Spaces:
Running
Running
File size: 3,004 Bytes
92e030f c22aebc 92e030f c22aebc 92e030f c22aebc 92e030f c22aebc 92e030f c22aebc 92e030f c22aebc 92e030f c22aebc 92e030f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
# main.py
# This is the main file that runs the Sanic web server.
from sanic import Sanic, response
from retriever import get_ensemble_retriever
from llm_chain import create_rag_chain
app = Sanic("VibbaBackend")
@app.before_server_start
async def setup_model(app_instance, loop):
"""
Initializes the retriever and RAG chain and attaches them
to the application context before the server starts.
"""
print("Server starting up... Initializing model pipeline.")
retriever = get_ensemble_retriever()
rag_chain = create_rag_chain(retriever)
app_instance.ctx.rag_chain = rag_chain
print("Model pipeline is ready.")
@app.get("/")
async def home(request):
"""
Root endpoint showing app name and description.
"""
html_content = """
<html>
<head>
<title>VibbaBackend</title>
<style>
body {
font-family: Arial, sans-serif;
margin: 40px;
background-color: #f9f9f9;
color: #333;
}
h1 { color: #0073e6; }
.container {
max-width: 800px;
margin: auto;
padding: 20px;
background: #fff;
border-radius: 8px;
box-shadow: 0 2px 6px rgba(0,0,0,0.1);
}
</style>
</head>
<body>
<div class="container">
<h1>VibbaBackend</h1>
<p>
Welcome to the <strong>VibbaBackend</strong> service! 🚀<br><br>
This backend powers a Retrieval-Augmented Generation (RAG) pipeline
using an ensemble retriever and a large language model.
</p>
<p>
<strong>Available endpoints:</strong>
<ul>
<li><code>/getResponse?question=Your+query</code> – Get an answer to your question.</li>
</ul>
</p>
</div>
</body>
</html>
"""
return response.html(html_content)
@app.get("/getResponse")
async def get_response_endpoint(request):
"""
Endpoint to get an answer to a question using the RAG chain.
Expects a 'question' query parameter.
"""
question = request.args.get("question")
if not question:
return response.json(
{"error": "Please provide a 'question' query parameter."},
status=400
)
try:
chain = request.app.ctx.rag_chain
result = chain.invoke(question)
return response.text(result)
except Exception as e:
print(f"An error occurred during invocation: {e}")
return response.json(
{"error": "An internal error occurred while processing your request."},
status=500
)
if __name__ == "__main__":
app.run(host="0.0.0.0", port=7860) |