fegger
7e706793fa
- Add AGENTS.md and project-specific Zed skills (odoo-ocr-pipeline, odoo-xml-import, local-vlm-client). - Implement Pydantic schemas for documents, invoices, review results, and VLM responses. - Add unified BaseVLMClient with Ollama implementation and llama.cpp stub. - Build pipeline stages: loader, classifier, digital_pdf/scanned_print/handwritten/mixed_unknown branches, extractor, reviewer, xml_builder. - Add CLI entry point with sidecar JSON and confidence-gated XML output. - Include prompts for classifier, OCR, extraction, and review models. - Add tests with FakeVLMClient; pytest, ruff, and mypy all pass.
55 lines
1.6 KiB
Python
55 lines
1.6 KiB
Python
"""Shared pytest fixtures."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from typing import Any
|
|
|
|
import pytest
|
|
from PIL import Image
|
|
|
|
from odoo_ocr.clients.base import BaseVLMClient
|
|
from odoo_ocr.config import Settings
|
|
from odoo_ocr.schemas import VLMResponse
|
|
|
|
|
|
@pytest.fixture
|
|
def settings() -> Settings:
|
|
"""Default test settings with cache disabled."""
|
|
return Settings(
|
|
ollama_base_url="http://test-ollama:11435",
|
|
cache=Settings().model_dump()["cache"] | {"enabled": False},
|
|
)
|
|
|
|
|
|
class FakeVLMClient(BaseVLMClient):
|
|
"""Test double that returns canned responses based on prompt content."""
|
|
|
|
def __init__(self, responses: dict[str, str] | None = None) -> None:
|
|
super().__init__(Settings())
|
|
self.responses = responses or {}
|
|
self.calls: list[dict[str, Any]] = []
|
|
|
|
async def complete(
|
|
self,
|
|
system_prompt: str,
|
|
user_prompt: str,
|
|
images: list[Image.Image],
|
|
response_format: type[Any] | None = None,
|
|
temperature: float = 0.1,
|
|
max_tokens: int = 4096,
|
|
model: str | None = None,
|
|
) -> VLMResponse:
|
|
self.calls.append(
|
|
{
|
|
"system_prompt": system_prompt,
|
|
"user_prompt": user_prompt,
|
|
"image_count": len(images),
|
|
"model": model,
|
|
}
|
|
)
|
|
for key, value in self.responses.items():
|
|
if key in system_prompt or key in user_prompt:
|
|
return VLMResponse(content=json.dumps(value), model="fake")
|
|
return VLMResponse(content=json.dumps({}), model="fake")
|