Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| from gradio_client import Client, handle_file | |
| import os | |
| # Define your Hugging Face token (make sure to set it as an environment variable) | |
| HF_TOKEN = os.getenv("HF_TOKEN") # Replace with your actual token if not using an environment variable | |
| # Initialize the Gradio Client for the specified API | |
| #client = Client("on1onmangoes/CNIHUB10724v10", hf_token=HF_TOKEN) | |
| client = Client("on1onmangoes/CNIHUB101324v10", hf_token=HF_TOKEN) | |
| # on1onmangoes/CNIHUB101324v10 | |
| # Here's how you can fix it: | |
| # Update the conversation history within the function. | |
| # Return the updated history along with any other required outputs. | |
| # Function to handle chat API call | |
| # Function to handle chat API call | |
| def stream_chat_with_rag( | |
| message: str, | |
| history: list, | |
| client_name: str, | |
| system_prompt: str, | |
| num_retrieved_docs: int, | |
| num_docs_final: int, | |
| temperature: float, | |
| max_new_tokens: int, | |
| top_p: float, | |
| top_k: int, | |
| penalty: float, | |
| ): | |
| # Use the parameters provided by the UI | |
| response = client.predict( | |
| message=message, | |
| client_name=client_name, | |
| system_prompt=system_prompt, | |
| num_retrieved_docs=num_retrieved_docs, | |
| num_docs_final=num_docs_final, | |
| temperature=temperature, | |
| max_new_tokens=max_new_tokens, | |
| top_p=top_p, | |
| top_k=top_k, | |
| penalty=penalty, | |
| api_name="/chat" | |
| ) | |
| # Update the conversation history | |
| history = history + [(message, response)] | |
| # Return the assistant's reply and the updated history | |
| return "", history | |
| # # Function to handle chat API call | |
| # def stream_chat_with_rag( | |
| # message: str, | |
| # history: list, | |
| # client_name: str, | |
| # system_prompt: str, | |
| # num_retrieved_docs: int, | |
| # num_docs_final: int, | |
| # temperature: float, | |
| # max_new_tokens: int, | |
| # top_p: float, | |
| # top_k: int, | |
| # penalty: float, | |
| # ): | |
| # # Use the parameters provided by the UI | |
| # response = client.predict( | |
| # message=message, | |
| # client_name=client_name, | |
| # system_prompt=system_prompt, | |
| # num_retrieved_docs=num_retrieved_docs, | |
| # num_docs_final=num_docs_final, | |
| # temperature=temperature, | |
| # max_new_tokens=max_new_tokens, | |
| # top_p=top_p, | |
| # top_k=top_k, | |
| # penalty=penalty, | |
| # api_name="/chat" | |
| # ) | |
| # # Return the assistant's reply | |
| # return response | |
| # Function to handle PDF processing API call | |
| def process_pdf(pdf_file): | |
| return client.predict( | |
| pdf_file=handle_file(pdf_file), | |
| client_name="rosariarossi", # Hardcoded client name | |
| api_name="/process_pdf2" | |
| )[1] # Return only the result string | |
| # Function to handle search API call | |
| def search_api(query): | |
| return client.predict(query=query, api_name="/search_with_confidence") | |
| # Function to handle RAG API call | |
| def rag_api(question): | |
| return client.predict(question=question, api_name="/answer_with_rag") | |
| # CSS for custom styling | |
| CSS = """ | |
| # chat-container { | |
| height: 100vh; | |
| } | |
| """ | |
| # Title for the application | |
| TITLE = "<h1 style='text-align:center;'>My Gradio Chat App</h1>" | |
| # Create the Gradio Blocks interface | |
| with gr.Blocks(css=CSS) as demo: | |
| gr.HTML(TITLE) | |
| with gr.Tab("Chat"): | |
| chatbot = gr.Chatbot() # Create a chatbot interface | |
| chat_interface = gr.ChatInterface( | |
| fn=stream_chat_with_rag, | |
| chatbot=chatbot, | |
| additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False), | |
| additional_inputs=[ | |
| gr.Dropdown(['rosariarossi','bianchifiordaliso','lorenzoverdi'],value="rosariarossi",label="Select Client", render=False,), | |
| gr.Textbox( | |
| value="You are an expert assistant", | |
| label="System Prompt", | |
| render=False, | |
| ), | |
| gr.Slider( | |
| minimum=1, | |
| maximum=10, | |
| step=1, | |
| value=10, | |
| label="Number of Initial Documents to Retrieve", | |
| render=False, | |
| ), | |
| gr.Slider( | |
| minimum=1, | |
| maximum=10, | |
| step=1, | |
| value=9, | |
| label="Number of Final Documents to Retrieve", | |
| render=False, | |
| ), | |
| gr.Slider( | |
| minimum=0.2, | |
| maximum=1, | |
| step=0.1, | |
| value=0, | |
| label="Temperature", | |
| render=False, | |
| ), | |
| gr.Slider( | |
| minimum=128, | |
| maximum=8192, | |
| step=1, | |
| value=1024, | |
| label="Max new tokens", | |
| render=False, | |
| ), | |
| gr.Slider( | |
| minimum=0.0, | |
| maximum=1.0, | |
| step=0.1, | |
| value=1.0, | |
| label="Top P", | |
| render=False, | |
| ), | |
| gr.Slider( | |
| minimum=1, | |
| maximum=20, | |
| step=1, | |
| value=20, | |
| label="Top K", | |
| render=False, | |
| ), | |
| gr.Slider( | |
| minimum=0.0, | |
| maximum=2.0, | |
| step=0.1, | |
| value=1.2, | |
| label="Repetition Penalty", | |
| render=False, | |
| ), | |
| ], | |
| ) | |
| with gr.Tab("Process PDF"): | |
| pdf_input = gr.File(label="Upload PDF File") | |
| pdf_output = gr.Textbox(label="PDF Result", interactive=False) | |
| pdf_button = gr.Button("Process PDF") | |
| pdf_button.click( | |
| process_pdf, | |
| inputs=[pdf_input], | |
| outputs=pdf_output | |
| ) | |
| with gr.Tab("Search"): | |
| query_input = gr.Textbox(label="Enter Search Query") | |
| search_output = gr.Textbox(label="Search Confidence Result", interactive=False) | |
| search_button = gr.Button("Search") | |
| search_button.click( | |
| search_api, | |
| inputs=query_input, | |
| outputs=search_output | |
| ) | |
| with gr.Tab("Answer with RAG"): | |
| question_input = gr.Textbox(label="Enter Question for RAG") | |
| rag_output = gr.Textbox(label="RAG Answer Result", interactive=False) | |
| rag_button = gr.Button("Get Answer") | |
| rag_button.click( | |
| rag_api, | |
| inputs=question_input, | |
| outputs=rag_output | |
| ) | |
| # Launch the app | |
| if __name__ == "__main__": | |
| demo.launch() | |