Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,95 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import openai
+import re
+import asyncio
+import httpx
+import time
+from io import StringIO
+from typing import List
+
+# --- CONFIG ---
+st.set_page_config(page_title="🖼️ Alt Text Generator", layout="wide")
+VALID_IMAGE_EXTENSIONS = [".jpg", ".jpeg", ".png", ".webp", ".gif", ".bmp"]
+
+st.title("🖼️ AI Alt Text Generator")
+st.markdown("Generate SEO-friendly alt text for image URLs using GPT-4o Vision.\nMade by [Florian Potier](https://twitter.com/FloPots)")
+
+# --- INPUT API KEY ---
+api_key = st.text_input("🔑 Enter your OpenAI API key", type="password")
+if not api_key:
+    st.stop()
+openai_client = openai.AsyncOpenAI(api_key=api_key)
+
+# --- INPUT FILE ---
+uploaded_file = st.file_uploader("📁 Upload a CSV with image URLs", type=["csv"])
+if not uploaded_file:
+    st.stop()
+
+df = pd.read_csv(uploaded_file)
+st.success("✅ File uploaded successfully")
+st.dataframe(df.head())
+
+# --- COLUMN SELECT ---
+image_col = st.selectbox("🧭 Select the column with image URLs", df.columns)
+
+# --- PROMPT INPUT ---
+prompt_instruction = st.text_area("📝 Enter the prompt to generate alt text",
+    value="Write a concise, SEO-friendly alt text for the image below. Do not use brand names unless visible.")
+
+# --- FILTER IMAGES ---
+def is_valid_image_url(url: str):
+    return any(url.lower().endswith(ext) for ext in VALID_IMAGE_EXTENSIONS)
+
+df["Valid Image"] = df[image_col].astype(str).apply(is_valid_image_url)
+valid_df = df[df["Valid Image"] == True]
+
+if valid_df.empty:
+    st.error("❌ No valid image URLs found. Make sure URLs end with .jpg, .png, .webp, etc.")
+    st.stop()
+
+st.info(f"🔍 {len(valid_df)} valid image URLs found. Invalid ones will be skipped.")
+
+# --- GENERATE ALT TEXT ---
+async def generate_alt_text(url: str, prompt: str):
+    try:
+        response = await openai_client.chat.completions.create(
+            model="gpt-4o",
+            messages=[
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": prompt},
+                        {"type": "image_url", "image_url": {"url": url}}
+                    ]
+                }
+            ]
+        )
+        return response.choices[0].message.content.strip()
+    except Exception as e:
+        return f"ERROR: {e}"
+
+st.markdown("### 🚀 Run Alt Text Generation")
+if st.button("Start Processing"):
+    progress = st.progress(0)
+    results = []
+    urls = valid_df[image_col].tolist()
+
+    async def run_all():
+        for idx, url in enumerate(urls):
+            alt_text = await generate_alt_text(url, prompt_instruction)
+            results.append(alt_text)
+            progress.progress((idx + 1) / len(urls))
+            await asyncio.sleep(1)  # polite delay
+
+    asyncio.run(run_all())
+
+    valid_df["Generated Alt Text"] = results
+    output_df = df.copy()
+    output_df.loc[valid_df.index, "Generated Alt Text"] = valid_df["Generated Alt Text"]
+
+    st.success("✅ Done! Preview of the results:")
+    st.dataframe(output_df[[image_col, "Generated Alt Text"]].head())
 
-"""
-# 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])),
-    ))
+    csv = output_df.to_csv(index=False).encode("utf-8")
+    st.download_button("📥 Download CSV with Alt Text", csv, "alt_text_output.csv", "text/csv")