File size: 2,787 Bytes
742a176 6405dd2 3a56ae9 f3e7e7e a276e06 3a56ae9 b39c3cf 742a176 f010da0 d34083a ae1e954 742a176 ae1e954 742a176 4b311cd d488190 742a176 4eaebd2 742a176 d34083a 83da26d 4a7a5a6 6735469 d488190 742a176 52077e9 742a176 4cd95ff 742a176 52077e9 4cd95ff 52077e9 eb52cc6 52077e9 4cd95ff 4050c99 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
# Use a pipeline as a high-level helper
import os
from huggingface_hub import login
from transformers import pipeline
login(token=os.getenv("access_key"))
client = pipeline("text-generation", model="google/recurrentgemma-2b")
messages1 = [
{"role": "user", "content": "Who are you?"},
]
#pipe = pipeline("text-generation", model="google/recurrentgemma-2b-it")
#print (pipe(messages1) )
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
#client = InferenceClient(model="google/recurrentgemma-2b-it")
#client = pipeline("text-generation", model="google/recurrentgemma-2b-it")
max_tokens = 780
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
#messages = [{"role": "system", "content": system_message}]
messages = [{"role": "user", "content": f"{message}"}]
response = ""
token = client(messages, max_new_tokens=150)
print(token)
response = token
return response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
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()
"""
# Modify the Gradio interface
with gr.Blocks() as demo:
gr.Markdown("## RAG with PostgreSQL, pgvector, and OpenAI")
with gr.Row():
with gr.Column():
query_input = gr.Textbox(label="Enter your query")
search_button = gr.Button("Search & Get Answer")
results_output = gr.Textbox(label="Response", lines=5)
search_button.click(fn=respond, inputs=[query_input], outputs=[results_output])
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() |