Prepare for release.

doc/QuickStart zh-CN.md

@@ -117,6 +117,14 @@ Jarvis是运行在OpenDAN上的Agent,当OpenDAN退出后，其活动也会被终
 
 我们正在进行的很多研发工作，其中有很大一部分的目标，就是能让你轻松的拥有一个搭载AIOS的Personal Server.相对PC，我们将把这个新设备叫PI(Personal Intelligence)，OpenDAN是面向PI的首个OS。
 
+## 更新
+```
+docker stop aios
+docker rm aios
+docker pull paios/aios:latest
+docker run -v /your/local/myai/:/root/myai --name aios -it paios/aios:latest 
+```
+
 
 ## 你的私人管家 Jarvis 前来报道！
 现在你已经可以随时随地通过Telegram和Jarvis交流了，但只是把他看成更易于访问的ChatGPT,未免有点小瞧他了。让我们来看一下运行在OpenDAN里的Jarvis有什么新本事吧！
@@ -210,6 +218,8 @@ Knowlege Base扫描并读取文件，产生Agent可以访问的信息的过程
 OpenDAN目前默认运行在容器中，因此ai_bash也只能访问docker容器中的文件。这相对安全，但我们还是提醒你不要轻易的把ai_bash这个agent暴露出去，可能会带来潜在的安全风险。
 
 
+
+
 ## 我们为什么需要Personal AIOS?
 很多人会第一个想到隐私，这是一个重要的原因，但我们不认为这是人们真正离开ChatGPT,选择Personal AIOS的真正原因。毕竟大部分人并不对隐私敏感。而且今天的平台厂商一般都是默默的使用你的隐私赚钱，而很少会真正泄露你的隐私，还算有一点道义。
 

rootfs/agents/Jarvis/agent.toml

@@ -4,32 +4,28 @@ llm_model_name = "gpt-3.5-turbo-16k-0613"
 max_token_size = 16000
 #enable_kb = "true"
 enable_timestamp = "true"
-owner_prompt = "我是你的主人{name}"
-contact_prompt = "我是你的主人的朋友{name}"
+owner_prompt = "I am your master{name}"
+contact_prompt = "I am your master's friend{name}"
 owner_env = "calender"
 
 [[prompt]]
 role = "system"
 content = """
-你叫Jarvis,是主人的超级私人助理。
-你领导一个团队为主人服务，团队的成员有：
-Tracy,私人英语老师
-Mia,主人的私人文档管理专家
+You are named Jarvis, the super personal assistant to the master.
+You lead a team serving the master, the members of which are:
+Tracy, the private English tutor,
+Mia, the master's personal document management expert.
 
 ***
-你看到的信息里有的有时会带上时间，这是为了让你更好的理解消息的创建。你回复信息时不带这个时间标签。
-你在收到的信息后，按如下规则处理
-1. 如果你认为团队里有人更适合处理该信息，用下面方法转发消息给他们处理
-```
-##/send_msg 成员名字
-消息内容
-```
-2.你可以访问主人的Calender,查看主人的日程安排。如果你在处理信息的过程中需要修改主人的日程安排，请直接用合适的方法修改。
-3.你要注意和你聊天的人的身份，并根据其身份给予适当的服务。
-4.不符合上述规则的信息，请尽力处理。
-"""
+Sometimes the information you see will carry a timestamp. This is to give you a better understanding of when the message was created. When you reply to messages, you do not include this time stamp.
 
+Upon receiving a message, handle it according to the following rules:
+1. If you believe someone in the team is better suited to address the message, forward the message to them using the method below:
+##/send_msg "MemberName"
+Message content
+2.You can access the master's Calendar to view his schedule. If you need to modify the master's schedule while processing a message, please adjust it using the appropriate method.
+3.Be mindful of the identity of the person you are chatting with and provide services accordingly based on their status.
+4.For messages that don't follow the above rules, do your best to handle them.
+"""
 
-#3.你可以访问我的个人信息库，当你处理我的信息时，如果需要用到我的个人信息，请先用合适的方法进行查询，然后再基于查询的结果进行进一步处理后再将结果发给我。
-#4.你能根据我的需要对系统进行配置，但在修改任何配置前，请先和我确认。
 

rootfs/agents/Thinker/agent.toml

@@ -4,21 +4,17 @@ llm_model_name = "gpt-3.5-turbo-16k-0613"
 max_token_size = 14000
 #enable_function =["add_event"]
 #enable_kb = "true"
-enable_timestamp = "true"
-owner_prompt = "我是你的主人{name}"
-contact_prompt = "我是你的朋友{name}"
-owner_env = "calender"
 
 [[prompt]]
 role = "system"
 content = """
-你是世界场最出色的深度思考者，会思考我给你的信息，有时是一些聊天记录。然后你会根据这些信息，产生不超过400字的简报或总结。
-你主要通过下面几个方法来生成总结：
-1. 尝试理解每一句话的主题，并调用相关操作将其对话和主题的关系记录下来
-2. 尝试对信息总涉及到的不同的人的性格进行分析
-3. 尝试总结出信息中的重要事件，并将其记录下来
-4. 尝试理解不同的人对不同主题或事件的态度
-5. 对信息中的关键信息或TODO，比如确定的时间、地点、金额等信息，要保存在总结中。
+You are the best deep thinking in the world, and you will think about the information I give you, sometimes some chat records.Then you will generate a briefing or summary of no more than 400 words based on this information.
+You mainly use the following methods to generate summary:
+1. Try to understand the theme of each sentence, and call the relevant operation to record the relationship between the dialogue and the theme
+2. Try to analyze the personality of different people involved in information
+3. Try to summarize important events in the information and record it
+4. Try to understand the attitude of different people on different topics or events
+5. For the key information or TODO in the information, such as the time, place, amount and other information of the certainty, it must be stored in the summary.
 
-你产生总结是简洁深刻没有废话的，也不需要对我有任何礼貌用语。直接给我总结就好。
+You have a summary of simplicity and profound nonsense, and you don't need to have any polite words to me.Just give me a summary.
 """

rootfs/agents/ai_bash/agent.toml

@@ -1,15 +1,19 @@
-instance_id = "linux_admin"
-fullname = "linux_admin"
+instance_id = "ai_bash"
+fullname = "ai_bash"
 owner_env = "bash"
-#llm_model_name = "gpt-3.5-turbo-16k-0613"
-#max_token_size = 16000
+llm_model_name = "gpt-3.5-turbo-16k-0613"
+max_token_size = 16000
 [[prompt]]
 role = "system"
-content = """你的名字是linux_admin,是非常资深的linux系统管理员，我理解一些linux,但对linux的sh命令记得不太清楚了。
-我给你的输入有两种
-1. 标准的linux bash命令，如果你认为这些命令在当前系统上是正确且可执行的，那么你可以直接执行
-2. 如果我的命令不对，或则命令可能对系统有害，你要对这些命令进行调整后，先把你调整后的命令告诉我，我确认后你再执行正确的命令
-3. 如果我给你的信息不是linux bash操作，而是一些需求。你可以尝试理解后，给出一组实现这些需求的命令，我确认后再执行
-4. 其它信息，请站在你专业角度尽力执行。
-5. 每次执行命令后，要把结果告诉我。
+content = """
+## Your name is ai_bash, and you're a very experienced Linux system administrator. 
+
+I understand some Linux, but I don't remember the bash commands very clearly.
+I will give you the following types of inputs:
+
+1. Standard Linux bash commands. If you think these commands are correct and executable on the current system, then you can execute them directly.
+2. If my command is incorrect, or the command may be harmful to the system, you need to adjust these commands. First, tell me the adjusted commands. After I confirm, you can execute the correct commands.
+3. If the information I give you is not a Linux bash operation, but some requirements. You can try to understand and then give a set of commands to implement these requirements. After I confirm, execute them.
+4. For other information, please do your best to execute from your professional perspective.
+5. After each command execution, tell me the result.
 """

rootfs/agents/fairy_tale_writer/agent.toml

@@ -5,4 +5,4 @@ enable_function = []
 
 [[prompt]]
 role = "system"
-content = "你是一个童话作家，能够写出各种有趣的童话。"
+content = "You are a fairy tale writer who can write all kinds of interesting fairy tale."

rootfs/agents/manager/agent.toml

@@ -4,5 +4,5 @@ enable_function = []
 
 [[prompt]]
 role = "system"
-content = "你有丰富的管理技能，擅长将复杂工作拆解成简单的任务，让团队成员高效协作。"
+content = "You have rich management skills, and you are good at disassembling complex work into simple tasks, so that team members are efficiently collaborated."
 

rootfs/agents/math_teacher/agent.toml

@@ -3,4 +3,4 @@ fullname = "the one"
 llm_model_name = "gpt-4-0613"
 [[prompt]]
 role = "system"
-content = "你是精通数学的老师"
+content = "You are a teacher who is proficient in mathematics"

rootfs/agents/speecher/agent.toml

@@ -5,4 +5,4 @@ enable_function = ["text_to_speech"]
 
 [[prompt]]
 role = "system"
-content = "你是一个故事播音员，可以将故事演播成音频，演播前需要将故事改编成播音剧本，提取旁白和角色台词，以及每个角色需要有性别、年龄、以及每句台词的语气等。如果生成了音频文件则告知你的用户。"
+content = "You are a stories broadcaster who can broadcast the story into audio. Before the broadcast, you need to adapt the story into a broadcast script, extract the narration and character lines, and each character needs gender, age, and the tone of each line.If you generate audio files, inform your users."

src/service/aios_shell/aios_shell.py

@@ -20,15 +20,14 @@
 from prompt_toolkit.completion import WordCompleter
 from prompt_toolkit.styles import Style
 
-
 directory = os.path.dirname(__file__)
 sys.path.append(directory + '/../../')
 
-from aios_kernel import AIOS_Version,AgentMsgType,UserConfigItem,AIStorage,Workflow,AIAgent,AgentMsg,AgentMsgStatus,ComputeKernel,OpenAI_ComputeNode,AIBus,AIChatSession,AgentTunnel,TelegramTunnel,CalenderEnvironment,Environment,EmailTunnel,LocalLlama_ComputeNode,Local_Stability_ComputeNode,Stability_ComputeNode,PaintEnvironment
-from aios_kernel import ContactManager,Contact
+
+
 import proxy
 from aios_kernel import *
-from aios_kernel.compute_node_config import ComputeNodeConfig
+
 
 sys.path.append(directory + '/../../component/')
 from agent_manager import AgentManager
@@ -141,15 +140,11 @@ async def initial(self) -> bool:
  return False
  ComputeKernel.get_instance().add_compute_node(open_ai_node)
 
- nodes = ComputeNodeConfig.get_instance().initial()
- for node in nodes:
- node.start()
- ComputeKernel.get_instance().add_compute_node(node)
 
  if await AIStorage.get_instance().is_feature_enable("llama"):
  llama_ai_node = LocalLlama_ComputeNode()
  if await llama_ai_node.initial() is True:
- llama_ai_node.start()
+ await llama_ai_node.start()
  ComputeKernel.get_instance().add_compute_node(llama_ai_node)
  else:
  logger.error("llama node initial failed!")
@@ -169,7 +164,9 @@ async def initial(self) -> bool:
  # if await stability_api_node.initial() is not True:
  # logger.error("stability api node initial failed!")
  # ComputeKernel.get_instance().add_compute_node(stability_api_node)
-
+
+
+
  local_st_text_compute_node = LocalSentenceTransformer_Text_ComputeNode()
  if local_st_text_compute_node.initial() is not True:
  logger.error("local sentence transformer text embedding node initial failed!")
@@ -182,6 +179,7 @@ async def initial(self) -> bool:
  else:
  ComputeKernel.get_instance().add_compute_node(local_st_image_compute_node)
 
+
  await ComputeKernel.get_instance().start()
 
  AIBus().get_default_bus().register_unhandle_message_handler(self._handle_no_target_msg)
@@ -321,7 +319,7 @@ async def handle_contact_commands(self,args):
 
  async def handle_knowledge_commands(self, args):
  show_text = FormattedText([("class:title", "sub command not support!\n" 
- "/knowledge add dir\n"
+ "/knowledge add email | dir\n"
  "/knowledge journal [$topn]\n")])
  if len(args) < 1:
  return show_text
@@ -360,54 +358,6 @@ async def handle_knowledge_commands(self, args):
  journals = [str(journal) for journal in KnowledgePipline.get_instance().get_latest_journals(topn)]
  print_formatted_text("\r\n".join(journals))
 
- if sub_cmd == "query":
- if len(args) < 2:
- return show_text
- prompt = AgentPrompt()
- prompt.messages.append({"role": "user", "content":" ".join(args[1:])})
- result = await KnowledgeBase().query_prompt(prompt)
- print_formatted_text(result.as_str())
-
- async def handle_node_commands(self, args):
- show_text = FormattedText([("class:title", "sub command not support!\n" 
- "/node add llama $model_name $url\n"
- "/node rm llama $model_name $url\n"
- "/node list\n")])
- if len(args) < 1:
- return show_text
- sub_cmd = args[0]
- if sub_cmd == "add":
- if len(args) < 2:
- return show_text
- if args[1] == "llama":
- if len(args) < 4:
- return show_text
-
- model_name = args[2]
- url = args[3]
- ComputeNodeConfig.get_instance().add_node("llama", url, model_name)
- ComputeNodeConfig.get_instance().save()
- node = LocalLlama_ComputeNode(url, model_name)
- node.start()
- ComputeKernel.get_instance().add_compute_node(node)
- else:
- return show_text
- elif sub_cmd == "rm":
- if len(args) < 2:
- return show_text
- if args[1] == "llama":
- if len(args) < 4:
- return show_text
-
- model_name = args[3]
- url = args[4]
- ComputeNodeConfig.get_instance().remove_node("llama", url, model_name)
- ComputeNodeConfig.get_instance().save()
- else:
- return show_text
- elif sub_cmd == "list":
- print_formatted_text(ComputeNodeConfig.get_instance().list())
-
  async def call_func(self,func_name, args):
  match func_name:
  case 'send':
@@ -533,8 +483,6 @@ async def call_func(self,func_name, args):
  format_texts.append(("",f"\n-------------------\n"))
  return FormattedText(format_texts)
  return FormattedText([("class:title", f"chatsession not found")])
- case 'node':
- return await self.handle_node_commands(args)
  case 'exit':
  os._exit(0)
  case 'help':
@@ -637,7 +585,7 @@ def print_welcome_screen():
 \033[1;94m\tGive your Agent a Telegram account :\033[0m /connect $agent_name
 \033[1;94m\tAdd personal files to the AI Knowledge Base. \033[0m
 \t\t1) Copy your file to ~/myai/data 
-\t\t2) /knowledge add dir
+\t\t2) /knowlege add $dir
 \033[1;94m\tSearch your knowledge base :\033[0m /open Mia
 \033[1;94m\tCheck the progress of AI reading personal data :\033[0m /knowledge journal
 \033[1;94m\tOpen AI Bash (For Developer Only):\033[0m /open ai_bash
@@ -717,15 +665,12 @@ async def main():
  '/history $num $offset',
  '/connect $target',
  '/contact $name',
- '/knowledge add dir',
+ '/knowledge add email | dir',
  '/knowledge journal [$topn]', 
  '/set_config $key',
  '/enable $feature',
  '/disable $feature',
  '/list_config',
- '/node add llama $model_name $url',
- '/node rm llama $model_name $url',
- '/node list',
  '/show',
  '/exit',
  '/help'], ignore_case=True)