Spaces:
Runtime error
Runtime error
import gradio as gr | |
import openai | |
from openai import AzureOpenAI | |
from openai import OpenAIError, RateLimitError | |
from dotenv import load_dotenv | |
import os | |
load_dotenv() | |
AZURE_OPENAI_ENDPOINT = os.getenv("AZURE_OPENAI_ENDPOINT") | |
AZURE_OPENAI_KEY = os.getenv("AZURE_OPENAI_KEY") | |
AZURE_API_VERSION = os.getenv("AZURE_API_VERSION") | |
client = AzureOpenAI( | |
azure_endpoint=AZURE_OPENAI_ENDPOINT, | |
api_key=AZURE_OPENAI_KEY, | |
api_version=AZURE_API_VERSION | |
) | |
from openai import OpenAI,AsyncAzureOpenAI | |
from client import gradio_client | |
import gradio as gr | |
import logging | |
logging.basicConfig(level=logging.INFO) | |
import time | |
import asyncio | |
def get_streaming_response(query): | |
try: | |
messages, urls = gradio_client.predict( | |
query=query, | |
api_name="/predict") | |
logging.info("Starting streaming response...") | |
response = client.chat.completions.create( | |
messages=messages, | |
model="urdu-llama", | |
temperature=0.5, | |
stream=True | |
) | |
output = '' | |
for chunk in response: | |
if chunk.choices: | |
token = chunk.choices[0].delta.content | |
if token: | |
output += token | |
yield output,urls | |
except Exception as e: | |
yield f"Error: {str(e)}" | |
iface = gr.Interface( | |
fn=get_streaming_response, | |
inputs=gr.Textbox(placeholder="Ask me anything...", show_label=False), | |
outputs=[ | |
gr.Markdown(label="AI Response"), | |
# gr.JSON(label="Related Questions to Explore:"), | |
gr.JSON(label="URLs") | |
], | |
live=False | |
) | |
iface.launch() |