{"id":13800809,"url":"https://github.com/IBM/Max-Question-Answering","last_synced_at":"2025-05-13T09:31:56.981Z","repository":{"id":39736073,"uuid":"207696489","full_name":"IBM/MAX-Question-Answering","owner":"IBM","description":"Answer questions on a given corpus of text.","archived":false,"fork":false,"pushed_at":"2023-05-23T00:41:00.000Z","size":491,"stargazers_count":33,"open_issues_count":6,"forks_count":21,"subscribers_count":15,"default_branch":"master","last_synced_at":"2025-05-07T05:42:15.627Z","etag":null,"topics":["docker-image","machine-learning","machine-learning-models","natural-language-processing","tensorflow"],"latest_commit_sha":null,"homepage":"https://developer.ibm.com/exchanges/models/all/max-question-answering","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/IBM.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2019-09-11T01:32:41.000Z","updated_at":"2023-10-01T10:16:56.000Z","dependencies_parsed_at":"2024-01-05T20:57:05.212Z","dependency_job_id":"b407bbd6-b107-4141-ada6-dc4c5e15b7e5","html_url":"https://github.com/IBM/MAX-Question-Answering","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IBM%2FMAX-Question-Answering","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IBM%2FMAX-Question-Answering/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IBM%2FMAX-Question-Answering/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IBM%2FMAX-Question-Answering/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/IBM","download_url":"https://codeload.github.com/IBM/MAX-Question-Answering/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253913246,"owners_count":21983285,"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":["docker-image","machine-learning","machine-learning-models","natural-language-processing","tensorflow"],"created_at":"2024-08-04T00:01:16.481Z","updated_at":"2025-05-13T09:31:55.079Z","avatar_url":"https://github.com/IBM.png","language":"Python","readme":"[![Build Status](https://travis-ci.com/IBM/MAX-Question-Answering.svg?branch=master)](https://travis-ci.com/IBM/MAX-Question-Answering) [![Website Status](https://img.shields.io/website/http/max-question-answering.codait-prod-41208c73af8fca213512856c7a09db52-0000.us-east.containers.appdomain.cloud/swagger.json.svg?label=api+demo)](http://max-question-answering.codait-prod-41208c73af8fca213512856c7a09db52-0000.us-east.containers.appdomain.cloud)\n\n[\u003cimg src=\"docs/deploy-max-to-ibm-cloud-with-kubernetes-button.png\" width=\"400px\"\u003e](http://ibm.biz/max-to-ibm-cloud-tutorial)\n\n# IBM Developer Model Asset Exchange: Question Answering Model\n\nThis repository contains code to instantiate and deploy a Question Answering model. Given a body of text (context) about a subject and questions about that subject, the model will answer questions based on the given context.\n\nThe model is based on the [BERT model](https://github.com/google-research/bert). The model files are hosted on\n[IBM Cloud Object Storage](https://max-cdn.cdn.appdomain.cloud/max-question-answering/1.0.0/assets.tar.gz).\nThe code in this repository deploys the model as a web service in a Docker container. This repository was developed\nas part of the [IBM Developer Model Asset Exchange](https://developer.ibm.com/exchanges/models/) and the public API is powered by [IBM Cloud](https://ibm.biz/Bdz2XM).\n\n## Model Metadata\n| Domain | Application | Industry  | Framework | Training Data | Input Data Format |\n| ------------- | --------  | -------- | --------- | --------- | -------------- |\n| Natural Language Processing | Question and Answer | General | TensorFlow | [SQuAD 1.1](https://rajpurkar.github.io/SQuAD-explorer/) | Text |\n\n_Note: the SQuAD 1.1 files are no longer on the dataset website but can be found on the [Google BERT](https://github.com/google-research/bert) repo_\n\n## Benchmark\n\nThe predictive performance of the model can be characterized by the benchmark table below.\n\n_Note: The performance of a model is not the only significant metric. The level of bias and fairness incorporated in the model are also of high importance. Learn more by reading up on the [AI Fairness 360 open source toolkit](http://ibm.biz/AI_Fairness_360)._\n\nOn datasets where the answers given are designed to not be exact matches to a span of text from the given context (MS MARCO), the model does not perform as well, since SQuAD 1.1 is a span-matching task.\n\n|  | SQuAD 1.1 | TriviaQA 1.0 for RC   | MS MARCO  |\n| -------- | --------  | -------- | --------- |\n| f1 Score | 88.7 | 60.9| 40.7 |\n| Exact Match | 81.5 | 53.8 | 9.4 |\n\n## References\n\n* _J. Devlin, M. Chang, K. Lee, K. Toutanova_, [\"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding\"](https://arxiv.org/abs/1810.04805), arXiv, 2018.\n* [Google BERT](https://github.com/google-research/bert)\n* [SQuAD Dataset](https://rajpurkar.github.io/SQuAD-explorer/) and version 1.1 on the [Google BERT](https://github.com/google-research/bert) repo\n\n## Licenses\n\n| Component | License | Link  |\n| ------------- | --------  | -------- |\n| This repository | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | [LICENSE](LICENSE) |\n| Fine-tuned Model Weights |  [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | [LICENSE](LICENSE)\n| Pre-trained Model Weights |  [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | [LICENSE](https://github.com/google-research/bert/blob/master/LICENSE)\n| Model Code (3rd party) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | [LICENSE](https://github.com/google-research/bert/blob/master/LICENSE) |\n| Test samples | [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/legalcode) | [samples README](samples/README.md) |\n\n## Pre-requisites:\n\n* `docker`: The [Docker](https://www.docker.com/) command-line interface. Follow the [installation instructions](https://docs.docker.com/install/) for your system.\n* The minimum recommended resources for this model is 2 GiB Memory and 4 CPUs.\n* If you are on x86-64/AMD64, your CPU must support [AVX](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions) at the minimum.\n\n## Deployment Options\n\n* [Deploy from Quay](#deploy-from-quay)\n* [Deploy on Red Hat OpenShift](#deploy-on-red-hat-openshift)\n* [Deploy on Kubernetes](#deploy-on-kubernetes)\n* [Run Locally](#run-locally)\n\n## Deploy from Quay\n\nTo run the docker image, which automatically starts the model serving API, run:\n\n```\n$ docker run -it -p 5000:5000 quay.io/codait/max-question-answering\n```\n\nThis will pull a pre-built image from This will pull a pre-built image from the Quay.io container registry (or use an\nexisting image if already cached locally) and run it. (or use an existing image if already cached locally) and run it.\nIf you'd rather checkout and build the model locally you can follow the [run locally](#run-locally) steps below.\n\n## Deploy on Red Hat OpenShift\n\nYou can deploy the model-serving microservice on Red Hat OpenShift by following the instructions for the OpenShift web console or the OpenShift Container Platform CLI [in this tutorial](https://developer.ibm.com/tutorials/deploy-a-model-asset-exchange-microservice-on-red-hat-openshift/), specifying `codait/max-question-answering` as the image name.\n\n## Deploy on Kubernetes\n\nYou can also deploy the model on Kubernetes using the latest docker image on Quay.\n\nOn your Kubernetes cluster, run the following commands:\n\n```\n$ kubectl apply -f https://github.com/IBM/MAX-Question-Answering/raw/master/max-question-answering.yaml\n```\n\nThe model will be available internally at port `5000`, but can also be accessed externally through the `NodePort`.\n\nA more elaborate tutorial on how to deploy this MAX model to production on [IBM Cloud](https://ibm.biz/Bdz2XM) can be found [here](http://ibm.biz/max-to-ibm-cloud-tutorial).\n\n## Run Locally\n\n1. [Build the Model](#1-build-the-model)\n2. [Deploy the Model](#2-deploy-the-model)\n3. [Use the Model](#3-use-the-model)\n4. [Run the Notebook](#4-run-the-notebook)\n5. [Development](#5-development)\n6. [Cleanup](#6-cleanup)\n\n\n### 1. Build the Model\n\nClone this repository locally. In a terminal, run the following command:\n\n```\n$ git clone https://github.com/IBM/MAX-Question-Answering.git\n```\n\nChange directory into the repository base folder:\n\n```\n$ cd MAX-Question-Answering\n```\n\nTo build the docker image locally, run:\n\n```\n$ docker build -t max-question-answering .\n```\n\nAll required model assets will be downloaded during the build process. _Note_ that currently this docker image is CPU only (we will add support for GPU images later).\n\n\n### 2. Deploy the Model\n\nTo run the docker image, which automatically starts the model serving API, run:\n\n```\n$ docker run -it -p 5000:5000 max-question-answering\n```\n\n### 3. Use the Model\n\nThe API server automatically generates an interactive Swagger documentation page. Go to `http://localhost:5000` to load it. From there you can explore the API and also create test requests.\n\nUse the `model/predict` endpoint to upload a test json file (you can use/alter the files from the `samples` folder) and get answers to the questions from the API.\n\nSample input:\n```json\n{\n  \"paragraphs\": [\n    {\n      \"context\": \"John lives in Brussels and works for the EU\",\n      \"questions\": [\n        \"Where does John Live?\",\n        \"What does John do?\",\n        \"What is his name?\"\n      ]\n    },\n    {\n      \"context\": \"Jane lives in Paris and works for the UN\",\n      \"questions\": [\n        \"Where does Jane Live?\",\n        \"What does Jane do?\"\n      ]\n    }\n  ]\n}\n```\n\n![Example of getting answers from the API](docs/swagger-screenshot.png)\n\nYou can also test it on the command line, for example:\n\n```shell\n$ curl -X POST \"http://localhost:5000/model/predict\" -H \"accept: application/json\" -H \"Content-Type: application/json\" -d \"{\\\"paragraphs\\\": [{ \\\"context\\\": \\\"John lives in Brussels and works for the EU\\\", \\\"questions\\\": [\\\"Where does John Live?\\\",\\\"What does John do?\\\",\\\"What is his name?\\\" ]},{ \\\"context\\\": \\\"Jane lives in Paris and works for the UN\\\", \\\"questions\\\": [\\\"Where does Jane Live?\\\",\\\"What does Jane do?\\\" ]}]}\"\n```\n\nYou should see a JSON response like that below:\n\n```json\n{\n  \"status\": \"ok\",\n  \"predictions\": [\n    [\n      \"Brussels\",\n      \"works for the EU\",\n      \"John\"\n    ],\n    [\n      \"Paris\",\n      \"works for the UN\"\n    ]\n  ]\n}\n```\n\n### 4. Run the Notebook\n\n[The demo notebook](samples/demo.ipynb) walks through how to use the model to run inference on a text file or on text in-memory. By default, the notebook uses the [hosted demo instance](http://max-question-answering.max.us-south.containers.appdomain.cloud), but you can use a locally running instance as well. _Note_ the demo requires `jupyter`, `pprint`, `json` and `requests`.\n\nRun the following command from the model repo base folder, in a new terminal window:\n\n```\n$ jupyter notebook\n```\n\nThis will start the notebook server. You can launch the demo notebook by clicking on `samples/demo.ipynb`.\n\n\n### 5. Development\n\nTo run the Flask API app in debug mode, edit `config.py` to set `DEBUG = True` under the application settings. You will then need to rebuild the docker image (see [step 1](#1-build-the-model)).\n\n### 6. Cleanup\n\nTo stop the Docker container, type `CTRL` + `C` in your terminal.\n\n## Train this Model on Watson Machine Learning\n\nThis model supports training from scratch on a custom dataset. Please follow the steps listed under the [training README](training/README.md) to retrain the model on [Watson Machine Learning](https://www.ibm.com/cloud/machine-learning), a deep learning as a service offering of [IBM Cloud](https://ibm.biz/Bdz2XM).\n\n## Resources and Contributions\n\nIf you are interested in contributing to the Model Asset Exchange project or have any queries, please follow the instructions [here](https://github.com/CODAIT/max-central-repo).\n","funding_links":[],"categories":["Data \u0026 AI"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FIBM%2FMax-Question-Answering","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FIBM%2FMax-Question-Answering","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FIBM%2FMax-Question-Answering/lists"}