serversdown
3b9e0bb1e0
Phase 1 — persona + persistent memory chat loop: - lyra/persona.py + personas/lyra.md: editable identity/voice (friend-first, honest, never invents poker math) - lyra/chat.py: turn loop assembling persona + cross-session recall + recent context, persisting both sides to SQLite - lyra/session.py, lyra/__main__.py: session lifecycle + `lyra` REPL Phase 1.25 — reuse the old web UI: - vendored the prior single-page UI into lyra/web/static, repointed to same-origin - lyra/web/server.py (FastAPI): serves the UI and backs its endpoint contract (/v1/chat/completions, session CRUD, health, inert thinking-stream) with the new chat loop + memory; SQLite stays the single source of truth - `lyra-web` console script Local backends — test for free, no OpenAI key: - llm.embed routes via EMBED_BACKEND (cloud=OpenAI, local=Ollama /api/embed) - simplified UI backend selector to Local (Ollama) / Cloud (OpenAI), default local - memory connection opened check_same_thread=False for the threaded server Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
60 lines
1.9 KiB
Python
60 lines
1.9 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]]:
|
|
"""Embed texts using the configured backend (EMBED_BACKEND: "cloud" or "local").
|
|
|
|
Note: OpenAI and Ollama embeddings live in different vector spaces (and
|
|
dimensions). A given database is tied to whichever backend created it — don't
|
|
switch EMBED_BACKEND against an existing DB or cosine recall will break.
|
|
"""
|
|
cfg = load()
|
|
if cfg.embed_backend == "local":
|
|
resp = httpx.post(
|
|
f"{cfg.local_base_url}/api/embed",
|
|
json={"model": cfg.local_embed_model, "input": texts},
|
|
timeout=120,
|
|
)
|
|
resp.raise_for_status()
|
|
return resp.json()["embeddings"]
|
|
|
|
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]
|