autogen.agents.experimental.InMemoryQueryEngine

InMemoryQueryEngine

InMemoryQueryEngine(llm_config: LLMConfig | dict[str, Any])

This engine stores ingested documents in memory and then injects them into an internal agent’s system message for answering queries.
This implements the autogen.agentchat.contrib.rag.RAGQueryEngine protocol.

Parameters:

Name	Description
llm_config	Type: LLMConfig | dict[str, typing.Any]

Instance Methods

add_docs

add_docs(
    self,
    new_doc_dir: Path | str | None = None,
    new_doc_paths_or_urls: Sequence[Path | str] | None = None
) -> None

Add additional documents to the in-memory store

Loads new Docling-parsed Markdown files from a specified directory or a list of file paths and inserts them into the in-memory store.

Parameters:

Name	Description
new_doc_dir	The directory path from which to load additional documents. If provided, all eligible files in this directory are loaded. Type: pathlib.Path | str | None Default: None
new_doc_paths_or_urls	A list of file paths specifying additional documents to load. Each file should be a Docling-parsed Markdown file. Type: Sequence[pathlib.Path | str] | None Default: None

connect_db

connect_db(
    self,
    *args: Any,
    **kwargs: Any
) -> bool

Not required nor implemented for InMemoryQueryEngine

Parameters:

Name	Description
*args	Type: Any
**kwargs	Type: Any

init_db

init_db(
    self,
    new_doc_dir: Path | str | None = None,
    new_doc_paths_or_urls: Sequence[Path | str] | None = None,
    *args: Any,
    **kwargs: Any
) -> bool

Not required nor implemented for InMemoryQueryEngine

Parameters:

Name	Description
new_doc_dir	Type: pathlib.Path | str | None Default: None
new_doc_paths_or_urls	Type: Sequence[pathlib.Path | str] | None Default: None
*args	Type: Any
**kwargs	Type: Any

query

query(
    self,
    question: str,
    *args: Any,
    **kwargs: Any
) -> str

Run a query against the ingested documents and return the answer.

Parameters:

Name	Description
question	Type: str
*args	Type: Any
**kwargs	Type: Any