Skip to content

A programming framework for agentic AI

improve ecosystem page (#823)

Qingyun Wu77e1d28c1bc2
diff --git a/CITATION.cff b/CITATION.cff
index 0ff9976aa..cbf8fe885 100644
--- a/CITATION.cff
+++ b/CITATION.cff
@@ -13,21 +13,24 @@ preferred-citation:
- family-names: "Wu"
given-names: "Yiran"
affiliation: "Penn State University, University Park PA USA"
- - family-names: "Zhang"
- given-names: "Shaokun"
- affiliation: "Penn State University, University Park PA USA"
- - family-names: "Zhu"
- given-names: "Eric"
- affiliation: "Microsoft Research, Redmond WA USA"
- family-names: "Li"
given-names: "Beibin"
affiliation: "Microsoft Research, Redmond WA USA"
+ - family-names: "Zhu"
+ given-names: "Eric"
+ affiliation: "Microsoft Research, Redmond WA USA"
- family-names: "Jiang"
given-names: "Li"
affiliation: "Microsoft Corporation"
+ - family-names: "Zhang"
+ given-names: "Shaokun"
+ affiliation: "Penn State University, University Park PA USA"
- family-names: "Zhang"
given-names: "Xiaoyun"
affiliation: "Microsoft Corporation, Redmond WA USA"
+ - family-names: "Liu"
+ given-names: "Jiale"
+ affiliation: "Xidian University, Xi'an China"
- family-names: "Awadallah"
given-names: "Ahmed Hassan"
affiliation: "Microsoft Research, Redmond WA USA"
diff --git a/website/docs/Ecosystem.md b/website/docs/Ecosystem.md
index 8b2474998..c85ecaa0f 100644
--- a/website/docs/Ecosystem.md
+++ b/website/docs/Ecosystem.md
@@ -3,9 +3,11 @@
This page lists libraries that have integrations with Autogen for LLM applications using multiple agents in alphabetical order. Including your own integration to this list is highly encouraged. Simply open a pull request with a few lines of text, see the dropdown below for more information.
-## [MemGPT + AutoGen](https://memgpt.readthedocs.io/en/latest/autogen/)
+## MemGPT + AutoGen
![Agent Chat Example](img/ecosystem-memgpt.png)
MemGPT enables LLMs to manage their own memory and overcome limited context windows. You can use MemGPT to create perpetual chatbots that learn about you and modify their own personalities over time. You can connect MemGPT to your own local filesystems and databases, as well as connect MemGPT to your own tools and APIs. The MemGPT + AutoGen integration allows you to equip any AutoGen agent with MemGPT capabilities.
+
+- [MemGPT + AutoGen documentation with code examples](https://memgpt.readthedocs.io/en/latest/autogen/)
diff --git a/website/docs/Examples.md b/website/docs/Examples.md
index b338e533f..b5596afc6 100644
--- a/website/docs/Examples.md
+++ b/website/docs/Examples.md
@@ -1,7 +1,6 @@
# Examples
-
-## Automated Multi Agent Chat
+### Automated Multi Agent Chat
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 via multi-agent conversation.
Please find documentation about this feature [here](/docs/Use-Cases/agent_chat).
@@ -58,7 +57,7 @@ Links to notebook examples:
- Multimodal Agent Chat with GPT-4V - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_lmm_gpt-4v.ipynb)
-## Tune GPT Models
+## Tune Inference Hyperparameters
AutoGen also offers a cost-effective hyperparameter optimization technique [EcoOptiGen](https://arxiv.org/abs/2303.04673) for tuning Large Language Models. The research study finds that tuning hyperparameters can significantly improve the utility of them.
Please find documentation about this feature [here](/docs/Use-Cases/enhanced_inference).
diff --git a/website/docs/Use-Cases/agent_chat.md b/website/docs/Use-Cases/agent_chat.md
index 56725d954..46b9f5bad 100644
--- a/website/docs/Use-Cases/agent_chat.md
+++ b/website/docs/Use-Cases/agent_chat.md
@@ -81,51 +81,7 @@ By adopting the conversation-driven control with both programming language and n
The figure below shows six examples of applications built using AutoGen.
![Applications](images/app.png)
-1. **Code Generation, Execution, and Debugging**
-
- - Automated Task Solving with Code Generation, Execution & Debugging - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_auto_feedback_from_code_execution.ipynb)
- - Auto Code Generation, Execution, Debugging and Human Feedback - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_human_feedback.ipynb)
- - Automated Code Generation and Question Answering with Retrieval Augmented Agents - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat.ipynb)
-
-2. **Multi-Agent Collaboration (>3 Agents)**
-
- - Automated Task Solving with GPT-4 + Multiple Human Users - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_two_users.ipynb)
- - Automated Task Solving by Group Chat (with 3 group member agents and 1 manager agent) - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat.ipynb)
- - Automated Data Visualization by Group Chat (with 3 group member agents and 1 manager agent) - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_vis.ipynb)
- - Automated Complex Task Solving by Group Chat (with 6 group member agents and 1 manager agent) - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_research.ipynb)
- - Automated Task Solving with Coding & Planning Agents - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_planning.ipynb)
- - Automated Task Solving with agents divided into 2 groups - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_hierarchy_flow_using_select_speaker.ipynb)
- - Automated Task Solving with transition paths specified in a graph - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_graph_modelling_language_using_select_speaker.ipynb)
-
-3. **Applications**
-
- - Automated Chess Game Playing & Chitchatting by GPT-4 Agents - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_chess.ipynb)
- - Automated Continual Learning from New Data - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_stream.ipynb)
- - [OptiGuide](https://github.com/microsoft/optiguide) - Coding, Tool Using, Safeguarding & Question Anwering for Supply Chain Optimization
-
-4. **Tool Use**
-
- - **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_langchain.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/agentchat_teaching.ipynb)
- - Teach Agents New Facts, User Preferences and Skills Beyond Coding - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_teachability.ipynb)
-
-6. **Multi-Agent Chat with OpenAI Assistants in the loop**
- - Hello-World Chat with OpenAi Assistant in AutoGen - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_twoagents_basic.ipynb)
- - Chat with OpenAI Assistant using Function Call - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_function_call.ipynb)
- - Chat with OpenAI Assistant with Code Interpreter - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_code_interpreter.ipynb)
- - Chat with OpenAI Assistant with Retrieval Augmentation - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_retrieval.ipynb)
- - OpenAI Assistant in a Group Chat - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_groupchat.ipynb)
-
-7. **Multimodal Agent**
- - Multimodal Agent Chat with DALLE and GPT-4V - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_dalle_and_gpt4v.ipynb)
- - Multimodal Agent Chat with Llava - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_lmm_llava.ipynb)
- - Multimodal Agent Chat with GPT-4V - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_lmm_gpt-4v.ipynb)
+Find a list of examples in this page: [Automated Agent Chat Examples](../Examples.md#automated-multi-agent-chat)
## For Further Reading
diff --git a/website/docs/Use-Cases/enhanced_inference.md b/website/docs/Use-Cases/enhanced_inference.md
index 855168e99..27dffb7d7 100644
--- a/website/docs/Use-Cases/enhanced_inference.md
+++ b/website/docs/Use-Cases/enhanced_inference.md
@@ -6,9 +6,7 @@ There are a number of benefits of using `autogen` to perform inference: performa
## Tune Inference Parameters (for openai<1)
-*Links to notebook examples:*
-* [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)
+Find a list of examples in this page: [Tune Inference Parameters Examples](../Examples.md#tune-inference-hyperparameters)
### Choices to optimize