Adding lakebase short term memory blog post #70
Conversation
This file contains hidden or 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
bcheng004
requested review from
QuentinAmbard,
alanreese-dbrx,
alexott,
anupkalburgi,
kwulffert23,
matthewmoorcroft,
slcc2c and
srinivasadmala
as code owners
pbv0
reviewed
Jan 13, 2026
| ### Prerequisites | ||
|
|
||
| 1. **Databricks Workspace** with Unity Catalog enabled | ||
| 2. **Lakebase Instance** - Create via SQL Warehouses → Lakebase Postgres → Create database instance |
There was a problem hiding this comment.
Why via SQL? Should this be via "Compute"?
|
|
||
| # TODO: Update with your system prompt | ||
| SYSTEM_PROMPT = """ | ||
| You are an cybersecurity assistant. |
| """Stateful agent using ResponsesAgent with pooled Lakebase checkpointing.""" | ||
|
|
||
| def __init__(self, lakebase_config: dict[str, Any]): | ||
| self.workspace_client = WorkspaceClient() |
| # Lakebase configuration | ||
| ############################################ | ||
| # TODO: Fill in Lakebase instance name | ||
| LAKEBASE_INSTANCE_NAME = "bo-test-lakebase-3" |
There was a problem hiding this comment.
Instead of hardcoding, maybe get from env?
|
|
||
| # Example UC tools; add your own as needed | ||
| UC_TOOL_NAMES: list[str] = [ | ||
| "bo_cheng_dnb_demos.agents.get_cyber_threat_info", |
| " FROM\n", | ||
| " bo_cheng_dnb_demos.agents.cyber_threat_detection\n", | ||
| " WHERE\n", | ||
| " threat_type = threat_type\n", |
| "output_type": "execute_result", | ||
| "data": { | ||
| "text/plain": [ | ||
| "DatabaseInstance(name='bo-test-lakebase-3', capacity='CU_1', child_instance_refs=[], creation_time='2026-01-08T19:16:22Z', creator='[email protected]', custom_tags=[], effective_capacity='CU_1', effective_custom_tags=[], effective_enable_pg_native_login=True, effective_enable_readable_secondaries=False, effective_node_count=1, effective_retention_window_in_days=7, effective_stopped=False, effective_usage_policy_id=None, enable_pg_native_login=None, enable_readable_secondaries=None, node_count=None, parent_instance_ref=None, pg_version='PG_VERSION_16', read_only_dns='instance-ro-cd00746e-b544-45c8-9f08-5062a0858c7d.database.cloud.databricks.com', read_write_dns='instance-cd00746e-b544-45c8-9f08-5062a0858c7d.database.cloud.databricks.com', retention_window_in_days=None, state=<DatabaseInstanceState.AVAILABLE: 'AVAILABLE'>, stopped=None, uid='cd00746e-b544-45c8-9f08-5062a0858c7d', usage_policy_id=None)" |
| @@ -0,0 +1,3 @@ | |||
| mlflow>=2.21.2 | |||
| streamlit==1.44.1 | |||
| databricks-sdk | |||
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.