TypeScript

import { Netra } from "netra-sdk-js";

const client = new Netra({
  apiKey: "your-api-key",
});

// Access the evaluation client
await client.evaluation.createDataset(...);
await client.evaluation.addDatasetItem(...);
await client.evaluation.getDataset(...);
await client.evaluation.runTestSuite(...);

import { Netra } from "netra-sdk-js";
import OpenAI from "openai";

async function main() {
  // Initialize
  const client = new Netra({
    apiKey: "your-api-key",
  });
  const openai = new OpenAI();

  // 1. Create a dataset
  const datasetResponse = await client.evaluation.createDataset(
    "Product FAQ Evaluation",
    ["faq", "products", "v2"]
  );

  if (!datasetResponse) {
    console.error("Failed to create dataset");
    return;
  }

  const datasetId = datasetResponse.id;
  console.log(`Created dataset: ${datasetId}`);

  // 2. Add test items
  const testCases = [
    {
      input: "What is your return policy?",
      expectedOutput: "Items can be returned within 30 days.",
    },
    {
      input: "How long does shipping take?",
      expectedOutput: "Standard shipping takes 3-5 business days.",
    },
    {
      input: "Do you offer international shipping?",
      expectedOutput: "Yes, we ship to over 50 countries.",
    },
  ];

  for (const testCase of testCases) {
    await client.evaluation.addDatasetItem(datasetId, {
      input: testCase.input,
      expectedOutput: testCase.expectedOutput,
    });
  }
  console.log(`Added ${testCases.length} test items`);

  // 3. Define the task
  async function faqAgent(query: string): Promise<string> {
    const response = await openai.chat.completions.create({
      model: "gpt-4o-mini",
      messages: [
        {
          role: "system",
          content: "You are a customer support agent. Answer concisely.",
        },
        { role: "user", content: query },
      ],
    });
    return response.choices[0].message.content || "";
  }

  // 4. Run the test suite
  const dataset = await client.evaluation.getDataset(datasetId);

  if (dataset) {
    const result = await client.evaluation.runTestSuite(
      "FAQ Agent v2 Evaluation",
      dataset,
      faqAgent,
      ["correctness", "relevance"],
      5
    );

    // 5. Review results
    if (result) {
      console.log(`\nRun completed: ${result.runId}`);
      for (const item of result.items) {
        console.log(
          `  Item ${item.index}: ${item.status} (trace: ${item.traceId})`
        );
      }

      console.log(
        "\nView detailed results in Netra dashboard → Evaluation → Test Runs"
      );
    }
  }
}

main();