def bot_ui():
corp_dir = os.path.join(PROJECT_ROOT, 'Data', 'Corpus')
knbs_dir = os.path.join(PROJECT_ROOT, 'Data', 'KnowledgeBase')
res_dir = os.path.join(PROJECT_ROOT, 'Data', 'Result')
rules_dir = os.path.join(PROJECT_ROOT, 'Data', 'Rules')
with tf.Session() as sess:
predictor = BotPredictor(sess,
corpus_dir=corp_dir,
knbase_dir=knbs_dir,
result_dir=res_dir,
aiml_dir=rules_dir,
result_file='basic')
# This command UI has a single chat session only
session_id = predictor.session_data.add_session()
# print("Welcome to Chat with ChatLearner!")
# print("Type exit and press enter to end the conversation.")
# Waiting from standard input.
sys.stdout.write("> ")
sys.stdout.flush()
question = sys.stdin.readline()
while question:
if question.strip() == 'exit':
print("Bye Bye ~")
break
print(
re.sub(r'_nl_|_np_', '\n',
predictor.predict(session_id, question)).strip())
print("> ", end="")
sys.stdout.flush()
question = sys.stdin.readline()
def bot_ui():
corp_dir = os.path.join(PROJECT_ROOT, 'Data', 'Corpus')
knbs_dir = os.path.join(PROJECT_ROOT, 'Data', 'KnowledgeBase')
res_dir = os.path.join(PROJECT_ROOT, 'Data', 'Result')
with tf.Session() as sess:
predictor = BotPredictor(sess,
corpus_dir=corp_dir,
knbase_dir=knbs_dir,
result_dir=res_dir,
result_file='basic')
# This command UI has a single chat session only
session_id = predictor.session_data.add_session()
# Waiting from standard input.
question = ''.join(sys.argv[1:])
#print(question)#, file=sys.stdout)
#print("\n")
print(
re.sub(r'_nl_|_np_', ' ', predictor.predict(session_id,
question)).strip())
def test_demo():
print("# Creating TF session ...")
corp_dir = os.path.join(PROJECT_ROOT, 'Data', 'Corpus')
knbs_dir = os.path.join(PROJECT_ROOT, 'Data', 'KnowledgeBase')
res_dir = os.path.join(PROJECT_ROOT, 'Data', 'Result')
test_dir = os.path.join(PROJECT_ROOT, 'Data', 'Test')
in_file = os.path.join(test_dir, 'samples.txt')
out_file = os.path.join(test_dir, 'responses.txt')
with tf.Session() as sess:
predictor = BotPredictor(sess,
corpus_dir=corp_dir,
knbase_dir=knbs_dir,
result_dir=res_dir,
result_file='basic')
session_id = predictor.session_data.add_session()
print("# Prediction started ...")
t0 = time.time()
with open(in_file, 'r') as f_in:
with open(out_file, 'a') as f_out:
f_out.write(get_header())
for line in f_in:
sentence = line.strip()
if not sentence or sentence.startswith("#=="):
continue
f_out.write("> {}\n".format(sentence))
output = re.sub(r'_nl_|_np_', '\n',
predictor.predict(session_id,
sentence)).strip()
f_out.write("{}\n\n".format(output))
t1 = time.time()
print(
"# Prediction completed. Time spent on prediction: {:4.2f} seconds"
.format(t1 - t0))
def main():
corp_dir = os.path.join(PROJECT_ROOT, 'Data', 'Corpus')
knbs_dir = os.path.join(PROJECT_ROOT, 'Data', 'KnowledgeBase')
res_dir = os.path.join(PROJECT_ROOT, 'Data', 'Result')
with tf.Session() as sess:
predictor = BotPredictor(sess,
corpus_dir=corp_dir,
knbase_dir=knbs_dir,
result_dir=res_dir,
result_file='basic-32334')
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
host = '127.0.0.1'
port = int(2000)
sock.bind((host, port))
sock.listen(1)
print("chatServer Start...\n")
while True:
connection, client_addr = sock.accept()
# print(connection, client_addr)
data = connection.recv(1024)
data = data.decode("utf-8")
print("data > " + data)
# This command UI has a single chat session only
session_id = predictor.session_data.add_session()
question = data
if question.strip() == 'exit':
print("Thank you for using HeroBot. Goodbye.")
break
answer = predictor.predict(session_id, question)
print("answ > " + answer)
connection.sendall(answer.encode("utf-8"))
connection.close()
sock.close()
def __init__(self, config_file='config.cfg', host='http://localhost', port=9000):
config = configparser.ConfigParser()
config.read(config_file)
self.filter_file = config.get('resource', 'filter_file')
self.load_file = config.get('resource', 'load_file')
self.save_file = config.get('resource', 'save_file')
self.shelve_file = config.get('resource', 'shelve_file')
corp_dir = os.path.join(PROJECT_ROOT, 'Data', 'Corpus')
knbs_dir = os.path.join(PROJECT_ROOT, 'Data', 'KnowledgeBase')
res_dir = os.path.join(PROJECT_ROOT, 'Data', 'Result')
# Initialize the KERNEL
self.mybot = aiml.Kernel()
sess = tf.Session()
self.predictor = BotPredictor(sess, corpus_dir=corp_dir, knbase_dir=knbs_dir, result_dir=res_dir, result_file='basic')
self.session_id = self.predictor.session_data.add_session()
# Create AI Engine
if os.path.isfile("model\AIChatEngine.brn"):
self.mybot.bootstrap(brainFile = "model\AIChatEngine.brn")
else:
self.mybot.bootstrap(learnFiles=self.load_file, commands='load aiml b')
self.mybot.saveBrain("model\AIChatEngine.brn")
#Initialization learning library
self.template = '<aiml version="1.0" encoding="UTF-8">\n{rule}\n</aiml>'
self.category_template = '<category><pattern>{pattern}</pattern><template>{answer}</template></category>'
# Initialize Filter sensitive words
#self.gfw = filter.DFAFilter()
#self.gfw.parse(self.filter_file)
# Use an existing server: StanfordCoreNLP
self.nlp = StanfordCoreNLP(host, port=port, timeout=30000)
self.props = {
'annotators': 'tokenize,ssplit,pos,lemma,ner,parse,depparse,dcoref,relation',
'pipelineLanguage': 'en',
'outputFormat': 'json'
}
# Initialize the Language Tool for GEC
self.tool = language_check.LanguageTool('en-US')
def __init__(self,
config_file='config.cfg',
host='http://localhost',
port=9000):
config = configparser.ConfigParser()
config.read(config_file)
self.load_file = config.get('resource', 'load_file')
self.save_file = config.get('resource', 'save_file')
self.shelve_file = config.get('resource', 'shelve_file')
self.filter_file = config.get('resource', 'filter_file')
corp_dir = os.path.join(PROJECT_ROOT, 'Data', 'Corpus')
knbs_dir = os.path.join(PROJECT_ROOT, 'Data', 'KnowledgeBase')
res_dir = os.path.join(PROJECT_ROOT, 'Data', 'Result')
# Initialize the KERNEL
self.mybot = aiml.Kernel()
sess = tf.Session()
self.predictor = BotPredictor(sess,
corpus_dir=corp_dir,
knbase_dir=knbs_dir,
result_dir=res_dir,
result_file='basic')
self.session_id = self.predictor.session_data.add_session()
# Create AI Engine
if os.path.isfile("model\AIChatEngine.brn"):
self.mybot.bootstrap(brainFile="model\AIChatEngine.brn")
else:
self.mybot.bootstrap(learnFiles=self.load_file,
commands='load aiml b')
self.mybot.saveBrain("model\AIChatEngine.brn")
# Use an existing server: StanfordCoreNLP
self.nlp = StanfordCoreNLP(host, port=port, timeout=30000)
self.props = {
'annotators':
'tokenize,ssplit,pos,lemma,ner,parse,depparse,dcoref,relation',
'pipelineLanguage': 'en',
'outputFormat': 'json'
}
outputSentence: The sessionId is the same as in the input for validation purpose.
The answer is the response from the ChatLearner.
"""
if sessionId not in predictor.session_data.session_dict: # Including the case of 0
sessionId = self.predictor.session_data.add_session()
answer = self.predictor.predict(sessionId, question)
outputSentence = SessionSentence()
outputSentence.sessionId = sessionId
outputSentence.sentence = answer
return outputSentence
if __name__ == "__main__":
corp_dir = os.path.join(PROJECT_ROOT, 'Data', 'Corpus')
knbs_dir = os.path.join(PROJECT_ROOT, 'Data', 'Variety')
res_dir = os.path.join(PROJECT_ROOT, 'Data', 'Result')
rules_dir = os.path.join(PROJECT_ROOT, 'Data', 'Rules')
with tf.Session() as sess:
predictor = BotPredictor(sess, corpus_dir=corp_dir, knbase_dir=knbs_dir,
result_dir=res_dir, aiml_dir=rules_dir,
result_file='basic')
service = [('ChatService', ChatService, {'predictor': predictor})]
app = webservices.WebService(service)
ws = tornado.httpserver.HTTPServer(app)
ws.listen(8080)
print("Web service started.")
tornado.ioloop.IOLoop.instance().start()
PROJECT_ROOT = os.path.abspath(os.path.dirname(__file__))
DIR_PATH = os.path.dirname(os.path.realpath(__file__))
app = Flask(__name__)
CORS(app)
k = aiml.Kernel()
for f in glob.glob(DIR_PATH + '/xml/*.xml'):
k.learn(f)
with tf.Session() as sess:
predictor = BotPredictor(
sess,
corpus_dir=os.path.join(PROJECT_ROOT, 'Data', 'Corpus'),
knbase_dir=os.path.join(PROJECT_ROOT, 'Data', 'KnowledgeBase'),
result_dir=os.path.join(PROJECT_ROOT, 'Data', 'Result'),
result_file='basic'
)
@app.route('/ping', methods=['GET'])
def ping():
return 'pong'
@app.route('/chat', methods=['POST'])
def chat():
session_id = predictor.session_data.add_session()
question = str(request.get_json()['body'])
aiml_reply = k.respond(question)
