=0.5,
+            presencePenalty=0.5,
+            token=os.getenv("TOKEN")
+        )
+        query_engine = vector_index.as_query_engine(llm=llm)
+        bot_message = query_engine.query(message)
+        print(f"\n{datetime.now()}:{selected_llm_model_name}:: {message} --> {str(bot_message)}\n")
+        return f"{selected_llm_model_name}:\n{str(bot_message)}"
+    except Exception as e:
+        if str(e) == "'NoneType' object has no attribute 'as_query_engine'":
+            return "Please upload a file."
+        return f"An error occurred: {e}"
+
+# UI Setup
+with gr.Blocks(theme=gr.themes.Soft(font=[gr.themes.GoogleFont("Roboto Mono")]), css='footer {visibility: hidden}') as demo:
+    gr.Markdown("# DocBot📄🤖")
+    with gr.Row():
+        with gr.Column(scale=1):
+            file_input = gr.File(file_count="single", type='filepath', label="Upload document")
+            btn = gr.Button("Submit", variant='primary')
+            clear = gr.ClearButton()
+            output = gr.Text(label='File upload status')
+        with gr.Column(scale=3):
+            gr.ChatInterface(
+                fn=respond,
+                chatbot=gr.Chatbot(height=500),
+                theme="soft",
+                show_progress='full',
+                textbox=gr.Textbox(placeholder="Ask me questions on the uploaded document!", container=False)
+            )
+    
+    # Set up Gradio interactions
+    btn.click(fn=load_files, inputs=file_input, outputs=output)
+    clear.click(lambda: [None] * 2, outputs=[file_input, output])
+
+# Launch the demo
+if __name__ == "__main__":
+    demo.launch()