adding all files

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.9-slim
+
+WORKDIR /code
+
+# Install git (required for pip installing from github)
+RUN apt-get update && apt-get install -y git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements and install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Copy the rest of the application code
+COPY . .
+
+# Expose the port for Streamlit
+EXPOSE 7860
+
+# Command to run the app
+CMD ["streamlit", "run", "app.py", "--server.address=0.0.0.0", "--server.port=7860"]

app.py

@@ -0,0 +1,62 @@
+import streamlit as st
+import json
+# Importing directly from the installed package as requested
+from impresso_pipelines.oneclassadclassifier import AdClassificationPipeline
+
+# --- PAGE CONFIG ---
+st.set_page_config(page_title="Impresso Ad Classifier", layout="centered")
+
+st.title("📰 Impresso Ad Classifier")
+st.markdown("Enter text below to classify it as an Advertisement or Non-Advertisement using the `ad_model_pipeline`.")
+
+# --- LOAD PIPELINE ---
+@st.cache_resource
+def load_pipeline():
+    # Initialize with diagnostics=True to get all parameters
+    return AdClassificationPipeline(diagnostics=True)
+
+try:
+    with st.spinner("Loading pipeline from GitHub..."):
+        pipeline = load_pipeline()
+except Exception as e:
+    st.error(f"Failed to load pipeline: {e}")
+    st.stop()
+
+# --- USER INTERFACE ---
+text_input = st.text_area("Input Text", height=200, placeholder="Paste historical text here...")
+
+if st.button("Classify", type="primary"):
+    if text_input.strip():
+        with st.spinner("Running classification..."):
+            try:
+                # Running the pipeline exactly as shown in your snippet
+                results = pipeline(text_input, precision=2)
+                
+                # Handle if result is a list (batch) or dict (single)
+                # The pipeline usually returns a list for text input, so we take the first item if so
+                if isinstance(results, list) and len(results) > 0:
+                    main_result = results[0]
+                else:
+                    main_result = results
+
+                # --- DISPLAY RESULTS ---
+                st.divider()
+                
+                # 1. Visual Header
+                result_type = main_result.get('type', 'unknown')
+                if result_type == 'ad':
+                    st.success(f"### Result: ADVERTISEMENT")
+                else:
+                    st.info(f"### Result: NON-ADVERTISEMENT")
+
+                # 2. Diagnostics Data
+                st.subheader("Full Diagnostics")
+                st.markdown("Below are the classification details, probabilities, and rule scores:")
+                
+                # Display as pretty JSON
+                st.json(main_result)
+
+            except Exception as e:
+                st.error(f"Error during processing: {e}")
+    else:
+        st.warning("Please enter some text first.")

requirements.txt

@@ -0,0 +1,2 @@
+streamlit
+git+https://github.com/impresso/impresso-pipelines.git@ad_model_pipeline#egg=impresso_pipelines[adclassifier]