Create app.py

app.py

@@ -0,0 +1,57 @@
+import json
+import streamlit as st
+from google.oauth2 import service_account
+from google.cloud import language_v1
+
+# Sidebar content
+st.sidebar.title("About This Tool")
+st.sidebar.markdown("### Descriptive Introduction")
+st.sidebar.markdown("This tool leverages Google's NLP technology for text classification.")
+st.sidebar.markdown("### Step-by-Step Guide")
+st.sidebar.markdown("""
+1. **Open the Tool**: Navigate to the URL where the tool is hosted.
+2. **User Input**: Enter the text you want to classify.
+3. **Analyze**: Click the 'Analyze' button.
+4. **View Results**: See the classified categories and their confidence scores.
+""")
+
+# Header and intro
+st.title("Google Cloud NLP Text Classifier")
+st.write("This tool classifies text into predefined categories.")
+
+def sample_classify_text(text_content):
+    # Assuming service_account_info is set in your Streamlit secrets
+    service_account_info = json.loads(st.secrets["google_nlp"])
+    credentials = service_account.Credentials.from_service_account_info(
+        service_account_info, scopes=["https://www.googleapis.com/auth/cloud-platform"]
+    )
+    
+    client = language_v1.LanguageServiceClient(credentials=credentials)
+    document = {"content": text_content, "type_": language_v1.Document.Type.PLAIN_TEXT, "language": "en"}
+    
+    content_categories_version = (
+        language_v1.ClassificationModelOptions.V2Model.ContentCategoriesVersion.V2
+    )
+    response = client.classify_text(
+        request={
+            "document": document,
+            "classification_model_options": {
+                "v2_model": {"content_categories_version": content_categories_version}
+            },
+        }
+    )
+
+    st.write(f"### We found {len(response.categories)} categories")
+    st.write("---")
+
+    for category in response.categories:
+        st.write(f"Category Name: {category.name}")
+        st.write(f"Confidence Score: {category.confidence}")
+        st.write("---")
+
+# User input for text analysis
+user_input = st.text_area("Enter text to classify", max_chars=2500)
+
+if st.button("Analyze"):
+    if user_input:
+        sample_classify_text(user_input)