{
  "id": "user_guide",
  "title": "User Guides",
  "url": "https://redis.io/docs/latest/develop/ai/redisvl/0.8.1/user_guide/",
  "summary": "",
  "content": "\n\nUser guides provide helpful resources for using RedisVL and its different components.\n\n\n\n* [Getting Started with RedisVL](getting_started/)\n  * [Define an `IndexSchema`](getting_started/#define-an-indexschema)\n  * [Sample Dataset Preparation](getting_started/#sample-dataset-preparation)\n  * [Create a `SearchIndex`](getting_started/#create-a-searchindex)\n  * [Inspect with the `rvl` CLI](getting_started/#inspect-with-the-rvl-cli)\n  * [Load Data to `SearchIndex`](getting_started/#load-data-to-searchindex)\n  * [Creating `VectorQuery` Objects](getting_started/#creating-vectorquery-objects)\n  * [Using an Asynchronous Redis Client](getting_started/#using-an-asynchronous-redis-client)\n  * [Updating a schema](getting_started/#updating-a-schema)\n  * [Check Index Stats](getting_started/#check-index-stats)\n  * [Cleanup](getting_started/#cleanup)\n* [Querying with RedisVL](hybrid_queries/)\n  * [Hybrid Queries](hybrid_queries/#hybrid-queries)\n  * [Combining Filters](hybrid_queries/#combining-filters)\n  * [Non-vector Queries](hybrid_queries/#non-vector-queries)\n  * [Count Queries](hybrid_queries/#count-queries)\n  * [Range Queries](hybrid_queries/#range-queries)\n  * [Advanced Query Modifiers](hybrid_queries/#advanced-query-modifiers)\n* [Initializing `SemanticCache`](llmcache/)\n* [Basic Cache Usage](llmcache/#basic-cache-usage)\n* [Customize the Distance Threshold](llmcache/#customize-the-distance-threshold)\n* [Utilize TTL](llmcache/#utilize-ttl)\n* [Simple Performance Testing](llmcache/#simple-performance-testing)\n* [Cache Access Controls, Tags \u0026 Filters](llmcache/#cache-access-controls-tags-filters)\n* [Caching Embeddings](embeddings_cache/)\n  * [Setup](embeddings_cache/#setup)\n  * [Initializing the EmbeddingsCache](embeddings_cache/#initializing-the-embeddingscache)\n  * [Basic Usage](embeddings_cache/#basic-usage)\n  * [Advanced Usage](embeddings_cache/#advanced-usage)\n  * [Async Support](embeddings_cache/#async-support)\n  * [Real-World Example](embeddings_cache/#real-world-example)\n  * [Performance Benchmark](embeddings_cache/#performance-benchmark)\n  * [Common Use Cases for Embedding Caching](embeddings_cache/#common-use-cases-for-embedding-caching)\n  * [Cleanup](embeddings_cache/#cleanup)\n  * [Summary](embeddings_cache/#summary)\n* [Vectorizers](vectorizers/)\n  * [Creating Text Embeddings](vectorizers/#creating-text-embeddings)\n  * [Search with Provider Embeddings](vectorizers/#search-with-provider-embeddings)\n  * [Selecting your float data type](vectorizers/#selecting-your-float-data-type)\n* [Hash vs JSON Storage](hash_vs_json/)\n  * [Hash or JSON – how to choose?](hash_vs_json/#hash-or-json-how-to-choose)\n  * [Cleanup](hash_vs_json/#cleanup)\n* [Working with nested data in JSON](hash_vs_json/#working-with-nested-data-in-json)\n  * [Full JSON Path support](hash_vs_json/#full-json-path-support)\n  * [As an example:](hash_vs_json/#as-an-example)\n* [Cleanup](hash_vs_json/#id1)\n* [Rerankers](rerankers/)\n  * [Simple Reranking](rerankers/#simple-reranking)\n* [LLM Message History](message_history/)\n  * [Managing multiple users and conversations](message_history/#managing-multiple-users-and-conversations)\n  * [Semantic message history](message_history/#semantic-message-history)\n  * [Conversation control](message_history/#conversation-control)\n* [Semantic Routing](semantic_router/)\n  * [Define the Routes](semantic_router/#define-the-routes)\n  * [Initialize the SemanticRouter](semantic_router/#initialize-the-semanticrouter)\n  * [Simple routing](semantic_router/#simple-routing)\n  * [Update the routing config](semantic_router/#update-the-routing-config)\n  * [Router serialization](semantic_router/#router-serialization)\n  * [Add route references](semantic_router/#add-route-references)\n  * [Get route references](semantic_router/#get-route-references)\n  * [Delete route references](semantic_router/#delete-route-references)\n  * [Clean up the router](semantic_router/#clean-up-the-router)\n",
  "tags": [],
  "last_updated": "2026-04-01T08:10:08-05:00",
  "children": [{"id":"getting_started","summary":"","title":"Getting Started with RedisVL","url":"https://redis.io/docs/latest/develop/ai/redisvl/0.8.1/user_guide/getting_started/"},{"id":"hybrid_queries","summary":"","title":"Querying with RedisVL","url":"https://redis.io/docs/latest/develop/ai/redisvl/0.8.1/user_guide/hybrid_queries/"},{"id":"llmcache","summary":"","title":"First, we will import [OpenAI](https://platform.openai.com) to use their API for responding to user prompts. We will also create a simple `ask_openai` helper method to assist.","url":"https://redis.io/docs/latest/develop/ai/redisvl/0.8.1/user_guide/llmcache/"},{"id":"vectorizers","summary":"","title":"Vectorizers","url":"https://redis.io/docs/latest/develop/ai/redisvl/0.8.1/user_guide/vectorizers/"},{"id":"hash_vs_json","summary":"","title":"Hash vs JSON Storage","url":"https://redis.io/docs/latest/develop/ai/redisvl/0.8.1/user_guide/hash_vs_json/"},{"id":"rerankers","summary":"","title":"Rerankers","url":"https://redis.io/docs/latest/develop/ai/redisvl/0.8.1/user_guide/rerankers/"},{"id":"message_history","summary":"","title":"LLM Message History","url":"https://redis.io/docs/latest/develop/ai/redisvl/0.8.1/user_guide/message_history/"},{"id":"semantic_router","summary":"","title":"Semantic Routing","url":"https://redis.io/docs/latest/develop/ai/redisvl/0.8.1/user_guide/semantic_router/"},{"id":"embeddings_cache","summary":"","title":"Caching Embeddings","url":"https://redis.io/docs/latest/develop/ai/redisvl/0.8.1/user_guide/embeddings_cache/"}]
}