sageRefiner
Intelligent Context Compression Library for LLM Systems
sageRefiner provides state-of-the-art context compression algorithms to reduce token usage while maintaining semantic quality for Large Language Model applications.
Features
-
8 Compression Algorithms
- LongRefiner: LLM-based selective compression with importance scoring
- REFORM: Attention-based compression with KV cache optimization
- Provence: Sentence-level pruning using DeBERTa reranker
- LLMLingua2: Fast BERT-based token classification
- LongLLMLingua: Question-aware perplexity-based compression
- RECOMP-Abstractive: T5-based summarization
- RECOMP-Extractive: BERT-based sentence selection
- EHPC: Evaluator Heads based efficient compression
-
High Compression Ratios: 2-10x compression while preserving key information
-
Flexible Configuration: YAML/dict-based configuration
-
Production Ready: Battle-tested in the SAGE framework
Installation
# Basic installation
pip install isage-refiner
# With benchmark support
pip install isage-refiner[benchmark]
# Development mode
git clone https://github.com/intellistream/sageRefiner.git
cd sageRefiner
pip install -e .
Quick Start
from sage_refiner import LLMLingua2Compressor
# Initialize compressor
compressor = LLMLingua2Compressor()
# Compress context
result = compressor.compress(
context="Your long document text here...",
question="What is the main topic?",
target_token=500,
)
print(f"Compression rate: {result['compression_rate']:.2%}")
print(f"Compressed: {result['compressed_context']}")
Algorithms
| Algorithm | Model | Best For |
|---|---|---|
| LongRefiner | Qwen/Llama + LoRA | High-quality semantic compression |
| REFORM | Any Llama/Qwen | Fast attention-based selection |
| Provence | DeBERTa | Document-level filtering |
| LLMLingua2 | BERT | Speed-critical applications |
| LongLLMLingua | GPT-2/Llama | Long document scenarios |
| RECOMP-Abst | T5 | Summarization-style compression |
| RECOMP-Extr | BERT | Sentence extraction |
| EHPC | Llama-8B | Evaluator heads selection |
Configuration
from sage_refiner import RefinerConfig
config = RefinerConfig(
algorithm="llmlingua2",
target_token=500,
force_tokens=["important", "keyword"],
)
Examples
# Basic compression
python examples/basic_compression.py
# Compare algorithms
python examples/algorithm_comparison.py
Requirements
- Python 3.11+
- PyTorch 2.0+
- Transformers 4.43+
Benchmarking
The benchmarks module provides a comprehensive evaluation framework for all compression
algorithms:
# Quick comparison of multiple algorithms
pip install isage-refiner[benchmark]
sage-refiner-bench compare \
--algorithms baseline,longrefiner,reform,provence \
--samples 100
# Detailed evaluation with budget sweep
sage-refiner-bench sweep \
--algorithm longrefiner \
--budgets 512,1024,2048,4096
For detailed benchmarking documentation, see benchmarks/README.md and benchmarks/STRUCTURE.md.
Citation
@software{sageRefiner2025,
title = {sageRefiner: Context Compression for LLM},
author = {SAGE Team},
year = {2025},
url = {https://github.com/intellistream/sageRefiner}
}
License
Apache License 2.0
Links
- SAGE Framework: https://github.com/intellistream/SAGE
- Issues: https://github.com/intellistream/sageRefiner/issues
Documentation & Development
- Development Guide - Setup, workflow, and guidelines
- Pre-commit Hooks - Setup and usage guide
- CI/CD Pipeline - Automated checks details
For quick setup:
bash utils/installation/quickstart.sh # Full installation
bash utils/hooks/setup-hooks.sh # Setup pre-commit hooks
Metadata
Release files for isage-refiner 0.1.0.10
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| isage_refiner-0.1.0.10.tar.gz | 87.9 kB | Without provenance | Details for isage_refiner-0.1.0.10.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| isage_refiner-0.1.0.10-py2.py3-none-any.whl | Python 2, Python 3 | none | any | Details for isage_refiner-0.1.0.10-py2.py3-none-any.whl |
Total release size: 168.0 kB
Release files / isage_refiner-0.1.0.10.tar.gz
| Download URL | isage_refiner-0.1.0.10.tar.gz |
|---|---|
| Size | 87.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fb7d5635abebdc69d1368d04957a0e1b3430c9561617d0cb9674eff50d496d88
|
|
BLAKE2b-256 checksum How to use checksums |
68509c2b5dee7b9823bd4dccdfd348c2c71b9b5e0f3d4d4cb7c822887d613584
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.14
|
Release files / isage_refiner-0.1.0.10-py2.py3-none-any.whl
| Download URL | isage_refiner-0.1.0.10-py2.py3-none-any.whl |
|---|---|
| Size | 80.1 kB |
| Tags | Python 2 Python 3 |
|
SHA-256 checksum How to use checksums |
84347fddfe6c0d0bb1a91b4feca27501356cdef94d869bb958c9a139c812777e
|
|
BLAKE2b-256 checksum How to use checksums |
857d38fc8b7924235ccc30fac02e5ac14da1b1e5418a0fe1830ac09417b142d8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.14
|
Security for isage-refiner 0.1.0.10
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.