From b137fa033b30a51bb99b1108de83bca6669fda43 Mon Sep 17 00:00:00 2001 From: Li Jiang Date: Fri, 20 Oct 2023 09:25:22 +0800 Subject: [PATCH 1/4] Fix format and links --- website/blog/2023-10-18-RetrieveChat/index.mdx | 1 + website/docs/Examples/AutoGen-AgentChat.md | 1 + website/docs/Installation.md | 3 +++ website/docs/Use-Cases/agent_chat.md | 6 +++--- 4 files changed, 8 insertions(+), 3 deletions(-) diff --git a/website/blog/2023-10-18-RetrieveChat/index.mdx b/website/blog/2023-10-18-RetrieveChat/index.mdx index 74c03d6604d0..a03535c62b91 100644 --- a/website/blog/2023-10-18-RetrieveChat/index.mdx +++ b/website/blog/2023-10-18-RetrieveChat/index.mdx @@ -48,6 +48,7 @@ The conversation terminates if no more documents are available for the context. ## Basic Usage of RAG Agents 0. Install dependencies + Please install pyautogen with the [retrievechat] option before using RAG agents. ```bash pip install "pyautogen[retrievechat]" diff --git a/website/docs/Examples/AutoGen-AgentChat.md b/website/docs/Examples/AutoGen-AgentChat.md index 1360aa9f5d8e..a308275d5cf5 100644 --- a/website/docs/Examples/AutoGen-AgentChat.md +++ b/website/docs/Examples/AutoGen-AgentChat.md @@ -17,3 +17,4 @@ Links to notebook examples: * [Automated Continual Learning from New Data](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_stream.ipynb) * [Teach Agents New Skills & Reuse via Automated Chat](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_teaching.ipynb) * [Automated Code Generation and Question Answering with Retrieval Augemented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat.ipynb) +* [Use Retrieval Augemented Agents in Group Chat (with 5 group member agents and 1 manager agent)](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb) diff --git a/website/docs/Installation.md b/website/docs/Installation.md index ede82dc534d5..d7a0f5d690b2 100644 --- a/website/docs/Installation.md +++ b/website/docs/Installation.md @@ -43,18 +43,21 @@ pip install docker ``` * blendsearch + AutoGen offers a cost-effective hyperparameter optimization technique [EcoOptiGen](https://arxiv.org/abs/2303.04673) for tuning Large Language Models. Please install with the [blendsearch] option to use it. ```bash pip install "pyautogen[blendsearch]" ``` * retrievechat + AutoGen supports retrieval-augmented generation tasks such as question answering and code generation with RAG agents. Please install with the [retrievechat] option to use it. ```bash pip install "pyautogen[retrievechat]" ``` * mathchat + AutoGen offers an experimental agent for math problem solving. Please install with the [mathchat] option to use it. ```bash pip install "pyautogen[mathchat]" diff --git a/website/docs/Use-Cases/agent_chat.md b/website/docs/Use-Cases/agent_chat.md index 38d4ea81bf45..a98080c18209 100644 --- a/website/docs/Use-Cases/agent_chat.md +++ b/website/docs/Use-Cases/agent_chat.md @@ -105,11 +105,11 @@ The figure below shows six examples of applications built using AutoGen. - **Web Search**: Solve Tasks Requiring Web Info - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_web_info.ipynb) - Use Provided Tools as Functions - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_function_call.ipynb) - Task Solving with Langchain Provided Tools as Functions - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_function_call.ipynb) - - **RAG**: Group Chat with Retrieval Augmented Generation - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb) - - In-depth Guide to OpenAI Utility Functions - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb) + - **RAG**: Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent) - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb) + - In-depth Guide to OpenAI Utility Functions - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/oai_openai_utils.ipynb) 5. **Agent Teaching and Learning** - - Teach Agents New Skills & Reuse via Automated Chat - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/oai_openai_utils.ipynb) + - Teach Agents New Skills & Reuse via Automated Chat - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_teaching.ipynb) ## For Further Reading From 6ed32230d7fcd6840960f2e87abc452b6db657ed Mon Sep 17 00:00:00 2001 From: Li Jiang Date: Fri, 20 Oct 2023 09:27:38 +0800 Subject: [PATCH 2/4] Update title --- website/blog/2023-10-18-RetrieveChat/index.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/website/blog/2023-10-18-RetrieveChat/index.mdx b/website/blog/2023-10-18-RetrieveChat/index.mdx index a03535c62b91..71d2ad3f46c0 100644 --- a/website/blog/2023-10-18-RetrieveChat/index.mdx +++ b/website/blog/2023-10-18-RetrieveChat/index.mdx @@ -472,5 +472,5 @@ The online app and the source code are hosted in [HuggingFace](https://huggingfa ## Read More You can check out more example notebooks for RAG use cases: -- [Auto Generated Agent Chat: Using RetrieveChat for Retrieve Augmented Code Generation and Question Answering](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat.ipynb) -- [Auto Generated Agent Chat: Group Chat with Retrieval Augmented Generation](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb) +- [Automated Code Generation and Question Answering with Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat.ipynb) +- [Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent)](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb) From c059567cd7308f02155e36df207a390e456c421f Mon Sep 17 00:00:00 2001 From: Li Jiang Date: Fri, 20 Oct 2023 09:31:25 +0800 Subject: [PATCH 3/4] Sync title --- website/docs/Examples/AutoGen-AgentChat.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/Examples/AutoGen-AgentChat.md b/website/docs/Examples/AutoGen-AgentChat.md index a308275d5cf5..58ad28d3ded2 100644 --- a/website/docs/Examples/AutoGen-AgentChat.md +++ b/website/docs/Examples/AutoGen-AgentChat.md @@ -17,4 +17,4 @@ Links to notebook examples: * [Automated Continual Learning from New Data](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_stream.ipynb) * [Teach Agents New Skills & Reuse via Automated Chat](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_teaching.ipynb) * [Automated Code Generation and Question Answering with Retrieval Augemented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat.ipynb) -* [Use Retrieval Augemented Agents in Group Chat (with 5 group member agents and 1 manager agent)](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb) +* [Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent)](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb) From 326d723044047b7121c26fcae7656048b23ef738 Mon Sep 17 00:00:00 2001 From: Li Jiang Date: Fri, 20 Oct 2023 09:48:44 +0800 Subject: [PATCH 4/4] Add examples to installation --- website/docs/Installation.md | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/website/docs/Installation.md b/website/docs/Installation.md index d7a0f5d690b2..9d064d4abb73 100644 --- a/website/docs/Installation.md +++ b/website/docs/Installation.md @@ -49,6 +49,10 @@ AutoGen offers a cost-effective hyperparameter optimization technique [EcoOptiGe pip install "pyautogen[blendsearch]" ``` +Example notebooks: +[Optimize for Code Generation](https://github.com/microsoft/autogen/blob/main/notebook/oai_completion.ipynb), +[Optimize for Math](https://github.com/microsoft/autogen/blob/main/notebook/oai_chatgpt_gpt4.ipynb) + * retrievechat AutoGen supports retrieval-augmented generation tasks such as question answering and code generation with RAG agents. Please install with the [retrievechat] option to use it. @@ -56,9 +60,16 @@ AutoGen supports retrieval-augmented generation tasks such as question answering pip install "pyautogen[retrievechat]" ``` +Example notebooks: +[Automated Code Generation and Question Answering with Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat.ipynb), +[Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent)](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb) + * mathchat AutoGen offers an experimental agent for math problem solving. Please install with the [mathchat] option to use it. ```bash pip install "pyautogen[mathchat]" ``` + +Example notebooks: +[Using MathChat to Solve Math Problems](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_MathChat.ipynb)