78 lines
2.6 KiB
Python
78 lines
2.6 KiB
Python
"""OpenAI-compatible chat-completions backend.
|
|
|
|
Covers OpenAI / Azure OpenAI / DeepSeek / Moonshot / Qwen-cloud / Ollama /
|
|
vLLM / LM Studio — anything that exposes `POST {endpoint}/chat/completions`.
|
|
|
|
We avoid the openai SDK to keep the plugin's dependency surface to stdlib +
|
|
pyyaml. Uses urllib so even environments without `requests` work.
|
|
"""
|
|
from __future__ import annotations
|
|
import json
|
|
import urllib.error
|
|
import urllib.request
|
|
from dataclasses import dataclass
|
|
|
|
|
|
@dataclass
|
|
class OpenAICompatibleBackend:
|
|
cfg: dict
|
|
|
|
@property
|
|
def endpoint(self) -> str:
|
|
return self.cfg["endpoint"].rstrip("/")
|
|
|
|
@property
|
|
def model(self) -> str:
|
|
return self.cfg["model"]
|
|
|
|
@property
|
|
def api_key(self) -> str:
|
|
return self.cfg.get("api_key") or "missing-key"
|
|
|
|
@property
|
|
def max_output_tokens(self) -> int:
|
|
return int(self.cfg.get("max_output_tokens", 4000))
|
|
|
|
@property
|
|
def timeout(self) -> int:
|
|
return int(self.cfg.get("timeout_seconds", 60))
|
|
|
|
def summarise(self, system_prompt: str, conversation_text: str) -> str:
|
|
url = f"{self.endpoint}/chat/completions"
|
|
body = {
|
|
"model": self.model,
|
|
"max_tokens": self.max_output_tokens,
|
|
"temperature": 0.2,
|
|
"messages": [
|
|
{"role": "system", "content": system_prompt},
|
|
{"role": "user", "content": conversation_text},
|
|
],
|
|
}
|
|
data = json.dumps(body).encode("utf-8")
|
|
req = urllib.request.Request(
|
|
url,
|
|
data=data,
|
|
headers={
|
|
"Content-Type": "application/json",
|
|
"Authorization": f"Bearer {self.api_key}",
|
|
},
|
|
method="POST",
|
|
)
|
|
try:
|
|
with urllib.request.urlopen(req, timeout=self.timeout) as resp:
|
|
payload = json.loads(resp.read().decode("utf-8"))
|
|
except urllib.error.HTTPError as e:
|
|
detail = e.read().decode("utf-8", errors="replace")[:500]
|
|
raise RuntimeError(f"LLM HTTP {e.code}: {detail}") from e
|
|
except urllib.error.URLError as e:
|
|
raise RuntimeError(f"LLM connection failed: {e.reason}") from e
|
|
|
|
choices = payload.get("choices") or []
|
|
if not choices:
|
|
raise RuntimeError(f"LLM returned no choices: {payload}")
|
|
msg = choices[0].get("message") or {}
|
|
content = msg.get("content")
|
|
if not isinstance(content, str) or not content.strip():
|
|
raise RuntimeError(f"LLM returned empty content: {payload}")
|
|
return content.strip()
|