PalimpChat: Declarative and Interactive AI analytics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Chunwei, Vitagliano, Gerardo, Rose, Brandon, Prinz, Matt, Samson, David Andrew, Cafarella, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915139976953856
author Liu, Chunwei
Vitagliano, Gerardo
Rose, Brandon
Prinz, Matt
Samson, David Andrew
Cafarella, Michael
author_facet Liu, Chunwei
Vitagliano, Gerardo
Rose, Brandon
Prinz, Matt
Samson, David Andrew
Cafarella, Michael
contents Thanks to the advances in generative architectures and large language models, data scientists can now code pipelines of machine-learning operations to process large collections of unstructured data. Recent progress has seen the rise of declarative AI frameworks (e.g., Palimpzest, Lotus, and DocETL) to build optimized and increasingly complex pipelines, but these systems often remain accessible only to expert programmers. In this demonstration, we present PalimpChat, a chat-based interface to Palimpzest that bridges this gap by letting users create and run sophisticated AI pipelines through natural language alone. By integrating Archytas, a ReAct-based reasoning agent, and Palimpzest's suite of relational and LLM-based operators, PalimpChat provides a practical illustration of how a chat interface can make declarative AI frameworks truly accessible to non-experts. Our demo system is publicly available online. At SIGMOD'25, participants can explore three real-world scenarios--scientific discovery, legal discovery, and real estate search--or apply PalimpChat to their own datasets. In this paper, we focus on how PalimpChat, supported by the Palimpzest optimizer, simplifies complex AI workflows such as extracting and analyzing biomedical data.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03368
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PalimpChat: Declarative and Interactive AI analytics
Liu, Chunwei
Vitagliano, Gerardo
Rose, Brandon
Prinz, Matt
Samson, David Andrew
Cafarella, Michael
Artificial Intelligence
Databases
Information Retrieval
Thanks to the advances in generative architectures and large language models, data scientists can now code pipelines of machine-learning operations to process large collections of unstructured data. Recent progress has seen the rise of declarative AI frameworks (e.g., Palimpzest, Lotus, and DocETL) to build optimized and increasingly complex pipelines, but these systems often remain accessible only to expert programmers. In this demonstration, we present PalimpChat, a chat-based interface to Palimpzest that bridges this gap by letting users create and run sophisticated AI pipelines through natural language alone. By integrating Archytas, a ReAct-based reasoning agent, and Palimpzest's suite of relational and LLM-based operators, PalimpChat provides a practical illustration of how a chat interface can make declarative AI frameworks truly accessible to non-experts. Our demo system is publicly available online. At SIGMOD'25, participants can explore three real-world scenarios--scientific discovery, legal discovery, and real estate search--or apply PalimpChat to their own datasets. In this paper, we focus on how PalimpChat, supported by the Palimpzest optimizer, simplifies complex AI workflows such as extracting and analyzing biomedical data.
title PalimpChat: Declarative and Interactive AI analytics
topic Artificial Intelligence
Databases
Information Retrieval
url https://arxiv.org/abs/2502.03368