Skip to content

Enhance output nodes with OpenAlex-inspired topic attributes #31

Description

@FrancisTembo

Problem Statement
OpenAlex provides a robust system of topics and labels that accurately describe research outputs. By adopting a similar framework—as detailed in this system overview—we can enhance our research index. This approach will enable us to categorise and discover outputs more effectively based on key attributes.

Proposed Solution
Investigate the use of large language models (LLMs) to process database nodes and associated metadata, thereby generating structured metadata fields. These enriched metadata fields can be integrated through a dedicated service (e.g., an Azure Function) that periodically runs to update and enhance the nodes in our database.

References

  1. LangChain Structured Outputs
  2. Azure Functions: Create Your First Function Using the Azure Developer CLI
  3. OpenAlex Topic Classification Whitepaper
  4. OpenAlex_topic_mapping_table

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

enhancementNew feature or request

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions