Merge branch 'microsoft:main' into main

.github/workflows/contrib-tests.yml

@@ -9,6 +9,8 @@ on:
     paths:
       - "autogen/**"
       - "test/agentchat/contrib/**"
+      - "test/test_browser_utils.py"
+      - "test/test_retrieve_utils.py"
       - ".github/workflows/contrib-tests.yml"
       - "setup.py"
 
@@ -598,3 +600,79 @@ jobs:
         with:
           file: ./coverage.xml
           flags: unittests
+
+  GroqTest:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-2019]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        exclude:
+          - os: macos-latest
+            python-version: "3.9"
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          lfs: true
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install packages and dependencies for all tests
+        run: |
+          python -m pip install --upgrade pip wheel
+          pip install pytest-cov>=5
+      - name: Install packages and dependencies for Groq
+        run: |
+          pip install -e .[groq,test]
+      - name: Set AUTOGEN_USE_DOCKER based on OS
+        shell: bash
+        run: |
+          if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
+            echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
+          fi
+      - name: Coverage
+        run: |
+          pytest test/oai/test_groq.py --skip-openai
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v3
+        with:
+          file: ./coverage.xml
+          flags: unittests
+
+  CohereTest:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          lfs: true
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install packages and dependencies for all tests
+        run: |
+          python -m pip install --upgrade pip wheel
+          pip install pytest-cov>=5
+      - name: Install packages and dependencies for Cohere
+        run: |
+          pip install -e .[cohere,test]
+      - name: Set AUTOGEN_USE_DOCKER based on OS
+        shell: bash
+        run: |
+          if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
+            echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
+          fi
+      - name: Coverage
+        run: |
+          pytest test/oai/test_cohere.py --skip-openai
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v3
+        with:
+          file: ./coverage.xml
+          flags: unittests

.github/workflows/dotnet-build.yml

@@ -56,11 +56,16 @@ jobs:
     - name: Setup .NET
       uses: actions/setup-dotnet@v4
       with:
-        global-json-file: dotnet/global.json
+        dotnet-version: '8.0.x'
     - name: Restore dependencies
       run: |
         # dotnet nuget add source --name dotnet-tool https://pkgs.dev.azure.com/dnceng/public/_packaging/dotnet-tools/nuget/v3/index.json --configfile NuGet.config
         dotnet restore -bl
+    - name: Format check
+      run: |
+        echo "Format check"
+        echo "If you see any error in this step, please run 'dotnet format' locally to format the code."
+        dotnet format --verify-no-changes -v diag --no-restore
     - name: Build
       run: |
         echo "Build AutoGen"

.github/workflows/dotnet-release.yml

@@ -32,7 +32,7 @@ jobs:
     - name: Setup .NET
       uses: actions/setup-dotnet@v4
       with:
-        global-json-file: dotnet/global.json
+        dotnet-version: '8.0.x'
     - name: Restore dependencies
       run: |
         dotnet restore -bl

README.md

@@ -66,7 +66,12 @@
 
 ## What is AutoGen
 
-AutoGen is a framework that enables the 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 is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. AutoGen aims to streamline the development and research of agentic AI, much like PyTorch does for Deep Learning. It offers features such as agents capable of interacting with each other, facilitates the use of various large language models (LLMs) and tool use support, autonomous and human-in-the-loop workflows, and multi-agent conversation patterns.
+
+**Open Source Statement**: The project welcomes contributions from developers and organizations worldwide. Our goal is to foster a collaborative and inclusive community where diverse perspectives and expertise can drive innovation and enhance the project's capabilities. Whether you are an individual contributor or represent an organization, we invite you to join us in shaping the future of this project. Together, we can build something truly remarkable.
+
+The project is currently maintained by a [dynamic group of volunteers](https://butternut-swordtail-8a5.notion.site/410675be605442d3ada9a42eb4dfef30?v=fa5d0a79fd3d4c0f9c112951b2831cbb&pvs=4) from several different organizations. Contact project administrators Chi Wang and Qingyun Wu via [email protected] if you are interested in becoming a maintainer.
+
 
 ![AutoGen Overview](https://github.com/microsoft/autogen/blob/main/website/static/img/autogen_agentchat.png)
 
@@ -288,6 +293,16 @@ In addition, you can find:
 }
 ```
 
+[StateFlow](https://arxiv.org/abs/2403.11322)
+```
+@article{wu2024stateflow,
+  title={StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows},
+  author={Wu, Yiran and Yue, Tianwei and Zhang, Shaokun and Wang, Chi and Wu, Qingyun},
+  journal={arXiv preprint arXiv:2403.11322},
+  year={2024}
+}
+```
+
 <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
   <a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
     ↑ Back to Top ↑

autogen/agentchat/contrib/agent_eval/README.md

@@ -1,7 +1,9 @@
-Agents for running the AgentEval pipeline.
+Agents for running the [AgentEval](https://microsoft.github.io/autogen/blog/2023/11/20/AgentEval/) pipeline.
 
 AgentEval is a process for evaluating a LLM-based system's performance on a given task.
 
 When given a task to evaluate and a few example runs, the critic and subcritic agents create evaluation criteria for evaluating a system's solution. Once the criteria has been created, the quantifier agent can evaluate subsequent task solutions based on the generated criteria.
 
 For more information see: [AgentEval Integration Roadmap](https://github.com/microsoft/autogen/issues/2162)
+
+See our [blog post](https://microsoft.github.io/autogen/blog/2024/06/21/AgentEval) for usage examples and general explanations.

autogen/agentchat/contrib/llamaindex_conversable_agent.py

@@ -8,15 +8,14 @@
 
 try:
     from llama_index.core.agent.runner.base import AgentRunner
+    from llama_index.core.base.llms.types import ChatMessage
     from llama_index.core.chat_engine.types import AgentChatResponse
-    from llama_index_client import ChatMessage
 except ImportError as e:
     logger.fatal("Failed to import llama-index. Try running 'pip install llama-index'")
     raise e
 
 
 class LLamaIndexConversableAgent(ConversableAgent):
-
     def __init__(
         self,
         name: str,

autogen/agentchat/contrib/retrieve_user_proxy_agent.py

@@ -1,6 +1,7 @@
 import hashlib
 import os
 import re
+import uuid
 from typing import Any, Callable, Dict, List, Literal, Optional, Tuple, Union
 
 from IPython import get_ipython
@@ -135,7 +136,7 @@ def __init__(
                 - `client` (Optional, chromadb.Client) - the chromadb client. If key not provided, a
                      default client `chromadb.Client()` will be used. If you want to use other
                      vector db, extend this class and override the `retrieve_docs` function.
-                     **Deprecated**: use `vector_db` instead.
+                     *[Deprecated]* use `vector_db` instead.
                 - `docs_path` (Optional, Union[str, List[str]]) - the path to the docs directory. It
                      can also be the path to a single file, the url to a single file or a list
                      of directories, files and urls. Default is None, which works only if the
@@ -149,7 +150,7 @@ def __init__(
                     By default, "extra_docs" is set to false, starting document IDs from zero.
                     This poses a risk as new documents might overwrite existing ones, potentially
                     causing unintended loss or alteration of data in the collection.
-                    **Deprecated**: use `new_docs` when use `vector_db` instead of `client`.
+                    *[Deprecated]* use `new_docs` when use `vector_db` instead of `client`.
                 - `new_docs` (Optional, bool) - when True, only adds new documents to the collection;
                     when False, updates existing documents and adds new ones. Default is True.
                     Document id is used to determine if a document is new or existing. By default, the
@@ -172,7 +173,7 @@ def __init__(
                     models can be found at `https://www.sbert.net/docs/pretrained_models.html`.
                     The default model is a fast model. If you want to use a high performance model,
                     `all-mpnet-base-v2` is recommended.
-                    **Deprecated**: no need when use `vector_db` instead of `client`.
+                    *[Deprecated]* no need when use `vector_db` instead of `client`.
                 - `embedding_function` (Optional, Callable) - the embedding function for creating the
                     vector db. Default is None, SentenceTransformer with the given `embedding_model`
                     will be used. If you want to use OpenAI, Cohere, HuggingFace or other embedding
@@ -219,7 +220,7 @@ def __init__(
 
         Example of overriding retrieve_docs - If you have set up a customized vector db, and it's
         not compatible with chromadb, you can easily plug in it with below code.
-        **Deprecated**: Use `vector_db` instead. You can extend VectorDB and pass it to the agent.
+        *[Deprecated]* use `vector_db` instead. You can extend VectorDB and pass it to the agent.
         ```python
         class MyRetrieveUserProxyAgent(RetrieveUserProxyAgent):
             def query_vector_db(
@@ -365,7 +366,11 @@ def _init_db(self):
             else:
                 all_docs_ids = set()
 
-            chunk_ids = [hashlib.blake2b(chunk.encode("utf-8")).hexdigest()[:HASH_LENGTH] for chunk in chunks]
+            chunk_ids = (
+                [hashlib.blake2b(chunk.encode("utf-8")).hexdigest()[:HASH_LENGTH] for chunk in chunks]
+                if not self._vector_db.type == "qdrant"
+                else [str(uuid.UUID(hex=hashlib.md5(chunk.encode("utf-8")).hexdigest())) for chunk in chunks]
+            )
             chunk_ids_set = set(chunk_ids)
             chunk_ids_set_idx = [chunk_ids.index(hash_value) for hash_value in chunk_ids_set]
             docs = [

autogen/agentchat/contrib/vectordb/base.py

@@ -1,4 +1,16 @@
-from typing import Any, List, Mapping, Optional, Protocol, Sequence, Tuple, TypedDict, Union, runtime_checkable
+from typing import (
+    Any,
+    Callable,
+    List,
+    Mapping,
+    Optional,
+    Protocol,
+    Sequence,
+    Tuple,
+    TypedDict,
+    Union,
+    runtime_checkable,
+)
 
 Metadata = Union[Mapping[str, Any], None]
 Vector = Union[Sequence[float], Sequence[int]]
@@ -49,6 +61,9 @@ class VectorDB(Protocol):
 
     active_collection: Any = None
     type: str = ""
+    embedding_function: Optional[Callable[[List[str]], List[List[float]]]] = (
+        None  # embeddings = embedding_function(sentences)
+    )
 
     def create_collection(self, collection_name: str, overwrite: bool = False, get_or_create: bool = True) -> Any:
         """
@@ -185,7 +200,7 @@ class VectorDBFactory:
     Factory class for creating vector databases.
     """
 
-    PREDEFINED_VECTOR_DB = ["chroma", "pgvector"]
+    PREDEFINED_VECTOR_DB = ["chroma", "pgvector", "qdrant"]
 
     @staticmethod
     def create_vector_db(db_type: str, **kwargs) -> VectorDB:
@@ -207,6 +222,10 @@ def create_vector_db(db_type: str, **kwargs) -> VectorDB:
             from .pgvectordb import PGVectorDB
 
             return PGVectorDB(**kwargs)
+        if db_type.lower() in ["qdrant", "qdrantdb"]:
+            from .qdrant import QdrantVectorDB
+
+            return QdrantVectorDB(**kwargs)
         else:
             raise ValueError(
                 f"Unsupported vector database type: {db_type}. Valid types are {VectorDBFactory.PREDEFINED_VECTOR_DB}."