class DialogBackendLocal(DialogBackend):
def __init__(self):
super().__init__()
self.model_mrc = BidafQA()
self.model_cmr = ConversingByReading()
self.model_open = DialoGPT()
self.kb = KnowledgeBase()
model_mmi = DialoGPT(path_model='models/DialoGPT/small_reverse.pkl')
self.ranker = Ranker(self.model_open, model_mmi)
self.local = True
def predict(self, context, max_n=-1):
context, query = self.history2inp(context)
print('backend running, context = %s' % context)
# get results from different models
results = self.model_open.predict(context)
passages = []
url_snippet = []
for line in open('args/kb_sites.txt', encoding='utf-8'):
cust = line.strip('\n')
kb_args = {'domain': 'cust', 'cust': cust, 'must_include': []}
url_snippet.append(self.kb.predict(query, args=kb_args)[0])
passage = ' ... '.join([snippet for _, snippet in url_snippet])
passages.append((passage, query))
for passage, kb_query in passages:
results += self.model_mrc.predict(kb_query, passage)
results += self.model_cmr.predict(kb_query, passage)
# rank hyps from different models
hyps = [hyp for _, _, hyp in results]
scored = self.ranker.predict(context, hyps)
ret = []
for i, d in enumerate(scored):
d['way'], _, d['hyp'] = results[i]
ret.append((d['score'], d))
ranked = [d for _, d in sorted(ret, reverse=True)]
if max_n > 0:
ranked = ranked[:min(len(ranked), max_n)]
return ranked, url_snippet
class DialogBackendLocal(DialogBackend):
def __init__(self):
super().__init__()
self.model_lm = LanguageModel()
self.model_ct = ContentTransfer()
self.kb = KnowledgeBase()
self.ranker = Ranker(self.model_lm)
self.local = True
def predict(self, context, max_n=1):
print('backend running, context = %s' % context)
query = self.get_query(context)
# get results from different models
results = self.model_lm.predict(context)
passages = []
url_snippet = []
for line in open('args/kb_sites.txt', encoding='utf-8'):
cust = line.strip('\n')
kb_args = {'domain': 'cust', 'cust': cust, 'must_include': []}
url_snippet.append(self.kb.predict(query, args=kb_args)[0])
passage = ' ... '.join([snippet for _, snippet in url_snippet])
passages.append((passage, query))
for passage, kb_query in passages:
results += self.model_ct.predict(kb_query, passage)
# rank hyps from different models
hyps = [hyp for _, _, hyp in results]
scored = self.ranker.predict(context, hyps)
ret = []
for i, d in enumerate(scored):
d['way'], _, d['hyp'] = results[i]
ret.append((d['score'], d))
ranked = [d for _, d in sorted(ret, reverse=True)]
if max_n > 0:
ranked = ranked[:min(len(ranked), max_n)]
return ranked, url_snippet
