host.today/ht-docker-ai
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Jürgen Kunz
2026-01-19 21:19:37 +00:00
parent 235aa1352b
commit 09770d3177
4 changed files with 58 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
test/test.bankstatements.nanonets.ts
View File

@@ -51,11 +51,21 @@ 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 = `Extract ALL transactions from this bank statement as JSON array. Each transaction: {"date": "YYYY-MM-DD", "counterparty": "NAME", "amount": -25.99}. Amount negative for debits, positive for credits. Only include actual transactions, not balances. Return ONLY JSON array, no explanation.
// JSON extraction prompt for GPT-OSS 20B (sent AFTER the statement text is provided)
const JSON_EXTRACTION_PROMPT = `Extract ALL transactions from the bank statement. Return ONLY valid JSON array.
STATEMENT:
`;
WHERE TO FIND DATA:
- Transactions are typically in TABLES with columns: Date, Description/Counterparty, Debit, Credit, Balance
- Look for rows with actual money movements, NOT header rows or summary totals
RULES:
1. date: Convert to YYYY-MM-DD format
2. counterparty: The name/description of who the money went to/from
3. amount: NEGATIVE for debits/withdrawals, POSITIVE for credits/deposits
4. Only include actual transactions, NOT opening/closing balances
JSON array only:
[{"date":"YYYY-MM-DD","counterparty":"NAME","amount":-25.99}]`;
// Constants for smart batching
const MAX_VISUAL_TOKENS = 28000; // ~32K context minus prompt/output headroom
@@ -246,12 +256,8 @@ async function ensureExtractionModel(): Promise<boolean> {
*/
async function extractTransactionsFromMarkdown(markdown: string, queryId: string): Promise<ITransaction[]> {
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}] Statement: ${markdown.length} chars, Prompt: ${JSON_EXTRACTION_PROMPT.length} chars`);
const response = await fetch(`${OLLAMA_URL}/api/chat`, {
method: 'POST',
@@ -261,9 +267,15 @@ async function extractTransactionsFromMarkdown(markdown: string, queryId: string
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 a bank statement document:\n\n${markdown}` },
{ role: 'assistant', content: 'I have read the bank statement document you provided. I can see all the transaction data. 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 statements + thinking
temperature: 0, // Deterministic for JSON extraction
},
}),
signal: AbortSignal.timeout(600000), // 10 minute timeout
});