Get Document Content

{
  "success": true,
  "chunks": [
    {
      "chunk_text": "Welcome to our company handbook. This document outlines our policies, procedures, and company culture. Our mission is to provide exceptional service while maintaining a positive work environment.",
      "chunk_index": 0
    },
    {
      "chunk_text": "Employee Benefits: We offer comprehensive health insurance, 401(k) matching, unlimited PTO, and professional development opportunities. All employees are eligible for benefits after 30 days of employment.",
      "chunk_index": 1
    },
    {
      "chunk_text": "Work Schedule: Our standard work week is Monday through Friday, 9 AM to 5 PM. Remote work options are available for eligible positions. Please discuss flexible arrangements with your manager.",
      "chunk_index": 2
    }
  ],
  "content": "Welcome to our company handbook. This document outlines our policies, procedures, and company culture. Our mission is to provide exceptional service while maintaining a positive work environment.\n\n---\n\nEmployee Benefits: We offer comprehensive health insurance, 401(k) matching, unlimited PTO, and professional development opportunities. All employees are eligible for benefits after 30 days of employment.\n\n---\n\nWork Schedule: Our standard work week is Monday through Friday, 9 AM to 5 PM. Remote work options are available for eligible positions. Please discuss flexible arrangements with your manager.",
  "chunk_count": 3
}

{
  "success": false,
  "error": "Error al obtener contenido del documento"
}

{
  "success": true,
  "chunks": [],
  "content": "",
  "chunk_count": 0
}

$chunks = $db->fetchAll(
    'SELECT chunk_text, chunk_index FROM vectors WHERE document_id = :id ORDER BY chunk_index ASC',
    [':id' => $id]
);

$content = implode("\n\n---\n\n", array_column($chunks, 'chunk_text'));

const { content, chunk_count } = await fetch(
  `/api/get-document-content?id=${docId}`
).then(r => r.json());

// Show first 500 characters as preview
const preview = content.substring(0, 500) + '...';
console.log(`Preview (${chunk_count} chunks total):\n${preview}`);

const { chunks } = await fetch(
  `/api/get-document-content?id=${docId}`
).then(r => r.json());

const chunkLengths = chunks.map(c => c.chunk_text.length);
const avgLength = chunkLengths.reduce((a, b) => a + b, 0) / chunks.length;
const maxLength = Math.max(...chunkLengths);
const minLength = Math.min(...chunkLengths);

console.log(`Avg: ${avgLength}, Min: ${minLength}, Max: ${maxLength}`);

const { chunks } = await fetch(
  `/api/get-document-content?id=${docId}`
).then(r => r.json());

// Find chunks containing specific keywords
const keyword = 'pricing';
const relevantChunks = chunks.filter(c => 
  c.chunk_text.toLowerCase().includes(keyword)
);

console.log(`Found "${keyword}" in ${relevantChunks.length} chunks:`);
relevantChunks.forEach(c => {
  console.log(`  Chunk ${c.chunk_index}: ${c.chunk_text.substring(0, 100)}...`);
});

const { content } = await fetch(
  `/api/get-document-content?id=${docId}`
).then(r => r.json());

const blob = new Blob([content], { type: 'text/plain' });
const url = URL.createObjectURL(blob);

const a = document.createElement('a');
a.href = url;
a.download = 'document-content.txt';
a.click();

async function searchInDocument(docId, searchTerm) {
  const { chunks } = await fetch(
    `/api/get-document-content?id=${docId}`
  ).then(r => r.json());
  
  const results = chunks
    .map(chunk => ({
      index: chunk.chunk_index,
      text: chunk.chunk_text,
      matches: (chunk.chunk_text.match(
        new RegExp(searchTerm, 'gi')
      ) || []).length
    }))
    .filter(r => r.matches > 0)
    .sort((a, b) => b.matches - a.matches);
  
  return results;
}

const results = await searchInDocument(42, 'customer service');
console.log(`Found ${results.length} chunks with matches`);