Update app.py

app.py

@@ -1,18 +1,22 @@
-from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
+from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel, load_tool, tool
 import datetime
 import requests
 import pytz
 import yaml
 import os
 from tools.final_answer import FinalAnswerTool
-
 from Gradio_UI import GradioUI
 
+import fitz  # PyMuPDF
+from sentence_transformers import SentenceTransformer, util
+from transformers import pipeline
+
+# API Key for weather
 API_KEY = os.getenv("Weather_Token")
-# Below is an example of a tool that does nothing. Amaze us with your creativity !
+
+# -------------------- TOOL 1: Get Weather --------------------
 @tool
-def get_current_weather(place: str)-> str: #it's import to specify the return type
-    #Keep this format for the description / args / args description but feel free to modify the tool
+def get_current_weather(place: str) -> str:
     """A tool that fetches the current weather of a particular place
     Args:
         place: A string representing a valid place (e.g., 'London/Paris')
@@ -24,19 +28,17 @@ def get_current_weather(place: str)-> str: #it's import to specify the return ty
         "appid": api_key,
         "units": "metric"
     }
-    
+
     try:
         response = requests.get(url, params=params)
         data = response.json()
 
-        # Check if the request was successful
         if response.status_code == 200:
             weather_desc = data["weather"][0]["description"]
             temperature = data["main"]["temp"]
             humidity = data["main"]["humidity"]
             wind_speed = data["wind"]["speed"]
 
-            # Display the results
             return (
                 f"Weather in {place}:\n"
                 f"- Condition: {weather_desc}\n"
@@ -49,6 +51,7 @@ def get_current_weather(place: str)-> str: #it's import to specify the return ty
     except Exception as e:
         return f"Error fetching weather data for '{place}': {str(e)}"
 
+# -------------------- TOOL 2: Get Time --------------------
 @tool
 def get_current_time_in_timezone(timezone: str) -> str:
     """A tool that fetches the current local time in a specified timezone.
@@ -56,38 +59,77 @@ def get_current_time_in_timezone(timezone: str) -> str:
         timezone: A string representing a valid timezone (e.g., 'America/New_York').
     """
     try:
-        # Create timezone object
         tz = pytz.timezone(timezone)
-        # Get current time in that timezone
         local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
         return f"The current local time in {timezone} is: {local_time}"
     except Exception as e:
         return f"Error fetching time for timezone '{timezone}': {str(e)}"
 
+# -------------------- TOOL 3: Document QnA --------------------
+embedding_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+qa_pipeline = pipeline("text2text-generation", model="google/flan-t5-base")
+
+@tool
+def document_qna_tool(pdf_path: str, question: str) -> str:
+    """A tool for answering questions based on the content of a PDF document.
+    Args:
+        pdf_path: A string path to the local PDF file.
+        question: A natural language question to ask about the PDF content.
+    """
+    try:
+        # Step 1: Extract text from PDF
+        doc = fitz.open(pdf_path)
+        text_chunks = []
+        for page in doc:
+            text = page.get_text()
+            if text.strip():
+                text_chunks.append(text)
+        doc.close()
+
+        if not text_chunks:
+            return "No text found in the PDF."
+
+        # Step 2: Semantic search
+        embeddings = embedding_model.encode(text_chunks, convert_to_tensor=True)
+        question_embedding = embedding_model.encode(question, convert_to_tensor=True)
+        scores = util.pytorch_cos_sim(question_embedding, embeddings)[0]
+        best_match_idx = scores.argmax()
+        best_context = text_chunks[best_match_idx]
+
+        # Step 3: Answer question
+        prompt = f"Context: {best_context}\nQuestion: {question}"
+        answer = qa_pipeline(prompt, max_new_tokens=100)[0]['generated_text']
+        return f"Answer: {answer.strip()}"
+
+    except Exception as e:
+        return f"Error processing document QnA: {str(e)}"
 
+# -------------------- Other Components --------------------
 final_answer = FinalAnswerTool()
 search_tool = DuckDuckGoSearchTool()
 
-# 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:
-# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
-
 model = HfApiModel(
-max_tokens=2096,
-temperature=0.5,
-model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
-custom_role_conversions=None,
+    max_tokens=2096,
+    temperature=0.5,
+    model_id='Qwen/Qwen2.5-Coder-32B-Instruct',
+    custom_role_conversions=None,
 )
 
-
-# Import tool from Hub
 image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
 
 with open("prompts.yaml", 'r') as stream:
     prompt_templates = yaml.safe_load(stream)
-    
+
 agent = CodeAgent(
     model=model,
-    tools=[get_current_time_in_timezone, get_current_weather, image_generation_tool, search_tool, final_answer], ## add your tools here (don't remove final answer)
+    tools=[
+        get_current_time_in_timezone,
+        get_current_weather,
+        image_generation_tool,
+        search_tool,
+        document_qna_tool,  # ← New Tool Added
+        final_answer
+    ],
     max_steps=6,
     verbosity_level=1,
     grammar=None,
@@ -97,5 +139,4 @@ agent = CodeAgent(
     prompt_templates=prompt_templates
 )
 
-
-GradioUI(agent).launch()
+GradioUI(agent).launch()