Merge pull request #207 from Eyobyb/fix/pypdf2

changed the pdfplumber with pypdf2

Author: Eyobyb

src/pyproject.toml

@@ -18,7 +18,8 @@ pinecone-client = "^2.2.2"
 beautifulsoup4 = "4.12.2"
 markdown = ">=3.4.4,<3.5.0"
 loguru = ">=0.7.0,<0.8.0"
-pdfplumber = "0.10.3"
+pypdf2 = "^3.0.1"
+
 
 
 [tool.poetry.group.test.dependencies]

src/sherpa_ai/utils.py

@@ -14,8 +14,7 @@
 import sherpa_ai.config as cfg
 from sherpa_ai.models.sherpa_base_model import SherpaOpenAI
 
-import pdfplumber
-
+import PyPDF2
 def load_files(files: List[str]) -> List[Document]:
     documents = []
     loader = None
@@ -247,7 +246,13 @@ def show_commands_only(logs):
 
 def extract_text_from_pdf(pdf_path):
     text = ""
-    with pdfplumber.open(pdf_path) as pdf:
-        for page in pdf.pages:
-            text += page.extract_text()
+    # Extract text from a PDF using PdfReader
+    pdf_file = open(pdf_path, "rb")
+    pdf_reader = PyPDF2.PdfReader(pdf_file)
+
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+
+    pdf_file.close()
     return text