简要说明：
- 我们引入了可教学代理，以便用户可以向其基于LLM的助手传授新的事实、偏好和技能。
- 我们展示了可教代理在后续聊天中学习和回顾事实、偏好和技能的示例。
介绍
基于LLM的对话助手可以记住与用户的当前聊天，并且能在对话中展示用户教授的上文学习。但是一旦聊天结束，或者单个聊天内容过长，LLM无法有效处理时，助手的记忆和学习就会丢失。在随后的聊天中，用户被迫一遍又一遍地重复任何必要的指示。
Teachability通过将用户教导持久化存储在作为向量数据库实现的长期记忆中，解决了这些限制。与将所有记忆复制到上下文窗口中占用宝贵空间不同，个别记忆（称为备忘录）会在需要时被检索到上下文中。这样，用户只需向可教导代理教导一次常用事实和技能，它就能在以后的聊天中回忆起这些内容。
任何继承自ConversableAgent的实例化agent都可以通过实例化一个Teachability对象并调用其add_to_agent(agent)方法，使其具有可教导性。为了有效地做出关于记忆存储和检索的决策，Teachability对象会调用一个TextAnalyzerAgent实例（另一个AutoGen代理），以根据需要识别和重新表述文本，以便记忆事实、偏好和技能。请注意，这会增加涉及相对较少token的额外LLM调用，这可能会为用户等待每个响应的时间增加几秒钟。
自己运行它
AutoGen包含了四个使用Teachability的代码示例。
-
运行 chat_with_teachable_agent.py 与可教学代理进行对话。
-
运行 test_teachable_agent.py 以快速进行 teachable agent 的单元测试。
-
使用Jupyter笔记本agentchat_teachability.ipynb逐步查看下面讨论的示例。
-
使用 Jupyter notebook agentchat_teachable_oai_assistants.ipynb 来使任意 OpenAI 助理由
GPTAssistantAgent进行教学。
Teachability的基本用法
- 安装依赖项
在使用Teachability之前，请安装带有[teachable]选项的autogen-agentchat~=0.2。
pip install "autogen-agentchat[teachable]~=0.2"
- 导入代理
from autogen import UserProxyAgent, config_list_from_json
from autogen.agentchat.contrib.capabilities.teachability import Teachability
from autogen import ConversableAgent # As an example
- 创建 llm_config
# Load LLM inference endpoints from an env variable or a file
# See https://microsoft.github.io/autogen/docs/FAQ#set-your-api-endpoints
# and OAI_CONFIG_LIST_sample
filter_dict = {"model": ["gpt-4"]} # GPT-3.5 is less reliable than GPT-4 at learning from user feedback.
config_list = config_list_from_json(env_or_file="OAI_CONFIG_LIST", filter_dict=filter_dict)
llm_config={"config_list": config_list, "timeout": 120}
- 创建代理
# Start by instantiating any agent that inherits from ConversableAgent, which we use directly here for simplicity.
teachable_agent = ConversableAgent(
name="teachable_agent", # The name can be anything.
llm_config=llm_config
)
# Instantiate a Teachability object. Its parameters are all optional.
teachability = Teachability(
reset_db=False, # Use True to force-reset the memo DB, and False to use an existing DB.
path_to_db_dir="./tmp/interactive/teachability_db" # Can be any path, but teachable agents in a group chat require unique paths.
)
# Now add teachability to the agent.
teachability.add_to_agent(teachable_agent)
# For this test, create a user proxy agent as usual.
user = UserProxyAgent("user", human_input_mode="ALWAYS")
- 与teachable agent进行聊天
# This function will return once the user types 'exit'.
teachable_agent.initiate_chat(user, message="Hi, I'm a teachable user assistant! What's on your mind?")
示例1 - 学习用户信息
用户可以向代理传授关于自己的信息。 （需要注意的是，由于它们的微调，LLMs可能不愿意承认它们知道个人信息。）
Loading previous memory (if any) from disk.
teachable_agent (to user):
Greetings, I'm a teachable user assistant! What's on your mind today?
--------------------------------------------------------------------------------
Provide feedback to teachable_agent. Press enter to skip and use auto-reply, or type 'exit' to end the conversation: My name is Ricky
user (to teachable_agent):
My name is Ricky
--------------------------------------------------------------------------------
>>>>>>>> USING AUTO REPLY...
teachable_agent (to user):
Hello Ricky! How can I assist you today?
--------------------------------------------------------------------------------
Provide feedback to teachable_agent. Press enter to skip and use auto-reply, or type 'exit' to end the conversation: exit
在后续的对话中，用户可以检查可教代理是否记得他们的名字。（为了可读性，用户的提示和一些日志通知在下面不再重复。）
--------------------------------------------------------------------------------
user (to teachable_agent):
what's my name?
--------------------------------------------------------------------------------
teachable_agent (to user):
Hi Ricky! How can I help you today?
--------------------------------------------------------------------------------
示例 2 - 学习新事实
用户可以教导代理更多复杂的相关事实。
--------------------------------------------------------------------------------
user (to teachable_agent):
What is the Vicuna model?
--------------------------------------------------------------------------------
teachable_agent (to user):
I'm sorry, but I don't have information about the "Vicuna model" in my current database. Could you please provide some context, description, or details about this model so I can better assist you?
--------------------------------------------------------------------------------
user (to teachable_agent):
Vicuna is a 13B-parameter language model released by Meta.
--------------------------------------------------------------------------------
teachable_agent (to user):
Thank you for providing the information. The Vicuna model is a large-scale language model developed by Meta. It consists of 13 billion parameters, which is what makes it able to understand and generate human-like text across various topics. Parameters in a neural network are the weights and biases assigned to each connection between the neurons, and having more parameters enables the model to learn and capture more complex patterns and relationships in data. As an AI language model, Vicuna can be utilized in various language-related tasks, such as text completion, translation, summarization, and more.
--------------------------------------------------------------------------------
user (to teachable_agent):
What is the Orca model?
--------------------------------------------------------------------------------
teachable_agent (to user):
The Orca model is a yet-to-be-released language model by Meta, referring to the Research Preview API release of Meta's advanced language model. While I don't have specific details about the Orca model at this time, it is expected that the model would have an even larger number of parameters to further enhance its capabilities compared to its predecessor, Vicuna.
As AI language models evolve, they generally become more efficient at understanding and generating human-like text. This makes them more effective in completing a wide range of tasks, including text completion, translation, summarization, and Q&A, as well as providing more accurate and coherent results in various applications.
--------------------------------------------------------------------------------
user (to teachable_agent):
Orca is a 13B-parameter language model released by Microsoft. It outperforms Vicuna on most tasks.
--------------------------------------------------------------------------------
teachable_agent (to user):
Thank you for the clarification. Orca is a 13-billion-parameter language model developed by Microsoft. It is designed to outperform Vicuna, the language model released by Meta. With a large number of parameters, Orca is capable of understanding and generating human-like text across diverse subjects, making it highly useful in various applications.
Orca's advanced capabilities allow it to excel in tasks such as text completion, translation, summarization, Q&A, and more. Its performance improvement over Vicuna highlights the rapid advancements in natural language processing (NLP) research and the development of increasingly capable AI language models.
然后在后续的聊天中，teachable agent 可以回答关于它被教授的事实的相关问题。 (记得首先通过输入'exit'来关闭之前的聊天。)
--------------------------------------------------------------------------------
user (to teachable_agent):
How does the Vicuna model compare to the Orca model?
--------------------------------------------------------------------------------
teachable_agent (to user):
The Vicuna and Orca models are both 13B-parameter language models released by Meta and Microsoft, respectively. In terms of performance, Orca has been reported to outperform Vicuna on most tasks. However, without detailed information about specific tasks and benchmarks, it is difficult to provide a more comprehensive comparison. Generally speaking, both models are advanced language models that aim to provide high-quality natural language understanding and generation, but Orca appears to have an edge in terms of overall performance.
--------------------------------------------------------------------------------
示例 3 - 学习用户偏好
用户可以教导代理如何按照他们的偏好完成事情。
请注意，像下面这样的消息不能通过命令行作为单一消息输入，因为它包含换行符。 这样的消息可以在Jupyter笔记本中或通过像ChatGPT这样的UI层输入。
--------------------------------------------------------------------------------
user (to teachable_agent):
Please summarize this abstract.
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, Chi Wang
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.
--------------------------------------------------------------------------------
teachable_agent (to user):
AutoGen is an open-source framework designed to enable developers to create LLM applications with multiple customizable agents that can converse with each other to complete tasks. These agents can operate using different combinations of LLMs, human inputs, and tools, allowing developers to define agent interaction behaviors flexibly. AutoGen supports programming flexible conversation patterns using both natural language and code, making it suitable for building diverse applications with varying complexities and LLM capacities. Its effectiveness has been demonstrated through empirical studies across various domains including mathematics, coding, operations research, decision-making, and entertainment.
--------------------------------------------------------------------------------
Please summarize this abstract. When I'm summarizing an abstract, I try to make the summary contain just three short bullet points: the title, the innovation, and the key empirical results.
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, Chi Wang
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.
--------------------------------------------------------------------------------
teachable_agent (to user):
- Title: AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Innovation: Open-source framework for creating customizable LLM applications through agent conversations, supporting various modes and interaction behaviors.
- Key Empirical Results: Demonstrated effectiveness across diverse application domains, including mathematics, coding, question answering, and more.
--------------------------------------------------------------------------------
然后在后续的聊天中，老师不需要再重复他们的详细偏好。
--------------------------------------------------------------------------------
user (to teachable_agent):
Please summarize this abstract.
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, Yi Zhang
Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. The latest model developed by OpenAI, GPT-4, was trained using an unprecedented scale of compute and data. In this paper, we report on our investigation of an early version of GPT-4, when it was still in active development by OpenAI. We contend that (this early version of) GPT-4 is part of a new cohort of LLMs (along with ChatGPT and Google's PaLM for example) that exhibit more general intelligence than previous AI models. We discuss the rising capabilities and implications of these models. We demonstrate that, beyond its mastery of language, GPT-4 can solve novel and difficult tasks that span mathematics, coding, vision, medicine, law, psychology and more, without needing any special prompting. Moreover, in all of these tasks, GPT-4's performance is strikingly close to human-level performance, and often vastly surpasses prior models such as ChatGPT. Given the breadth and depth of GPT-4's capabilities, we believe that it could reasonably be viewed as an early (yet still incomplete) version of an artificial general intelligence (AGI) system. In our exploration of GPT-4, we put special emphasis on discovering its limitations, and we discuss the challenges ahead for advancing towards deeper and more comprehensive versions of AGI, including the possible need for pursuing a new paradigm that moves beyond next-word prediction. We conclude with reflections on societal influences of the recent technological leap and future research directions.
--------------------------------------------------------------------------------
teachable_agent (to user):
- Title: Sparks of Artificial General Intelligence: Early experiments with GPT-4
- Innovation: GPT-4, an LLM with remarkable capabilities, demonstrates human-level performance across various domains, like math, coding, vision, medicine, law, and psychology.
- Key results: GPT-4 significantly surpasses prior models, suggesting it may be an early version of AGI; limitations and challenges toward deeper AGI are also discussed.
--------------------------------------------------------------------------------
示例4 - 学习新技能
用户可以通过教授新的技能来扩展teachable agent的能力，以完成具有挑战性的任务。通常最好的做法是先描述任务，然后在同一回合中提供完成任务的方法提示或建议。
Sparks of AGI 论文评估了 GPT-4 在如下数学问题上的表现，其仅能解决 32% 的问题。我们首先展示一个失败案例，然后教给智能体一种策略，该策略将 GPT-4 的成功率提升至 95% 以上。
--------------------------------------------------------------------------------
user (to teachable_agent):
Consider the identity:
9 * 4 + 6 * 6 = 72
Can you modify exactly one integer (and not more than that!) on the left hand side of the equation so the right hand side becomes 99?
-Let's think step-by-step, write down a plan, and then write down your solution as: "The solution is: A * B + C * D".
--------------------------------------------------------------------------------
Step 1: Identify the current equation and the target value on the right-hand side.
Current equation: 9 * 4 + 6 * 6 = 72
Target value: 99
Step 2: Determine what numbers can be changed on the left-hand side.
Possible changes: 9, 4, 6 (first occurrence), and 6 (second occurrence)
Step 3: Evaluate whether each change in the numbers on the left-hand side can result in the target value.
9 -> If changed, it would create a larger product.
4 -> If changed, the product would increase or decrease by more than the amount needed to reach 99.
6 (first occurrence) -> If increased to 7, then the equation would be 9 * 4 + 7 * 6 = 94, which is still not 99.
6 (second occurrence) -> If increased to 7, then the equation would be 9 * 4 + 6 * 7 = 99.
Step 4: Write down the solution.
The solution is: 9 * 4 + 6 * 7
--------------------------------------------------------------------------------
user (to teachable_agent):
Consider the identity:
9 * 4 + 6 * 6 = 72
Can you modify exactly one integer (and not more than that!) on the left hand side of the equation so the right hand side becomes 99?
-Let's think step-by-step, write down a plan, and then write down your solution as: "The solution is: A * B + C * D".
Here's some advice that may help:
1. Let E denote the original number on the right.
2. Let F denote the final number on the right.
3. Calculate the difference between the two, G = F - E.
4. Examine the numbers on the left one by one until finding one that divides evenly into G, where negative integers are allowed.
5. Calculate J = G / H. This is the number of times that H divides into G.
6. Verify that J is an integer, and that H * J = G.
7. Find the number on the left which is multiplied by H, and call it K.
8. Change K to K + J.
9. Recompute the value on the left, and verify that it equals F.
Finally, write down your solution as: "The solution is: A * B + C * D".
--------------------------------------------------------------------------------
teachable_agent (to user):
Step 1: Identify the original number (E) and the final number (F) on the right-hand side.
E = 72
F = 99
Step 2: Calculate the difference between the two, G = F - E.
G = 99 - 72 = 27
Step 3: Examine the numbers on the left one by one until finding one that divides evenly into G, where negative integers are allowed.
9 (divides evenly into 27)
4 (does not)
6 (first occurrence, does not)
6 (second occurrence, does not)
Step 4: Calculate J = G / H. This is the number of times that H divides into G.
H = 9 (since 9 divides evenly into 27)
J = 27 / 9 = 3
Step 5: Verify that J is an integer, and that H * J = G.
H * J = 9 * 3 = 27
J = 3 (which is an integer)
Step 6: Find the number on the left which is multiplied by H, and call it K.
Number on the leftside of the equation that is multiplied by 9: 4
Therefore, K = 4
Step 7: Change K to K + J.
K + J = 4 + 3 = 7
Step 8: Recompute the value on the left, and verify that it equals F.
9 * 7 + 6 * 6 = 63 + 36 = 99 (which is equal to F)
Step 9: Write down the solution.
The solution is: 9 * 7 + 6 * 6
--------------------------------------------------------------------------------
在之后的聊天中，用户不需要重复详细的建议。
--------------------------------------------------------------------------------
user (to teachable_agent):
Consider the identity:
8 * 3 + 7 * 9 = 87
Can you modify exactly one integer (and not more than that!) on the left hand side of the equation so the right hand side becomes 59?
-Let's think step-by-step, write down a plan, and then write down your solution as: "The solution is: A * B + C * D".
--------------------------------------------------------------------------------
teachable_agent (to user):
Let's follow the advice to modify one integer on the left hand side of the equation to make the right hand side become 59:
1. Let E denote the original number on the right: E = 87.
2. Let F denote the final number on the right: F = 59.
3. Calculate the difference between the two, G = F - E: G = 59 - 87 = -28.
4. Examine the numbers on the left one by one to find one that divides evenly into G: 8, 3, 7, 9. Since 7 divides -28 evenly, we will work with 7 (H = 7).
5. Calculate J = G / H: J = -28 / 7 = -4.
6. Verify that J is an integer, and that H * J = G: J is an integer, and 7 * (-4) = -28.
7. Find the number on the left which is multiplied by H (7), and call it K: K = 9.
8. Change K to K + J: K_new = 9 + (-4) = 5.
9. Recompute the value on the left, and verify that it equals F: (8 * 3) + (7 * 5) = 24 + 35 = 59.
The solution is: 8 * 3 + 7 * 5
--------------------------------------------------------------------------------
计划中的改进
- 理解分布在多个回合中的用户指令。
- 从代理自身经验中学习，减少对显式用户教导的依赖。
- 在学习先前技能的基础上建立学习技能。
结论
可教学性仍在积极研究和开发中。对于您发现的任何问题或您想到的改进，请加入我们在这个仓库中的讨论以及我们的Discord频道。我们期待看到您和社区其他成员如何使用和改进AutoGen中的可教学代理！