> ## Documentation Index
> Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt
> Use this file to discover all available pages before exploring further.
# FAQ Enrichment use case
> The FAQ enrichment use case uses a large language model (LLM) to ingest input text and return a JSON response that contains a list of question and answer pairs.
## OpenAPI
````yaml /api-reference/saas/machine-learning-platform-predict.json post /ai/prediction/faq-enrichment/{MODEL_ID}
openapi: 3.0.1
info:
title: Lucidworks AI Prediction API
version: v0
description: >-
The Lucidworks AI Prediction API is used to send synchronous API calls that
run predictions from pre-trained models or custom models.
The Use Case API returns a list of all supported models.
The `prediction` endpoints require an authentication token with scope
`machinelearning.predict`.
contact:
name: Lucidworks
url: https://lucidworks.com/
email: support@lucidworks.com
termsOfService: https://lucidworks.com/legal/developer-license-agreement/
license:
name: Lucidworks
url: https://lucidworks.com/legal/developer-license-agreement/
servers:
- url: https://APPLICATION_ID.applications.lucidworks.com
description: Production
security: []
tags:
- name: Get predictions
description: Submit prediction tasks to Lucidworks AI.
paths:
/ai/prediction/faq-enrichment/{MODEL_ID}:
post:
tags:
- Get predictions
summary: FAQ Enrichment use case
description: >-
The FAQ enrichment use case uses a large language model (LLM) to ingest
input text and return a JSON response that contains a list of question
and answer pairs.
operationId: post-ai-prediction-faq-enrichment-modelId
parameters:
- schema:
type: string
name: MODEL_ID
in: path
required: true
description: Unique identifier for the model.
example: bge-large
- in: header
name: Authorization
required: true
schema:
type: string
description: Bearer token used for authentication.
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/FaqEnrichmentRequest'
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/FaqEnrichmentResponse'
components:
schemas:
FaqEnrichmentRequest:
title: FaqEnrichmentRequest
type: object
x-examples: {}
properties:
batch:
type: array
description: >-
The text analyzed to predict possible frequently asked questions and
corresponding answers.
items:
type: object
properties:
text:
type: string
description: The content the model analyzes.
example: >-
Global Travel Spending and Payment Trends in 2024
Global tourism spending is expected to return to pre-pandemic
levels in 2024. However, with inflation still affecting
consumers, finding convenient and cost-effective payment
methods remains a top priority for travelers. To understand
payment preferences and behaviors, our Bank surveyed 1,800
consumers worldwide about their travel financing experiences
and future spending plans. The findings highlight six key
trends shaping how merchants can cater to global travelers.
1. Cash Remains Essential
While cash usage declined during the pandemic, it remains an
important travel resource. Half of respondents use cash for
purchases, while the other half carry it for emergencies.
Asian travelers rely on cash the most—99% reported carrying
it, compared to just 6% of total respondents who travel
without it.
2. Payment Choices Prioritize Ease, Deals, and Security
Travelers select payment methods based on convenience, the
best available deals, and security. Many prefer using
cash-on-hand (e.g., debit) over credit or financing options
like buy now, pay later.
3. Travelers Plan Around Payment Acceptance
Although credit cards are widely used, 73% of respondents have
faced acceptance issues while traveling, with 42% choosing not
to make a purchase as a result. To avoid complications, 72%
plan ahead to ensure their preferred payment method is
accepted, and 80% check for acceptance signage before
spending.
4. North American Travelers Favor Credit Cards
While most global travelers prefer debit cards, North
Americans rely heavily on credit—58% of respondents favor
credit cards over debit (43%) or cash (40%).
5. Airline-Branded Credit Cards Are Popular
Among travel-specific credit cards, airline-branded options
are the most widely used, with 15% of cardholders relying on
them. These cards are particularly popular in Asia and North
America.
6. Many Travelers Don’t Maximize Their Rewards
Although 43% of respondents have a travel rewards credit card,
many don’t use their points. Millennials are the most likely
to leverage travel rewards, and international travelers are
more likely to own a rewards card than domestic travelers.
However, only 54% of rewards cardholders use their points for
personal travel.
By understanding these trends, merchants can optimize payment
options to attract and accommodate travelers worldwide.
useCaseConfig:
$ref: '#/components/schemas/UseCaseConfigFaqEnrichment'
modelConfig:
$ref: '#/components/schemas/ModelConfig'
FaqEnrichmentResponse:
type: object
properties:
predictions:
type: array
items:
$ref: '#/components/schemas/FaqEnrichmentResponseTokens'
x-examples: {}
UseCaseConfigFaqEnrichment:
title: UseCaseConfigFaqEnrichment
type: object
properties:
maxPairs:
type: integer
example: 10
description: >-
This parameter specifies the maximum number of questions and answer
pairs that can be generated, though the model may not honor the
number specified in this field.
domain:
type: string
description: >-
This parameter specifies the domain specific for which the input FAQ
documents would be considered. The domain specification helps the
model generate more accurate and relevant questions for the content.
The domains are listed here.
enum:
- retail
- finance
- tourism
- consulting
- healthcare
- hospitality
- manufacturing
- it (information technology)
example: finance
ModelConfig:
title: ModelConfig
type: object
description: >-
Provides fields and values that specify ranges for tokens. Fields used
for specific use cases and models are specified. The default values are
used if other values are not specified.
properties:
temperature:
type: number
format: float
example: 0.8
minimum: 0
maximum: 2
description: >-
A sampling temperature between 0 and 2. A higher sampling
temperature such as 0.8, results in more random (creative) output. A
lower value such as 0.2 results in more focused (conservative)
output. A lower value does not guarantee the model returns the same
response for the same input. We recommend staying at or below a
temperature of 1.0. Values above 1.0 might return nonsense unless
the topP value is lowered to be more deterministic.
topP:
type: number
format: float
example: 1
minimum: 0
maximum: 1
description: >-
A floating-point number between 0 and 1 that controls the cumulative
probability of the top tokens to consider, known as the randomness
of the LLM's response. This parameter is also referred to as top
probability. Set `topP` to 1 to consider all tokens. A higher value
specifies a higher probability threshold and selects tokens whose
cumulative probability is greater than the threshold. The higher the
value, the more diverse the output.
topK:
type: integer
example: -1
description: >-
An integer that controls the number of top tokens to consider. Set
topK to -1 to consider all tokens.
presencePenalty:
type: number
format: float
minimum: -2
maximum: 2
description: >-
A floating-point number between -2.0 and 2.0 that penalizes new
tokens based on whether they have already appeared in the text. This
increases the model's use of diverse tokens. A value greater than
zero (0) encourages the model to use new tokens. A value less than
zero (0) encourages the model to repeat existing tokens. This is
applicable for all OpenAI and Llama models.
example: 2
frequencyPenalty:
type: number
format: float
minimum: -2
maximum: 2
example: 1
description: >-
A floating-point number between -2.0 and 2.0 that penalizes new
tokens based on their frequency in the generated text. A value
greater than zero (0) encourages the model to use new tokens. A
value less than zero (0) encourages the model to repeat existing
tokens. This is applicable for all OpenAI and Llama models.
maxTokens:
type: integer
format: int32
example: 1
description: >-
The maximum number of tokens to generate per output sequence. The
value is different for each model. Review individual model
specifications when the value exceeds 2048.
apiKey:
type: string
description: >-
This optional parameter is only required when using the model for
prediction. You can find this value in your model's settings:
* **OpenAI**: Copy and paste the API key found in your
organization's settings. For more information, see OpenAI
Authentication API keys.
* **Azure OpenAI**: Copy and paste the API key found in your Azure
portal. See Authenticate
with API key.
* **Anthropic**: Copy and paste the API key found in your Anthropic
console or by using the Anthropic
API.
* **Google Vertex AI**: Copy and paste the base64-encoded service
account key JSON found in your Google
Cloud console. This service account key must have the Vertex
AI user role enabled. For more information, see generate
service account key.
example: API key specific to use case and model
azureDeployment:
type: string
example: DEPLOYMENT_NAME
description: >-
This optional parameter is the name of the deployed Azure OpenAI
model and is only required when a deployed Azure OpenAI model is
used for prediction.
azureEndpoint:
type: string
description: "\t\nThis optional parameter is the URL endpoint of the deployed Azure OpenAI model and is only required when a deployed Azure OpenAI model is used for prediction."
example: https://azure.endpoint.com
googleProjectId:
type: string
example: '[GOOGLE_PROJECT_ID]'
description: >-
This parameter is optional, and is only required when a Google
Vertex AI model is used for prediction.
googleRegion:
type: string
description: >-
This parameter is optional, and is only required when a Google
Vertex AI model is used for prediction. A value of `global` routes
the query to any available region. Other possible region values are:
* us-central1
* us-west4
* northamerica-northeast1
* us-east4
* us-west1
* asia-northeast3
* asia-southeast1
* asia-northeast
example: '[GOOGLE_PROJECT_REGION_OF_MODEL_ACCESS]'
FaqEnrichmentResponseTokens:
type: object
properties:
faqPairs:
type: array
description: >-
A list of question and answer pairs returned from the FAQ enrichment
request.
items:
type: object
properties:
question:
type: string
description: The frequently asked question.
answer:
type: string
description: The answer corresponding to the question.
required:
- question
- answer
example:
- question: >-
What types of accounts are available for travelers looking to
manage their finances?
answer: >-
Travelers can choose from various account types such as debit
accounts, credit accounts, and travel-specific credit cards,
including airline-branded cards that offer travel rewards.
- question: >-
What are the eligibility requirements for obtaining a
travel-specific credit card?
answer: >-
Eligibility for travel-specific credit cards typically requires
a good credit score and a stable income. Specific requirements
may vary by issuer.
tokensUsed:
$ref: '#/components/schemas/Token'
Token:
type: object
properties:
promptTokens:
type: integer
format: int32
description: >-
The number of tokens generated to prompt the model to continue
generating results.
example: 148
completionTokens:
type: integer
format: int32
description: The number of tokens used until the model completes.
example: 27
totalTokens:
type: integer
format: int32
description: The sum of the prompt and completion tokens used in the model.
example: 175
````