Update agent.py

agent.py

@@ -34,6 +34,10 @@ from youtube_transcript_api import YouTubeTranscriptApi
 from youtube_transcript_api._errors import TranscriptsDisabled, VideoUnavailable
 import re
 
+from langchain_community.document_loaders import TextLoader, PyMuPDFLoader
+from docx import Document as DocxDocument
+import openpyxl
+
 
 load_dotenv()
 
@@ -131,6 +135,46 @@ def arvix_search(query: str) -> str:
     return {"arvix_results": formatted_search_docs}
 
 
+
+@tool
+def analyze_attachment(file_path: str) -> str:
+    """
+    Analyzes attachments including PDF, TXT, DOCX, and XLSX files and returns text content.
+
+    Args:
+        file_path: Local path to the attachment.
+    """
+    if not os.path.exists(file_path):
+        return f"File not found: {file_path}"
+
+    if file_path.lower().endswith(".pdf"):
+        loader = PyMuPDFLoader(file_path)
+        documents = loader.load()
+        content = "\n\n".join([doc.page_content for doc in documents])
+
+    elif file_path.lower().endswith(".txt"):
+        loader = TextLoader(file_path)
+        documents = loader.load()
+        content = "\n\n".join([doc.page_content for doc in documents])
+
+    elif file_path.lower().endswith(".docx"):
+        doc = DocxDocument(file_path)
+        content = "\n".join([para.text for para in doc.paragraphs])
+
+    elif file_path.lower().endswith(".xlsx"):
+        wb = openpyxl.load_workbook(file_path, data_only=True)
+        content = ""
+        for sheet in wb:
+            content += f"Sheet: {sheet.title}\n"
+            for row in sheet.iter_rows(values_only=True):
+                content += "\t".join([str(cell) if cell is not None else "" for cell in row]) + "\n"
+
+    else:
+        return "Unsupported file format. Please use PDF, TXT, DOCX, or XLSX."
+
+    return content[:3000]  # Limit size for readability
+
+
 @tool
 def get_youtube_transcript(url: str) -> str:
     """
@@ -210,6 +254,7 @@ tool_map = {
     "arvix_search": arvix_search,
     "get_youtube_transcript": get_youtube_transcript,
     "extract_video_id": extract_video_id,
+    "analyze_attachment": analyze_attachment,
     
 }