Merge branch 'microsoft:main' into main

Author: chris-han

.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"
 

.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

autogen/agentchat/chat.py

@@ -107,6 +107,15 @@ def __find_async_chat_order(chat_ids: Set[int], prerequisites: List[Prerequisite
     return chat_order
 
 
+def _post_process_carryover_item(carryover_item):
+    if isinstance(carryover_item, str):
+        return carryover_item
+    elif isinstance(carryover_item, dict) and "content" in carryover_item:
+        return str(carryover_item["content"])
+    else:
+        return str(carryover_item)
+
+
 def __post_carryover_processing(chat_info: Dict[str, Any]) -> None:
     iostream = IOStream.get_default()
 
@@ -116,7 +125,7 @@ def __post_carryover_processing(chat_info: Dict[str, Any]) -> None:
             UserWarning,
         )
     print_carryover = (
-        ("\n").join([t for t in chat_info["carryover"]])
+        ("\n").join([_post_process_carryover_item(t) for t in chat_info["carryover"]])
         if isinstance(chat_info["carryover"], list)
         else chat_info["carryover"]
     )
@@ -153,7 +162,7 @@ def initiate_chats(chat_queue: List[Dict[str, Any]]) -> List[ChatResult]:
         For example:
             - `"sender"` - the sender agent.
             - `"recipient"` - the recipient agent.
-            - `"clear_history"  (bool) - whether to clear the chat history with the agent.
+            - `"clear_history"` (bool) - whether to clear the chat history with the agent.
                Default is True.
             - `"silent"` (bool or None) - (Experimental) whether to print the messages in this
                conversation. Default is False.

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}."