Perplexity, 모델이 직접 검색 코드를 작성하게 해 토큰 비용 85% 절감
Perplexity가 모델이 고정된 API를 호출하는 대신 맞춤형 Python 검색 파이프라인을 작성하는 'search as code' 아키텍처를 공개했습니다. 이를 통해 복잡한 리서치 에이전트에서 토큰 사용량 85% 감소와 더 나은 데이터 정밀도를 약속합니다.
perplexity detailed its new search as code architecture, which replaces standard api calls with model-generated python scripts that execute in a secure sandbox. by using an agentic search sdk, models can perform custom retrieval, filtering, and reranking to keep context windows lean and improve result accuracy. the company demonstrated this on a cybersecurity task tracking 200 vulnerabilities, where the agent used 85% fewer tokens and outperformed standard pipelines. this approach challenges the dominant fixed api paradigm, suggesting that giving models programmatic control over search logic may be more efficient than universal, black-box tools.