Add more tools

agent.py

@@ -14,7 +14,7 @@ from supabase.client import Client, create_client
 from tools.math_tools import add, subtract, multiply, divide, modulus, power, sqrt
 from tools.search_tools import search_wikipedia, web_search, arxiv_search
 from tools.image_video_tools import query_image
-from tools.file_tools import analyze_excel_file, execute_python_code
+from tools.file_tools import analyze_excel_file, execute_python_code, analyze_csv_file, save_and_read_file, download_file_from_url, extract_text_from_image
 
 system_prompt = Path("system_prompt.txt").read_text()
 
@@ -43,7 +43,10 @@ def build_graph():
         max_retries=2,
         google_api_key=os.getenv("GOOGLE_API_KEY")  # Get API key from environment variable
         )
-    tools = [add, subtract, multiply, divide, modulus, power, sqrt, web_search, arxiv_search, search_wikipedia, query_image, analyze_excel_file, execute_python_code]
+    tools = [add, subtract, multiply, divide, modulus, power, sqrt, 
+             web_search, arxiv_search, search_wikipedia, 
+             query_image, 
+             analyze_excel_file, execute_python_code, analyze_csv_file, save_and_read_file, download_file_from_url, extract_text_from_image]
 
     llm_with_tools = llm.bind_tools(tools)
 

pyproject.toml

@@ -15,6 +15,7 @@ dependencies = [
     "langgraph>=0.4.3",
     "openai-whisper>=20240930",
     "pandas>=2.2.3",
+    "pytesseract>=0.3.13",
     "requests>=2.32.3",
     "supabase>=2.15.1",
     "torch==2.2.2",

requirements.txt

@@ -18,4 +18,5 @@ pymupdf
 wikipedia
 pgvector
 python-dotenv
-openai-whisper
+openai-whisper
+pytesseract

tools/file_tools.py

@@ -1,20 +1,29 @@
 import io
 import os
+import tempfile
+from typing import Optional
+from urllib.parse import urlparse
+import uuid
 import pandas as pd
 import contextlib
 from langchain_core.tools import tool
 from langchain_google_genai import ChatGoogleGenerativeAI
+import requests
 import whisper
+from PIL import Image
+import pytesseract
+
 
 # Load Whisper model once
 whisper_model = whisper.load_model("base")  # or "small", "medium", "large"
 
 @tool
-def analyze_excel_file(file_path: str) -> str:
+def analyze_excel_file(file_path: str, query: str) -> str:
     """
-    Provides summary statistics for an Excel file.
+    Analyze an Excel file using pandas and answer a question about it.
     Args:
         file_path (str): the path to the Excel file.
+        query (str): Question about the data
     """
     try:
         # Read the Excel file
@@ -36,6 +45,7 @@ def analyze_excel_file(file_path: str) -> str:
         return f"Error analyzing Excel file: {str(e)}"
 
 
+
 @tool
 def process_mp3_file(file_path: str, query: str) -> str:
     """
@@ -97,3 +107,105 @@ def execute_python_code(code: str) -> str:
         return "Code executed successfully, but produced no output."
     except Exception as e:
         return f"Error executing code: {e}"
+
+
+
+@tool
+def save_and_read_file(content: str, filename: Optional[str] = None) -> str:
+    """
+    Save content to a file and return the path.
+    Args:
+        content (str): the content to save to the file
+        filename (str, optional): the name of the file. If not provided, a random name file will be created.
+    """
+    temp_dir = tempfile.gettempdir()
+    if filename is None:
+        temp_file = tempfile.NamedTemporaryFile(delete=False, dir=temp_dir)
+        filepath = temp_file.name
+    else:
+        filepath = os.path.join(temp_dir, filename)
+
+    with open(filepath, "w") as f:
+        f.write(content)
+
+    return f"File saved to {filepath}. You can read this file to process its contents."
+
+
+@tool
+def download_file_from_url(url: str, filename: Optional[str] = None) -> str:
+    """
+    Download a file from a URL and save it to a temporary location.
+    Args:
+        url (str): the URL of the file to download.
+        filename (str, optional): the name of the file. If not provided, a random name file will be created.
+    """
+    try:
+        # Parse URL to get filename if not provided
+        if not filename:
+            path = urlparse(url).path
+            filename = os.path.basename(path)
+            if not filename:
+                filename = f"downloaded_{uuid.uuid4().hex[:8]}"
+
+        # Create temporary file
+        temp_dir = tempfile.gettempdir()
+        filepath = os.path.join(temp_dir, filename)
+
+        # Download the file
+        response = requests.get(url, stream=True)
+        
+        response.raise_for_status()
+
+        # Save the file
+        with open(filepath, "wb") as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+
+        return f"File downloaded to {filepath}. You can read this file to process its contents."
+    except Exception as e:
+        return f"Error downloading file: {str(e)}"
+
+
+@tool
+def extract_text_from_image(image_path: str) -> str:
+    """
+    Extract text from an image using OCR library pytesseract (if available).
+    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)}"
+
+
+@tool
+def analyze_csv_file(file_path: str, query: str) -> str:
+    """
+    Analyze a CSV file using pandas and answer a question about it.
+    Args:
+        file_path (str): the path to the CSV file.
+        query (str): Question about the data
+    """
+    try:
+        # Read the CSV file
+        df = pd.read_csv(file_path)
+
+        # Run various analyses based on the query
+        result = f"CSV file loaded with {len(df)} rows and {len(df.columns)} columns.\n"
+        result += f"Columns: {', '.join(df.columns)}\n\n"
+
+        # Add summary statistics
+        result += "Summary statistics:\n"
+        result += str(df.describe())
+
+        return result
+
+    except Exception as e:
+        return f"Error analyzing CSV file: {str(e)}"

uv.lock

@@ -370,6 +370,7 @@ dependencies = [
     { name = "langgraph" },
     { name = "openai-whisper" },
     { name = "pandas" },
+    { name = "pytesseract" },
     { name = "requests" },
     { name = "supabase" },
     { name = "torch" },
@@ -388,6 +389,7 @@ requires-dist = [
     { name = "langgraph", specifier = ">=0.4.3" },
     { name = "openai-whisper", specifier = ">=20240930" },
     { name = "pandas", specifier = ">=2.2.3" },
+    { name = "pytesseract", specifier = ">=0.3.13" },
     { name = "requests", specifier = ">=2.32.3" },
     { name = "supabase", specifier = ">=2.15.1" },
     { name = "torch", specifier = "==2.2.2" },
@@ -1782,6 +1784,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/61/ad/689f02752eeec26aed679477e80e632ef1b682313be70793d798c1d5fc8f/PyJWT-2.10.1-py3-none-any.whl", hash = "sha256:dcdd193e30abefd5debf142f9adfcdd2b58004e644f25406ffaebd50bd98dacb", size = 22997 },
 ]
 
+[[package]]
+name = "pytesseract"
+version = "0.3.13"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "packaging" },
+    { name = "pillow" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/9f/a6/7d679b83c285974a7cb94d739b461fa7e7a9b17a3abfd7bf6cbc5c2394b0/pytesseract-0.3.13.tar.gz", hash = "sha256:4bf5f880c99406f52a3cfc2633e42d9dc67615e69d8a509d74867d3baddb5db9", size = 17689 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7a/33/8312d7ce74670c9d39a532b2c246a853861120486be9443eebf048043637/pytesseract-0.3.13-py3-none-any.whl", hash = "sha256:7a99c6c2ac598360693d83a416e36e0b33a67638bb9d77fdcac094a3589d4b34", size = 14705 },
+]
+
 [[package]]
 name = "pytest"
 version = "8.3.5"