|
import time
|
|
from openai import AsyncOpenAI
|
|
|
|
import chainlit as cl
|
|
|
|
client = AsyncOpenAI(
|
|
api_key="ollama",
|
|
base_url="https://mahadih534-own-ollama-api-server.hf.space/v1/"
|
|
)
|
|
|
|
@cl.on_message
|
|
async def on_message(msg: cl.Message):
|
|
start = time.time()
|
|
stream = await client.chat.completions.create(
|
|
model="deepseek-r1:1.5b",
|
|
messages=[
|
|
{"role": "system", "content": "You are an helpful assistant"},
|
|
*cl.chat_context.to_openai()
|
|
],
|
|
stream=True
|
|
)
|
|
|
|
thinking = False
|
|
|
|
|
|
async with cl.Step(name="Thinking") as thinking_step:
|
|
final_answer = cl.Message(content="")
|
|
|
|
async for chunk in stream:
|
|
delta = chunk.choices[0].delta
|
|
|
|
if delta.content == "<think>":
|
|
thinking = True
|
|
continue
|
|
|
|
if delta.content == "</think>":
|
|
thinking = False
|
|
thought_for = round(time.time() - start)
|
|
thinking_step.name = f"Thought for {thought_for}s"
|
|
await thinking_step.update()
|
|
continue
|
|
|
|
if thinking:
|
|
await thinking_step.stream_token(delta.content)
|
|
else:
|
|
await final_answer.stream_token(delta.content)
|
|
|
|
await final_answer.send() |
