README.md

---
library_name: transformers
tags: []
---
### Requirements
```bash
pip install transformers[torch]
```

### Inference
```python
import json
import requests

def convert_to_json(answer):
    # Replace '<pad>' and '</s>' as per the provided logic
    answer = answer.replace("<pad>", "").replace("</s>", "")
    answer = answer.strip("'")  # Remove leading and trailing single quotes
    
    # Replace 'false' with 'False' and 'true' with 'True' for Python compatibility
    answer = answer.replace("false", "False").replace("true", "True")
    
    # Convert the string to a dictionary
    answer_dict = eval(answer)
    
    # Convert the dictionary to a JSON object
    answer_json = json.dumps(answer_dict)
    
    # Load the JSON object to ensure it's correctly formatted
    json_data = json.loads(answer_json)
    
    return json_data

def valid_url(url):
    valid_list = [
        "github.com", "bitbucket.org", "sourceforge.net", "aws.amazon.com",
        "dev.azure.com", "gitea.com", "gogs.io", "phabricator.com",
        "gitkraken.com", "beanstalkapp.com", "gitlab.com"
    ]
    platform = url.split("//")[1].split("/")[0]

    if platform in valid_list:
        return True
        
    return {'message': 'Provide a valid URL for scanning. Currently, we support PII_Scanner, SAST_Scanner, Sac_Scanner (Open_Source_Security), IaC_Scanner, Container_Scanner'}
```

```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch
import time

tokenizer = AutoTokenizer.from_pretrained("AquilaX-AI/NL-JSON-60M")
model = AutoModelForSeq2SeqLM.from_pretrained("AquilaX-AI/NL-JSON-60M")

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# Change YOUR_QUERY eg: can this https://github.com/mr-vicky-01/educational-assitant on every week using pii and sast scan
query = "Translate the following text to JSON: " + "YOUR_QUERY".lower()
query = query.replace(",", "")

start = time.time()

inputs = tokenizer(query, return_tensors="pt")
model.to(device)
inputs = inputs.to(device)
outputs = model.generate(**inputs, max_length=256)
answer = tokenizer.decode(outputs[0])
json_data = convert_to_json(answer)
try:
    valid = valid_url(json_data["repo"])
    if valid == True:
        print(json_data)
    else:
        print(valid)
except:
    print(json_data)

end = time.time()
print(f"Time taken: {end - start}")
```