6 papers
VectraFlow: Long-Horizon Semantic Processing over Data and Event Streams with LLMs
Shu Chen, Junhan Liu, Deepti Raghavan +1
Monitoring continuous data for meaningful signals increasingly demands long-horizon, stateful reasoning over unstructured streams. However, today's LLM frameworks remain stateless…
Making Prompts First-Class Citizens for Adaptive LLM Pipelines
Ugur Cetintemel, Shu Chen, Alexander W. Lee +3
Modern LLM pipelines increasingly resemble complex data-centric applications: they retrieve data, correct errors, call external tools, and coordinate interactions between agents. Y…
Continuous Prompts: LLM-Augmented Pipeline Processing over Unstructured Streams
Shu Chen, Deepti Raghavan, UÄur Ãetintemel
Monitoring unstructured streams increasingly requires persistent, semantics-aware computation, yet today's LLM frameworks remain stateless and one-shot, limiting their usefulness f…
When Are Reactive Notebooks Not Reactive?
Megan Zheng, Will Crichton, Akshay Narayan +2
Computational notebooks are convenient for programmers, but can easily become confusing and inconsistent due to the ability to incrementally edit a program that is running. Recent…
Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems
Alexander W. Lee, Justin Chan, Michael Fu +4
AI-augmented data processing systems (DPSs) integrate large language models (LLMs) into query pipelines, allowing powerful semantic operations on structured and unstructured data.…
Alto: Orchestrating Distributed Compound AI Systems with Nested Ancestry
Deepti Raghavan, Keshav Santhanam, Muhammad Shahir Rahman +7
Compound AI applications chain together subcomponents such as generative language models, document retrievers, and embedding models. Applying traditional systems optimizations such…