Merge branch 'main' into sfblog

.github/workflows/dotnet-release.yml

@@ -0,0 +1,69 @@
+# This workflow will build a .NET project
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-net
+
+name: dotnet-release
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - dotnet/release
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+  packages: write
+
+jobs:
+  build:
+    name: Build and release
+    runs-on: ubuntu-latest
+    environment: dotnet
+    defaults:
+      run:
+        working-directory: dotnet
+    steps:
+    - uses: actions/checkout@v3
+    - name: Setup .NET
+      uses: actions/setup-dotnet@v3
+      with:
+        global-json-file: dotnet/global.json
+    - name: Restore dependencies
+      run: |
+        dotnet restore -bl
+    - name: Build
+      run: |
+        echo "Build AutoGen"
+        dotnet build --no-restore --configuration Release -bl /p:SignAssembly=true
+    - name: Unit Test
+      run: dotnet test --no-build -bl --configuration Release
+      env:
+        AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+        AZURE_OPENAI_ENDPOINT: ${{ secrets.AZURE_OPENAI_ENDPOINT }}
+        AZURE_GPT_35_MODEL_ID: ${{ secrets.AZURE_GPT_35_MODEL_ID }}
+        OEPNAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+    - name: Pack
+      run: |
+        echo "Create release build package"
+        dotnet pack --no-build --configuration Release --output './output/release' -bl
+
+        echo "ls output directory"
+        ls -R ./output
+    - name: Publish package to Nuget
+      run: |
+        echo "Publish package to Nuget"
+        echo "ls output directory"
+        ls -R ./output/release
+        dotnet nuget push --api-key AzureArtifacts ./output/release/*.nupkg --skip-duplicate --api-key ${{ secrets.AUTOGEN_NUGET_API_KEY }}
+    - name: Tag commit
+      run: |
+        Write-Host "Tag commit"
+        # version = eng/MetaInfo.props.Project.PropertyGroup.VersionPrefix
+        $metaInfoContent = cat ./eng/MetaInfo.props
+        $version = $metaInfoContent | Select-String -Pattern "<VersionPrefix>(.*)</VersionPrefix>" | ForEach-Object { $_.Matches.Groups[1].Value }
+        git tag -a "$version" -m "AutoGen.Net release $version"
+        git push origin --tags
+      shell: pwsh

.github/workflows/type-check.yml

@@ -19,4 +19,7 @@ jobs:
       - uses: actions/setup-python@v4
       - run: pip install ".[jupyter-executor]" mypy
       # As more modules are type check clean, add them here
-      - run: mypy --install-types --non-interactive autogen/logger
+      - run: |
+          mypy --install-types --non-interactive \
+            autogen/logger \
+            autogen/exception_utils.py

.gitignore

@@ -178,5 +178,7 @@ test/agentchat/test_agent_scripts/*
 
 # test cache
 .cache_test
+.db
+
 
 notebook/result.png

autogen/agentchat/conversable_agent.py

@@ -130,6 +130,12 @@ def __init__(
             description (str): a short description of the agent. This description is used by other agents
                 (e.g. the GroupChatManager) to decide when to call upon this agent. (Default: system_message)
         """
+        # we change code_execution_config below and we have to make sure we don't change the input
+        # in case of UserProxyAgent, without this we could even change the default value {}
+        code_execution_config = (
+            code_execution_config.copy() if hasattr(code_execution_config, "copy") else code_execution_config
+        )
+
         self._name = name
         # a dictionary of conversations, default value is list
         self._oai_messages = defaultdict(list)

autogen/agentchat/user_proxy_agent.py

@@ -30,7 +30,7 @@ def __init__(
         max_consecutive_auto_reply: Optional[int] = None,
         human_input_mode: Literal["ALWAYS", "TERMINATE", "NEVER"] = "ALWAYS",
         function_map: Optional[Dict[str, Callable]] = None,
-        code_execution_config: Optional[Union[Dict, Literal[False]]] = None,
+        code_execution_config: Union[Dict, Literal[False]] = {},
         default_auto_reply: Optional[Union[str, Dict, None]] = "",
         llm_config: Optional[Union[Dict, Literal[False]]] = False,
         system_message: Optional[Union[str, List]] = "",

autogen/coding/local_commandline_code_executor.py

@@ -136,7 +136,8 @@ def execute_code_blocks(self, code_blocks: List[CodeBlock]) -> CommandLineCodeRe
                 filename = f"tmp_code_{code_hash}.{'py' if lang.startswith('python') else lang}"
 
             written_file = (self._work_dir / filename).resolve()
-            written_file.open("w", encoding="utf-8").write(code)
+            with written_file.open("w", encoding="utf-8") as f:
+                f.write(code)
             file_names.append(written_file)
 
             program = sys.executable if lang.startswith("python") else _cmd(lang)

autogen/exception_utils.py

@@ -1,20 +1,23 @@
+from typing import Any
+
+
 class AgentNameConflict(Exception):
-    def __init__(self, msg="Found multiple agents with the same name.", *args, **kwargs):
+    def __init__(self, msg: str = "Found multiple agents with the same name.", *args: Any, **kwargs: Any):
         super().__init__(msg, *args, **kwargs)
 
 
 class NoEligibleSpeaker(Exception):
     """Exception raised for early termination of a GroupChat."""
 
-    def __init__(self, message="No eligible speakers."):
+    def __init__(self, message: str = "No eligible speakers."):
         self.message = message
         super().__init__(self.message)
 
 
 class SenderRequired(Exception):
     """Exception raised when the sender is required but not provided."""
 
-    def __init__(self, message="Sender is required but not provided."):
+    def __init__(self, message: str = "Sender is required but not provided."):
         self.message = message
         super().__init__(self.message)
 
@@ -23,7 +26,7 @@ class InvalidCarryOverType(Exception):
     """Exception raised when the carryover type is invalid."""
 
     def __init__(
-        self, message="Carryover should be a string or a list of strings. Not adding carryover to the message."
+        self, message: str = "Carryover should be a string or a list of strings. Not adding carryover to the message."
     ):
         self.message = message
         super().__init__(self.message)
@@ -32,6 +35,6 @@ def __init__(
 class UndefinedNextAgent(Exception):
     """Exception raised when the provided next agents list does not overlap with agents in the group."""
 
-    def __init__(self, message="The provided agents list does not overlap with agents in the group."):
+    def __init__(self, message: str = "The provided agents list does not overlap with agents in the group."):
         self.message = message
         super().__init__(self.message)

notebook/agentchat_RetrieveChat.ipynb

@@ -92,7 +92,7 @@
     "\n",
     "## Construct agents for RetrieveChat\n",
     "\n",
-    "We start by initializing the `RetrieveAssistantAgent` and `RetrieveUserProxyAgent`. The system message needs to be set to \"You are a helpful assistant.\" for RetrieveAssistantAgent. The detailed instructions are given in the user message. Later we will use the `RetrieveUserProxyAgent.generate_init_prompt` to combine the instructions and a retrieval augmented generation task for an initial prompt to be sent to the LLM assistant."
+    "We start by initializing the `RetrieveAssistantAgent` and `RetrieveUserProxyAgent`. The system message needs to be set to \"You are a helpful assistant.\" for RetrieveAssistantAgent. The detailed instructions are given in the user message. Later we will use the `RetrieveUserProxyAgent.message_generator` to combine the instructions and a retrieval augmented generation task for an initial prompt to be sent to the LLM assistant."
    ]
   },
   {
@@ -3037,7 +3037,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.13"
   },
   "skip_test": "Requires interactive usage"
  },

samples/apps/autogen-studio/autogenstudio/datamodel.py

@@ -93,6 +93,7 @@ class LLMConfig:
     cache_seed: Optional[Union[int, None]] = None
     timeout: Optional[int] = None
     max_tokens: Optional[int] = None
+    extra_body: Optional[dict] = None
 
     def dict(self):
         result = asdict(self)

test/agentchat/test_agent_setup_with_use_docker_settings.py

@@ -16,17 +16,6 @@
     skip = False or skip_openai
 
 
-def get_current_autogen_env_var():
-    return os.environ.get("AUTOGEN_USE_DOCKER", None)
-
-
-def restore_autogen_env_var(current_env_value):
-    if current_env_value is None:
-        del os.environ["AUTOGEN_USE_DOCKER"]
-    else:
-        os.environ["AUTOGEN_USE_DOCKER"] = current_env_value
-
-
 def docker_running():
     return is_docker_running() or in_docker_container()
 
@@ -54,32 +43,36 @@ def test_agent_setup_with_use_docker_false():
 
 
 @pytest.mark.skipif(skip, reason="openai not installed")
-def test_agent_setup_with_env_variable_false_and_docker_running():
-    current_env_value = get_current_autogen_env_var()
+def test_agent_setup_with_env_variable_false_and_docker_running(monkeypatch):
+    monkeypatch.setenv("AUTOGEN_USE_DOCKER", "False")
 
-    os.environ["AUTOGEN_USE_DOCKER"] = "False"
     user_proxy = UserProxyAgent(
         name="test_agent",
         human_input_mode="NEVER",
     )
 
     assert user_proxy._code_execution_config["use_docker"] is False
 
-    restore_autogen_env_var(current_env_value)
-
 
 @pytest.mark.skipif(skip or (not docker_running()), reason="openai not installed OR docker not running")
-def test_agent_setup_with_default_and_docker_running():
+def test_agent_setup_with_default_and_docker_running(monkeypatch):
+    monkeypatch.delenv("AUTOGEN_USE_DOCKER", raising=False)
+
+    assert os.getenv("AUTOGEN_USE_DOCKER") is None
+
     user_proxy = UserProxyAgent(
         name="test_agent",
         human_input_mode="NEVER",
     )
 
+    assert os.getenv("AUTOGEN_USE_DOCKER") is None
+
     assert user_proxy._code_execution_config["use_docker"] is True
 
 
 @pytest.mark.skipif(skip or (docker_running()), reason="openai not installed OR docker running")
-def test_raises_error_agent_setup_with_default_and_docker_not_running():
+def test_raises_error_agent_setup_with_default_and_docker_not_running(monkeypatch):
+    monkeypatch.delenv("AUTOGEN_USE_DOCKER", raising=False)
     with pytest.raises(RuntimeError):
         UserProxyAgent(
             name="test_agent",
@@ -88,31 +81,23 @@ def test_raises_error_agent_setup_with_default_and_docker_not_running():
 
 
 @pytest.mark.skipif(skip or (docker_running()), reason="openai not installed OR docker running")
-def test_raises_error_agent_setup_with_env_variable_true_and_docker_not_running():
-    current_env_value = get_current_autogen_env_var()
-
-    os.environ["AUTOGEN_USE_DOCKER"] = "True"
+def test_raises_error_agent_setup_with_env_variable_true_and_docker_not_running(monkeypatch):
+    monkeypatch.setenv("AUTOGEN_USE_DOCKER", "True")
 
     with pytest.raises(RuntimeError):
         UserProxyAgent(
             name="test_agent",
             human_input_mode="NEVER",
         )
 
-    restore_autogen_env_var(current_env_value)
-
 
 @pytest.mark.skipif(skip or (not docker_running()), reason="openai not installed OR docker not running")
-def test_agent_setup_with_env_variable_true_and_docker_running():
-    current_env_value = get_current_autogen_env_var()
-
-    os.environ["AUTOGEN_USE_DOCKER"] = "True"
+def test_agent_setup_with_env_variable_true_and_docker_running(monkeypatch):
+    monkeypatch.setenv("AUTOGEN_USE_DOCKER", "True")
 
     user_proxy = UserProxyAgent(
         name="test_agent",
         human_input_mode="NEVER",
     )
 
     assert user_proxy._code_execution_config["use_docker"] is True
-
-    restore_autogen_env_var(current_env_value)

website/README.md

@@ -23,9 +23,9 @@ yarn install
 
 `quarto` is used to render notebooks.
 
-Install it [here](https://quarto.org/docs/get-started/).
+Install it [here](https://github.com/quarto-dev/quarto-cli/releases).
 
-> Note: Support for Docusaurus 3.0 in Quarto is from version `1.4`. Ensure that your `quarto` version is `1.4` or higher.
+> Note: Ensure that your `quarto` version is `1.5.23` or higher.
 
 ## Local Development
 

website/docs/topics/retrieval_augmentation.md

@@ -0,0 +1,68 @@
+# Retrieval Augmentation
+
+Retrieval Augmented Generation (RAG) is a powerful technique that combines language models with external knowledge retrieval to improve the quality and relevance of generated responses.
+
+One way to realize RAG in AutoGen is to construct agent chats with `RetrieveAssistantAgent` and `RetrieveUserProxyAgent` classes.
+
+## Example Setup: RAG with Retrieval Augmented Agents
+The following is an example setup demonstrating how to create retrieval augmented agents in AutoGen:
+
+### Step 1. Create an instance of `RetrieveAssistantAgent` and `RetrieveUserProxyAgent`.
+
+Here `RetrieveUserProxyAgent` instance acts as a proxy agent that retrieves relevant information based on the user's input.
+```python
+assistant = RetrieveAssistantAgent(
+    name="assistant",
+    system_message="You are a helpful assistant.",
+    llm_config={
+        "timeout": 600,
+        "cache_seed": 42,
+        "config_list": config_list,
+    },
+)
+ragproxyagent = RetrieveUserProxyAgent(
+    name="ragproxyagent",
+    human_input_mode="NEVER",
+    max_consecutive_auto_reply=3,
+    retrieve_config={
+        "task": "code",
+        "docs_path": [
+            "https://raw.githubusercontent.com/microsoft/FLAML/main/website/docs/Examples/Integrate%20-%20Spark.md",
+            "https://raw.githubusercontent.com/microsoft/FLAML/main/website/docs/Research.md",
+            os.path.join(os.path.abspath(""), "..", "website", "docs"),
+        ],
+        "custom_text_types": ["mdx"],
+        "chunk_token_size": 2000,
+        "model": config_list[0]["model"],
+        "client": chromadb.PersistentClient(path="/tmp/chromadb"),
+        "embedding_model": "all-mpnet-base-v2",
+        "get_or_create": True,  # set to False if you don't want to reuse an existing collection, but you'll need to remove the collection manually
+    },
+    code_execution_config=False,  # set to False if you don't want to execute the code
+)
+```
+
+### Step 2. Initiating Agent Chat with Retrieval Augmentation
+
+Once the retrieval augmented agents are set up, you can initiate a chat with retrieval augmentation using the following code:
+
+```python
+code_problem = "How can I use FLAML to perform a classification task and use spark to do parallel training. Train 30 seconds and force cancel jobs if time limit is reached."
+ragproxyagent.initiate_chat(
+    assistant, message=ragproxyagent.message_generator, problem=code_problem, search_string="spark"
+)  # search_string is used as an extra filter for the embeddings search, in this case, we only want to search documents that contain "spark".
+```
+
+## Online Demo
+[Retrival-Augmented Chat Demo on Huggingface](https://huggingface.co/spaces/thinkall/autogen-demos)
+
+## More Examples and Notebooks
+For more detailed examples and notebooks showcasing the usage of retrieval augmented agents in AutoGen, refer to the following:
+- Automated Code Generation and Question Answering with Retrieval Augmented Agents - [View Notebook](/docs/notebooks/agentchat_RetrieveChat)
+- Automated Code Generation and Question Answering with [Qdrant](https://qdrant.tech/) based Retrieval Augmented Agents - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_qdrant_RetrieveChat.ipynb)
+- Chat with OpenAI Assistant with Retrieval Augmentation - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_oai_assistant_retrieval.ipynb)
+- **RAG**: Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent) - [View Notebook](/docs/notebooks/agentchat_groupchat_RAG)
+
+## Roadmap
+
+Explore our detailed roadmap [here](https://github.com/microsoft/autogen/issues/1657) for further advancements plan around RAG. Your contributions, feedback, and use cases are highly appreciated! We invite you to engage with us and play a pivotal role in the development of this impactful feature.