KittenEli commited on
Commit
6bb4b14
·
verified ·
1 Parent(s): ae7a494

Add extract_text_from_pdf tool

Browse files
Files changed (1) hide show
  1. app.py +9 -20
app.py CHANGED
@@ -7,31 +7,20 @@ from tools.final_answer import FinalAnswerTool
7
 
8
  from Gradio_UI import GradioUI
9
 
10
- # Below is an example of a tool that does nothing. Amaze us with your creativity !
11
- @tool
12
- def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
13
- #Keep this format for the description / args / args description but feel free to modify the tool
14
- """A tool that does nothing yet
15
- Args:
16
- arg1: the first argument
17
- arg2: the second argument
18
- """
19
- return "What magic will you build ?"
20
 
21
  @tool
22
- def get_current_time_in_timezone(timezone: str) -> str:
23
- """A tool that fetches the current local time in a specified timezone.
24
  Args:
25
- timezone: A string representing a valid timezone (e.g., 'America/New_York').
26
  """
27
  try:
28
- # Create timezone object
29
- tz = pytz.timezone(timezone)
30
- # Get current time in that timezone
31
- local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
32
- return f"The current local time in {timezone} is: {local_time}"
33
  except Exception as e:
34
- return f"Error fetching time for timezone '{timezone}': {str(e)}"
35
 
36
 
37
  final_answer = FinalAnswerTool()
@@ -55,7 +44,7 @@ with open("prompts.yaml", 'r') as stream:
55
 
56
  agent = CodeAgent(
57
  model=model,
58
- tools=[final_answer], ## add your tools here (don't remove final answer)
59
  max_steps=6,
60
  verbosity_level=1,
61
  grammar=None,
 
7
 
8
  from Gradio_UI import GradioUI
9
 
 
 
 
 
 
 
 
 
 
 
10
 
11
  @tool
12
+ def extract_text_from_pdf(file_path: str) -> str:
13
+ """Reads a PDF file and extracts its text.
14
  Args:
15
+ file_path: The path to the PDF file.
16
  """
17
  try:
18
+ with open(file_path, "rb") as file:
19
+ reader = PyPDF2.PdfReader(file)
20
+ text = "\n".join([page.extract_text() for page in reader.pages if page.extract_text()])
21
+ return text if text else "No text found in the PDF."
 
22
  except Exception as e:
23
+ return f"Error reading PDF: {str(e)}"
24
 
25
 
26
  final_answer = FinalAnswerTool()
 
44
 
45
  agent = CodeAgent(
46
  model=model,
47
+ tools=[final_answer, extract_text_from_pdf], ## add your tools here (don't remove final answer)
48
  max_steps=6,
49
  verbosity_level=1,
50
  grammar=None,