feature : add PPTX data reader

README.md

@@ -299,7 +299,7 @@ The first part of the flow is to read data from a source.
 This can be a database, a csv file, a json file, a text file, a website, a pdf, a word document, an excel file, ...
 The only requirement is that you can read the data and that you can extract the text from it.
 
-For now we only support text files, pdf and docx but we plan to support other data type in the future.
+For now we only support text files, pdf, pptx and docx but we plan to support other data type in the future.
 
 You can use the [`FileDataReader`](src/Embeddings/DataReader/FileDataReader.php) class to read a file. It takes a path to a file or a directory as parameter.
 The second optional parameter is the class name of the entity that will be used to store the embedding.

composer.json

@@ -13,6 +13,7 @@
         "guzzlehttp/guzzle": "^7.4.5",
         "guzzlehttp/psr7": "^2.7",
         "openai-php/client": "^v0.7.7 || ^v0.8.4 || ^v0.9.2",
+        "phpoffice/phppresentation": "^1.1",
         "phpoffice/phpword": "^1.2.0",
         "psr/http-message": "^2.0",
         "smalot/pdfparser": "^2.7"

src/Embeddings/DataReader/FileDataReader.php

@@ -92,6 +92,12 @@ private function getContentFromFile(string $path): string|false
             return $docxReader->getText($path);
         }
 
+        if ($fileExtension === 'pptx') {
+            $pptxReader = new PptxReader();
+
+            return $pptxReader->getText($path);
+        }
+
         return file_get_contents($path);
     }
 

src/Embeddings/DataReader/PptxReader.php

@@ -0,0 +1,33 @@
+<?php
+
+namespace LLPhant\Embeddings\DataReader;
+
+use PhpOffice\PhpPresentation\Shape\RichText;
+use PhpOffice\PhpPresentation\IOFactory;
+
+class PptxReader
+{
+    public function getText(string $path): string
+    {
+        $reader = IOFactory::createReader('PowerPoint2007');
+        $ppt = $reader->load($path);
+        $fullText = '';
+
+        foreach ($ppt->getAllSlides() as $slideIndex => $slide) {
+            $fullText .= "Slide " . ($slideIndex + 1) . ": ";
+            foreach ($slide->getShapeCollection() as $shape) {
+                if ($shape instanceof RichText) {
+                    foreach ($shape->getParagraphs() as $paragraph) {
+                        $text = '';
+                        foreach ($paragraph->getRichTextElements() as $element) {
+                            $text .= $element->getText();
+                        }
+                        $fullText .= $text . " ";
+                    }
+                }
+            }
+        }
+
+        return $fullText;
+    }
+}

tests/Unit/Embeddings/DataReader/FileDataReaderTest.php

@@ -19,6 +19,7 @@
     ['document-with-text-breaks.docx', 'Sample document with text breaks'],
     ['simple_document_with_links.docx', 'This is a doc with links'],
     ['data-pdf.pdf', 'This data is from a pdf'],
+    ['powerpoint.pptx', 'Slide 1'],
 ]);
 
 it('can read pdf and texts ', function () {