@arizeai/phoenix-client

npm install @arizeai/phoenix-client

PHOENIX_HOST='http://localhost:6006' PHOENIX_API_KEY='xxxxxx' npx tsx examples/list_datasets.ts
# emits the following request:
# GET http://localhost:6006/v1/datasets
# headers: {
#   "Authorization": "Bearer xxxxxx",
# }

const phoenix = createClient({
  options: {
    baseUrl: "http://localhost:6006",
    headers: {
      Authorization: "Bearer xxxxxx",
    },
  },
});

import { createPrompt, promptVersion } from "@arizeai/phoenix-client/prompts";

const version = createPrompt({
  name: "my-prompt",
  description: "test-description",
  version: promptVersion({
    description: "version description here",
    modelProvider: "OPENAI",
    modelName: "gpt-3.5-turbo",
    template: [
      {
        role: "user",
        content: "{{ question }}",
      },
    ],
    invocationParameters: {
      temperature: 0.8,
    },
  }),
});

import { getPrompt } from "@arizeai/phoenix-client/prompts";

const prompt = await getPrompt({ name: "my-prompt" });
// Returns a strongly-typed prompt object

const promptByTag = await getPrompt({ tag: "production", name: "my-prompt" });
// Filter by tag

const promptByVersionId = await getPrompt({
  versionId: "1234567890",
});
// Filter by prompt version ID

import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";
import { getPrompt, toSDK } from "@arizeai/phoenix-client/prompts";

const prompt = await getPrompt({ name: "my-prompt" });
const promptAsAI = toSDK({
  sdk: "ai",
  variables: {
    "my-variable": "my-value",
  },
  prompt,
});

const response = await generateText({
  model: openai(prompt.model_name),
  ...promptAsAI,
});

import { createClient } from "@arizeai/phoenix-client";

const phoenix = createClient();

// Get all datasets
const datasets = await phoenix.GET("/v1/datasets");

// Get specific prompt
const prompt = await phoenix.GET("/v1/prompts/{prompt_identifier}/latest", {
  params: {
    path: {
      prompt_identifier: "my-prompt",
    },
  },
});

import { createDataset } from "@arizeai/phoenix-client/datasets";

const { datasetId } = await createDataset({
  name: "questions",
  description: "a simple dataset of questions",
  examples: [
    {
      input: { question: "What is the capital of France" },
      output: { answer: "Paris" },
      metadata: {},
    },
    {
      input: { question: "What is the capital of the USA" },
      output: { answer: "Washington D.C." },
      metadata: {},
    },
  ],
});

import { createDataset } from "@arizeai/phoenix-client/datasets";
import { asEvaluator, runExperiment } from "@arizeai/phoenix-client/experiments";

// 1. Create a dataset
const { datasetId } = await createDataset({
  name: "names-dataset",
  description: "a simple dataset of names",
  examples: [
    {
      input: { name: "John" },
      output: { text: "Hello, John!" },
      metadata: {},
    },
    {
      input: { name: "Jane" },
      output: { text: "Hello, Jane!" },
      metadata: {},
    },
  ],
});

// 2. Define a task to run on each example
const task = async (example) => `hello ${example.input.name}`;

// 3. Define evaluators
const evaluators = [
  asEvaluator({
    name: "matches",
    kind: "CODE",
    evaluate: async ({ output, expected }) => {
      const matches = output === expected?.text;
      return {
        label: matches ? "matches" : "does not match",
        score: matches ? 1 : 0,
        explanation: matches
          ? "output matches expected"
          : "output does not match expected",
        metadata: {},
      };
    },
  }),
  asEvaluator({
    name: "contains-hello",
    kind: "CODE",
    evaluate: async ({ output }) => {
      const matches = typeof output === "string" && output.includes("hello");
      return {
        label: matches ? "contains hello" : "does not contain hello",
        score: matches ? 1 : 0,
        explanation: matches
          ? "output contains hello"
          : "output does not contain hello",
        metadata: {},
      };
    },
  }),
];

// 4. Run the experiment
const experiment = await runExperiment({
  dataset: { datasetId },
  task,
  evaluators,
});