Update app.py

app.py

@@ -1,4 +1,5 @@
-import gradio as gr
+from fastapi import FastAPI
+from pydantic import BaseModel
 import requests
 import os
 import faiss
@@ -6,35 +7,53 @@ import numpy as np
 import json
 from sentence_transformers import SentenceTransformer
 
-# ✅ Load context data
+# ✅ Load your texts and vector index
 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")
+# ✅ Setup your API key and model name
+API_KEY = os.environ.get("OPENROUTER_API_KEY")  # Set this in environment or .env file
 MODEL = "qwen/qwen-2.5-coder-32b-instruct:free"
 
-# ✅ Get top-k context from FAISS
+# ✅ Define FastAPI app
+app = FastAPI()
+
+# ✅ Request schema
+class ChatRequest(BaseModel):
+    message: str
+    history: list = []  # Optional, not used in current logic
+
+# ✅ Function to get top-k similar chunks from FAISS
 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]])
 
-# ✅ Gradio chatbot function (takes message and history)
-def chat_fn(message, history):
+# ✅ Endpoint
+@app.post("/chat")
+def chat_api(data: ChatRequest):
+    user_message = data.message
+    context = get_context(user_message)
+
+    messages = [
+        {
+            "role": "system",
+            "content": f"You are a helpful coding assistant. Use the following context to answer the question:\n{context}"
+        },
+        {
+            "role": "user",
+            "content": user_message
+        }
+    ]
+
     headers = {
         "Authorization": f"Bearer {API_KEY}",
         "Content-Type": "application/json"
     }
 
-    context = get_context(message)
-    messages = [
-        {"role": "system", "content": "You are a helpful assistant. Use the following context: " + context},
-        {"role": "user", "content": message}
-    ]
-
     payload = {
         "model": MODEL,
         "messages": messages
@@ -43,22 +62,9 @@ def chat_fn(message, history):
     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"]
+        result = response.json()
+        reply = result["choices"][0]["message"]["content"]
     except Exception as e:
-        reply = f"❌ Error: {e}"
-
-    return reply
-
-# ✅ ChatInterface now exposed at /chat
-demo = gr.ChatInterface(
-    fn=chat_fn,
-    title="CODEX MIRXA KAMRAN",
-    description="Chat with our RAG-enabled coding assistant powered by OpenRouter",
-    examples=["How do I use pandas to filter rows?", "Fix this bug in my code", "What is Python typing?"],
-    theme="soft",
-    chatbot=gr.Chatbot(height=400),
-    api_name="/chat"
-)
+        reply = f"❌ Error: {str(e)}"
 
-if __name__ == "__main__":
-    demo.launch()
+    return {"reply": reply}