extract_key_facts
Extract structured key facts from Wikipedia articles to quickly identify essential information, optionally focusing on specific topics within the article.
Instructions
Extract key facts from a Wikipedia article, optionally focused on a topic.
Returns a dictionary containing a list of facts.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | ||
| topic_within_article | No | ||
| count | No |
Implementation Reference
- wikipedia_mcp/server.py:192-206 (handler)The primary handler function for the 'extract_key_facts' MCP tool, registered via @server.tool(). Defines the input schema through type hints and Annotated fields. Executes the tool by calling WikipediaClient.extract_facts and returning a formatted dictionary response.@server.tool() def extract_key_facts( title: str, topic_within_article: Annotated[str, Field(title="Topic Within Article")] = "", count: int = 5, ) -> Dict[str, Any]: """ Extract key facts from a Wikipedia article, optionally focused on a topic. Returns a dictionary containing a list of facts. """ logger.info(f"Tool: Extracting key facts for article: {title}, topic: {topic_within_article}") topic = topic_within_article if topic_within_article.strip() else None facts = wikipedia_client.extract_facts(title, topic, count=count) return {"title": title, "topic_within_article": topic_within_article, "facts": facts}
- Supporting utility method in WikipediaClient that implements the core fact extraction logic. Retrieves article content (summary or specific section), splits into sentences, and returns the top 'count' facts. Called by the tool handler.def extract_facts( self, title: str, topic_within_article: Optional[str] = None, count: int = 5, ) -> List[str]: """ Extract key facts from a Wikipedia article. This is a simplified implementation returning the first few sentences of the summary or a relevant section if topic_within_article is provided. Args: title: The title of the Wikipedia article. topic_within_article: Optional topic/section to focus fact extraction. count: The number of facts to extract. Returns: A list of key facts (strings). """ try: page = self.wiki.page(title) if not page.exists(): return [f"No Wikipedia article found for '{title}'."] text_to_process = "" if topic_within_article: # Try to find the section text def find_section_text_recursive(sections_list, target_title): for sec in sections_list: if sec.title.lower() == target_title.lower(): return sec.text found_in_subsection = find_section_text_recursive(sec.sections, target_title) if found_in_subsection: return found_in_subsection return None section_text = find_section_text_recursive(page.sections, topic_within_article) if section_text: text_to_process = section_text else: # Fallback to summary if specific topic section not found text_to_process = page.summary else: text_to_process = page.summary if not text_to_process: return ["No content found to extract facts from."] # Basic sentence splitting (can be improved with NLP libraries) sentences = [s.strip() for s in text_to_process.split(".") if s.strip()] facts: List[str] = [] for sentence in sentences[:count]: if sentence: # Ensure not an empty string after strip facts.append(sentence + ".") # Add back the period return facts if facts else ["Could not extract facts from the provided text."] except Exception as e: logger.error(f"Error extracting key facts for '{title}': {e}") return [f"Error extracting key facts for '{title}': {str(e)}"]