-
Epic
-
Resolution: Unresolved
-
Undefined
-
None
-
None
-
Lightspeed Evaluation Tool Integration & Setup
-
False
-
-
False
-
-
In Progress
-
RHDHPLAN-261 - [Lightspeed] Evaluations - testing accuracy and efficacy across models
-
25% To Do, 25% In Progress, 50% Done
-
-
Epic Goal
Integrate the existing Lightspeed Core evaluation tool with the RHDH Lightspeed plugin and establish a functional testing environment.
Why is this important?
- …
Scenarios
- Investigate & POC: Research the lightspeed-evaluation tool and establish a proof-of-concept (POC) integration with the RHDH Lightspeed plugin.
- Configure Environment: Set up the necessary configuration files (e.g., system.yaml) to define the evaluation environment, including the "Judge LLM" and API access.
- Validate Connectivity: Perform an initial test run with a minimal dummy dataset to ensure the evaluation tool can successfully communicate with the plugin and get responses.
- Define Test Harness: Document the end-to-end process for a developer to manually trigger an evaluation run from their local environment
Acceptance Criteria (Mandatory)
- CI - MUST be running successfully with tests automated
- Release Technical Enablement - Provide necessary release enablement details and documents.
- ...
Dependencies (internal and external)
- ...
Previous Work (Optional):
- …
Open questions::
- …
Done Checklist
- Acceptance criteria are met
- Non-functional properties of the Feature have been validated (such as performance, resource, UX, security or privacy aspects)
- User Journey automation is delivered
- Support and SRE teams are provided with enough skills to support the feature in production environment
- is cloned by
-
RHIDP-9982 Developer Lightspeed Standard Evaluation Dataset Creation
-
- New
-