Update app.py

app.py

@@ -2,7 +2,7 @@ import os
 import gradio as gr
 import numpy as np
 import tensorflow as tf
-from transformers import InferenceClient
+from transformers import pipeline
 from dotenv import load_dotenv
 import nltk
 
@@ -10,9 +10,9 @@ import nltk
 load_dotenv()
 hf_api_key = os.getenv("HUGGING_FACE_KEY")
 
-# Initialize Hugging Face Inference Client for Llama Model
+# Initialize Hugging Face Text Generation Pipeline
 llama_model = "meta-llama/Meta-Llama-3.1-8B-Instruct"
-client = InferenceClient(model=llama_model, token=hf_api_key)
+text_generator = pipeline("text-generation", model=llama_model, use_auth_token=hf_api_key)
 
 # Load the TensorFlow model
 model = tf.keras.models.load_model("resume_generator_model.h5")
@@ -21,13 +21,12 @@ model = tf.keras.models.load_model("resume_generator_model.h5")
 def enhance_with_huggingface(resume_text, job_title):
     """Generate enhanced resume content using Llama."""
     prompt = f"Enhance the following resume for the job title '{job_title}': {resume_text}"
-    response = client.text_generation(prompt, max_length=500)
-    return response['generated_text']
+    response = text_generator(prompt, max_length=500, num_return_sequences=1)
+    return response[0]['generated_text']
 
 def enhance_with_local_model(resume_text, job_title):
     """Generate enhancements using local TensorFlow model."""
     # Placeholder example: Use some custom logic for enhancement based on the local model.
-    # This is a simplified example assuming model returns some text modification.
     sample_input = np.array([[len(resume_text.split()), len(job_title.split())]])
     enhancement_score = model.predict(sample_input)
     return f"Enhanced (Local Model) - Score: {enhancement_score[0][0]:.2f}"