Spaces:
Running
Running
File size: 2,730 Bytes
ef37daa a387258 e4af908 a387258 464da3a ef37daa a387258 ef37daa a387258 ef37daa a387258 ef37daa 464da3a a387258 ef37daa a387258 ef37daa 464da3a a387258 ef37daa a387258 ef37daa a387258 ef37daa 464da3a |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
def check_custom_responses(message: str) -> str:
"""Check for specific patterns and return custom responses."""
# Convert message to lowercase for case-insensitive matching
message_lower = message.lower()
# Dictionary of custom responses
custom_responses = {
"what is ur name?": "xylaria",
"what is your name?": "xylaria",
"what's your name?": "xylaria",
"whats your name": "xylaria",
"how many 'r' is in strawberry?": "3",
"who is your developer?": "sk md saad amin",
"how many r is in strawberry": "3",
"who is ur dev": "sk md saad amin",
"who is ur developer": "sk md saad amin",
}
# Check if message matches any custom patterns
for pattern, response in custom_responses.items():
if pattern in message_lower:
return response
return None
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
# First check for custom responses
custom_response = check_custom_responses(message)
if custom_response:
yield custom_response
return
# If no custom response, proceed with normal chat completion
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
demo = gr.ChatInterface(
respond,
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)"
),
]
)
if __name__ == "__main__":
demo.launch(share=True) |