Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,187 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import requests
+import json
+import base64
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+# Configuration
+API_URL = "https://openrouter.ai/api/v1/chat/completions"
+
+def encode_image(uploaded_file):
+    """Encodes the uploaded file to base64."""
+    bytes_data = uploaded_file.getvalue()
+    return base64.b64encode(bytes_data).decode('utf-8')
+
+def analyze_receipt(base64_image, prompt_text, api_key):
+    """Sends the image to OpenRouter API for analysis."""
+    if not api_key:
+        return {"error": "API Key is missing."}
+        
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json"
+    }
+
+    data_url = f"data:image/jpeg;base64,{base64_image}"
+
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": prompt_text
+                },
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": data_url
+                    }
+                }
+            ]
+        }
+    ]
+
+    payload = {
+        "model": "qwen/qwen3-vl-8b-instruct",
+        "messages": messages
+    }
+
+    try:
+        response = requests.post(API_URL, headers=headers, json=payload)
+        response.raise_for_status() # Raise an error for bad status codes
+        return response.json()
+    except requests.exceptions.RequestException as e:
+        return {"error": str(e)}
+
+# Streamlit App UI
+st.set_page_config(page_title="Receipt Analyzer", page_icon="🧾", layout="wide")
+
+st.title("🧾 Receipt Cost Breakdown (Qwen 3-VL-8B)")
+st.markdown("Upload a receipt image to get a JSON breakdown of costs.")
+
+# Sidebar for configuration
+with st.sidebar:
+    st.header("⚙️ Configuration")
+    
+    # API Key Input for User Inference
+    st.subheader("API Access")
+    api_key = st.text_input("OpenRouter API Key", type="password", help="Enter your OpenRouter API Key here.")
+    if not api_key:
+        st.warning("Please enter your API Key to proceed.")
+    
+    st.divider()
+
+    # User-friendly schema builder - PRIORITY 1
+    # st.markdown("Define what to extract from the receipt.") # Removed to save space
+    st.subheader("Fields to Extract")
+    
+    default_fields = ["Merchant Name", "Total Amount", "Currency", "Date"]
+    available_fields = ["Merchant Name", "Total Amount", "Currency", "Date", "Tax/VAT", "Address", "Time", "Payment Method"]
+    
+    selected_fields = st.multiselect(
+        "Select fields:",
+        options=available_fields,
+        default=default_fields,
+        help="Leave empty to extract **ALL** available information automatically."
+    )
+    
+    if not selected_fields:
+        st.caption("✅ *No fields selected. The model will extract everything it finds.*")
+    
+    extract_line_items = st.checkbox("Extract Line Items (Name & Price)", value=True)
+    
+    st.divider()
+    
+    # Custom instructions - PRIORITY 2
+    custom_instructions = st.text_input(
+        "Custom Instructions (Optional)",
+        placeholder="e.g., Extract the cashier name",
+        help="Add any specific data points or rules not covered above."
+    )
+
+    st.divider()
+
+    # Model Indicator - MOVED TO BOTTOM
+    with st.expander("ℹ️ About the Model", expanded=False):
+        st.info(
+            "**Qwen 3-VL-8B**\n\n"
+            "This is an open-source model efficient enough to run locally on consumer hardware."
+        )
+
+    # Construct the prompt dynamically
+    if not selected_fields:
+        # User selected nothing -> Extract all
+        prompt_text = "Analyze this receipt image. Extract **all** visible information including merchant details, dates, totals, taxes, and address in a structured JSON format."
+    else:
+        # User selected specific fields
+        field_str = ", ".join(selected_fields)
+        prompt_text = f"Analyze this receipt image. Extract the following information in JSON format: {field_str}."
+    
+    if extract_line_items:
+        prompt_text += " Also include a detailed list of 'items' containing 'name' and 'price'."
+        
+    if custom_instructions:
+        prompt_text += f" Additionally: {custom_instructions}."
+    
+    # Enforce JSON structure
+    prompt_text += " Return a single valid JSON object. Do not include markdown formatting."
+    
+    # Store in variable to match existing function call
+    custom_prompt = prompt_text
+
+uploaded_file = st.file_uploader("Choose a receipt image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    col1, col2 = st.columns(2)
+    
+    with col1:
+        # Display the uploaded image
+        st.image(uploaded_file, caption="Uploaded Receipt", use_column_width=True)
+        analyze = st.button("Analyze Receipt", type="primary", use_container_width=True)
+
+    with col2:
+        if analyze:
+            if not api_key:
+                st.error("Please enter an API Key in the sidebar.")
+            else:
+                with st.spinner("Analyzing receipt..."):
+                    # Encode image
+                    base64_image = encode_image(uploaded_file)
+                    
+                    # Call API
+                    api_result = analyze_receipt(base64_image, custom_prompt, api_key)
+                    
+                    # Handle response
+                    if "error" in api_result:
+                        st.error(f"Error calling API: {api_result['error']}")
+                    elif "choices" in api_result:
+                        content = api_result["choices"][0]["message"]["content"]
+                        
+                        with st.expander("🔍 Raw Analysis Output"):
+                            st.code(content, language="json")
+                        
+                        # Try to clean and parse JSON if markdown code blocks are used
+                        try:
+                            # Clean up code blocks if present
+                            json_str = content.replace("```json", "").replace("```", "").strip()
+                            parsed_json = json.loads(json_str)
+                            
+                            st.success("Analysis Complete!")
+                            st.subheader("Structured Data")
+                            st.json(parsed_json)
+                            
+                            # Optional: Display as a nice table
+                            if "items" in parsed_json and isinstance(parsed_json["items"], list):
+                                st.subheader("Itemized Breakdown")
+                                st.dataframe(parsed_json["items"], use_container_width=True)
+                            
+                            # Display other top-level keys as metrics if simple
+                            for key, value in parsed_json.items():
+                                if key != "items" and isinstance(value, (int, float, str)):
+                                    st.metric(key.title(), value)
+                                
+                        except json.JSONDecodeError:
+                            st.warning("Could not parse the response as JSON. See the raw output above.")
+                    else:
+                        st.error("Unexpected response format from API.")
+                        st.json(api_result)