oobabooga_api.py

import json

import requests

import settings
from fdict import fdict

URI = f'http://{settings.oobabooga_api_host}/api/v1/chat'


def generate(user_input):

    history = fdict(settings.history_file_name)

    request = {
        'user_input': user_input,
        'max_new_tokens': 150,
        'history': history,
        'mode': 'chat',  # Valid options: 'chat', 'chat-instruct', 'instruct'
        'character': settings.oobabooga_api_name,
        'instruction_template': None,  # Will get autodetected if unset
        'context_instruct': None,  # Optional
        'your_name': 'You',

        'regenerate': False,
        '_continue': False,
        'stop_at_newline': False,
        'chat_generation_attempts': 1,
        'chat-instruct_command': None,


        # Generation params. If 'preset' is set to different than 'None', the values
        # in presets/preset-name.yaml are used instead of the individual numbers.
        'preset': 'None',
        'do_sample': True,
        'temperature': 0.7,
        'top_p': 0.1,
        'typical_p': 1,
        'epsilon_cutoff': 0,  # In units of 1e-4
        'eta_cutoff': 0,  # In units of 1e-4
        'tfs': 1,
        'top_a': 0,
        'repetition_penalty': 1.18,
        'repetition_penalty_range': 0,
        'top_k': 40,
        'min_length': 0,
        'no_repeat_ngram_size': 0,
        'num_beams': 1,
        'penalty_alpha': 0,
        'length_penalty': 1,
        'early_stopping': False,
        'mirostat_mode': 0,
        'mirostat_tau': 5,
        'mirostat_eta': 0.1,

        'seed': -1,
        'add_bos_token': True,
        'truncation_length': 4096,
        'ban_eos_token': False,
        'skip_special_tokens': True,
        'stopping_strings': []
    }

    response = requests.post(URI, json=request)

    if response.status_code == 200:
        result = response.json()['results'][0]['history']
        history = fdict(settings.history_file_name, result)
        return result['visible'][-1][1]