You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
psql -h ${aws_rds_cluster.test.endpoint} -U ${aws_rds_cluster.test.master_username} -d ${aws_rds_cluster.test.database_name} -c "CREATE SCHEMA IF NOT EXISTS bedrock_new;"
847
852
psql -h ${aws_rds_cluster.test.endpoint} -U ${aws_rds_cluster.test.master_username} -d ${aws_rds_cluster.test.database_name} -c "CREATE ROLE bedrock_user WITH PASSWORD '$PGPASSWORD' LOGIN;"
848
853
psql -h ${aws_rds_cluster.test.endpoint} -U ${aws_rds_cluster.test.master_username} -d ${aws_rds_cluster.test.database_name} -c "GRANT ALL ON SCHEMA bedrock_integration TO bedrock_user;"
psql -h ${aws_rds_cluster.test.endpoint} -U ${aws_rds_cluster.test.master_username} -d ${aws_rds_cluster.test.database_name} -c "CREATE INDEX ON bedrock_integration.bedrock_kb USING hnsw (embedding vector_cosine_ops);"
851
856
psql -h ${aws_rds_cluster.test.endpoint} -U ${aws_rds_cluster.test.master_username} -d ${aws_rds_cluster.test.database_name} -c "CREATE INDEX ON bedrock_integration.bedrock_kb USING gin (to_tsvector('simple', chunks));"
857
+
psql -h ${aws_rds_cluster.test.endpoint} -U ${aws_rds_cluster.test.master_username} -d ${aws_rds_cluster.test.database_name} -c "CREATE INDEX ON bedrock_integration.bedrock_kb USING gin (custom_metadata);"
Copy file name to clipboardExpand all lines: website/docs/r/bedrockagent_knowledge_base.html.markdown
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -184,6 +184,7 @@ The `pinecone_configuration` configuration block supports the following argument
184
184
*`credentials_secret_arn` - (Required) ARN of the secret that you created in AWS Secrets Manager that is linked to your Amazon RDS database.
185
185
*`database_name` - (Required) Name of your Amazon RDS database.
186
186
*`field_mapping` - (Required) Names of the fields to which to map information about the vector store. This block supports the following arguments:
187
+
*`custom_metadata_field` - (Optional) Name for the universal metadata field where Amazon Bedrock will store any custom metadata from your data source.
187
188
*`metadata_field` - (Required) Name of the field in which Amazon Bedrock stores metadata about the vector store.
188
189
*`primary_key_field` - (Required) Name of the field in which Amazon Bedrock stores the ID for each entry.
189
190
*`text_field` - (Required) Name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose.
0 commit comments