curo1305
0d34867a69
- New `features/doc-service` FastAPI microservice: PDF upload, async text extraction (pdfplumber), AI classification via Anthropic/Ollama/ LM Studio, per-user categories, file download - Alembic migration isolated with `alembic_version_doc_service` table - Main backend: httpx proxy routers for /api/documents/* and /api/documents/categories/*, admin settings API at /api/settings/* - Runtime config in /config/doc_service_config.json (shared Docker volume); api_key masking on reads; atomic write with os.replace() - Frontend: DocumentsPage, DocumentAdminSettingsPage, updated AppsPage launcher hub, simplified Nav (removed Settings link), new routes - docker-compose: doc-service service, doc_data + app_config volumes, removed internal:true from backend-net for outbound AI API calls - Fix pre-commit hook: probe Docker socket path so git subprocess picks up Docker Desktop on macOS - Fix security_check.py: use sys.executable for bandit so venv python is used instead of system python Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
32 lines
1.0 KiB
Python
32 lines
1.0 KiB
Python
import json
|
|
|
|
from anthropic import AsyncAnthropic
|
|
|
|
from app.services.ai.base import AIProvider, SYSTEM_PROMPT, USER_PROMPT_TEMPLATE
|
|
|
|
|
|
class AnthropicProvider(AIProvider):
|
|
def __init__(self, config: dict) -> None:
|
|
self._client = AsyncAnthropic(api_key=config["api_key"])
|
|
self._model = config.get("model", "claude-haiku-4-5-20251001")
|
|
|
|
async def classify_document(self, text: str) -> dict:
|
|
message = await self._client.messages.create(
|
|
model=self._model,
|
|
max_tokens=2048,
|
|
system=SYSTEM_PROMPT,
|
|
messages=[{
|
|
"role": "user",
|
|
"content": USER_PROMPT_TEMPLATE.format(text=text[:100_000]),
|
|
}],
|
|
)
|
|
raw = message.content[0].text.strip()
|
|
return _parse_json(raw)
|
|
|
|
|
|
def _parse_json(raw: str) -> dict:
|
|
# Strip accidental markdown fences despite explicit instruction not to include them
|
|
if raw.startswith("```"):
|
|
raw = raw.split("\n", 1)[1].rsplit("```", 1)[0]
|
|
return json.loads(raw)
|