Skip to content

[Feature Request] Enhancements/Updates based on: "HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction"Β #99

@BuildBackBuehler

Description

@BuildBackBuehler

Paper in Question

I imagine that there are algos/techniques to add/build off of with KRAGEN. Forgive me if I'm wrong, haven't read much of it, but stumbled upon it when looking to see what else was out there, competing with KRAGEN (spoiler alert: this is all I found πŸ˜‚).

Describe alternatives you've considered
If KRAGEN support has fell off, which is a concern of mine, then I guess I'll be doing my own science experiments, but I'm no expert in what I'll call the niche-of-all-niches.

Additional context
Looking to see what's out there as I'm not a huge fan of Docker, Python. In an ideal world, it'd be allll Rust(y)!

Edit: After doing a thorough read through...me thinks I may be wrong, forgive me if so. This seems like a step backwards, 'err at least I avoid LangChain at all costs. Curious to see if the team finds anything to build upon from this!

Edit 2: I may have snagged something worth a look @; from the citations of course haha Integrated Contextual Knowledge Graph
Generator (ICKG)

ICKG (Integrated Contextual Knowledge Graph Generator) 2.0 is a knowledge graph construction (KGC) task-specific instruction-following language model fine-tuned from LMSYS's Vicuna-7B, which itself is derived from Meta's LLaMA 2.0 LLM.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions