NARA · NARA - 0006 · record R3202

AI based Semantic Search for National Archives Catalog (aka ArchiAI)

National Archives and Records Administration · National Archives & Records Administration (NARA)

Overview

Development stage: PilotSource: b) Pilot – The use case has been deployed in a limited test or pilot capacity.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: 2024-09-01 (day precision)Source: 2024-09-01T00:00:00
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Other
Operational functions: Search and knowledge retrieval Derived by keyword rules; see methodology

Problem the AI is intended to solve

The AI is intended to solve the problem of "unsophisticated" keyword-based search limitations by implementing semantic search that understands user intent and historical context, allowing researchers to find relevant records even when they don't match exact search terms.

Expected benefits

NARA is using AI to create a smarter search engine for its online catalog. This new search understands the meaning behind your search, not just the keywords, and can even find hidden connections between documents. This will make research faster, easier, and more insightful.

System outputs

This AI search tool will provide better search results and show connections between records, making research easier and more insightful.

Technology

AI classification: Natural language processingSource: Natural Language Processing: AI that processes, interprets, and shares information in human language.
System name(s): Catalog
Custom-developed code: Yes
Public source code: Not reported

Sourcing

How it was built: Developed in-houseSource: b) Developed in-house
Vendor (as reported): Not reported
Vendors (standardized): None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII: No
Privacy Impact Assessment: Not reported
Authorization to Operate: Yes
Demographic features: k) None of the above
Training and evaluation data: Agency is strictly using its data to test the pre-trained model for the purpose of prototype work. The data is publicly available at catalog.archives.gov.
Federal Data Catalog: Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported