Ahren09 / SARA
Official Implementation for the ACL 2026 paper "SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression"
Why this job: says: retrieval augmented; topics: rag, retrieval-augmented-generation
What it does
- Two-method, apples-to-apples. Standard RAG vs SARA under identical data, retriever, prompts, decoding, and seeds.
- Projector + tokens. retriever embeddings projected into the LM hidden space at compress positions.
- LoRA-first. adapters + projector only — no merged or full-model checkpoints are ever saved.
- Fully batched generation and evaluation (dynamic padding, one GPU call per batch).
- Leakage-safe. document-level (per-paper) train/dev/test splits.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 258
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 84% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 0% closed
- 1 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| VectifyAI / PageIndex | 40,264 | 4 days ago | MIT | No downloads |
| bosun-ai / swiftide | 803 | 3 days ago | MIT | No downloads |
| MLSysOps / MLE-agent | 1,580 | 4 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 84%
- JavaScript 11%
- HTML 4%
- CSS <1%
Topics
- ai
- context-compression
- context-engineering
- efficiency
- llm
- ml
- rag
- retrieval-augmented-generation
Project record
- JobRAG and search
- StatusListed
- Commits2
- Forks0
- Watching0
- Stars in 28 days+3
- CreatedAug 16, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026