Tworzenie czatbota z Gemmą

Wyświetl na ai.google.dev Uruchom w Google Colab Otwórz w Vertex AI Wyświetl źródło w GitHubie

Duże modele językowe (LLM), takie jak Gemma, doskonale nadają się do generowania przydatnych odpowiedzi, dzięki czemu idealnie nadają się do tworzenia wirtualnych asystentów i czatbotów.

Tradycyjnie duże modele językowe działają bezstanowo, co oznacza, że nie mają wbudowanej pamięci do przechowywania wcześniejszych rozmów. Każdy prompt i pytanie jest przetwarzany niezależnie, z pominięciem wcześniejszych interakcji. Kluczowym aspektem naturalnej rozmowy jest jednak zdolność do zapamiętywania kontekstu wcześniejszych interakcji. Aby przezwyciężyć to ograniczenie i umożliwić LLM zachowanie kontekstu rozmowy, muszą oni w sposób jednoznaczny otrzymywać odpowiednie informacje, takie jak historia rozmowy (lub powiązane fragmenty) do każdego nowego promptu prezentowanego LLM.

W tym samouczku pokazujemy, jak stworzyć czatbota przy użyciu wariantu Gemmy dostrojonego zgodnie z instrukcjami.

Konfiguracja

Konfiguracja Gemma

Aby ukończyć ten samouczek, musisz najpierw wykonać instrukcje konfiguracji opisane na stronie konfiguracji Gemma. Z instrukcji konfiguracji Gemma dowiesz się, jak:

  • Uzyskaj dostęp do Gemmy na kaggle.com.
  • Wybierz środowisko wykonawcze Colab z wystarczającą ilością zasobów do uruchomienia modelu Gemma 2B.
  • Wygeneruj i skonfiguruj nazwę użytkownika i klucz interfejsu API Kaggle.

Po zakończeniu konfiguracji Gemma przejdź do następnej sekcji, w której możesz ustawić zmienne środowiskowe dla środowiska Colab.

Ustawianie zmiennych środowiskowych

Ustaw zmienne środowiskowe dla interfejsów KAGGLE_USERNAME i KAGGLE_KEY.

import os
from google.colab import userdata

# Note: `userdata.get` is a Colab API. If you're not using Colab, set the env
# vars as appropriate for your system.
os.environ["KAGGLE_USERNAME"] = userdata.get('KAGGLE_USERNAME')
os.environ["KAGGLE_KEY"] = userdata.get('KAGGLE_KEY')

Instalowanie zależności

Zainstaluj Keras i KerasNLP.

# Install Keras 3 last. See https://keras.io/getting_started/ for more details.
pip install -q tensorflow-cpu
pip install -q -U keras-nlp tensorflow-hub
pip install -q -U "keras>=3"
pip install -q -U tensorflow-text

Wybierz backend

Keras to wysokopoziomowy, wieloramowy interfejs API deep learning, który jest łatwy w użyciu. Keras 3 pozwala wybrać backend: TensorFlow, JAX lub PyTorch. W tym samouczku będą działać wszystkie 3 metody.

import os

# Select JAX as the backend
os.environ["KERAS_BACKEND"] = "jax"

# Pre-allocate 100% of TPU memory to minimize memory fragmentation
os.environ["XLA_PYTHON_CLIENT_MEM_FRACTION"] = "1.0"

Importuj pakiety

Importuj Keras i KerasNLP.

import keras
import keras_nlp

# for reproducibility
keras.utils.set_random_seed(42)

Utwórz instancję modelu

KerasNLP udostępnia implementacje wielu popularnych architektur modeli. W tym samouczku utworzysz instancję modelu przy użyciu GemmaCausalLM – kompleksowego modelu Gemma do modelowania przyczynowego języka. Przypadkowy model językowy przewiduje kolejny token na podstawie poprzednich tokenów.

Utwórz instancję modelu przy użyciu metody from_preset:

gemma_lm = keras_nlp.models.GemmaCausalLM.from_preset("gemma2_instruct_2b_en")

Funkcja GemmaCausalLM.from_preset() tworzy instancję modelu na podstawie gotowej architektury i wag. W powyższym kodzie ciąg "gemma2_instruct_2b_en" określa gotowe ustawienie modelu Gemma 2 2B z 2 miliardami parametrów. Dostępne są również modele Gemma z parametrami 7B, 9B i 27B. Ciągi kodu dla modeli Gemma znajdziesz w informacjach o odmianach modelu na stronie Kaggle.

Aby uzyskać więcej informacji o modelu, użyj metody summary:

gemma_lm.summary()

Jak widać z podsumowania, model ma 2,6 mld parametrów z możliwością trenowania.

Zdefiniuj funkcje pomocnicze formatowania

from IPython.display import Markdown
import textwrap

def display_chat(prompt, text):
  formatted_prompt = "<font size='+1' color='brown'>🙋‍♂️<blockquote>" + prompt + "</blockquote></font>"
  text = text.replace('', '  *')
  text = textwrap.indent(text, '> ', predicate=lambda _: True)
  formatted_text = "<font size='+1' color='teal'>🤖\n\n" + text + "\n</font>"
  return Markdown(formatted_prompt+formatted_text)

def to_markdown(text):
  text = text.replace('', '  *')
  return Markdown(textwrap.indent(text, '> ', predicate=lambda _: True))

Tworzenie czatbota

Model gemma2_instruct_2b_en dostrojony przez Gemma został dostrojony pod kątem rozpoznawania tych tokenów skrętu:

<start_of_turn>user\n  ... <end_of_turn>\n
<start_of_turn>model\n ... <end_of_turn>\n

Ten samouczek korzysta z tych tokenów do budowania czatbota. Więcej informacji o tokenach kontrolnych Gemma znajdziesz w instrukcjach formatowania i systemu.

Utwórz pomocnik na czacie do zarządzania stanem rozmowy

class ChatState():
  """
  Manages the conversation history for a turn-based chatbot
  Follows the turn-based conversation guidelines for the Gemma family of models
  documented at https://ai.google.dev/gemma/docs/formatting
  """

  __START_TURN_USER__ = "<start_of_turn>user\n"
  __START_TURN_MODEL__ = "<start_of_turn>model\n"
  __END_TURN__ = "<end_of_turn>\n"

  def __init__(self, model, system=""):
    """
    Initializes the chat state.

    Args:
        model: The language model to use for generating responses.
        system: (Optional) System instructions or bot description.
    """
    self.model = model
    self.system = system
    self.history = []

  def add_to_history_as_user(self, message):
      """
      Adds a user message to the history with start/end turn markers.
      """
      self.history.append(self.__START_TURN_USER__ + message + self.__END_TURN__)

  def add_to_history_as_model(self, message):
      """
      Adds a model response to the history with start/end turn markers.
      """
      self.history.append(self.__START_TURN_MODEL__ + message)

  def get_history(self):
      """
      Returns the entire chat history as a single string.
      """
      return "".join([*self.history])

  def get_full_prompt(self):
    """
    Builds the prompt for the language model, including history and system description.
    """
    prompt = self.get_history() + self.__START_TURN_MODEL__
    if len(self.system)>0:
      prompt = self.system + "\n" + prompt
    return prompt

  def send_message(self, message):
    """
    Handles sending a user message and getting a model response.

    Args:
        message: The user's message.

    Returns:
        The model's response.
    """
    self.add_to_history_as_user(message)
    prompt = self.get_full_prompt()
    response = self.model.generate(prompt, max_length=2048)
    result = response.replace(prompt, "")  # Extract only the new response
    self.add_to_history_as_model(result)
    return result

Czatuj z modelem

Rozpocznij czat z modelem.

chat = ChatState(gemma_lm)
message = "Tell me, in a few words,  how to compute all prime numbers up to 1000?"
display_chat(message, chat.send_message(message))

🙋‍♂️

Powiedz mi w kilku słowach, jak obliczyć wszystkie liczby pierwsze do 1000?
🤖

Siedem Eratotenów.

Kontynuuj rozmowę.

message = "Now in Python! No numpy, please!"
display_chat(message, chat.send_message(message))

🙋‍♂️

Teraz w Pythonie! Uwaga!
🤖

def sieve_of_eratosthenes(n):
  """Returns a list of prime numbers up to n."""
  primes = [True] * (n + 1)
  primes[0] = primes[1] = False
  for i in range(2, int(n**0.5) + 1):
    if primes[i]:
      for j in range(i * i, n + 1, i):
        primes[j] = False
  return [i for i, is_prime in enumerate(primes) if is_prime]

primes = sieve_of_eratosthenes(1000)
print(primes)

Wyjaśnienie:

  1. Inicjalizacja:

    • primes = [True] * (n + 1): tworzy listę primes wartości logicznych, przy założeniu, że wszystkie liczby są liczbą pierwszą.
    • primes[0] = primes[1] = False: ustawia wartości 0 i 1 jako inne niż główne.
  2. Iteracja:

    • for i in range(2, int(n**0.5) + 1):: powtarza wartość z 2 do pierwiastka kwadratowego z n. Musimy sprawdzić wartość do pierwiastka kwadratowego, ponieważ w przypadku każdej liczby złożonej współczynnik pierwszy musi być mniejszy niż lub równy jej pierwiastkowi kwadratowemu.
    • if primes[i]:: jeśli pole i jest oznaczone jako pierwsze:
      • for j in range(i * i, n + 1, i):: oznacza wszystkie wielokrotności wartości i jako nieprzejściowe.
  3. Wynik:

    • return [i for i, is_prime in enumerate(primes) if is_prime]: tworzy listę indeksów, gdzie primes[i] ma wartość Prawda, co reprezentuje liczby pierwsze.

Daj mi znać, jeśli potrzebujesz bardziej szczegółowych wyjaśnień.

message = "Thank you, it works! Can you explain the code in French?"
display_chat(message, chat.send_message(message))

🙋‍♂️

Dziękujemy, to działa. Czy możesz wyjaśnić kod po francusku?
🤖

Bien sMembershipr ! Voici une explication du code en français :

def sieve_of_eratosthenes(n):
  """Retourne une liste de nombres premiers jusqu'à n."""
  primes = [True] * (n + 1)
  primes[0] = primes[1] = False
  for i in range(2, int(n**0.5) + 1):
    if primes[i]:
      for j in range(i * i, n + 1, i):
        primes[j] = False
  return [i for i, is_prime in enumerate(primes) if is_prime]

primes = sieve_of_eratosthenes(1000)
print(primes)

Wyjaśnienie:

  1. Inicjacja:

    • primes = [True] * (n + 1): Crée une liste primes de valeurs booléennes, initialement supposant que tous les nombres sont premiers
    • primes[0] = primes[1] = False: Définit 0 i 1 comme inne niż premiera.
  2. iteracja:

    • for i in range(2, int(n**0.5) + 1):: Itère de 2 jusqu'à la racine carrée de n. Nous ne devons vérifier que jusqu'à la racine carrée carrée tout nombre Compl doit avoir unfacteur premier inférieur ou égal à sa racine carrée.
    • if primes[i]:: Si i est considéré comme premier:
      • for j in range(i * i, n + 1, i):: Marquer tous les multiples de i to miłośnicy programów innych niż premier.
  3. Wynik:

    • return [i for i, is_prime in enumerate(primes) if is_prime]: Crée une liste liste des indices où primes[i] est vrai, représentant les nombres premiers.

N'hésitez pas à me requester si vous avez besoin d'une explication plus détaillée de quelque choose!

message = "Great! Now add those explanations as comments in the code."
display_chat(message, chat.send_message(message))

🙋‍♂️

Świetnie. Teraz dodaj te wyjaśnienia jako komentarze w kodzie.
🤖

def sieve_of_eratosthenes(n):
  """Retourne une liste de nombres premiers jusqu'à n."""
  # Initialise une liste de boolean avec True pour tous les nombres de 0 à n
  primes = [True] * (n + 1)
  # Définit 0 et 1 comme non-premiers
  primes[0] = primes[1] = False
  # Itère de 2 à la racine carrée de n
  for i in range(2, int(n**0.5) + 1):
    # Si i est considéré comme premier
    if primes[i]:
      # Itère sur tous les multiples de i
      for j in range(i * i, n + 1, i):
        # Définit les multiples de i comme non-premiers
        primes[j] = False
  # Retourne la liste des indices des nombres premiers
  return [i for i, is_prime in enumerate(primes) if is_prime]

primes = sieve_of_eratosthenes(1000)
print(primes)

Wyjaśnienie:

  • Inicjacja:
    • primes = [True] * (n + 1): Crée une liste primes de valeurs booléennes, initialement supposant que tous les nombres sont premiers
    • primes[0] = primes[1] = False: Définit 0 i 1 comme inne niż premiera.
  • iteracja:
    • for i in range(2, int(n**0.5) + 1):: Itère de 2 jusqu'à la racine carrée de n. Nous ne devons vérifier que jusqu'à la racine carrée carrée tout nombre Compl doit avoir unfacteur premier inférieur ou égal à sa racine carrée.
    • if primes[i]:: Si i est considéré comme premier:
      • for j in range(i * i, n + 1, i):: Marquer tous les multiples de i to miłośnicy programów innych niż premier.
  • Wynik:
    • return [i for i, is_prime in enumerate(primes) if is_prime]: Crée une liste liste des indices où primes[i] est vrai, représentant les nombres premiers.

Przetestuj wygenerowaną odpowiedź, uruchamiając wygenerowany kod:

def sieve_of_eratosthenes(n):
  """Retourne une liste de nombres premiers jusqu'à n."""
  # Initialise une liste de boolean avec True pour tous les nombres de 0 à n
  primes = [True] * (n + 1)
  # Définit 0 et 1 comme non-premiers
  primes[0] = primes[1] = False
  # Itère de 2 à la racine carrée de n
  for i in range(2, int(n**0.5) + 1):
    # Si i est considéré comme premier
    if primes[i]:
      # Itère sur tous les multiples de i
      for j in range(i * i, n + 1, i):
        # Définit les multiples de i comme non-premiers
        primes[j] = False
  # Retourne la liste des indices des nombres premiers
  return [i for i, is_prime in enumerate(primes) if is_prime]

primes = sieve_of_eratosthenes(1000)
print(primes)
[2, 3, 5, 7, 11, 13, 17, 19, 23, 29, 31, 37, 41, 43, 47, 53, 59, 61, 67, 71, 73, 79, 83, 89, 97, 101, 103, 107, 109, 113, 127, 131, 137, 139, 149, 151, 157, 163, 167, 173, 179, 181, 191, 193, 197, 199, 211, 223, 227, 229, 233, 239, 241, 251, 257, 263, 269, 271, 277, 281, 283, 293, 307, 311, 313, 317, 331, 337, 347, 349, 353, 359, 367, 373, 379, 383, 389, 397, 401, 409, 419, 421, 431, 433, 439, 443, 449, 457, 461, 463, 467, 479, 487, 491, 499, 503, 509, 521, 523, 541, 547, 557, 563, 569, 571, 577, 587, 593, 599, 601, 607, 613, 617, 619, 631, 641, 643, 647, 653, 659, 661, 673, 677, 683, 691, 701, 709, 719, 727, 733, 739, 743, 751, 757, 761, 769, 773, 787, 797, 809, 811, 821, 823, 827, 829, 839, 853, 857, 859, 863, 877, 881, 883, 887, 907, 911, 919, 929, 937, 941, 947, 953, 967, 971, 977, 983, 991, 997]

Użyj metody get_history, aby zobaczyć, jak cały kontekst został zachowany przez klasę Chat.

print(chat.get_history())
<start_of_turn>user
Tell me, in a few words,  how to compute all prime numbers up to 1000?<end_of_turn>
<start_of_turn>model
**Sieve of Eratosthenes.** 
<end_of_turn><start_of_turn>user
Now in Python! No numpy, please!<end_of_turn>
<start_of_turn>model

```python
def sieve_of_eratosthenes(n):
  """Returns a list of prime numbers up to n."""
  primes = [True] * (n + 1)
  primes[0] = primes[1] = False
  for i in range(2, int(n**0.5) + 1):
    if primes[i]:
      for j in range(i * i, n + 1, i):
        primes[j] = False
  return [i for i, is_prime in enumerate(primes) if is_prime]

primes = sieve_of_eratosthenes(1000)
print(primes)
```

**Explanation:**

1. **Initialization:**
   - `primes = [True] * (n + 1)`: Creates a list `primes` of boolean values, initially assuming all numbers are prime.
   - `primes[0] = primes[1] = False`: Sets 0 and 1 as non-prime.

2. **Iteration:**
   - `for i in range(2, int(n**0.5) + 1):`: Iterates from 2 to the square root of `n`. We only need to check up to the square root because any composite number must have a prime factor less than or equal to its square root.
   - `if primes[i]:`: If `i` is marked as prime:
     - `for j in range(i * i, n + 1, i):`: Marks all multiples of `i` as non-prime.

3. **Result:**
   - `return [i for i, is_prime in enumerate(primes) if is_prime]`: Creates a list of indices where `primes[i]` is True, representing the prime numbers.


Let me know if you'd like a more detailed explanation of any part! 
<end_of_turn><start_of_turn>user
Thank you, it works! Can you explain the code in French?<end_of_turn>
<start_of_turn>model
Bien sûr ! Voici une explication du code en français :

```python
def sieve_of_eratosthenes(n):
  """Retourne une liste de nombres premiers jusqu'à n."""
  primes = [True] * (n + 1)
  primes[0] = primes[1] = False
  for i in range(2, int(n**0.5) + 1):
    if primes[i]:
      for j in range(i * i, n + 1, i):
        primes[j] = False
  return [i for i, is_prime in enumerate(primes) if is_prime]

primes = sieve_of_eratosthenes(1000)
print(primes)
```

**Explication:**

1. **Initialisation:**
   - `primes = [True] * (n + 1)`: Crée une liste `primes` de valeurs booléennes, initialement supposant que tous les nombres sont premiers.
   - `primes[0] = primes[1] = False`: Définit 0 et 1 comme non-premiers.

2. **Itération:**
   - `for i in range(2, int(n**0.5) + 1):`: Itère de 2 jusqu'à la racine carrée de `n`. Nous ne devons vérifier que jusqu'à la racine carrée car tout nombre composite doit avoir un facteur premier inférieur ou égal à sa racine carrée.
   - `if primes[i]:`: Si `i` est considéré comme premier:
     - `for j in range(i * i, n + 1, i):`:  Marquer tous les multiples de `i` comme non-premiers.

3. **Resultat:**
   - `return [i for i, is_prime in enumerate(primes) if is_prime]`: Crée une liste des indices où `primes[i]` est vrai, représentant les nombres premiers.


N'hésitez pas à me demander si vous avez besoin d'une explication plus détaillée de quelque chose! 
<end_of_turn><start_of_turn>user
Great! Now add those explanations as comments in the code.<end_of_turn>
<start_of_turn>model

```python
def sieve_of_eratosthenes(n):
  """Retourne une liste de nombres premiers jusqu'à n."""
  # Initialise une liste de boolean avec True pour tous les nombres de 0 à n
  primes = [True] * (n + 1)
  # Définit 0 et 1 comme non-premiers
  primes[0] = primes[1] = False
  # Itère de 2 à la racine carrée de n
  for i in range(2, int(n**0.5) + 1):
    # Si i est considéré comme premier
    if primes[i]:
      # Itère sur tous les multiples de i
      for j in range(i * i, n + 1, i):
        # Définit les multiples de i comme non-premiers
        primes[j] = False
  # Retourne la liste des indices des nombres premiers
  return [i for i, is_prime in enumerate(primes) if is_prime]

primes = sieve_of_eratosthenes(1000)
print(primes)
```

**Explication:**

* **Initialisation:**
    * `primes = [True] * (n + 1)`:  Crée une liste `primes` de valeurs booléennes, initialement supposant que tous les nombres sont premiers.
    * `primes[0] = primes[1] = False`: Définit 0 et 1 comme non-premiers.
* **Itération:**
    * `for i in range(2, int(n**0.5) + 1):`: Itère de 2 jusqu'à la racine carrée de `n`. Nous ne devons vérifier que jusqu'à la racine carrée car tout nombre composite doit avoir un facteur premier inférieur ou égal à sa racine carrée.
    * `if primes[i]:`: Si `i` est considéré comme premier:
        * `for j in range(i * i, n + 1, i):`:  Marquer tous les multiples de `i` comme non-premiers.
* **Resultat:**
    * `return [i for i, is_prime in enumerate(primes) if is_prime]`: Crée une liste des indices où `primes[i]` est vrai, représentant les nombres premiers. 



<end_of_turn>

Podsumowanie i dalsze materiały

Z tego samouczka dowiesz się, jak czatować z modelem dostrojonym w narzędziu Gemma 2B Instruction z wykorzystaniem Keras w języku JAX.

Zapoznaj się z tymi przewodnikami i samouczkami, aby dowiedzieć się więcej o Gemmie: