AVNLP

All

24 repositories

vectordb
Public
Pipelines for Semantic Search, Metadata Filtering, Hybrid Search, Reranking, and Retrieval-Augmented Generation (RAG) on the TriviaQA, ARC, PopQA, FactScore, an…
haystack pinecone weaviate milvus vector-database llm langchain
Python
•
MIT License
•1•4•0•6•Updated Feb 21, 2026Feb 21, 2026
med-reason-evals
Public
Python
•
MIT License
•0•2•0•1•Updated Feb 16, 2026Feb 16, 2026
biothink
Public
Self-Reflective Question Answering for Biomedical Reasoning
rag biomedical-question-answering self-rag grpo
Python
•
MIT License
•1•5•0•1•Updated Feb 16, 2026Feb 16, 2026
rag-pipelines
Public
Advanced RAG Pipelines and Evaluation
pubmed unstructured rag baml milvus earnings-calls contextual-ai llm langgraph rag-pipeline
Python
•
MIT License
•1•10•0•1•Updated Feb 16, 2026Feb 16, 2026
dspy-opt
Public
Advanced RAG pipeline optimization framework using DSPy. Implements modular RAG pipelines with Query-Rewriting, Sub-Query Decomposition, and Hybrid Search via W…
metadata-extraction query-rewriting rag weaviate dspy rag-pipeline deepeval sub-query-generation
Python
•
MIT License
•1•6•0•1•Updated Feb 16, 2026Feb 16, 2026
llm-finetuning
Public
Pipelines for Fine-Tuning LLMs using SFT and RLHF
lora fine-tuning ppo peft sft dpo kto p-tuning qlora orpo
Python
•
MIT License
•2•6•0•1•Updated Feb 16, 2026Feb 16, 2026
rankers
Public
Modular LLM ranking library for Information Retrieval and RAG. Implements state-of-the-art Pairwise, Setwise, and Listwise ranking with structured generation an…
ranker pairwise listwise pointwise setwise llm-rankers
Python
•
MIT License
•1•5•0•0•Updated Dec 22, 2025Dec 22, 2025
llm-blender
Public
LLM-Blender: Ensembling framework that maximizes LLM performance via pairwise ranking. Employs PairRanker to rank candidates and GenFuser to merge outputs, gene…
rag llms rankers llm-blender
Python
•
MIT License
•3•36•0•0•Updated Dec 20, 2025Dec 20, 2025
rag-model-training
Public
Training code for advanced RAG techniques - Adaptive-RAG, Corrective RAG, RQ-RAG, Self-RAG, Agentic RAG, and ReZero. Reproduces paper methodologies to fine-tune…
rag sft rezero crag llm-training agentic-rag adaptive-rag self-rag grpo rq-rag
Python
•
MIT License
•2•6•0•0•Updated Dec 13, 2025Dec 13, 2025
rrf
Public
Performance Evaluation of Rankers and RRF Techniques for Retrieval Pipelines: Employs Diversity, Lost-in-the-Middle, and Similarity rankers to reorder documents…
ranker rrf reciprocal-rank-fusion similarity-ranker lost-in-the-middle-ranker diversity-ranker
Python
•
MIT License
•1•6•0•0•Updated Nov 23, 2025Nov 23, 2025
avnlp.github.io
Public
MIT License
•0•0•0•0•Updated Oct 2, 2025Oct 2, 2025
grpo
Public
Group Relative Policy Optimization (GRPO) Implementations
reward-functions rlhf grpo
Python
•
MIT License
•0•4•0•0•Updated Sep 3, 2025Sep 3, 2025
prp
Public
Pairwise Ranking Prompting (PRP): Zero-shot LLM reranking library implementing efficient pairwise strategies (Heapsort, Sliding Window, All-Pairs). Mitigates po…
ranker pairwise prp pairwise-ranking-prompting
Python
•
MIT License
•0•3•0•0•Updated Jul 24, 2025Jul 24, 2025
MedRAG
Public
Python
•
Other
•42•0•0•0•Updated Jul 16, 2025Jul 16, 2025
scGPT
Public
Jupyter Notebook
•
MIT License
•316•0•0•0•Updated Jul 9, 2025Jul 9, 2025
BioReason
Public
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
Jupyter Notebook
•
Apache License 2.0
•51•0•0•0•Updated Jun 14, 2025Jun 14, 2025
dataloaders
Public
Dataloaders is a versatile library designed for processing and formatting datasets to support various Retrieval-Augmented Generation (RAG) pipelines, facilitati…
Python
•
MIT License
•1•4•0•0•Updated May 1, 2025May 1, 2025
hyperparameter-tuning
Public
Effect of Optimizer Selection and Hyperparameter Tuning on Training Efficiency and LLM Performance
hyperparameter-tuning adam-optimizer sgd-optimizer sgd-momentum optimizers rmsprop-optimizer
Python
•
MIT License
•1•4•0•0•Updated Apr 16, 2025Apr 16, 2025
.github
Public
MIT License
•0•0•0•0•Updated Jan 2, 2025Jan 2, 2025
PPO-for-Beginners
Public
A simple and well styled PPO implementation. Based on my Medium series: https://medium.com/@eyyu/coding-ppo-from-scratch-with-pytorch-part-1-4-613dfc1b14c8.
Python
•
MIT License
•157•0•0•0•Updated Oct 1, 2024Oct 1, 2024
direct-preference-optimization
Public
Reference implementation for DPO (Direct Preference Optimization)
Python
•
Apache License 2.0
•234•0•0•0•Updated Aug 11, 2024Aug 11, 2024
self-biorag
Public
[ISMB '24] Self-BioRAG: Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models
Python
•10•0•0•0•Updated Apr 4, 2024Apr 4, 2024
GenePT
Public
Jupyter Notebook
•46•0•0•0•Updated Mar 18, 2024Mar 18, 2024
finbert-hf
Public
Python
•
MIT License
•0•0•0•0•Updated Jan 30, 2023Jan 30, 2023