cisco/mindmeld

READ THIS FIRST

The MindMeld SDK is no longer maintained. Though once a state-of-the-art conversational AI platform, MindMeld has long since been surpassed by technologies enabled by LLMs. If you are currently using the MindMeld library, we advise you to evaluate alternatives. MindMeld hasn't had a release since November of 2022, and will not have any future releases.

Thank you to all our users and contributors.

MindMeld Conversational AI Platform

This repository contains the MindMeld Conversational AI Platform.

Introducing MindMeld

The MindMeld Conversational AI platform is among the most advanced AI platforms for building production-quality conversational applications. It is a Python-based machine learning framework which encompasses all of the algorithms and utilities required for this purpose. Evolved over several years of building and deploying dozens of the most advanced conversational experiences achievable, MindMeld is optimized for building advanced conversational assistants which demonstrate deep understanding of a particular use case or domain while providing highly useful and versatile conversational experiences.

MindMeld is the only Conversational AI platform available today that provides tools and capabilities for every step in the workflow for a state-of-the-art conversational application. The architecture of MindMeld is illustrated below.

To summarize, the functionality available in MindMeld includes:

• advanced Natural Language Processing, consisting of

  • Domain Classification
  • Intent Classification
  • Entity Recognition
  • Entity Role Labeling
  • Entity Resolution
  • Language Parsing

• versatile dialogue management

• custom knowledge base creation

• advanced question answering

• training data collection and management support

• large-scale data analytics

The MindMeld Philosophy

MindMeld has been used for applications in dozens of different domains by some of the largest global organizations. Over the course of these production deployments, MindMeld has evolved to be ideally suited for building production-quality, large-vocabulary language understanding capabilities for any custom application domain. This has been achieved by following the architectural philosophy whose guiding principles are expressed in the table below.

Quick Start

Assuming you have pip installed with Python 3.6 or Python 3.7 and Elasticsearch running in the background:

pip install mindmeld
mindmeld blueprint home_assistant
python -m home_assistant build
python -m home_assistant converse

For detailed installation instructions, see Getting Started. To start with pre-built sample applications, see MindMeld Blueprints.

MindMeld UI

You can use our sample web-based chat client interface to interact with any MindMeld application. This web UI also serves as a debugging tool to step through the various stages of query processing by the MindMeld pipeline.

git clone [email protected]:cisco/mindmeld.git
cd mindmeld/mindmeld-ui
npm install
npm start

For detailed installation instructions, see Getting Started for UI.

Note: this web client only works on Chrome browser.

How to contribute to the MindMeld platform:

We are very happy to receive your contributions. We maintain a list of open issues on our GitHub project.

You can also create your own issue and link it to your code in a pull request, which we will promptly review.

To setup local development for MindMeld, first you will need to fork the MindMeld repository from GitHub and follow instructions on Getting Started page to setup the virtual environment.

git clone [email protected]:[username]/mindmeld.git
cd mindmeld
virtualenv -p python3 .
source bin/activate

To develop MindMeld, you need Python 3.6 or Python 3.7. To install and manage different versions of Python, you can checkout pyenv which also works with virtualenv.

Now we can install MindMeld and its dependencies:

pip install -e .
pip install -r dev-requirements.txt
pip install -r test-requirements.txt

Make sure that the numerical parser and Elasticsearch are running in the background. Finally we are ready to run MindMeld static style checks and unit tests.

./lintme
cd tests
pytest .

After making changes and all tests are passing locally, commit the code to your fork and issue a PR against the cisco/mindmeld repo.

Documentation

You can view the documentation for the latest stable release on mindmeld.com/docs and the documentation for the latest master branch version on our Github Page.

You can contribute to the documentation under the source directory.

To generate the documentation, please follow these steps:

pip install -r docs-requirements.txt
make apidoc

Citation

Please cite this paper if you use MindMeld in your work:

Raghuvanshi, A., Carroll, L. and Raghunathan, K., 2018, November. Developing Production-Level Conversational Interfaces with Shallow Semantic Parsing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (pp. 157-162)

@inproceedings{raghuvanshi2018developing,
  title={Developing Production-Level Conversational Interfaces with Shallow Semantic Parsing},
  author={Raghuvanshi, Arushi and Carroll, Lucien and Raghunathan, Karthik},
  booktitle={Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing:
             System Demonstrations},
  pages={157--162},
  year={2018}
}

Want to learn more about MindMeld?

Visit the MindMeld website.

Feedback or Support Questions

Please contact us at [email protected].