Pdf extractor

backend/src/PDFExtractor.py

@@ -0,0 +1,33 @@
+import fitz  # PyMuPDF library
+
+class PDFExtractor:
+    def __init__(self):
+        pass
+
+    @staticmethod
+    def extract_text_from_pdf(buffer: bytes) -> str:
+        """
+        Extract text content from a PDF file using a buffer object.
+
+        :param buffer: Bytes-like object containing the PDF file content.
+        :return: String containing the extracted text.
+        """
+        text = ""
+
+        try:
+            # Open the PDF file from the buffer
+            pdf_document = fitz.open(stream=buffer, filetype="pdf")
+
+            # Iterate through each page and extract text
+            for page_number in range(pdf_document.page_count):
+                page = pdf_document[page_number]
+                text += page.get_text()
+
+            # Close the PDF document
+            pdf_document.close()
+
+        except Exception as e:
+            # Handle exceptions (e.g., invalid PDF format)
+            text = f"Error extracting text: {str(e)}"
+
+        return text

backend/src/main.py

@@ -1,10 +1,19 @@
 import os
 import sys
-from ReplicateBot import ReplicateBot
+import json
+import threading
+
+from ReplicateBot import ReplicateBot, Message
 
 bot = ReplicateBot("mistralai/mixtral-8x7b-instruct-v0.1", os.getenv("REPLICATEKEY"))
 
-bot.Prompt(sys.argv[1])
-bot.Run()
+bot.Prompt(Message("user", sys.argv[1]))
+
+def Main():
+    bot.Run()
+
+t = threading.Thread(target=Main)
+t.run()
 
-print(bot.Results)
+while (True):
+    print(bot.States[-1].Result)