Add app.py and dependencies

app.py

@@ -2,41 +2,55 @@
 import streamlit as st
 import pickle
 import numpy as np
-
+import huggingface_hub import hf_hub_url, cached_download
 import os
 
-downloads_path = '/Users/preethamreddygollapalli/Downloads/model_test_steps.pkl'
-
-# Load the saved model
-with open(downloads_path, 'rb') as file:
-    model_test_steps = pickle.load(file)
 
+def load_model():
+    repo_id = 'Preethamreddy799/NLP_MODEL'
+    filename = 'model_test_steps.pkl'
 
-# Function to process input and make predictions
-def predict_test_steps(input_embedding):
-    input_array = np.array(input_embedding).reshape((1, 1, len(input_embedding)))
-    predicted_steps = model_test_steps.predict(input_array)
-    return predicted_steps[0][0]  # Adjust according to the model's output structure
+    # Get model URL and download
+    model_url = hf_hub_url(repo_id=repo_id, filename=filename)
+    cached_model_path = cached_download(model_url)
 
+    # Load the model from the cached path
+    with open(cached_model_path, 'rb') as file:
+        model = pickle.load(file)
 
-# Streamlit app interface
-st.title("Test Case Prediction App")
-st.write("Enter the test case criteria below to generate test steps and expected results:")
+    print(f"Model loaded successfully from {cached_model_path}")
+    return model
 
-# Input section
-user_input = st.text_area("Input Test Case Criteria", "")
+model = load_model()
 
-if st.button("Generate Predictions"):
-    if user_input:
-        # Simple tokenization and embedding logic (you might need to match this to your training process)
-        input_embedding = [0] * 100  # Replace with actual embedding method for user input
+# Function to generate predictions
+def generate_test_steps(acceptance_criteria, test_data):
+    # Example input preprocessing (tokenization/embedding logic should match training)
+    input_features = np.array([len(acceptance_criteria), len(test_data)]).reshape(1, -1)
 
-        # Predict using the loaded models
-        predicted_test_steps = predict_test_steps(input_embedding)
+    # Generate prediction
+    predicted_steps = model.predict(input_features)
+    return predicted_steps
 
-        # Display the results
-        st.subheader("Predicted Test Steps")
-        st.write(predicted_test_steps)
+# Streamlit App
+st.title("Test Case Steps Generator")
+st.write("This app generates test steps based on Test Case Acceptance Criteria and Test Data.")
 
+# Input section
+acceptance_criteria = st.text_area("Enter Test Case Acceptance Criteria", "")
+test_data = st.text_area("Enter Test Data", "")
+
+# Generate Test Steps
+if st.button("Generate Test Steps"):
+    if acceptance_criteria and test_data:
+        if model:
+            # Call the function to generate predictions
+            test_steps = generate_test_steps(acceptance_criteria, test_data)
+
+            # Display the results
+            st.subheader("Generated Test Steps")
+            st.write(test_steps)
+        else:
+            st.error("Model not loaded. Please check the model repository and file.")
     else:
-        st.warning("Please enter test case criteria before generating predictions.")
+        st.warning("Please fill in both Acceptance Criteria and Test Data.")