Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions .github/workflows/docs-ingestion-ci.yml
Original file line number Diff line number Diff line change
Expand Up @@ -323,6 +323,17 @@ jobs:
working-directory: docs-embeddings
run: yarn build

- name: Restore embedding state from S3
working-directory: docs-embeddings
env:
AWS_REGION: ${{ vars.AWS_REGION }}
CONTENT_BUCKET_NAME: ${{ vars.CONTENT_BUCKET_NAME }}
run: |
mkdir -p state
aws s3 cp "s3://${CONTENT_BUCKET_NAME}/embed-state/indexed-hashes.json" state/indexed-hashes.json \
&& echo "Restored state from S3" \
|| echo "No previous state found — starting fresh"

- name: Run embedding sync
working-directory: docs-embeddings
env:
Expand All @@ -335,3 +346,10 @@ jobs:
EMBEDDING_CONCURRENCY: ${{ vars.EMBEDDING_CONCURRENCY }}
INGESTION_OUTPUT_PATH: ${{ github.workspace }}/docs-ingestion/output/chunks.json
run: node dist/index.js

- name: Persist embedding state to S3
working-directory: docs-embeddings
env:
AWS_REGION: ${{ vars.AWS_REGION }}
CONTENT_BUCKET_NAME: ${{ vars.CONTENT_BUCKET_NAME }}
run: aws s3 cp state/indexed-hashes.json "s3://${CONTENT_BUCKET_NAME}/embed-state/indexed-hashes.json"
Loading