barn

app.py

@@ -1,6 +1,6 @@
 import os
 import base64
-from pdfminer.high_level import extract_text
+import fitz  # PyMuPDF
 from langchain_core.prompts import PromptTemplate
 from google.cloud import aiplatform
 from google.cloud.aiplatform_v1 import ModelServiceClient
@@ -20,7 +20,7 @@ documents = [
     Document(content_type="application/pdf", data=base64.b64decode("JVBERi0xLj+CnN0YXJ0eHJlZgoyMTk5MDYKJSVFT0YK")),
     Document(content_type="application/pdf", data=base64.b64decode("JVBERi0xLjQKJiUlRU9GCg==")),
     Document(content_type="application/pdf", data=base64.b64decode("JVBERi0xLjQKJe90IDMwOCAwIFIvU2l6ZSAzMTg+PgpzdGFydHhyZWYKMjcwNzU3CiUlRU9GCg==")),
-    Document(content_type="application/pdf", data=base64.b64decode("JVBERi0xLjUNJeLjz9MNCjcgMCBvYmoNPDwvTGluZWFyaXplZCAxL0wgNjc1NzgvTyA5L0UgNjAyNDYvTiAxL1QgNjcyODcvSCBbIDQ4MyAxNTRdPj4NZW5kb2JxDSAgICAgICAgICAgICAgICAgICAgDQoyMiAwIG9iag08PC9EZWNvZGVQYXJtczw8L0NvbHVtbnMgNC9QcmVkaWN0b3IgMTI+Pi9GaWx0ZXIvRmxhdGVEZWNvZGUvSURbPDE3NzU4MkJFODc4MzRFQjNBOEM3RkIzQTgyRjFFMEFCPjw5MzI2Qjk4REM4NjQ2RTRCODI3MzZFQUEzOENEQjFBQj5dL0luZGV4WzcgMjhdL0luZm8gNiAwIFIvTGVuZ3RoIDgzL1ByZXYgNjcyODgvUm9vdCA4IDAgUi9TaXplIDM1L1R5cGUvWFPRg0K"))
+    Document(content_type="application/pdf", data=base64.b64decode("JVBERi0xLjUNJeLjz9MNCjcgMCBvYmoNPDwvTGluZWFyaXplZCAxL0wgNjc1NzgvTyA5L0UgNjAyNDYvTiAxL1QgNjcyODcvSCBbIDQ4MyAxNTRdPj4NZW5kb2JqDSAgICAgICAgICAgICAgICAgICAgDQoyMiAwIG9iag08PC9EZWNvZGVQYXJtczw8L0NvbHVtbnMgNC9QcmVkaWN0b3IgMTI+Pi9GaWx0ZXIvRmxhdGVEZWNvZGUvSURbPDE3NzU4MkJFODc4MzRFQjNBOEM3RkIzQTgyRjFFMEFCPjw5MzI2Qjk4REM4NjQ2RTRCODI3MzZFQUEzOENEQjFBQj5dL0luZGV4WzcgMjhdL0luZm8gNiAwIFIvTGVuZ3RoIDgzL1ByZXYgNjcyODgvUm9vdCA4IDAgUi9TaXplIDM1L1R5cGUvWFPRg0K"))
 ]
 
 text1 = """
@@ -109,8 +109,12 @@ if uploaded_file is not None:
     file_details = {"FileName": uploaded_file.name, "FileType": uploaded_file.type}
     st.write(file_details)
     
-    # Display the content of the uploaded file
-    content = extract_text(uploaded_file)
+    # Extract text from the uploaded PDF file
+    pdf_document = fitz.open(stream=uploaded_file.read(), filetype="pdf")
+    content = ""
+    for page_num in range(len(pdf_document)):
+        page = pdf_document.load_page(page_num)
+        content += page.get_text()
     st.text(content)
 
     # Placeholder for user inputs