Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,76 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import duckdb
+import requests
+import re
+import os
 
-"""
-# Welcome to Streamlit!
+st.set_page_config(page_title="🧠 SQL Chatbot with Groq", layout="centered")
+
+# 🔐 Load Groq API Key from Hugging Face secret or env var
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+
+if not GROQ_API_KEY:
+    st.error("❌ GROQ_API_KEY not found. Please set it in Streamlit Secrets or environment.")
+    st.stop()
+
+# 🧠 Generate SQL using Groq API
+def generate_sql(prompt, df):
+    schema = ", ".join([f"{col} ({dtype})" for col, dtype in df.dtypes.items()])
+    full_prompt = f"""
+You are a SQL expert. The table 'df' has the following columns and types:
+{schema}
 
-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).
+User question: "{prompt}"
 
-In the meantime, below is an example of what you can do with just a few lines of code:
+Write a valid SQL query using the 'df' table. Return only the SQL.
 """
 
-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])),
-    ))
+    headers = {
+        "Authorization": f"Bearer {GROQ_API_KEY}",
+        "Content-Type": "application/json"
+    }
+    payload = {
+        "model": "llama3-70b-8192",
+        "messages": [{"role": "user", "content": full_prompt}],
+        "temperature": 0.2,
+        "max_tokens": 300
+    }
+
+    url = "https://api.groq.com/openai/v1/chat/completions"
+    response = requests.post(url, headers=headers, json=payload)
+    response.raise_for_status()
+    result = response.json()
+    return result["choices"][0]["message"]["content"].strip()
+
+# 🧽 Clean SQL
+def clean_sql(sql, df_columns):
+    sql = sql.replace("`", '"')
+    for col in df_columns:
+        if " " in col and f'"{col}"' not in sql:
+            pattern = r'\b' + re.escape(col) + r'\b'
+            sql = re.sub(pattern, f'"{col}"', sql)
+    return sql
+
+# 🖥️ UI
+st.title("📊 Excel SQL Chatbot (Groq + Streamlit)")
+uploaded_file = st.file_uploader("📂 Upload your Excel file", type=["xlsx"])
+user_prompt = st.text_input("🧠 Ask a question about your data")
+
+if st.button("🚀 Generate & Run SQL"):
+    if uploaded_file and user_prompt:
+        try:
+            df = pd.read_excel(uploaded_file)
+            sql = generate_sql(user_prompt, df)
+            cleaned_sql = clean_sql(sql, df.columns)
+            result = duckdb.query(cleaned_sql).to_df()
+
+            st.markdown(f"### 🧾 Generated SQL")
+            st.code(sql, language="sql")
+            st.markdown("### 📈 Query Results")
+            st.dataframe(result)
+
+        except Exception as e:
+            st.error(f"❌ Error: {str(e)}")
+    else:
+        st.warning("⚠️ Please upload a file and enter a question.")