pkargupta/taxoadapt
Dynamically constructs and adapts an LLM-generated taxonomy to a given corpus across multiple dimensions.
Implements iterative hierarchical classification that expands taxonomy width and depth based on corpus topical distribution, with separate taxonomies generated across user-defined research dimensions. Integrates with OpenAI's GPT API (or vLLM) for LLM prompting and HuggingFace datasets, using a density-driven expansion mechanism that triggers refinement when leaf nodes exceed configurable thresholds. Evaluated on computer science conference corpora to capture evolving research landscapes with 26.51% better granularity preservation and 50.41% improved coherence versus comparable baselines.
No commits in the last 6 months.
Stars
35
Forks
11
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/pkargupta/taxoadapt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
llmware-ai/llmware
Unified framework for building enterprise RAG pipelines with small, specialized models
Sinapsis-AI/sinapsis-chatbots
Monorepo for sinapsis templates supporting LLM based Agents
aimclub/ProtoLLM
Framework for prototyping of LLM-based applications
Azure-Samples/azureai-foundry-finetuning-raft
A recipe that will walk you through using either Meta Llama 3.1 405B or OpenAI GPT-4o deployed...
xi029/Qwen3-VL-MoeLORA
在千问最新的多模态image-text模型Qwen3-VL-4B-Instruct 进行多种lora微调对比效果，通过langchain+RAG+多智能体(Multi-Agent)进行部署