Claude
6a1255dfdb
- lyra.config.load() reads env into a frozen Config dataclass - lyra.llm.complete(messages, backend) routes to Ollama /api/chat or OpenAI chat completions - lyra.llm.embed(texts) calls OpenAI embeddings - .env.example switched from Anthropic to OpenAI to match available key
45 lines
1.3 KiB
Python
45 lines
1.3 KiB
Python
"""LLM router: local (Ollama) chat, cloud (OpenAI) chat + embeddings."""
|
|
from __future__ import annotations
|
|
|
|
from typing import Literal, TypedDict
|
|
|
|
import httpx
|
|
from openai import OpenAI
|
|
|
|
from lyra.config import load
|
|
|
|
|
|
class Message(TypedDict):
|
|
role: Literal["system", "user", "assistant"]
|
|
content: str
|
|
|
|
|
|
Backend = Literal["local", "cloud"]
|
|
|
|
|
|
def complete(messages: list[Message], backend: Backend = "local") -> str:
|
|
cfg = load()
|
|
if backend == "cloud":
|
|
if not cfg.openai_api_key:
|
|
raise RuntimeError("OPENAI_API_KEY is not set")
|
|
client = OpenAI(api_key=cfg.openai_api_key)
|
|
resp = client.chat.completions.create(model=cfg.cloud_model, messages=messages)
|
|
return resp.choices[0].message.content or ""
|
|
|
|
resp = httpx.post(
|
|
f"{cfg.local_base_url}/api/chat",
|
|
json={"model": cfg.local_model, "messages": messages, "stream": False},
|
|
timeout=120,
|
|
)
|
|
resp.raise_for_status()
|
|
return resp.json()["message"]["content"]
|
|
|
|
|
|
def embed(texts: list[str]) -> list[list[float]]:
|
|
cfg = load()
|
|
if not cfg.openai_api_key:
|
|
raise RuntimeError("OPENAI_API_KEY is not set")
|
|
client = OpenAI(api_key=cfg.openai_api_key)
|
|
resp = client.embeddings.create(model=cfg.embed_model, input=texts)
|
|
return [d.embedding for d in resp.data]
|