{"id":19984494,"url":"https://github.com/intellabs/convassist","last_synced_at":"2026-03-09T17:10:57.124Z","repository":{"id":272847965,"uuid":"734085370","full_name":"IntelLabs/ConvAssist","owner":"IntelLabs","description":null,"archived":false,"fork":false,"pushed_at":"2025-02-27T15:14:59.000Z","size":99460,"stargazers_count":0,"open_issues_count":3,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-02-27T21:51:04.196Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/IntelLabs.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-12-20T20:42:09.000Z","updated_at":"2025-02-27T15:15:03.000Z","dependencies_parsed_at":"2025-02-07T02:26:34.464Z","dependency_job_id":"6f93e1ce-b539-4248-b19a-8bd522b16438","html_url":"https://github.com/IntelLabs/ConvAssist","commit_stats":null,"previous_names":["intellabs/convassist"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IntelLabs%2FConvAssist","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IntelLabs%2FConvAssist/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IntelLabs%2FConvAssist/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IntelLabs%2FConvAssist/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/IntelLabs","download_url":"https://codeload.github.com/IntelLabs/ConvAssist/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242250928,"owners_count":20096897,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-13T04:19:12.085Z","updated_at":"2026-03-09T17:10:57.115Z","avatar_url":"https://github.com/IntelLabs.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ConvAssist\n[![OpenSSF Scorecard](https://api.scorecard.dev/projects/github.com/IntelLabs/ConvAssist/badge)](https://scorecard.dev/viewer/?uri=github.com/IntelLabs/ConvAssist)\n[![Unit Tests](https://github.com/IntelLabs/ConvAssist/actions/workflows/run_unittests.yaml/badge.svg?branch=covassist-cleanup)](https://github.com/IntelLabs/ConvAssist/actions/workflows/run_unittests.yaml)\n[![pytorch](https://img.shields.io/badge/PyTorch-v2.4.1-green?logo=pytorch)](https://pytorch.org/get-started/locally/)\n![GitHub License](https://img.shields.io/github/license/IntelLabs/ConvAssist)\n![python-support](https://img.shields.io/badge/Python-3.12-3?logo=python)\n[![Documentation - Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/IntelLabs/ConvAssist)\n\nConvAssist is a library intended to enable and empower users with disabilities to communicate using the latest language modeling technologies, via Intel's Assistive Context Aware Toolkit, ACAT. ConvAssist can quickly suggest utterances/sentences that the user can use to have a social conversation or communicate with their caregiver in near real time. \n\nConvAssist is built on [Pressagio](https://github.com/Poio-NLP/pressagio), that is a library that predicts text based on n-gram models. Pressagio is a pure Python port of the [presage library](https://presage.sourceforge.io) and is part of the [Poio project](https://www.poio.eu).  \n\nConvAssist contains language models based on specific Assistive and Augmentative Communication (AAC) datasets, and dialog datasets, tailored for day-to-day communication in our assistive usecase. These language models support both next word prediction and sentence completion for enabling near-real time communication with least amount of user effort and intervention. \n\n## Predictor Classes\n\n### Sentence Completion Predictor\n```SentenceCompletionPredictor``` is a class that provides sentence completion predictions using a combination of n-gram models and GPT-2.\n\n### Spell Correct Predictor\n```SpellCorrectPredictor``` is a class that extends the Predictor class to provide spell correction functionality. It uses a spell checker to generate suggestions for the last token in the context.\n\n### Canned Phrases Predictor\n```CannedPhrasesPredictor``` is a class that searches a database of canned phrases to find matching next words and sentences based on a given context. \n\n### Canned Word Predictor\n```CannedWordPredictor``` is a specialized predictor that extends the SmoothedNgramPredictor.  It is designed to handle canned responses using natural language processing (NLP) techniques.\n\n### Smoothed NGram Predictor\n```SmoothedNgramPredictor``` is a class that extends the Predictor class to provide functionality for predicting the next word(s) in a sequence using smoothed n-grams.\n\n### General Word Predictor\n```GeneralWordPredictor``` is a class that extends SmoothedNgramPredictor to provide word predictions based on a precomputed set of most frequent starting words from an AAC dataset.\n\n## Installation and use\nConvAssist works with Python 3.12.x or greater. Create a virtual environment and install the required packages.  We provide a pyproject.toml file to assist, and use Poetry for package management.\n\n#### Create a Virtual Environment with Poetry\n\n1. **Clone the Repository**:\n    ```sh\n    git clone https://github.com/IntelLabs/ConvAssist.git\n    cd ConvAssist\n    ```\n\n2. **Install Poetry**:\n    If you don't have Poetry installed, you can install it by following the instructions on the [Poetry website](https://python-poetry.org/docs/#installation).\n\n3. **Install Dependencies and Create Virtual Environment**:\n    ```sh\n    poetry install\n    ```\n\n    This command will create a virtual environment, install the dependencies specified in the `pyproject.toml` file, and set up the environment for you.\n\n4. **Activate the Virtual Environment**:\n    ```sh\n    poetry shell\n    ```\n\n    This command activates the virtual environment created by Poetry.\n\n## Installation and use\nConvAssist works with Python 3.12.x or greater. Create a virtual environment and install the required packages.  We provide a pyproject.toml file to assist, and use Poetry for package management.\n\n#### Create a Virtual Environment with Poetry\n\n1. **Clone the Repository**:\n    ```sh\n    git clone https://github.com/IntelLabs/ConvAssist.git\n    cd ConvAssist\n    ```\n\n2. **Install Poetry**:\n    If you don't have Poetry installed, you can install it by following the instructions on the [Poetry website](https://python-poetry.org/docs/#installation).\n\n3. **Install Dependencies and Create Virtual Environment**:\n    ```sh\n    poetry install\n    ```\n\n    This command will create a virtual environment, install the dependencies specified in the `pyproject.toml` file, and set up the environment for you.\n\n4. **Activate the Virtual Environment**:\n    ```sh\n    poetry shell\n    ```\n\n    This command activates the virtual environment created by Poetry.\n\n### Run\nWe provide several demonstration apps to showcase how to use ConvAssist\n\n#### DEMO - Continuous Predict\n\n``` sh\ncd interfaces/Demos/continuous_predict\npython pyprompter.py\n```\n\nThe `continuous_prediction.ini` file defines which predictors are enable.  See documentation for continuous_predict for details on how to use the configuration file.\n\n## License\nConvAssist source code is distributed under the GPL-3.0 or later license.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintellabs%2Fconvassist","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fintellabs%2Fconvassist","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintellabs%2Fconvassist/lists"}