fix(extraction): improve JSON extraction prompts and model options for invoice and bank statement tests

This commit is contained in:
2026-01-19 21:19:37 +00:00
parent 235aa1352b
commit 09770d3177
4 changed files with 58 additions and 38 deletions

View File

@@ -54,31 +54,24 @@ If there is an image in the document and image caption is not present, add a sma
Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>.
Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number>.`;
// JSON extraction prompt for GPT-OSS 20B
const JSON_EXTRACTION_PROMPT = `You are an invoice data extractor. Below is an invoice document converted to text/markdown. Extract the key invoice fields as JSON.
// JSON extraction prompt for GPT-OSS 20B (sent AFTER the invoice text is provided)
const JSON_EXTRACTION_PROMPT = `Extract key fields from the invoice. Return ONLY valid JSON.
IMPORTANT RULES:
1. invoice_number: The unique invoice/document number (NOT VAT ID, NOT customer ID)
2. invoice_date: Format as YYYY-MM-DD
3. vendor_name: The company that issued the invoice
WHERE TO FIND DATA:
- invoice_number, invoice_date, vendor_name: Look in the HEADER section at the TOP of PAGE 1 (near "Invoice no.", "Invoice date:", "Rechnungsnummer")
- net_amount, vat_amount, total_amount: Look in the SUMMARY section at the BOTTOM (look for "Total", "Amount due", "Gesamtbetrag")
RULES:
1. invoice_number: Extract ONLY the value (e.g., "R0015632540"), NOT the label "Invoice no."
2. invoice_date: Convert to YYYY-MM-DD format (e.g., "14/04/2022" → "2022-04-14")
3. vendor_name: The company issuing the invoice
4. currency: EUR, USD, or GBP
5. net_amount: Amount before tax
6. vat_amount: Tax/VAT amount
7. total_amount: Final total (gross amount)
5. net_amount: Total before tax
6. vat_amount: Tax amount
7. total_amount: Final total with tax
Return ONLY this JSON format, no explanation:
{
"invoice_number": "INV-2024-001",
"invoice_date": "2024-01-15",
"vendor_name": "Company Name",
"currency": "EUR",
"net_amount": 100.00,
"vat_amount": 19.00,
"total_amount": 119.00
}
INVOICE TEXT:
`;
JSON only:
{"invoice_number":"X","invoice_date":"YYYY-MM-DD","vendor_name":"X","currency":"EUR","net_amount":0,"vat_amount":0,"total_amount":0}`;
// Constants for smart batching
const MAX_VISUAL_TOKENS = 28000; // ~32K context minus prompt/output headroom
@@ -370,12 +363,8 @@ function parseJsonToInvoice(response: string): IInvoice | null {
*/
async function extractInvoiceFromMarkdown(markdown: string, queryId: string): Promise<IInvoice | null> {
const startTime = Date.now();
const fullPrompt = JSON_EXTRACTION_PROMPT + markdown;
// Log exact prompt
console.log(`\n [${queryId}] ===== PROMPT =====`);
console.log(fullPrompt);
console.log(` [${queryId}] ===== END PROMPT (${fullPrompt.length} chars) =====\n`);
console.log(` [${queryId}] Invoice: ${markdown.length} chars, Prompt: ${JSON_EXTRACTION_PROMPT.length} chars`);
const response = await fetch(`${OLLAMA_URL}/api/chat`, {
method: 'POST',
@@ -385,9 +374,15 @@ async function extractInvoiceFromMarkdown(markdown: string, queryId: string): Pr
messages: [
{ role: 'user', content: 'Hi there, how are you?' },
{ role: 'assistant', content: 'Good, how can I help you today?' },
{ role: 'user', content: fullPrompt },
{ role: 'user', content: `Here is an invoice document:\n\n${markdown}` },
{ role: 'assistant', content: 'I have read the invoice document you provided. I can see all the text content. What would you like me to do with it?' },
{ role: 'user', content: JSON_EXTRACTION_PROMPT },
],
stream: true,
options: {
num_ctx: 32768, // Larger context for long invoices + thinking
temperature: 0, // Deterministic for JSON extraction
},
}),
signal: AbortSignal.timeout(600000), // 10 minute timeout for large documents
});