# API Reference

- [Vector Stores](https://mariadb.com/docs/connectors/other/langchain-mariadb/api-reference/vectorstores.md): MariaDBStore provides a LangChain-compatible vector store backed by MariaDB, supporting similarity search, metadata filtering, and maximal marginal relevance retrieval.
- [Chat Message History](https://mariadb.com/docs/connectors/other/langchain-mariadb/api-reference/chat_message_histories.md): MariaDBChatMessageHistory persists LangChain conversation history to a MariaDB database table, providing methods to add, retrieve, and clear messages per session.
- [Expression Filters](https://mariadb.com/docs/connectors/other/langchain-mariadb/api-reference/expression_filter.md): Expression filter reference for langchain-mariadb, documenting the operator enum, filter builder classes, and MariaDBFilterExpressionConverter for metadata-based vector queries.
- [Translator](https://mariadb.com/docs/connectors/other/langchain-mariadb/api-reference/translator.md): MariaDBTranslator converts LangChain internal query language operations and comparisons into valid MariaDB filter dictionaries for use with structured vector store queries.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://mariadb.com/docs/connectors/other/langchain-mariadb/api-reference.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.