August 2025 Summaries

SurrealDB Cloud has achieved a significant milestone by completing the SOC 2 Type 2 audit with an unqualified opinion and no exceptions, signaling that its security controls are not only well-designed but also effectively operational over time. This audit, which builds on the previously attained SOC 2 Type 1 certification, involved independent auditors evaluating controls pertinent to Security, Availability, and Confidentiality Trust Service Criteria, thereby providing assurance that the company's protective measures are actively implemented. For customers, this accomplishment means enhanced confidence in the security and operational integrity of SurrealDB Cloud, which emphasizes security as a fundamental principle in its operations. This achievement underscores SurrealDB's ongoing commitment to data protection and its philosophy of continually improving security standards.

Agno provides a Python framework for developing multi-agent systems that utilize shared memory, knowledge, and reasoning capabilities. This blog post focuses on creating an agent equipped with multiple tools, including SurrealMCP, integrated with SurrealDB, to function as a "researcher" that retrieves and organizes information from the web before storing it in SurrealDB. The agent effectively responds to naturally phrased queries, such as listing F1 drivers since 2000 along with their race starts and wins. Users are advised to familiarize themselves with Agno agents and set up necessary components like an LLM and SurrealMCP server. The post recommends starting with smaller LLMs to identify and improve potential areas of confusion, and it details the process of running SurrealMCP locally. Additionally, the agent's functionality can be enhanced by integrating tools like ReasoningTools and WebsiteTools, which allow it to refine actions and extract web content. The article encourages users to experiment by running different queries and highlights that support is available through SurrealDB Cloud and its community.

SurrealDB has introduced SurrealMCP, an official Model Context Protocol server that enhances AI tools by providing them with persistent, permission-aware, real-time memory, allowing them to recall past interactions, query live data securely, and reason over structured knowledge. This development enables AI agents to remember conversations, update live data securely with role-based access controls, and perform administrative tasks. SurrealMCP integrates seamlessly with SurrealDB's multi-model engine, offering a unified interface for querying various data types and supporting flexible deployment options, such as running locally or as an HTTP server. It facilitates smarter AI applications, like agent memory and contextual CRM insights, by allowing for easy integration with AI models and tools, and can be deployed using Docker or as a standalone binary.

The post explores the transformation of unstructured data into structured data using SurrealDB and LangChain, demonstrating how such data can be utilized for graph queries, vector searches, and data visualizations. It illustrates the process with a series of examples using SurrealQL and Rust, while guiding readers on how to recreate these steps in other languages like Python. The text explains the concept of unstructured data, its challenges for computer processing, and how recent advancements, particularly large language models (LLMs), have enabled the conversion of natural language into structured formats without human intervention. A key focus is on using a question-answering model from the Rust programming library to extract specific information from employee statements, like names, roles, and team affiliations, and structuring this data in SurrealDB for advanced querying and visualization. The post emphasizes using unique indexes and relation tables in SurrealDB to ensure data integrity, and demonstrates linking employees to their respective teams, managers, and companies. The article concludes by highlighting the ability to visualize this structured data graphically, promising further exploration in future posts.

Financial institutions, burdened by vast amounts of transactional data stored in legacy systems like HBase, can transform their operations by migrating to SurrealDB's multi-model database, which combines document, relational, graph, and vector data models. This transition is part of a strategic roadmap for financial firms to stabilize and modernize their data to meet regulatory needs, followed by using intelligence to create customer value and ultimately monetizing their data through new revenue streams. SurrealDB enables the creation of connected graph schemas that facilitate compliance, enhance customer personalization, and enable innovative services such as real-time credit scoring, fraud detection via AI, and building holistic customer profiles. By treating data as a dynamic asset rather than static history, financial institutions can unlock new business models, offering data-as-a-service, open banking APIs, and synthetic data products. This shift from legacy storage to intelligent, real-time connectivity allows these institutions to not only manage but also monetize and differentiate through their data, leading the way in financial innovation.

Abdelrahman Omar, a Rust software engineer, discusses how SurrealDB can simplify tech stacks by eliminating the need for separate caching and relational databases, using an example of enforcing XOR (Either/Or) constraints in database schema design. In scenarios where a record should contain one of two possible fields, such as a repository owned by either a user or an organization but not both or neither, Omar demonstrates how to apply XOR constraints in SurrealDB using DEFINE statements and VALUE clauses. By testing four possible cases, he illustrates how the database handles constraints, throwing errors when both or neither fields are set, and offering a cleaner solution using a single field type. The methodology reflects typical SQL practices with CHECK constraints, moving validation logic into the schema to ensure the database remains the single source of truth.

SurrealDB has successfully achieved the Cyber Essentials Plus (CE+) certification, a UK Government-backed program that involves rigorous testing to ensure the effectiveness of security measures against common cyber threats such as phishing, malware, ransomware, and unauthorized access. This certification offers independent assurance to customers and partners that SurrealDB's security practices are robust and effective in real-world scenarios. CE+ complements existing certifications like ISO 27001 and SOC2 Type 1, enhancing SurrealDB's security framework and reinforcing its commitment to data protection. The achievement is not merely symbolic but serves as a testament to SurrealDB's proactive approach to safeguarding data, allowing users to innovate confidently while meeting recognized industry standards.

This blog post provides ten insightful tips and tricks for optimizing queries in SurrealDB, focusing on enhancing data retrieval and manipulation. It explores advanced features such as using the `??` and `?` operators to manage default values and avoid errors, employing SPLIT clause for more efficient graph queries, and utilizing SELECT expressions within graph queries for precise data filtering. The post also highlights the benefits of complex IDs for graph edges to streamline queries and demonstrates how to manage polymorphic relationships in graph queries. It addresses current limitations in SurrealQL, such as variable awareness in closures, and suggests using array functions like `.reduce()` and `.fold()` as workarounds. Furthermore, it discusses the strategic use of nested statements to ensure transaction integrity and the utility of the RETURN clause for adding metadata without altering the stored data, providing a comprehensive guide to leveraging SurrealDB's capabilities for robust database management.

In a blog post by Martin Schaer, the process of building a Retrieval-Augmented Generation (RAG) solution using SurrealDB and LangChain is explored, highlighting the importance of optimizing for accuracy and latency in AI applications. Schaer details his experiment, including using WhatsApp chat data to create a vector and graph store with SurrealDB, employing LangChain's document loaders for data ingestion, and utilizing Ollama's embeddings for vector storage. The use of prompt engineering and keyword inference is discussed to enhance semantic search capabilities, while Schaer shares insights on the limitations of simple graphs and the potential benefits of incorporating more complex relationships, as seen in LightRAG. He emphasizes the importance of structuring code to allow for testing variations and measuring results, suggesting that a multi-model RAG architecture can be tailored to specific use cases to improve document retrieval and provide efficient, cost-effective solutions. The post concludes with recommendations for further experimentation and optimization, encouraging readers to engage with the SurrealDB community for further discussion and exploration.

SurrealDB, a database built in Rust, combines a graphical interface and low-level command-line capabilities, making it versatile for various applications, including small edge devices. The blog post discusses using SurrealDB in conjunction with Ratatui, a tool for building terminal user interfaces in Rust, to create an AI-native demo app that integrates Wikipedia API-sourced documents, allowing users to link and search documents through both full-text and semantic search methods. A significant focus is on the novel "hybrid search" feature, recently added to SurrealDB, which combines lexical search with vector search using Reciprocal Rank Fusion (RRF) to enhance search precision and recall. The post also delves into the technicalities of implementing hybrid search, its benefits, and the setup required. Additionally, the app demonstrates how to perform various searches, including full-text and semantic searches using embeddings from OpenAI and Mistral, with the ability to visualize connections between articles. The post concludes with instructions on running the app using Rust, emphasizing the need for OpenAI and Mistral API keys for full functionality.

SurrealDB has introduced Surreal Sync, a new command-line tool designed to facilitate the migration of data from existing databases into SurrealDB, supporting sources such as Neo4J, MongoDB, and JSON Lines. Surreal Sync translates data types from these sources into compatible formats for SurrealDB, with full support for some types and partial support for others, ensuring minimal data loss. The tool also allows the conversion of JSON Lines files into SurrealQL tables, enabling seamless integration of different data formats into SurrealDB. The documentation provides detailed guidance on data conversion processes, with Surreal Sync currently in active development and open to community feedback.