File size: 894 Bytes
2b5ccc9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 |
from transformers import RagTokenizer, RagRetriever, RagTokenForGeneration
from datasets import load_dataset
import torch
def load_rag_model():
tokenizer = RagTokenizer.from_pretrained("nklomp/rag-example")
retriever = RagRetriever.from_pretrained("nklomp/rag-example", dataset=load_dataset("your_dataset"))
model = RagTokenForGeneration.from_pretrained("nklomp/rag-example", retriever=retriever)
return tokenizer, model
def query_model(tokenizer, model, query):
inputs = tokenizer(query, return_tensors="pt")
with torch.no_grad():
outputs = model.generate(**inputs)
return tokenizer.decode(outputs[0], skip_special_tokens=True)
# Example usage
tokenizer, model = load_rag_model()
user_query = "I am looking for companies that can handle a large construction project."
response = query_model(tokenizer, model, user_query)
print(response)
|