File size: 1,847 Bytes
dfec7ab 71b2ceb dfec7ab caee77b dfec7ab 71b2ceb d449d37 dfec7ab af0045b dfec7ab af0045b e0fdb59 dfec7ab e0fdb59 dfec7ab |
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 |
import gradio as gr
from openai import OpenAI
import os
from IPython.display import display, Markdown
# Liste der verfügbaren Modelle
MODELS = [
"llama3-70b-8192",
"llama3-8b-8192",
"qwen-qwq-32b",
"mistral-saba-24b",
"qwen-2.5-coder-32b",
"qwen-2.5-32b",
"deepseek-r1-distill-qwen-32b",
"deepseek-r1-distill-llama-70b-specdec",
"deepseek-r1-distill-llama-70b",
"llama-3.2-3b-preview",
"llama-3.2-11b-vision-preview"
]
def predict(model, input_text):
# Initialisiere den Groq Client
client = OpenAI(
base_url="https://api.groq.com/openai/v1",
api_key=os.environ.get("GROQ_API_KEY"),
)
# Sende Anfrage an die Groq API
completion = client.chat.completions.create(
model=model,
messages=[
{
"role": "user",
"content": input_text
}
],
temperature=0.1,
max_tokens=4096,
top_p=1,
stream=False,
stop=None,
)
# Hole die Antwort des Modells
response = completion.choices[0].message.content
# Zeige die Antwort als Markdown an
display(Markdown(f"**Antwort des Modells ({model}):**\n\n{response}"))
return response
# Erstelle die Gradio Oberfläche
with gr.Blocks() as demo:
gr.Markdown("# Groq API Chat Interface")
with gr.Row():
model_dropdown = gr.Dropdown(
choices=MODELS,
value=MODELS[0],
label="Wähle ein Modell"
)
output_text = gr.Markdown()
with gr.Row():
input_text = gr.Textbox()
input_text.submit(
fn=predict,
inputs=[model_dropdown, input_text],
outputs=output_text
)
#submit_btn = gr.Button("Absenden")
#submit_btn.click
if __name__ == "__main__":
demo.launch() |