Add extract_text_from_image tool and update requirements

agent.py

@@ -28,6 +28,7 @@ from tools.square_root import square_root
 from tools.execute_code_multilang import execute_code_multilang
 from tools.save_read_file import save_read_file
 from tools.download_file import download_file
+from tools.extract_text_from_image import extract_text_from_image
 # from tools.audio_transcription import audio_transcription
 
 load_dotenv()
@@ -71,6 +72,7 @@ tools = [
     square_root,
     save_read_file,
     download_file,
+    extract_text_from_image,
     # audio_transcription,
 ]
 

requirements.txt

@@ -21,4 +21,5 @@ pymupdf
 wikipedia
 pgvector
 python-dotenv
-matplotlib
+matplotlib
+pytesseract

tools/extract_text_from_image.py

@@ -0,0 +1,21 @@
+import pytesseract
+from PIL import Image
+from langchain_core.tools import tool
+
+@tool
+def extract_text_from_image(image_path: str) -> str:
+    """
+    Extract text from an image in using the pytesseract library.
+    Args:
+        image_path (str): the path to the image file.
+    """
+    try:
+        # Open the image
+        image = Image.open(image_path)
+
+        # Extract text from the image
+        text = pytesseract.image_to_string(image)
+
+        return f"Extracted text from image:\n\n{text}"
+    except Exception as e:
+        return f"Error extracting text from image: {str(e)}"