Create app.py

app.py

@@ -0,0 +1,81 @@
+import gradio as gr
+import requests
+import os
+import faiss
+import numpy as np
+import json
+from fastapi import FastAPI, Request
+from pydantic import BaseModel
+from sentence_transformers import SentenceTransformer
+
+# ✅ Load vector data
+with open("texts.json", "r", encoding="utf-8") as f:
+    texts = json.load(f)
+
+index = faiss.read_index("faiss_index.bin")
+embed_model = SentenceTransformer("all-MiniLM-L6-v2")
+
+API_KEY = os.environ.get("OPENROUTER_API_KEY")
+MODEL = "qwen/qwen-2.5-coder-32b-instruct:free"
+
+# ✅ Semantic search
+def get_context(query, top_k=5):
+    query_vec = embed_model.encode([query])
+    D, I = index.search(np.array(query_vec), top_k)
+    return "\n".join([texts[i] for i in I[0]])
+
+# ✅ Chatbot response
+def chat_fn(message, history):
+    headers = {
+        "Authorization": f"Bearer {API_KEY}",
+        "Content-Type": "application/json"
+    }
+
+    context = get_context(message)
+    messages = [{"role": "system", "content": f"You are CODEX Assistant by Mirxa Kamran. Use this context:\n{context}"}]
+
+    for user, assistant in history:
+        messages.append({"role": "user", "content": user})
+        messages.append({"role": "assistant", "content": assistant})
+
+    messages.append({"role": "user", "content": message})
+
+    payload = {"model": MODEL, "messages": messages}
+
+    try:
+        response = requests.post("https://openrouter.ai/api/v1/chat/completions", headers=headers, json=payload)
+        response.raise_for_status()
+        reply = response.json()["choices"][0]["message"]["content"]
+    except Exception as e:
+        reply = f"❌ Error: {e}"
+
+    return reply
+
+# ✅ Gradio UI
+demo = gr.ChatInterface(
+    fn=chat_fn,
+    title="💻 CODEX Assistant by Mirxa Kamran",
+    description="Chat with a context-aware AI code assistant.",
+    theme="soft"
+)
+
+# ✅ FastAPI app
+app = FastAPI()
+
+# ✅ Mount Gradio on root path
+app = gr.mount_gradio_app(app, demo, path="/")
+
+# ✅ FastAPI POST API endpoint
+class ChatRequest(BaseModel):
+    message: str
+    history: list = []
+
+@app.post("/chat")
+def api_chat(req: ChatRequest):
+    reply = chat_fn(req.message, req.history)
+    return {"response": reply}
+
+# ✅ Run manually in local dev or on Spaces
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)