doc-to-vector-dataset-generator

Doc-to-Vector Dataset Generator

Transform documents into high-quality vector search datasets.

Pipeline Steps

1. Extract text from various formats (PDF, DOCX, HTML)
2. Clean text (remove noise, normalize)
3. Chunk strategically (semantic boundaries)
4. Add metadata (source, timestamps, classification)
5. Deduplicate (near-duplicate detection)
6. Quality check (length, content validation)
7. Export JSONL (one chunk per line)

Text Extraction

# PDF extraction
import pymupdf

def extract_pdf(filepath: str) -> str:
    doc = pymupdf.open(filepath)
    text = ""
    for page in doc:
        text += page.get_text()
    return text

# Markdown extraction
def extract_markdown(filepath: str) -> str:
    with open(filepath) as f:
        return f.read()

Text Cleaning

import re

def clean_text(text: str) -> str:
    # Remove extra whitespace
    text = re.sub(r'\s+', ' ', text)

    # Remove page numbers
    text = re.sub(r'Page \d+', '', text)

    # Remove URLs (optional)
    text = re.sub(r'http\S+', '', text)

    # Normalize unicode
    text = text.encode('utf-8', 'ignore').decode('utf-8')

    return text.strip()

Semantic Chunking

def semantic_chunk(text: str, max_chunk_size: int = 1000) -> List[str]:
    """Chunk at semantic boundaries (paragraphs, sentences)"""
    # Split by paragraphs first
    paragraphs = text.split('\n\n')

    chunks = []
    current_chunk = ""

    for para in paragraphs:
        if len(current_chunk) + len(para) <= max_chunk_size:
            current_chunk += para + "\n\n"
        else:
            if current_chunk:
                chunks.append(current_chunk.strip())
            current_chunk = para + "\n\n"

    if current_chunk:
        chunks.append(current_chunk.strip())

    return chunks

Metadata Extraction

def extract_metadata(filepath: str, chunk: str, chunk_idx: int) -> dict:
    return {
        "source": filepath,
        "chunk_id": f"{hash(filepath)}_{chunk_idx}",
        "chunk_index": chunk_idx,
        "char_count": len(chunk),
        "word_count": len(chunk.split()),
        "created_at": datetime.now().isoformat(),

        # Content classification
        "has_code": bool(re.search(r'```|def |class |function', chunk)),
        "has_table": bool(re.search(r'\|.*\|', chunk)),
        "language": detect_language(chunk),
    }