Update app.py

app.py

@@ -4,6 +4,13 @@ import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
+import nltk
+import networkx as nx
+from sklearn.feature_extraction.text import TfidfVectorizer
+from nltk.tokenize import sent_tokenize
+
+# Ensure necessary NLTK resources are downloaded
+nltk.download('punkt')
 
 from Gradio_UI import GradioUI
 
@@ -34,6 +41,45 @@ def get_current_time_in_timezone(timezone: str) -> str:
         return f"Error fetching time for timezone '{timezone}': {str(e)}"
 
 
+@tool
+def extract_sent(doc: str, top_n: int = 3) -> list:
+    """ Extracts key sentences from a document using TextRank.
+    
+    Args:
+        doc (str): The document (e.g., abstract) to extract sentences from.
+        top_n (int): The number of top-ranked sentences to return.
+
+    Returns:
+        List[str]: The most pertinent sentences.
+    """
+    try:
+        # Step 1: Tokenize the document into sentences
+        sentences = sent_tokenize(doc)
+
+        # Step 2: Convert sentences to vector representations (TF-IDF)
+        vectorizer = TfidfVectorizer()
+        sentence_vectors = vectorizer.fit_transform(sentences)
+
+        # Step 3: Compute similarity matrix (cosine similarity)
+        similarity_matrix = (sentence_vectors * sentence_vectors.T).toarray()
+
+        # Step 4: Create a graph where nodes are sentences, and edges are similarities
+        sentence_graph = nx.from_numpy_array(similarity_matrix)
+
+        # Step 5: Apply PageRank algorithm to rank sentences
+        scores = nx.pagerank(sentence_graph)
+
+        # Step 6: Sort sentences by score and return top-N sentences
+        ranked_sentences = sorted(((scores[i], s) for i, s in enumerate(sentences)), reverse=True)
+        extracted_sentences = [s for _, s in ranked_sentences[:top_n]]
+
+        return extracted_sentences
+    
+    except Exception as e:
+        print(f"Error in extract_sent: {e}")
+        return []
+
+
 final_answer = FinalAnswerTool()
 
 # If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
@@ -55,7 +101,7 @@ with open("prompts.yaml", 'r') as stream:
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer], ## add your tools here (don't remove final answer)
+    tools=[get_current_time_in_timezone,image_generation_tool,extract_sent,final_answer], ## add your tools here (don't remove final answer)
     max_steps=6,
     verbosity_level=1,
     grammar=None,