cllm integration design doc

[puja-trivedi]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @puja-trivedi, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a comprehensive design document detailing the proposed integration of the Claim LLM (CLLM) tool. The primary objective is to establish a robust pipeline for extracting and evaluating scientific claims from research papers using large language models, and subsequently ingesting this structured data into a knowledge graph. This foundational work aims to enhance the system's capability for automated scientific claim verification and analysis, paving the way for advanced features and broader application within the StructSense framework.

Highlights

• New Design Document: A new design document, cllm_integration.md, has been added to outline the integration of the Claim LLM (CLLM) tool.
• CLLM Overview and Workflow: The document provides an overview of CLLM, a command-line tool for extracting, evaluating, and comparing scientific claims using Large Language Models, detailing its 4-stage workflow.
• Minimum Viable Product (MVP): An MVP is defined for ingesting assertions and evidence from scientific papers into a knowledge graph using CLLM, including steps for input, processing, output formatting, and ingestion.
• Architectural Diagram: A Mermaid flowchart visually represents the proposed CLLM CLI integration architecture, illustrating the data flow from input to knowledge graph ingestion.
• Future Enhancements: The document outlines future plans, such as integrating peer review evaluations, developing a user interface, and incorporating CLLM into the StructSense Agentic Framework.
• Example Outputs: Example CLLM output metrics, including extraction and evaluation details, costs, and processing times for several bioRxiv papers, are provided.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• doc/design/cllm_integration.md
  • Added a new design document outlining the integration proposal for the Claim LLM (CLLM) tool, including its overview, MVP, future enhancements, architectural diagram, and example outputs.

Activity

• The pull request was created by puja-trivedi.
• No further human activity (comments, reviews, or updates) has been recorded since its creation.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a design document for integrating the CLLM tool. The document is well-structured and clearly outlines the overview, MVP, future enhancements, and architecture. My review includes a couple of minor formatting suggestions to improve the readability and correctness of the markdown file, particularly in the output results table.

[tekrajchhetri]

@puja-trivedi How does this align with StructSense? The design document doesn't make clear on how it will be integrated with the StructSense. Also, what is it that CLLM does differently, is it the prompt based? If yes, can't we just incorporate those prompts? If not, can we use CLLM as tool in StructSense or the core components as tools?

Please remember, we have the extraction pipeline in theStructSense already.

[tekrajchhetri]

@puja-trivedi It looks like you're thinking from the independent application, is it so?

[tekrajchhetri]

The UI development should be the part of the BrainKB UI as it integrates different application. I believe this design document here should only focus on how it will be integrated with StructSense.

[tekrajchhetri]

Please check the comments below.

[tekrajchhetri]

Please check the comments below.