Ctrl+K

Semantic Routing#

RedisVL provides a SemanticRouter interface to utilize Redis’ built-in search & aggregation in order to perform KNN-style classification over a set of Route references to determine the best match.

This notebook will go over how to use Redis as a Semantic Router for your applications

Define the Routes#

Below we define 3 different routes. One for technology, one for sports, and another for entertainment. Now for this example, the goal here is surely topic “classification”. But you can create routes and references for almost anything.

Each route has a set of references that cover the “semantic surface area” of the route. The incoming query from a user needs to be semantically similar to one or more of the references in order to “match” on the route.

from redisvl.extensions.router import Route


# Define routes for the semantic router
technology = Route(
    name="technology",
    references=[
        "what are the latest advancements in AI?",
        "tell me about the newest gadgets",
        "what's trending in tech?"
    ],
    metadata={"category": "tech", "priority": 1}
)

sports = Route(
    name="sports",
    references=[
        "who won the game last night?",
        "tell me about the upcoming sports events",
        "what's the latest in the world of sports?",
        "sports",
        "basketball and football"
    ],
    metadata={"category": "sports", "priority": 2}
)

entertainment = Route(
    name="entertainment",
    references=[
        "what are the top movies right now?",
        "who won the best actor award?",
        "what's new in the entertainment industry?"
    ],
    metadata={"category": "entertainment", "priority": 3}
)

Initialize the SemanticRouter#

SemanticRouter will automatically create an index within Redis upon initialization for the route references. By default, it uses the HFTextVectorizer to generate embeddings for each route reference.

import os
from redisvl.extensions.router import SemanticRouter
from redisvl.utils.vectorize import HFTextVectorizer

os.environ["TOKENIZERS_PARALLELISM"] = "false"

# Initialize the SemanticRouter
router = SemanticRouter(
    name="topic-router",
    vectorizer=HFTextVectorizer(),
    routes=[technology, sports, entertainment],
    redis_url="redis://localhost:6379",
    overwrite=True # Blow away any other routing index with this name
)

router.vectorizer

HFTextVectorizer(model='sentence-transformers/all-mpnet-base-v2', dims=768)

# look at the index specification created for the semantic router
!rvl index info -i topic-router

Index Information:
╭──────────────┬────────────────┬──────────────────┬─────────────────┬────────────╮
│ Index Name   │ Storage Type   │ Prefixes         │ Index Options   │   Indexing │
├──────────────┼────────────────┼──────────────────┼─────────────────┼────────────┤
│ topic-router │ HASH           │ ['topic-router'] │ []              │          0 │
╰──────────────┴────────────────┴──────────────────┴─────────────────┴────────────╯
Index Fields:
╭────────────┬─────────────┬────────┬────────────────┬────────────────┬────────────────┬────────────────┬────────────────┬────────────────┬─────────────────┬────────────────╮
│ Name       │ Attribute   │ Type   │ Field Option   │ Option Value   │ Field Option   │ Option Value   │ Field Option   │   Option Value │ Field Option    │ Option Value   │
├────────────┼─────────────┼────────┼────────────────┼────────────────┼────────────────┼────────────────┼────────────────┼────────────────┼─────────────────┼────────────────┤
│ route_name │ route_name  │ TAG    │ SEPARATOR      │ ,              │                │                │                │                │                 │                │
│ reference  │ reference   │ TEXT   │ WEIGHT         │ 1              │                │                │                │                │                 │                │
│ vector     │ vector      │ VECTOR │ algorithm      │ FLAT           │ data_type      │ FLOAT32        │ dim            │            768 │ distance_metric │ COSINE         │
╰────────────┴─────────────┴────────┴────────────────┴────────────────┴────────────────┴────────────────┴────────────────┴────────────────┴─────────────────┴────────────────╯

Simple routing#

# Query the router with a statement
route_match = router("Can you tell me about the latest in artificial intelligence?")
route_match

RouteMatch(name='technology', distance=0.119614243507)

# Query the router with a statement and return a miss
route_match = router("are aliens real?")
route_match

RouteMatch(name=None, distance=None)

# Toggle the runtime distance threshold
route_match = router("Which basketball team will win the NBA finals?", distance_threshold=0.7)
route_match

RouteMatch(name='sports', distance=0.554210186005)

We can also route a statement to many routes and order them by distance:

# Perform multi-class classification with route_many() -- toggle the max_k and the distance_threshold
route_matches = router.route_many("Lebron James", distance_threshold=1.0, max_k=3)
route_matches

[RouteMatch(name='sports', distance=0.758580708504),
 RouteMatch(name='entertainment', distance=0.812423825264),
 RouteMatch(name='technology', distance=0.88423516353)]

# Toggle the aggregation method -- note the different distances in the result
from redisvl.extensions.router.schema import DistanceAggregationMethod

route_matches = router.route_many("Lebron James", aggregation_method=DistanceAggregationMethod.min, distance_threshold=1.0, max_k=3)
route_matches

[RouteMatch(name='sports', distance=0.663253903389),
 RouteMatch(name='entertainment', distance=0.712985396385),
 RouteMatch(name='technology', distance=0.832674384117)]

Note the different route match distances. This is because we used the min aggregation method instead of the default avg approach.

Update the routing config#

from redisvl.extensions.router import RoutingConfig

router.update_routing_config(
    RoutingConfig(distance_threshold=1.0, aggregation_method=DistanceAggregationMethod.min, max_k=3)
)

route_matches = router.route_many("Lebron James")
route_matches

[RouteMatch(name='sports', distance=0.663253903389),
 RouteMatch(name='entertainment', distance=0.712985396385),
 RouteMatch(name='technology', distance=0.832674384117)]

Router serialization#

router.to_dict()

{'name': 'topic-router',
 'routes': [{'name': 'technology',
   'references': ['what are the latest advancements in AI?',
    'tell me about the newest gadgets',
    "what's trending in tech?"],
   'metadata': {'category': 'tech', 'priority': '1'}},
  {'name': 'sports',
   'references': ['who won the game last night?',
    'tell me about the upcoming sports events',
    "what's the latest in the world of sports?",
    'sports',
    'basketball and football'],
   'metadata': {'category': 'sports', 'priority': '2'}},
  {'name': 'entertainment',
   'references': ['what are the top movies right now?',
    'who won the best actor award?',
    "what's new in the entertainment industry?"],
   'metadata': {'category': 'entertainment', 'priority': '3'}}],
 'vectorizer': {'type': 'hf',
  'model': 'sentence-transformers/all-mpnet-base-v2'},
 'routing_config': {'distance_threshold': 1.0,
  'max_k': 3,
  'aggregation_method': 'min'}}

router2 = SemanticRouter.from_dict(router.to_dict(), redis_url="redis://localhost:6379")

assert router2 == router

15:16:28 redisvl.index.index INFO   Index already exists, not overwriting.

router.to_yaml("router.yaml", overwrite=True)

router3 = SemanticRouter.from_yaml("router.yaml", redis_url="redis://localhost:6379")

assert router3 == router2 == router

15:17:42 redisvl.index.index INFO   Index already exists, not overwriting.

Clean up the router#

# Use clear to flush all routes from the index
router.clear()

# Use delete to clear the index and remove it completely
router.delete()
On this page
Edit on GitHub
Show Source