prevectorchunks-core 0.1.31__tar.gz → 0.1.32__tar.gz

{prevectorchunks_core-0.1.31/prevectorchunks_core.egg-info → prevectorchunks_core-0.1.32}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: prevectorchunks-core
-Version: 0.1.31
+Version: 0.1.32
 Summary: A Python module that allows conversion of a document into chunks to be inserted into Pinecone vector database
 Author-email: Zul Al-Kabir <zul.developer.2023@gmail.com>
 License: MIT License
@@ -49,6 +49,8 @@ Requires-Dist: weasyprint~=62.0
 Requires-Dist: lxml~=4.9.3
 Requires-Dist: cssselect2~=0.7.0
 Requires-Dist: cairocffi~=1.4.0
+Requires-Dist: tensorflow<3.0.0,>=2.15.0
+Requires-Dist: codecarbon>=2.3.0
 Dynamic: license-file
 
 # 📚 PreVectorChunks

prevectorchunks_core-0.1.32/prevectorchunks_core/services/DocuToImageConverter.py

@@ -0,0 +1,143 @@
+import os
+import tempfile
+import shutil
+import subprocess
+from pathlib import Path
+from PIL import Image
+import io
+import fitz
+from docx2pdf import convert as docx2pdf_convert
+from docx import Document
+from reportlab.pdfgen import canvas
+from reportlab.lib.pagesizes import A4
+import pypandoc
+
+# Ensure pandoc is available
+try:
+    pypandoc.get_pandoc_path()
+except OSError:
+    pypandoc.download_pandoc()
+
+class DocuToImageConverter:
+    """Converts a document (PDF, DOCX, DOC, image bytes) into a list of PIL images."""
+
+    def __init__(self):
+        pass
+
+    def _write_temp_file(self, input_bytes: bytes, suffix: str):
+        """Write bytes to a temporary file and return path."""
+        tmp_fd, tmp_path = tempfile.mkstemp(suffix=suffix)
+        with os.fdopen(tmp_fd, "wb") as f:
+            f.write(input_bytes)
+        return tmp_path
+
+    def _convert_doc_to_pdf(self, input_path: str) -> str:
+        """Convert DOC/DOCX file to PDF using Word COM, LibreOffice, Pandoc, or fallback."""
+        if not os.path.exists(input_path):
+            raise FileNotFoundError(input_path)
+
+        output_dir = tempfile.mkdtemp()
+        output_pdf = os.path.join(output_dir, Path(input_path).stem + ".pdf")
+
+        # 1️⃣ Microsoft Word COM automation (Windows only)
+        try:
+            import win32com.client
+            word = win32com.client.Dispatch("Word.Application")
+            word.Visible = False
+            doc = word.Documents.Open(str(Path(input_path).resolve()))
+            doc.SaveAs(str(Path(output_pdf).resolve()), FileFormat=17)
+            doc.Close()
+            word.Quit()
+            return output_pdf
+        except Exception:
+            pass
+
+        # 2️⃣ LibreOffice fallback
+        try:
+            subprocess.run(
+                ["soffice", "--headless", "--convert-to", "pdf", "--outdir", output_dir, input_path],
+                check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE
+            )
+            return output_pdf
+        except Exception:
+            pass
+
+        # 3️⃣ Pandoc fallback
+        try:
+            pdf_engine = "pdflatex" if shutil.which("pdflatex") else "wkhtmltopdf"
+            pypandoc.convert_file(input_path, "pdf", outputfile=output_pdf,
+                                  extra_args=["--standalone", f"--pdf-engine={pdf_engine}"])
+            return output_pdf
+        except Exception:
+            pass
+
+        # 4️⃣ Last resort: ReportLab plain text
+        doc = Document(input_path)
+        c = canvas.Canvas(output_pdf, pagesize=A4)
+        width, height = A4
+        y = height - 50
+        for p in doc.paragraphs:
+            c.drawString(50, y, p.text[:1000])
+            y -= 15
+            if y < 50:
+                c.showPage()
+                y = height - 50
+        c.save()
+        return output_pdf
+
+    def _convert_pdf_to_images(self, pdf_path: str, dpi: int = 200):
+        images = []
+        pdf_document = fitz.open(pdf_path)
+        for page_num in range(len(pdf_document)):
+            page = pdf_document[page_num]
+            pixmap = page.get_pixmap(dpi=dpi)
+            image = Image.frombytes("RGB", [pixmap.width, pixmap.height], pixmap.samples)
+            images.append(image)
+        pdf_document.close()
+        return images
+
+    def convert_to_images(self, file_path: str = None, input_bytes: bytes = None, dpi: int = 200, output_format: str = "PNG"):
+        """
+        Convert a file path or binary content to PIL images.
+        Supports PDF, DOC, DOCX, and image files.
+        """
+        if not file_path and not input_bytes:
+            raise ValueError("Provide either file_path or input_bytes.")
+
+        # Determine extension
+        if file_path:
+            ext = os.path.splitext(file_path)[1].lower()
+        elif input_bytes:
+            # Attempt to infer from first few bytes (simple)
+            if input_bytes[:4] == b"%PDF":
+                ext = ".pdf"
+            elif input_bytes[:2] == b"PK":
+                ext = ".docx"
+            else:
+                ext = ".img"  # Treat as generic image
+
+            # Write to temp file if doc/pdf
+            if ext in [".pdf", ".doc", ".docx"]:
+                file_path = self._write_temp_file(input_bytes, suffix=ext)
+
+        # Word → PDF
+        if ext in [".doc", ".docx"]:
+            pdf_path = self._convert_doc_to_pdf(file_path)
+            images = self._convert_pdf_to_images(pdf_path, dpi=dpi)
+
+        # PDF → images
+        elif ext == ".pdf":
+            images = self._convert_pdf_to_images(file_path, dpi=dpi)
+
+        # Image
+        elif ext in [".jpg", ".jpeg", ".png", ".bmp", ".tiff", ".img"]:
+            image = Image.open(io.BytesIO(input_bytes) if input_bytes else file_path).convert("RGB")
+            buffer = io.BytesIO()
+            image.save(buffer, format=output_format)
+            buffer.seek(0)
+            images = [Image.open(buffer)]
+
+        else:
+            raise ValueError("Unsupported file type.")
+
+        return images

{prevectorchunks_core-0.1.31 → prevectorchunks_core-0.1.32}/prevectorchunks_core/services/markdown_and_chunk_documents.py

@@ -23,7 +23,7 @@ load_dotenv(override=True)
 class BaseDocumentStrategy:
     """Defines a standard interface for all document processing strategies."""
 
-    def process(self, file_path: str):
+    def process(self, file_path: str, input_bytes: bytes = None):
         raise NotImplementedError("process() must be implemented by subclasses")
 
 
@@ -31,7 +31,7 @@ class BaseDocumentStrategy:
 # PDF Strategy
 # -----------------------------
 class PDFStrategy(BaseDocumentStrategy):
-    def process(self, file_path: str):
+    def process(self, file_path: str, input_bytes: bytes = None):
         print(f"📄 Using PDFStrategy for {file_path}")
         converter = DocuToImageConverter()
         # Example: detect multi-column layout or extract embedded text first
@@ -52,7 +52,7 @@ class PDFStrategy(BaseDocumentStrategy):
 # Word Strategy
 # -----------------------------
 class WordStrategy(BaseDocumentStrategy):
-    def process(self, file_path: str):
+    def process(self, file_path: str, input_bytes: bytes = None):
         file_path = Path(file_path)
 
         print(f"📝 Using WordStrategy for {file_path}")
@@ -72,7 +72,7 @@ class WordStrategy(BaseDocumentStrategy):
 # Image Strategy
 # -----------------------------
 class ImageStrategy(BaseDocumentStrategy):
-    def process(self, file_path: str):
+    def process(self, file_path: str, input_bytes: bytes = None):
         print(f"🖼️ Using ImageStrategy for {file_path}")
         image = Image.open(file_path).convert("RGB")
         return [image]
@@ -109,14 +109,14 @@ class MarkdownAndChunkDocuments:
         self.api_key = os.getenv("OPENAI_API_KEY")
         self.extractor = DocuToMarkdownExtractor(api_key=self.api_key)
 
-    def markdown_and_chunk_documents(self, file_path: str,include_image:bool):
+    def markdown_and_chunk_documents(self, file_path: str, input_bytes: bytes = None, include_image:bool=None):
         # Pick strategy
         strategy = StrategyFactory.get_strategy(file_path)
         if not strategy:
             raise ValueError(f"Unsupported file type: {file_path}")
 
         # Convert to images using correct strategy
-        images = strategy.process(file_path)
+        images = strategy.process(file_path, input_bytes)
 
         # Extract Markdown from images
         markdown_output, text_content = self.extractor.extract_markdown(images, include_image=include_image)

{prevectorchunks_core-0.1.31 → prevectorchunks_core-0.1.32/prevectorchunks_core.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: prevectorchunks-core
-Version: 0.1.31
+Version: 0.1.32
 Summary: A Python module that allows conversion of a document into chunks to be inserted into Pinecone vector database
 Author-email: Zul Al-Kabir <zul.developer.2023@gmail.com>
 License: MIT License
@@ -49,6 +49,8 @@ Requires-Dist: weasyprint~=62.0
 Requires-Dist: lxml~=4.9.3
 Requires-Dist: cssselect2~=0.7.0
 Requires-Dist: cairocffi~=1.4.0
+Requires-Dist: tensorflow<3.0.0,>=2.15.0
+Requires-Dist: codecarbon>=2.3.0
 Dynamic: license-file
 
 # 📚 PreVectorChunks

{prevectorchunks_core-0.1.31 → prevectorchunks_core-0.1.32}/prevectorchunks_core.egg-info/requires.txt

@@ -35,3 +35,5 @@ weasyprint~=62.0
 lxml~=4.9.3
 cssselect2~=0.7.0
 cairocffi~=1.4.0
+tensorflow<3.0.0,>=2.15.0
+codecarbon>=2.3.0

{prevectorchunks_core-0.1.31 → prevectorchunks_core-0.1.32}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "prevectorchunks-core"
-version = "0.1.31"
+version = "0.1.32"
 description = "A Python module that allows conversion of a document into chunks to be inserted into Pinecone vector database"
 readme = "README.md"
 license = { file = "LICENSE" }
@@ -50,7 +50,9 @@ dependencies = [
     "weasyprint~=62.0",
     "lxml~=4.9.3",
     "cssselect2~=0.7.0",
-    "cairocffi~=1.4.0"
+    "cairocffi~=1.4.0",
+    "tensorflow>=2.15.0,<3.0.0",   # <-- Add this
+    "codecarbon>=2.3.0"            # <-- Add this
 ]
 
 [tool.setuptools.packages.find]

prevectorchunks_core-0.1.31/prevectorchunks_core/services/DocuToImageConverter.py

@@ -1,148 +0,0 @@
-import os
-import shutil
-import subprocess
-import sys
-import tempfile
-from pathlib import Path
-
-import pypandoc
-from PIL import Image
-import io
-from docx2pdf import convert as docx_to_pdf
-import fitz
-from docx2pdf import convert as docx2pdf_convert
-try:
-    pypandoc.get_pandoc_path()
-except OSError:
-    print("Pandoc not found — downloading it temporarily...")
-    pypandoc.download_pandoc()
-
-class DocuToImageConverter:
-    """Converts a document (PDF, DOCX, DOC) into a list of PIL images."""
-
-    def __init__(self):
-        pass
-
-    def _convert_doc_to_pdf(self, input_path: str) -> str:
-        import os, tempfile, shutil, subprocess
-        from pathlib import Path
-
-        if not os.path.exists(input_path):
-            raise FileNotFoundError(input_path)
-
-        output_dir = tempfile.mkdtemp()
-        output_pdf = os.path.join(output_dir, Path(input_path).stem + ".pdf")
-
-        # 1️⃣ Try Microsoft Word COM automation (Windows only)
-        try:
-            import win32com.client
-            word = win32com.client.Dispatch("Word.Application")
-            word.Visible = False
-            doc = word.Documents.Open(str(Path(input_path).resolve()))
-            doc.SaveAs(str(Path(output_pdf).resolve()), FileFormat=17)  # 17 = wdFormatPDF
-            doc.Close()
-            word.Quit()
-            print("✅ Word COM conversion successful:", output_pdf)
-            return output_pdf
-        except Exception as e:
-            print("⚠️ Word COM conversion failed:", e)
-
-        # 2️⃣ Fallback: LibreOffice (cross-platform, preserves layout)
-        try:
-            # Requires LibreOffice installed and in PATH
-            subprocess.run(
-                ["soffice", "--headless", "--convert-to", "pdf", "--outdir", output_dir, input_path],
-                check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE
-            )
-            print("✅ LibreOffice conversion successful:", output_pdf)
-            return output_pdf
-        except Exception as e:
-            print("⚠️ LibreOffice conversion failed:", e)
-
-        # 3️⃣ Fallback: Pandoc (simpler, loses layout)
-        try:
-            import pypandoc
-            def which(cmd):
-                return shutil.which(cmd) is not None
-
-            pdf_engine = "pdflatex" if which("pdflatex") else "wkhtmltopdf"
-            pypandoc.convert_file(
-                input_path, "pdf", outputfile=output_pdf,
-                extra_args=["--standalone", f"--pdf-engine={pdf_engine}"]
-            )
-            print("✅ Pandoc conversion successful:", output_pdf)
-            return output_pdf
-        except Exception as e:
-            print("⚠️ Pandoc conversion failed:", e)
-
-        # 4️⃣ Last resort: ReportLab basic text (no formatting)
-        from reportlab.pdfgen import canvas
-        from reportlab.lib.pagesizes import A4
-        from docx import Document
-
-        doc = Document(input_path)
-        c = canvas.Canvas(output_pdf, pagesize=A4)
-        width, height = A4
-        y = height - 50
-        for p in doc.paragraphs:
-            c.drawString(50, y, p.text[:1000])
-            y -= 15
-            if y < 50:
-                c.showPage()
-                y = height - 50
-        c.save()
-        print("⚠️ Fallback to plain ReportLab text output:", output_pdf)
-        return output_pdf
-
-    def _convert_pdf_to_images(self, pdf_path: str, dpi: int = 200):
-        """
-        Converts each page of a PDF into images using PyMuPDF directly.
-        """
-        images = []
-
-        try:
-            pdf_document = fitz.open(pdf_path)  # Use `PyMuPDF` instead of fitz alias
-            for page_num in range(len(pdf_document)):
-                page = pdf_document[page_num]
-                # Render page to a pixmap with the specified DPI
-                pixmap = page.get_pixmap(dpi=dpi)
-                # Convert pixmap to an Image object using PIL
-                image = Image.frombytes("RGB", [pixmap.width, pixmap.height], pixmap.samples)
-                images.append(image)
-            pdf_document.close()
-        except Exception as e:
-            raise RuntimeError(f"Failed to convert PDF to images: {e}")
-
-        return images
-
-    def convert_to_images(self, file_path: str, dpi: int = 200, output_format: str = "PNG"):
-        """
-        Converts each page of a document into a list of PIL images.
-        Supports .pdf, .doc, .docx, and image files (.jpg, .png, etc.)
-        Ensures all outputs are in a consistent image format.
-        """
-        ext = os.path.splitext(file_path)[1].lower()
-
-        # Convert Word → PDF first
-        if ext in [".doc", ".docx"]:
-            pdf_path = self._convert_doc_to_pdf(file_path)
-            images = self._convert_pdf_to_images(pdf_path, dpi=dpi)
-
-        # Convert PDF → list of images
-        elif ext == ".pdf":
-            images = self._convert_pdf_to_images(file_path, dpi=dpi)
-
-        # Handle already an image file
-        elif ext in [".jpg", ".jpeg", ".png", ".bmp", ".tiff"]:
-            image = Image.open(file_path).convert("RGB")
-            # Convert to consistent format (e.g., PNG or JPEG in memory)
-            buffer = io.BytesIO()
-            image.save(buffer, format=output_format)
-            buffer.seek(0)
-            converted_image = Image.open(buffer)
-            images = [converted_image]
-
-        else:
-            raise ValueError("Unsupported file type. Use .pdf, .doc, .docx, or image files")
-
-        return images