firecrawl/.github/workflows/ci.yml
Gergő Móricz 8d467c8ca7
WebScraper refactor into scrapeURL (#714)
* feat: use strictNullChecking

* feat: switch logger to Winston

* feat(scrapeURL): first batch

* fix(scrapeURL): error swallow

* fix(scrapeURL): add timeout to EngineResultsTracker

* fix(scrapeURL): report unexpected error to sentry

* chore: remove unused modules

* feat(transfomers/coerce): warn when a format's response is missing

* feat(scrapeURL): feature flag priorities, engine quality sorting, PDF and DOCX support

* (add note)

* feat(scrapeURL): wip readme

* feat(scrapeURL): LLM extract

* feat(scrapeURL): better warnings

* fix(scrapeURL/engines/fire-engine;playwright): fix screenshot

* feat(scrapeURL): add forceEngine internal option

* feat(scrapeURL/engines): scrapingbee

* feat(scrapeURL/transformars): uploadScreenshot

* feat(scrapeURL): more intense tests

* bunch of stuff

* get rid of WebScraper (mostly)

* adapt batch scrape

* add staging deploy workflow

* fix yaml

* fix logger issues

* fix v1 test schema

* feat(scrapeURL/fire-engine/chrome-cdp): remove wait inserts on actions

* scrapeURL: v0 backwards compat

* logger fixes

* feat(scrapeurl): v0 returnOnlyUrls support

* fix(scrapeURL/v0): URL leniency

* fix(batch-scrape): ts non-nullable

* fix(scrapeURL/fire-engine/chromecdp): fix wait action

* fix(logger): remove error debug key

* feat(requests.http): use dotenv expression

* fix(scrapeURL/extractMetadata): extract custom metadata

* fix crawl option conversion

* feat(scrapeURL): Add retry logic to robustFetch

* fix(scrapeURL): crawl stuff

* fix(scrapeURL): LLM extract

* fix(scrapeURL/v0): search fix

* fix(tests/v0): grant larger response size to v0 crawl status

* feat(scrapeURL): basic fetch engine

* feat(scrapeURL): playwright engine

* feat(scrapeURL): add url-specific parameters

* Update readme and examples

* added e2e tests for most parameters. Still a few actions, location and iframes to be done.

* fixed type

* Nick:

* Update scrape.ts

* Update index.ts

* added actions and base64 check

* Nick: skipTls feature flag?

* 403

* todo

* todo

* fixes

* yeet headers from url specific params

* add warning when final engine has feature deficit

* expose engine results tracker for ScrapeEvents implementation

* ingest scrape events

* fixed some tests

* comment

* Update index.test.ts

* fixed rawHtml

* Update index.test.ts

* update comments

* move geolocation to global f-e option, fix removeBase64Images

* Nick:

* trim url-specific params

* Update index.ts

---------

Co-authored-by: Eric Ciarla <ericciarla@yahoo.com>
Co-authored-by: rafaelmmiller <8574157+rafaelmmiller@users.noreply.github.com>
Co-authored-by: Nicolas <nicolascamara29@gmail.com>
2024-11-07 20:57:33 +01:00

64 lines
1.9 KiB
YAML

name: CI/CD
on:
pull_request:
branches:
- main
# schedule:
# - cron: '0 */4 * * *'
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
BULL_AUTH_KEY: ${{ secrets.BULL_AUTH_KEY }}
FLY_API_TOKEN: ${{ secrets.FLY_API_TOKEN }}
HOST: ${{ secrets.HOST }}
LLAMAPARSE_API_KEY: ${{ secrets.LLAMAPARSE_API_KEY }}
POSTHOG_API_KEY: ${{ secrets.POSTHOG_API_KEY }}
POSTHOG_HOST: ${{ secrets.POSTHOG_HOST }}
NUM_WORKERS_PER_QUEUE: ${{ secrets.NUM_WORKERS_PER_QUEUE }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
PLAYWRIGHT_MICROSERVICE_URL: ${{ secrets.PLAYWRIGHT_MICROSERVICE_URL }}
PORT: ${{ secrets.PORT }}
REDIS_URL: ${{ secrets.REDIS_URL }}
SCRAPING_BEE_API_KEY: ${{ secrets.SCRAPING_BEE_API_KEY }}
SUPABASE_ANON_TOKEN: ${{ secrets.SUPABASE_ANON_TOKEN }}
SUPABASE_SERVICE_TOKEN: ${{ secrets.SUPABASE_SERVICE_TOKEN }}
SUPABASE_URL: ${{ secrets.SUPABASE_URL }}
TEST_API_KEY: ${{ secrets.TEST_API_KEY }}
HDX_NODE_BETA_MODE: 1
FIRE_ENGINE_BETA_URL: ${{ secrets.FIRE_ENGINE_BETA_URL }}
USE_DB_AUTHENTICATION: ${{ secrets.USE_DB_AUTHENTICATION }}
ENV: ${{ secrets.ENV }}
jobs:
pre-deploy:
name: Pre-deploy checks
runs-on: ubuntu-latest
services:
redis:
image: redis
ports:
- 6379:6379
steps:
- uses: actions/checkout@v3
- name: Set up Node.js
uses: actions/setup-node@v3
with:
node-version: "20"
- name: Install pnpm
run: npm install -g pnpm
- name: Install dependencies
run: pnpm install
working-directory: ./apps/api
- name: Start the application
run: npm start &
working-directory: ./apps/api
id: start_app
- name: Start workers
run: npm run workers &
working-directory: ./apps/api
id: start_workers
- name: Run E2E tests
run: |
npm run test:prod
working-directory: ./apps/api