Vector database developer Weaviate is adding a crucial piece to its AI development stack—Weaviate Agents, a new set of services for building the next generation of AI and agentic applications.
According to the company, Weaviate Agents join Weaviate’s industry-leading vector database and vector embedding service to provide a unified solution for developers building applications powered by GenAI.
“Weaviate’s development tools come with batteries included,” said Weaviate VP of product Alvin Richards. “By unifying data management, agentic workflows and vector storage and search on our enterprise-class infrastructure, we empower development teams to quickly create applications that bring intelligent AI to the masses.”
Weaviate Agents are modular agentic workflows that use LLMs and prompts to interact dynamically with data in Weaviate. They are pretrained on Weaviate’s APIs, making them experts in performing Weaviate-specific data tasks based on natural language commands. Agents can be easily swapped, rearranged or used together, speeding up development with their simple APIs and powerful functionality.
The first three Weaviate Agents, launching in Public Preview this month, enable developers to query, improve, and augment their data with less operational overhead.
These agents include:
Query Agent: Developers configure Query Agent with their desired collections in Weaviate and submit search parameters and aggregations for each query in plain text prompts. Query Agent decides which data is relevant, formulates the necessary searches, retrieves the data, correlates, and ranks the answers and returns the results. It can even chain commands together, taking the results of a previous query and extending it with a new prompt.
Transformation Agent: Based on the natural language instructions passed into it, Transformation Agent can automatically update data, create new properties, add new data and more. Use cases include cleaning and organizing raw data for AI, generating and enriching metadata, automatically categorizing, labeling, and preprocessing data or even translating your entire dataset.
Personalization Agent: With Weaviate Personalization Agent, developers can go beyond static, rules-based recommendations and deliver smart, LLM-based personalization on the fly. Personalization Agent makes it easy to curate search results tailored to each user’s preferences and interactions. It can be used in conjunction with Weaviate Query and Transformation Agents to deliver hyper-personalized user experiences in real-time.
As they are released, Weaviate Agents will become available in Weaviate Cloud, including its free developer sandbox. Query Agent is available now, and Transformation and Personalization Agents are coming later this month.
"The emergence of vector databases, vector embedding services, and agentic architectures represents a pivotal moment in the evolution of data management and transformation," said Bob van Luijt, CEO of Weaviate. “This milestone is a natural next step in a journey we saw beginning a decade ago. And that's why I’m incredibly excited to see a new stack emerging for developers. For those using Weaviate, it’s made up of the Weaviate vector database, Agents, and Vector Embeddings. And what’s most exciting is that this is just the beginning.”
For more information about this news, visit www.weaviate.io.