ag2 0.9.7__py3-none-any.whl → 0.9.9__py3-none-any.whl

autogen/agentchat/contrib/graph_rag/neo4j_native_graph_query_engine.py

@@ -4,7 +4,7 @@
 
 import asyncio
 import logging
-from typing import List, Optional, Union
+from typing import Optional
 
 from ....import_utils import optional_import_block, require_optional_import
 from .document import Document, DocumentType
@@ -39,12 +39,12 @@ class Neo4jNativeGraphQueryEngine:
         username: str = "neo4j",
         password: str = "password",
         embeddings: Optional["Embedder"] = None,
-        embedding_dimension: Optional[int] = 3072,
+        embedding_dimension: int | None = 3072,
         llm: Optional["LLMInterface"] = None,
         query_llm: Optional["LLMInterface"] = None,
-        entities: Optional[List[str]] = None,
-        relations: Optional[List[str]] = None,
-        potential_schema: Optional[List[tuple[str, str, str]]] = None,
+        entities: list[str] | None = None,
+        relations: list[str] | None = None,
+        potential_schema: list[tuple[str, str, str]] | None = None,
     ):
         """Initialize a Neo4j graph query engine.
 
@@ -74,7 +74,7 @@ class Neo4jNativeGraphQueryEngine:
         self.relations = relations
         self.potential_schema = potential_schema
 
-    def init_db(self, input_doc: Optional[Union[list[Document]]] = None) -> None:
+    def init_db(self, input_doc: list[Document] | None = None) -> None:
         """Initialize the Neo4j graph database using the provided input doc.
         Currently this method only supports single document input (only reads the first doc).
 
@@ -189,7 +189,7 @@ class Neo4jNativeGraphQueryEngine:
             from_pdf=True,
         )
 
-    def _build_graph(self, input_doc: List[Document]) -> None:
+    def _build_graph(self, input_doc: list[Document]) -> None:
         """Build the knowledge graph using the provided input documents.
 
         Args:

autogen/agentchat/contrib/graph_rag/neo4j_native_graph_rag_capability.py

@@ -2,7 +2,7 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
-from typing import Any, Optional, Union
+from typing import Any
 
 from .... import Agent, ConversableAgent
 from .graph_query_engine import GraphStoreQueryResult
@@ -41,10 +41,10 @@ class Neo4jNativeGraphCapability(GraphRagCapability):
     def _reply_using_native_neo4j_query(
         self,
         recipient: ConversableAgent,
-        messages: Optional[list[dict[str, Any]]] = None,
-        sender: Optional[Agent] = None,
-        config: Optional[Any] = None,
-    ) -> tuple[bool, Optional[Union[str, dict[str, Any]]]]:
+        messages: list[dict[str, Any]] | None = None,
+        sender: Agent | None = None,
+        config: Any | None = None,
+    ) -> tuple[bool, str | dict[str, Any] | None]:
         """Query Neo4j and return the message. Internally, it uses the Neo4jNativeGraphQueryEngine to query the graph.
 
         The agent's system message will be incorporated into the query, if it's not blank.
@@ -66,7 +66,7 @@ class Neo4jNativeGraphCapability(GraphRagCapability):
 
         return True, result.answer if result.answer else "I'm sorry, I don't have an answer for that."
 
-    def _messages_summary(self, messages: Union[dict[str, Any], str], system_message: str) -> str:
+    def _messages_summary(self, messages: dict[str, Any] | str, system_message: str) -> str:
         """Summarize the messages in the conversation history. Excluding any message with 'tool_calls' and 'tool_responses'
         Includes the 'name' (if it exists) and the 'content', with a new line between each one, like:
         customer:

autogen/agentchat/contrib/img_utils.py

@@ -194,7 +194,7 @@ def convert_base64_to_data_uri(base64_image):
 
 
 @require_optional_import("PIL", "unknown")
-def gpt4v_formatter(prompt: str, img_format: str = "uri") -> list[Union[str, dict[str, Any]]]:
+def gpt4v_formatter(prompt: str, img_format: str = "uri") -> list[str | dict[str, Any]]:
     """Formats the input prompt by replacing image tags and returns a list of text and images.
 
     Args:

autogen/agentchat/contrib/llamaindex_conversable_agent.py

@@ -4,7 +4,7 @@
 #
 # Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
 # SPDX-License-Identifier: MIT
-from typing import Any, Optional, Union
+from typing import Any
 
 from ... import OpenAIWrapper
 from ...import_utils import optional_import_block, require_optional_import
@@ -32,7 +32,7 @@ class LLamaIndexConversableAgent(ConversableAgent):
         self,
         name: str,
         llama_index_agent: "AgentRunner",
-        description: Optional[str] = None,
+        description: str | None = None,
         **kwargs: Any,
     ):
         """Args:
@@ -65,10 +65,10 @@ class LLamaIndexConversableAgent(ConversableAgent):
 
     def _generate_oai_reply(
         self,
-        messages: Optional[list[dict[str, Any]]] = None,
-        sender: Optional[Agent] = None,
-        config: Optional[OpenAIWrapper] = None,
-    ) -> tuple[bool, Optional[Union[str, dict[str, Any]]]]:
+        messages: list[dict[str, Any]] | None = None,
+        sender: Agent | None = None,
+        config: OpenAIWrapper | None = None,
+    ) -> tuple[bool, str | dict[str, Any] | None]:
         """Generate a reply using autogen.oai."""
         user_message, history = self._extract_message_and_history(messages=messages, sender=sender)
 
@@ -80,10 +80,10 @@ class LLamaIndexConversableAgent(ConversableAgent):
 
     async def _a_generate_oai_reply(
         self,
-        messages: Optional[list[dict[str, Any]]] = None,
-        sender: Optional[Agent] = None,
-        config: Optional[OpenAIWrapper] = None,
-    ) -> tuple[bool, Optional[Union[str, dict[str, Any]]]]:
+        messages: list[dict[str, Any]] | None = None,
+        sender: Agent | None = None,
+        config: OpenAIWrapper | None = None,
+    ) -> tuple[bool, str | dict[str, Any] | None]:
         """Generate a reply using autogen.oai."""
         user_message, history = self._extract_message_and_history(messages=messages, sender=sender)
 
@@ -96,7 +96,7 @@ class LLamaIndexConversableAgent(ConversableAgent):
         return (True, extracted_response)
 
     def _extract_message_and_history(
-        self, messages: Optional[list[dict[str, Any]]] = None, sender: Optional[Agent] = None
+        self, messages: list[dict[str, Any]] | None = None, sender: Agent | None = None
     ) -> tuple[str, list["ChatMessage"]]:
         """Extract the message and history from the messages."""
         if not messages:

autogen/agentchat/contrib/llava_agent.py

@@ -6,7 +6,8 @@
 # SPDX-License-Identifier: MIT
 import json
 import logging
-from typing import Any, Optional, Union
+import warnings
+from typing import Any
 
 import requests
 
@@ -33,7 +34,7 @@ class LLaVAAgent(MultimodalConversableAgent):
     def __init__(
         self,
         name: str,
-        system_message: Optional[tuple[str, list]] = DEFAULT_LLAVA_SYS_MSG,
+        system_message: tuple[str, list] | None = DEFAULT_LLAVA_SYS_MSG,
         *args,
         **kwargs: Any,
     ):
@@ -84,12 +85,25 @@ class LLaVAAgent(MultimodalConversableAgent):
         retry = 10
         while len(out) == 0 and retry > 0:
             # image names will be inferred automatically from llava_call
+            if "max_new_tokens" in self.llm_config:
+                warnings.warn(
+                    (
+                        "`max_new_tokens` is deprecated in `llm_config` for llava agents. "
+                        "Use `max_tokens` instead. "
+                        "Scheduled for removal in 0.10.0 version."
+                    ),
+                    DeprecationWarning,
+                )
+                max_tokens = self.llm_config["max_new_tokens"]
+            else:
+                max_tokens = self.llm_config.get("max_tokens")
+
             out = llava_call_binary(
                 prompt=prompt,
                 images=images,
                 config_list=self.llm_config["config_list"],
                 temperature=self.llm_config.get("temperature", 0.5),
-                max_new_tokens=self.llm_config.get("max_new_tokens", 2000),
+                max_new_tokens=max_tokens or 2000,
             )
             retry -= 1
 
@@ -169,7 +183,7 @@ def llava_call_binary(
             continue
 
 
-def llava_call(prompt: str, llm_config: Union[LLMConfig, dict]) -> str:
+def llava_call(prompt: str, llm_config: LLMConfig | dict) -> str:
     """Makes a call to the LLaVA service to generate text based on a given prompt"""
     prompt, images = llava_formatter(prompt, order_image_tokens=False)
 

autogen/agentchat/contrib/math_user_proxy_agent.py

@@ -6,8 +6,9 @@
 # SPDX-License-Identifier: MIT
 import os
 import re
+from collections.abc import Callable
 from time import sleep
-from typing import Any, Callable, Dict, Literal, Optional, Union
+from typing import Any, Literal
 
 from pydantic import BaseModel, root_validator
 
@@ -141,12 +142,11 @@ class MathUserProxyAgent(UserProxyAgent):
 
     def __init__(
         self,
-        name: Optional[str] = "MathChatAgent",  # default set to MathChatAgent
-        is_termination_msg: Optional[
-            Callable[[Dict[str, Any]], bool]
-        ] = _is_termination_msg_mathchat,  # terminate if \boxed{} in message
+        name: str | None = "MathChatAgent",  # default set to MathChatAgent
+        is_termination_msg: Callable[[dict[str, Any]], bool]
+        | None = _is_termination_msg_mathchat,  # terminate if \boxed{} in message
         human_input_mode: Literal["ALWAYS", "NEVER", "TERMINATE"] = "NEVER",  # Fully automated
-        default_auto_reply: Optional[Union[str, dict[str, Any]]] = DEFAULT_REPLY,
+        default_auto_reply: str | dict[str, Any] | None = DEFAULT_REPLY,
         max_invalid_q_per_step=3,  # a parameter needed in MathChat
         **kwargs: Any,
     ):
@@ -294,9 +294,9 @@ class MathUserProxyAgent(UserProxyAgent):
 
     def _generate_math_reply(
         self,
-        messages: Optional[list[dict]] = None,
-        sender: Optional[Agent] = None,
-        config: Optional[Any] = None,
+        messages: list[dict] | None = None,
+        sender: Agent | None = None,
+        config: Any | None = None,
     ):
         """Generate an auto reply."""
         if messages is None:
@@ -366,7 +366,7 @@ class MathUserProxyAgent(UserProxyAgent):
 # THE SOFTWARE.
 
 
-def get_from_dict_or_env(data: dict[str, Any], key: str, env_key: str, default: Optional[str] = None) -> str:
+def get_from_dict_or_env(data: dict[str, Any], key: str, env_key: str, default: str | None = None) -> str:
     """Get a value from a dictionary or an environment variable."""
     if data.get(key):
         return data[key]
@@ -395,7 +395,7 @@ class WolframAlphaAPIWrapper(BaseModel):
     """
 
     wolfram_client: Any  #: :meta private:
-    wolfram_alpha_appid: Optional[str] = None
+    wolfram_alpha_appid: str | None = None
 
     @root_validator(skip_on_failure=True)
     @classmethod

autogen/agentchat/contrib/multimodal_conversable_agent.py

@@ -5,7 +5,7 @@
 # Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
 # SPDX-License-Identifier: MIT
 import copy
-from typing import Any, Optional, Union
+from typing import Any
 
 from ... import OpenAIWrapper
 from ...code_utils import content_str
@@ -27,7 +27,7 @@ class MultimodalConversableAgent(ConversableAgent):
     def __init__(
         self,
         name: str,
-        system_message: Optional[Union[str, list]] = DEFAULT_LMM_SYS_MSG,
+        system_message: str | list | None = DEFAULT_LMM_SYS_MSG,
         is_termination_msg: str = None,
         *args,
         **kwargs: Any,
@@ -61,7 +61,7 @@ class MultimodalConversableAgent(ConversableAgent):
             MultimodalConversableAgent.a_generate_oai_reply,
         )
 
-    def update_system_message(self, system_message: Union[dict[str, Any], list[str], str]):
+    def update_system_message(self, system_message: dict[str, Any] | list[str] | str):
         """Update the system message.
 
         Args:
@@ -71,7 +71,7 @@ class MultimodalConversableAgent(ConversableAgent):
         self._oai_system_message[0]["role"] = "system"
 
     @staticmethod
-    def _message_to_dict(message: Union[dict[str, Any], list[str], str]) -> dict:
+    def _message_to_dict(message: dict[str, Any] | list[str] | str) -> dict:
         """Convert a message to a dictionary. This implementation
         handles the GPT-4V formatting for easier prompts.
 
@@ -100,10 +100,10 @@ class MultimodalConversableAgent(ConversableAgent):
 
     def generate_oai_reply(
         self,
-        messages: Optional[list[dict[str, Any]]] = None,
-        sender: Optional[Agent] = None,
-        config: Optional[OpenAIWrapper] = None,
-    ) -> tuple[bool, Optional[Union[str, dict[str, Any]]]]:
+        messages: list[dict[str, Any]] | None = None,
+        sender: Agent | None = None,
+        config: OpenAIWrapper | None = None,
+    ) -> tuple[bool, str | dict[str, Any] | None]:
         """Generate a reply using autogen.oai."""
         client = self.client if config is None else config
         if client is None:

autogen/agentchat/contrib/qdrant_retrieve_user_proxy_agent.py

@@ -5,7 +5,8 @@
 # Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
 # SPDX-License-Identifier: MIT
 import warnings
-from typing import Any, Callable, Literal, Optional
+from collections.abc import Callable
+from typing import Any, Literal, Optional
 
 from ...import_utils import optional_import_block, require_optional_import
 from ...retrieve_utils import TEXT_FORMATS, get_files_from_dir, split_files_to_chunks
@@ -30,8 +31,8 @@ class QdrantRetrieveUserProxyAgent(RetrieveUserProxyAgent):
         self,
         name="RetrieveChatAgent",  # default set to RetrieveChatAgent
         human_input_mode: Literal["ALWAYS", "NEVER", "TERMINATE"] = "ALWAYS",
-        is_termination_msg: Optional[Callable[[dict[str, Any]], bool]] = None,
-        retrieve_config: Optional[dict[str, Any]] = None,  # config for the retrieve agent
+        is_termination_msg: Callable[[dict[str, Any]], bool] | None = None,
+        retrieve_config: dict[str, Any] | None = None,  # config for the retrieve agent
         **kwargs: Any,
     ):
         """Args:
@@ -175,7 +176,7 @@ def create_qdrant_from_dir(
     quantization_config: Optional["models.QuantizationConfig"] = None,
     hnsw_config: Optional["models.HnswConfigDiff"] = None,
     payload_indexing: bool = False,
-    qdrant_client_options: Optional[dict[str, Any]] = {},
+    qdrant_client_options: dict[str, Any] | None = {},
 ):
     """Create a Qdrant collection from all the files in a given directory, the directory can also be a single file or a
       url to a single file.
@@ -271,7 +272,7 @@ def query_qdrant(
     collection_name: str = "all-my-documents",
     search_string: str = "",
     embedding_model: str = "BAAI/bge-small-en-v1.5",
-    qdrant_client_options: Optional[dict[str, Any]] = {},
+    qdrant_client_options: dict[str, Any] | None = {},
 ) -> list[list["QueryResponse"]]:
     """Perform a similarity search with filters on a Qdrant collection
 

autogen/agentchat/contrib/rag/chromadb_query_engine.py

@@ -4,8 +4,9 @@
 
 import logging
 import os
+from collections.abc import Sequence
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Optional, Sequence, Union
+from typing import TYPE_CHECKING, Any, Optional
 
 from ....doc_utils import export_module
 from ....import_utils import optional_import_block, require_optional_import
@@ -37,8 +38,7 @@ logger = logging.getLogger(__name__)
 @require_optional_import(["chromadb", "llama_index"], "rag")
 @export_module("autogen.agentchat.contrib.rag")
 class ChromaDBQueryEngine:
-    """
-    This engine leverages Chromadb to persist document embeddings in a named collection
+    """This engine leverages Chromadb to persist document embeddings in a named collection
     and LlamaIndex's VectorStoreIndex to efficiently index and retrieve documents, and generate an answer in response
     to natural language queries. Collection can be regarded as an abstraction of group of documents in the database.
 
@@ -51,18 +51,18 @@ class ChromaDBQueryEngine:
 
     def __init__(  # type: ignore[no-any-unimported]
         self,
-        host: Optional[str] = "localhost",
-        port: Optional[int] = 8000,
+        host: str | None = "localhost",
+        port: int | None = 8000,
         settings: Optional["Settings"] = None,
-        tenant: Optional[str] = None,
-        database: Optional[str] = None,
-        embedding_function: "Optional[EmbeddingFunction[Any]]" = None,
-        metadata: Optional[dict[str, Any]] = None,
+        tenant: str | None = None,
+        database: str | None = None,
+        embedding_function: "EmbeddingFunction[Any] | None" = None,
+        metadata: dict[str, Any] | None = None,
         llm: Optional["LLM"] = None,
-        collection_name: Optional[str] = None,
+        collection_name: str | None = None,
     ) -> None:
-        """
-        Initializes the ChromaDBQueryEngine with db_path, metadata, and embedding function and llm.
+        """Initializes the ChromaDBQueryEngine with db_path, metadata, and embedding function and llm.
+
         Args:
             host: The host address of the ChromaDB server. Default is localhost.
             port: The port number of the ChromaDB server. Default is 8000.
@@ -101,8 +101,8 @@ class ChromaDBQueryEngine:
 
     def init_db(
         self,
-        new_doc_dir: Optional[Union[Path, str]] = None,
-        new_doc_paths_or_urls: Optional[Sequence[Union[Path, str]]] = None,
+        new_doc_dir: Path | str | None = None,
+        new_doc_paths_or_urls: Sequence[Path | str] | None = None,
         *args: Any,
         **kwargs: Any,
     ) -> bool:
@@ -125,7 +125,6 @@ class ChromaDBQueryEngine:
             bool: True if initialization is successful
 
         """
-
         self._set_up(overwrite=True)
         documents = self._load_doc(input_dir=new_doc_dir, input_docs=new_doc_paths_or_urls)
         self.index = VectorStoreIndex.from_documents(documents=documents, storage_context=self.storage_context)
@@ -155,8 +154,8 @@ class ChromaDBQueryEngine:
 
     def add_docs(
         self,
-        new_doc_dir: Optional[Union[Path, str]] = None,
-        new_doc_paths_or_urls: Optional[Sequence[Union[Path, str]]] = None,
+        new_doc_dir: Path | str | None = None,
+        new_doc_paths_or_urls: Sequence[Path | str] | None = None,
         *args: Any,
         **kwargs: Any,
     ) -> None:
@@ -174,8 +173,7 @@ class ChromaDBQueryEngine:
             self.index.insert(doc)
 
     def query(self, question: str) -> str:
-        """
-        Retrieve information from indexed documents by processing a query using the engine's LLM.
+        """Retrieve information from indexed documents by processing a query using the engine's LLM.
 
         Args:
             question: A natural language query string used to search the indexed documents.
@@ -193,8 +191,7 @@ class ChromaDBQueryEngine:
         return str(response)
 
     def get_collection_name(self) -> str:
-        """
-        Get the name of the collection used by the query engine.
+        """Get the name of the collection used by the query engine.
 
         Returns:
             The name of the collection.
@@ -210,10 +207,10 @@ class ChromaDBQueryEngine:
             raise Exception("Query index is not initialized. Please call init_db or connect_db first.")
 
     def _set_up(self, overwrite: bool) -> None:
-        """
-        Set up ChromaDB and LlamaIndex storage by:
+        """Set up ChromaDB and LlamaIndex storage by:
         1. Initialize the ChromaDB using VectorDBFactory and create a collection with the given name.
         2. Create the LlamaIndex vector store and storage context for the collection.
+
         Args:
             overwrite: If True, overwrite the existing collection with the same name.
         """
@@ -223,10 +220,9 @@ class ChromaDBQueryEngine:
         self.storage_context = StorageContext.from_defaults(vector_store=self.vector_store)
 
     def _load_doc(  # type: ignore[no-any-unimported]
-        self, input_dir: Optional[Union[Path, str]], input_docs: Optional[Sequence[Union[Path, str]]]
+        self, input_dir: Path | str | None, input_docs: Sequence[Path | str] | None
     ) -> Sequence["LlamaDocument"]:
-        """
-        Load documents from a directory and/or a sequence of file paths.
+        """Load documents from a directory and/or a sequence of file paths.
 
         It uses LlamaIndex's SimpleDirectoryReader that supports multiple file[formats]((https://docs.llamaindex.ai/en/stable/module_guides/loading/simpledirectoryreader/#supported-file-types)).
 

autogen/agentchat/contrib/rag/llamaindex_query_engine.py

@@ -4,8 +4,9 @@
 
 import logging
 import os
+from collections.abc import Sequence
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Optional, Sequence, Union
+from typing import TYPE_CHECKING, Any, Optional
 
 from ....doc_utils import export_module
 from ....import_utils import optional_import_block, require_optional_import
@@ -33,8 +34,7 @@ logger = logging.getLogger(__name__)
 @require_optional_import("llama_index", "rag")
 @export_module("autogen.agentchat.contrib.rag")
 class LlamaIndexQueryEngine:
-    """
-    This engine leverages LlamaIndex's VectorStoreIndex to efficiently index and retrieve documents, and generate an answer in response
+    """This engine leverages LlamaIndex's VectorStoreIndex to efficiently index and retrieve documents, and generate an answer in response
     to natural language queries. It use any LlamaIndex [vector store](https://docs.llamaindex.ai/en/stable/module_guides/storing/vector_stores/).
 
     By default the engine will use OpenAI's GPT-4o model (use the `llm` parameter to change that).
@@ -44,10 +44,10 @@ class LlamaIndexQueryEngine:
         self,
         vector_store: "BasePydanticVectorStore",
         llm: Optional["LLM"] = None,
-        file_reader_class: Optional[type["SimpleDirectoryReader"]] = None,
+        file_reader_class: type["SimpleDirectoryReader"] | None = None,
     ) -> None:
-        """
-        Initializes the LlamaIndexQueryEngine with the given vector store.
+        """Initializes the LlamaIndexQueryEngine with the given vector store.
+
         Args:
             vector_store: The vector store to use for indexing and querying documents.
             llm: LLM model used by LlamaIndex for query processing. You can find more supported LLMs at [LLM](https://docs.llamaindex.ai/en/stable/module_guides/models/llms/).
@@ -59,8 +59,8 @@ class LlamaIndexQueryEngine:
 
     def init_db(
         self,
-        new_doc_dir: Optional[Union[Path, str]] = None,
-        new_doc_paths_or_urls: Optional[Sequence[Union[Path, str]]] = None,
+        new_doc_dir: Path | str | None = None,
+        new_doc_paths_or_urls: Sequence[Path | str] | None = None,
         *args: Any,
         **kwargs: Any,
     ) -> bool:
@@ -80,7 +80,6 @@ class LlamaIndexQueryEngine:
             bool: True if initialization is successful
 
         """
-
         self.storage_context = StorageContext.from_defaults(vector_store=self.vector_store)
         documents = self._load_doc(input_dir=new_doc_dir, input_docs=new_doc_paths_or_urls)
         self.index = VectorStoreIndex.from_documents(documents=documents, storage_context=self.storage_context)
@@ -106,8 +105,8 @@ class LlamaIndexQueryEngine:
 
     def add_docs(
         self,
-        new_doc_dir: Optional[Union[Path, str]] = None,
-        new_doc_paths_or_urls: Optional[Sequence[Union[Path, str]]] = None,
+        new_doc_dir: Path | str | None = None,
+        new_doc_paths_or_urls: Sequence[Path | str] | None = None,
         *args: Any,
         **kwargs: Any,
     ) -> None:
@@ -125,8 +124,7 @@ class LlamaIndexQueryEngine:
             self.index.insert(doc)
 
     def query(self, question: str) -> str:
-        """
-        Retrieve information from indexed documents by processing a query using the engine's LLM.
+        """Retrieve information from indexed documents by processing a query using the engine's LLM.
 
         Args:
             question: A natural language query string used to search the indexed documents.
@@ -149,10 +147,9 @@ class LlamaIndexQueryEngine:
             raise Exception("Query index is not initialized. Please call init_db or connect_db first.")
 
     def _load_doc(  # type: ignore[no-any-unimported]
-        self, input_dir: Optional[Union[Path, str]], input_docs: Optional[Sequence[Union[Path, str]]]
+        self, input_dir: Path | str | None, input_docs: Sequence[Path | str] | None
     ) -> Sequence["LlamaDocument"]:
-        """
-        Load documents from a directory and/or a sequence of file paths.
+        """Load documents from a directory and/or a sequence of file paths.
 
         Default to uses LlamaIndex's SimpleDirectoryReader that supports multiple file[formats](https://docs.llamaindex.ai/en/stable/module_guides/loading/simpledirectoryreader/#supported-file-types).
 
@@ -170,7 +167,7 @@ class LlamaIndexQueryEngine:
             ValueError: If any provided file path does not exist.
             ValueError: If neither input_dir nor input_docs is provided.
         """
-        loaded_documents: list["LlamaDocument"] = []  # type: ignore[no-any-unimported]
+        loaded_documents: list[LlamaDocument] = []  # type: ignore[no-any-unimported]
         if input_dir:
             logger.info(f"Loading docs from directory: {input_dir}")
             if not os.path.exists(input_dir):