diff --git a/content/integrate/redisvl/api/searchindex.md b/content/integrate/redisvl/api/searchindex.md
index 3d805d1477..5e00c89f49 100644
--- a/content/integrate/redisvl/api/searchindex.md
+++ b/content/integrate/redisvl/api/searchindex.md
@@ -14,7 +14,7 @@ type: integration
## SearchIndex
-### `class SearchIndex(schema, redis_client=None, redis_url=None, connection_args={}, **kwargs)`
+### `class SearchIndex(schema, redis_client=None, redis_url=None, connection_kwargs=None, **kwargs)`
A search index class for interacting with Redis as a vector database.
@@ -26,8 +26,7 @@ settings and field configurations.
from redisvl.index import SearchIndex
# initialize the index object with schema from file
-index = SearchIndex.from_yaml("schemas/schema.yaml")
-index.connect(redis_url="redis://localhost:6379")
+index = SearchIndex.from_yaml("schemas/schema.yaml", redis_url="redis://localhost:6379")
# create the index
index.create(overwrite=True)
@@ -49,7 +48,7 @@ kwargs.
instantiated redis client.
* **redis_url** (*Optional* *[* *str* *]*) – The URL of the Redis server to
connect to.
- * **connection_args** (*Dict* *[* *str* *,* *Any* *]* *,* *optional*) – Redis client connection
+ * **connection_kwargs** (*Dict* *[* *str* *,* *Any* *]* *,* *optional*) – Redis client connection
args.
#### `aggregate(*args, **kwargs)`
@@ -85,13 +84,13 @@ extra options specific to the Redis connection.
* **Parameters:**
**redis_url** (*Optional* *[* *str* *]* *,* *optional*) – The URL of the Redis server to
- connect to. If not provided, the method defaults to using the
- REDIS_URL environment variable.
+ connect to.
* **Raises:**
* **redis.exceptions.ConnectionError** – If the connection to the Redis
server fails.
* **ValueError** – If the Redis URL is not provided nor accessible
through the REDIS_URL environment variable.
+ * **ModuleNotFoundError** – If required Redis modules are not installed.
```python
index.connect(redis_url="redis://localhost:6379")
@@ -158,6 +157,16 @@ Check if the index exists in Redis.
* **Return type:**
bool
+#### `expire_keys(keys, ttl)`
+
+Set the expiration time for a specific entry or entries in Redis.
+
+* **Parameters:**
+ * **keys** (*Union* *[* *str* *,* *List* *[* *str* *]* *]*) – The entry ID or IDs to set the expiration for.
+ * **ttl** (*int*) – The time-to-live in seconds.
+* **Return type:**
+ int | *List*[int]
+
#### `fetch(id)`
Fetch an object from Redis by id.
@@ -210,6 +219,9 @@ Initialize from an existing search index in Redis by index name.
instantiated redis client.
* **redis_url** (*Optional* *[* *str* *]*) – The URL of the Redis server to
connect to.
+* **Raises:**
+ * **ValueError** – If redis_url or redis_client is not provided.
+ * **RedisModuleVersionError** – If required Redis modules are not installed.
#### `classmethod from_yaml(schema_path, **kwargs)`
@@ -438,7 +450,7 @@ hash or json.
## AsyncSearchIndex
-### `class AsyncSearchIndex(schema, **kwargs)`
+### `class AsyncSearchIndex(schema, *, redis_url=None, redis_client=None, connection_kwargs=None, **kwargs)`
A search index class for interacting with Redis as a vector database in
async-mode.
@@ -451,8 +463,10 @@ various settings and field configurations.
from redisvl.index import AsyncSearchIndex
# initialize the index object with schema from file
-index = AsyncSearchIndex.from_yaml("schemas/schema.yaml")
-await index.connect(redis_url="redis://localhost:6379")
+index = AsyncSearchIndex.from_yaml(
+ "schemas/schema.yaml",
+ redis_url="redis://localhost:6379"
+)
# create the index
await index.create(overwrite=True)
@@ -468,7 +482,11 @@ Initialize the RedisVL async search index with a schema.
* **Parameters:**
* **schema** ([*IndexSchema*]({{< relref "schema/#indexschema" >}})) – Index schema object.
- * **connection_args** (*Dict* *[* *str* *,* *Any* *]* *,* *optional*) – Redis client connection
+ * **redis_url** (*Optional* *[* *str* *]* *,* *optional*) – The URL of the Redis server to
+ connect to.
+ * **redis_client** (*Optional* *[* *aredis.Redis* *]*) – An
+ instantiated redis client.
+ * **connection_kwargs** (*Optional* *[* *Dict* *[* *str* *,* *Any* *]* *]*) – Redis client connection
args.
#### `async aggregate(*args, **kwargs)`
@@ -494,27 +512,12 @@ available and in-place for future insertions or updates.
* **Return type:**
int
-#### `async connect(redis_url=None, **kwargs)`
-
-Connect to a Redis instance using the provided redis_url, falling
-back to the REDIS_URL environment variable (if available).
+#### `connect(redis_url=None, **kwargs)`
-Note: Additional keyword arguments (\*\*kwargs) can be used to provide
-extra options specific to the Redis connection.
+[DEPRECATED] Connect to a Redis instance. Use connection parameters in \_\_init_\_.
* **Parameters:**
- **redis_url** (*Optional* *[* *str* *]* *,* *optional*) – The URL of the Redis server to
- connect to. If not provided, the method defaults to using the
- REDIS_URL environment variable.
-* **Raises:**
- * **redis.exceptions.ConnectionError** – If the connection to the Redis
- server fails.
- * **ValueError** – If the Redis URL is not provided nor accessible
- through the REDIS_URL environment variable.
-
-```python
-index.connect(redis_url="redis://localhost:6379")
-```
+ **redis_url** (*str* *|* *None*)
#### `async create(overwrite=False, drop=False)`
@@ -553,9 +556,9 @@ Delete the search index.
* **Raises:**
**redis.exceptions.ResponseError** – If the index does not exist.
-#### `disconnect()`
+#### `async disconnect()`
-Disconnect and cleanup the underlying async redis connection.
+Disconnect from the Redis database.
#### `async drop_keys(keys)`
@@ -577,6 +580,16 @@ Check if the index exists in Redis.
* **Return type:**
bool
+#### `async expire_keys(keys, ttl)`
+
+Set the expiration time for a specific entry or entries in Redis.
+
+* **Parameters:**
+ * **keys** (*Union* *[* *str* *,* *List* *[* *str* *]* *]*) – The entry ID or IDs to set the expiration for.
+ * **ttl** (*int*) – The time-to-live in seconds.
+* **Return type:**
+ int | *List*[int]
+
#### `async fetch(id)`
Asynchronously etch an object from Redis by id. The id is typically
@@ -805,29 +818,13 @@ to the redis-py ft.search() method.
* **Return type:**
Result
-#### `async set_client(redis_client)`
+#### `set_client(redis_client)`
-Manually set the Redis client to use with the search index.
-
-This method configures the search index to use a specific
-Async Redis client. It is useful for cases where an external,
-custom-configured client is preferred instead of creating a new one.
+[DEPRECATED] Manually set the Redis client to use with the search index.
+This method is deprecated; please provide connection parameters in \_\_init_\_.
* **Parameters:**
- **redis_client** (*aredis.Redis*) – An Async Redis
- client instance to be used for the connection.
-* **Raises:**
- **TypeError** – If the provided client is not valid.
-
-```python
-import redis.asyncio as aredis
-from redisvl.index import AsyncSearchIndex
-
-# async Redis client and index
-client = aredis.Redis.from_url("redis://localhost:6379")
-index = AsyncSearchIndex.from_yaml("schemas/schema.yaml")
-await index.set_client(client)
-```
+ **redis_client** (*Redis* *|* *Redis*)
#### `property client: Redis | None`
diff --git a/content/integrate/redisvl/overview/cli.md b/content/integrate/redisvl/overview/cli.md
index 1d1653aeda..565c3094a4 100644
--- a/content/integrate/redisvl/overview/cli.md
+++ b/content/integrate/redisvl/overview/cli.md
@@ -19,7 +19,7 @@ Before running this notebook, be sure to
!rvl version
```
- 18:12:25 [RedisVL] INFO RedisVL version 0.3.9
+ 16:19:10 [RedisVL] INFO RedisVL version 0.4.0
## Commands
diff --git a/content/integrate/redisvl/user_guide/_index.md b/content/integrate/redisvl/user_guide/_index.md
index a133211c3b..8baf1e07e6 100644
--- a/content/integrate/redisvl/user_guide/_index.md
+++ b/content/integrate/redisvl/user_guide/_index.md
@@ -11,48 +11,52 @@ User guides provide helpful resources for using RedisVL and its different compon
-* [Getting Started with RedisVL](01_getting_started/)
- * [Define an `IndexSchema`](01_getting_started/#define-an-indexschema)
- * [Sample Dataset Preparation](01_getting_started/#sample-dataset-preparation)
- * [Create a `SearchIndex`](01_getting_started/#create-a-searchindex)
- * [Inspect with the `rvl` CLI](01_getting_started/#inspect-with-the-rvl-cli)
- * [Load Data to `SearchIndex`](01_getting_started/#load-data-to-searchindex)
- * [Creating `VectorQuery` Objects](01_getting_started/#creating-vectorquery-objects)
- * [Using an Asynchronous Redis Client](01_getting_started/#using-an-asynchronous-redis-client)
- * [Updating a schema](01_getting_started/#updating-a-schema)
- * [Check Index Stats](01_getting_started/#check-index-stats)
- * [Cleanup](01_getting_started/#cleanup)
-* [Querying with RedisVL](02_hybrid_queries/)
- * [Hybrid Queries](02_hybrid_queries/#hybrid-queries)
- * [Combining Filters](02_hybrid_queries/#combining-filters)
- * [Non-vector Queries](02_hybrid_queries/#non-vector-queries)
- * [Count Queries](02_hybrid_queries/#count-queries)
- * [Range Queries](02_hybrid_queries/#range-queries)
- * [Advanced Query Modifiers](02_hybrid_queries/#advanced-query-modifiers)
-* [Semantic Caching for LLMs](03_llmcache/)
- * [Initializing `SemanticCache`](03_llmcache/#initializing-semanticcache)
- * [Basic Cache Usage](03_llmcache/#basic-cache-usage)
- * [Customize the Distance Threshhold](03_llmcache/#customize-the-distance-threshhold)
- * [Utilize TTL](03_llmcache/#utilize-ttl)
- * [Simple Performance Testing](03_llmcache/#simple-performance-testing)
- * [Cache Access Controls, Tags & Filters](03_llmcache/#cache-access-controls-tags-filters)
-* [Vectorizers](04_vectorizers/)
- * [Creating Text Embeddings](04_vectorizers/#creating-text-embeddings)
- * [Search with Provider Embeddings](04_vectorizers/#search-with-provider-embeddings)
- * [Selecting your float data type](04_vectorizers/#selecting-your-float-data-type)
-* [Hash vs JSON Storage](05_hash_vs_json/)
- * [Hash or JSON – how to choose?](05_hash_vs_json/#hash-or-json-how-to-choose)
- * [Cleanup](05_hash_vs_json/#cleanup)
-* [Rerankers](06_rerankers/)
- * [Simple Reranking](06_rerankers/#simple-reranking)
-* [LLM Session Memory](07_session_manager/)
- * [Managing multiple users and conversations](07_session_manager/#managing-multiple-users-and-conversations)
- * [Semantic conversation memory](07_session_manager/#semantic-conversation-memory)
- * [Conversation control](07_session_manager/#conversation-control)
-* [Semantic Routing](08_semantic_router/)
- * [Define the Routes](08_semantic_router/#define-the-routes)
- * [Initialize the SemanticRouter](08_semantic_router/#initialize-the-semanticrouter)
- * [Simple routing](08_semantic_router/#simple-routing)
- * [Update the routing config](08_semantic_router/#update-the-routing-config)
- * [Router serialization](08_semantic_router/#router-serialization)
- * [Clean up the router](08_semantic_router/#clean-up-the-router)
+* [Getting Started with RedisVL](getting_started/)
+ * [Define an `IndexSchema`](getting_started/#define-an-indexschema)
+ * [Sample Dataset Preparation](getting_started/#sample-dataset-preparation)
+ * [Create a `SearchIndex`](getting_started/#create-a-searchindex)
+ * [Inspect with the `rvl` CLI](getting_started/#inspect-with-the-rvl-cli)
+ * [Load Data to `SearchIndex`](getting_started/#load-data-to-searchindex)
+ * [Creating `VectorQuery` Objects](getting_started/#creating-vectorquery-objects)
+ * [Using an Asynchronous Redis Client](getting_started/#using-an-asynchronous-redis-client)
+ * [Updating a schema](getting_started/#updating-a-schema)
+ * [Check Index Stats](getting_started/#check-index-stats)
+ * [Cleanup](getting_started/#cleanup)
+* [Querying with RedisVL](hybrid_queries/)
+ * [Hybrid Queries](hybrid_queries/#hybrid-queries)
+ * [Combining Filters](hybrid_queries/#combining-filters)
+ * [Non-vector Queries](hybrid_queries/#non-vector-queries)
+ * [Count Queries](hybrid_queries/#count-queries)
+ * [Range Queries](hybrid_queries/#range-queries)
+ * [Advanced Query Modifiers](hybrid_queries/#advanced-query-modifiers)
+* [Semantic Caching for LLMs](llmcache/)
+ * [Initializing `SemanticCache`](llmcache/#initializing-semanticcache)
+ * [Basic Cache Usage](llmcache/#basic-cache-usage)
+ * [Customize the Distance Threshhold](llmcache/#customize-the-distance-threshhold)
+ * [Utilize TTL](llmcache/#utilize-ttl)
+ * [Simple Performance Testing](llmcache/#simple-performance-testing)
+ * [Cache Access Controls, Tags & Filters](llmcache/#cache-access-controls-tags-filters)
+* [Vectorizers](vectorizers/)
+ * [Creating Text Embeddings](vectorizers/#creating-text-embeddings)
+ * [Search with Provider Embeddings](vectorizers/#search-with-provider-embeddings)
+ * [Selecting your float data type](vectorizers/#selecting-your-float-data-type)
+* [Hash vs JSON Storage](hash_vs_json/)
+ * [Hash or JSON – how to choose?](hash_vs_json/#hash-or-json-how-to-choose)
+ * [Cleanup](hash_vs_json/#cleanup)
+* [Working with nested data in JSON](hash_vs_json/#working-with-nested-data-in-json)
+ * [Full JSON Path support](hash_vs_json/#full-json-path-support)
+ * [As an example:](hash_vs_json/#as-an-example)
+* [Cleanup](hash_vs_json/#id1)
+* [Rerankers](rerankers/)
+ * [Simple Reranking](rerankers/#simple-reranking)
+* [LLM Session Memory](session_manager/)
+ * [Managing multiple users and conversations](session_manager/#managing-multiple-users-and-conversations)
+ * [Semantic conversation memory](session_manager/#semantic-conversation-memory)
+ * [Conversation control](session_manager/#conversation-control)
+* [Semantic Routing](semantic_router/)
+ * [Define the Routes](semantic_router/#define-the-routes)
+ * [Initialize the SemanticRouter](semantic_router/#initialize-the-semanticrouter)
+ * [Simple routing](semantic_router/#simple-routing)
+ * [Update the routing config](semantic_router/#update-the-routing-config)
+ * [Router serialization](semantic_router/#router-serialization)
+ * [Clean up the router](semantic_router/#clean-up-the-router)
diff --git a/content/integrate/redisvl/user_guide/getting_started.md b/content/integrate/redisvl/user_guide/getting_started.md
index 6032bdb897..dd02b3c86c 100644
--- a/content/integrate/redisvl/user_guide/getting_started.md
+++ b/content/integrate/redisvl/user_guide/getting_started.md
@@ -148,7 +148,7 @@ index = SearchIndex.from_dict(schema)
Now we also need to facilitate a Redis connection. There are a few ways to do this:
- Create & manage your own client connection (recommended)
-- Provide a simple Redis URL and let RedisVL connect on your behalf
+- Provide a Redis URL and let RedisVL connect on your behalf (by default, it will connect to "redis://localhost:6379")
### Bring your own Redis connection instance
@@ -159,9 +159,14 @@ This is ideal in scenarios where you have custom settings on the connection inst
from redis import Redis
client = Redis.from_url("redis://localhost:6379")
+index = SearchIndex.from_dict(schema, redis_client=client)
+
+# alternatively, provide an async Redis client object to enable async index operations
+# from redis.asyncio import Redis
+# from redisvl.index import AsyncSearchIndex
+# client = Redis.from_url("redis://localhost:6379")
+# index = AsyncSearchIndex.from_dict(schema, redis_client=client)
-index.set_client(client)
-# optionally provide an async Redis client object to enable async index operations
```
@@ -177,8 +182,10 @@ This is ideal for simple cases:
```python
-index.connect("redis://localhost:6379")
-# optionally use an async client by passing use_async=True
+index = SearchIndex.from_dict(schema, redis_url="redis://localhost:6379")
+
+# If you don't specify a client or Redis URL, the index will attempt to
+# connect to Redis at the default address ("redis://localhost:6379").
```
@@ -299,8 +306,11 @@ results = index.query(query)
result_print(results)
```
+ *=>[KNN 3 @user_embedding $vector AS vector_distance] RETURN 6 user age job credit_score vector_distance vector_distance SORTBY vector_distance ASC DIALECT 2 LIMIT 0 3
-| vector_distance | user | age | job | credit_score |
|---|
| 0 | john | 1 | engineer | high |
| 0 | mary | 2 | doctor | low |
| 0.0566299557686 | tyler | 9 | engineer | high |
+
+
+table>| vector_distance | user | age | job | credit_score |
|---|
| 0 | john | 1 | engineer | high |
| 0 | mary | 2 | doctor | low |
| 0.0566299557686 | tyler | 9 | engineer | high |
## Using an Asynchronous Redis Client
@@ -337,8 +347,7 @@ from redis.asyncio import Redis
client = Redis.from_url("redis://localhost:6379")
-index = AsyncSearchIndex.from_dict(schema)
-await index.set_client(client)
+index = AsyncSearchIndex.from_dict(schema, redis_client=client)
```
@@ -393,7 +402,7 @@ index.schema.add_fields([
await index.create(overwrite=True, drop=False)
```
- 11:53:25 redisvl.index.index INFO Index already exists, overwriting.
+ 11:28:32 redisvl.index.index INFO Index already exists, overwriting.
@@ -404,7 +413,7 @@ result_print(results)
```
-| vector_distance | user | age | job | credit_score |
|---|
| 0 | john | 1 | engineer | high |
| 0 | mary | 2 | doctor | low |
| 0.0566299557686 | tyler | 9 | engineer | high |
+| vector_distance | user | age | job | credit_score |
|---|
| 0 | mary | 2 | doctor | low |
| 0 | john | 1 | engineer | high |
| 0.0566299557686 | tyler | 9 | engineer | high |
## Check Index Stats
@@ -426,19 +435,19 @@ Use the `rvl` CLI to check the stats for the index:
│ num_records │ 22 │
│ percent_indexed │ 1 │
│ hash_indexing_failures │ 0 │
- │ number_of_uses │ 5 │
- │ bytes_per_record_avg │ 50.9091 │
+ │ number_of_uses │ 2 │
+ │ bytes_per_record_avg │ 47.8 │
│ doc_table_size_mb │ 0.000423431 │
- │ inverted_sz_mb │ 0.00106812 │
+ │ inverted_sz_mb │ 0.000911713 │
│ key_table_size_mb │ 0.000165939 │
- │ offset_bits_per_record_avg │ 8 │
- │ offset_vectors_sz_mb │ 5.72205e-06 │
- │ offsets_per_term_avg │ 0.272727 │
- │ records_per_doc_avg │ 5.5 │
+ │ offset_bits_per_record_avg │ nan │
+ │ offset_vectors_sz_mb │ 0 │
+ │ offsets_per_term_avg │ 0 │
+ │ records_per_doc_avg │ 5 │
│ sortable_values_size_mb │ 0 │
- │ total_indexing_time │ 0.197 │
- │ total_inverted_index_blocks │ 12 │
- │ vector_index_sz_mb │ 0.0201416 │
+ │ total_indexing_time │ 0.239 │
+ │ total_inverted_index_blocks │ 11 │
+ │ vector_index_sz_mb │ 0.235603 │
╰─────────────────────────────┴─────────────╯
diff --git a/content/integrate/redisvl/user_guide/hash_vs_json.md b/content/integrate/redisvl/user_guide/hash_vs_json.md
index ade92835b1..b141ffe93c 100644
--- a/content/integrate/redisvl/user_guide/hash_vs_json.md
+++ b/content/integrate/redisvl/user_guide/hash_vs_json.md
@@ -102,10 +102,7 @@ hash_schema = {
```python
# construct a search index from the hash schema
-hindex = SearchIndex.from_dict(hash_schema)
-
-# connect to local redis instance
-hindex.connect("redis://localhost:6379")
+hindex = SearchIndex.from_dict(hash_schema, redis_url="redis://localhost:6379")
# create the index (no data yet)
hindex.create(overwrite=True)
@@ -193,10 +190,12 @@ from redisvl.query.filter import Tag, Text, Num
t = (Tag("credit_score") == "high") & (Text("job") % "enginee*") & (Num("age") > 17)
-v = VectorQuery([0.1, 0.1, 0.5],
- "user_embedding",
- return_fields=["user", "credit_score", "age", "job", "office_location"],
- filter_expression=t)
+v = VectorQuery(
+ vector=[0.1, 0.1, 0.5],
+ vector_field_name="user_embedding",
+ return_fields=["user", "credit_score", "age", "job", "office_location"],
+ filter_expression=t
+)
results = hindex.query(v)
@@ -216,30 +215,12 @@ hindex.delete()
```
### Working with JSON
-Redis also supports native **JSON** objects. These can be multi-level (nested) objects, with full JSONPath support for updating/retrieving sub elements:
-
-```python
-{
- "name": "bike",
- "metadata": {
- "model": "Deimos",
- "brand": "Ergonom",
- "type": "Enduro bikes",
- "price": 4972,
- }
-}
-```
JSON is best suited for use cases with the following characteristics:
- Ease of use and data model flexibility are top concerns
- Application data is already native JSON
- Replacing another document storage/db solution
-#### Full JSON Path support
-Because Redis enables full JSON path support, when creating an index schema, elements need to be indexed and selected by their path with the desired `name` AND `path` that points to where the data is located within the objects.
-
-By default, RedisVL will assume the path as `$.{name}` if not provided in JSON fields schema.
-
```python
# define the json index schema
@@ -273,10 +254,7 @@ json_schema = {
```python
# construct a search index from the json schema
-jindex = SearchIndex.from_dict(json_schema)
-
-# connect to local redis instance
-jindex.connect("redis://localhost:6379")
+jindex = SearchIndex.from_dict(json_schema, redis_url="redis://localhost:6379")
# create the index (no data yet)
jindex.create(overwrite=True)
@@ -297,8 +275,6 @@ Vectorized data stored in JSON must be stored as a pure array (python list) of f
```python
-import numpy as np
-
json_data = data.copy()
for d in json_data:
@@ -344,3 +320,168 @@ result_print(jindex.query(v))
```python
jindex.delete()
```
+
+# Working with nested data in JSON
+
+Redis also supports native **JSON** objects. These can be multi-level (nested) objects, with full JSONPath support for updating/retrieving sub elements:
+
+```json
+{
+ "name": "Specialized Stump jumper",
+ "metadata": {
+ "model": "Stumpjumper",
+ "brand": "Specialized",
+ "type": "Enduro bikes",
+ "price": 3000
+ },
+}
+```
+
+#### Full JSON Path support
+Because Redis enables full JSON path support, when creating an index schema, elements need to be indexed and selected by their path with the desired `name` AND `path` that points to where the data is located within the objects.
+
+By default, RedisVL will assume the path as `$.{name}` if not provided in JSON fields schema. If nested provide path as `$.object.attribute`
+
+### As an example:
+
+
+```python
+from redisvl.utils.vectorize import HFTextVectorizer
+
+emb_model = HFTextVectorizer()
+
+bike_data = [
+ {
+ "name": "Specialized Stump jumper",
+ "metadata": {
+ "model": "Stumpjumper",
+ "brand": "Specialized",
+ "type": "Enduro bikes",
+ "price": 3000
+ },
+ "description": "The Specialized Stumpjumper is a versatile enduro bike that dominates both climbs and descents. Features a FACT 11m carbon fiber frame, FOX FLOAT suspension with 160mm travel, and SRAM X01 Eagle drivetrain. The asymmetric frame design and internal storage compartment make it a practical choice for all-day adventures."
+ },
+ {
+ "name": "bike_2",
+ "metadata": {
+ "model": "Slash",
+ "brand": "Trek",
+ "type": "Enduro bikes",
+ "price": 5000
+ },
+ "description": "Trek's Slash is built for aggressive enduro riding and racing. Featuring Trek's Alpha Aluminum frame with RE:aktiv suspension technology, 160mm travel, and Knock Block frame protection. Equipped with Bontrager components and a Shimano XT drivetrain, this bike excels on technical trails and enduro race courses."
+ }
+]
+
+bike_data = [{**d, "bike_embedding": emb_model.embed(d["description"])} for d in bike_data]
+
+bike_schema = {
+ "index": {
+ "name": "bike-json",
+ "prefix": "bike-json",
+ "storage_type": "json", # JSON storage type
+ },
+ "fields": [
+ {
+ "name": "model",
+ "type": "tag",
+ "path": "$.metadata.model" # note the '$'
+ },
+ {
+ "name": "brand",
+ "type": "tag",
+ "path": "$.metadata.brand"
+ },
+ {
+ "name": "price",
+ "type": "numeric",
+ "path": "$.metadata.price"
+ },
+ {
+ "name": "bike_embedding",
+ "type": "vector",
+ "attrs": {
+ "dims": len(bike_data[0]["bike_embedding"]),
+ "distance_metric": "cosine",
+ "algorithm": "flat",
+ "datatype": "float32"
+ }
+
+ }
+ ],
+}
+```
+
+ /Users/robert.shelton/.pyenv/versions/3.11.9/lib/python3.11/site-packages/huggingface_hub/file_download.py:1142: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
+ warnings.warn(
+
+
+
+```python
+# construct a search index from the json schema
+bike_index = SearchIndex.from_dict(bike_schema, redis_url="redis://localhost:6379")
+
+# create the index (no data yet)
+bike_index.create(overwrite=True)
+```
+
+
+```python
+bike_index.load(bike_data)
+```
+
+
+
+
+ ['bike-json:de92cb9955434575b20f4e87a30b03d5',
+ 'bike-json:054ab3718b984532b924946fa5ce00c6']
+
+
+
+
+```python
+from redisvl.query import VectorQuery
+
+vec = emb_model.embed("I'd like a bike for aggressive riding")
+
+v = VectorQuery(
+ vector=vec,
+ vector_field_name="bike_embedding",
+ return_fields=[
+ "brand",
+ "name",
+ "$.metadata.type"
+ ]
+)
+
+
+results = bike_index.query(v)
+```
+
+**Note:** As shown in the example if you want to retrieve a field from json object that was not indexed you will also need to supply the full path as with `$.metadata.type`.
+
+
+```python
+results
+```
+
+
+
+
+ [{'id': 'bike-json:054ab3718b984532b924946fa5ce00c6',
+ 'vector_distance': '0.519989073277',
+ 'brand': 'Trek',
+ '$.metadata.type': 'Enduro bikes'},
+ {'id': 'bike-json:de92cb9955434575b20f4e87a30b03d5',
+ 'vector_distance': '0.657624483109',
+ 'brand': 'Specialized',
+ '$.metadata.type': 'Enduro bikes'}]
+
+
+
+# Cleanup
+
+
+```python
+bike_index.delete()
+```
diff --git a/content/integrate/redisvl/user_guide/hybrid_queries.md b/content/integrate/redisvl/user_guide/hybrid_queries.md
index 15bfd11ccb..25b2ea8b2b 100644
--- a/content/integrate/redisvl/user_guide/hybrid_queries.md
+++ b/content/integrate/redisvl/user_guide/hybrid_queries.md
@@ -60,23 +60,33 @@ schema = {
from redisvl.index import SearchIndex
# construct a search index from the schema
-index = SearchIndex.from_dict(schema)
-
-# connect to local redis instance
-index.connect("redis://localhost:6379")
+index = SearchIndex.from_dict(schema, redis_url="redis://localhost:6379")
# create the index (no data yet)
index.create(overwrite=True)
```
+ 13:02:18 redisvl.index.index INFO Index already exists, overwriting.
+
+
```python
# use the CLI to see the created index
!rvl index listall
```
- 14:16:51 [RedisVL] INFO Indices:
- 14:16:51 [RedisVL] INFO 1. user_queries
+ 13:02:25 [RedisVL] INFO Indices:
+ 13:02:25 [RedisVL] INFO 1. float64_cache
+ 13:02:25 [RedisVL] INFO 2. float64_session
+ 13:02:25 [RedisVL] INFO 3. float16_cache
+ 13:02:25 [RedisVL] INFO 4. float16_session
+ 13:02:25 [RedisVL] INFO 5. float32_session
+ 13:02:25 [RedisVL] INFO 6. float32_cache
+ 13:02:25 [RedisVL] INFO 7. bfloat_cache
+ 13:02:25 [RedisVL] INFO 8. user_queries
+ 13:02:25 [RedisVL] INFO 9. student tutor
+ 13:02:25 [RedisVL] INFO 10. tutor
+ 13:02:25 [RedisVL] INFO 11. bfloat_session
@@ -112,7 +122,7 @@ result_print(results)
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
@@ -125,7 +135,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
@@ -138,7 +148,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
@@ -151,7 +161,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
What about scenarios where you might want to dynamically generate a list of tags? Have no fear. RedisVL allows you to do this gracefully without having to check for the **empty case**. The **empty case** is when you attempt to run a Tag filter on a field with no defined values to match:
@@ -170,7 +180,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
### Numeric Filters
@@ -188,7 +198,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
@@ -201,7 +211,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
@@ -214,7 +224,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
### Text Filters
@@ -233,7 +243,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
@@ -246,7 +256,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
@@ -259,7 +269,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
@@ -272,7 +282,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
@@ -285,7 +295,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
@@ -298,7 +308,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
Use raw query strings as input. Below we use the `~` flag to indicate that the full text query is optional. We also choose the BM25 scorer and return document scores along with the result.
@@ -314,15 +324,15 @@ index.query(v)
- [{'id': 'user_queries_docs:409ff48274724984ba14865db0495fc5',
- 'score': 0.9090908893868948,
+ [{'id': 'user_queries_docs:01JMJJHE28ZW4F33ZNRKXRHYCS',
+ 'score': 1.8181817787737895,
'vector_distance': '0',
'user': 'john',
'credit_score': 'high',
'age': '18',
'job': 'engineer',
'office_location': '-122.4194,37.7749'},
- {'id': 'user_queries_docs:69cb262c303a4147b213dfdec8bd4b01',
+ {'id': 'user_queries_docs:01JMJJHE2899024DYPXT6424N9',
'score': 0.0,
'vector_distance': '0',
'user': 'derrick',
@@ -330,15 +340,47 @@ index.query(v)
'age': '14',
'job': 'doctor',
'office_location': '-122.4194,37.7749'},
- {'id': 'user_queries_docs:562263669ff74a0295c515018d151d7b',
- 'score': 0.9090908893868948,
+ {'id': 'user_queries_docs:01JMJJPEYCQ89ZQW6QR27J72WT',
+ 'score': 1.8181817787737895,
+ 'vector_distance': '0',
+ 'user': 'john',
+ 'credit_score': 'high',
+ 'age': '18',
+ 'job': 'engineer',
+ 'office_location': '-122.4194,37.7749'},
+ {'id': 'user_queries_docs:01JMJJPEYD544WB1TKDBJ3Z3J9',
+ 'score': 0.0,
+ 'vector_distance': '0',
+ 'user': 'derrick',
+ 'credit_score': 'low',
+ 'age': '14',
+ 'job': 'doctor',
+ 'office_location': '-122.4194,37.7749'},
+ {'id': 'user_queries_docs:01JMJJHE28B5R6T00DH37A7KSJ',
+ 'score': 1.8181817787737895,
+ 'vector_distance': '0.109129190445',
+ 'user': 'tyler',
+ 'credit_score': 'high',
+ 'age': '100',
+ 'job': 'engineer',
+ 'office_location': '-122.0839,37.3861'},
+ {'id': 'user_queries_docs:01JMJJPEYDPF9S5328WHCQN0ND',
+ 'score': 1.8181817787737895,
'vector_distance': '0.109129190445',
'user': 'tyler',
'credit_score': 'high',
'age': '100',
'job': 'engineer',
'office_location': '-122.0839,37.3861'},
- {'id': 'user_queries_docs:94176145f9de4e288ca2460cd5d1188e',
+ {'id': 'user_queries_docs:01JMJJHE28G5F943YGWMB1ZX1V',
+ 'score': 0.0,
+ 'vector_distance': '0.158808946609',
+ 'user': 'tim',
+ 'credit_score': 'high',
+ 'age': '12',
+ 'job': 'dermatologist',
+ 'office_location': '-122.0839,37.3861'},
+ {'id': 'user_queries_docs:01JMJJPEYDKA9ARKHRK1D7KPXQ',
'score': 0.0,
'vector_distance': '0.158808946609',
'user': 'tim',
@@ -346,7 +388,7 @@ index.query(v)
'age': '12',
'job': 'dermatologist',
'office_location': '-122.0839,37.3861'},
- {'id': 'user_queries_docs:d0bcf6842862410583901004b6b3aeba',
+ {'id': 'user_queries_docs:01JMJJHE28NR7KF0EZEA433T2J',
'score': 0.0,
'vector_distance': '0.217882037163',
'user': 'taimur',
@@ -354,21 +396,13 @@ index.query(v)
'age': '15',
'job': 'CEO',
'office_location': '-122.0839,37.3861'},
- {'id': 'user_queries_docs:3dec0e9f2db04e19bff224c5a2a0ba3c',
+ {'id': 'user_queries_docs:01JMJJPEYD9EAVGJ2AZ8K9VX7Q',
'score': 0.0,
- 'vector_distance': '0.266666650772',
- 'user': 'nancy',
- 'credit_score': 'high',
- 'age': '94',
- 'job': 'doctor',
- 'office_location': '-122.4194,37.7749'},
- {'id': 'user_queries_docs:93ee6c0e4ccb42f6b7af7858ea6a6408',
- 'score': 0.0,
- 'vector_distance': '0.653301358223',
- 'user': 'joe',
- 'credit_score': 'medium',
- 'age': '35',
- 'job': 'dentist',
+ 'vector_distance': '0.217882037163',
+ 'user': 'taimur',
+ 'credit_score': 'low',
+ 'age': '15',
+ 'job': 'CEO',
'office_location': '-122.0839,37.3861'}]
@@ -389,7 +423,7 @@ result_print(index.query(v))
```
-| score | vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.4545454446934474 | 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.4545454446934474 | 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.4545454446934474 | 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
+| score | vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.4545454446934474 | 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.4545454446934474 | 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.4545454446934474 | 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.4545454446934474 | 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.4545454446934474 | 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.4545454446934474 | 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
@@ -402,7 +436,7 @@ result_print(index.query(v))
```
-| score | vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.4545454446934474 | 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.4545454446934474 | 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.4545454446934474 | 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.4545454446934474 | 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.4545454446934474 | 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.4545454446934474 | 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.4545454446934474 | 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| score | vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.4545454446934474 | 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.4545454446934474 | 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.4545454446934474 | 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.4545454446934474 | 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.4545454446934474 | 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.4545454446934474 | 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.4545454446934474 | 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.4545454446934474 | 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.4545454446934474 | 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.4545454446934474 | 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
@@ -415,7 +449,7 @@ result_print(index.query(v))
```
-| score | vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.0 | 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.0 | 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.0 | 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.0 | 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| score | vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.0 | 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.0 | 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.0 | 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.0 | 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.0 | 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.0 | 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.0 | 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
| 0.0 | 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
## Combining Filters
@@ -442,7 +476,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
### Union ("or")
@@ -461,7 +495,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
### Dynamic Combination
@@ -497,7 +531,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
@@ -509,7 +543,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
@@ -521,7 +555,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
@@ -533,7 +567,7 @@ result_print(index.query(v))
```
-| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.266666650772 | nancy | high | 94 | doctor | -122.4194,37.7749 |
| 0.653301358223 | joe | medium | 35 | dentist | -122.0839,37.3861 |
+| vector_distance | user | credit_score | age | job | office_location |
|---|
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0 | john | high | 18 | engineer | -122.4194,37.7749 |
| 0 | derrick | low | 14 | doctor | -122.4194,37.7749 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.109129190445 | tyler | high | 100 | engineer | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.158808946609 | tim | high | 12 | dermatologist | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
| 0.217882037163 | taimur | low | 15 | CEO | -122.0839,37.3861 |
## Non-vector Queries
@@ -557,7 +591,7 @@ result_print(results)
```
-| user | credit_score | age | job |
|---|
| derrick | low | 14 | doctor |
| taimur | low | 15 | CEO |
+| user | credit_score | age | job |
|---|
| derrick | low | 14 | doctor |
| taimur | low | 15 | CEO |
| derrick | low | 14 | doctor |
| taimur | low | 15 | CEO |
## Count Queries
@@ -577,7 +611,7 @@ count = index.query(filter_query)
print(f"{count} records match the filter expression {str(has_low_credit)} for the given index.")
```
- 2 records match the filter expression @credit_score:{low} for the given index.
+ 4 records match the filter expression @credit_score:{low} for the given index.
## Range Queries
@@ -602,7 +636,7 @@ result_print(results)
```
-| vector_distance | user | credit_score | age | job |
|---|
| 0 | john | high | 18 | engineer |
| 0 | derrick | low | 14 | doctor |
| 0.109129190445 | tyler | high | 100 | engineer |
| 0.158808946609 | tim | high | 12 | dermatologist |
+| vector_distance | user | credit_score | age | job |
|---|
| 0 | john | high | 18 | engineer |
| 0 | derrick | low | 14 | doctor |
| 0 | john | high | 18 | engineer |
| 0 | derrick | low | 14 | doctor |
| 0.109129190445 | tyler | high | 100 | engineer |
| 0.109129190445 | tyler | high | 100 | engineer |
| 0.158808946609 | tim | high | 12 | dermatologist |
| 0.158808946609 | tim | high | 12 | dermatologist |
We can also change the distance threshold of the query object between uses if we like. Here we will set ``distance_threshold==0.1``. This means that the query object will return all matches that are within 0.1 of the query object. This is a small distance, so we expect to get fewer matches than before.
@@ -615,7 +649,7 @@ result_print(index.query(range_query))
```
-| vector_distance | user | credit_score | age | job |
|---|
| 0 | john | high | 18 | engineer |
| 0 | derrick | low | 14 | doctor |
+| vector_distance | user | credit_score | age | job |
|---|
| 0 | john | high | 18 | engineer |
| 0 | derrick | low | 14 | doctor |
| 0 | john | high | 18 | engineer |
| 0 | derrick | low | 14 | doctor |
Range queries can also be used with filters like any other query type. The following limits the results to only include records with a ``job`` of ``engineer`` while also being within the vector range (aka distance).
@@ -630,7 +664,7 @@ result_print(index.query(range_query))
```
-| vector_distance | user | credit_score | age | job |
|---|
| 0 | john | high | 18 | engineer |
+| vector_distance | user | credit_score | age | job |
|---|
| 0 | john | high | 18 | engineer |
| 0 | john | high | 18 | engineer |
## Advanced Query Modifiers
@@ -653,7 +687,7 @@ result_print(result)
```
-| vector_distance | age | user | credit_score | job | office_location |
|---|
| 0.109129190445 | 100 | tyler | high | engineer | -122.0839,37.3861 |
| 0 | 18 | john | high | engineer | -122.4194,37.7749 |
+| vector_distance | age | user | credit_score | job | office_location |
|---|
| 0.109129190445 | 100 | tyler | high | engineer | -122.0839,37.3861 |
| 0.109129190445 | 100 | tyler | high | engineer | -122.0839,37.3861 |
| 0 | 18 | john | high | engineer | -122.4194,37.7749 |
| 0 | 18 | john | high | engineer | -122.4194,37.7749 |
### Raw Redis Query String
@@ -715,10 +749,14 @@ for r in results.docs:
print(r.__dict__)
```
- {'id': 'user_queries_docs:409ff48274724984ba14865db0495fc5', 'payload': None, 'user': 'john', 'age': '18', 'job': 'engineer', 'credit_score': 'high', 'office_location': '-122.4194,37.7749', 'user_embedding': '==\x00\x00\x00?'}
- {'id': 'user_queries_docs:3dec0e9f2db04e19bff224c5a2a0ba3c', 'payload': None, 'user': 'nancy', 'age': '94', 'job': 'doctor', 'credit_score': 'high', 'office_location': '-122.4194,37.7749', 'user_embedding': '333?=\x00\x00\x00?'}
- {'id': 'user_queries_docs:562263669ff74a0295c515018d151d7b', 'payload': None, 'user': 'tyler', 'age': '100', 'job': 'engineer', 'credit_score': 'high', 'office_location': '-122.0839,37.3861', 'user_embedding': '=>\x00\x00\x00?'}
- {'id': 'user_queries_docs:94176145f9de4e288ca2460cd5d1188e', 'payload': None, 'user': 'tim', 'age': '12', 'job': 'dermatologist', 'credit_score': 'high', 'office_location': '-122.0839,37.3861', 'user_embedding': '>>\x00\x00\x00?'}
+ {'id': 'user_queries_docs:01JMJJHE28G5F943YGWMB1ZX1V', 'payload': None, 'user': 'tim', 'age': '12', 'job': 'dermatologist', 'credit_score': 'high', 'office_location': '-122.0839,37.3861', 'user_embedding': '>>\x00\x00\x00?'}
+ {'id': 'user_queries_docs:01JMJJHE28ZW4F33ZNRKXRHYCS', 'payload': None, 'user': 'john', 'age': '18', 'job': 'engineer', 'credit_score': 'high', 'office_location': '-122.4194,37.7749', 'user_embedding': '==\x00\x00\x00?'}
+ {'id': 'user_queries_docs:01JMJJHE28B5R6T00DH37A7KSJ', 'payload': None, 'user': 'tyler', 'age': '100', 'job': 'engineer', 'credit_score': 'high', 'office_location': '-122.0839,37.3861', 'user_embedding': '=>\x00\x00\x00?'}
+ {'id': 'user_queries_docs:01JMJJHE28EX13NEE7BGBM8FH3', 'payload': None, 'user': 'nancy', 'age': '94', 'job': 'doctor', 'credit_score': 'high', 'office_location': '-122.4194,37.7749', 'user_embedding': '333?=\x00\x00\x00?'}
+ {'id': 'user_queries_docs:01JMJJPEYCQ89ZQW6QR27J72WT', 'payload': None, 'user': 'john', 'age': '18', 'job': 'engineer', 'credit_score': 'high', 'office_location': '-122.4194,37.7749', 'user_embedding': '==\x00\x00\x00?'}
+ {'id': 'user_queries_docs:01JMJJPEYDAN0M3V7EQEVPS6HX', 'payload': None, 'user': 'nancy', 'age': '94', 'job': 'doctor', 'credit_score': 'high', 'office_location': '-122.4194,37.7749', 'user_embedding': '333?=\x00\x00\x00?'}
+ {'id': 'user_queries_docs:01JMJJPEYDPF9S5328WHCQN0ND', 'payload': None, 'user': 'tyler', 'age': '100', 'job': 'engineer', 'credit_score': 'high', 'office_location': '-122.0839,37.3861', 'user_embedding': '=>\x00\x00\x00?'}
+ {'id': 'user_queries_docs:01JMJJPEYDKA9ARKHRK1D7KPXQ', 'payload': None, 'user': 'tim', 'age': '12', 'job': 'dermatologist', 'credit_score': 'high', 'office_location': '-122.0839,37.3861', 'user_embedding': '>>\x00\x00\x00?'}
diff --git a/content/integrate/redisvl/user_guide/vectorizers.md b/content/integrate/redisvl/user_guide/vectorizers.md
index 516861aca3..fe538de131 100644
--- a/content/integrate/redisvl/user_guide/vectorizers.md
+++ b/content/integrate/redisvl/user_guide/vectorizers.md
@@ -75,6 +75,25 @@ print("Vector dimensions: ", len(test))
test[:10]
```
+ Vector dimensions: 1536
+
+
+
+
+
+ [-0.0011391325388103724,
+ -0.003206387162208557,
+ 0.002380132209509611,
+ -0.004501554183661938,
+ -0.010328996926546097,
+ 0.012922565452754498,
+ -0.005491119809448719,
+ -0.0029864837415516376,
+ -0.007327961269766092,
+ -0.03365817293524742]
+
+
+
```python
# Create many embeddings at once
@@ -89,6 +108,22 @@ embeddings[0][:10]
```
+
+
+ [-0.017466850578784943,
+ 1.8471690054866485e-05,
+ 0.00129731057677418,
+ -0.02555876597762108,
+ -0.019842341542243958,
+ 0.01603139191865921,
+ -0.0037347301840782166,
+ 0.0009670283179730177,
+ 0.006618348415941,
+ -0.02497442066669464]
+
+
+
+
```python
# openai also supports asyncronous requests, which we can use to speed up the vectorization process.
embeddings = await oai.aembed_many(sentences)
@@ -96,6 +131,9 @@ print("Number of Embeddings:", len(embeddings))
```
+ Number of Embeddings: 3
+
+
### Azure OpenAI
The ``AzureOpenAITextVectorizer`` is a variation of the OpenAI vectorizer that calls OpenAI models within Azure. If you've already installed ``openai``, then you're ready to use Azure OpenAI.
@@ -132,6 +170,66 @@ test[:10]
```
+ ---------------------------------------------------------------------------
+
+ ValueError Traceback (most recent call last)
+
+ Cell In[7], line 4
+ 1 from redisvl.utils.vectorize import AzureOpenAITextVectorizer
+ 3 # create a vectorizer
+ ----> 4 az_oai = AzureOpenAITextVectorizer(
+ 5 model=deployment_name, # Must be your CUSTOM deployment name
+ 6 api_config={
+ 7 "api_key": api_key,
+ 8 "api_version": api_version,
+ 9 "azure_endpoint": azure_endpoint
+ 10 },
+ 11 )
+ 13 test = az_oai.embed("This is a test sentence.")
+ 14 print("Vector dimensions: ", len(test))
+
+
+ File ~/src/redis-vl-python/redisvl/utils/vectorize/text/azureopenai.py:78, in AzureOpenAITextVectorizer.__init__(self, model, api_config, dtype)
+ 54 def __init__(
+ 55 self,
+ 56 model: str = "text-embedding-ada-002",
+ 57 api_config: Optional[Dict] = None,
+ 58 dtype: str = "float32",
+ 59 ):
+ 60 """Initialize the AzureOpenAI vectorizer.
+ 61
+ 62 Args:
+ (...)
+ 76 ValueError: If an invalid dtype is provided.
+ 77 """
+ ---> 78 self._initialize_clients(api_config)
+ 79 super().__init__(model=model, dims=self._set_model_dims(model), dtype=dtype)
+
+
+ File ~/src/redis-vl-python/redisvl/utils/vectorize/text/azureopenai.py:106, in AzureOpenAITextVectorizer._initialize_clients(self, api_config)
+ 99 azure_endpoint = (
+ 100 api_config.pop("azure_endpoint")
+ 101 if api_config
+ 102 else os.getenv("AZURE_OPENAI_ENDPOINT")
+ 103 )
+ 105 if not azure_endpoint:
+ --> 106 raise ValueError(
+ 107 "AzureOpenAI API endpoint is required. "
+ 108 "Provide it in api_config or set the AZURE_OPENAI_ENDPOINT\
+ 109 environment variable."
+ 110 )
+ 112 api_version = (
+ 113 api_config.pop("api_version")
+ 114 if api_config
+ 115 else os.getenv("OPENAI_API_VERSION")
+ 116 )
+ 118 if not api_version:
+
+
+ ValueError: AzureOpenAI API endpoint is required. Provide it in api_config or set the AZURE_OPENAI_ENDPOINT environment variable.
+
+
+
```python
# Just like OpenAI, AzureOpenAI supports batching embeddings and asynchronous requests.
sentences = [
@@ -423,10 +521,7 @@ fields:
from redisvl.index import SearchIndex
# construct a search index from the schema
-index = SearchIndex.from_yaml("./schema.yaml")
-
-# connect to local redis instance
-index.connect("redis://localhost:6379")
+index = SearchIndex.from_yaml("./schema.yaml", redis_url="redis://localhost:6379")
# create the index (no data yet)
index.create(overwrite=True)