Weaviate Feature Trails

Feature trailActive

Engram: Managed Memory and Context Service

Engram is now generally available as a managed memory and context service for LLM agents. It provides asynchronous, durable pipelines for extracting, reconciling, and persisting structured memory states from raw agent events. Key features include active memory maintenance, fire-and-forget application layer integration with Temporal-grade durability, ready-to-deploy templates for personalization and multi-agent state, built-in scopes for data isolation, and unified retrieval on Weaviate's hybrid search. The Claude Code plugin leverages Engram to provide LLM agents with long-term memory across sessions and codebases, improving consistency and developer productivity by recalling past decisions and code patterns. Memory is saved asynchronously as a side-effect of working, and recalled silently when relevant.

8 posts · 2026

Timeline

Feature trailActive

Google Modules Security Fix

This post details a critical security vulnerability fix in Weaviate's Google-backed modules (text2vec-google, multi2vec-google, generative-google). The vulnerability allowed for credential disclosure via an unvalidated apiEndpoint configuration, potentially exposing static API keys or live OAuth access tokens. The fix involves extending endpoint validation to the apiEndpoint field at both configuration and query parameter layers. This addresses a high-severity (CVSS 7.1) issue impacting versions prior to v1.39.3. Customers are advised to upgrade or disable affected modules. The post also mentions ongoing efforts to secure enterprise authentication and authorization, including API key management, OIDC integration, and RBAC.

1 post · 2026

Timeline

Feature trailActive

HFresh: Memory-Efficient Vector Search

HFresh is Weaviate's disk-based vector index designed for memory-efficient applications and large datasets. It utilizes a two-stage search strategy: an in-memory HNSW centroid index routes queries to relevant disk-based postings, which contain compressed vectors. Background operations like splitting, merging, and reassigning postings ensure index freshness without full rebuilds. In v1.39, HFresh reaches technical preview with RQ-8 for centroid index and RQ-1 for postings, supporting cosine and l. This release introduces 4-bit Rotational Quantization (RQ4) with centering and outlier storage, significantly improving memory efficiency (45% heap reduction for a 1536-dim dataset) and import times (37% faster for RQ4). Encoding and distance kernels are optimized with SIMD support, and prefetching is improved for better memory access. Recall remains stable across datasets from 1M to 250M vectors.

2 posts · 2026

Timeline

Feature trailActive

Semantic Search for Creative Assets

Foundry turns an existing archive into a searchable creative library by scanning files, recording metadata, preparing assets for retrieval with descriptions and tags, and synchronizing this data with Weaviate. It supports keyword, semantic, and hybrid search modes, linking results back to original source files without moving or renaming them. The system uses content hashes for stable identity and change detection, and allows for filtering by project, file type, and relationship role. This post details the application of semantic search to creative asset management, focusing on reducing friction in retrieval and reuse.

7 posts · 2026

Timeline

Feature trailActive

Weaviate Release Notes

Weaviate v1.39 is released, making the Boost API and Maximal Marginal Relevance (MMR) diversity selection generally available. New previews include 4-bit Rotational Quantization and an experimental Search REST API. gRPC-Web support and HNSW snapshot rework are also included, improving disk usage and startup times. Performance improvements and community contributions are noted.

3 posts · 2026

Timeline

Feature trailActive

Search Mode Effort Tiers

Introduces the 'effort' parameter for the Query Agent's Search Mode, allowing users to control the trade-off between compute, latency, and accuracy. Three tiers (medium, high, ultrahigh) scale computation at query writing and reranking stages. Benchmarks demonstrate consistent accuracy gains with higher effort across various retrieval tasks, particularly on reasoning-intensive problems.

1 post · 2026

Timeline

Feature trailActive

Query Profiling

Query profiling is a per-query, opt-in debugging tool that provides detailed timing breakdowns of query execution stages across the entire cluster. This feature allows engineers to pinpoint performance bottlenecks within specific queries, replacing the previous node-per-node slow query log for real-time, granular analysis. It covers vector search, keyword scoring, and filter evaluation, and is generally available as of v1.38. The v1.37 release makes this a preview feature with per-shard timing breakdowns.

3 posts · 2026

Timeline

Feature trailActive

Data Ingestion and Vectorization at Scale

This post introduces robust strategies for importing and vectorizing large datasets into Weaviate. It details server-side batching for dynamic rate control, comprehensive error handling with retry-with-checkpoint mechanisms, and the `blobHash` data type for efficient storage of media embeddings. It also highlights Weaviate Embeddings for multimodal PDF ingestion without OCR. The MCP server is positioned for conversational, small-batch writes, distinct from bulk ingestion pipelines. The post also details building a coding assistant using the MCP server for RAG over code and docs, leveraging hybrid search and agentic workflows.

1 post · 2026

Timeline

Feature trailActive

Text Analysis for Hybrid Search

This post introduces and details enhancements to Weaviate's text analysis capabilities for hybrid search. It covers tokenization methods (word, lowercase, whitespace, field, and language-specific options), accent folding for multilingual support, and per-property stopword management. A new `/v1/tokenize` endpoint is also introduced for verifying tokenization results. These features aim to improve the recall and accuracy of the BM25 component in hybrid search by providing more control and observability.

1 post · 2026

Timeline

Feature trailActive

Weaviate Managed C# Client

The Weaviate Managed C# Client provides an Entity Framework Core-inspired experience for .NET developers, enabling schema definition via C# attributes, type-safe LINQ queries, and automatic schema creation and migration. It supports features like named vectors, cross-collection references, batch operations, and Retrieval-Augmented Generation (RAG) directly within the .NET ecosystem.

1 post · 2026

Timeline

Feature trailActive

Enterprise Authentication and Authorization

Weaviate supports enterprise security needs through robust authentication and authorization mechanisms. This includes API key management for programmatic access, OpenID Connect (OIDC) integration with external Identity Providers (IdPs) for centralized user management and SSO, and Role-Based Access Control (RBAC) for fine-grained permission management. RBAC allows for the definition of custom roles and permissions, and can be integrated with OIDC groups for dynamic role assignment. Audit logging provides a detailed trail of all authorization decisions, valuable for security monitoring, incident response, and compliance. The v1.30 release introduced programmatic user management for API keys, allowing creation, deletion, and rotation without restarts. OIDC integration supports SSO and MFA, and can leverage OIDC groups for RBAC. The post also mentions Weaviate Cloud's Premium plan with SSO/SAML and Assurance support for self-hosted OIDC setup.

2 posts · 2026

Timeline