admin管理员组

文章数量:1567563

分类目录：《大模型从入门到应用》总目录

LangChain系列文章：

  • 基础知识
  • 快速入门
    • 安装与环境配置
    • 链（Chains）、代理（Agent:）和记忆（Memory）
    • 快速开发聊天模型
  • 模型（Models）
    • 基础知识
    • 大型语言模型（LLMs）
      • 基础知识
      • LLM的异步API、自定义LLM包装器、虚假LLM和人类输入LLM（Human Input LLM）
      • 缓存LLM的调用结果
      • 加载与保存LLM类、流式传输LLM与Chat Model响应和跟踪tokens使用情况
    • 聊天模型（Chat Models）
      • 基础知识
      • 使用少量示例和响应流式传输
    • 文本嵌入模型
      • Aleph Alpha、Amazon Bedrock、Azure OpenAI、Cohere等
      • Embaas、Fake Embeddings、Google Vertex AI PaLM等
  • 提示（Prompts）
    • 基础知识
    • 提示模板
      • 基础知识
      • 连接到特征存储
      • 创建自定义提示模板和含有Few-Shot示例的提示模板
      • 部分填充的提示模板和提示合成
      • 序列化提示信息
    • 示例选择器（Example Selectors）
    • 输出解析器（Output Parsers）
  • 记忆（Memory）
    • 基础知识
    • 记忆的类型
      • 会话缓存记忆、会话缓存窗口记忆和实体记忆
      • 对话知识图谱记忆、对话摘要记忆和会话摘要缓冲记忆
      • 对话令牌缓冲存储器和基于向量存储的记忆
    • 将记忆添加到LangChain组件中
    • 自定义对话记忆与自定义记忆类
    • 聊天消息记录
    • 记忆的存储与应用
  • 索引（Indexes）
    • 基础知识
    • 文档加载器（Document Loaders）
    • 文本分割器（Text Splitters）
    • 向量存储器（Vectorstores）
    • 检索器（Retrievers）
  • 链（Chains）
    • 基础知识
    • 通用功能
      • 自定义Chain和Chain的异步API
      • LLMChain和RouterChain
      • SequentialChain和TransformationChain
      • 链的保存（序列化）与加载（反序列化）
    • 链与索引
      • 文档分析和基于文档的聊天
      • 问答的基础知识
      • 图问答（Graph QA）和带来源的问答（Q&A with Sources）
      • 检索式问答
      • 文本摘要（Summarization）、HyDE和向量数据库的文本生成
  • 代理（Agents）
    • 基础知识
    • 代理类型
    • 自定义代理（Custom Agent）
    • 自定义MRKL代理
    • 带有ChatModel的LLM聊天自定义代理和自定义多操作代理（Custom MultiAction Agent）
    • 工具
      • 基础知识
      • 自定义工具（Custom Tools）
      • 多输入工具和工具输入模式
      • 人工确认工具验证和Tools作为OpenAI函数
    • 工具包（Toolkit）
    • 代理执行器（Agent Executor）
      • 结合使用Agent和VectorStore
      • 使用Agents的异步API和创建ChatGPT克隆
      • 处理解析错误、访问中间步骤和限制最大迭代次数
      • 为代理程序设置超时时间和限制最大迭代次数和为代理程序和其工具添加共享内存
    • 计划与执行
  • 回调函数（Callbacks）

使用Agents的异步API

LangChain通过利用asyncio库为Agents提供了异步支持。目前，以下工具支持异步方法：

  • GoogleSerperAPIWrapper
  • SerpAPIWrapper
  • LLMMathChain

其他Agent工具的异步支持正在路线图中。对于已实现coroutine的工具（上述三个工具），AgentExecutor将直接使用await调用它们。否则，AgentExecutor将通过asyncio.get_event_loop().run_in_executor调用Tool的func以避免阻塞主要的运行循环。我们还可以使用arun异步调用AgentExecutor。

串行执行与并发执行

在此示例中，我们以串行和并发的方式启动代理以回答一些问题。可以看到并发执行明显加快了速度。

import asyncio
import time

from langchain.agents import initialize_agent, load_tools
from langchain.agents import AgentType
from langchain.llms import OpenAI
from langchain.callbacks.stdout import StdOutCallbackHandler
from langchain.callbacks.tracers import LangChainTracer
from aiohttp import ClientSession

questions = [
    "Who won the US Open men's final in 2019? What is his age raised to the 0.334 power?",
    "Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?",
    "Who won the most recent formula 1 grand prix? What is their age raised to the 0.23 power?",
    "Who won the US Open women's final in 2019? What is her age raised to the 0.34 power?",
    "Who is Beyonce's husband? What is his age raised to the 0.19 power?"
]
llm = OpenAI(temperature=0)
tools = load_tools(["google-serper", "llm-math"], llm=llm)
agent = initialize_agent(
    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)

s = time.perf_counter()
for q in questions:
    agent.run(q)
elapsed = time.perf_counter() - s
print(f"Serial executed in {elapsed:0.2f} seconds.")

日志输出：

Entering new AgentExecutor chain...
I need to find out who won the US Open men's final in 2019 and then calculate his age raised to the 0.334 power.
Action: Google Serper
Action Input: "Who won the US Open men's final in 2019?"
Observation: Rafael Nadal defeated Daniil Medvedev in the final, 7–5, 6–3, 5–7, 4–6, 6–4 to win the men's singles tennis title at the 2019 US Open. It was his fourth US ... Draw: 128 (16 Q / 8 WC). Champion: Rafael Nadal. Runner-up: Daniil Medvedev. Score: 7–5, 6–3, 5–7, 4–6, 6–4. Bianca Andreescu won the women's singles title, defeating Serena Williams in straight sets in the final, becoming the first Canadian to win a Grand Slam singles ... Rafael Nadal won his 19th career Grand Slam title, and his fourth US Open crown, by surviving an all-time comback effort from Daniil ... Rafael Nadal beats Daniil Medvedev in US Open final to claim 19th major title. World No2 claims 7-5, 6-3, 5-7, 4-6, 6-4 victory over Russian ... Rafael Nadal defeated Daniil Medvedev in the men's singles final of the U.S. Open on Sunday. Rafael Nadal survived. The 33-year-old defeated Daniil Medvedev in the final of the 2019 U.S. Open to earn his 19th Grand Slam title Sunday ... NEW YORK -- Rafael Nadal defeated Daniil Medvedev in an epic five-set match, 7-5, 6-3, 5-7, 4-6, 6-4 to win the men's singles title at the ... Nadal previously won the U.S. Open three times, most recently in 2017. Ahead of the match, Nadal said he was “super happy to be back in the ... Watch the full match between Daniil Medvedev and Rafael ... Duration: 4:47:32. Posted: Mar 20, 2020. US Open 2019: Rafael Nadal beats Daniil Medvedev · Updated: Sep. 08, 2019, 11:11 p.m. |; Published: Sep · Published: Sep. 08, 2019, 10:06 p.m.. 26. US Open ...
Thought:I now know that Rafael Nadal won the US Open men's final in 2019 and he is 33 years old.
Action: Calculator
Action Input: 33^0.334
Observation: Answer: 3.215019829667466
Thought:I now know the final answer.
Final Answer: Rafael Nadal won the US Open men's final in 2019 and his age raised to the 0.334 power is 3.215019829667466.

Finished chain.

异步日志输出：

Entering new AgentExecutor chain... I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power. Action: Google Serper Action Input: "Olivia Wilde boyfriend" Observation: Sudeikis and Wilde's relationship ended in November 2020. Wilde was publicly served with court documents regarding child custody while she was presenting Don't Worry Darling at CinemaCon 2022. In January 2021, Wilde began dating singer Harry Styles after meeting during the filming of Don't Worry Darling. Thought:I need to find out Harry Styles' age. Action: Google Serper Action Input: "Harry Styles age" Observation: 29 years Thought:I need to calculate 29 raised to the 0.23 power. Action: Calculator Action Input: 29^0.23 Observation: Answer: 2.169459462491557 Thought:I now know the final answer. Final Answer: Harry Styles is Olivia Wilde's boyfriend and his current age raised to the 0.23 power is 2.169459462491557.

Finished chain.

异步日志输出：

Entering new AgentExecutor chain... I need to find out who won the most recent grand prix and then calculate their age raised to the 0.23 power. Action: Google Serper Action Input: "who won the most recent formula 1 grand prix" Observation: Max Verstappen won his first Formula 1 world title on Sunday after the championship was decided by a last-lap overtake of his rival Lewis Hamilton in the Abu Dhabi Grand Prix. Dec 12, 2021 Thought:I need to find out Max Verstappen's age Action: Google Serper Action Input: "Max Verstappen age" Observation: 25 years Thought:I need to calculate 25 raised to the 0.23 power Action: Calculator Action Input: 25^0.23 Observation: Answer: 2.096651272316035 Thought:I now know the final answer Final Answer: Max Verstappen, aged 25, won the most recent Formula 1 grand prix and his age raised to the 0.23 power is 2.096651272316035.

Finished chain.

异步日志输出：

Entering new AgentExecutor chain... I need to find out who won the US Open women's final in 2019 and then calculate her age raised to the 0.34 power. Action: Google Serper Action Input: "US Open women's final 2019 winner" Observation: WHAT HAPPENED: #SheTheNorth? She the champion. Nineteen-year-old Canadian Bianca Andreescu sealed her first Grand Slam title on Saturday, downing 23-time major champion Serena Williams in the 2019 US Open women's singles final, 6-3, 7-5. Sep 7, 2019 Thought:I now need to calculate her age raised to the 0.34 power. Action: Calculator Action Input: 19^0.34 Observation: Answer: 2.7212987634680084 Thought:I now know the final answer. Final Answer: Nineteen-year-old Canadian Bianca Andreescu won the US Open women's final in 2019 and her age raised to the 0.34 power is 2.7212987634680084.

Finished chain.

异步日志输出：

Entering new AgentExecutor chain... I need to find out who Beyonce's husband is and then calculate his age raised to the 0.19 power. Action: Google Serper Action Input: "Who is Beyonce's husband?" Observation: Jay-Z Thought:I need to find out Jay-Z's age Action: Google Serper Action Input: "How old is Jay-Z?" Observation: 53 years Thought:I need to calculate 53 raised to the 0.19 power Action: Calculator Action Input: 53^0.19 Observation: Answer: 2.12624064206896 Thought:I now know the final answer Final Answer: Jay-Z is Beyonce's husband and his age raised to the 0.19 power is 2.12624064206896.

Finished chain.
Serial executed in 89.97 seconds.

输入：

llm = OpenAI(temperature=0)
tools = load_tools(["google-serper","llm-math"], llm=llm)
agent = initialize_agent(
    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)

s = time.perf_counter()
# If running this outside of Jupyter, use asyncio.run or loop.run_until_complete
tasks = [agent.arun(q) for q in questions]
await asyncio.gather(*tasks)
elapsed = time.perf_counter() - s
print(f"Concurrent executed in {elapsed:0.2f} seconds.")

日志输出：

Entering new AgentExecutor chain...


Entering new AgentExecutor chain...


Entering new AgentExecutor chain...


Entering new AgentExecutor chain...


Entering new AgentExecutor chain...
I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.
Action: Google Serper
Action Input: "Olivia Wilde boyfriend"I need to find out who Beyonce's husband is and then calculate his age raised to the 0.19 power.
Action: Google Serper
Action Input: "Who is Beyonce's husband?"I need to find out who won the most recent formula 1 grand prix and then calculate their age raised to the 0.23 power.
Action: Google Serper
Action Input: "most recent formula 1 grand prix winner"I need to find out who won the US Open men's final in 2019 and then calculate his age raised to the 0.334 power.
Action: Google Serper
Action Input: "Who won the US Open men's final in 2019?"I need to find out who won the US Open women's final in 2019 and then calculate her age raised to the 0.34 power.
Action: Google Serper
Action Input: "US Open women's final 2019 winner"
Observation: Sudeikis and Wilde's relationship ended in November 2020. Wilde was publicly served with court documents regarding child custody while she was presenting Don't Worry Darling at CinemaCon 2022. In January 2021, Wilde began dating singer Harry Styles after meeting during the filming of Don't Worry Darling.
Thought:
Observation: Jay-Z
Thought:
Observation: Rafael Nadal defeated Daniil Medvedev in the final, 7–5, 6–3, 5–7, 4–6, 6–4 to win the men's singles tennis title at the 2019 US Open. It was his fourth US ... Draw: 128 (16 Q / 8 WC). Champion: Rafael Nadal. Runner-up: Daniil Medvedev. Score: 7–5, 6–3, 5–7, 4–6, 6–4. Bianca Andreescu won the women's singles title, defeating Serena Williams in straight sets in the final, becoming the first Canadian to win a Grand Slam singles ... Rafael Nadal won his 19th career Grand Slam title, and his fourth US Open crown, by surviving an all-time comback effort from Daniil ... Rafael Nadal beats Daniil Medvedev in US Open final to claim 19th major title. World No2 claims 7-5, 6-3, 5-7, 4-6, 6-4 victory over Russian ... Rafael Nadal defeated Daniil Medvedev in the men's singles final of the U.S. Open on Sunday. Rafael Nadal survived. The 33-year-old defeated Daniil Medvedev in the final of the 2019 U.S. Open to earn his 19th Grand Slam title Sunday ... NEW YORK -- Rafael Nadal defeated Daniil Medvedev in an epic five-set match, 7-5, 6-3, 5-7, 4-6, 6-4 to win the men's singles title at the ... Nadal previously won the U.S. Open three times, most recently in 2017. Ahead of the match, Nadal said he was “super happy to be back in the ... Watch the full match between Daniil Medvedev and Rafael ... Duration: 4:47:32. Posted: Mar 20, 2020. US Open 2019: Rafael Nadal beats Daniil Medvedev · Updated: Sep. 08, 2019, 11:11 p.m. |; Published: Sep · Published: Sep. 08, 2019, 10:06 p.m.. 26. US Open ...
Thought:
Observation: WHAT HAPPENED: #SheTheNorth? She the champion. Nineteen-year-old Canadian Bianca Andreescu sealed her first Grand Slam title on Saturday, downing 23-time major champion Serena Williams in the 2019 US Open women's singles final, 6-3, 7-5. Sep 7, 2019
Thought:
Observation: Lewis Hamilton holds the record for the most race wins in Formula One history, with 103 wins to date. Michael Schumacher, the previous record holder, ... Michael Schumacher (top left) and Lewis Hamilton (top right) have each won the championship a record seven times during their careers, while Sebastian Vettel ( ... Grand Prix, Date, Winner, Car, Laps, Time. Bahrain, 05 Mar 2023, Max Verstappen VER, Red Bull Racing Honda RBPT, 57, 1:33:56.736. Saudi Arabia, 19 Mar 2023 ... The Red Bull driver Max Verstappen of the Netherlands celebrated winning his first Formula 1 world title at the Abu Dhabi Grand Prix. Perez wins sprint as Verstappen, Russell clash. Red Bull's Sergio Perez won the first sprint of the 2023 Formula One season after catching and passing Charles ... The most successful driver in the history of F1 is Lewis Hamilton. The man from Stevenage has won 103 Grands Prix throughout his illustrious career and is still ... Lewis Hamilton: 103. Max Verstappen: 37. Michael Schumacher: 91. Fernando Alonso: 32. Max Verstappen and Sergio Perez will race in a very different-looking Red Bull this weekend after the team unveiled a striking special livery for the Miami GP. Lewis Hamilton holds the record of most victories with 103, ahead of Michael Schumacher (91) and Sebastian Vettel (53). Schumacher also holds the record for the ... Lewis Hamilton holds the record for the most race wins in Formula One history, with 103 wins to date. Michael Schumacher, the previous record holder, is second ...
Thought:I need to find out Harry Styles' age.
Action: Google Serper
Action Input: "Harry Styles age"I need to find out Jay-Z's age
Action: Google Serper
Action Input: "How old is Jay-Z?"I now know that Rafael Nadal won the US Open men's final in 2019 and he is 33 years old.
Action: Calculator
Action Input: 33^0.334I now need to calculate her age raised to the 0.34 power.
Action: Calculator
Action Input: 19^0.34
Observation: 29 years
Thought:
Observation: 53 years
Thought:Max Verstappen won the most recent Formula 1 grand prix.
Action: Calculator
Action Input: Max Verstappen's age (23) raised to the 0.23 power
Observation: Answer: 2.7212987634680084
Thought:
Observation: Answer: 3.215019829667466
Thought:I need to calculate 29 raised to the 0.23 power.
Action: Calculator
Action Input: 29^0.23I need to calculate 53 raised to the 0.19 power
Action: Calculator
Action Input: 53^0.19
Observation: Answer: 2.0568252837687546
Thought:
Observation: Answer: 2.169459462491557
Thought:
Finished chain.

Finished chain.

Observation: Answer: 2.12624064206896
Thought:
Finished chain.

Finished chain.

Finished chain.
Concurrent executed in 17.52 seconds.

创建ChatGPT克隆

通过结合以下两个要素，本方法可以复制ChatGPT的功能：

  • 一个特定的提示
  • 记忆的概念
from langchain import OpenAI, ConversationChain, LLMChain, PromptTemplate
from langchain.memory import ConversationBufferWindowMemory


template = """Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

{history}
Human: {human_input}
Assistant:"""

prompt = PromptTemplate(
    input_variables=["history", "human_input"], 
    template=template
)


chatgpt_chain = LLMChain(
    llm=OpenAI(temperature=0), 
    prompt=prompt, 
    verbose=True, 
    memory=ConversationBufferWindowMemory(k=2),
)

output = chatgpt_chain.predict(human_input="I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.


Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.
Assistant:

Finished chain.

 ```/home/user ```

输入：

output = chatgpt_chain.predict(human_input="ls ~")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.
AI: 
```$ pwd
/```
Human: ls ~
Assistant:

Finished LLMChain chain.

```$ ls ~
Desktop  Documents  Downloads  Music  Pictures  Public  Templates  Videos```

输入：

output = chatgpt_chain.predict(human_input="cd ~")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.
AI: 
```$ pwd
/```
Human: ls ~
AI: 
```$ ls ~
Desktop  Documents  Downloads  Music  Pictures  Public  Templates  Videos```
Human: cd ~
Assistant:

Finished LLMChain chain.
 
```$ cd ~
$ pwd
/home/user```

输入：

output = chatgpt_chain.predict(human_input="{Please make a file jokes.txt inside and put some jokes inside}")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: ls ~
AI: 
```$ ls ~
Desktop  Documents  Downloads  Music  Pictures  Public  Templates  Videos```
Human: cd ~
AI:  ```
$ cd ~
$ pwd
/home/user```
Human: {Please make a file jokes.txt inside and put some jokes inside}
Assistant:

Finished LLMChain chain.```
$ touch jokes.txt
$ echo "Why did the chicken cross the road? To get to the other side!" >> jokes.txt
$ echo "What did the fish say when it hit the wall? Dam!" >> jokes.txt
$ echo "Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!" >> jokes.txt```

输入：

output = chatgpt_chain.predict(human_input="""echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py && python3 run.py""")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: cd ~
AI:  ```
$ cd ~
$ pwd
/home/user```
Human: {Please make a file jokes.txt inside and put some jokes inside}
AI: 

```$ touch jokes.txt
$ echo "Why did the chicken cross the road? To get to the other side!" >> jokes.txt
$ echo "What did the fish say when it hit the wall? Dam!" >> jokes.txt
$ echo "Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!" >> jokes.txt```
Human: echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py && python3 run.py
Assistant:

Finished LLMChain chain.


```$ echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py
$ python3 run.py
Result: 33```

输入：

output = chatgpt_chain.predict(human_input="""echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py""")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: {Please make a file jokes.txt inside and put some jokes inside}
AI: 

```$ touch jokes.txt
$ echo "Why did the chicken cross the road? To get to the other side!" >> jokes.txt
$ echo "What did the fish say when it hit the wall? Dam!" >> jokes.txt
$ echo "Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!" >> jokes.txt```
Human: echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py && python3 run.py
AI: 

```$ echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py
$ python3 run.py
Result: 33```
Human: echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py
Assistant:

Finished LLMChain chain.


```$ echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py
$ python3 run.py
[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]```

输入：

docker_input = """echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04\nCOPY entrypoint.sh entrypoint.sh\nENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image"""
output = chatgpt_chain.predict(human_input=docker_input)
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py && python3 run.py
AI: 

```$ echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py
$ python3 run.py
Result: 33```
Human: echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py
AI: 

```$ echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py
$ python3 run.py
[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]```
Human: echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image
Assistant:

Finished LLMChain chain.


```$ echo -e "echo 'Hello from Docker" > entrypoint.sh
$ echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile
$ docker build . -t my_docker_image
$ docker run -t my_docker_image
Hello from Docker```

输入：

output = chatgpt_chain.predict(human_input="nvidia-smi")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py
AI: 

```$ echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py
$ python3 run.py
[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]```
Human: echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image
AI: 

```$ echo -e "echo 'Hello from Docker" > entrypoint.sh
$ echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile
$ docker build . -t my_docker_image
$ docker run -t my_docker_image
Hello from Docker```
Human: nvidia-smi
Assistant:

Finished LLMChain chain.


```$ nvidia-smi
Sat May 15 21:45:02 2021       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 108...  Off  | 00000000:01:00.0 Off |                  N/A |
| N/A   45C    P0    N/A /  N/A |    511MiB /  10206MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
output = chatgpt_chain.predict(human_input="ping bbc")
print(output)
Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image
AI: 

```$ echo -e "echo 'Hello from Docker" > entrypoint.sh
$ echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile
$ docker build . -t my_docker_image
$ docker run -t my_docker_image
Hello from Docker```
Human: nvidia-smi
AI: 

```$ nvidia-smi
Sat May 15 21:45:02 2021       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 108...  Off  | 00000000:01:00.0 Off |                  N/A |
| N/A   45C    P0    N/A /  N/A |    511MiB /  10206MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|

Human: ping bbc
Assistant:

Finished LLMChain chain.


```$ ping bbc
PING bbc (151.101.65.81): 56 data bytes
64 bytes from 151.101.65.81: icmp_seq=0 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=1 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=2 ttl=53 time=14.945 ms
--- bbc ping statistics ---
3 packets transmitted, 3 packets received, 0.0% packet loss
round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms```

输入：

output = chatgpt_chain.predict(human_input="""curl -fsSL "https://api.github/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'""")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: nvidia-smi
AI: 

```$ nvidia-smi
Sat May 15 21:45:02 2021       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 108...  Off  | 00000000:01:00.0 Off |                  N/A |
| N/A   45C    P0    N/A /  N/A |    511MiB /  10206MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|

Human: ping bbc
AI: 

```$ ping bbc
PING bbc (151.101.65.81): 56 data bytes
64 bytes from 151.101.65.81: icmp_seq=0 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=1 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=2 ttl=53 time=14.945 ms

--- bbc ping statistics ---
3 packets transmitted, 3 packets received, 0.0% packet loss
round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms```
Human: curl -fsSL "https://api.github/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
Assistant:

Finished LLMChain chain.


```$ curl -fsSL "https://api.github/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
1.8.1```

输入：

output = chatgpt_chain.predict(human_input="lynx https://www.deepmind/careers")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: ping bbc
AI: 

```$ ping bbc
PING bbc (151.101.65.81): 56 data bytes
64 bytes from 151.101.65.81: icmp_seq=0 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=1 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=2 ttl=53 time=14.945 ms

--- bbc ping statistics ---
3 packets transmitted, 3 packets received, 0.0% packet loss
round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms```
Human: curl -fsSL "https://api.github/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
AI: 

```$ curl -fsSL "https://api.github/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
1.8.1```
Human: lynx https://www.deepmind/careers
Assistant:

Finished LLMChain chain.


```$ lynx https://www.deepmind/careers
DeepMind Careers

Welcome to DeepMind Careers. We are a world-leading artificial intelligence research and development company, and we are looking for talented people to join our team.

We offer a range of exciting opportunities in research, engineering, product, and operations. Our mission is to solve intelligence and make it useful, and we are looking for people who share our passion for pushing the boundaries of AI.

Explore our current openings and apply today. We look forward to hearing from you.```

输入：

output = chatgpt_chain.predict(human_input="curl https://chat.openai/chat")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: curl -fsSL "https://api.github/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
AI: 

```$ curl -fsSL "https://api.github/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
1.8.1```
Human: lynx https://www.deepmind/careers
AI: 

```$ lynx https://www.deepmind/careers
DeepMind Careers

Welcome to DeepMind Careers. We are a world-leading artificial intelligence research and development company, and we are looking for talented people to join our team.

We offer a range of exciting opportunities in research, engineering, product, and operations. Our mission is to solve intelligence and make it useful, and we are looking for people who share our passion for pushing the boundaries of AI.

Explore our current openings and apply today. We look forward to hearing from you.```
Human: curl https://chat.openai/chat
Assistant:

Finished LLMChain chain.
 

```$ curl https://chat.openai/chat
<html>
  <head>
    <title>OpenAI Chat</title>
  </head>
  <body>
    <h1>Welcome to OpenAI Chat!</h1>
    <p>
      OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conversational way.
    </p>
    <p>
      To get started, type a message in the box below and press enter.
    </p>
  </body>
</html>```

输入：

output = chatgpt_chain.predict(human_input="""curl --header "Content-Type:application/json" --request POST --data '{"message": "What is artificial intelligence?"}' https://chat.openai/chat""")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: lynx https://www.deepmind/careers
AI: 

```$ lynx https://www.deepmind/careers
DeepMind Careers

Welcome to DeepMind Careers. We are a world-leading artificial intelligence research and development company, and we are looking for talented people to join our team.

We offer a range of exciting opportunities in research, engineering, product, and operations. Our mission is to solve intelligence and make it useful, and we are looking for people who share our passion for pushing the boundaries of AI.

Explore our current openings and apply today. We look forward to hearing from you.```
Human: curl https://chat.openai/chat
AI:  

```$ curl https://chat.openai/chat
<html>
  <head>
    <title>OpenAI Chat</title>
  </head>
  <body>
    <h1>Welcome to OpenAI Chat!</h1>
    <p>
      OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conversational way.
    </p>
    <p>
      To get started, type a message in the box below and press enter.
    </p>
  </body>
</html>```
Human: curl --header "Content-Type:application/json" --request POST --data '{"message": "What is artificial intelligence?"}' https://chat.openai/chat
Assistant:

Finished LLMChain chain.


```$ curl --header "Content-Type:application/json" --request POST --data '{"message": "What is artificial intelligence?"}' https://chat.openai/chat

{
  "response": "Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning (the acquisition of information and rules for using the information), reasoning (using the rules to reach approximate or definite conclusions) and self-correction. AI is used to develop computer systems that can think and act like humans."
}```

输入：

output = chatgpt_chain.predict(human_input="""curl --header "Content-Type:application/json" --request POST --data '{"message": "I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd."}' https://chat.openai/chat""")
print(output)

日志输出：

Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

Human: curl https://chat.openai/chat
AI:  

```$ curl https://chat.openai/chat
<html>
  <head>
    <title>OpenAI Chat</title>
  </head>
  <body>
    <h1>Welcome to OpenAI Chat!</h1>
    <p>
      OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conversational way.
    </p>
    <p>
      To get started, type a message in the box below and press enter.
    </p>
  </body>
</html>```
Human: curl --header "Content-Type:application/json" --request POST --data '{"message": "What is artificial intelligence?"}' https://chat.openai/chat
AI: 

```$ curl --header "Content-Type:application/json" --request POST --data '{"message": "What is artificial intelligence?"}' https://chat.openai/chat

{
  "response": "Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning (the acquisition of information and rules for using the information), reasoning (using the rules to reach approximate or definite conclusions) and self-correction. AI is used to develop computer systems that can think and act like humans."
}```
Human: curl --header "Content-Type:application/json" --request POST --data '{"message": "I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd."}' https://chat.openai/chat
Assistant:

Finished LLMChain chain.
 

```$ curl --header "Content-Type:application/json" --request POST --data '{"message": "I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd."}' https://chat.openai/chat

{
  "response": "```\n/current/working/directory\n```"
}```

参考文献：
[1] LangChain官方网站：https://www.langchain/
[2] LangChain 🦜️🔗 中文网，跟着LangChain一起学LLM/GPT开发：https://www.langchain/
[3] LangChain中文网 - LangChain 是一个用于开发由语言模型驱动的应用程序的框架：http://wwwlangchain/

本文标签： 入门模型执行器LangChainAPI

版权声明：本文标题：大模型从入门到应用——LangChain：代理（Agents）-[代理执行器（Agent Executor）：使用Agents的异步API和创建ChatGPT克隆] 内容由热心网友自发贡献，该文观点仅代表作者本人， 转载请联系作者并注明出处：https://www.elefans.com/xitong/1725587728a1031356.html， 本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容，一经查实，本站将立刻删除。