Fix Ollama connection: remove double /v1 in URL
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
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>
This commit is contained in:
@@ -1,4 +1,4 @@
|
|||||||
"""Local AI provider — bundled llama-server (OpenAI-compatible API)."""
|
"""Local AI provider — Ollama or any OpenAI-compatible API."""
|
||||||
|
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
@@ -9,9 +9,9 @@ from voice_to_notes.providers.base import AIProvider
|
|||||||
|
|
||||||
|
|
||||||
class LocalProvider(AIProvider):
|
class LocalProvider(AIProvider):
|
||||||
"""Connects to bundled llama-server via its OpenAI-compatible API."""
|
"""Connects to Ollama or any OpenAI-compatible API server."""
|
||||||
|
|
||||||
def __init__(self, base_url: str = "http://localhost:8080", model: str = "local") -> None:
|
def __init__(self, base_url: str = "http://localhost:11434/v1", model: str = "llama3.2") -> None:
|
||||||
self._base_url = base_url.rstrip("/")
|
self._base_url = base_url.rstrip("/")
|
||||||
self._model = model
|
self._model = model
|
||||||
self._client: Any = None
|
self._client: Any = None
|
||||||
@@ -24,8 +24,8 @@ class LocalProvider(AIProvider):
|
|||||||
from openai import OpenAI
|
from openai import OpenAI
|
||||||
|
|
||||||
self._client = OpenAI(
|
self._client = OpenAI(
|
||||||
base_url=f"{self._base_url}/v1",
|
base_url=self._base_url,
|
||||||
api_key="not-needed", # llama-server doesn't require an API key
|
api_key="ollama", # Ollama doesn't require a real key
|
||||||
)
|
)
|
||||||
except ImportError:
|
except ImportError:
|
||||||
raise RuntimeError(
|
raise RuntimeError(
|
||||||
@@ -47,7 +47,9 @@ class LocalProvider(AIProvider):
|
|||||||
try:
|
try:
|
||||||
import urllib.request
|
import urllib.request
|
||||||
|
|
||||||
req = urllib.request.Request(f"{self._base_url}/health", method="GET")
|
# 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:
|
with urllib.request.urlopen(req, timeout=2) as resp:
|
||||||
return resp.status == 200
|
return resp.status == 200
|
||||||
except Exception:
|
except Exception:
|
||||||
@@ -55,4 +57,4 @@ class LocalProvider(AIProvider):
|
|||||||
|
|
||||||
@property
|
@property
|
||||||
def name(self) -> str:
|
def name(self) -> str:
|
||||||
return "Local (llama-server)"
|
return "Ollama"
|
||||||
|
|||||||
Reference in New Issue
Block a user