Update qdrant notebook for new qdrant vectordb

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:
         """

autogen/agentchat/contrib/vectordb/qdrant.py

@@ -92,7 +92,7 @@ def __init__(
             collection_options: dict | The options for creating the collection.
             kwargs: dict | Additional keyword arguments.
         """
-        self.client: QdrantClient = client if client is not None else QdrantClient(location=":memory:")
+        self.client: QdrantClient = client or QdrantClient(location=":memory:")
         self.embedding_function = FastEmbedEmbeddingFunction() or embedding_function
         self.collection_options = collection_options
         self.content_payload_key = content_payload_key
@@ -102,6 +102,10 @@ def __init__(
     def create_collection(self, collection_name: str, overwrite: bool = False, get_or_create: bool = True) -> None:
         """
         Create a collection in the vector database.
+        Case 1. if the collection does not exist, create the collection.
+        Case 2. the collection exists, if overwrite is True, it will overwrite the collection.
+        Case 3. the collection exists and overwrite is False, if get_or_create is True, it will get the collection,
+            otherwise it raise a ValueError.
 
         Args:
             collection_name: str | The name of the collection.
@@ -122,6 +126,8 @@ def create_collection(self, collection_name: str, overwrite: bool = False, get_o
                 vectors_config=models.VectorParams(size=embeddings_size, distance=models.Distance.COSINE),
                 **self.collection_options,
             )
+        elif not get_or_create:
+            raise ValueError(f"Collection {collection_name} already exists.")
 
     def get_collection(self, collection_name: str = None):
         """

website/blog/2023-10-18-RetrieveChat/index.mdx

@@ -483,4 +483,4 @@ The online app and the source code are hosted in [HuggingFace](https://huggingfa
 You can check out more example notebooks for RAG use cases:
 - [Automated Code Generation and Question Answering with Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat.ipynb)
 - [Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent)](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb)
-- [Automated Code Generation and Question Answering with Qdrant based Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_qdrant_RetrieveChat.ipynb)
+- [Automated Code Generation and Question Answering with Qdrant based Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat_qdrant.ipynb)

website/docs/Examples.md

@@ -11,7 +11,7 @@ Links to notebook examples:
 
 - Automated Task Solving with Code Generation, Execution & Debugging - [View Notebook](/docs/notebooks/agentchat_auto_feedback_from_code_execution)
 - 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](/docs/notebooks/agentchat_qdrant_RetrieveChat)
+- Automated Code Generation and Question Answering with [Qdrant](https://qdrant.tech/) based Retrieval Augmented Agents - [View Notebook](/docs/notebooks/agentchat_RetrieveChat_qdrant)
 
 ### Multi-Agent Collaboration (>3 Agents)
 

website/docs/ecosystem/pgvector.md

@@ -2,4 +2,4 @@
 
 [PGVector](https://github.com/pgvector/pgvector) is an open-source vector similarity search for Postgres.
 
-- [PGVector + AutoGen Code Examples](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_pgvector_RetrieveChat.ipynb)
+- [PGVector + AutoGen Code Examples](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat_pgvector.ipynb)

website/docs/installation/Optional-Dependencies.md

@@ -75,7 +75,7 @@ Example notebooks:
 
 [Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent)](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_RAG.ipynb)
 
-[Automated Code Generation and Question Answering with Qdrant based Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_qdrant_RetrieveChat.ipynb)
+[Automated Code Generation and Question Answering with Qdrant based Retrieval Augmented Agents](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat_qdrant.ipynb)
 
 ## Teachability
 

website/docs/topics/retrieval_augmentation.md

@@ -119,8 +119,8 @@ ragproxyagent.initiate_chat(
 ## 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 [PGVector](https://github.com/pgvector/pgvector) based Retrieval Augmented Agents - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_pgvector_RetrieveChat.ipynb)
-- 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)
+- Automated Code Generation and Question Answering with [PGVector](https://github.com/pgvector/pgvector) based Retrieval Augmented Agents - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_RetrieveChat_pgvector.ipynb)
+- 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_RetrieveChat_qdrant.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)