# Explorer tool The Explorer tool is a graphical interface for working with the data in a Weaviate Cloud cluster. Browse [collections](../concepts/data.md#collections), examine [objects](../concepts/data.md#data-object-concepts), inspect metadata and vectors, and run keyword, semantic, hybrid, and aggregation searches, all without writing a query. :::callout{intent="info" title="Moving from the Query tool"} The Query tool was removed from the Weaviate Cloud console on **September 14, 2026**. Nothing changes for your clusters. This is console tooling only, so they keep running exactly as they are, with no downtime and nothing you need to do on your end. The Explorer tool covers the everyday Query tool tasks without writing a query: [keyword](#keyword-search), [semantic](#semantic-search), and [hybrid](#hybrid-search) search, [aggregations](#aggregate), [filters](#filter-and-sort), and [inference keys](#inference-keys). For anything beyond that, use a [client library](../client-libraries/index.md) to query your data from your application code. ::: ## Open the Explorer tool The Explorer tool is available for collections that are hosted in Weaviate Cloud. [Embedded content embed](https://app.guideflow.com/embed/dr9vvzmtop) :::accordion{title="Open the Explorer tool step by step"} 1. Open the [Weaviate Cloud console](/go/console?utm_content=cloud). 2. Select a cluster from the list. 3. Select the `Explorer` tool from the left sidebar. 4. Select a collection to see its objects. ::: If you don't see any available clusters, select the `Clusters` option from the left sidebar and follow the steps to [create a new cluster](../manage-clusters/create.md). To review how the collection itself is configured, click the `View collection details` button in the page header. ## Search and explore The `Search & explore` panel sits above the results and has five modes: | Mode | What it does | | :---------- | :-------------------------------------------------------------------- | | `Browse` | Lists the objects in the collection, page by page. | | `Hybrid` | Blends keyword and vector search in a single search. | | `Semantic` | Ranks objects by meaning, from a description or from a vector. | | `Keyword` | Ranks objects by keyword relevance. | | `Aggregate` | Calculates a metric over the collection instead of returning objects. | [Embedded content embed](https://app.guideflow.com/embed/5pvnnvxtwk) ### Browse `Browse` mode lists the objects in the collection. Each object is shown with its: - Unique identifier (UUID) - Properties and their values - Metadata - Vector embeddings Some details are initially collapsed. Click a color-coded property group, such as metadata or vectors, to expand it and view the details. Hover over a property name to see the property type. Vectors are shown initially by name, where [named vectors](../concepts/data.md#multiple-vector-embeddings-named-vectors) are used, and by their number of dimensions. Expand the entry to see part of the vector, or click `copy` to copy the entire vector to your clipboard. Pagination controls at the bottom of the list step through the objects. A dropdown next to them sets the number of objects per page and shows the total number of objects in the collection. The refresh button at the top of the page reloads the list. ### Hybrid search `Hybrid` mode blends keyword and vector search in a single search, so an object can rank highly because it matches your search terms, because it matches your meaning, or both. For each half on its own, see [semantic search](#semantic-search) and [keyword search](#keyword-search). Search with either of: - `Text`: describe what you are looking for. - `Vector`: provide a raw vector to search with. Use the `in:` selector to choose which properties are searched. Under `Advanced options`, the `Keyword ↔ vector balance (alpha)` slider sets how much each half of the search contributes. In the Explorer tool the slider starts at `0.5`, which weights the keyword and vector components equally. See the [alpha parameter](../search/hybrid-search.md#alpha-parameter) for what the value means. If the panel asks for a model provider key, see [inference keys](#inference-keys). For the equivalent query in application code, see [hybrid search](../how-to-query-search/hybrid.md). ### Semantic search `Semantic` mode ranks results by meaning rather than by exact words, so a relevant object can rank highly even if it shares no words with your search. Search with either of: - `Text`: describe what you are looking for. - `Vector`: provide a raw vector to search with. If the panel asks for a model provider key, see [inference keys](#inference-keys). For the equivalent query in application code, see [vector similarity search](../how-to-query-search/similarity.md), and for the underlying idea, see [vector search](../search/vector-search.md). ### Keyword search `Keyword` mode ranks results by [BM25](../search/keyword-search.md) relevance, so the objects that match your search terms most strongly come first. A keyword search reads every property by default. To narrow it, use the `in:` selector to choose which properties are searched. For the equivalent query in application code, see [keyword search](../how-to-query-search/bm25.md). ### Aggregate `Aggregate` mode calculates a metric over the collection instead of returning objects. The controls read as a sentence: `Show of grouped by `. - **Metric**: one of `Count`, `Minimum`, `Maximum`, `Mean`, `Median`, `Mode`, or `Sum`. - **Target**: all objects in the collection, or a single property. - **Grouped by**: optional. Select a property to break the result down by that property's values. Click `Calculate` to run the aggregation. For the equivalent query in application code, see [aggregate](../how-to-query-search/aggregate.md). ## Filter and sort Filters are available in every mode, including `Browse`. Click `Add condition` to build a [filter](../how-to-query-search/filters.md) condition, then click `Apply` to run it. Sorting is available in `Browse` only. `Browse` offers a `Filter & Sort` control, while the search modes offer `Filter` alone, since those modes order the results by relevance. ## Inference keys `Semantic` and `Hybrid` searches vectorize your search text with the [model provider](../model-provider-integrations/index.md) that the collection is configured to use. Where that provider needs an API key, the `Search & explore` panel prompts you for one before the search runs. Enter the key in the panel. The field is named for that provider, for example `OpenAI API key`, and the key is used for this search only and never stored. ## Work with a result Hover over a result card to reveal two buttons: - `Find similar` searches for the nearest neighbors of that object, so you can pivot from one result to the objects most like it. - `Show JSON` shows the raw JSON for that object. ## Further resources - [Collections tool](../manage-collections/tools-collections-tool.md) - [Query Agent](../cloud-agents/query-agent.md) - [Search: keyword (BM25)](../how-to-query-search/bm25.md) - [Search: hybrid](../how-to-query-search/hybrid.md) - [Search: aggregate](../how-to-query-search/aggregate.md) - [Model provider integrations](../model-provider-integrations/index.md) ## Support If you use **Weaviate Cloud** (Database cluster(s) or Weaviate product in the cloud) or have a self-hosted support package, open a ticket in the [Support Portal](https://support.weaviate.io) or email [Weaviate support](mailto\:support@weaviate.io) directly. To add a [support plan](https://weaviate.io/support-plans), contact [Weaviate sales](https://weaviate.io/pricing#contact-sales). Use the **Support Portal** for direct help from the Weaviate team: open and track tickets, and we'll respond in line with your support plan. The **Community Forum** is open to everyone, and a great place to ask questions, get help with your cluster, and connect with other developers. For all the ways to get help, see the [Support overview](../support/overview.md). ::::card-grid :::card{title="Weaviate Support Portal" href="https://support.weaviate.io" icon="headset"} Direct help from the Weaviate team for Weaviate Cloud. Open and track tickets in the **Support Portal**. ::: :::card{title="Weaviate Community Forum" href="https://forum.weaviate.io/c/support" icon="messages-square"} Ask questions, share ideas, and connect with other developers on our **Community forum**. ::: :::: ## Related pages - [Agents](./agents-index.md) - [AI-assisted Weaviate code generation](./ai-assisted-vibe-coding-index.md) - [APIs](./apis-index.md) - [Authorization and authentication](./authorization-and-authentication-index.md) - [Benchmarks](./benchmarks-index.md) - [Best practices](./best-practices-index.md) - [Client libraries](./clients-index.md) - [Client Libraries / SDKs](./client-libraries-index.md) - [Cloud](./cloud-index.md) - [Cloud account management](./cloud-account-management-index.md) # Agent Instructions This portal answers questions programmatically. To receive a synthesized, source-cited answer instead of crawling page by page, append the `?ask=` query parameter to any page URL on this site: /guides/quickstart?ask=how+do+I+authenticate Optional parameters: - `&goal=` steers the answer toward your objective (e.g. `&goal=write+a+python+client`). - `&version=