Merge branch 'main' into u/xiaoyun/openai

.github/workflows/build.yml

@@ -40,7 +40,7 @@ jobs:
           python -m pip install --upgrade pip wheel
           pip install -e .
           python -c "import autogen"
-          pip install -e.[mathchat] datasets pytest
+          pip install -e.[mathchat,retrievechat] datasets pytest
           pip uninstall -y openai
       - name: Test with pytest
         if: matrix.python-version != '3.10'

.github/workflows/openai.yml

@@ -73,6 +73,7 @@ jobs:
           OAI_CONFIG_LIST: ${{ secrets.OAI_CONFIG_LIST }}
         run: |
           pip install nbconvert nbformat ipykernel
+          coverage run -a -m pytest test/test_with_openai.py
           coverage run -a -m pytest test/test_notebook.py
           coverage xml
           cat "$(pwd)/test/executed_openai_notebook_output.txt"

.gitignore

@@ -159,3 +159,8 @@ output/
 
 # local config files
 *.config.local
+OAI_CONFIG_LIST
+key_openai.txt
+key_aoai.txt
+base_aoai.txt
+wolfram.txt

OAI_CONFIG_LIST_sample

@@ -0,0 +1,21 @@
+// Please modify the content, remove this comment and rename this file to OAI_CONFIG_LIST to run the sample code.
+[
+    {
+        "model": "gpt-4",
+        "api_key": "<your OpenAI API key here>"
+    },
+    {
+        "model": "gpt-4",
+        "api_key": "<your Azure OpenAI API key here>",
+        "api_base": "<your Azure OpenAI API base here>",
+        "api_type": "azure",
+        "api_version": "2023-07-01-preview"
+    },
+    {
+        "model": "gpt-3.5-turbo",
+        "api_key": "<your Azure OpenAI API key here>",
+        "api_base": "<your Azure OpenAI API base here>",
+        "api_type": "azure",
+        "api_version": "2023-07-01-preview"
+    }
+]

README.md

@@ -2,7 +2,7 @@
 [![PyPI version](https://badge.fury.io/py/pyautogen.svg)](https://badge.fury.io/py/pyautogen)
 [![Build](https://github.com/microsoft/autogen/actions/workflows/python-package.yml/badge.svg)](https://github.com/microsoft/autogen/actions/workflows/python-package.yml)
 ![Python Version](https://img.shields.io/badge/3.8%20%7C%203.9%20%7C%203.10%20%7C%203.11-blue)
-[![](https://img.shields.io/discord/1025786666260111483?logo=discord&style=flat)](https://discord.gg/pAbnFJrkgZ)
+[![](https://img.shields.io/discord/1153072414184452236?logo=discord&style=flat)](https://discord.gg/pAbnFJrkgZ)
 
 This project is a spinoff from [FLAML](https://github.com/microsoft/FLAML).
 
@@ -26,15 +26,15 @@ This project is a spinoff from [FLAML](https://github.com/microsoft/FLAML).
 
 ## What is AutoGen
 
-AutoGen is a framework that enables development of LLM applications using multiple agents that can converse with each other to solve task. AutoGen agents are customizable, conversable, and seamlessly allow human participation. They can operate in various modes that employ combinations of LLMs, human inputs, and tools.
+AutoGen is a framework that enables development of LLM applications using multiple agents that can converse with each other to solve tasks. AutoGen agents are customizable, conversable, and seamlessly allow human participation. They can operate in various modes that employ combinations of LLMs, human inputs, and tools.
 
 ![AutoGen Overview](https://github.com/microsoft/autogen/blob/main/website/static/img/autogen_agentchat.png)
 
-* AutoGen enables building next-gen LLM applications based on **multi-agent conversations** with minimal effort. It simplifies the orchestration, automation and optimization of a complex LLM workflow. It maximizes the performance of LLM models and overcome their weaknesses.
+* AutoGen enables building next-gen LLM applications based on **multi-agent conversations** with minimal effort. It simplifies the orchestration, automation and optimization of a complex LLM workflow. It maximizes the performance of LLM models and overcomes their weaknesses.
 * It supports **diverse conversation patterns** for complex workflows. With customizable and conversable agents, developers can use AutoGen to build a wide range of conversation patterns concerning conversation autonomy,
 the number of agents, and agent conversation topology.
-* It provides a collection of working systems with different complexities. These systems span a **wide range of applications** from various domains and complexities. They demonstrate how AutoGen can easily support different conversation patterns.
-* AutoGen provides a drop-in replacement of `openai.Completion` or `openai.ChatCompletion` as an **enhanced inference API**. It allows easy performance tuning, utilities like API unification & caching, and advanced usage patterns, such as error handling, multi-config inference, context programming etc.
+* It provides a collection of working systems with different complexities. These systems span a **wide range of applications** from various domains and complexities. This demonstrates how AutoGen can easily support diverse conversation patterns.
+* AutoGen provides a drop-in replacement of `openai.Completion` or `openai.ChatCompletion` as an **enhanced inference API**. It allows easy performance tuning, utilities like API unification and caching, and advanced usage patterns, such as error handling, multi-config inference, context programming, etc.
 
 AutoGen is powered by collaborative [research studies](https://microsoft.github.io/autogen/docs/Research) from Microsoft, Penn State University, and University of Washington.
 
@@ -55,22 +55,38 @@ pip install "pyautogen[blendsearch]"
 Find more options in [Installation](https://microsoft.github.io/autogen/docs/Installation).
 <!-- Each of the [`notebook examples`](https://github.com/microsoft/autogen/tree/main/notebook) may require a specific option to be installed. -->
 
+For LLM inference configurations, check the [FAQ](https://microsoft.github.io/autogen/docs/FAQ#set-your-api-endpoints).
+
 ## Quickstart
 
-* Autogen enables the next-gen LLM applications with a generic multi-agent conversation framework. It offers customizable and conversable agents which integrate LLMs, tools and human.
-By automating chat among multiple capable agents, one can easily make them collectively perform tasks autonomously or with human feedback, including tasks that require using tools via code. For example,
+* Autogen enables the next-gen LLM applications with a generic multi-agent conversation framework. It offers customizable and conversable agents which integrate LLMs, tools, and humans.
+By automating chat among multiple capable agents, one can easily make them collectively perform tasks autonomously or with human feedback, including tasks that require using tools via code. For [example](https://github.com/microsoft/autogen/blob/main/test/twoagent.py),
 ```python
-from autogen import AssistantAgent, UserProxyAgent
-assistant = AssistantAgent("assistant")
-user_proxy = UserProxyAgent("user_proxy")
-user_proxy.initiate_chat(assistant, message="Plot a chart of META and TESLA stock price change YTD.")
+from autogen import AssistantAgent, UserProxyAgent, config_list_from_json
+# 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
+config_list = config_list_from_json(env_or_file="OAI_CONFIG_LIST")
+assistant = AssistantAgent("assistant", llm_config={"config_list": config_list})
+user_proxy = UserProxyAgent("user_proxy", code_execution_config={"work_dir": "coding"})
+user_proxy.initiate_chat(assistant, message="Plot a chart of NVDA and TESLA stock price change YTD.")
 # This initiates an automated chat between the two agents to solve the task
 ```
+Multi-agent conversations: AutoGen agents can communicate with each other to solve tasks. This allows for more complex and sophisticated applications than would be possible with a single LLM.
+Customization: AutoGen agents can be customized to meet the specific needs of an application. This includes the ability to choose the LLMs to use, the types of human input to allow, and the tools to employ.
+Human participation: AutoGen seamlessly allows human participation. This means that humans can provide input and feedback to the agents as needed.
 
+This example can be run with
+```python
+python test/twoagent.py
+```
+After the repo is cloned.
 The figure below shows an example conversation flow with AutoGen.
 ![Agent Chat Example](https://github.com/microsoft/autogen/blob/main/website/static/img/chat_example.png)
 
-* Autogen also helps maximize the utility out of the expensive LLMs such as ChatGPT and GPT-4. It offers a drop-in replacement of `openai.Completion` or `openai.ChatCompletion` with powerful functionalites like tuning, caching, error handling, templating. For example, you can optimize generations by LLM with your own tuning data, success metrics and budgets.
+Please find more [code examples](https://microsoft.github.io/autogen/docs/Examples/AutoGen-AgentChat) for this feature.
+
+* Autogen also helps maximize the utility out of the expensive LLMs such as ChatGPT and GPT-4. It offers a drop-in replacement of `openai.Completion` or `openai.ChatCompletion` adding powerful functionalities like tuning, caching, error handling, and templating. For example, you can optimize generations by LLM with your own tuning data, success metrics and budgets.
 ```python
 # perform tuning
 config, analysis = autogen.Completion.tune(
@@ -86,6 +102,8 @@ config, analysis = autogen.Completion.tune(
 response = autogen.Completion.create(context=test_instance, **config)
 ```
 
+Please find more [code examples](https://microsoft.github.io/autogen/docs/Examples/AutoGen-Inference) for this feature.
+
 ## Documentation
 
 You can find a detailed documentation about AutoGen [here](https://microsoft.github.io/autogen/).
@@ -111,7 +129,7 @@ a CLA and decorate the PR appropriately (e.g., status check, comment). Simply fo
 provided by the bot. You will only need to do this once across all repos using our CLA.
 
 This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
-For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
+For more information, see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
 contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.
 
 # Legal Notices
@@ -130,3 +148,38 @@ Privacy information can be found at https://privacy.microsoft.com/en-us/
 
 Microsoft and any contributors reserve all other rights, whether under their respective copyrights, patents,
 or trademarks, whether by implication, estoppel or otherwise.
+
+
+## Citation
+[AutoGen](https://arxiv.org/abs/2308.08155).
+```
+@inproceedings{wu2023autogen,
+      title={AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework},
+      author={Qingyun Wu and Gagan Bansal and Jieyu Zhang and Yiran Wu and Shaokun Zhang and Erkang Zhu and Beibin Li and Li Jiang and Xiaoyun Zhang and Chi Wang},
+      year={2023},
+      eprint={2308.08155},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI}
+}
+```
+
+[EcoOptiGen](https://arxiv.org/abs/2303.04673).
+```
+@inproceedings{wang2023EcoOptiGen,
+    title={Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference},
+    author={Chi Wang and Susan Xueqing Liu and Ahmed H. Awadallah},
+    year={2023},
+    booktitle={AutoML'23},
+}
+```
+
+[MathChat](https://arxiv.org/abs/2306.01337).
+
+```
+@inproceedings{wu2023empirical,
+    title={An Empirical Study on Challenging Math Problem Solving with GPT-4},
+    author={Yiran Wu and Feiran Jia and Shaokun Zhang and Hangyu Li and Erkang Zhu and Yue Wang and Yin Tat Lee and Richard Peng and Qingyun Wu and Chi Wang},
+    year={2023},
+    booktitle={ArXiv preprint arXiv:2306.01337},
+}
+```

autogen/agentchat/assistant_agent.py

@@ -16,7 +16,7 @@ class AssistantAgent(ConversableAgent):
     DEFAULT_SYSTEM_MESSAGE = """You are a helpful AI assistant.
 Solve tasks using your coding and language skills.
 In the following cases, suggest python code (in a python coding block) or shell script (in a sh coding block) for the user to execute.
-    1. When you need to collect info, use the code to output the info you need, for example, browse or search the web, download/read a file, print the content of a webpage or a file, get the current date/time. After sufficient info is printed and the task is ready to be solved based on your language skill, you can solve the task by yourself.
+    1. When you need to collect info, use the code to output the info you need, for example, browse or search the web, download/read a file, print the content of a webpage or a file, get the current date/time, check the operating system. After sufficient info is printed and the task is ready to be solved based on your language skill, you can solve the task by yourself.
     2. When you need to perform some task with code, use the code to perform the task and output the result. Finish the task smartly.
 Solve the task step by step if you need to. If a plan is not provided, explain your plan first. Be clear which step uses code, and which step uses your language skill.
 When using code, you must indicate the script type in the code block. The user cannot provide any other feedback or perform any other action beyond executing the code you suggest. The user can't modify your code. So do not suggest incomplete code which requires users to modify. Don't use a code block if it's not intended to be executed by the user.