Custom RAG Pipeline

This is a Retrieval-Augmented Generation (RAG) pipeline built using the google/flan-t5-small model.

Usage

from transformers import pipeline

# Load the model
generator = pipeline("text2text-generation", model="VidishaKhalpada/RAG")

# Generate text
result = generator("Translate English to French: How are you?")
print(result)
Downloads last month
2
Safetensors
Model size
77M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support