A Declarative System for Optimizing AI Workloads

Modern AI models provide the key to a long-standing dream: processing analytical queries about almost any kind of data. Until recently, it was difficult and expensive to extract facts from company documents, data from scientific papers, or insights from image and video corpora. Today's models can accomplish these tasks with high accuracy. However, a programmer who wants to answer a substantive AI-powered query must orchestrate large numbers of models, prompts, and data operations. For even a single query, the programmer has to make a vast number of decisions such as the choice of model, the right inference method, the most cost-effective inference hardware, the ideal prompt design, and so on. The optimal set of decisions can change as the query changes and as the rapidly-evolving technical landscape shifts. In this paper we present Palimpzest, a system that enables anyone to process AI-powered analytical queries simply by defining them in a declarative language. The system uses its cost optimization framework -- which explores the search space of AI models, prompting techniques, and related foundation model optimizations -- to implement the query with the best trade-offs between runtime, financial cost, and output data quality. We describe the workload of AI-powered analytics tasks, the optimization methods that Palimpzest uses, and the prototype system itself. We evaluate Palimpzest on tasks in Legal Discovery, Real Estate Search, and Medical Schema Matching. We show that even our simple prototype offers a range of appealing plans, including one that is 3.3x faster, 2.9x cheaper, and offers better data quality than the baseline method. With parallelism enabled, Palimpzest can produce plans with up to a 90.3x speedup at 9.1x lower cost relative to a single-threaded GPT-4 baseline, while obtaining an F1-score within 83.5% of the baseline. These require no additional work by the user.

PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design

Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases. However, retrievals from large databases can constitute a substantial portion of the overall generation time, particularly when retrievals are periodically performed to align the retrieved content with the latest states of generation. In this paper, we introduce PipeRAG, a novel algorithm-system co-design approach to reduce generation latency and enhance generation quality. PipeRAG integrates (1) pipeline parallelism to enable concurrent retrieval and generation processes, (2) flexible retrieval intervals to maximize the efficiency of pipeline parallelism, and (3) a performance model to automatically balance retrieval quality and latency based on the generation states and underlying hardware. Our evaluation shows that, by combining the three aforementioned methods, PipeRAG achieves up to 2.6$\times$ speedup in end-to-end generation latency while improving generation quality. These promising results showcase the effectiveness of co-designing algorithms with underlying systems, paving the way for the adoption of PipeRAG in future RAG systems.

Extract-Transform-Load for Video Streams

Social media, self-driving cars, and traffic cameras produce video streams at large scales and cheap cost. However, storing and querying video at such scales is prohibitively expensive. We propose to treat large-scale video analytics as a data warehousing problem: Video is a format that is easy to produce but needs to be transformed into an application-specific format that is easy to query. Analogously, we define the problem of Video Extract-Transform-Load (V-ETL). V-ETL systems need to reduce the cost of running a user-defined V-ETL job while also giving throughput guarantees to keep up with the rate at which data is produced. We find that no current system sufficiently fulfills both needs and therefore propose Skyscraper, a system tailored to V-ETL. Skyscraper can execute arbitrary video ingestion pipelines and adaptively tunes them to reduce cost at minimal or no quality degradation, e.g., by adjusting sampling rates and resolutions to the ingested content. Skyscraper can hereby be provisioned with cheap on-premises compute and uses a combination of buffering and cloud bursting to deal with peaks in workload caused by expensive processing configurations. In our experiments, we find that Skyscraper significantly reduces the cost of V-ETL ingestion compared to adaptions of current SOTA systems, while at the same time giving robustness guarantees that these systems are lacking.

SEED: Simple, Efficient, and Effective Data Management via Large Language Models

We introduce SEED, an LLM-centric system that allows users to easily create efficient, and effective data management applications. SEED comprises three main components: code generation, model generation, and augmented LLM query to address the challenges that LLM services are computationally and economically expensive and do not always work well on all cases for a given data management task. SEED addresses the expense challenge by localizing LLM computation as much as possible. This includes replacing most of LLM calls with local code, local models, and augmenting LLM queries with batching and data access tools, etc. To ensure effectiveness, SEED features a bunch of optimization techniques to enhance the localized solution and the LLM queries, including automatic code validation, code ensemble, model representatives selection, selective tool usages, etc. Moreover, with SEED users are able to easily construct a data management solution customized to their applications. It allows the users to configure each component and compose an execution pipeline in natural language. SEED then automatically compiles it into an executable program. We showcase the efficiency and effectiveness of SEED using diverse data management tasks such as data imputation, NL2SQL translation, etc., achieving state-of-the-art few-shot performance while significantly reducing the number of required LLM calls.

FactorJoin: A New Cardinality Estimation Framework for Join Queries

Cardinality estimation is one of the most fundamental and challenging problems in query optimization. Neither classical nor learning-based methods yield satisfactory performance when estimating the cardinality of the join queries. They either rely on simplified assumptions leading to ineffective cardinality estimates or build large models to understand the data distributions, leading to long planning times and a lack of generalizability across queries. In this paper, we propose a new framework FactorJoin for estimating join queries. FactorJoin combines the idea behind the classical join-histogram method to efficiently handle joins with the learning-based methods to accurately capture attribute correlation. Specifically, FactorJoin scans every table in a DB and builds single-table conditional distributions during an offline preparation phase. When a join query comes, FactorJoin translates it into a factor graph model over the learned distributions to effectively and efficiently estimate its cardinality. Unlike existing learning-based methods, FactorJoin does not need to de-normalize joins upfront or require executed query workloads to train the model. Since it only relies on single-table statistics, FactorJoin has small space overhead and is extremely easy to train and maintain. In our evaluation, FactorJoin can produce more effective estimates than the previous state-of-the-art learning-based methods, with 40x less estimation latency, 100x smaller model size, and 100x faster training speed at comparable or better accuracy. In addition, FactorJoin can estimate 10,000 sub-plan queries within one second to optimize the query plan, which is very close to the traditional cardinality estimators in commercial DBMS.

LSI: A Learned Secondary Index Structure

Learned index structures have been shown to achieve favorable lookup performance and space consumption compared to their traditional counterparts such as B-trees. However, most learned index studies have focused on the primary indexing setting, where the base data is sorted. In this work, we investigate whether learned indexes sustain their advantage in the secondary indexing setting. We introduce Learned Secondary Index (LSI), a first attempt to use learned indexes for indexing unsorted data. LSI works by building a learned index over a permutation vector, which allows binary search to performed on the unsorted base data using random access. We additionally augment LSI with a fingerprint vector to accelerate equality lookups. We show that LSI achieves comparable lookup performance to state-of-the-art secondary indexes while being up to 6x more space efficient.

Bounding the Last Mile: Efficient Learned String Indexing

We introduce the RadixStringSpline (RSS) learned index structure for efficiently indexing strings. RSS is a tree of radix splines each indexing a fixed number of bytes. RSS approaches or exceeds the performance of traditional string indexes while using 7-70$\times$ less memory. RSS achieves this by using the minimal string prefix to sufficiently distinguish the data unlike most learned approaches which index the entire string. Additionally, the bounded-error nature of RSS accelerates the last mile search and also enables a memory-efficient hash-table lookup accelerator. We benchmark RSS on several real-world string datasets against ART and HOT. Our experiments suggest this line of research may be promising for future memory-intensive database applications.

PLEX: Towards Practical Learned Indexing

Latest research proposes to replace existing index structures with learned models. However, current learned indexes tend to have many hyperparameters, often do not provide any error guarantees, and are expensive to build. We introduce Practical Learned Index (PLEX). PLEX only has a single hyperparameter $\epsilon$ (maximum prediction error) and offers a better trade-off between build and lookup time than state-of-the-art approaches. Similar to RadixSpline, PLEX consists of a spline and a (multi-level) radix layer. It first builds a spline satisfying the given $\epsilon$ and then performs an ad-hoc analysis of the distribution of spline points to quickly tune the radix layer.

TagMe: GPS-Assisted Automatic Object Annotation in Videos

Training high-accuracy object detection models requires large and diverse annotated datasets. However, creating these data-sets is time-consuming and expensive since it relies on human annotators. We design, implement, and evaluate TagMe, a new approach for automatic object annotation in videos that uses GPS data. When the GPS trace of an object is available, TagMe matches the object's motion from GPS trace and the pixels' motions in the video to find the pixels belonging to the object in the video and creates the bounding box annotations of the object. TagMe works using passive data collection and can continuously generate new object annotations from outdoor video streams without any human annotators. We evaluate TagMe on a dataset of 100 video clips. We show TagMe can produce high-quality object annotations in a fully-automatic and low-cost way. Compared with the traditional human-in-the-loop solution, TagMe can produce the same amount of annotations at a much lower cost, e.g., up to 110x.

Learned Indexes for a Google-scale Disk-based Database

There is great excitement about learned index structures, but understandable skepticism about the practicality of a new method uprooting decades of research on B-Trees. In this paper, we work to remove some of that uncertainty by demonstrating how a learned index can be integrated in a distributed, disk-based database system: Google's Bigtable. We detail several design decisions we made to integrate learned indexes in Bigtable. Our results show that integrating learned index significantly improves the end-to-end read latency and throughput for Bigtable.