feat: capability to retrieve news and parse them to extract details

.env.example

@@ -0,0 +1,2 @@
+HF_TOKEN=
+NEWSAPI_TOKEN=

.gitignore

@@ -0,0 +1,2 @@
+.DS_Store
+.env

Dockerfile

@@ -10,4 +10,8 @@ COPY ./src /app/src
 
 COPY ./prompts.yaml /app
 
-CMD ["python", "src/app.py"]
+COPY ./.env /app/.env
+
+EXPOSE 7860
+
+CMD python -u src/app.py

Justfile

@@ -3,4 +3,4 @@ default:
 
 run:
   docker build --tag 'ai-agents-course' .
-  docker run 'ai-agents-course'
+  docker run -p 7860:7860 'ai-agents-course'

README.md

@@ -15,4 +15,10 @@ tags:
 - agent-course
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## Development
+
+### Setup
+
+- Copy the `.env.example` into `.env` and pass a Read Only Access HuggingFace Token
+
+> Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -1,6 +1,7 @@
 duckduckgo_search == 7.4.4
 gradio == 5.17.1
 markdownify == 0.14.1
+python-dotenv == 1.0.1
 smolagents == 1.9.2
 requests == 2.32.3
 pandas == 2.2.3

src/Gradio_UI.py

@@ -17,8 +17,8 @@ import mimetypes
 import os
 import re
 import shutil
-from typing import Optional
 
+from typing import Optional
 from smolagents.agent_types import AgentAudio, AgentImage, AgentText, handle_agent_output_types
 from smolagents.agents import ActionStep, MultiStepAgent
 from smolagents.memory import MemoryStep

src/app.py

@@ -1,22 +1,17 @@
 import datetime
+import os
 import requests
 import pytz
 import yaml
 
+from dotenv import load_dotenv
 from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
 from tools.final_answer import FinalAnswerTool
+from tools.newsapi_search import NewsApiSearch
+from tools.visit_webpage import VisitWebpageTool
 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 ?"
+load_dotenv()
 
 @tool
 def get_current_time_in_timezone(timezone: str) -> str:
@@ -33,29 +28,27 @@ def get_current_time_in_timezone(timezone: str) -> str:
     except Exception as e:
         return f"Error fetching time for timezone '{timezone}': {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'
+newsapi_search = NewsApiSearch(apikey=os.environ['NEWSAPI_TOKEN'])
+visit_webpage = VisitWebpageTool()
 
 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
+    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,
+      newsapi_search,
+      visit_webpage,
+    ],
     max_steps=6,
     verbosity_level=1,
     grammar=None,
@@ -65,5 +58,4 @@ agent = CodeAgent(
     prompt_templates=prompt_templates
 )
 
-
-GradioUI(agent).launch()
+GradioUI(agent).launch(server_name="0.0.0.0")

src/tools/newsapi_search.py

@@ -0,0 +1,46 @@
+import requests
+
+from smolagents.tools import Tool
+from typing import Any, Optional
+
+
+class NewsApiSearch(Tool):
+    name = "newsapi_search"
+    description = "Performs a NewsAPI search based on your query then returns the top search News results."
+    inputs = {'query': {'type': 'string', 'description': 'The search query to perform.'}}
+    output_type = "string"
+
+    def __init__(self, max_results=10, apikey='', **kwargs):
+        super().__init__()
+        self.max_results = max_results
+        self.client = NewsApi(apikey)
+
+    def forward(self, query: str) -> str:
+        results = self.client.search(query)
+        return results
+
+
+class NewsApi:
+    def __init__(self, api_key: str):
+        self.apikey = api_key
+        self.endpoint = "https://newsapi.org/v2/everything"
+
+    def search(self, query: str) -> str:
+        params = {
+          'apiKey': self.apikey,
+          'q': query,
+        }
+
+        response = requests.get(self.endpoint, params=params)
+
+        if response.status_code == 200:
+            data = response.json()
+            articles = data['articles']
+
+            if len(articles) == 0:
+                raise Exception('No news found for the provided query')
+
+            first_result = articles[0]
+            return first_result['url']
+
+        raise Exception('Failed to access NewsAPI Server')

src/tools/visit_webpage.py

@@ -1,9 +1,11 @@
-from typing import Any, Optional
-from smolagents.tools import Tool
+import re
 import requests
 import markdownify
 import smolagents
 
+from typing import Any, Optional
+from smolagents.tools import Tool
+
 class VisitWebpageTool(Tool):
     name = "visit_webpage"
     description = "Visits a webpage at the given url and reads its content as a markdown string. Use this to browse webpages."

src/tools/web_search.py

@@ -1,6 +1,7 @@
+import duckduckgo_search
+
 from typing import Any, Optional
 from smolagents.tools import Tool
-import duckduckgo_search
 
 class DuckDuckGoSearchTool(Tool):
     name = "web_search"