to open my app

src/streamlit_app.py

@@ -1,40 +1,48 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
-
-"""
-# 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])),
-    ))
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from youtubesearchpython import VideosSearch
+
+# Load FLAN-T5
+st.set_page_config(page_title="🔧 AI Vehicle Repair Assistant", layout="centered")
+@st.cache_resource
+def load_model():
+    tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base")
+    model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base")
+    return tokenizer, model
+
+tokenizer, model = load_model()
+
+# App UI
+
+st.title("🔧 AI Vehicle Repair Assistant")
+st.caption("Get brief repair instructions and a helpful YouTube video.")
+
+# Inputs
+vehicle = st.selectbox("Choose Vehicle Type:", ["Car", "Bike"])
+issue = st.text_area("Describe the issue (e.g. engine won't start, AC not cooling):", height=100)
+
+# Button
+if st.button("🔍 Get Repair Instructions"):
+    if issue.strip() == "":
+        st.warning("Please enter a vehicle issue.")
+    else:
+        # Prompt for FLAN-T5
+        prompt = f"Give a short repair tip for a {vehicle.lower()} with this issue: {issue}."
+        inputs = tokenizer(prompt, return_tensors="pt", max_length=128, truncation=True)
+        outputs = model.generate(**inputs, max_new_tokens=100)
+        instruction = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+        # Show AI output
+        st.markdown("### 🛠 Repair Tip:")
+        st.success(instruction)
+
+        # Search YouTube
+        query = f"{vehicle} {issue} repair"
+        videos_search = VideosSearch(query, limit=1)
+        results = videos_search.result()["result"]
+        if results:
+            video_url = results[0]["link"]
+            st.markdown("### 📺 Watch Tutorial:")
+            st.video(video_url)
+        else:
+            st.info("No matching video found.")