Merge branch 'main' into DOC-5468

Author: rrelledge

.github/workflows/main.yml

@@ -193,8 +193,10 @@ jobs:
             bucket_path=`echo "version/${{ github.ref_name }}" | sed 's/-build$//'`
           else
             bucket_path=staging/${{ github.ref_name }}
-          fi \
-          && gsutil -m rsync -r -c -j html -d ${{ github.workspace }}/public gs://$BUCKET/$bucket_path
+          fi
+          
+          gsutil -m rsync -r -c -j html -d ${{ github.workspace }}/public gs://$BUCKET/$bucket_path
+          gsutil -m rsync -r -c -j html -d ${{ github.workspace }}/public gs://$BUCKET/docs/$bucket_path
 
           if [[ "${{ github.ref_name }}" == "latest" ]]
           then
@@ -203,8 +205,10 @@ jobs:
               product=$(awk 'BEGIN{FS=OFS="-"}{NF--; print}' <<< $versioned_build)
               if [[ "${product}" == "redis-data-integration" ]]; then
                 gsutil -m rsync -r -c -j html -d "${{ github.workspace }}/${versioned_build}/integrate/${product}" "gs://${BUCKET}/${versioned_build}/integrate/${product}"
+                gsutil -m rsync -r -c -j html -d "${{ github.workspace }}/${versioned_build}/integrate/${product}" "gs://${BUCKET}/docs/${versioned_build}/integrate/${product}"
               else
                 gsutil -m rsync -r -c -j html -d "${{ github.workspace }}/${versioned_build}/operate/${product}" "gs://${BUCKET}/${versioned_build}/operate/${product}"
+                gsutil -m rsync -r -c -j html -d "${{ github.workspace }}/${versioned_build}/operate/${product}" "gs://${BUCKET}/docs/${versioned_build}/operate/${product}"
               fi
             done
           fi
@@ -216,8 +220,10 @@ jobs:
               product=$(awk 'BEGIN{FS=OFS="-"}{NF--; print}' <<< $versioned_build)
               if [[ "${product}" == "redis-data-integration" ]]; then
                 gsutil -m rsync -r -c -j html -d "${{ github.workspace }}/${versioned_build}/integrate/${product}" "gs://${BUCKET}/${bucket_path}/${versioned_build}/integrate/${product}"
+                gsutil -m rsync -r -c -j html -d "${{ github.workspace }}/${versioned_build}/integrate/${product}" "gs://${BUCKET}/docs/${bucket_path}/${versioned_build}/integrate/${product}"
               else
                 gsutil -m rsync -r -c -j html -d "${{ github.workspace }}/${versioned_build}/operate/${product}" "gs://${BUCKET}/${bucket_path}/${versioned_build}/operate/${product}"
+                gsutil -m rsync -r -c -j html -d "${{ github.workspace }}/${versioned_build}/operate/${product}" "gs://${BUCKET}/docs/${bucket_path}/${versioned_build}/operate/${product}"
               fi
             done
           fi

content/develop/ai/redisvl/api/_index.md

@@ -1,10 +1,10 @@
 ---
 linkTitle: RedisVL API
 title: RedisVL API
-weight: 5
-hideListLinks: true
 aliases:
 - /integrate/redisvl/api
+weight: 5
+hideListLinks: true
 ---
 
 
@@ -59,6 +59,3 @@ Reference documentation for the RedisVL API.
   * [Route](router/#route)
   * [Route Match](router/#route-match)
   * [Distance Aggregation Method](router/#distance-aggregation-method)
-* [Threshold Optimizers](threshold_optimizer/)
-  * [CacheThresholdOptimizer](threshold_optimizer/#cachethresholdoptimizer)
-  * [RouterThresholdOptimizer](threshold_optimizer/#routerthresholdoptimizer)

content/develop/ai/redisvl/api/cache.md

@@ -79,7 +79,7 @@ LLM responses.
 
 ```python
 response = await cache.acheck(
-    prompt="What is the captial city of France?"
+    prompt="What is the capital city of France?"
 )
 ```
 
@@ -169,7 +169,7 @@ Async stores the specified key-value pair in the cache along with metadata.
 
 ```python
 key = await cache.astore(
-    prompt="What is the captial city of France?",
+    prompt="What is the capital city of France?",
     response="Paris",
     metadata={"city": "Paris", "country": "France"}
 )
@@ -233,7 +233,7 @@ LLM responses.
 
 ```python
 response = cache.check(
-    prompt="What is the captial city of France?"
+    prompt="What is the capital city of France?"
 )
 ```
 
@@ -347,7 +347,7 @@ Stores the specified key-value pair in the cache along with metadata.
 
 ```python
 key = cache.store(
-    prompt="What is the captial city of France?",
+    prompt="What is the capital city of France?",
     response="Paris",
     metadata={"city": "Paris", "country": "France"}
 )
@@ -408,7 +408,7 @@ The default TTL, in seconds, for entries in the cache.
 
 <a id="embeddings-cache-api"></a>
 
-### `class EmbeddingsCache(name='embedcache', ttl=None, redis_client=None, redis_url='redis://localhost:6379', connection_kwargs={})`
+### `class EmbeddingsCache(name='embedcache', ttl=None, redis_client=None, async_redis_client=None, redis_url='redis://localhost:6379', connection_kwargs={})`
 
 Bases: `BaseCache`
 
@@ -419,9 +419,10 @@ Initialize an embeddings cache.
 * **Parameters:**
   * **name** (*str*) – The name of the cache. Defaults to “embedcache”.
   * **ttl** (*Optional* *[* *int* *]*) – The time-to-live for cached embeddings. Defaults to None.
-  * **redis_client** (*Optional* *[* *Redis* *]*) – Redis client instance. Defaults to None.
+  * **redis_client** (*Optional* *[* *SyncRedisClient* *]*) – Redis client instance. Defaults to None.
   * **redis_url** (*str*) – Redis URL for connection. Defaults to “redis://localhost:6379”.
   * **connection_kwargs** (*Dict* *[* *str* *,* *Any* *]*) – Redis connection arguments. Defaults to {}.
+  * **async_redis_client** (*Redis* *|* *RedisCluster* *|* *None*)
 * **Raises:**
   **ValueError** – If vector dimensions are invalid
 

content/develop/ai/redisvl/api/message_history.md

@@ -93,7 +93,7 @@ Remove a specific exchange from the message history.
 
 #### `get_recent(top_k=5, as_text=False, raw=False, session_tag=None)`
 
-Retreive the recent message history in sequential order.
+Retrieve the recent message history in sequential order.
 
 * **Parameters:**
   * **top_k** (*int*) – The number of previous exchanges to return. Default is 5.

content/develop/ai/redisvl/api/query.md

@@ -174,6 +174,8 @@ Add fields to return fields.
 Use a different scoring function to evaluate document relevance.
 Default is TFIDF.
 
+Since Redis 8.0 default was changed to BM25STD.
+
 * **Parameters:**
   **scorer** (*str*) – The scoring function to use
   (e.g. TFIDF.DOCNORM or BM25)
@@ -488,6 +490,8 @@ Add fields to return fields.
 Use a different scoring function to evaluate document relevance.
 Default is TFIDF.
 
+Since Redis 8.0 default was changed to BM25STD.
+
 * **Parameters:**
   **scorer** (*str*) – The scoring function to use
   (e.g. TFIDF.DOCNORM or BM25)
@@ -934,7 +938,7 @@ A query for running a full text search, along with an optional filter expression
   * **text_field_name** (*str*) – The name of the document field to perform text search on.
   * **text_scorer** (*str* *,* *optional*) – The text scoring algorithm to use.
     Defaults to BM25STD. Options are {TFIDF, BM25STD, BM25, TFIDF.DOCNORM, DISMAX, DOCSCORE}.
-    See [https://redis.io/docs/latest/develop/ai/search-and-query/advanced-concepts/scoring/](https://redis.io/docs/latest/develop/ai/search-and-query/advanced-concepts/scoring/)
+    See [https://redis.io/docs/latest/develop/interact/search-and-query/advanced-concepts/scoring/](https://redis.io/docs/latest/develop/interact/search-and-query/advanced-concepts/scoring/)
   * **filter_expression** (*Union* *[* *str* *,* [*FilterExpression*]({{< relref "filter/#filterexpression" >}}) *]* *,* *optional*) – A filter to apply
     along with the text search. Defaults to None.
   * **return_fields** (*List* *[* *str* *]*) – The declared fields to return with search
@@ -1070,6 +1074,8 @@ Add fields to return fields.
 Use a different scoring function to evaluate document relevance.
 Default is TFIDF.
 
+Since Redis 8.0 default was changed to BM25STD.
+
 * **Parameters:**
   **scorer** (*str*) – The scoring function to use
   (e.g. TFIDF.DOCNORM or BM25)
@@ -1282,6 +1288,8 @@ Add fields to return fields.
 Use a different scoring function to evaluate document relevance.
 Default is TFIDF.
 
+Since Redis 8.0 default was changed to BM25STD.
+
 * **Parameters:**
   **scorer** (*str*) – The scoring function to use
   (e.g. TFIDF.DOCNORM or BM25)
@@ -1499,6 +1507,8 @@ Add fields to return fields.
 Use a different scoring function to evaluate document relevance.
 Default is TFIDF.
 
+Since Redis 8.0 default was changed to BM25STD.
+
 * **Parameters:**
   **scorer** (*str*) – The scoring function to use
   (e.g. TFIDF.DOCNORM or BM25)

content/develop/ai/redisvl/api/router.md

@@ -21,7 +21,7 @@ Initialize the SemanticRouter.
   * **routes** (*List* *[*[Route](#route) *]*) – List of Route objects.
   * **vectorizer** (*BaseVectorizer* *,* *optional*) – The vectorizer used to embed route references. Defaults to default HFTextVectorizer.
   * **routing_config** ([RoutingConfig](#routingconfig) *,* *optional*) – Configuration for routing behavior. Defaults to the default RoutingConfig.
-  * **redis_client** (*Optional* *[* *Redis* *]* *,* *optional*) – Redis client for connection. Defaults to None.
+  * **redis_client** (*Optional* *[* *SyncRedisClient* *]* *,* *optional*) – Redis client for connection. Defaults to None.
   * **redis_url** (*str* *,* *optional*) – The redis url. Defaults to redis://localhost:6379.
   * **overwrite** (*bool* *,* *optional*) – Whether to overwrite existing index. Defaults to False.
   * **connection_kwargs** (*Dict* *[* *str* *,* *Any* *]*) – The connection arguments
@@ -99,7 +99,7 @@ Return SemanticRouter instance from existing index.
 
 * **Parameters:**
   * **name** (*str*)
-  * **redis_client** (*Redis* *|* *None*)
+  * **redis_client** (*Redis* *|* *RedisCluster* *|* *None*)
   * **redis_url** (*str*)
 * **Return type:**
   [SemanticRouter](#semanticrouter)

content/develop/ai/redisvl/api/searchindex.md

@@ -49,7 +49,7 @@ kwargs.
 
 * **Parameters:**
   * **schema** ([*IndexSchema*]({{< relref "schema/#indexschema" >}})) – Index schema object.
-  * **redis_client** (*Optional* *[* *redis.Redis* *]*) – An
+  * **redis_client** (*Optional* *[* *Redis* *]*) – An
     instantiated redis client.
   * **redis_url** (*Optional* *[* *str* *]*) – The URL of the Redis server to
     connect to.
@@ -89,13 +89,13 @@ This method takes a list of queries and optionally query params and
 returns a list of Result objects for each query. Results are
 returned in the same order as the queries.
 
+NOTE: Cluster users may need to incorporate hash tags into their query
+to avoid cross-slot operations.
+
 * **Parameters:**
-  * **queries** (*List* *[* *SearchParams* *]*) – The queries to search for. batch_size
-  * **(* ***int** – The number of queries to search for at a time.
-    Defaults to 10.
-  * **optional****)** – The number of queries to search for at a time.
+  * **queries** (*List* *[* *SearchParams* *]*) – The queries to search for.
+  * **batch_size** (*int* *,* *optional*) – The number of queries to search for at a time.
     Defaults to 10.
-  * **batch_size** (*int*)
 * **Returns:**
   The search results for each query.
 * **Return type:**
@@ -106,6 +106,10 @@ returned in the same order as the queries.
 Clear all keys in Redis associated with the index, leaving the index
 available and in-place for future insertions or updates.
 
+NOTE: This method requires custom behavior for Redis Cluster because
+here, we can’t easily give control of the keys we’re clearing to the
+user so they can separate them based on hash tag.
+
 * **Returns:**
   Count of records deleted from Redis.
 * **Return type:**
@@ -177,6 +181,10 @@ Remove documents from the index by their document IDs.
 This method converts document IDs to Redis keys automatically by applying
 the index’s key prefix and separator configuration.
 
+NOTE: Cluster users will need to incorporate hash tags into their
+document IDs and only call this method with documents from a single hash
+tag at a time.
+
 * **Parameters:**
   **ids** (*Union* *[* *str* *,* *List* *[* *str* *]* *]*) – The document ID or IDs to remove from the index.
 * **Returns:**
@@ -262,7 +270,7 @@ Initialize from an existing search index in Redis by index name.
 
 * **Parameters:**
   * **name** (*str*) – Name of the search index in Redis.
-  * **redis_client** (*Optional* *[* *redis.Redis* *]*) – An
+  * **redis_client** (*Optional* *[* *Redis* *]*) – An
     instantiated redis client.
   * **redis_url** (*Optional* *[* *str* *]*) – The URL of the Redis server to
     connect to.
@@ -437,12 +445,12 @@ Async Redis client. It is useful for cases where an external,
 custom-configured client is preferred instead of creating a new one.
 
 * **Parameters:**
-  **redis_client** (*redis.Redis*) – A Redis or Async Redis
+  **redis_client** (*Redis*) – A Redis or Async Redis
   client instance to be used for the connection.
 * **Raises:**
   **TypeError** – If the provided client is not valid.
 
-#### `property client: Redis | None`
+#### `property client: Redis | RedisCluster | None`
 
 The underlying redis-py client object.
 
@@ -504,7 +512,7 @@ Initialize the RedisVL async search index with a schema.
   * **schema** ([*IndexSchema*]({{< relref "schema/#indexschema" >}})) – Index schema object.
   * **redis_url** (*Optional* *[* *str* *]* *,* *optional*) – The URL of the Redis server to
     connect to.
-  * **redis_client** (*Optional* *[* *aredis.Redis* *]*) – An
+  * **redis_client** (*Optional* *[* *AsyncRedis* *]*) – An
     instantiated redis client.
   * **connection_kwargs** (*Optional* *[* *Dict* *[* *str* *,* *Any* *]* *]*) – Redis client connection
     args.
@@ -536,28 +544,42 @@ Asynchronously execute a batch of queries and process results.
 
 #### `async batch_search(queries, batch_size=10)`
 
-Perform a search against the index for multiple queries.
+Asynchronously execute a batch of search queries.
+
+This method takes a list of search queries and executes them in batches
+to improve performance when dealing with multiple queries.
 
-This method takes a list of queries and returns a list of Result objects
-for each query. Results are returned in the same order as the queries.
+NOTE: Cluster users may need to incorporate hash tags into their query
+to avoid cross-slot operations.
 
 * **Parameters:**
-  * **queries** (*List* *[* *SearchParams* *]*) – The queries to search for. batch_size
-  * **(* ***int** – The number of queries to search for at a time.
-    Defaults to 10.
-  * **optional****)** – The number of queries to search for at a time.
-    Defaults to 10.
-  * **batch_size** (*int*)
+  * **queries** (*List* *[* *SearchParams* *]*) – A list of search queries to execute.
+    Each query can be either a string or a tuple of (query, params).
+  * **batch_size** (*int* *,* *optional*) – The number of queries to execute in each
+    batch. Defaults to 10.
 * **Returns:**
-  The search results for each query.
+  A list of search results corresponding to each query.
 * **Return type:**
   List[Result]
 
+```python
+queries = [
+    "hello world",
+    ("goodbye world", {"num_results": 5}),
+]
+
+results = await index.batch_search(queries)
+```
+
 #### `async clear()`
 
 Clear all keys in Redis associated with the index, leaving the index
 available and in-place for future insertions or updates.
 
+NOTE: This method requires custom behavior for Redis Cluster because here,
+we can’t easily give control of the keys we’re clearing to the user so they
+can separate them based on hash tag.
+
 * **Returns:**
   Count of records deleted from Redis.
 * **Return type:**
@@ -618,6 +640,10 @@ Remove documents from the index by their document IDs.
 This method converts document IDs to Redis keys automatically by applying
 the index’s key prefix and separator configuration.
 
+NOTE: Cluster users will need to incorporate hash tags into their
+document IDs and only call this method with documents from a single hash
+tag at a time.
+
 * **Parameters:**
   **ids** (*Union* *[* *str* *,* *List* *[* *str* *]* *]*) – The document ID or IDs to remove from the index.
 * **Returns:**
@@ -701,7 +727,7 @@ Initialize from an existing search index in Redis by index name.
 
 * **Parameters:**
   * **name** (*str*) – Name of the search index in Redis.
-  * **redis_client** (*Optional* *[* *redis.Redis* *]*) – An
+  * **redis_client** (*Optional* *[* *Redis* *]*) – An
     instantiated redis client.
   * **redis_url** (*Optional* *[* *str* *]*) – The URL of the Redis server to
     connect to.
@@ -873,11 +899,11 @@ results = await index.query(query)
 
 #### `async search(*args, **kwargs)`
 
-Perform a search on this index.
+Perform an async search against the index.
 
-Wrapper around redis.search.Search that adds the index name
-to the search query and passes along the rest of the arguments
-to the redis-py ft.search() method.
+Wrapper around the search API that adds the index name
+to the query and passes along the rest of the arguments
+to the redis-py ft().search() method.
 
 * **Returns:**
   Raw Redis search results.
@@ -890,9 +916,9 @@ to the redis-py ft.search() method.
 This method is deprecated; please provide connection parameters in \_\_init_\_.
 
 * **Parameters:**
-  **redis_client** (*Redis* *|* *Redis*)
+  **redis_client** (*Redis* *|* *RedisCluster* *|* *Redis* *|* *RedisCluster*)
 
-#### `property client: Redis | None`
+#### `property client: Redis | RedisCluster | None`
 
 The underlying redis-py client object.
 

content/develop/ai/redisvl/api/vectorizer.md

@@ -545,7 +545,7 @@ embeddings for text data.
 This vectorizer is designed to accept a provided callable text vectorizer and
 provides a class definition to allow for compatibility with RedisVL.
 The vectorizer may support both synchronous and asynchronous operations which
-allows for batch processing of texts, but at a minimum only syncronous embedding
+allows for batch processing of texts, but at a minimum only synchronous embedding
 is required to satisfy the ‘embed()’ method.
 
 You can optionally enable caching to improve performance when generating
@@ -585,8 +585,8 @@ Initialize the Custom vectorizer.
 * **Parameters:**
   * **embed** (*Callable*) – a Callable function that accepts a string object and returns a list of floats.
   * **embed_many** (*Optional* *[* *Callable* *]*) – a Callable function that accepts a list of string objects and returns a list containing lists of floats. Defaults to None.
-  * **aembed** (*Optional* *[* *Callable* *]*) – an asyncronous Callable function that accepts a string object and returns a lists of floats. Defaults to None.
-  * **aembed_many** (*Optional* *[* *Callable* *]*) – an asyncronous Callable function that accepts a list of string objects and returns a list containing lists of floats. Defaults to None.
+  * **aembed** (*Optional* *[* *Callable* *]*) – an asynchronous Callable function that accepts a string object and returns a lists of floats. Defaults to None.
+  * **aembed_many** (*Optional* *[* *Callable* *]*) – an asynchronous Callable function that accepts a list of string objects and returns a list containing lists of floats. Defaults to None.
   * **dtype** (*str*) – the default datatype to use when embedding text as byte arrays.
     Used when setting as_buffer=True in calls to embed() and embed_many().
     Defaults to ‘float32’.