update tools

.gitignore

@@ -0,0 +1,171 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# PyPI configuration file
+.pypirc

app.py

@@ -7,10 +7,13 @@ from tools.final_answer import FinalAnswerTool
 
 from Gradio_UI import GradioUI
 
+from huggingface_hub import login
+
+login()
 
 @tool
 def lookup_wikipedia_page(search_query: str) -> str:
-    """Looks up the exact Wikipedia page title for a given search query
+    """Looks up the exact Wikipedia page title for a given search query, allowing to get the exact page title for subsequent wikipedia views tool
     Args:
         search_query: The search term to find the Wikipedia page for
     """
@@ -43,36 +46,49 @@ def lookup_wikipedia_page(search_query: str) -> str:
 
 @tool
 def get_wikipedia_views(article_title: str, window_size_in_days: int) -> str:
-    """Fetches view statistics for a Wikipedia article
+    """Fetches view statistics for a Wikipedia article. The article title is the exact page title from the lookup_wikipedia_page tool.
     Args:
         article_title: The title of the Wikipedia article to get views for
         window_size_in_days: The number of days to get views for
     """
     try:
-        # Format the dates (get views for last 7 days)
-        end_date = datetime.datetime.now()
-        start_date = end_date - datetime.timedelta(days=window_size_in_days)
-        
-        # Format dates as YYYYMMDD for the API
-        start_str = start_date.strftime('%Y%m%d')
-        end_str = end_date.strftime('%Y%m%d')
         
         # Clean article title for URL
-        article = article_title.replace(' ', '_')
+        article_title = article_title.replace(' ', '_')
         
         # Construct API URL
-        url = f"https://wikimedia.org/api/rest_v1/metrics/pageviews/per-article/en.wikipedia/all-access/all-agents/{article}/daily/{start_str}/{end_str}"
+        # First get the page ID using the API
+        id_url = "https://en.wikipedia.org/w/api.php"
+        id_params = {
+            "action": "query",
+            "format": "json", 
+            "titles": article_title,
+            "prop": "pageviews",
+            "pvipdays": window_size_in_days
+        }
+
+        # Get the response data
+        id_response = requests.get(id_url, params=id_params)
+        if id_response.status_code != 200:
+            return f"Error getting page ID: {id_response.status_code}"
+            
+        id_data = id_response.json()
         
-        # Make request
-        response = requests.get(url)
+        # Check if pages data exists
+        if "pages" not in id_data["query"]:
+            return f"Could not find page '{article_title}'"
+            
+        # Get the first page's data
+        page_data = next(iter(id_data["query"]["pages"].values()))
         
-        if response.status_code == 200:
-            data = response.json()
-            total_views = sum(item['views'] for item in data['items'])
-            return f"The article '{article_title}' had {total_views} views in the last 7 days"
-        else:
-            return f"Error fetching data: {response.status_code}"
+        if "pageviews" not in page_data:
+            return f"No pageview data available for '{article_title}'"
             
+        # Calculate total views
+        total_views = sum(views for views in page_data["pageviews"].values() if views is not None)
+        
+        return f"The article '{article_title}' had {total_views} views in the last {window_size_in_days} days"
+        
     except Exception as e:
         return f"Error processing request: {str(e)}"