{ "cells": [ { "cell_type": "code", "execution_count": 212, "id": "706dd5e1-57ee-416b-a77c-5d15df8dbdc8", "metadata": {}, "outputs": [], "source": [ "from convlab.base_models.t5.nlu import T5NLU\n", "import requests\n", "\n", "\n", "def translate_text(text, target_language='en'):\n", " url = 'https://translate.googleapis.com/translate_a/single?client=gtx&sl=auto&tl={}&dt=t&q={}'.format(\n", " target_language, text)\n", " response = requests.get(url)\n", " if response.status_code == 200:\n", " translated_text = response.json()[0][0][0]\n", " return translated_text\n", " else:\n", " return None\n", "\n", "\n", "class NaturalLanguageAnalyzer: \n", " def predict(self, text, context=None):\n", " # Inicjalizacja modelu NLU\n", " model_name = \"ConvLab/t5-small-nlu-multiwoz21\"\n", " nlu_model = T5NLU(speaker='user', context_window_size=0, model_name_or_path=model_name)\n", "\n", " # Automatyczne tłumaczenie na język angielski\n", " translated_input = translate_text(text)\n", "\n", " # Wygenerowanie odpowiedzi z modelu NLU\n", " nlu_output = nlu_model.predict(translated_input)\n", "\n", " return nlu_output\n", "\n", " def init_session(self):\n", " # Inicjalizacja sesji (jeśli konieczne)\n", " pass" ] }, { "cell_type": "code", "execution_count": 213, "id": "06926543-cab1-48e7-8e82-0560fc0fa16a", "metadata": {}, "outputs": [], "source": [ "import json\n", "import os\n", "from convlab.dst.dst import DST\n", "from convlab.dst.rule.multiwoz.dst_util import normalize_value\n", "\n", "\n", "def default_state():\n", " return {\n", " 'belief_state': {\n", " 'hotel': {\n", " 'info': {\n", " 'name': '',\n", " 'area': '',\n", " 'parking': '',\n", " 'price range': '',\n", " 'stars': '',\n", " 'internet': '',\n", " 'type': ''\n", " },\n", " 'booking': {\n", " 'book stay': '',\n", " 'book day': '',\n", " 'book people': ''\n", " }\n", " }\n", " },\n", " 'request_state': {},\n", " 'history': [],\n", " 'user_action': [],\n", " 'system_action': [],\n", " 'terminated': False,\n", " 'booked': []\n", " }\n", "\n", "\n", "class DialogueStateTracker(DST):\n", " def __init__(self):\n", " DST.__init__(self)\n", " self.state = default_state()\n", " with open('./hotels_data.json') as f:\n", " self.value_dict = json.load(f)\n", "\n", " def update(self, user_act=None):\n", " for intent, domain, slot, value in user_act:\n", " domain = domain.lower()\n", " intent = intent.lower()\n", " slot = slot.lower()\n", " \n", " if domain not in self.state['belief_state']:\n", " continue\n", "\n", " if intent == 'inform':\n", " if slot == 'none' or slot == '' or value == 'dontcare':\n", " continue\n", "\n", " domain_dic = self.state['belief_state'][domain]['info']\n", "\n", " if slot in domain_dic:\n", " nvalue = self.normalize_value(self.value_dict, domain, slot, value)\n", " self.state['belief_state'][domain]['info'][slot] = nvalue\n", "\n", " elif intent == 'request':\n", " if domain not in self.state['request_state']:\n", " self.state['request_state'][domain] = {}\n", " if slot not in self.state['request_state'][domain]:\n", " self.state['request_state'][domain][slot] = 0\n", "\n", " return self.state\n", "\n", " def normalize_value(self, value_dict, domain, slot, value):\n", " normalized_value = value.lower().strip()\n", " if domain in value_dict and slot in value_dict[domain]:\n", " possible_values = value_dict[domain][slot]\n", " if isinstance(possible_values, dict) and normalized_value in possible_values:\n", " return possible_values[normalized_value]\n", " return value\n", "\n", " def init_session(self):\n", " self.state = default_state()\n" ] }, { "cell_type": "code", "execution_count": 214, "id": "a7f3d067-3a95-4ef5-b216-be5840bc8831", "metadata": {}, "outputs": [], "source": [ "from collections import defaultdict\n", "import copy\n", "import json\n", "from copy import deepcopy\n", "\n", "from convlab.policy.policy import Policy\n", "from convlab.util.multiwoz.dbquery import Database\n", "\n", "db_path = './hotels_data.json'\n", "\n", "class DialoguePolicy(Policy):\n", " def __init__(self):\n", " Policy.__init__(self)\n", " self.db = self.load_database(db_path)\n", "\n", " def load_database(self, db_path):\n", " with open(db_path, 'r', encoding='utf-8') as f:\n", " return json.load(f)\n", "\n", " def query(self, domain, constraints):\n", " if domain != 'hotel':\n", " return []\n", " \n", " results = []\n", " for entry in self.db:\n", " match = all(entry.get(key) == value for key, value in constraints)\n", " if match:\n", " results.append(entry)\n", " return results\n", "\n", " def predict(self, state):\n", " self.results = []\n", " system_action = defaultdict(list)\n", " user_action = defaultdict(list)\n", "\n", " for intent, domain, slot, value in state['user_action']:\n", " user_action[(domain.lower(), intent.lower())].append((slot.lower(), value))\n", "\n", " for user_act in user_action:\n", " self.update_system_action(user_act, user_action, state, system_action)\n", "\n", " if any(True for slots in user_action.values() for (slot, _) in slots if slot in ['book stay', 'book day', 'book people']):\n", " if self.results:\n", " system_action = {('Booking', 'Book'): [[\"Ref\", self.results[0].get('Ref', 'N/A')]]}\n", "\n", " system_acts = [[intent, domain, slot, value] for (domain, intent), slots in system_action.items() for slot, value in slots]\n", " state['system_action'] = system_acts\n", " return system_acts\n", "\n", " def update_system_action(self, user_act, user_action, state, system_action):\n", " domain, intent = user_act\n", " constraints = [(slot, value) for slot, value in state['belief_state'][domain]['info'].items() if value != '']\n", " print(f\"Constraints: {constraints}\")\n", " self.results = deepcopy(self.query(domain.lower(), constraints))\n", " print(f\"Query results: {self.results}\")\n", "\n", " if intent == 'request':\n", " if len(self.results) == 0:\n", " system_action[(domain, 'NoOffer')] = []\n", " else:\n", " for slot in user_action[user_act]: \n", " if slot[0] in self.results[0]:\n", " system_action[(domain, 'Inform')].append([slot[0], self.results[0].get(slot[0], 'unknown')])\n", "\n", " elif intent == 'inform':\n", " if len(self.results) == 0:\n", " system_action[(domain, 'NoOffer')] = []\n", " else:\n", " system_action[(domain, 'Inform')].append(['Choice', str(len(self.results))])\n", " choice = self.results[0]\n", "\n", " if domain in [\"hotel\"]:\n", " system_action[(domain, 'Recommend')].append(['Name', choice['name']])\n", " for slot in state['belief_state'][domain]['info']:\n", " if choice.get(slot):\n", " state['belief_state'][domain]['info'][slot] = choice[slot]" ] }, { "cell_type": "code", "execution_count": 218, "id": "11f34b20-c5b0-4752-8610-21f5eef4b569", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "WARNING:root:nlu info_dict is not initialized\n", "WARNING:root:dst info_dict is not initialized\n", "WARNING:root:policy info_dict is not initialized\n", "WARNING:root:nlg info_dict is not initialized\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "NLG seed 0\n" ] } ], "source": [ "from convlab.nlg.template.multiwoz import TemplateNLG\n", "from convlab.dialog_agent import PipelineAgent\n", "\n", "nlu = NaturalLanguageAnalyzer()\n", "dst = DialogueStateTracker()\n", "policy = DialoguePolicy()\n", "nlg = TemplateNLG(is_user=False)\n", "\n", "agent = PipelineAgent(nlu=nlu, dst=dst, policy=policy, nlg=nlg, name='sys')" ] }, { "cell_type": "code", "execution_count": 219, "id": "faf05778-2bca-4044-97a7-d6facf853e10", "metadata": {}, "outputs": [], "source": [ "# nla = NaturalLanguageAnalyzer()\n", "# nla_response = nla.predict(\"chciałbym zarezerwować drogi hotel bez parkingu 1 stycznia w Warszawie w centrum\")\n", "# print(nla_response)\n", "# response = agent.response(nla_response)\n", "# print(response)" ] }, { "cell_type": "code", "execution_count": 220, "id": "6c837788-e7d5-483e-b873-00061f118619", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Constraints: [('area', 'centre'), ('parking', 'yes'), ('price range', 'expensive'), ('type', 'hotel')]\n", "Query results: [{'name': 'Four Seasons Hotel', 'area': 'centre', 'parking': 'yes', 'price range': 'expensive', 'stars': '5', 'internet': 'yes', 'type': 'hotel'}, {'name': 'The Ritz Hotel', 'area': 'centre', 'parking': 'yes', 'price range': 'expensive', 'stars': '5', 'internet': 'yes', 'type': 'hotel'}, {'name': 'The Savoy Hotel', 'area': 'centre', 'parking': 'yes', 'price range': 'expensive', 'stars': '5', 'internet': 'yes', 'type': 'hotel'}, {'name': 'Shangri-La Hotel', 'area': 'centre', 'parking': 'yes', 'price range': 'expensive', 'stars': '5', 'internet': 'yes', 'type': 'hotel'}]\n", "We have 4 such places . Four Seasons Hotel looks like it would be a good choice .\n" ] } ], "source": [ "response = agent.response(\"chciałbym zarezerwować drogi hotel z parkingiem 1 stycznia w Warszawie w centrum\")\n", "print(response)" ] }, { "cell_type": "code", "execution_count": null, "id": "7f831f56-10ba-40da-a89c-baeed37df81e", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.8" } }, "nbformat": 4, "nbformat_minor": 5 }