We are currently in open beta. Please sign up for try it for free.
We are currently in open beta.
Please sign up for try it for free.
Intent Router
Intent Router
Intent Router
Captures the intent of the query and classifies it as a route
Captures the intent of the query
and classifies it as a route
Computer Science
Math
Biology
Intent Router
How do neural networks work
in machine learning?
Computer Science
Math
Biology
Intent Router
How do neural networks work
in machine learning?
Computer Science
Math
Biology
Intent Router
How do neural networks work
in machine learning?
What does the Intent Router do?
What does the Intent Router do?
What does the
Intent Router do?
Intent Router receives a natural language query along with a set of routes and then selects the route that matches the intent of the query.
Intent Router receives a natural language query along with a set of routes and then selects the route that matches the intent of the query.
!pip install sineps
import sineps
client = sineps.Client(SINEPS_API_KEY)
query = "How do neural networks work in machine learning?"
routes = [
{
"name": "mathematics",
"description": "Assign queries to this route when they are related to mathematics.",
"utterances": [
"What is the Pythagorean theorem?",
"Can you explain the concept of integrals?",
"What are the different types of symmetry in geometry?",
],
},
{
"name": "computer_science",
"description": "Assign queries to this route when they are related to computer science.",
"utterances": [
"What is the difference between Java and Python?",
"How does deep learning work?",
"What are the main principles of object-oriented programming?",
],
},
{
"name": "biology",
"description": "Assign queries to this route when they are related to biology.",
"utterances": [
"How do photosynthesis and cellular respiration differ?",
"What is the structure of a DNA molecule?",
"How do ecosystems maintain balance?",
],
},
]
response = client.exec_intent_router(query=query, routes=routes, allow_none=True)
print(f"{response.result.routes[0].name}")
# computer_science
!pip install sineps
import sineps
client = sineps.Client(SINEPS_API_KEY)
query = "How do neural networks work in machine learning?"
routes = [
{
"name": "mathematics",
"description": "Assign queries to this route when they are related to mathematics.",
"utterances": [
"What is the Pythagorean theorem?",
"Can you explain the concept of integrals?",
"What are the different types of symmetry in geometry?",
],
},
{
"name": "computer_science",
"description": "Assign queries to this route when they are related to computer science.",
"utterances": [
"What is the difference between Java and Python?",
"How does deep learning work?",
"What are the main principles of object-oriented programming?",
],
},
{
"name": "biology",
"description": "Assign queries to this route when they are related to biology.",
"utterances": [
"How do photosynthesis and cellular respiration differ?",
"What is the structure of a DNA molecule?",
"How do ecosystems maintain balance?",
],
},
]
response = client.exec_intent_router(query=query, routes=routes, allow_none=True)
print(f"{response.result.routes[0].name}")
# computer_science
Values
Values
Low-cost
Low-cost
138x cheaper than GPT-4o,
4x cheaper than GPT-4o mini
138x cheaper than GPT-4o,
4x cheaper than GPT-4o mini
Average cost / 1K calls in intent classification problems
0.029 $
0.025 $
Sineps
4 $
3 $
2 $
1 $
0 $
GPT - 4o
mini
GPT - 4o
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
0.1$
3.47 $
0.35 $
2.43 $
Average cost / 1K calls in intent classification problems
0.029 $
0.025 $
Sineps
4 $
3 $
2 $
1 $
0 $
GPT - 4o
mini
GPT - 4o
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
0.1$
3.47 $
0.35 $
2.43 $
Consistently Fast
Consistently Fast
Average latency 3.8x lower,
Maximum latency 6.8x lower than GPT-4o mini
Average latency 3.8x lower,
Maximum latency 6.8x lower than GPT-4o mini
1000ms
750ms
500ms
250ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
573ms
508ms
148ms
482ms
1195ms
1026ms
Average latency in intent classification problems
6000ms
4500ms
3000ms
1500ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
2089ms
6115ms
309ms
1573ms
3131ms
1821ms
Maximum latency (at 300 calls) in intent classification problems
1000ms
750ms
500ms
250ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
573ms
508ms
148ms
482ms
1195ms
1026ms
Average latency in intent classification problems
6000ms
4500ms
3000ms
1500ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
2089ms
6115ms
309ms
1573ms
3131ms
1821ms
Maximum latency (at 300 calls) in intent classification problems
1000ms
750ms
500ms
250ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
573ms
508ms
148ms
482ms
1195ms
1026ms
Average latency in intent classification problems
6000ms
4500ms
3000ms
1500ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
2089ms
6115ms
309ms
1573ms
3131ms
1821ms
Maximum latency (at 300 calls) in intent classification problems
1000ms
750ms
500ms
250ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
573ms
508ms
148ms
482ms
1195ms
1026ms
Average latency in intent classification problems
6000ms
4500ms
3000ms
1500ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
2089ms
6115ms
309ms
1573ms
3131ms
1821ms
Maximum latency (at 300 calls) in intent classification problems
1000ms
750ms
500ms
250ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
573ms
508ms
148ms
482ms
1195ms
1026ms
Average latency in intent classification problems
6000ms
4500ms
3000ms
1500ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
2089ms
6115ms
309ms
1573ms
3131ms
1821ms
Maximum latency (at 300 calls) in intent classification problems
1000ms
750ms
500ms
250ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
573ms
508ms
148ms
482ms
1195ms
1026ms
Average latency in intent classification problems
6000ms
4500ms
3000ms
1500ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
2089ms
6115ms
309ms
1573ms
3131ms
1821ms
Maximum latency (at 300 calls) in intent classification problems
1000ms
750ms
500ms
250ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
573ms
508ms
148ms
482ms
1195ms
1026ms
Average latency in intent classification problems
6000ms
4500ms
3000ms
1500ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
2089ms
6115ms
309ms
1573ms
3131ms
1821ms
Maximum latency (at 300 calls) in intent classification problems
1000ms
750ms
500ms
250ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
573ms
508ms
148ms
482ms
1195ms
1026ms
Average latency in intent classification problems
6000ms
4500ms
3000ms
1500ms
0ms
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
2089ms
6115ms
309ms
1573ms
3131ms
1821ms
Maximum latency (at 300 calls) in intent classification problems
Highly Accurate
Highly Accurate
GPT-4o level accuracy
GPT-4o level accuracy
Accuracy in intent classification problems
100%
95%
90%
85%
80%
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
97.32%
98.21%
97.32%
95.98%
100%
93.75%
Accuracy in intent classification problems
100%
95%
90%
85%
80%
GPT - 4o
mini
GPT - 4o
Sineps
GPT - 3.5
turbo
Claude 3.5
Sonnet
Semantic
Router
97.32%
98.21%
97.32%
95.98%
100%
93.75%
Multilingual
Multilingual
Supports English, Chinese, French, Korean, Spanish, Italian, and Arabic
Supports English, Chinese, French, Korean, Spanish, Italian, and Arabic
* We will make the dataset publicly available for evaluation.
* We will make the dataset publicly available for evaluation.
Use cases
Use cases
In your chatbot
application,
In your chatbot
application,
it enables the implementation of different response logic for different categories of questions
it enables the implementation of different response logic for different categories of questions
Intent Router
How to use
Recommendation
I want a refund for clothes I bought
Intent Router
How to use
Recommendation
I want a refund for clothes I bought
In your RAG
application,
In your RAG
application,
it selects the appropriate database
to answer the question
it selects the appropriate database
to answer the question
Intent Router
Large Language Model
I want to know the specifications of this laptop.
Electronics
Clothing
Food
Intent Router
Large Language Model
I want to know the specifications of this laptop.
Electronics
Clothing
Food
In your agent,
In your agent,
In your agent,
In your agent,
In your agent,
it ensures that commands
take appropriate follow-up actions
it ensures that commands
take appropriate follow-up actions
Intent Router
Check my meeting schedule for tomorrow.
View Calendar
Intent Router
Check my meeting schedule for tomorrow.
View Calendar
Sineps
Company : Ceres Technologies, Co., Ltd. | CEO : Inhyuk Na
Call : +82 70-7355-4189 | E-mail : infosec@sineps.io
Registration number : 716-81-02382
Address : 577, Dongdaegu-ro, Dong-gu, Daegu, Republic of Korea
ⓒ 2024 Ceres Technologies, All rights reserved.
Sineps
Company : Ceres Technologies, Co., Ltd.
CEO : Inhyuk Na
Call : +82 70-7355-4189
E-mail : infosec@sineps.io
Registration number : 716-81-02382
Address : 577, Dongdaegu-ro, Dong-gu,
Daegu, Republic of Korea
ⓒ 2024 Ceres Technologies,
All rights reserved.
Privacy Policy
Terms of Use