Initiative #144
Factoid Finder Tool
Listed in the registry Pilot Original language : English
About the initiative
Description of the initiative
This completed project used the Factoid Finder extracts text from machine-readable PDFs to create searchable content libraries. Small Language Models are used to implement semantic search techniques, allowing users to search the library for relevant passages within the PDFs.
AI family
Bucket rationale Not translated
Production/structuration de connaissances via NLP génératif.
Lifecycle
-
Ideation
Stage status : Completed
June 1, 2025
-
Assessment
Stage status : Completed
-
Approved
Stage status : Completed
-
Development
Stage status : Completed
-
Pilot
Stage status : In progress
-
Production
Stage status : Upcoming
-
Archived
Stage status : Upcoming
Schedule for this initiative
- Completed
- In progress
- Planned
- Not applicable
- Today
- Ideation
A similar need?
Nobody has come forward yet. If your team faces the same problem, say so: it helps bring initiatives together and share a solution.
Contacts
- Requester
- Smith, Melannie
- Sector contact
- Smith, Melannie
- Subject matter expert
- Winegardner, Amanda
- Smith, Melannie
Data and tools
- Sector
- Ecosystems and Oceans Science
- Region
- National Capital Region
- Could this initiative be shared with the Treasury Board Secretariat?
- Yes
- Submitted on
- June 1, 2025
Primary users
- Departmental employees
Government priorities and declaration
- Prime Minister's mandate commitment
- Spending less on government operations so that Canadians can invest more in the people and businesses that will build the strongest economy in the G7.
Declared to TBS Recorded as transmitted to TBS; not editable here.
- Declared name of the AI system
- Factoid Finder Tool
- TBS registry identifier
- 2526-DFO-MPO-011
- Status declared to TBS
- Deployed
- Sent to TBS on
- October 10, 2025
- Purpose of the system, as declared
- Problem: Efficiently extracting and navigating information from machine-readable PDFs. Traditional keyword-based search methods often fall short in identifying contextually relevant content, making it difficult for users to locate specific information within large document libraries. Objective for AI: The Factoid Finder addresses this issue by extracting text from PDFs to build searchable content libraries. It leverages Small Language Models to implement semantic search techniques, enabling users to retrieve contextually relevant passages from within the documents more effectively.