AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913041618042880 |
|---|---|
| author | Seal, Shuvam Banerji Poddar, Aheli Mishra, Alok Roy, Dwaipayan |
| author_facet | Seal, Shuvam Banerji Poddar, Aheli Mishra, Alok Roy, Dwaipayan |
| contents | This paper introduces AgriIR, a configurable retrieval augmented generation (RAG) framework designed to deliver grounded, domain-specific answers while maintaining flexibility and low computational cost. Instead of relying on large, monolithic models, AgriIR decomposes the information access process into declarative modular stages -- query refinement, sub-query planning, retrieval, synthesis, and evaluation. This design allows practitioners to adapt the framework to new knowledge verticals without modifying the architecture. Our reference implementation targets Indian agricultural information access, integrating 1B-parameter language models with adaptive retrievers and domain-aware agent catalogues. The system enforces deterministic citation, integrates telemetry for transparency, and includes automated deployment assets to ensure auditable, reproducible operation. By emphasizing architectural design and modular control, AgriIR demonstrates that well-engineered pipelines can achieve domain-accurate, trustworthy retrieval even under constrained resources. We argue that this approach exemplifies ``AI for Agriculture'' by promoting accessibility, sustainability, and accountability in retrieval-augmented generation systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16353 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval Seal, Shuvam Banerji Poddar, Aheli Mishra, Alok Roy, Dwaipayan Information Retrieval Artificial Intelligence This paper introduces AgriIR, a configurable retrieval augmented generation (RAG) framework designed to deliver grounded, domain-specific answers while maintaining flexibility and low computational cost. Instead of relying on large, monolithic models, AgriIR decomposes the information access process into declarative modular stages -- query refinement, sub-query planning, retrieval, synthesis, and evaluation. This design allows practitioners to adapt the framework to new knowledge verticals without modifying the architecture. Our reference implementation targets Indian agricultural information access, integrating 1B-parameter language models with adaptive retrievers and domain-aware agent catalogues. The system enforces deterministic citation, integrates telemetry for transparency, and includes automated deployment assets to ensure auditable, reproducible operation. By emphasizing architectural design and modular control, AgriIR demonstrates that well-engineered pipelines can achieve domain-accurate, trustworthy retrieval even under constrained resources. We argue that this approach exemplifies ``AI for Agriculture'' by promoting accessibility, sustainability, and accountability in retrieval-augmented generation systems. |
| title | AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2604.16353 |