Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Autobuild notebook minor fix #1049

Merged
merged 4 commits into from
Dec 24, 2023
Merged

Autobuild notebook minor fix #1049

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
57c6c86
Add python version requirement
AdiG1123 Dec 22, 2023
271c157
Add relevant blog link
AdiG1123 Dec 22, 2023
a099e7f
wording and grammar
AdiG1123 Dec 22, 2023
e081a4a
minor wording a grammar issue
AdiG1123 Dec 22, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 12 additions & 12 deletions notebook/agentchat_autobuild.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,10 @@
},
"source": [
"# AutoBuild\n",
"AutoGen offers conversable agents powered by LLM, tool, or human, which can be used to perform tasks collectively via automated chat. This framework allows tool use and human participation through multi-agent conversation.\n",
"AutoGen offers conversable agents powered by LLMs, tools, or humans, which can be used to perform tasks collectively via automated chat. This framework allows tool use and human participation through multi-agent conversation.\n",
"Please find documentation about this feature [here](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat).\n",
"\n",
"In this notebook, we introduce a new class, `AgentBuilder`, to help user build an automatic task solving process powered by multi-agent system. Specifically, in `build()`, we prompt a LLM to create multiple participant agent and initialize a group chat, and specify whether this task need programming to solve. AgentBuilder also support open-source LLMs by [vLLM](https://docs.vllm.ai/en/latest/index.html) and [Fastchat](https://github.com/lm-sys/FastChat). Check the supported model list [here](https://docs.vllm.ai/en/latest/models/supported_models.html)."
"In this notebook, we introduce a new class, `AgentBuilder`, to help users build an automatic task-solving process powered by a multi-agent system. Specifically, in `build()`, we prompt an LLM to create multiple participant agents, initialize a group chat, and specify whether this task need programming to solve. AgentBuilder also supports open-source LLMs by [vLLM](https://docs.vllm.ai/en/latest/index.html) and [Fastchat](https://github.com/lm-sys/FastChat). Check the supported model list [here](https://docs.vllm.ai/en/latest/models/supported_models.html)."
]
},
{
Expand All @@ -23,7 +23,7 @@
"source": [
"## Requirement\n",
"\n",
"AutoBuild need the latest version of AutoGen.\n",
"AutoGen requires `Python>=3.8`. AutoBuild need the latest version of AutoGen.\n",
"You can install AutoGen by the following command:"
]
},
Expand All @@ -47,7 +47,7 @@
},
"source": [
"## Step 1: prepare configuration\n",
"Prepare a `config_path` for assistant agent to limit the choice of LLM you want to use in this task. This config can be a path of json file or a name of environment variable. A `default_llm_config` is also required for initialize the specific config of LLMs like seed, temperature, etc..."
"Prepare a `config_path` for assistant agent to limit the choice of LLM you want to use in this task. This config can be a path to a json file or a name of an environment variable. A `default_llm_config` is also required to initialize the specific configurations of LLMs like seed, temperature, etc..."
]
},
{
Expand Down Expand Up @@ -77,7 +77,7 @@
},
"source": [
"## Step 2: create a AgentBuilder\n",
"Create a `AgentBuilder` with the specified `config_path`. AgentBuilder will use GPT-4 in default to complete the whole process, you can also change the `builder_model` to other OpenAI model if you want. You can also specify a OpenAI or open-source LLM as agent backbone, see blog for more details."
"Create an `AgentBuilder` with the specified `config_path`. AgentBuilder will use GPT-4 in default to complete the whole process, you can also change the `builder_model` to other OpenAI models. You can also specify an OpenAI or open-source LLM as the agent backbone, see [blog](https://microsoft.github.io/autogen/blog/2023/07/14/Local-LLMs/) for more details."
]
},
{
Expand Down Expand Up @@ -107,7 +107,7 @@
"source": [
"## Step 3: specify a building task\n",
"\n",
"Specify a building task with a general description. Building task will help build manager (a LLM) decide what agents should be build."
"Specify a building task with a general description. A building task will help the build manager (an LLM) decide what agents should be built."
]
},
{
Expand Down Expand Up @@ -181,7 +181,7 @@
},
"source": [
"## Step 5: execute task\n",
"Let agents generated in `build()` to complete the task collaboratively in a group chat."
"Let agents generated in `build()` complete the task collaboratively in a group chat."
]
},
{
Expand Down Expand Up @@ -417,7 +417,7 @@
},
"source": [
"## Step 6 (Optional): clear all agents and prepare for the next task\n",
"You can clear all agents generated in this task by the following code if your task is completed or the next task is largely different from the current task. If the agent's backbone is an open-source LLM, this process will also shutdown the endpoint server. If necessary, you can use `recycle_endpoint=False` to retain the previous open-source LLMs' endpoint server."
"You can clear all agents generated in this task with the following code if your task is complete or the next task is significantly different from the current one. If the agent's backbone is an open-source LLM, this process will also shutdown the endpoint server. If necessary, you can use `recycle_endpoint=False` to retain the previous open-source LLMs' endpoint server."
]
},
{
Expand Down Expand Up @@ -453,7 +453,7 @@
"source": [
"## Save & load configs\n",
"\n",
"You can save all necessary information of the built group chat agents. Here is a case for those agents generated in the above task:\n",
"You can save all necessary information of the built group chat agents. The following information is for those agents generated in the above task:\n",
"```json\n",
"{\n",
" \"building_task\": \"Find a paper on arxiv by programming, and analysis its application in some domain. For example, find a latest paper about gpt-4 on arxiv and find its potential applications in software.\",\n",
Expand All @@ -480,7 +480,7 @@
" }\n",
"}\n",
"```\n",
"These information will be saved in JSON format. You can provide a specific filename, otherwise, AgentBuilder will save config to the current path with a generated filename 'save_config_TASK_MD5.json'."
"This information will be saved in JSON format. You can provide a specific filename; otherwise, AgentBuilder will save the config to the current path with a generated filename 'save_config_TASK_MD5.json'."
]
},
{
Expand Down Expand Up @@ -514,7 +514,7 @@
"collapsed": false
},
"source": [
"After that, you can load the saved config and skip the building process. AgentBuilder will create agents with those information without prompting the builder manager."
"After that, you can load the saved config and skip the building process. AgentBuilder will create agents with the config information without prompting the builder manager."
]
},
{
Expand Down Expand Up @@ -874,7 +874,7 @@
"## Use OpenAI Assistant\n",
"\n",
"[The Assistants API](https://platform.openai.com/docs/assistants/overview) allows you to build AI assistants within your own applications. An Assistant has instructions and can leverage models, tools, and knowledge to respond to user queries.\n",
"AutoBuild also support assistant api by adding `use_oai_assistant=True` to `build()`."
"AutoBuild also supports assistants api by adding `use_oai_assistant=True` to `build()`."
]
},
{
Expand Down
Loading