# Weaviate

> Source: https://aiwiki.ai/wiki/weaviate
> Updated: 2026-10-28
> Fact-checked: 2026-11-02
> Categories: AI Infrastructure, Open Source AI
> License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) - attribute to "AI Wiki (aiwiki.ai)"
> Cite as: AI Wiki. "Weaviate." aiwiki.ai, 28 Oct 2026. https://aiwiki.ai/wiki/weaviate
> From AI Wiki (https://aiwiki.ai), the free encyclopedia of artificial intelligence. Reuse freely with attribution.

**Weaviate** is an open-source [vector database](https://aiwiki.ai/wiki/vector_database) that stores both data objects and their vector [embeddings](https://aiwiki.ai/wiki/embeddings), enabling a combination of vector similarity search with structured filtering, keyword retrieval, and integrated generative search. Written in [Go](https://aiwiki.ai/wiki/go_programming_language) and licensed under [BSD-3-Clause](https://aiwiki.ai/wiki/bsd_3_clause_license), the system is designed for speed and reliability in [artificial intelligence](https://aiwiki.ai/wiki/artificial_intelligence) applications. The project began as an open-source initiative by [Bob van Luijt](https://aiwiki.ai/wiki/bob_van_luijt) in March 2016 and was later commercialized by SeMI Technologies, the Amsterdam-based company that he co-founded with [Etienne Dilocker](https://aiwiki.ai/wiki/etienne_dilocker) in 2019, after entering a startup accelerator at the end of 2018. SeMI Technologies rebranded to Weaviate B.V. in January 2023 [1][2][3]. As of November 2026, the open-source project had close to 17,000 [GitHub](https://aiwiki.ai/wiki/github) stars, and the company reported more than 20 million open-source downloads and thousands of customers; in early 2026 its website also cited a community of over 50,000 AI builders [4][5].

<figure class="w-56">
<img src="/images/site-2026-10-28-weaviate-logo-82b31c0106e1-tile.png" alt="Weaviate logo" width="474" height="126" />
<figcaption>Weaviate logo, from the official website <a href="https://weaviate.io/">weaviate.io</a>. Trademark of its owner.</figcaption>
</figure>

## Who created Weaviate and when?

The Weaviate project began in March 2016, when Dutch technology entrepreneur [Bob van Luijt](https://aiwiki.ai/wiki/bob_van_luijt) started experimenting with the idea of a database where semantic relationships were a first-class citizen. He was working through a strategic design consultancy called Kubrickology, and his early thinking was shaped by two influences: the GloVe paper on [word embedding](https://aiwiki.ai/wiki/word_embedding)s, which he encountered in 2015, and [Google](https://aiwiki.ai/wiki/google)'s Weave and Brillo "things" framework, which he first saw at the Ubiquity Conference in San Francisco in January 2016 [3][6].

In September 2017, van Luijt published a blog post connecting [Internet of Things](https://aiwiki.ai/wiki/internet_of_things) concepts with the semantic web, sketching the framework that would later become Weaviate. By the end of 2018, he had entered a startup accelerator in the Netherlands and assembled the founding team that would become SeMI Technologies. The company name stood for Semantic Machine Insights. The original Weaviate codebase had been more of a traditional [knowledge graph](https://aiwiki.ai/wiki/knowledge_graph), but during the accelerator phase the team pivoted toward [semantic search](https://aiwiki.ai/wiki/semantic_search) powered by vector embeddings, what they called the "Weaviate Search Graph" [3][6].

[Etienne Dilocker](https://aiwiki.ai/wiki/etienne_dilocker) joined as co-founder and Chief Technology Officer. Dilocker is a German engineer whose public profile describes his focus as Go, database development, cloud-native technology, and performance programming, with an emphasis on site reliability engineering [8].

The 2022 Series A announcement named Micha Verhagen as a third founder, serving as chief operating officer. The same announcement said SeMI Technologies was originally spun out of ING Labs, the innovation arm of Dutch bank ING Group, whose venture arm ING Ventures invested in the seed round [12].

Version 1.0.0 of Weaviate was released on 14 January 2021. This release introduced the modular API that allows the database to plug into different embedding providers and other extensions. By that point the project had already moved away from being a niche knowledge graph and was positioning itself as a dedicated vector database for the emerging generative-AI era [9].

In January 2023, the company changed its legal name from SeMI Technologies to Weaviate B.V. According to a press release at the time, the open-source product had become significantly better known than the corporate entity, so the team decided to consolidate under the Weaviate brand [2].

## How much funding has Weaviate raised?

Weaviate has raised approximately $67.6 million across three publicly disclosed funding rounds. The company has remained at the Series B stage as of early 2026 and has not announced any subsequent priced rounds [10][11].

| Round | Date | Amount | Lead investor(s) | Other participants |
|-------|------|--------|------------------|--------------------|
| Seed | August 2020 | $1.6M | Zetta Venture Partners | ING Ventures |
| Series A | February 2022 | $16M | Cortical Ventures, NEA | Zetta Venture Partners, ING Ventures |
| Series B | April 2023 | $50M | [Index Ventures](https://aiwiki.ai/wiki/index_ventures) | Battery Ventures, NEA, Cortical Ventures, Zetta Venture Partners, ING Ventures |

The $1.6 million seed round in August 2020 was led by Zetta Venture Partners with ING Ventures participating, and was not announced until the Series A in 2022 [12]. The $16 million Series A in February 2022 was co-led by Cortical Ventures and [New Enterprise Associates](https://aiwiki.ai/wiki/new_enterprise_associates) (NEA), with Zetta and ING Ventures continuing as participants. The Series A press release was headlined as highlighting "a new wave of AI-first database tech" [12][13].

The Series B closed on 21 April 2023 at $50 million, led by [Index Ventures](https://aiwiki.ai/wiki/index_ventures) and joined by Battery Ventures alongside the prior investors. The round was driven by demand from teams building [retrieval-augmented generation](https://aiwiki.ai/wiki/retrieval_augmented_generation) systems on top of [large language models](https://aiwiki.ai/wiki/large_language_model). Announcing the round, co-founder and CEO Bob van Luijt framed the product's positioning directly: "The Weaviate vector database is used as core infrastructure in the emerging AI-native ecosystem" [11]. Index Ventures partner Erin Price-Wright, who led the investment, added that "Weaviate's vector database and search engine provides a critical piece of infrastructure that's helping to drive a massive AI platform shift" [11]. Capital from the Series B has been used to expand the engineering team, build out Weaviate Cloud, and grow commercial operations across North America and Europe [11][14].

Third-party estimates compiled by GetLatka put Weaviate's annual revenue at around $12.3 million in October 2024, with about 104 employees in December 2024, suggesting strong commercial traction without an immediate need for additional priced rounds [15].

## headquarters and team

Weaviate is headquartered at Prinsengracht 769A in Amsterdam, Netherlands, the same canal-side district where the founding team began. The company is structured as remote-first, with engineers, researchers, and commercial staff distributed across Europe, North America, and other regions. Public estimates put headcount at roughly 90 to 105 people through 2024 and 2025 [15][16].

Key leadership disclosed publicly includes:

| Role | Person |
|------|--------|
| Chief Executive Officer | Bob van Luijt (co-founder) |
| Chief Technology Officer | Etienne Dilocker (co-founder) |
| Vice President of Engineering | Paul de Grijp |
| Director of Applied Research | John Trengrove |
| Head of People and Culture | Jessie de Groot |

The company describes its values as Be Kind, Work Together as One, Strive for Excellence, Encourage Transparency, and Inspire Trust [16].

## How does Weaviate's architecture work?

Weaviate's architecture is designed to handle multiple search paradigms (vector, keyword, and hybrid) within a single system. The database is written in [Go](https://aiwiki.ai/wiki/go_programming_language), which the team chose for its concurrency model, low memory overhead, and strong tooling around binary builds. Roughly 97 percent of the codebase is Go, with a small amount of Python tooling for tests and developer scripts [4].

A Weaviate node combines several subsystems: a storage engine based on a custom log-structured merge-tree (LSM-tree), an inverted index for keyword search, one or more [vector indexes](https://aiwiki.ai/wiki/vector_index) per collection, a schema and metadata service, and a multi-protocol API surface (REST, gRPC, and [GraphQL](https://aiwiki.ai/wiki/graphql)). Cluster coordination uses the Raft consensus algorithm, while object data is replicated using a leaderless eventually consistent model [17][18].

### HNSW index

Weaviate uses [HNSW](https://aiwiki.ai/wiki/hnsw) (Hierarchical Navigable Small World) as its primary vector index algorithm. HNSW is a graph-based approach that searches vectors by navigating through multiple layers, moving from coarse approximations to fine ones. Its complexity grows logarithmically rather than linearly with the dataset size, which makes it effective even at billions of vectors [19].

Each named vector in Weaviate maintains its own vector index, which can be either an HNSW graph or a flat index. The HNSW graph is held in memory for fast access, with commit logs and snapshots used to restore the structure after a restart. From version 1.31, Weaviate added HNSW snapshotting, which produces periodic on-disk snapshots that can be loaded directly at startup. According to the release notes, this can reduce startup time for large indexes by approximately 10 to 15 times compared with replaying the write-ahead log [9][20].

In single-instance mode, Weaviate's in-memory HNSW index handles millions of vectors with sub-second response times. For larger datasets, cluster mode distributes data across nodes with sharding and replication, enabling horizontal scaling to billions of data points [19].

Weaviate exposes several HNSW tuning parameters that allow developers to optimize the tradeoff between recall, speed, and memory:

| Parameter | Default | Description |
|-----------|---------|-------------|
| efConstruction | 128 | Size of dynamic candidate list during index construction; higher values improve graph quality at the cost of slower builds |
| maxConnections | 32 | Maximum number of connections per node in the HNSW graph; higher values improve recall but increase memory usage |
| ef | -1 (dynamic) | Size of the candidate list during search; controls the recall-latency tradeoff at query time |
| vectorCacheMaxObjects | 1 trillion | Maximum number of vectors to cache in memory; reducing this value helps when the dataset exceeds available RAM |
| flatSearchCutoff | 40,000 | For filtered searches, if the filter matches fewer objects than this threshold, Weaviate uses a brute-force (flat) search instead of the HNSW graph |

The flat index option is useful for small collections or multi-tenant environments where each tenant has a relatively small dataset. Instead of building and maintaining an HNSW graph, flat indexing stores vectors in a simple array and performs brute-force search, which is faster for small collections due to lower overhead [19].

### vector quantization

Weaviate supports several quantization techniques for compressing vectors and reducing memory consumption. Quantization is configured per HNSW (or flat) index and can be combined with rescoring, where the database re-ranks the top candidates using their full-precision vectors to recover most of the lost recall [21].

| Technique | Bit-width | Memory saving | Notes |
|-----------|-----------|--------------|-------|
| [Product Quantization](https://aiwiki.ai/wiki/product_quantization) (PQ) | Variable | About 85% | Splits vectors into segments and quantizes each segment using [k-means](https://aiwiki.ai/wiki/k-means) codebooks |
| Scalar Quantization (SQ) | 8 bits per dimension | About 75% | Maps each 32-bit float dimension into one of 256 buckets, trained on the data distribution |
| Binary Quantization (BQ) | 1 bit per dimension | About 97% | Stores each dimension as a single bit; fastest but least precise |
| Rotational Quantization (RQ) | 8, 4 or 1 bits | About 75% (8-bit) to about 97% (1-bit) | Applies a rotation to decorrelate dimensions before quantization, improving recall over SQ and BQ |

Rotational quantization (RQ) was introduced in version 1.32 (July 2025), and from version 1.33 8-bit RQ became the default compression for new collections. A 1-bit RQ variant, providing extreme compression rates while preserving most of the search quality, became a preview feature in version 1.33 (October 2025). Each quantization mode preserves a copy of the uncompressed vectors so that rescoring can refine the final top-k results [22][23].

### GPU-accelerated indexing

Through a partnership with NVIDIA, Weaviate supports GPU-accelerated index building using the cuVS library. The CAGRA algorithm builds indexes on the GPU, then converts them to HNSW format for cost-effective CPU-based query serving. This approach speeds up index construction while keeping query costs low [24].

### inverted index for keyword search

In addition to the HNSW vector index, Weaviate maintains an inverted index based on [BM25F](https://aiwiki.ai/wiki/bm25) scoring for keyword search. The BM25F algorithm extends the standard BM25 scoring function with field-level weighting, so different properties of an object (such as title versus body text) can contribute differently to keyword relevance scores. This inverted index powers Weaviate's keyword search and is also used as one component of [hybrid search](https://aiwiki.ai/wiki/hybrid_search) [25][26].

From version 1.30, Weaviate replaced the previous BM25 implementation with BlockMax WAND, an algorithm that allows the database to skip large blocks of postings during scoring. In Weaviate's internal benchmarks, BlockMax WAND reduced BM25 query latency by an order of magnitude on large corpora compared with the previous traversal strategy [27].

### What is Weaviate hybrid search?

Weaviate's hybrid search combines dense vector similarity with BM25 keyword matching in a single native API call. Combining the two signals is particularly relevant for retrieval-augmented generation workloads, where recall directly affects the quality of generated answers [25][26].

The system fuses dense [vector embeddings](https://aiwiki.ai/wiki/vector_embeddings) with sparse BM25 lexical matching, and developers can control the weighting between the two methods.

Weaviate offers two fusion algorithms for combining vector and keyword results:

| Fusion algorithm | Description | Best for |
|-----------------|-------------|----------|
| Ranked Fusion | Combines results by summing the inverse of each result's rank in the individual search lists | General-purpose hybrid queries |
| Relative Score Fusion | Normalizes scores from each search method to [0, 1] range and combines them | When the raw score distributions of the two methods differ significantly |

The `alpha` parameter controls the balance between vector search (alpha = 1.0) and keyword search (alpha = 0.0). Setting alpha to 0.5 weights both methods equally. The default value is 0.75, which favors vector search slightly [26].

### multi-vector embeddings and MUVERA

From version 1.31 (June 2025), Weaviate added support for multi-vector embeddings using MUVERA encoding. Multi-vector models such as [ColBERT](https://aiwiki.ai/wiki/colbert) represent each document as a set of token-level vectors rather than one pooled vector, which can improve retrieval accuracy at the cost of storage. MUVERA provides a fixed-dimension single-vector representation that approximates the late-interaction scoring used by ColBERT, allowing Weaviate to plug multi-vector models into its standard HNSW pipeline without exotic data structures [20].

### replication and consistency

From version 1.25 onward, Weaviate uses the Raft consensus algorithm for cluster metadata, including schema operations, role-based access control changes, and tenant lifecycle events. Raft is implemented using the HashiCorp Raft library; one node is elected leader, and metadata changes are committed once a quorum of nodes acknowledges them. This was a significant change from earlier versions, which had used a simpler gossip-style protocol that could not safely support concurrent schema operations [17].

Object data replication uses a leaderless, eventually consistent model with tunable consistency levels (ONE, QUORUM, ALL) at read and write time. Async replication, asynchronous shard replica movement between nodes, and rebalancing capabilities have all been added across the 1.25 through 1.32 release series, gradually maturing Weaviate into a distributed system suitable for production workloads at scale [17][22].

## module system

Weaviate's module system is one of its defining architectural features. Modules extend the database with additional capabilities at various stages of the data pipeline: vectorization (generating embeddings from raw data), [generative AI](https://aiwiki.ai/wiki/generative_ai) (producing text from search results), reranking (refining result order), and reference resolution (loading data from external sources).

Modules are loaded at server startup via configuration. In Docker deployments, modules are specified as environment variables. In [Kubernetes](https://aiwiki.ai/wiki/kubernetes), they are configured in the Helm chart values. Weaviate Cloud instances come with a default set of modules pre-configured [29].

### vectorizer modules

Vectorizer modules automatically generate embeddings when objects are inserted into Weaviate. Instead of computing embeddings externally and uploading them, users configure a vectorizer module on a collection and Weaviate handles embedding generation transparently.

| Module | Provider | Model type | Key notes |
|--------|----------|-----------|----------|
| text2vec-openai | [OpenAI](https://aiwiki.ai/wiki/openai) | Text | Uses OpenAI's embedding API (text-embedding-ada-002, text-embedding-3-small, etc.) |
| text2vec-cohere | [Cohere](https://aiwiki.ai/wiki/cohere) | Text | Uses Cohere's multilingual embedding models |
| text2vec-huggingface | [Hugging Face](https://aiwiki.ai/wiki/hugging_face) | Text | Uses Hugging Face Inference API for hosted models |
| text2vec-transformers | Self-hosted | Text | Runs transformer models locally in a sidecar container |
| text2vec-ollama | [Ollama](https://aiwiki.ai/wiki/ollama) | Text | Runs local embedding models through an Ollama instance |
| text2vec-google | [Google](https://aiwiki.ai/wiki/google) | Text | Uses Google's embedding models (Vertex AI, PaLM) |
| text2vec-aws | AWS | Text | Uses [Amazon Bedrock](https://aiwiki.ai/wiki/amazon_bedrock) embedding models |
| text2vec-jinaai | Jina AI | Text | Uses Jina AI's embedding models |
| text2vec-voyageai | [Voyage AI](https://aiwiki.ai/wiki/voyage_ai) | Text | Uses Voyage AI's domain-specific embeddings |
| text2vec-weaviate | Weaviate Embeddings | Text and multimodal | Weaviate's hosted embedding service, serving [Snowflake Arctic](https://aiwiki.ai/wiki/snowflake_arctic) and ModernVBERT models |
| multi2vec-clip | OpenAI CLIP | Multi-modal | Embeds both text and images into a shared vector space |
| multi2vec-bind | [ImageBind](https://aiwiki.ai/wiki/imagebind) | Multi-modal | Meta's ImageBind for text, image, audio, and video embeddings |
| multi2vec-cohere | [Cohere](https://aiwiki.ai/wiki/cohere) | Multi-modal | Cohere Embed v4 multimodal text and image embeddings |

Users can also import pre-computed vector embeddings directly, bypassing the module system entirely. This is the recommended path for users who already maintain a centralized embedding pipeline outside the database [29].

### generative modules

Generative modules connect Weaviate to large language models for retrieval-augmented generation (RAG) directly within the database.

| Module | Provider | Description |
|--------|----------|-------------|
| generative-openai | [OpenAI](https://aiwiki.ai/wiki/openai) | Uses [GPT-4](https://aiwiki.ai/wiki/gpt-4), GPT-3.5-turbo, and newer OpenAI chat models |
| generative-anthropic | [Anthropic](https://aiwiki.ai/wiki/anthropic) | Uses [Claude](https://aiwiki.ai/wiki/claude) family models |
| generative-cohere | [Cohere](https://aiwiki.ai/wiki/cohere) | Uses Cohere's Command models |
| generative-aws | AWS | Uses [Amazon Bedrock](https://aiwiki.ai/wiki/amazon_bedrock) models (Claude, Titan, Llama) |
| generative-google | [Google](https://aiwiki.ai/wiki/google) | Uses Google's Gemini and PaLM models |
| generative-anyscale | [Anyscale](https://aiwiki.ai/wiki/anyscale) | Uses open-source models hosted on Anyscale |
| generative-mistral | Mistral | Uses [Mistral](https://aiwiki.ai/wiki/mistral_ai) chat and instruct models |
| generative-friendliai | FriendliAI | Hosted open-source LLM endpoints |
| generative-contextual | [Contextual AI](https://aiwiki.ai/wiki/contextual_ai) | Generation tuned for grounded enterprise RAG |

A generative search query in Weaviate consists of two parts: a search query (vector, keyword, or hybrid) and a prompt for the [language model](https://aiwiki.ai/wiki/language_model). Weaviate first retrieves relevant objects, then passes both the search results and the prompt to the configured [generative model](https://aiwiki.ai/wiki/generative_model), returning the generated response alongside the original search results [30].

### reranker modules

Reranker modules apply a second-pass ranking model after the initial retrieval step. Cross-encoder reranking models score each retrieved result against the original query, which typically produces more accurate relevance judgments than the initial bi-encoder similarity search. Available reranker modules include reranker-cohere, reranker-voyageai, reranker-jinaai, reranker-contextual, and reranker-transformers [29].

## schema and collection definition

Weaviate organizes data into collections (previously called "classes"). Each collection defines a schema that specifies the properties of its objects, the vectorizer to use, the generative module (if any), and index configuration.

A collection definition includes:

- **Properties**: Named fields with data types (text, int, number, boolean, date, object, geoCoordinates, phoneNumber, blob, uuid, and arrays of these types).
- **Vectorizer configuration**: Which vectorizer module to use and which properties to vectorize.
- **Generative module configuration**: Which LLM module to use for RAG queries.
- **Vector index configuration**: HNSW or flat index, with tuning parameters and quantization options.
- **Inverted index configuration**: Settings for keyword search, including BM25 parameters and stopword configuration.
- **Replication configuration**: Number of replicas for the collection.
- **Multi-tenancy configuration**: Whether to enable tenant isolation.

Weaviate also supports auto-schema, which is enabled by default. When auto-schema is active, Weaviate infers collection definitions from the data being inserted, automatically detecting property names and types. This is convenient for prototyping but should be disabled in production for predictable behavior [31].

Cross-references allow linking objects across collections. For example, an Article collection might reference objects in an Author collection, enabling graph-like traversals in queries.

From version 1.32, Weaviate added collection aliases, which let operators point an alias name at different underlying collections. This makes zero-downtime migrations practical: a new collection is built behind a fresh name, the alias is swapped to it once the data is ready, and the old collection can be dropped without changing client code [22].

## key features

### multi-tenancy

Weaviate implements native multi-tenancy with one shard per tenant, dynamic resource management, and true data isolation. This design means each tenant's data is physically separated, not just logically filtered. Recent updates introduced tenant offloading to S3 cloud storage and renamed the tenant activity statuses from HOT/COLD to ACTIVE/INACTIVE for clarity [32].

Multi-tenancy is useful for SaaS applications where each customer needs their own isolated dataset but the application operator does not want to manage separate database instances for each customer.

Weaviate's multi-tenancy implementation supports three tenant states:

| State | Data location | Cost | Access speed |
|-------|--------------|------|-------------|
| ACTIVE (formerly HOT) | In memory and on local disk | Highest | Fastest |
| INACTIVE (formerly COLD) | On local disk only | Medium | Moderate (requires activation) |
| OFFLOADED | In S3 cloud storage | Lowest | Slowest (requires reactivation to local disk) |

This tiered approach allows operators to manage costs by offloading inactive tenants to cheaper storage while keeping frequently accessed tenants in memory for low-latency queries. Reference customers such as [Instabase](https://aiwiki.ai/wiki/instabase) operate clusters with more than 50,000 tenants, illustrating that the design holds up at significant scale [32][33].

### GraphQL, REST, and gRPC APIs

Weaviate exposes three APIs: REST, [GraphQL](https://aiwiki.ai/wiki/graphql), and gRPC. The GraphQL API was long distinctive among vector databases, since most competitors offer only REST or gRPC interfaces, but Weaviate has since deprecated it: as of November 2026 its documentation says the GraphQL API will be switched off on Weaviate Cloud on May 1, 2027, and the official client libraries use gRPC instead [34]. GraphQL allows clients to specify exactly which fields they need, reducing over-fetching and making it easier to build flexible query interfaces [34].

A typical Weaviate GraphQL query can combine vector search, keyword filters, and property selection in a single request:

```graphql
{
  Get {
    Article(
      hybrid: {
        query: "machine learning applications"
        alpha: 0.75
      }
      limit: 5
    ) {
      title
      content
      _additional {
        score
        distance
      }
    }
  }
}
```

The `alpha` parameter controls the balance between vector search (1.0) and keyword search (0.0).

The gRPC interface, introduced incrementally between version 1.19 and version 1.23.7, is the preferred protocol for high-throughput workloads. Internal benchmarks comparing the gRPC and REST/GraphQL paths on identical hardware showed query latency reductions of 40 to 70 percent and import-time reductions of close to 50 percent on the DBPedia benchmark dataset [35]. The gRPC API uses HTTP/2 and Protocol Buffers, which produce smaller, faster-to-parse payloads than JSON over HTTP/1.1.

A short example using the v4 [Python](https://aiwiki.ai/wiki/python) client illustrates a hybrid query:

```python
import weaviate
from weaviate.classes.query import HybridFusion

client = weaviate.connect_to_local()
articles = client.collections.get("Article")

results = articles.query.hybrid(
    query="vector databases for RAG",
    alpha=0.75,
    fusion_type=HybridFusion.RELATIVE_SCORE,
    limit=5,
)

for obj in results.objects:
    print(obj.properties["title"], obj.metadata.score)

client.close()
```

### generative search (RAG)

Weaviate includes built-in generative search capabilities, allowing users to perform retrieval-augmented generation directly within the database. After retrieving relevant objects through vector or hybrid search, Weaviate can pass those results to a configured language model (such as [OpenAI](https://aiwiki.ai/wiki/openai)'s [GPT-4](https://aiwiki.ai/wiki/gpt-4), [Anthropic](https://aiwiki.ai/wiki/anthropic)'s [Claude](https://aiwiki.ai/wiki/claude), or [Cohere](https://aiwiki.ai/wiki/cohere)'s models) to generate answers, summaries, or transformations. This eliminates the need for a separate orchestration layer for basic RAG use cases [30].

Generative search supports two modes:

- **Single-prompt**: A prompt is applied to each individual search result. For example, summarizing each retrieved document.
- **Grouped-task**: All search results are passed together to the model in a single prompt. For example, generating a comprehensive answer that synthesizes information from multiple retrieved documents.

### reranking

Integrated reranking modules let users apply a second-pass ranking model after the initial retrieval step. Reranking models score each retrieved result against the original query using a cross-encoder, which typically produces more accurate relevance judgments than the initial bi-encoder similarity search.

### named vectors

Weaviate supports multiple named vectors per object, allowing a single object to have separate embeddings for different properties or different embedding models. For example, a product listing might have one vector for its title (embedded with a lightweight model) and another for its description (embedded with a more powerful model). Queries can target specific named vectors, enabling flexible multi-modal and multi-representation search strategies.

### authentication, RBAC, and security

Weaviate supports API-key, OIDC, and anonymous authentication modes, configured via environment variables on each node. From the 1.29/1.30 release series, the database includes a built-in role-based access control (RBAC) system, with predefined roles for root and viewer plus user-defined roles that pin down permissions at the level of individual collections, tenants, and operations [36].

From version 1.34, observability capabilities expanded with more than 30 new monitoring metrics, covering LSM bucket reads and writes, write-ahead log recovery, memtable flushing, and asynchronous replication. These metrics are exposed in Prometheus format and feed into Weaviate Cloud's standard monitoring dashboards [37].

## How can you deploy Weaviate?

Weaviate offers several ways to run the database, from fully self-managed to fully hosted. The core engine is identical across deployment modes [38][39].

| Deployment | Operator | Notes |
|-----------|----------|-------|
| Self-hosted (Docker) | User | Single-node or small clusters; ideal for development |
| Self-hosted ([Kubernetes](https://aiwiki.ai/wiki/kubernetes)) | User | Helm chart; the recommended path for production self-hosting |
| Embedded Weaviate | User | Library mode that starts a local Weaviate process from inside Python or Node.js scripts |
| Weaviate Shared Cloud (formerly Serverless) | Weaviate | Multi-tenant shared cloud, billed by usage |
| Weaviate Dedicated Cloud (formerly Enterprise Cloud) | Weaviate | Dedicated single-tenant clusters with SLA, HIPAA on AWS |
| BYOC (Bring Your Own Cloud) | Joint | Database runs in customer's VPC; Weaviate manages the control plane |
| AWS Marketplace | User or Joint | Container deployment inside customer AWS account |

Weaviate restructured its pricing in October 2025, replacing earlier per-dimension billing with three usage-based dimensions (data, performance, and AI features) plus a $45/month minimum to cover baseline cluster costs. As of November 2026, Weaviate Cloud's published plans are Free, Flex, and Premium [60].

| Plan | Starting price | Description |
|------|----------------|-------------|
| Free | $0 | Always-free managed cluster for exploring Weaviate (earlier the free tier was a 14-day sandbox) |
| Flex | $45/month minimum | Pay-as-you-go shared cloud cluster, no commitment |
| Premium | Prepaid contract (third-party guides cited a $400/month minimum) | Shared or dedicated deployment, higher SLA, lower per-unit rates |
| Enterprise / Dedicated | Custom | Single-tenant clusters with HIPAA and other enterprise options |

As described on Weaviate's former BYOC page, the BYOC offering was targeted at enterprises with data-residency, regulatory, or networking constraints. The cluster runs inside the customer's AWS, GCP, or Azure VPC on managed Kubernetes, while Weaviate handles application-level security, configuration, upgrades, patches, and 24/7 monitoring. This design separates the control plane (Weaviate's responsibility) from the data plane (customer's environment) [38].

Weaviate Cloud also runs HIPAA-eligible Enterprise Cloud workloads on AWS, with parallel work in progress for Azure and GCP. The same engine powers integrations with the [AWS Marketplace](https://aiwiki.ai/wiki/aws_marketplace), where users can deploy Weaviate as a containerized cluster inside their AWS tenant.

## Weaviate Embeddings

Weaviate Embeddings, launched in December 2024, is a managed embedding service that runs inside Weaviate Cloud. The service offers GPU-backed inference for both open-source and proprietary models, removing the need for users to call external APIs or operate their own embedding infrastructure [41][42].

The service launched in preview with Snowflake's open-source Arctic-Embed model. As of November 2026 it offers two [Snowflake Arctic](https://aiwiki.ai/wiki/snowflake_arctic) text models, snowflake-arctic-embed-m-v1.5 (English, best for texts under 512 tokens) and snowflake-arctic-embed-l-v2.0 (multilingual, up to 8192 tokens), plus the multimodal ModernVBERT/colmodernvbert model for document-image retrieval [42][61]. Pricing is consumption-based, and the service has no hard cap on embeddings per second, making it suitable for production-scale ingestion. Additional models and modalities have been added on a rolling basis since 2025 [41][42].

## Weaviate Agents

In March 2025, Weaviate introduced a new product line called Weaviate Agents: pre-built agentic services that ship with Weaviate Cloud. Three agents were released, but only the Query Agent reached general availability; by mid-2026 Weaviate had sunset the Transformation and Personalization agents in favor of the Query Agent and its Engram memory service [43][44][62][63].

| Agent | First preview | Status | Purpose |
|-------|---------------|--------|---------|
| Query Agent | March 2025 | GA September 2025 | Natural-language access to Weaviate collections, including multi-stage queries and aggregations |
| Transformation Agent | March 2025 | Sunset (2026) | Uses an LLM to rewrite, enrich, or augment objects already in a collection based on natural-language instructions |
| Personalization Agent | April 2025 | Sunset (2026) | Re-ranks results for a user based on a stored persona and prior interactions |

The Query Agent reads a Weaviate cluster's schema, decides which collections to query, generates the appropriate vector or aggregation query, and returns a natural-language answer with citations to the underlying objects. It became generally available in September 2025 [45].

In February 2026, Weaviate also announced Agent Skills, a developer toolkit that helps [coding agent](https://aiwiki.ai/wiki/coding_agent)s (such as those built on the [Model Context Protocol](https://aiwiki.ai/wiki/model_context_protocol)) understand Weaviate APIs and write correct queries against them [46].

## Verba

Verba was Weaviate's open-source RAG reference application. The repository, hosted on GitHub at weaviate/Verba, provides a modular [chatbot](https://aiwiki.ai/wiki/chatbot) interface that ingests documents from sources such as PDFs (via UnstructuredIO), GitHub repositories, and Markdown files, then answers questions using Weaviate as the retrieval back-end and a configurable LLM as the generation step. The project accumulated about 7,700 GitHub stars and was used as a starting point for self-hosted RAG demos, but Weaviate discontinued it and archived the repository on 8 June 2026; it no longer receives updates, bug fixes, or security patches [47][48].

Verba supports four deployment modes: a fully embedded mode using Weaviate Embedded, a Docker mode, a connection to an existing Weaviate Cloud cluster, and a custom URL mode pointing at any reachable Weaviate instance. The default model stack is intentionally swappable: SentenceTransformers for embeddings, OpenAI or [Ollama](https://aiwiki.ai/wiki/ollama) for generation, and either Weaviate Cloud or local Weaviate for storage.

## release history

Weaviate ships approximately one minor release every one to two months. The table below highlights selected releases that introduced major capabilities. Weaviate's stated support policy is to maintain bug fixes and security patches for the latest three minor versions [9][20][22][23][37][64].

| Version | Release date | Highlights |
|---------|-------------|-----------|
| 1.0.0 | January 14, 2021 | Initial GA, modular API, support for importing pre-computed vectors |
| 1.2.0 | 2021 | text2vec-transformers module |
| 1.5.0 | 2021 | LSM-tree storage, auto-schema |
| 1.8.0 | 2021 | Horizontal scalability, sharding, pagination |
| 1.17.0 | December 2022 | Replication, [hybrid search](https://aiwiki.ai/wiki/hybrid_search) |
| 1.18.0 | March 2023 | Bitmap indexing for faster filtering, HNSW-PQ, cursor API, tunable consistency |
| 1.19.0 | 2023 | gRPC interface (initial), generative-cohere |
| 1.20.0 | July 2023 | Multi-tenancy, rerankers, PQ GA |
| 1.22.0 | October 2023 | Async indexing, nested object support, expanded gRPC API support |
| 1.23.0 | December 2023 | Flat index with binary quantization, AutoPQ, generative-anyscale; gRPC search GA in v1.23.7 |
| 1.24.0 | February 2024 | Named vectors (multiple vectors per collection), HNSW binary quantization, Japanese and Chinese tokenizers |
| 1.25.0 | 2024 | Raft consensus for cluster metadata |
| 1.26.0 | July 2024 | Tenant offloading, multi-target vector search, scalar quantization, async replication |
| 1.27.0 | October 2024 | ACORN-based filtered HNSW search, multi-target vector improvements |
| 1.28.0 | December 2024 | RBAC preview, Weaviate Embeddings (Snowflake Arctic), experimental BlockMax WAND |
| 1.29.0 | February 2025 | RBAC GA, async replication GA, multi-vector ([ColBERT](https://aiwiki.ai/wiki/colbert)-style) embeddings, NVIDIA modules |
| 1.30.0 | April 2025 | Runtime configuration, dynamic user management, BlockMax WAND BM25 |
| 1.31.0 | June 2025 | MUVERA multi-vector encoding, HNSW snapshots |
| 1.32.0 | July 2025 | Collection aliases, Rotational Quantization (RQ), shard replica movement GA |
| 1.33.0 | October 2025 | 1-bit RQ preview, ContainsNone and Not filter operators |
| 1.34.0 | November 2025 | Flat-index plus RQ, expanded observability metrics, [Contextual AI](https://aiwiki.ai/wiki/contextual_ai) integration |
| 1.35.0 | December 2025 | Object time-to-live (TTL) preview, zstd compression, flat-index RQ, multimodal Weaviate Embeddings |
| 1.36.0 | February 2026 | HFresh vector index (preview); server-side batching and object TTL GA |
| 1.37.0 | April 2026 | Built-in [MCP server](https://aiwiki.ai/wiki/mcp_server) (preview), extensible tokenizers, incremental backups |
| 1.38.0 | June 2026 | HFresh disk-based vector index and built-in MCP server GA, Boost API preview |
| 1.39.0 | August 2026 | Boost API and MMR diversity selection GA, 4-bit RQ preview |
| 1.40.0 | October 2026 | 4-bit RQ GA, PathSeer filtering, multi-vector embeddings on HFresh |

## performance benchmarks

Weaviate publishes benchmark results for its search modes. In September 2025, the team benchmarked the Query Agent's Search Mode against standard hybrid search across 12 [information retrieval](https://aiwiki.ai/wiki/information_retrieval) datasets from BEIR, LoTTe, and BRIGHT, as well as WixQA and EnronQA.

Key findings from these benchmarks include:

| Metric | Search Mode vs hybrid search | Notes |
|------------|---------------------|-------|
| Success@1 | +17% (mean across benchmarks) | Largest gain; measures whether the top result is relevant |
| Recall@5 | +11% (mean across benchmarks) | |
| Per-benchmark range | +5% (BEIR SciFact, BRIGHT Economics) to +24% (BRIGHT Biology) | Search Mode adds query expansion, query decomposition, schema introspection, and reranking on top of hybrid retrieval [49] |

Throughput and latency depend heavily on dataset size, dimensionality, and hardware configuration. For ingestion, the move from REST to gRPC roughly halved the time to insert the 1 million records of the DBPedia benchmark dataset, from over 42 minutes to about 23 minutes on the same hardware [35].

## How does Weaviate differ from other vector databases?

Weaviate is most often compared with [Pinecone](https://aiwiki.ai/wiki/pinecone), [Qdrant](https://aiwiki.ai/wiki/qdrant), [Chroma](https://aiwiki.ai/wiki/chroma), and [Milvus](https://aiwiki.ai/wiki/milvus). The competitive picture is shaped by license model (open source versus proprietary), deployment options, hybrid search capabilities, and the level of integration with embedding and generative providers [50][51].

### versus Pinecone

| Feature | Weaviate | Pinecone |
|---------|----------|----------|
| Source model | Open-source ([BSD-3-Clause](https://aiwiki.ai/wiki/bsd_3_clause_license)) | Closed-source, managed SaaS |
| Self-hosting | Yes (Docker, [Kubernetes](https://aiwiki.ai/wiki/kubernetes), BYOC) | No (cloud-only, or BYOC on Dedicated plan) |
| [Hybrid search](https://aiwiki.ai/wiki/hybrid_search) | Native BM25 + vector in one API call | Requires separate [sparse vector](https://aiwiki.ai/wiki/sparse_vector) index |
| API style | REST, gRPC, GraphQL | REST, gRPC |
| Auto-vectorization | Yes, via modules and Weaviate Embeddings | Yes, via Pinecone Inference |
| Multi-tenancy | Native, one shard per tenant | Via namespaces |
| Generative search | Built-in RAG modules | Via Pinecone Assistant |
| Primary language | Go | Rust, with Go for the Kubernetes control plane (closed source) [65] |

Pinecone tends to win on setup simplicity and consistent low-latency performance for pure vector search workloads. Weaviate tends to win on flexibility, hybrid search quality, and cost control through self-hosting options. For workloads where hybrid search is central to the application, Weaviate's native BM25 + vector fusion in a single API call is more efficient than Pinecone's approach of maintaining separate sparse and dense indexes [50].

A published Pinecone customer benchmark on Dedicated Read Nodes reported 5,700 QPS at a P99 latency of 60ms on 1.4 billion vectors; the cited comparison gives no equivalent Weaviate throughput figure. Direct comparisons are difficult since the hardware, dataset sizes, and query patterns differ across benchmarks [50].

### versus Qdrant

| Feature | Weaviate | [Qdrant](https://aiwiki.ai/wiki/qdrant) |
|---------|----------|--------|
| Source model | Open-source (BSD-3-Clause) | Open-source (Apache 2.0) |
| Primary language | Go | Rust |
| [Hybrid search](https://aiwiki.ai/wiki/hybrid_search) | Native (BM25 + vector) | Native (sparse + dense) |
| GraphQL | Yes (deprecated; Weaviate Cloud switch-off set for May 1, 2027) | No |
| Modular embedding/generation | Extensive module catalog | Smaller, focused integration list |
| Sharding model | One shard per tenant or hash-based | Hash-based |
| Filtering optimization | Inverted index plus dynamic filter strategy | Custom filterable HNSW |

Qdrant emphasizes raw performance, especially around payload-heavy filtered search, and is often praised for its memory footprint due to its Rust implementation. Weaviate emphasizes a richer feature surface (modules, agents, Weaviate Embeddings, generative search). Both are viable open-source options at production scale, and many teams pick between them based on whether they prefer Go or Rust on their infrastructure team [50][51].

### versus Milvus

Milvus, maintained by Zilliz under the Apache 2.0 license, is another open-source vector database focused on raw performance and a broad menu of index types (HNSW, IVF, DiskANN, GPU indexes). Compared with Milvus, Weaviate ships with a thinner index menu (HNSW, flat, dynamic, and the disk-based HFresh index added in 2026) but a richer module catalog and integrated generative search. Milvus tends to perform better on extremely large pure-vector workloads with custom index choices, while Weaviate tends to be easier to integrate with embedding and LLM providers out of the box [51].

### versus Chroma and pgvector

Chroma is a developer-friendly embedding database aimed mostly at prototyping; it does not target the same scale or feature set as Weaviate. [pgvector](https://aiwiki.ai/wiki/pgvector) is a [PostgreSQL](https://aiwiki.ai/wiki/postgresql) extension that adds vector indexing to an existing relational database; it is a strong choice when an application already uses PostgreSQL and needs only modest vector-search functionality. Weaviate occupies a middle ground: more capable than Chroma, more specialized than pgvector, and open-source unlike Pinecone [51].

## Who uses Weaviate?

Weaviate publishes case studies on its website covering production deployments. Notable users include [5][33][52][53]:

| Company | Use case | Notes |
|---------|---------|-------|
| [Stack Overflow](https://aiwiki.ai/wiki/stack_overflow) | [Hybrid search](https://aiwiki.ai/wiki/hybrid_search) for OverflowAI features on Stack Overflow's question and answer corpus | Required an open-source [vector database](https://aiwiki.ai/wiki/vector_database) that could run on existing Azure infrastructure |
| [Instabase](https://aiwiki.ai/wiki/instabase) | Document intelligence for mortgage, insurance, and other regulated industries | Processes more than 500,000 documents per day across more than 50,000 tenants in a single Weaviate cluster, ingesting more than 450 distinct data types |
| Stack AI | Enterprise no-code AI platform with retrieval-augmented assistants | Highlighted in Weaviate's case study library |
| Morningstar | Financial research and analyst tooling | Cited as a customer in Weaviate's commercial materials |
| Cisco | Internal knowledge and search applications | Cited as a customer |
| NetApp | Data infrastructure for [enterprise AI](https://aiwiki.ai/wiki/enterprise_ai) workloads | Cited as a customer in joint AWS materials |
| MetaBuddy | AI coaching platform | Reported a 60 percent reduction in trainer analysis time and triple the user engagement after migrating to Weaviate |

In December 2025, AWS named Weaviate its Rising Star Technology Partner of the Year for the Benelux region in its regional 2025 EMEA Partners of the Year awards, citing its use of Amazon Bedrock and SageMaker for generative [AI infrastructure](https://aiwiki.ai/wiki/ai_infrastructure) and search [54].

## ecosystem and community

The Weaviate open-source project had close to 17,000 GitHub stars as of November 2026, and the company reports more than 20 million open-source downloads and thousands of customers; in early 2026 it also cited a community of more than 50,000 AI builders [4][5].

Weaviate provides official client libraries for Python, [JavaScript](https://aiwiki.ai/wiki/javascript)/[TypeScript](https://aiwiki.ai/wiki/typescript), Go, Java, and C#/.NET. The Python client is the most popular, with active development tracked in its changelog [55].

| Client library | Package | Status |
|---------------|---------|--------|
| Python | `weaviate-client` (PyPI) | Most popular; supports sync and async operations on top of gRPC |
| [JavaScript](https://aiwiki.ai/wiki/javascript)/[TypeScript](https://aiwiki.ai/wiki/typescript) | `weaviate-client` (npm) | Used in Node.js and browser applications |
| Go | `weaviate-go-client` | Native Go client for Go applications |
| Java | `io.weaviate:client` (Maven) | Java client for JVM-based applications |
| C#/.NET | `Weaviate.Client` (NuGet) | Official client announced with Weaviate 1.34 in November 2025 |

Integrations exist with [LangChain](https://aiwiki.ai/wiki/langchain), [LlamaIndex](https://aiwiki.ai/wiki/llamaindex), [Semantic Kernel](https://aiwiki.ai/wiki/semantic_kernel), [Haystack](https://aiwiki.ai/wiki/haystack), [Dify](https://aiwiki.ai/wiki/dify), Embedchain, and other AI orchestration frameworks. These integrations allow developers to use Weaviate as the vector store component in larger [machine learning](https://aiwiki.ai/wiki/machine_learning) pipelines.

The Weaviate community includes an active forum, a Slack workspace with thousands of members, and regular community calls. Engagement levels are high, with the company reporting more than 200 messages per week across its open Discourse forum and GitHub repositories. The Weaviate Hero program recognizes members who contribute through speaking, blogging, code, and community moderation [56][57].

The company also runs Weaviate Academy, a free educational platform with structured courses on using the database, from zero-to-MVP guides to advanced performance optimization tutorials, and the Weaviate World Tour series of in-person workshops, conferences, and hackathons across Europe and North America [29][57].

## current state (2025-2026)

By May 2026, Weaviate continues to develop as both an open-source project and a commercial cloud service. The company has focused on several areas: improving multi-tenancy efficiency with features like tenant offloading to S3, GPU-accelerated index building through the NVIDIA partnership, native multi-vector embeddings with MUVERA, more efficient quantization through RQ, and agentic services centered on the Query Agent (the Transformation and Personalization agents were later sunset) [22][24][32][43][62][63].

The vector database market has become increasingly competitive, with Weaviate, Qdrant, Milvus, Chroma, and Pinecone all vying for developer adoption, and incumbents such as Oracle, [Microsoft Azure](https://aiwiki.ai/wiki/azure) (with Azure [AI Search](https://aiwiki.ai/wiki/ai_search)), MongoDB, and PostgreSQL (via pgvector) adding vector capabilities to their existing databases. Weaviate differentiates itself through its combination of open-source availability, native hybrid search, automatic vectorization modules, and its multi-protocol API (although its GraphQL API is now deprecated) [34]. The open-core business model (free self-hosted, paid cloud) gives it flexibility that purely managed competitors like Pinecone cannot match, while the managed cloud option reduces friction for teams that do not want to operate their own infrastructure [50][51].

Weaviate's stated direction for 2026 emphasizes deeper agentic capabilities, including reasoning workflows, broader multimodal support, [model evaluation](https://aiwiki.ai/wiki/model_evaluation) tools, and shared memory across agents. CEO Bob van Luijt has singled out "generative feedback loops", in which applications prompt the database rather than the model, as one of the developments he is most excited about in AI-native databases [58].

Weaviate's focus on developer experience, with features like built-in generative search, automatic vectorization, integrated agents, and BYOC deployments, reflects a broader trend in the vector database space toward reducing the amount of glue code required to build AI applications. Rather than forcing developers to stitch together separate embedding services, vector stores, and LLM orchestration layers, Weaviate aims to handle much of this within the database itself.

## references

1. [SeMI Technologies - Crunchbase Company Profile and Funding](https://www.crunchbase.com/organization/semi-technologies/) - Crunchbase
2. [SeMI Technologies becomes Weaviate](https://www.prnewswire.com/news-releases/semi-technologies-becomes-weaviate-301724752.html) - PR Newswire, 18 January 2023
3. [The History of Weaviate](https://weaviate.io/blog/history-of-weaviate) - Weaviate Blog, January 2021
4. [weaviate/weaviate on GitHub](https://github.com/weaviate/weaviate) - GitHub
5. [The AI database developers love](https://weaviate.io/) - Weaviate
6. [The History of the Weaviate Vector Search Engine](https://medium.com/semi-technologies/the-history-of-the-weaviate-vector-search-engine-17a274f36178) - Medium / SeMI Technologies
7. [Etienne Dilocker - Co-founder and CTO](https://careers.weaviate.io/people/1332062-etienne-dilocker) - Weaviate Careers
8. [Etienne Dilocker on GitHub](https://github.com/etiennedi) - GitHub
9. [Release Notes](https://docs.weaviate.io/weaviate/release-notes) - Weaviate Documentation
10. [Weaviate - Crunchbase Company Profile and Funding](https://www.crunchbase.com/organization/weaviate) - Crunchbase
11. [Weaviate Raises $50 Million Series B Funding](https://www.prnewswire.com/news-releases/weaviate-raises-50-million-series-b-funding-to-meet-soaring-demand-for-ai-native-vector-database-technology-301803296.html) - PR Newswire, 21 April 2023
12. [SeMI Technologies $16M Series A Round Highlights a New Wave of AI-first Database Tech](https://www.prnewswire.com/news-releases/semi-technologies-16m-series-a-round-highlights-a-new-wave-of-ai-first-database-tech-301486766.html) - PR Newswire, February 2022
13. [SeMI Technologies' search engine opens up new ways to query your data](https://techcrunch.com/2022/02/22/semi-technologies-search-engine-data/) - TechCrunch, 22 February 2022
14. [Index Ventures Leads $50 Million Investment in AI Startup Weaviate](https://www.theinformation.com/articles/index-ventures-leads-50-million-investment-in-ai-startup-weaviate) - The Information, April 2023
15. [How Weaviate hit $12.3M revenue with a 104 person team in 2024](https://getlatka.com/companies/weaviate) - GetLatka
16. [About Us](https://weaviate.io/company/about-us) - Weaviate
17. [Replication Architecture](https://docs.weaviate.io/weaviate/concepts/replication-architecture) - Weaviate Documentation
18. [Weaviate 1.25 Release](https://weaviate.io/blog/weaviate-1-25-release) - Weaviate Blog
19. [Weaviate Vector Index documentation](https://docs.weaviate.io/weaviate/concepts/vector-index) - Weaviate Documentation
20. [Weaviate 1.31 Release](https://weaviate.io/blog/weaviate-1-31-release) - Weaviate Blog
21. [Compression (Vector Quantization)](https://docs.weaviate.io/weaviate/concepts/vector-quantization) - Weaviate Documentation
22. [Weaviate 1.32 Release](https://weaviate.io/blog/weaviate-1-32-release) - Weaviate Blog
23. [Weaviate 1.33 Release](https://weaviate.io/blog/weaviate-1-33-release) - Weaviate Blog
24. [Unleashing AI Factories: Weaviate and NVIDIA Turbocharge Vector Search](https://weaviate.io/blog/nvidia-and-weaviate) - Weaviate Blog
25. [Hybrid Search](https://docs.weaviate.io/weaviate/search/hybrid) - Weaviate Documentation
26. [Hybrid Search Explained](https://weaviate.io/blog/hybrid-search-explained) - Weaviate Blog
27. [Weaviate 1.30 Release: Runtime config, BlockMax WAND BM25](https://github.com/weaviate/weaviate/releases/tag/v1.30.0) - GitHub Releases
28. [Weaviate GraphQL: Python Hybrid Search Implementations 2026](https://www.johal.in/weaviate-graphql-python-hybrid-search-implementations-2026/) - Johal.in
29. [Weaviate Modules documentation](https://docs.weaviate.io/weaviate/modules) - Weaviate Documentation
30. [Generative Search documentation](https://docs.weaviate.io/weaviate/search/generative) - Weaviate Documentation
31. [How to define a schema](https://docs.weaviate.io/academy/py/zero_to_mvp/schema_and_imports/schema) - Weaviate Academy
32. [Rethinking Vector Search at Scale: Weaviate's Multi-Tenancy](https://weaviate.io/blog/weaviate-multi-tenancy-architecture-explained) - Weaviate Blog
33. [Case Study - Instabase](https://weaviate.io/case-studies/instabase) - Weaviate
34. [GraphQL API documentation](https://docs.weaviate.io/weaviate/api/graphql) - Weaviate Documentation
35. [gRPC-Driven Performance Improvements in Weaviate](https://weaviate.io/blog/grpc-performance-improvements) - Weaviate Blog
36. [Setting up RBAC in Weaviate](https://docs.weaviate.io/weaviate/tutorials/rbac) - Weaviate Documentation
37. [Weaviate 1.34 Release](https://weaviate.io/blog/weaviate-1-34-release) - Weaviate Blog
38. [BYOC - Bring Your Own Cloud](https://weaviate.io/services/byoc) - Weaviate
39. [Weaviate Cloud documentation](https://docs.weaviate.io/cloud) - Weaviate Documentation
40. [Weaviate Pricing in 2026](https://particula.tech/blog/weaviate-pricing-free-tier-guide) - Particula Tech
41. [Introducing Weaviate Embeddings](https://weaviate.io/blog/introducing-weaviate-embeddings) - Weaviate Blog
42. [Weaviate Launches Flexible Embedding Service for AI Development](https://www.globenewswire.com/news-release/2024/12/03/2990699/0/en/Weaviate-Launches-Flexible-Embedding-Service-for-AI-Development.html) - GlobeNewswire, 3 December 2024
43. [Welcome to the Next Era of Data and AI: Meet Weaviate Agents](https://weaviate.io/blog/weaviate-agents) - Weaviate Blog
44. [Weaviate Goes Full Stack With Launch of Weaviate Agents for AI Development](https://www.globenewswire.com/news-release/2025/03/04/3036570/0/en/Weaviate-Goes-Full-Stack-With-Launch-of-Weaviate-Agents-for-AI-Development.html) - GlobeNewswire, 4 March 2025
45. [Accelerating Data Workflows with Query Agent, now GA](https://weaviate.io/blog/query-agent-generally-available) - Weaviate Blog
46. [Weaviate Launches Agent Skills to Empower AI Coding Agents](https://www.globenewswire.com/news-release/2026/02/21/3242244/0/en/Weaviate-Launches-Agent-Skills-to-Empower-AI-Coding-Agents.html) - GlobeNewswire, 21 February 2026
47. [weaviate/Verba on GitHub](https://github.com/weaviate/Verba) - GitHub
48. [Verba: Building an Open Source, Modular RAG Application](https://weaviate.io/blog/verba-open-source-rag-app) - Weaviate Blog
49. [Search Mode Benchmarking](https://weaviate.io/blog/search-mode-benchmarking) - Weaviate Blog
50. [Pinecone vs Weaviate 2026: Engineered Decision Guide](https://ranksquire.com/2026/03/02/pinecone-vs-weaviate/) - RankSquire
51. [Best Vector Databases in 2026: A Complete Comparison Guide](https://www.firecrawl.dev/blog/best-vector-databases) - Firecrawl
52. [From prototype to production: Vector databases in generative AI applications](https://stackoverflow.blog/2023/10/09/from-prototype-to-production-vector-databases-in-generative-ai-applications/) - Stack Overflow Blog
53. [Case Studies](https://weaviate.io/case-studies) - Weaviate
54. [Announcing the Regional 2025 AWS Partners of the Year for Europe, Middle East, and Africa](https://aws.amazon.com/blogs/apn/announcing-the-regional-2025-aws-partners-of-the-year-for-europe-middle-east-and-africa/) - AWS Partner Network Blog
55. [Weaviate Python Client Changelog](https://weaviate-python-client.readthedocs.io/en/stable/changelog.html) - Read the Docs
56. [Weaviate Hero](https://weaviate.io/blog/weaviate-community-hero) - Weaviate Blog
57. [Weaviate community](https://weaviate.io/community) - Weaviate
58. [Bob van Luijt on AI-Native Apps, Open Source, and Innovation](https://www.analyticsvidhya.com/blog/2024/11/bob-van-luijt/) - Analytics Vidhya
59. [Weaviate in 2025: Reliable Foundations for Agentic Systems](https://weaviate.io/blog/weaviate-in-2025) - Weaviate Blog
60. [Weaviate Pricing](https://weaviate.io/pricing) - Weaviate
61. [Weaviate Embeddings: model choice](https://docs.weaviate.io/cloud/embeddings/models) - Weaviate Documentation
62. [Weaviate Transformation Agent (sunset)](https://weaviate.io/product/transformation-agent.md) - Weaviate, updated 26 June 2026
63. [Weaviate Personalization Agent (sunset)](https://weaviate.io/product/personalization-agent.md) - Weaviate, updated 26 June 2026
64. [Release posts](https://weaviate.io/blog/tags/release) - Weaviate Blog
65. [Inside the Pinecone](https://www.pinecone.io/blog/inside-the-pinecone/) - Pinecone Blog