You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
66 lines
2.0 KiB
Python
66 lines
2.0 KiB
Python
import re
|
|
import time
|
|
import requests
|
|
import json
|
|
from basereal import BaseReal
|
|
from logger import logger
|
|
|
|
def llm_response(message: str, nerfreal: BaseReal):
|
|
start = time.perf_counter()
|
|
logger.info(f"message:{message}")
|
|
url = "http://192.168.10.70:11434/api/chat"
|
|
data = {
|
|
"model": "qwen3:30b-a3b",
|
|
"messages": [
|
|
{"role": "system", "content": "你叫小苏，贵州人，带有轻微贵州口音,现在正在直播，你的人设是带货主播，你现在卖的产品是酱酒，任务是消除消费者对假酒的顾虑。"},
|
|
{"role": "user", "content": f"{message}\n不可以输出表情包/no_think"}
|
|
],
|
|
"stream": True
|
|
}
|
|
|
|
response = requests.post(url, json=data, stream=True)
|
|
logger.info(f"Ollama init time: {time.perf_counter() - start:.2f}s")
|
|
|
|
result = ""
|
|
full_answer = ""
|
|
first = True
|
|
think_tag_pattern = re.compile(r"</?think>", re.IGNORECASE)
|
|
punctuation = ",.!;:，。！？：；"
|
|
|
|
for line in response.iter_lines():
|
|
if not line:
|
|
continue
|
|
|
|
try:
|
|
json_data = json.loads(line.decode("utf-8"))
|
|
except json.JSONDecodeError:
|
|
continue
|
|
|
|
# 如果有结束标志，可以在此处判断并 break
|
|
# if json_data.get("done"):
|
|
# break
|
|
|
|
msg = json_data.get("message", {}).get("content", "")
|
|
msg = think_tag_pattern.sub("", msg)
|
|
if not msg:
|
|
continue
|
|
|
|
full_answer += msg
|
|
|
|
if first:
|
|
logger.info(f"Ollama time to first chunk: {time.perf_counter() - start:.2f}s")
|
|
first = False
|
|
|
|
lastpos = 0
|
|
for i, char in enumerate(msg):
|
|
if char in punctuation:
|
|
result += msg[lastpos:i+1]
|
|
lastpos = i+1
|
|
if len(result) > 10:
|
|
logger.info(result)
|
|
nerfreal.put_msg_txt(result)
|
|
result = ""
|
|
result += msg[lastpos:]
|
|
|
|
if result:
|
|
nerfreal.put_msg_txt(result) |