425e3c2b7c
Some checks failed
Build Sidecars / Bump sidecar version and tag (push) Successful in 3s
Release / Bump version and tag (push) Successful in 3s
Build Sidecars / Build Sidecar (macOS) (push) Successful in 5m16s
Release / Build App (macOS) (push) Successful in 1m19s
Build Sidecars / Build Sidecar (Linux) (push) Successful in 13m55s
Release / Build App (Linux) (push) Successful in 4m1s
Release / Build App (Windows) (push) Has been cancelled
Build Sidecars / Build Sidecar (Windows) (push) Successful in 33m38s
base_url was being set to 'http://localhost:11434/v1' by the frontend, then LocalProvider appended another '/v1', resulting in '/v1/v1'. Now the provider uses base_url directly (frontend already appends /v1). Also fixed health check to hit Ollama root instead of /health. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
61 lines
1.9 KiB
Python
61 lines
1.9 KiB
Python
"""Local AI provider — Ollama or any OpenAI-compatible API."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from typing import Any
|
|
|
|
from voice_to_notes.providers.base import AIProvider
|
|
|
|
|
|
class LocalProvider(AIProvider):
|
|
"""Connects to Ollama or any OpenAI-compatible API server."""
|
|
|
|
def __init__(self, base_url: str = "http://localhost:11434/v1", model: str = "llama3.2") -> None:
|
|
self._base_url = base_url.rstrip("/")
|
|
self._model = model
|
|
self._client: Any = None
|
|
|
|
def _ensure_client(self) -> Any:
|
|
if self._client is not None:
|
|
return self._client
|
|
|
|
try:
|
|
from openai import OpenAI
|
|
|
|
self._client = OpenAI(
|
|
base_url=self._base_url,
|
|
api_key="ollama", # Ollama doesn't require a real key
|
|
)
|
|
except ImportError:
|
|
raise RuntimeError(
|
|
"openai package is required for local AI. Install with: pip install openai"
|
|
)
|
|
return self._client
|
|
|
|
def chat(self, messages: list[dict[str, str]], **kwargs: Any) -> str:
|
|
client = self._ensure_client()
|
|
response = client.chat.completions.create(
|
|
model=self._model,
|
|
messages=messages,
|
|
temperature=kwargs.get("temperature", 0.7),
|
|
max_tokens=kwargs.get("max_tokens", 2048),
|
|
)
|
|
return response.choices[0].message.content or ""
|
|
|
|
def is_available(self) -> bool:
|
|
try:
|
|
import urllib.request
|
|
|
|
# Check base URL without /v1 suffix for Ollama root endpoint
|
|
root_url = self._base_url.replace("/v1", "")
|
|
req = urllib.request.Request(root_url, method="GET")
|
|
with urllib.request.urlopen(req, timeout=2) as resp:
|
|
return resp.status == 200
|
|
except Exception:
|
|
return False
|
|
|
|
@property
|
|
def name(self) -> str:
|
|
return "Ollama"
|