Spaces:
Paused
Paused
File size: 1,055 Bytes
334fdf5 34acb45 783cf28 334fdf5 c72165a f34cd04 c72165a 579c6dd c72165a 334fdf5 34acb45 c72165a 579c6dd c72165a 334fdf5 579c6dd 9b7b2f5 334fdf5 |
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 |
from http.server import HTTPServer, BaseHTTPRequestHandler
from urllib.parse import urlparse, parse_qs
import urllib.parse
import json
from llama_cpp import Llama
print("Loading model...")
# llm = Llama(model_path="/home/oluser/olapp/model-q4_K.gguf")
print("Model loaded!")
class OlHandler(BaseHTTPRequestHandler):
def do_GET(self):
query_components = parse_qs(urlparse(self.path).query)
#q = urllib.parse.unquote_plus(query_components["q"]) #.encode("cp1252").decode("utf-8"))
q = query_components["q"][0]
#output = llm.create_completion(
# q,
# max_tokens=32,
# echo=False
#)["choices"][0]["text"].encode("cp1252").decode("utf-8")
self.send_response(200)
self.end_headers()
#self.wfile.write(output.encode('utf-8'))
self.wfile.write(q.encode('utf-8'))
return
if __name__ == '__main__':
olserver = HTTPServer(('0.0.0.0', 7860), OlHandler)
print('Starting server at http://0.0.0.0:7860')
olserver.serve_forever()
|