updated tools and agent

agent.py

@@ -7,13 +7,14 @@ 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, compound_interest, convert_temperature,
+from tools import (absolute, add, analyze_excel_file, arvix_search,
+                   audio_transcription, compound_interest, convert_temperature,
                    divide, exponential, factorial, floor_divide,
                    get_current_time_in_timezone, greatest_common_divisor,
                    is_prime, least_common_multiple, logarithm, modulus,
                    multiply, percentage_calculator, power,
                    roman_calculator_converter, square_root, subtract,
-                   web_search)
+                   web_search, wiki_search)
 
 # Load Constants
 load_dotenv()
@@ -26,7 +27,8 @@ tools = [
     exponential, web_search, roman_calculator_converter,
     get_current_time_in_timezone, compound_interest,
     convert_temperature, factorial, greatest_common_divisor,
-    is_prime, least_common_multiple, percentage_calculator
+    is_prime, least_common_multiple, percentage_calculator,
+    wiki_search, analyze_excel_file, arvix_search, audio_transcription
 ]
 
 def build_graph():

tools.py

@@ -1,9 +1,14 @@
 import datetime
 import math
+import os
 from typing import Union
 
+import pandas
 import pytz
-from langchain_community.document_loaders import ArxivLoader, WikipediaLoader
+from langchain_community.document_loaders import (
+    ArxivLoader, AssemblyAIAudioTranscriptLoader, WikipediaLoader)
+from langchain_community.document_loaders.generic import GenericLoader
+from langchain_community.document_loaders.parsers import LanguageParser
 from langchain_community.tools import DuckDuckGoSearchRun
 from langchain_core.tools import tool
 
@@ -581,3 +586,83 @@ def arvix_search(query: str) -> str:
             for doc in search_docs
         ])
     return {"arvix_results": formatted_search_docs}
+
+
+@tool
+def analyze_excel_file(file_path: str, query: str) -> str:
+    """
+    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:
+        file = pandas.read_excel(file_path)
+
+        result = (
+            f"Excel file loaded with {len(file)} rows and {len(file.columns)} columns.\n"
+        )
+        result += f"Columns: {', '.join(file.columns)}\n\n"
+
+        result += "Summary statistics:\n"
+        result += str(file.describe())
+
+        return result
+
+    except Exception as e:
+        return f"Error analyzing Excel file: {str(e)}"
+    
+
+@tool
+def python_code_parser(file_path: str) -> str:
+    """
+    Parse Python code to extract function names and their docstrings.
+
+    Args:
+        file_path: The path to the Python file to parse.
+
+    Returns:
+        Interpreted Python code as a string.
+    """
+    if not os.path.exists(file_path):
+        return "0"
+
+
+    loader = GenericLoader.from_filesystem(
+        file_path,
+        glob="**/*",
+        suffixes=[".py"],
+        parser=LanguageParser()
+    )
+    search_docs = loader.load()
+
+    formatted_search_docs = "\n\n---\n\n".join(
+    [
+        f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+        for doc in search_docs
+    ])
+
+    return {"audio_results": formatted_search_docs}
+
+
+@tool
+def audio_transcription(file_path: str) -> str:
+    """
+    Transcribe an audio file to text using AssemblyAI.
+    
+    Args:
+        file_path: The path to the audio file.
+    
+    Returns:
+        The transcribed text from the audio file.
+    """
+    search_docs = AssemblyAIAudioTranscriptLoader(file_path=file_path).load()
+
+    formatted_search_docs = "\n\n---\n\n".join(
+    [
+        f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+        for doc in search_docs
+    ])
+
+    return {"audio_results": formatted_search_docs}
+