Update tools.py

tools.py

@@ -5,6 +5,7 @@ from langchain_community.document_loaders import WikipediaLoader
 import pandas as pd
 import whisper
 import os
+import re
 import tempfile
 from transformers import Blip2Processor, Blip2ForConditionalGeneration
 from PIL import Image
@@ -64,6 +65,32 @@ def divide(a: int, b: int) -> int:
         raise ValueError("Cannot divide by zero.")
     return a / b
 
+def match_referenced_files(question: str, uploaded_files: list) -> list:
+    """
+    Given a question string and a list of uploaded files with metadata,
+    return the list of files that are referenced in the question.
+
+    Parameters:
+        - question: str — The user's question.
+        - uploaded_files: list of dicts with keys:
+            - name (e.g., "data.xlsx")
+            - type (e.g., "excel", "image", "audio")
+            - path (e.g., "/tmp/data.xlsx")
+
+    Returns:
+        A list of file dicts that were referenced in the question.
+    """
+    # Find all mentions of possible filenames in the question (e.g., .xlsx, .png, .mp3)
+    referenced_names = set(re.findall(r'[\w\-\s]+\.(xlsx|xls|csv|png|jpg|jpeg|mp3|wav)', question, flags=re.IGNORECASE))
+
+    matched = []
+    for file in uploaded_files:
+        base_name = os.path.basename(file["name"]).lower()
+        if any(base_name.endswith(name.lower()) for name in referenced_names):
+            matched.append(file)
+
+    return matched
+
 
 @tool
 def analyze_image(image_path: str, question: str = "What’s in this image?") -> str: