This is an automated email from the ASF dual-hosted git repository.
aradzinski pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft-website.git
The following commit(s) were added to refs/heads/master by this push:
new 425132d WIP.
425132d is described below
commit 425132dcf8ccd78b3b3d4020c6a09bee85763376
Author: Aaron Radzinski <[email protected]>
AuthorDate: Fri Jan 22 14:05:19 2021 -0800
WIP.
---
docs.html | 41 +++++++++++++++++++----------------------
index.html | 21 ++++++++++++---------
2 files changed, 31 insertions(+), 31 deletions(-)
diff --git a/docs.html b/docs.html
index cffef50..000203f 100644
--- a/docs.html
+++ b/docs.html
@@ -25,24 +25,23 @@ id: overview
<section id="overview">
<h2 class="section-title">Overview</h2>
<p>
- Apache NLPCraft is a Java-based <a target=_blank
href="https://www.apache.org/licenses/";>open source</a> library for adding a
natural language
- interface to any applications. It can work with
- any private or public data source, and has no hardware or software
lock-in.
- You can build models and intents for NLPCraft using any JVM-based
languages like Java, Scala, Kotlin, Groovy, etc. NLPCraft
- exposes REST APIs for integration with user applications that can
be written in any language or system.
+ Apache NLPCraft is a Java-based <a target=_blank
href="https://www.apache.org/licenses/";>open source</a> library
+ for adding a natural language interaction interface to any
applications. It can connect with
+ any private or public data source, and has no hardware or software
lock-in. It is based on advanced intent-based matching
+ of the input utterances. You can build intents for NLPCraft using
any JVM-based languages like Java, Scala, Kotlin, Groovy, etc. NLPCraft
+ exposes REST APIs for integration with end-user applications that
can be written in any language or system.
</p>
<p>
- One of the key features of NLPCraft is its use of advance semantic
modelling that is tailor made for
- domain-specific natural language interface. It doesn't force
developers to use direct ML/DL
- approach involving time consuming model training or corpora
development leading to much <em>simpler <span class="amp">&</span> faster</em>
+ One of the key features of NLPCraft is its use of deterministic
intent matching that is tailor made for
+ domain-specific natural language interface. It doesn't force
developers to use direct deep learning
+ approach that involves time consuming model training or corpora
development - resulting in much <em>simpler <span class="amp">&</span>
faster</em>
implementation.
</p>
<p>
- Another key aspect of NLPCraft is its focus on processing English
language. Although it may sound
- counterintuitive, this narrower focus enables NLPCraft to deliver
unprecedented ease of use combined with
- unparalleled comprehension capabilities for English input
out-of-the-box. It's been shown that
- support for multiple languages in a single framework leads to
either watered down functionality or overly
- complicated configuration, training and usage. It's also important
to note that English language is spoken by more
+ Another key aspect of NLPCraft is its initial focus on processing
English language. Although it may sound
+ counterintuitive, this narrower initial focus enables NLPCraft to
deliver unprecedented ease of use combined with
+ unparalleled comprehension capabilities for English input
out-of-the-box. It avoids watered down functionality and overly
+ complicated configuration, training and usage. English language is
spoken by more
than a billion people on this planet and is de facto standard
global language of the business and commerce.
</p>
<p>
@@ -67,14 +66,13 @@ id: overview
NLPCraft employs model-as-a-code approach where entire data model
is an implementation of
<a target="javadoc"
href="/apis/latest/org/apache/nlpcraft/model/NCModel.html">NCModel</a> Java
interface that
can be developed using any JVM programming language like Java,
Scala, Kotlin or Groovy.
- Data model implementation defines how to interpret user input, and
how to query or control a particular
- data source. Model-as-a-code natively supports any software
lifecycle tools and frameworks in Java ecosystem.
+ Data model defines named entities, various configuration
properties as well as intents that use defined named entities. Model-as-a-code
natively supports
+ any software lifecycle tools and frameworks in Java ecosystem.
</p>
<p>
Typically, declarative portion of the model will be stored in a
separate JSON or YAML file
for simpler maintenance. There are no practical limitation on how
complex or simple a model
- can be, or what other tools it can use. Data models use
comprehensive <a href="/intent-matching.html">intent-based matching</a>
- provided by NLPCraft out-of-the-box.
+ can be, or what other tools it can use. Data models use
comprehensive <a href="/intent-matching.html">intent-based matching</a>.
</p>
<p>
To use data model it has to be deployed into a data probe.
@@ -98,14 +96,13 @@ id: overview
<section id="server">
<h3 class="section-title">REST Server</h3>
<p>
- REST server (or a cluster of REST servers behind a load balancer)
provides URL endpoint for user applications
- to securely query data sources using NLI via data models deployed
in data probes. Its main purpose is to
- accept REST-over-HTTP calls from user applications, manage
connected data probes, and route user requests
- to and from requested data probes.
+ REST server (or a cluster of REST servers behind a load balancer)
provides URL endpoint for end-user applications
+ to securely query data sources using natural language via data
models deployed in data probes. Its main purpose is to
+ accept REST-over-HTTP calls from end-user applications and route
these requests to and from requested data probes.
</p>
<p>
Unlike data probe that gets restarted every time the model is
changed, i.e. during development, the
- REST server is a "start-and-forget" component that can be launched
once while various data probes can
+ REST server is a "fire-and-forget" component that can be launched
once while various data probes can
continuously reconnect to it. It can typically run as a Docker
image locally on premise or in the cloud.
</p>
<p>
diff --git a/index.html b/index.html
index 48bdf24..1991c89 100644
--- a/index.html
+++ b/index.html
@@ -43,7 +43,7 @@ layout: default
to modern applications.
</p>
<p>
- Define your model and intents to interpret
+ Define the intents to interpret
user input using any JVM-based language like Java,
Scala, Groovy or Kotlin. Use REST API to explore the data with natural language.
</p>
<div class="learn-more">
@@ -55,7 +55,7 @@ layout: default
<h2 class="section-title">Natural <span>Language</span></h2>
<section>
<p>
- Natural Language Interface (NLI) enables users to
explore any type of data
+ Natural Language Interface enables users to explore
any type of data
using natural language augmenting existing UI/UX with
fidelity
and simplicity of a familiar spoken language.
</p>
@@ -249,17 +249,20 @@ layout: default
<section>
<p>
There are three main software components:
- <p>
- <b>Data model</b> specifies how to interpret user
input, how to query a data
- source, and how to format the result back. Developers
use model-as-a-code approach
+ </p>
+ <p>
+ <b>Data model</b> provides named entities,
configuration properties and intents.
+ Developers use model-as-a-code approach
to build models using any JVM language like Java,
Scala, Groovy or Kotlin.
- <p>
+ </p>
+ <p>
<b>Data probe</b> is a DMZ-deployed application
designed to securely
deploy and manage data models. Each probe can manage
multiple models and you can
have many probes.
- <p>
- <b>REST server</b> provides REST endpoint for user
applications to securely query data
- sources using NLI via data models deployed in data
probes.
+ </p>
+ <p>
+ <b>REST server</b> provides REST endpoint for end-user
applications to securely query data
+ sources using natural language via data models
deployed in data probes.
</p>
</section>
</div>
