parla_process_documents #286
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Process documents (repository_dispatch) | |
| on: | |
| repository_dispatch: | |
| types: [parla_process_documents] | |
| jobs: | |
| process_documents: | |
| name: parla-process-documents-${{ github.event.client_payload.environment }} | |
| environment: ${{ github.event.client_payload.environment }} | |
| runs-on: ubuntu-latest | |
| env: | |
| SUPABASE_URL: ${{ secrets.SUPABASE_URL }} | |
| SUPABASE_SERVICE_ROLE_KEY: ${{ secrets.SUPABASE_SERVICE_ROLE_KEY }} | |
| SUPABASE_DB_CONNECTION: ${{ secrets.SUPABASE_DB_CONNECTION }} | |
| OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} | |
| OPENAI_MODEL: ${{ vars.OPENAI_MODEL }} | |
| OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL }} | |
| PROCESSING_DIR: ${{ vars.PROCESSING_DIR }} | |
| ALLOW_DELETION: ${{ vars.ALLOW_DELETION }} | |
| MAX_PAGES_LIMIT: ${{ vars.MAX_PAGES_LIMIT }} | |
| MAX_PAGES_FOR_LLM_PARSE_LIMIT: ${{ vars.MAX_PAGES_FOR_LLM_PARSE_LIMIT }} | |
| MAX_DOCUMENTS_TO_PROCESS_IN_ONE_RUN: ${{ vars.MAX_DOCUMENTS_TO_PROCESS_IN_ONE_RUN }} | |
| MAX_DOCUMENTS_TO_IMPORT_PER_DOCUMENT_TYPE: ${{ vars.MAX_DOCUMENTS_TO_IMPORT_PER_DOCUMENT_TYPE }} | |
| LLAMA_PARSE_TOKEN: ${{ secrets.LLAMA_PARSE_TOKEN }} | |
| steps: | |
| - name: checkout code | |
| uses: actions/checkout@v4 | |
| - name: Setup node | |
| uses: actions/setup-node@v4 | |
| with: | |
| node-version-file: '.nvmrc' | |
| - name: preparation | |
| run: npm ci && mkdir -p processing_data && curl https://oxzjdwqsmpgqlrziuugr.supabase.co/storage/v1/object/public/assets/deu.traineddata > deu.traineddata && ls -all | |
| - name: register documents | |
| run: npx tsx ./src/run_import.ts | |
| - name: process documents | |
| run: export PROCESSING_DIR=$(pwd)/processing_data && npx tsx ./src/run_process.ts |