updated tools and requirements

agent.py

@@ -8,10 +8,10 @@ from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
 from langgraph.graph import START, MessagesState, StateGraph
 from langgraph.prebuilt import ToolNode, tools_condition
 
-from tools import (absolute, add, analyze_csv_file,  # extract_text_from_image,
-                   analyze_excel_file, arxiv_search, audio_transcription,
-                   compound_interest, convert_temperature, divide,
-                   download_file, exponential, factorial, floor_divide,
+from tools import (absolute, add, analyze_csv_file, analyze_excel_file,
+                   arxiv_search, audio_transcription, compound_interest,
+                   convert_temperature, divide, download_file, exponential,
+                   extract_text, factorial, floor_divide,
                    get_current_time_in_timezone, greatest_common_divisor,
                    is_prime, least_common_multiple, logarithm, modulus,
                    multiply, percentage_calculator, power, python_code_parser,
@@ -32,7 +32,7 @@ tools = [
     is_prime, least_common_multiple, percentage_calculator,
     wikipedia_search, analyze_excel_file, arxiv_search,
     audio_transcription, python_code_parser, analyze_csv_file,
-    # extract_text_from_image,
+    extract_text,
     reverse_sentence, web_content_extract,
     download_file,
 ]
@@ -73,13 +73,7 @@ You are an advanced AI agent equipped with multiple tools to solve complex, mult
    - **Plan multi-tool sequences** - many questions require 2-5 tools in various combinations
    - **Consider tool order flexibility** - tools can be used in any sequence that makes logical sense
    - **Validate tool choice** - ensure the selected tool is the optimal match for your needs
-   - Examples of multi-tool workflows:
-     - reserve_sentence -> read the reversed question and answer it.
-     - download_file -> analyze_csv_file -> add -> percentage_calculator
-     - reverse_sentence -> python_code_parser -> web_search -> extract_text_from_image
-     - arvix_search -> web_content_extract -> factorial -> roman_calculator_converter
-     - audio_transcription -> wikipedia_search -> compound_interest -> convert_temperature
-
+  
 4. **Multi-Step Problem Solving**: For complex questions:
    - Break down the problem into logical steps
    - Execute each step systematically, including any text transformations
@@ -113,7 +107,7 @@ You are an advanced AI agent equipped with multiple tools to solve complex, mult
 - **download_file**: Download files from URLs or attachments
 - **analyze_csv_file**: Analyze CSV file data
 - **analyze_excel_file**: Analyze Excel file data
-- **extract_text_from_image**: Extract text from image files
+- **extract_text**: Extract text from image files
 - **audio_transcription**: Transcribe audio files to text
 
 ### Text Processing
@@ -137,7 +131,7 @@ You are an advanced AI agent equipped with multiple tools to solve complex, mult
 - **Sequential Processing**: Use outputs from one tool as inputs for another when necessary
 - **File Processing Priority**: Always download and process files before attempting to answer questions about them
 - **Mathematical Chains**: Combine mathematical operations as needed (e.g., add -> multiply -> percentage_calculator)
-- **Information + Processing**: Combine search tools with processing tools (e.g., web_search -> extract_text_from_image -> analyze_csv_file)
+- **Information + Processing**: Combine search tools with processing tools (e.g., web_search -> extract_text -> analyze_csv_file)
 - **Text Transformations**: Use text processing tools before analysis (e.g., reverse_sentence -> python_code_parser). In other words, first reverse the text when needed and then re-read the adjusted question.
 - **Pattern Recognition**: Look for hidden patterns, instructions, or transformations within questions
 

requirements.txt

@@ -14,6 +14,7 @@ langchain-huggingface
 langfuse
 langchain-google-genai
 langchain-tavily
+langchain-openai
 
 # Hugging Face integration
 huggingface_hub

tools.py

@@ -19,6 +19,7 @@ from langchain_core.messages import HumanMessage
 # from langchain_community.tools import DuckDuckGoSearchRun
 from langchain_core.tools import tool
 from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_openai import ChatOpenAI
 from langchain_tavily import TavilySearch
 
 
@@ -744,24 +745,18 @@ def analyze_csv_file(file_path: str, query: str) -> str:
     except Exception as e:
         return f"Error analyzing CSV file: {str(e)}"
 
-'''
-# Extract Text Tool
-vision_llm = ChatGoogleGenerativeAI(model="gemini-1.5-pro",temperature=0)
+
+vision_llm = ChatOpenAI(model="gpt-4o")
 
 @tool
-def extract_text_from_image(img_path: str) -> str:
+def extract_text(img_path: str) -> str:
     """
     Extract text from an image file using a multimodal model.
-
-    Args:
-        img_path: A local image file path (strings).
-
-    Returns:
-        A single string containing the concatenated text extracted from each image.
+    
+    This allows me to properly analyze the contents.
     """
     all_text = ""
     try:
-
         # Read image and encode as base64
         with open(img_path, "rb") as image_file:
             image_bytes = image_file.read()
@@ -797,11 +792,11 @@ def extract_text_from_image(img_path: str) -> str:
 
         return all_text.strip()
     except Exception as e:
-        # You can choose whether to raise or just return an empty string / error message
+        # A butler should handle errors gracefully
         error_msg = f"Error extracting text: {str(e)}"
         print(error_msg)
         return ""
-'''
+
 
 @tool
 def reverse_sentence(text: str) -> str: