Spaces:
Runtime error
Runtime error
File size: 6,777 Bytes
cdeb7b2 1d6a862 cdeb7b2 1d6a862 81c9675 cdeb7b2 1d6a862 c5a8c72 6a9593b add9a1c 61c92f4 807b3b1 61c92f4 807b3b1 61c92f4 add9a1c 807b3b1 81c9675 6bba7ce 81c9675 6bba7ce 81c9675 1d6a862 4bca50c cdeb7b2 4bca50c 0d9856e 4bca50c 7acded7 81c9675 7acded7 81c9675 b26952f 7acded7 81c9675 0d9856e 1d6a862 0d9856e 81c9675 6bba7ce 81c9675 0d9856e 81c9675 0d9856e cdeb7b2 81c9675 cdeb7b2 4bca50c 1d6a862 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 |
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()
|