{"id":49298300,"url":"https://github.com/weni-ai/bothub-nlp-api","last_synced_at":"2026-04-26T05:03:59.944Z","repository":{"id":39962773,"uuid":"233106937","full_name":"weni-ai/bothub-nlp-api","owner":"weni-ai","description":null,"archived":false,"fork":false,"pushed_at":"2024-07-26T22:18:42.000Z","size":5155,"stargazers_count":4,"open_issues_count":3,"forks_count":1,"subscribers_count":7,"default_branch":"master","last_synced_at":"2024-07-26T23:29:33.539Z","etag":null,"topics":["bothub-nlp","celery","docker","fastapi","hacktoberfest","hacktoberfest-accepted","python","python3"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/weni-ai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","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,"dei":null,"publiccode":null,"codemeta":null},"funding":{"custom":["https://www.ilhasoft.com.br/en/contact/"]}},"created_at":"2020-01-10T18:26:01.000Z","updated_at":"2024-07-26T23:29:44.380Z","dependencies_parsed_at":"2023-10-02T23:04:19.995Z","dependency_job_id":"8516fb99-96bb-46de-9404-764299dbda64","html_url":"https://github.com/weni-ai/bothub-nlp-api","commit_stats":null,"previous_names":[],"tags_count":88,"template":false,"template_full_name":null,"purl":"pkg:github/weni-ai/bothub-nlp-api","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weni-ai%2Fbothub-nlp-api","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weni-ai%2Fbothub-nlp-api/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weni-ai%2Fbothub-nlp-api/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weni-ai%2Fbothub-nlp-api/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/weni-ai","download_url":"https://codeload.github.com/weni-ai/bothub-nlp-api/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weni-ai%2Fbothub-nlp-api/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32286273,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-25T18:29:39.964Z","status":"online","status_checked_at":"2026-04-26T02:00:05.962Z","response_time":129,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["bothub-nlp","celery","docker","fastapi","hacktoberfest","hacktoberfest-accepted","python","python3"],"created_at":"2026-04-26T05:03:59.046Z","updated_at":"2026-04-26T05:03:59.935Z","avatar_url":"https://github.com/weni-ai.png","language":"Python","funding_links":["https://www.ilhasoft.com.br/en/contact/"],"categories":[],"sub_categories":[],"readme":"# Bothub NLP - Natural Language Processing services\n\n[![Build Status](https://travis-ci.org/bothub-it/bothub-nlp-api.svg?branch=master)](https://travis-ci.org/bothub-it/bothub-nlp-api) [![Coverage Status](https://coveralls.io/repos/github/bothub-it/bothub-nlp-api/badge.svg)](https://coveralls.io/github/bothub-it/bothub-nlp-api) ![version 2.2.0](https://img.shields.io/badge/version-2.2.0-blue.svg) [![python 3.6](https://img.shields.io/badge/python-3.6-green.svg)](https://docs.python.org/3.6/whatsnew/changelog.html) [![license AGPL-3.0](https://img.shields.io/badge/license-AGPL--3.0-red.svg)](https://github.com/udomobi/bothub-nlp/blob/master/LICENSE)\n\nCheck the [main Bothub project repository](https://github.com/Ilhasoft/bothub).\n\n\n## Services\n\n### bothub-nlp-api\n\n## Packages\n\n### [bothub-backend](https://github.com/bothub-it/bothub-backend) (python 3.6)\n\n### [bothub-nlp-celery](https://github.com/bothub-it/bothub-nlp-celery) (python 3.6)\n\n\n# Requirements\n\n* Python (3.6)\n* Docker\n* Docker-Compose\n\n## Development\n\nUse ```make``` commands to ```init_development_env```.\n\n| Command | Description |\n|--|--|\n| make init_development_env | Init file .env with variables environment\n\n## Environment Variables\n\n### General\n\n| Variable | Type | Default | Description |\n|--|--|--|--|\n| ENVIRONMENT | `str` | `production` | |\n| BOTHUB_ENGINE_URL | `str` | `https://api.bothub.it` | Web service api url |\n| BOTHUB_NLP_API_HOST | `str` | `0.0.0.0` | Web service ip |\n| BOTHUB_NLP_API_PORT | `int` | `2657` | Web service port |\n| BOTHUB_NLP_API_WEB_CONCURRENCY | `int` | `None` |  |\n| BOTHUB_NLP_API_WORKERS_PER_CORE | `int` | `3` |  |\n| BOTHUB_NLP_API_LOG_LEVEL | `str` | `info` |  |\n| BOTHUB_NLP_API_KEEPALIVE | `int` | `120` |  |\n| BOTHUB_NLP_SENTRY_CLIENT | `bool` | `False` | Enable Sentry Client |\n| BOTHUB_NLP_SENTRY | `str` | `None` | Sentry Client URL |\n| SUPPORTED_LANGUAGES | `str` | `en|pt` | Set supported languages. Separate languages using `|` |\n\n### QA tasks\n\n| Variable | Type | Default | Description |\n|--|--|--|--|\n| BOTHUB_NLP_API_ENABLE_QA_ROUTE | `bool` | `False` | Enable QA api route |\n| BOTHUB_NLP_API_QA_TEXT_LIMIT | `int` | `25000` | Limit of characters allowed in QA text |\n| BOTHUB_NLP_API_QA_QUESTION_LIMIT | `int` | `500` | Limit of characters allowed in QA question |\n\n\n### Training\n\n| Variable | Type | Default | Description |\n|--|--|--|--|\n| BOTHUB_SERVICE_TRAIN | `str` | `celery` | `celery` to train on celery worker or `ai-platform` to use GCP service |\n| BOTHUB_GOOGLE_PROJECT_ID | `int` | `None` | GCP project id |\n| BOTHUB_GOOGLE_CREDENTIALS_REFRESH_TOKEN | `str` | `None` | GCP credentials |\n| BOTHUB_GOOGLE_CREDENTIALS_TOKEN_URI | `str` | `None` | GCP credentials |\n| BOTHUB_GOOGLE_CREDENTIALS_CLIENT_ID | `str` | `None` | GCP credentials |\n| BOTHUB_GOOGLE_CREDENTIALS_CLIENT_SECRET | `str` | `None` | GCP credentials |\n| BOTHUB_GOOGLE_AI_PLATFORM_REGISTRY | `str` | `us.gcr.io/bothub/bothub-nlp-ai-platform` | Google Container Registry (GCR) project url |\n| BOTHUB_GOOGLE_AI_PLATFORM_IMAGE_VERSION | `str` | `1.0.0` | String to match built image version in google GCR |\n| BOTHUB_GOOGLE_AI_PLATFORM_PACKAGE_URI | `list` | `[\"gs://poc-training-ai-platform/bothub-nlp-ai-platform/bothub-nlp-ai-platform-0.1.tar.gz\"]` |  |\n| BOTHUB_GOOGLE_AI_PLATFORM_JOB_TIMEOUT | `int` | `None` | Time limit (seconds) a job can run before sending a cancel signal to GCP |\n\n### Celery connection\nNeeded variables to connect to celery running on workers\n\n| Variable | Type | Default | Description |\n|--|--|--|--|\n| BOTHUB_NLP_CELERY_BROKER_URL | `str` | `redis://localhost:6379/0` | Celery Broker URL, check usage instructions in [Celery Docs](http://docs.celeryproject.org/en/latest/index.html) |\n| BOTHUB_NLP_CELERY_BACKEND_URL | `str` | `BOTHUB_NLP_CELERY_BROKER_URL` value | Celery Backend URL, check usage instructions in [Celery Docs](http://docs.celeryproject.org/en/latest/index.html) |\n\n### Celery queue\nVariables to set available queues running on workers\n\n| Variable | Type | Default | Description |\n|--|--|--|--|\n| AVAILABLE_SPACY_MODELS | `string` | \u003ccode\u003een\u0026#124;pt_br\u0026#124;es\u0026#124;fr\u0026#124;ru\u003c/code\u003e | Available SPACY models of working nodes |\n| AVAILABLE_BERT_MODELS | `string` | \u003ccode\u003een\u0026#124;pt_br\u0026#124;xx\u003c/code\u003e | Available BERT models of working nodes |\n| AVAILABLE_QA_MODELS | `string` | \u003ccode\u003een\u0026#124;pt_br\u0026#124;xx\u003c/code\u003e | Available QA models of working nodes |\n| AVAILABLE_SPECIFIC_SPACY_QUEUES | `string` | \u003ccode\u003een\u0026#124;pt_br\u0026#124;es\u0026#124;fr\u0026#124;ru\u003c/code\u003e | Available languages with word2vec models. It means there is workers listening to `en-SPACY, pt_br-SPACY, ...` queues |\n| AVAILABLE_SPECIFIC_BERT_QUEUES | `string` | \u003ccode\u003een\u0026#124;pt_br\u003c/code\u003e | Available languages with BERT models. It means there is workers listening to `en-BERT, pt_br-BERT` queues. Other languages will be sent to `multilang-BERT` queue |\n| AVAILABLE_SPECIFIC_QA_QUEUES | `string` | \u003ccode\u003een\u0026#124;pt_br\u003c/code\u003e | Available languages with QA models. It means there is workers listening to `en-QA, pt_br-QA` queues. Other languages will be sent to `multilang-QA` queue |\n| AVAILABLE_SPECIFIC_QUEUES | `string` | `\"\"` | Languages without model that need to be handled in exclusive queues. It means there is workers listening to `\"\"` queue. Other languages will be sent to `multilang` queue |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fweni-ai%2Fbothub-nlp-api","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fweni-ai%2Fbothub-nlp-api","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fweni-ai%2Fbothub-nlp-api/lists"}