Skip to content

MAINTENANCE.md

Latest commit

 

History

History
29 lines (21 loc) · 3.3 KB

MAINTENANCE.md

File metadata and controls

29 lines (21 loc) · 3.3 KB
Raw

DeepResearch Maintenance Plan

1. Objectives & Responsibilities

The primary goals of the Deep Research maintenance objectives are to:

  • Ensure long-term availability and functionality of the code by addressing and fix bugs and issues as they arise.
  • Continuously add search systems and extend support for various LLM libraries.
  • Incorporate user feedback and adapt to evolving research trends.
  • Maintain up-to-date documentation to support ease of use and understanding.
  • Regularly review and update dependencies to maintain compatibility with the latest technology and standards.

A core team will be responsible for the ongoing maintenance of Deep Research, including:

  • Lead Maintainer: Oversee all maintenance activities, ensure the direction aligns with the project's vision, and handle critical issues.
    • Dr. Jennifer D'Souza – Responsible for guiding ideation, refining ideas, and defining the project's high-level direction to align the library's goals with broader academic and research objectives.

2. Current Ongoing Maintenance and Plans

A roadmap for new features and improvements, ensuring the library evolves in response to user needs and feedback is presented as follows. This list will be updated regularly as we explore the variety of works within the ontology alignment field to ensure the diverse methods within the library.

Category Description Status
Citation or Evidence grounding Add reference links to the sources within the generated report or answer. So basically to ground the sentence from the generated source. TODO
Search engine support Integrate other search systems (https://serper.dev/, https://api.semanticscholar.org/api-docs/). Allow the user the option to choose multiple or just a single search system TODO
Handle full-text as part of learnings At the moment, the ORKG search only focuses on titles and abstracts. TODO
OpenAI-compatible LLM libraries Support for other OpenAI-compatible libraries like Ollama... TODO
Other LLM libraries Support for other LLM libraries like HuggingFace. This would entail adding special features for processing structured content like those within <think> tokens or in the responses since pydantic is not fully supported in these contexts. TODO
... ... ..