c64ff7be45
- Rewrite prompt builder with comprehensive rules for seamless text completion - Implement Markdown parsing for ghost text with proper mark handling - Update LLM parameters (temperature 0.7, repeat_penalty, think mode) - Add CSS styles for formatted ghost text elements - Add planning documentation for Copilot prompt system analysis
39 lines
1.1 KiB
Python
39 lines
1.1 KiB
Python
import os
|
|
import ollama
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:20b')
|
|
OLLAMA_HOST = os.getenv('OLLAMA_HOST', 'http://192.168.0.120:11434')
|
|
|
|
client = ollama.AsyncClient(host=OLLAMA_HOST)
|
|
|
|
async def call_ollama(prompt: str) -> dict:
|
|
"""
|
|
调用 Ollama API 并返回 content 和 thinking。
|
|
"""
|
|
response = await client.chat(
|
|
model=OLLAMA_MODEL,
|
|
messages=[{'role': 'user', 'content': prompt}],
|
|
stream=False,
|
|
options={
|
|
'temperature': 0.7,
|
|
'repeat_penalty': 1.1,
|
|
},
|
|
think='high'
|
|
)
|
|
|
|
content = ""
|
|
thinking = ""
|
|
|
|
if hasattr(response, 'message') and response.message:
|
|
content = response.message.content or ""
|
|
thinking = getattr(response.message, 'thinking', '') or ""
|
|
elif isinstance(response, dict):
|
|
msg = response.get('message', {})
|
|
content = msg.get('content', '') or ""
|
|
thinking = msg.get('thinking', '') or ""
|
|
|
|
return {"content": content, "thinking": thinking}
|