curo1305
88c1ea297e
All feature containers now POST messages to ai-service (port 8010) instead of calling AI providers directly. ai-service routes to LM Studio, Ollama, or Anthropic based on /config/ai_service_config.json. doc-service AI providers removed; replaced by httpx ai_client.py. Backend settings restructured to /api/settings/ai. Frontend gets dedicated AIAdminSettingsPage and AI Service card in AppsPage. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
24 lines
1.0 KiB
Python
24 lines
1.0 KiB
Python
SYSTEM_PROMPT = (
|
|
"You are a financial document analysis assistant. "
|
|
"Given the text extracted from a PDF document, return ONLY a JSON object "
|
|
"with no markdown, no code fences, and no explanation."
|
|
)
|
|
|
|
USER_PROMPT_TEMPLATE = """Analyze the following document text and return a JSON object with exactly these keys:
|
|
document_type (one of: invoice, bill, receipt, order, expense, revenue, unknown),
|
|
total_amount (string or null),
|
|
currency (string or null),
|
|
vendor_name (string or null),
|
|
customer_name (string or null),
|
|
billing_address (string or null),
|
|
customer_address (string or null),
|
|
invoice_number (string or null),
|
|
invoice_date (string or null),
|
|
due_date (string or null),
|
|
tags (array of short keyword strings describing the document),
|
|
line_items (array of objects, each with keys: description, amount),
|
|
suggested_categories (array of 2 to 5 short category name strings a user might want to file this document under, e.g. "Utilities", "Travel", "Software Subscriptions", "Client Invoices").
|
|
|
|
Document text:
|
|
{text}"""
|