From c6eff086c3a8d83a09b2ce2da5a1e6b1230ff119 Mon Sep 17 00:00:00 2001 From: mich-elle-luna Date: Wed, 12 Aug 2026 14:46:43 -0700 Subject: [PATCH 1/3] Link search and RAG pages to the AI agent builder Add pointers from the high-traffic search and RAG pages to the AI agent builder, telling readers to choose the Knowledge Assistant template to generate a working RAG agent built on Redis vector search: - Redis Search overview: a next-step list item (the page already has other callouts, so this avoids stacking a third box) - Vector search concepts: appended to the intro - Vector search how-to and the RAG quick start: a tip callout each The Redis Agent Memory pages are deferred: they should point at the Redis Iris Conversational Assistant template, which ships with a separate PR. Co-Authored-By: Claude Opus 4.8 (1M context) --- content/develop/ai/search-and-query/_index.md | 1 + content/develop/ai/search-and-query/query/vector-search.md | 4 ++++ content/develop/ai/search-and-query/vectors/_index.md | 2 +- content/develop/get-started/rag.md | 4 ++++ 4 files changed, 10 insertions(+), 1 deletion(-) diff --git a/content/develop/ai/search-and-query/_index.md b/content/develop/ai/search-and-query/_index.md index 14d1fff327..ee76052ae2 100644 --- a/content/develop/ai/search-and-query/_index.md +++ b/content/develop/ai/search-and-query/_index.md @@ -46,6 +46,7 @@ Here are the next steps to get you started: 1. Learn how to [create an index]({{< relref "/develop/ai/search-and-query/indexing/" >}}). 1. Learn how to [query your data]({{< relref "/develop/ai/search-and-query/query/" >}}). 1. [Install Redis Insight]({{< relref "/operate/redisinsight" >}}), connect it to your Redis database, and then use [Redis Copilot]({{< relref "/develop/tools/insight" >}}#redis-copilot) to help you learn how to execute complex queries against your own data using simple, plain language prompts. +1. Want working code to start from? Open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template to generate a complete RAG agent built on Redis vector search. {{< alert title="Try it out" >}} Experiment with Redis Search interactively in the [Redis playground](https://redis.io/try/sandbox) — no installation required. diff --git a/content/develop/ai/search-and-query/query/vector-search.md b/content/develop/ai/search-and-query/query/vector-search.md index a07adef715..481e872340 100644 --- a/content/develop/ai/search-and-query/query/vector-search.md +++ b/content/develop/ai/search-and-query/query/vector-search.md @@ -21,6 +21,10 @@ This article gives you a good overview of how to perform vector search queries w A vector search query on a vector field allows you to find all vectors in a vector space that are close to a given vector. You can query for the k-nearest neighbors or vectors within a given radius. +{{< tip >}} +Want a working example instead of building from scratch? Open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template to generate a complete RAG agent that uses the vector search queries described here. +{{< /tip >}} + The examples in this article use a schema with the following fields: | JSON field | Field alias | Field type | Description | diff --git a/content/develop/ai/search-and-query/vectors/_index.md b/content/develop/ai/search-and-query/vectors/_index.md index 92e85baa98..45f2db0c3a 100644 --- a/content/develop/ai/search-and-query/vectors/_index.md +++ b/content/develop/ai/search-and-query/vectors/_index.md @@ -22,7 +22,7 @@ weight: 8 Redis includes a [high-performance vector database](https://redis.io/blog/benchmarking-results-for-vector-databases/) that lets you perform semantic searches over vector embeddings. You can augment these searches with filtering over text, numerical, geospatial, and tag metadata. -To quickly get started, check out the [Redis vector quickstart guide]({{< relref "develop/get-started/search-tutorial/vector-search" >}}) and the [Redis AI Resources](https://github.com/redis-developer/redis-ai-resources) Github repo. +To quickly get started, check out the [Redis vector quickstart guide]({{< relref "develop/get-started/search-tutorial/vector-search" >}}) and the [Redis AI Resources](https://github.com/redis-developer/redis-ai-resources) Github repo. For a ready-to-run example, open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template. {{< alert title="See vector search in action" >}} [Redis Repo Memory](https://github.com/marketplace/actions/redis-repo-memory) is a GitHub Action that gives your repository a memory: on every pull request it embeds the change and uses Redis KNN vector search to surface semantically related past PRs, issues, and commits — a concise, real-world example of the concepts on this page. See the [source on GitHub](https://github.com/redis-learn/redis-repo-memory). diff --git a/content/develop/get-started/rag.md b/content/develop/get-started/rag.md index 590c8539aa..d856743908 100644 --- a/content/develop/get-started/rag.md +++ b/content/develop/get-started/rag.md @@ -29,6 +29,10 @@ RAG involves three main steps: RAG enables LLMs to use real-time information, improving the accuracy and relevance of generated content. Redis is ideal for RAG due to its speed, versatility, and familiarity. +{{< tip >}} +Prefer to start from working code? Open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template — it generates a complete RAG agent with document ingestion, hybrid retrieval, and citations. +{{< /tip >}} + ### The role of Redis in RAG Redis provides a robust platform for managing real-time data. It supports the storage and retrieval of vectors, essential for handling large-scale, unstructured data and performing similarity searches. Key features and components of Redis that make it suitable for RAG include: From 3dbfd62cc691cf9e5a998bd3f29b5a6d13d4ef8a Mon Sep 17 00:00:00 2001 From: mich-elle-luna Date: Thu, 13 Aug 2026 09:25:20 -0700 Subject: [PATCH 2/3] Revise agent builder callouts to Google technical style Drop the rhetorical "Want.../Prefer..." hooks and marketing phrasing, lead with the task/goal, and use direct present-tense imperative. Co-Authored-By: Claude Opus 4.8 (1M context) --- content/develop/ai/search-and-query/_index.md | 2 +- content/develop/ai/search-and-query/query/vector-search.md | 2 +- content/develop/ai/search-and-query/vectors/_index.md | 2 +- content/develop/get-started/rag.md | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/content/develop/ai/search-and-query/_index.md b/content/develop/ai/search-and-query/_index.md index ee76052ae2..4a86e2a613 100644 --- a/content/develop/ai/search-and-query/_index.md +++ b/content/develop/ai/search-and-query/_index.md @@ -46,7 +46,7 @@ Here are the next steps to get you started: 1. Learn how to [create an index]({{< relref "/develop/ai/search-and-query/indexing/" >}}). 1. Learn how to [query your data]({{< relref "/develop/ai/search-and-query/query/" >}}). 1. [Install Redis Insight]({{< relref "/operate/redisinsight" >}}), connect it to your Redis database, and then use [Redis Copilot]({{< relref "/develop/tools/insight" >}}#redis-copilot) to help you learn how to execute complex queries against your own data using simple, plain language prompts. -1. Want working code to start from? Open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template to generate a complete RAG agent built on Redis vector search. +1. Open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template to generate a working RAG agent built on Redis vector search. {{< alert title="Try it out" >}} Experiment with Redis Search interactively in the [Redis playground](https://redis.io/try/sandbox) — no installation required. diff --git a/content/develop/ai/search-and-query/query/vector-search.md b/content/develop/ai/search-and-query/query/vector-search.md index 481e872340..1ba93a59c7 100644 --- a/content/develop/ai/search-and-query/query/vector-search.md +++ b/content/develop/ai/search-and-query/query/vector-search.md @@ -22,7 +22,7 @@ This article gives you a good overview of how to perform vector search queries w A vector search query on a vector field allows you to find all vectors in a vector space that are close to a given vector. You can query for the k-nearest neighbors or vectors within a given radius. {{< tip >}} -Want a working example instead of building from scratch? Open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template to generate a complete RAG agent that uses the vector search queries described here. +To generate a complete RAG agent that uses the vector search queries described here, open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template. {{< /tip >}} The examples in this article use a schema with the following fields: diff --git a/content/develop/ai/search-and-query/vectors/_index.md b/content/develop/ai/search-and-query/vectors/_index.md index 45f2db0c3a..88e3f033fe 100644 --- a/content/develop/ai/search-and-query/vectors/_index.md +++ b/content/develop/ai/search-and-query/vectors/_index.md @@ -22,7 +22,7 @@ weight: 8 Redis includes a [high-performance vector database](https://redis.io/blog/benchmarking-results-for-vector-databases/) that lets you perform semantic searches over vector embeddings. You can augment these searches with filtering over text, numerical, geospatial, and tag metadata. -To quickly get started, check out the [Redis vector quickstart guide]({{< relref "develop/get-started/search-tutorial/vector-search" >}}) and the [Redis AI Resources](https://github.com/redis-developer/redis-ai-resources) Github repo. For a ready-to-run example, open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template. +To quickly get started, check out the [Redis vector quickstart guide]({{< relref "develop/get-started/search-tutorial/vector-search" >}}) and the [Redis AI Resources](https://github.com/redis-developer/redis-ai-resources) Github repo. To generate a working example, open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template. {{< alert title="See vector search in action" >}} [Redis Repo Memory](https://github.com/marketplace/actions/redis-repo-memory) is a GitHub Action that gives your repository a memory: on every pull request it embeds the change and uses Redis KNN vector search to surface semantically related past PRs, issues, and commits — a concise, real-world example of the concepts on this page. See the [source on GitHub](https://github.com/redis-learn/redis-repo-memory). diff --git a/content/develop/get-started/rag.md b/content/develop/get-started/rag.md index d856743908..8e93e94369 100644 --- a/content/develop/get-started/rag.md +++ b/content/develop/get-started/rag.md @@ -30,7 +30,7 @@ RAG enables LLMs to use real-time information, improving the accuracy and releva Redis is ideal for RAG due to its speed, versatility, and familiarity. {{< tip >}} -Prefer to start from working code? Open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template — it generates a complete RAG agent with document ingestion, hybrid retrieval, and citations. +To generate a complete RAG agent with document ingestion, hybrid retrieval, and citations, open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template. {{< /tip >}} ### The role of Redis in RAG From ea504b2ff26fb235b03a738084a692121c4a4570 Mon Sep 17 00:00:00 2001 From: mich-elle-luna Date: Thu, 13 Aug 2026 09:48:16 -0700 Subject: [PATCH 3/3] Move the Try it out note to the end of Enable Redis Search Relocate the Redis playground "Try it out" alert from after the next-steps list to the end of the Enable Redis Search section, next to the installation instructions where trying it out is more relevant. Co-Authored-By: Claude Opus 4.8 (1M context) --- content/develop/ai/search-and-query/_index.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/content/develop/ai/search-and-query/_index.md b/content/develop/ai/search-and-query/_index.md index 4a86e2a613..7e87e5385f 100644 --- a/content/develop/ai/search-and-query/_index.md +++ b/content/develop/ai/search-and-query/_index.md @@ -48,10 +48,6 @@ Here are the next steps to get you started: 1. [Install Redis Insight]({{< relref "/operate/redisinsight" >}}), connect it to your Redis database, and then use [Redis Copilot]({{< relref "/develop/tools/insight" >}}#redis-copilot) to help you learn how to execute complex queries against your own data using simple, plain language prompts. 1. Open the [AI agent builder]({{< relref "/develop/ai/agent-builder" >}}) and choose the **Knowledge Assistant** template to generate a working RAG agent built on Redis vector search. -{{< alert title="Try it out" >}} -Experiment with Redis Search interactively in the [Redis playground](https://redis.io/try/sandbox) — no installation required. -{{< /alert >}} - {{< tip >}} See Redis vector search in a real workflow: [Redis Repo Memory](https://github.com/marketplace/actions/redis-repo-memory) is a GitHub Action that surfaces related past PRs, issues, and commits on every pull request. Add it to any repository in a few minutes. {{< /tip >}} @@ -64,6 +60,10 @@ See [Install Redis Software]({{< relref "/operate/rs/installing-upgrading/install" >}}) for full installation instructions. +{{< alert title="Try it out" >}} +Experiment with Redis Search interactively in the [Redis playground](https://redis.io/try/sandbox) — no installation required. +{{< /alert >}} + ## License and source code The Redis Search features of Redis are available under the Source Available License 2.0 (RSALv2), the Server Side Public License v1 (SSPLv1), or the GNU Affero General Public License version 3 (AGPLv3). Please read the [license file](https://raw.githubusercontent.com/RediSearch/RediSearch/master/LICENSE.txt) for further details. The source code and the [detailed release notes](https://github.com/RediSearch/RediSearch/releases) are available on [GitHub](https://github.com/RediSearch/RediSearch).