Text Classification
Transformers
Safetensors
English
bert
agriculture
agronomy
query-classification
farming
corn
soybeans
rag
routing
text-embeddings-inference
Instructions to use zanegraper/ag_query_classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zanegraper/ag_query_classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="zanegraper/ag_query_classifier")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("zanegraper/ag_query_classifier") model = AutoModelForSequenceClassification.from_pretrained("zanegraper/ag_query_classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| language: en | |
| license: apache-2.0 | |
| pipeline_tag: text-classification | |
| library_name: transformers | |
| tags: | |
| - agriculture | |
| - agronomy | |
| - query-classification | |
| - farming | |
| - corn | |
| - soybeans | |
| - rag | |
| - routing | |
| # Cornbelt AI Agronomy Query Router (MiniLM) | |
| ## Overview | |
| The **Cornbelt AI Agronomy Query Router** is a lightweight classification model designed to analyze farmer queries and determine how they should be processed by an agricultural AI assistant. | |
| The model acts as a **routing layer** for a Retrieval-Augmented Generation (RAG) system by identifying: | |
| - whether a query is agriculture-related | |
| - which crop the query concerns | |
| - agronomic topic categories | |
| - whether additional context such as weather or location may be required | |
| This allows an AI system to efficiently determine which knowledge sources and tools should be used to answer the question. | |
| The model was trained using **MiniLM**, a compact transformer architecture optimized for fast inference. | |
| --- | |
| ## Intended Use | |
| This model is intended to support agronomy-focused AI systems by performing **query understanding and routing** before deeper reasoning or retrieval occurs. | |
| Example use cases include: | |
| - agronomy chat assistants | |
| - agricultural decision support systems | |
| - RAG pipelines for extension publications | |
| - crop management advisory tools | |
| - agronomy knowledge search systems | |
| Typical pipeline usage: | |