Create app.py

app.py

@@ -0,0 +1,56 @@
+import streamlit as st
+from huggingface_hub import InferenceClient
+from dotenv import load_dotenv
+import os
+
+# Load environment variables
+load_dotenv()
+api_key = os.getenv("HF_API_KEY")
+
+# Initialize Hugging Face client
+client = InferenceClient(api_key=api_key)
+
+# Streamlit UI
+st.title("Job Fit Assessment")
+st.write("Find out if your resume is a strong fit for the job you're applying to.")
+
+# User inputs
+job_title = st.text_input("Job Title")
+job_description = st.text_area("Job Description")
+resume_description = st.text_area("Resume Description")
+educational_qualifications = st.text_area("Educational Qualifications")
+
+if st.button("Assess Job Fit"):
+    # Combine inputs into a message for the model
+    input_text = (
+        f"Based on the following:\n"
+        f"- Job Title: {job_title}\n"
+        f"- Job Description: {job_description}\n"
+        f"- Resume Description: {resume_description}\n"
+        f"- Educational Qualifications: {educational_qualifications}\n\n"
+        "Evaluate if this candidate's profile is a strong fit for the job."
+    )
+    
+    messages = [{"role": "user", "content": input_text}]
+    
+    # Make the API call
+    result = ""
+    try:
+        stream = client.chat.completions.create(
+            model="meta-llama/Llama-3.2-1B-Instruct",
+            messages=messages,
+            max_tokens=500,
+            stream=True
+        )
+        
+        # Collect the response in chunks
+        for chunk in stream:
+            content = chunk.choices[0].delta.content
+            result += content
+        
+        # Display the full result at once
+        st.write("Job Fit Assessment Result:")
+        st.write(result)
+
+    except Exception as e:
+        st.error(f"Error: {e}")