LLM Prompt Engineering 实践：原型

import openai
openai.proxy = 'http://localhost:8080'

from langchain.chat_models import ChatOpenAI
from langchain.schema import HumanMessage

user_message = HumanMessage(content='将这句话翻译成中文: “to be or not to be”')

# 安全考虑这里把真实 API KEY 隐藏了，后文不再强调
llm = ChatOpenAI(temperature=0, openai_api_key='sk-xxxxxxxxxxxxxxxx')
answer = llm([user_message])
print(answer.content)

from langchain.memory import ChatMessageHistory

memory = ChatMessageHistory()

memory.add_user_message(user_message.content)
memory.add_ai_message(answer.content)

print(memory.messages)

user_message = HumanMessage(content='再翻译成日语')
answer = llm(memory.messages + [user_message])
print('Answer:', answer.content)

memory.add_user_message(user_message.content)
memory.add_ai_message(answer.content)
print('History')
print(memory.messages)

from langchain.chat_models import ChatOpenAI
from langchain.memory import ChatMessageHistory

memory = ChatMessageHistory()
llm = ChatOpenAI(temperature=0, openai_api_key='sk-xxxxxxxxxxxxxxxx')
while True:
    user_message = input('You: ').strip()
    if not user_message:
        continue

    if user_message.lower() in ('quit', 'exit'):
        break

    memory.add_user_message(user_message)
    answer = llm(memory.messages)
    print('BOT:', answer.content)
    memory.add_ai_message(answer.content)

max_tokens = 1024
llm = ChatOpenAI(
    temperature=0,
    openai_api_key='sk-xxxxxxxxxxxxxxxx',
    max_tokens=max_tokens
)

from tiktoken.model import encoding_for_model

encoder = encoding_for_model('gpt-3.5-turbo')

import tiktoken

def num_tokens_from_messages(messages, model="gpt-3.5-turbo-0301"):
    """Returns the number of tokens used by a list of messages."""
    try:
        encoding = tiktoken.encoding_for_model(model)
    except KeyError:
        encoding = tiktoken.get_encoding("cl100k_base")

    if model == "gpt-3.5-turbo-0301":  # note: future models may deviate from this
        num_tokens = 0
        for message in messages:
            num_tokens += 4  # every message follows <im_start>{role/name}\n{content}<im_end>\n
            for key, value in message.items():
                num_tokens += len(encoding.encode(value))
                if key == "name":  # if there's a name, the role is omitted
                    num_tokens += -1  # role is always required and always 1 token

        return num_tokens
    else:
        raise NotImplementedError(
            f"num_tokens_from_messages() is not presently implemented for model {model}.\n"
            "See https://github.com/openai/openai-python/blob/main/chatml.md "
            "for information on how messages are converted to tokens."
        )

from langchain.schema import AIMessage, HumanMessage

def select_messages(messages, max_total_tokens=4096, max_output_tokens=1024):
    tokens_num = 0
    selected = []
    for message in messages[::-1]:
        role = 'system'
        if isinstance(message, AIMessage):
            role = 'assistant'
        elif isinstance(message, HumanMessage):
            role = 'user'

        cur_token_num = num_tokens_from_messages([{'role': role, 'content': message.content}])
        if tokens_num + cur_token_num + 2 + max_output_tokens > max_total_tokens:
            break

        selected.append(message)
        tokens_num += cur_token_num

    selected = selected[::-1]
    if isinstance(selected[0], AIMessage): # 确保第一条是用户消息
        selected = selected[1:]

    if not selected:            # 假设 messages 里最后一条是当前用户输入
        selected = message[-1]

    return selected

from langchain.chat_models import ChatOpenAI
from langchain.memory import ChatMessageHistory

memory = ChatMessageHistory()

max_output_tokens, max_total_tokens = 1024, 4096
llm = ChatOpenAI(
    temperature=0,
    openai_api_key='sk-xxxxxxxxxxxxxxxx',
    max_tokens=max_output_tokens,
)
while True:
    user_message = input('You: ').strip()
    if not user_message:
        continue

    if user_message.lower() in ('quit', 'exit'):
        break

    memory.add_user_message(user_message)
    messages = select_messages(
        memory.messages,
        max_total_tokens=max_total_tokens,
        max_output_tokens=max_output_tokens
    )
    print(f"selected messages: {messages}")
    answer = llm(messages)
    print('BOT:', answer.content)
    memory.add_ai_message(answer.content)

from langchain.chat_models import ChatOpenAI
from langchain.memory import ChatMessageHistory
from langchain.schema import SystemMessage

memory = ChatMessageHistory()
system_message = SystemMessage(
    content=(
        "You are an AI assistant. Your name is xorius. "
        "You can discuss any ideas and topics with your users, "
        "and you will help your users solve their problems as much as you can."
    ),
)
max_total_tokens = 4096 - num_tokens_from_messages([{'role': 'system', 'content': system_message.content}])
max_output_tokens = 1024
llm = ChatOpenAI(
    temperature=0,
    openai_api_key='sk-xxxxxxxxxxxxxxxx',
    max_tokens=max_output_tokens,
)
while True:
    user_message = input('You: ').strip()
    if not user_message:
        continue

    if user_message.lower() in ('quit', 'exit'):
        break

    memory.add_user_message(user_message)
    messages = select_messages(
        memory.messages,
        max_total_tokens=max_total_tokens,
        max_output_tokens=max_output_tokens
    )
    print(f"selected messages: {messages}")
    answer = llm([system_message] + messages)
    print('BOT:', answer.content)
    memory.add_ai_message(answer.content)