upload_ingest.py

\
import os
from typing import List, Tuple
import pdfplumber
from docx import Document as DocxDocument
from PIL import Image
import pytesseract

TEXT_EXT = {".txt", ".md", ".csv"}
DOCX_EXT = {".docx"}
PDF_EXT = {".pdf"}
IMG_EXT  = {".png", ".jpg", ".jpeg", ".webp"}

def _read_text_file(path: str) -> str:
    return open(path, "r", encoding="utf-8", errors="ignore").read()

def _read_docx(path: str) -> str:
    doc = DocxDocument(path)
    return "\n".join([p.text for p in doc.paragraphs])

def _read_pdf(path: str) -> str:
    out = []
    with pdfplumber.open(path) as pdf:
        for p in pdf.pages:
            out.append(p.extract_text() or "")
    return "\n".join(out)

def _read_image_ocr(path: str) -> str:
    img = Image.open(path)
    return pytesseract.image_to_string(img)

def extract_text_from_files(filepaths: List[str]) -> List[Tuple[str, str]]:
    results = []
    for fp in filepaths:
        _, ext = os.path.splitext(fp.lower())
        try:
            if ext in TEXT_EXT:
                txt = _read_text_file(fp)
            elif ext in DOCX_EXT:
                txt = _read_docx(fp)
            elif ext in PDF_EXT:
                txt = _read_pdf(fp)
            elif ext in IMG_EXT:
                txt = _read_image_ocr(fp)
            else:
                txt = ""
            if txt and txt.strip():
                results.append((os.path.basename(fp), txt))
        except Exception:
            continue
    return results