Skip to main content

Simple interface for neural chatbots.

Project description

neural_chat

Setting Up A Basic Assistant

from neural_chat import GenericAssistant

assistant = GenericAssistant("intents.json",
                             model_name="test_model")
assistant.train_model()
assistant.save_model()

while True:
    message = input("Enter a message: ").lower()
    if message == "stop":
        break
    else:
        assistant.request(message)

Also support a voice assistant

from neural_chat import GenericAssistant

assistant = GenericAssistant("intents.json",
                             model_name="test_model",
                             voice_assistant=True)
assistant.train_model()
assistant.save_model()

while True:
    message = input("Enter a message: ").lower()
    if message == "stop":
        break
    else:
        response = assistant.request(input(">>> "))
        if type(response) == str:
            print(response)
        # else: will speak the answer text and print it.
        #       Print function hardcoded in voice_assistant.py

Binding Functions To Requests

from neural_chat import GenericAssistant

def function_for_greetings():
    print("You triggered the greetings intent!")
    # Some action you want to take

def function_for_stocks():
    print("You triggered the stocks intent!")
    # Some action you want to take

mappings = {
    "greeting" : function_for_greetings,
    "stocks" : function_for_stocks
}

assistant = GenericAssistant("intents.json",
                             intent_methods=mappings,
                             model_name="test_model")
assistant.train_model()
assistant.save_model()

while True:
    message = input("Enter a message: ")
    if message == "stop":
        break
    else:
        assistant.request(message)

Sample intents.json File

{"intents": [
  {"tag": "greeting",
    "patterns": ["Hi", "How are you", "Is anyone there?", "Hello", "Good day", "Whats up", "Hey", "greetings"],
    "responses": ["Hello!", "Good to see you again!", "Hi there, how can I help?"],
    "context_set": ""
  },
  {"tag": "goodbye",
    "patterns": ["cya", "See you later", "Goodbye", "I am Leaving", "Have a Good day", "bye", "cao", "see ya"],
    "responses": ["Sad to see you go :(", "Talk to you later", "Goodbye!"],
    "context_set": ""
  },
  {"tag": "stocks",
    "patterns": ["what stocks do I own?", "how are my shares?", "what companies am I investing in?", "what am I doing in the markets?"],
    "responses": ["You own the following shares: ABBV, AAPL, FB, NVDA and an ETF of the S&P 500 Index!"],
    "context_set": ""
  }
]
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

neural_chat-0.0.5.tar.gz (3.5 kB view details)

Uploaded Source

File details

Details for the file neural_chat-0.0.5.tar.gz.

File metadata

  • Download URL: neural_chat-0.0.5.tar.gz
  • Upload date:
  • Size: 3.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.8.0 pkginfo/1.8.3 readme-renderer/37.0 requests/2.28.1 requests-toolbelt/0.9.1 urllib3/1.26.12 tqdm/4.64.0 importlib-metadata/4.12.0 keyring/23.8.2 rfc3986/1.5.0 colorama/0.4.5 CPython/3.10.6

File hashes

Hashes for neural_chat-0.0.5.tar.gz
Algorithm Hash digest
SHA256 7ee1567f72bf2d9c82d312cf4232b3379c68e274c9787084e112d131057932d0
MD5 05b6bcdffa9389877c0a5b7bad4c7d5e
BLAKE2b-256 db54b5a53bfb7c1e6b0615342aac3b85e5ac529d0ce2c8e75705fc6a6de23d36

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page