Updated app.py

app.py

@@ -1,69 +1,73 @@
-from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
+from smolagents import CodeAgent, HfApiModel, load_tool, tool
 import datetime
 import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
-
-from Gradio_UI import GradioUI
-
-# Below is an example of a tool that does nothing. Amaze us with your creativity !
-@tool
-def my_custom_tool(arg1:str, arg2:int)-> 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
-    """A tool that does nothing yet 
-    Args:
-        arg1: the first argument
-        arg2: the second argument
-    """
-    return "What magic will you build ?"
+from scholarly import scholarly
+import gradio as gr
 
 @tool
-def get_current_time_in_timezone(timezone: str) -> str:
-    """A tool that fetches the current local time in a specified timezone.
+def fetch_latest_research_papers(keywords: list, num_results: int = 5) -> list:
+    """Fetches the latest research papers from Google Scholar based on provided keywords.
     Args:
-        timezone: A string representing a valid timezone (e.g., 'America/New_York').
+        keywords: A list of keywords to search for relevant papers.
+        num_results: The number of papers to fetch (default is 5).
     """
     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}"
+        query = " ".join(keywords)
+        search_results = scholarly.search_pubs(query)
+        papers = []
+        for i in range(num_results):
+            paper = next(search_results, None)
+            if paper:
+                papers.append({
+                    "title": paper['bib'].get('title', 'No Title'),
+                    "authors": paper['bib'].get('author', 'Unknown Authors'),
+                    "year": paper['bib'].get('pub_year', 'Unknown Year'),
+                    "abstract": paper['bib'].get('abstract', 'No Abstract Available'),
+                    "link": paper.get('pub_url', 'No Link Available')
+                })
+        return papers
     except Exception as e:
-        return f"Error fetching time for timezone '{timezone}': {str(e)}"
-
+        return [f"Error fetching research papers: {str(e)}"]
 
 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:
-# 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=[final_answer], ## add your tools here (don't remove final answer)
+    tools=[final_answer, fetch_latest_research_papers],
     max_steps=6,
     verbosity_level=1,
     grammar=None,
     planning_interval=None,
-    name=None,
-    description=None,
+    name="ScholarAgent",
+    description="An AI agent that fetches the latest research papers from Google Scholar based on user-defined keywords and filters.",
     prompt_templates=prompt_templates
 )
 
+def search_papers(user_input):
+    keywords = user_input.split(",")  # Split input by commas for multiple keywords
+    results = fetch_latest_research_papers(keywords, num_results=5)
+    return "\n\n".join([f"**Title:** {paper['title']}\n**Authors:** {paper['authors']}\n**Year:** {paper['year']}\n**Abstract:** {paper['abstract']}\n[Read More]({paper['link']})" for paper in results])
+
+# Create a simple Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Google Scholar Research Paper Fetcher")
+    keyword_input = gr.Textbox(label="Enter keywords (comma-separated)", placeholder="e.g., deep learning, reinforcement learning")
+    output_display = gr.Markdown()
+    search_button = gr.Button("Search")
+    
+    search_button.click(search_papers, inputs=[keyword_input], outputs=[output_display])
 
-GradioUI(agent).launch()
+demo.launch()