Skip to content

Add job_id to table schemata. #2096

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
whilo wants to merge 6 commits into
base: edge
Choose a base branch
from
Draft

Add job_id to table schemata. #2096

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
391ece7
Add job_id to table schemata.
whilo Jul 13, 2025
2905409
Add changes to the rest of the pipeline.
whilo Jul 13, 2025
e062b08
Keep separate conversation and comment ids and make job id optionally…
whilo Jul 14, 2025
961b846
Work towards job system.
whilo Jul 21, 2025
b4c4a3b
Better job-id pass through with fixes (WIP).
whilo Jul 23, 2025
8bc5d91
Fix job id passing.
whilo Jul 24, 2025
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
159 changes: 150 additions & 9 deletions delphi/create_dynamodb_tables.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,10 @@ def create_job_queue_table(dynamodb, delete_existing=False):
{'AttributeName': 'conversation_id', 'AttributeType': 'S'},
{'AttributeName': 'job_type', 'AttributeType': 'S'},
{'AttributeName': 'priority', 'AttributeType': 'N'},
{'AttributeName': 'worker_id', 'AttributeType': 'S'}
{'AttributeName': 'worker_id', 'AttributeType': 'S'},
{'AttributeName': 'parent_job_id', 'AttributeType': 'S'},
{'AttributeName': 'root_job_id', 'AttributeType': 'S'},
{'AttributeName': 'job_stage', 'AttributeType': 'S'}
],
'BillingMode': 'PAY_PER_REQUEST',

Expand Down Expand Up @@ -201,6 +204,31 @@ def create_job_queue_table(dynamodb, delete_existing=False):
{'AttributeName': 'status', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
},
# Job tree-related indexes
{
'IndexName': 'ParentJobIndex',
'KeySchema': [
{'AttributeName': 'parent_job_id', 'KeyType': 'HASH'},
{'AttributeName': 'created_at', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
},
{
'IndexName': 'RootJobIndex',
'KeySchema': [
{'AttributeName': 'root_job_id', 'KeyType': 'HASH'},
{'AttributeName': 'job_stage', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
},
{
'IndexName': 'JobStageIndex',
'KeySchema': [
{'AttributeName': 'job_stage', 'KeyType': 'HASH'},
{'AttributeName': 'created_at', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
}
],
}
Expand Down Expand Up @@ -301,7 +329,29 @@ def create_evoc_tables(dynamodb, delete_existing=False):
],
'AttributeDefinitions': [
{'AttributeName': 'conversation_id', 'AttributeType': 'S'},
{'AttributeName': 'comment_id', 'AttributeType': 'N'}
{'AttributeName': 'comment_id', 'AttributeType': 'N'},
{'AttributeName': 'job_id', 'AttributeType': 'S'},
{'AttributeName': 'created_at', 'AttributeType': 'S'}
],
'GlobalSecondaryIndexes': [
{
'IndexName': 'JobIdIndex',
'KeySchema': [
{'AttributeName': 'job_id', 'KeyType': 'HASH'},
{'AttributeName': 'conversation_id', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
'ProvisionedThroughput': {'ReadCapacityUnits': 5, 'WriteCapacityUnits': 5}
},
{
'IndexName': 'ConversationTimeIndex',
'KeySchema': [
{'AttributeName': 'conversation_id', 'KeyType': 'HASH'},
{'AttributeName': 'created_at', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
'ProvisionedThroughput': {'ReadCapacityUnits': 5, 'WriteCapacityUnits': 5}
}
],
'ProvisionedThroughput': {
'ReadCapacityUnits': 5,
Expand All @@ -315,7 +365,29 @@ def create_evoc_tables(dynamodb, delete_existing=False):
],
'AttributeDefinitions': [
{'AttributeName': 'conversation_id', 'AttributeType': 'S'},
{'AttributeName': 'comment_id', 'AttributeType': 'N'}
{'AttributeName': 'comment_id', 'AttributeType': 'N'},
{'AttributeName': 'job_id', 'AttributeType': 'S'},
{'AttributeName': 'created_at', 'AttributeType': 'S'}
],
'GlobalSecondaryIndexes': [
{
'IndexName': 'JobIdIndex',
'KeySchema': [
{'AttributeName': 'job_id', 'KeyType': 'HASH'},
{'AttributeName': 'conversation_id', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
'ProvisionedThroughput': {'ReadCapacityUnits': 5, 'WriteCapacityUnits': 5}
},
{
'IndexName': 'ConversationTimeIndex',
'KeySchema': [
{'AttributeName': 'conversation_id', 'KeyType': 'HASH'},
{'AttributeName': 'created_at', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
'ProvisionedThroughput': {'ReadCapacityUnits': 5, 'WriteCapacityUnits': 5}
}
],
'ProvisionedThroughput': {
'ReadCapacityUnits': 5,
Expand All @@ -329,7 +401,29 @@ def create_evoc_tables(dynamodb, delete_existing=False):
],
'AttributeDefinitions': [
{'AttributeName': 'conversation_id', 'AttributeType': 'S'},
{'AttributeName': 'cluster_key', 'AttributeType': 'S'}
{'AttributeName': 'cluster_key', 'AttributeType': 'S'},
{'AttributeName': 'job_id', 'AttributeType': 'S'},
{'AttributeName': 'created_at', 'AttributeType': 'S'}
],
'GlobalSecondaryIndexes': [
{
'IndexName': 'JobIdIndex',
'KeySchema': [
{'AttributeName': 'job_id', 'KeyType': 'HASH'},
{'AttributeName': 'conversation_id', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
'ProvisionedThroughput': {'ReadCapacityUnits': 5, 'WriteCapacityUnits': 5}
},
{
'IndexName': 'ConversationTimeIndex',
'KeySchema': [
{'AttributeName': 'conversation_id', 'KeyType': 'HASH'},
{'AttributeName': 'created_at', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
'ProvisionedThroughput': {'ReadCapacityUnits': 5, 'WriteCapacityUnits': 5}
}
],
'ProvisionedThroughput': {
'ReadCapacityUnits': 5,
Expand All @@ -343,7 +437,19 @@ def create_evoc_tables(dynamodb, delete_existing=False):
],
'AttributeDefinitions': [
{'AttributeName': 'conversation_id', 'AttributeType': 'S'},
{'AttributeName': 'edge_id', 'AttributeType': 'S'}
{'AttributeName': 'edge_id', 'AttributeType': 'S'},
{'AttributeName': 'job_id', 'AttributeType': 'S'}
],
'GlobalSecondaryIndexes': [
{
'IndexName': 'JobIdIndex',
'KeySchema': [
{'AttributeName': 'job_id', 'KeyType': 'HASH'},
{'AttributeName': 'conversation_id', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
'ProvisionedThroughput': {'ReadCapacityUnits': 5, 'WriteCapacityUnits': 5}
}
],
'ProvisionedThroughput': {
'ReadCapacityUnits': 5,
Expand All @@ -354,12 +460,25 @@ def create_evoc_tables(dynamodb, delete_existing=False):
# Extended tables
'Delphi_CommentClustersFeatures': {
'KeySchema': [
{'AttributeName': 'conversation_id', 'KeyType': 'HASH'},
{'AttributeName': 'cluster_key', 'KeyType': 'RANGE'}
{'AttributeName': 'job_id', 'KeyType': 'HASH'},
{'AttributeName': 'conversation_id_cluster_key', 'KeyType': 'RANGE'}
],
'AttributeDefinitions': [
{'AttributeName': 'job_id', 'AttributeType': 'S'},
{'AttributeName': 'conversation_id_cluster_key', 'AttributeType': 'S'},
{'AttributeName': 'conversation_id', 'AttributeType': 'S'},
{'AttributeName': 'cluster_key', 'AttributeType': 'S'}
{'AttributeName': 'created_at', 'AttributeType': 'S'}
],
'GlobalSecondaryIndexes': [
{
'IndexName': 'ConversationIndex',
'KeySchema': [
{'AttributeName': 'conversation_id', 'KeyType': 'HASH'},
{'AttributeName': 'created_at', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
'ProvisionedThroughput': {'ReadCapacityUnits': 5, 'WriteCapacityUnits': 5}
}
],
'ProvisionedThroughput': {
'ReadCapacityUnits': 5,
Expand All @@ -373,7 +492,29 @@ def create_evoc_tables(dynamodb, delete_existing=False):
],
'AttributeDefinitions': [
{'AttributeName': 'conversation_id', 'AttributeType': 'S'},
{'AttributeName': 'topic_key', 'AttributeType': 'S'}
{'AttributeName': 'topic_key', 'AttributeType': 'S'},
{'AttributeName': 'job_id', 'AttributeType': 'S'},
{'AttributeName': 'created_at', 'AttributeType': 'S'}
],
'GlobalSecondaryIndexes': [
{
'IndexName': 'JobIdIndex',
'KeySchema': [
{'AttributeName': 'job_id', 'KeyType': 'HASH'},
{'AttributeName': 'conversation_id', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
'ProvisionedThroughput': {'ReadCapacityUnits': 5, 'WriteCapacityUnits': 5}
},
{
'IndexName': 'ConversationTimeIndex',
'KeySchema': [
{'AttributeName': 'conversation_id', 'KeyType': 'HASH'},
{'AttributeName': 'created_at', 'KeyType': 'RANGE'}
],
'Projection': {'ProjectionType': 'ALL'},
'ProvisionedThroughput': {'ReadCapacityUnits': 5, 'WriteCapacityUnits': 5}
}
],
'ProvisionedThroughput': {
'ReadCapacityUnits': 5,
Expand Down
Loading
Loading