fixes;

firebase · Dec 13, 2024 · d2bebb8 · d2bebb8
1 parent d26761f
commit d2bebb8
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 11 deletions.
diff --git a/docs/evaluation.md b/docs/evaluation.md
@@ -18,7 +18,7 @@ Genkit faithfulness and answer relevancy metrics:
 ```ts
 import { genkit } from 'genkit';
 import { genkitEval, GenkitMetric } from '@genkit-ai/evaluator';
-import { vertexAI, textEmbedding004, gemini15Pro } from '@genkit-ai/vertexai';
+import { vertexAI, textEmbedding004, gemini15Flash, gemini15Pro } from '@genkit-ai/vertexai';
 
 const ai = genkit({
   plugins: [

diff --git a/docs/plugin-authoring-evaluator.md b/docs/plugin-authoring-evaluator.md
@@ -90,7 +90,7 @@ export async function deliciousnessScore<
     throw new Error('Output is required for Deliciousness detection');
   }
 
-  //Hydrate the prompt and generate an evaluation result
+  // Hydrate the prompt and generate an evaluation result
   const deliciousnessPrompt = getDeliciousnessPrompt(ai);
   const response = await deliciousnessPrompt(
     {
@@ -152,13 +152,6 @@ export function createDeliciousnessEvaluator<
 }
 ```
 
-<!-- TODO: Test out the deliciousness evaluator 
-
-
-export const deliciousness = createDeliciousnessEvaluator(ai, gemini15Pro);
-
--->
-
 The `defineEvaluator` method is similar to other Genkit constructors like `defineFlow`, `defineRetriever` etc. The user should provide an `EvaluatorFn` to the `defineEvaluator` callback. The `EvaluatorFn` accepts a `BaseEvalDataPoint` which corresponds to a single entry in a dataset under evaluation, along with an optional custom options parameter if specified. The function, should process the datapoint and return an `EvalResponse` object. 
 
 Here are the Zod Schemas for `BaseEvalDataPoint` and `EvalResponse`:
@@ -268,7 +261,7 @@ export function createUSPhoneRegexEvaluator(ai: Genkit): EvaluatorAction {
 }
 ```
 
-## Configuration
+## Putting it together
 
 ### Plugin definition
 
@@ -352,4 +345,4 @@ genkit eval:run deliciousness_dataset.json
 
 Navigate to `localhost:4000/evaluate` to view your results in the Genkit UI.
 
-It is important to note that confidence in custom evaluators will increase as you benchmark them with standard datasets or approaches. Iterate on the results of such benchmarks to improve your evaluators' performance till it reaches the desired quality.
+It is important to note that confidence in custom evaluators will increase as you benchmark them with standard datasets or approaches. Iterate on the results of such benchmarks to improve your evaluators' performance till it reaches the desired quality.