implementsrdf:typecomputescontrolFlowusesMechanismrdfs:labelimplementationDetaildemonstratesimplementationStatusOther subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. “X motherOf this subject” — and answer questions the forward facts can't. Grouped by predicate.
hasMethodHas Method(3)ex:ContextWindowex:ContextWindowex:context-window-classcallsMethodCalls Method(1)ex:windowmethodMethod(1)ex:ContextWindowThe long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
doc:beam/e1b0d9f6-0084-4481-9dd3-e53740c7af294. **Segmentation**: - Implement segmentation to handle large inputs by breaking them into smaller chunks. - Use overlap between segments to maintain context continuity. 5. **Caching**: - Use caching to store and reuse results of …
doc:beam/da44b8f0-5e1d-4fe9-a919-e78922d1e95d# Example usage window = ContextWindow(max_tokens=2000, overlap=100) # Add tokens for i in range(2000): window.add_token(f'token_{i}') # Get context context = window.get_context() print(context) # Segment input input_data = [f'token_…
doc:beam/21e9b325-d329-454b-ac72-e96bf0443044def add_token(self, token): self.tokens.append(token) def get_context(self): # Return context here pass window = ContextWindow() window.add_token('token1') window.add_token('token2') print(window.get_contex…
Dontopedia is in a read-only public launch. Follow the references and disputed branches now; contributions will open after durable identity and moderation are in place.