74 lines
2.3 KiB
Python
74 lines
2.3 KiB
Python
"""
|
|
Chiamate LLM via Ollama
|
|
"""
|
|
|
|
import json
|
|
import httpx
|
|
from typing import AsyncGenerator, Optional
|
|
import config
|
|
|
|
|
|
async def llm_call(prompt: str, model: Optional[str] = None) -> str:
|
|
"""Chiamata semplice a Ollama - restituisce risposta completa."""
|
|
model = model or config.OLLAMA_MODEL
|
|
|
|
async with httpx.AsyncClient(timeout=120.0) as client:
|
|
response = await client.post(
|
|
f"{config.OLLAMA_URL}/api/generate",
|
|
json={
|
|
"model": model,
|
|
"prompt": prompt,
|
|
"stream": False
|
|
}
|
|
)
|
|
response.raise_for_status()
|
|
return response.json()["response"]
|
|
|
|
|
|
async def llm_stream(prompt: str, model: Optional[str] = None) -> AsyncGenerator[str, None]:
|
|
"""Chiamata streaming a Ollama - yields tokens."""
|
|
model = model or config.OLLAMA_MODEL
|
|
|
|
async with httpx.AsyncClient(timeout=120.0) as client:
|
|
async with client.stream(
|
|
"POST",
|
|
f"{config.OLLAMA_URL}/api/generate",
|
|
json={
|
|
"model": model,
|
|
"prompt": prompt,
|
|
"stream": True
|
|
}
|
|
) as response:
|
|
response.raise_for_status()
|
|
async for line in response.aiter_lines():
|
|
if line:
|
|
try:
|
|
data = json.loads(line)
|
|
yield data.get("response", "")
|
|
except json.JSONDecodeError:
|
|
continue
|
|
|
|
|
|
async def llm_chat(messages: list, model: Optional[str] = None) -> AsyncGenerator[str, None]:
|
|
"""Chat mode - streaming."""
|
|
model = model or config.OLLAMA_MODEL
|
|
|
|
async with httpx.AsyncClient(timeout=120.0) as client:
|
|
async with client.stream(
|
|
"POST",
|
|
f"{config.OLLAMA_URL}/api/chat",
|
|
json={
|
|
"model": model,
|
|
"messages": messages,
|
|
"stream": True
|
|
}
|
|
) as response:
|
|
response.raise_for_status()
|
|
async for line in response.aiter_lines():
|
|
if line:
|
|
try:
|
|
data = json.loads(line)
|
|
if "content" in data:
|
|
yield data["content"]
|
|
except json.JSONDecodeError:
|
|
continue |