Weaviate Cloud Shared

What do you like best about the product?

What I like most about Weaviate is how easy it is to build semantic search and RAG applications around it. The vector search is fast and flexible, and I like that it supports structured metadata along with embeddings, so I can narrow down results without making the retrieval logic overly complicated.

What do you dislike about the product?

The main thing I find challenging with Weaviate is that there can be a learning curve when setting up more advanced configurations, especially around schemas, indexing, and tuning retrieval. It also takes some time to understand how to get the best results from the vector search instead of relying on the default setup. For smaller projects, it can sometimes feel like more infrastructure than I actually need.

What problems is the product solving and how is that benefiting you?

Weaviate mainly helps with the search and retrieval side of AI applications. I use it to store and search vectorized data based on semantic similarity, which is much more useful than relying only on keyword matching. It makes things like RAG and knowledge-base search easier to build, and helps return more relevant context to the application without having to manually manage the retrieval layer.

What do you like best about the product?

Its seamless hybrid search combining BM25 and vector search and native module integrations. It makes setting up, scaling, and retrieving data for production-grade RAG applications remarkably fast and easy.

What do you dislike about the product?

The initial setup and GraphQL/API query structure have a steep learning curve for new teams. While the documentation is improving, debugging complex filter queries and schema errors can still be time-consuming.

What problems is the product solving and how is that benefiting you?

Traditional SQL and keyword-based databases often fall short when queries include synonyms, misspellings, or more conceptual matches. Weaviate, on the other hand, focuses on intent and context instead of relying on exact string matching.

What do you like best about the product?

What I like most about Weaviate is how straightforward it makes working with vector search and embeddings. The setup feels intuitive, and it’s easy to store, search, and retrieve relevant data for AI applications without adding unnecessary complexity to my workflow.

What do you dislike about the product?

What I dislike about Weaviate is that some of its advanced features and configuration options can feel a bit overwhelming at first. It can take a while to understand the different settings and to get everything configured exactly the way you want.

What problems is the product solving and how is that benefiting you?

Weaviate simplifies how we store and search vector data for AI applications. It makes it easier to retrieve relevant information quickly, which cuts down on manual searching and keeps our AI workflows more efficient, organized, and easier to manage.

What do you like best about the product?

It natively supports hybrid search, allowing developers to combine dense vector search (for semantic meaning) with traditional keyword search (BM25). This is widely considered the gold standard for retrieving highly accurate context in RAG applications.

What do you dislike about the product?

Instead of using standard SQL, Weaviate's primary query language is a custom implementation of GraphQL. While powerful for complex graph relationships, developers accustomed to traditional relational databases often report a steep learning curve.

What problems is the product solving and how is that benefiting you?

Beyond just storing isolated vectors, Weaviate allows you to define cross-references and relationships between data objects (similar to a graph database), making it easier to represent highly complex, interconnected enterprise data.

What do you like best about the product?

What I like best about Weaviate is how easy it makes working with vector search at scale. The setup is straightforward, the performance is solid, and it handles embeddings without forcing you into complicated configurations. It feels like a tool built to get real semantic search running quickly.

What do you dislike about the product?

The only downside is that some of the more advanced configuration options feel a bit scattered. When you’re trying to fine‑tune performance or adjust hybrid search behavior, it takes a bit of digging through docs and settings. It’s powerful, but not always as straightforward as the basics.

What problems is the product solving and how is that benefiting you?

Weaviate solves the problem of building fast, reliable semantic search without having to manage a lot of custom infrastructure. Instead of stitching together your own vector store, index logic, and retrieval pipeline, it handles all of that cleanly. The benefit is quicker development, better search accuracy, and less time wasted maintaining your own search stack.

What do you like best about the product?

What stands out most about weaviate is its native hybrid search and multi-tenancy capabilities, which make combining BM25 keyword matching with dense vector search effortless. It allows us to deliver ultra-fast semantic video discovery and personalized viewer recommendations across huge OTT metadata catalogs.

What do you dislike about the product?

Setting up self hosted clusters and tuning HNSW index memory parmeters for large scale video catalogs requires significant infrastructure overhead. Additionally, breaking SDK changes between major version updates can require unexpected maintenance for our automated OTT metadata ingestion pipelines.

What problems is the product solving and how is that benefiting you?

Weaviate solves the challenge of organizing and searching millions of unstructured video transcripts, viewer logs, and show metadata in real time. It benefits our OTT platform my powering instant, highly accurate semantic search and personalized content recommendations, which keeps subscribers engaged longer.

What do you like best about the product?

Weaviate offers a clean and developer-friendly interface with an intuitive cloud console. Most administration is API- or SDK-driven rather than GUI-based.

This tool offers extensive integrations with LLMs, embedding models, AI frameworks, cloud platforms, and programming languages.

This tool provides high-performance vector search with low-latency retrieval, horizontal scalability, and support for billions of vectors.

Open-source edition offers excellent value. Managed cloud pricing is competitive, providing strong ROI for enterprise AI search and RAG applications.

This tool is well-documented with tutorials, SDKs, community support, and enterprise support options. Some learning is required for vector databases and AI concepts.

Weaviate is purpose-built for AI-driven applications, delivering advanced capabilities such as semantic search, hybrid search, vector-based retrieval, and Retrieval-Augmented Generation (RAG) to enable intelligent and context-aware information discovery.

What do you dislike about the product?

Weaviate is a retrieval platform rather than a generative AI model. It relies on external LLMs (such as GPT, Claude, or Gemini) to generate natural language responses after retrieving relevant information.

What problems is the product solving and how is that benefiting you?

This tool is helping my team build an AI-powered search enterprise knowledge solution, particularly when flexibility, self-hosting, and open-source capabilities are important factors.

What do you like best about the product?

What I like best about Weaviate is its powerful vector search capabilities combined with a flexible, developer-friendly architecture for building AI-powered applications. The platform makes it easy to store, index, and retrieve embeddings while supporting hybrid search, semantic search, and integrations with popular AI frameworks. I also appreciate its scalability, intuitive API, and open-source foundation, which provide both flexibility and transparency for production deployments. Overall, Weaviate simplifies the development of intelligent search and retrieval systems, accelerates AI application development, and delivers excellent performance for large-scale vector data.

What do you dislike about the product?

One area where Weaviate could improve is offering more advanced monitoring, performance analytics, and cluster management tools for large-scale production deployments. While the platform is highly flexible and feature-rich, optimizing indexes and tuning retrieval performance for complex workloads can require additional experimentation. I'd also like to see broader integrations with more developer and observability tools, richer documentation for advanced use cases, and more granular cost and resource management capabilities. Overall, the experience has been very positive, but enhanced observability, deeper operational tooling, and expanded enterprise features would make Weaviate even more valuable.

What problems is the product solving and how is that benefiting you?

Weaviate solves the challenge of storing, indexing, and retrieving vector embeddings for AI applications, making semantic search and retrieval-augmented generation (RAG) significantly easier to implement at scale. Instead of building and managing custom vector search infrastructure, it provides a scalable database with hybrid search, filtering, and AI integrations in a single platform. This has simplified the development of intelligent search systems, improved the relevance of AI-powered results, reduced infrastructure complexity, and accelerated the deployment of production-ready AI applications. As a result, it has increased development efficiency, improved search quality, and enabled faster delivery of AI-powered features.

What do you like best about the product?

Weaviate is an excellent vector database for building AI-powered applications that rely on semantic search, retrieval-augmented generation (RAG), and recommendation systems. Its hybrid search features, GraphQL API, automatic vectorization, and scalability—along with seamless integration with popular embedding models and AI frameworks—make it straightforward to develop and deploy production-ready AI solutions.

What do you dislike about the product?

While Weaviate is highly capable, setting up advanced indexing strategies and tuning performance for large-scale deployments still requires a solid level of familiarity with vector databases. The developer experience would be even better with more built-in monitoring, clearer query optimization insights, and a more streamlined approach to cluster management.

What problems is the product solving and how is that benefiting you?

It enables efficient storage and retrieval of vector embeddings, allowing applications to perform semantic search and deliver more relevant AI responses. It also simplifies implementing RAG pipelines, recommendation engines, and intelligent search systems by reducing development time, improving search accuracy, and helping teams build scalable AI applications without having to manage complex retrieval infrastructure.

What do you like best about the product?

I like how easy Weaviate makes it to store and search vector data. It works well for AI applications and delivers fast, relevant search results. The documentation is clear, and the available integrations make it simpler to get started and connect it with other tools.

What do you dislike about the product?

The initial setup can feel a bit confusing, especially if you’re using Weaviate for the first time. Some of the more advanced features take time to fully understand, and it would be helpful if troubleshooting configuration issues were more straightforward. Overall, though, these challenges are manageable once you become familiar with the platform.

What problems is the product solving and how is that benefiting you?

Weaviate helps me store and search large volumes of vector data quickly. It makes it much easier to build AI features like semantic search and RAG without having to create everything from scratch. That saves development time and helps me get more relevant search results with less effort.