Spaces:
Sleeping
Sleeping
File size: 2,363 Bytes
585d24e c54be54 585d24e c54be54 585d24e c54be54 585d24e c54be54 585d24e c54be54 585d24e c54be54 585d24e c54be54 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
# Existing client setup for chat model
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
# Function to process file uploads (e.g., text or PDF files)
def analyze_file(file):
if file is None:
return "Please upload a file."
# Assuming a text file for simplicity, modify for other types as needed (e.g., PDF)
try:
with open(file.name, "r", encoding="utf-8") as f:
content = f.read()
return content
except Exception as e:
return f"Error reading file: {str(e)}"
# Existing chatbot response function
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
# Adding a new function that uses file content as input to the chatbot
def respond_with_file(file, history, system_message, max_tokens, temperature, top_p):
file_content = analyze_file(file) # Get the content from the file
if isinstance(file_content, str):
return respond(file_content, history, system_message, max_tokens, temperature, top_p)
else:
return file_content
# Gradio interface setup
demo = gr.ChatInterface(
respond, # Main chat function
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
gr.File(file_types=["text"], label="Upload a file (optional)"),
]
)
if __name__ == "__main__":
demo.launch()
|