TypeScript - Latitude Docs

The Latitude TypeScript SDK provides a convenient way to interact with the Latitude platform from your Node.js or browser applications.

Installation

The Latitude SDK is compatible with Node.js 16 or higher.

npm install @latitude-data/sdk
# or
yarn add @latitude-data/sdk
# or
pnpm add @latitude-data/sdk

Authentication and Initialization

Import the SDK and initialize it with your API key. You can generate API keys in your Latitude project settings under “API Access”.

import { Latitude } from '@latitude-data/sdk'

const latitude = new Latitude(process.env.LATITUDE_API_KEY)

You can also provide additional options during initialization:

const latitude = new Latitude(process.env.LATITUDE_API_KEY, {
  projectId: 123, // Your Latitude project ID
  versionUuid: 'version-uuid', // Optional version UUID
}) // Keep your API key secure and avoid committing it directly into your codebase.

Both projectId and versionUuid options can be overridden on a per-method basis when needed.

Examples

Check out our Examples section for more examples of how to use the Latitude SDK.

SDK Structure

The Latitude SDK is organized into several namespaces:

prompts: Methods for managing and running prompts
runs: Methods for managing active runs
logs: Methods for pushing logs to Latitude
evaluations: Methods for pushing evaluation results to Latitude
projects: Methods for managing projects
versions: Methods for managing project versions

Prompt Management

Get a Prompt

To retrieve a specific prompt by its path:

const prompt = await latitude.prompts.get('prompt-path')

Get All Prompts

To retrieve all prompts in your project:

const prompts = await latitude.prompts.getAll()

Get or Create a Prompt

To get an existing prompt or create a new one if it doesn’t exist:

const prompt = await latitude.prompts.getOrCreate('prompt-path')

You can also provide the content when creating a new prompt:

const prompt = await latitude.prompts.getOrCreate('prompt-path', {
  prompt: 'This is the content of my new prompt',
})

Version Management

Get All Versions

To retrieve all versions from a project:

const versions = await latitude.versions.getAll()

You can also specify a different project ID:

const versions = await latitude.versions.getAll(123)

Running Prompts

Non-Streaming Run

Execute a prompt and get the complete response once generation is finished:

const result = await latitude.prompts.run('prompt-path', {
  parameters: {
    productName: 'CloudSync Pro',
    audience: 'Small Business Owners',
  },
  // Optional: Provide a custom identifier for this run
  customIdentifier: 'email-campaign-2023',
  // Optional: Provide callbacks for events
  onFinished: (result) => {
    console.log('Run completed:', result.uuid)
  },
  onError: (error) => {
    console.error('Run error:', error.message)
  },
})

console.log('Conversation UUID:', result.uuid)
console.log('Conversation messages:', result.conversation)

Handling Streaming Responses

For real-time applications (like chatbots), use streaming to get response chunks as they are generated:

await latitude.prompts.run('prompt-path', {
  parameters: {
    productName: 'CloudSync Pro',
    audience: 'Small Business Owners',
  },
  // Enable streaming
  stream: true,
  // Provide callbacks for events
  onEvent: ({ event, data }) => {
    if (event === StreamEventTypes.Provider && data.type === 'text-delta') {
      console.log(data.textDelta)
    } else if (
      event === StreamEventTypes.Latitude &&
      data.type === 'chain-completed'
    ) {
      console.log('Conversation UUID:', data.uuid)
      console.log('Conversation messages:', data.messages)
    }
  },
  onFinished: (result) => {
    console.log('Stream completed:', result.uuid)
  },
  onError: (error) => {
    console.error('Stream error:', error.message)
  },
})

Using Tools with Prompts

You can provide tool handlers that the model can call during execution:

await latitude.prompts.run('prompt-path', {
  parameters: {
    query: 'What is the weather in San Francisco?',
  },
  // Define the tools the model can use
  tools: {
    getWeather: async (args, details) => {
      // `args` contains the arguments passed by the model
      // `details` contains context like tool id, name, messages...
      // The result can be anything JSON serializable
      console.log('Getting weather for:', args.location)
      return { temperature: '72°F', conditions: 'Sunny' }
    },
  },
})

Prompts that return structured outputs

By default the sdk assumes your prompt return text. If you expect your prompt to return structured output you can type it in the prompts.run method:

const result = await latitude.prompts.run<{ expected: 'property' }>(
  'structured-output-prompt',
)

console.log(result.object) // outputs { expected: 'property' }

Chat with a Prompt

Follow the conversation of a runned prompt:

const messages = [
  {
    role: 'user',
    content: 'Hello, how can you help me today?',
  },
]

const result = await latitude.prompts.chat('conversation-uuid', messages, {
  // Chat options are similar to the run method
  onFinished: (result) => {
    console.log('Chat completed:', result.uuid)
  },
  onError: (error) => {
    console.error('Chat error:', error.message)
  },
})

console.log('Conversation UUID:', result.uuid)
console.log('Conversation messages:', result.conversation)

Messages follow the PromptL format. If you’re using a different method to run your prompts, you’ll need to format your messages accordingly.

Running a Prompt in the Background

For long-running prompts, such as large Agent systems, that you don’t need to wait for, use background runs:

const job = await latitude.prompts.run('prompt-path', {
  parameters: {
    productName: 'CloudSync Pro',
    audience: 'Small Business Owners',
  },
  // Enable background processing
  background: true,
})

console.log('Job UUID:', job.uuid)
// The request returns immediately with a conversation UUID
// You can use this UUID to attach to the run later to check its status or stop it programmatically

const result = await latitude.runs.attach(job.uuid, {
  stream: true,
  onEvent: ({ event, data }) => {
    console.log('Received event:', event, data)
  },
})

console.log('Conversation UUID:', result.uuid)
console.log('Conversation messages:', result.conversation)

Run Management

Stop a Run

Stop an active conversation that is currently running:

await latitude.runs.stop('conversation-uuid')
console.log('Run stopped successfully')

Attach to a Run

Attach to an active conversation to receive its ongoing output:

const result = await latitude.runs.attach('conversation-uuid', {
  // Optional: Enable streaming for real-time updates
  stream: true,
  // Optional: Make the run interactive (abort when client disconnects)
  interactive: false,
  // Optional: Provide callbacks for events
  onEvent: ({ event, data }) => {
    if (event === StreamEventTypes.Provider && data.type === 'text-delta') {
      console.log(data.textDelta)
    }
  },
  onFinished: (result) => {
    console.log('Attach completed:', result.uuid)
  },
  onError: (error) => {
    console.error('Attach error:', error.message)
  },
})

console.log('Conversation UUID:', result.uuid)
console.log('Conversation messages:', result.conversation)

Rendering Prompts

Prompt Rendering

Render a prompt locally without running it:

const result = await latitude.prompts.render({
  prompt: {
    content: 'Your prompt content here with {{ parameters }}',
  },
  parameters: {
    topic: 'Artificial Intelligence',
    tone: 'Professional',
  },
  // Optional: Specify a provider adapter
  adapter: Adapters.OpenAI,
})

console.log('Rendered config:', result.config)
console.log('Rendered messages:', result.messages)

Chain Rendering

Render a chain of prompts locally:

const result = await latitude.prompts.renderChain({
  prompt: {
    path: 'prompt-path',
    content: 'Your prompt content here with {{ parameters }}',
    provider: 'openai',
  },
  parameters: {
    topic: 'Machine Learning',
    complexity: 'Advanced',
  },
  // Required: Process each step in the chain
  onStep: async ({ config, messages }) => {
    // Process each step in the chain
    console.log('Processing step with messages:', messages)
    // Return a string or a message object
    return 'Step response'
  },
  // Optional: Specify a provider adapter
  adapter: Adapters.OpenAI,
  // Optional: Log responses to Latitude
  logResponses: true,
  // Optional: Define tools for the chain
  tools: {
    getExample: async (args, details) => {
      return { example: 'This is an example response' }
    },
  },
})

console.log('Rendered config:', result.config)
console.log('Rendered messages:', result.messages)

Agent Rendering

Render an agent prompt locally (similar to renderChain but with a final agent result):

const result = await latitude.prompts.renderAgent({
  prompt: {
    path: 'prompt-path',
    content: 'Agent prompt content with {{ parameters }}',
    provider: 'openai',
  },
  parameters: {
    task: 'Research quantum computing',
    depth: 'Detailed',
  },
  // Required: Process each agent step
  onStep: async ({ config, messages }) => {
    // Process each step in the agent execution
    console.log('Processing agent step:', messages)
    // Return a string or a message object
    return 'Agent step response'
  },
  // Optional: Log responses to Latitude
  logResponses: true,
  // Optional: Define tools for the agent
  tools: {
    search: async (args, details) => {
      console.log('Agent using search tool with args:', args)
      return { results: ['Result 1', 'Result 2'] }
    },
  },
})

console.log('Rendered config:', result.config)
console.log('Rendered messages:', result.messages)
// Agent final response is available in result.result
console.log('Agent final response:', result.result)

Make sure to provide the config.tools parameter to the LLM provider in your onStep handler, otherwise the AI won’t be able to stop the Agent loop!

Logging

Creating Logs

Push a log to Latitude manually for a prompt:

const messages = [
  {
    role: 'user',
    content: 'Hello, how can you help me today?',
  },
]

const log = await latitude.logs.create('prompt-path', messages, {
  response: 'I can help you with anything!',
})

Evaluations

Annotate a log

Push an evaluation result (annotate) to Latitude:

const result = await latitude.evaluations.annotate(
  'conversation-uuid',
  100,
  'evaluation-uuid',
  {
    reason: 'I liked it!',
  },
)

Complete Method Reference

Initialization

// SDK initialization
new Latitude(
  apiKey: string,
  options: {
    projectId?: number,
    versionUuid?: string,
    __internal?: {
      gateway?: GatewayApiConfig,
      source?: LogSources,
      retryMs?: number
    }
  }
)

Prompts Namespace

// Get a prompt
latitude.prompts.get(
  path: string,
  options?: {
    projectId?: number,
    versionUuid?: string
  }
): Promise<Prompt>

// Get all prompts
latitude.prompts.getAll(
  options?: {
    projectId?: number,
    versionUuid?: string
  }
): Promise<Prompt[]>

// Create a prompt
latitude.prompts.create(
  path: string,
  options?: {
    projectId?: number,
    versionUuid?: string,
    prompt?: string
  }
): Promise<Prompt>

// Get or create a prompt
latitude.prompts.getOrCreate(
  path: string,
  options?: {
    projectId?: number,
    versionUuid?: string,
    prompt?: string
  }
): Promise<Prompt>

// Run a prompt
latitude.prompts.run<S extends AssertedStreamType = 'text', Tools extends ToolSpec = {}, Background extends boolean = false>(
  path: string,
  options: {
    projectId?: number,
    versionUuid?: string,
    customIdentifier?: string,
    parameters?: Record<string, unknown>,
    stream?: boolean,
    background?: Background,
    tools?: ToolCalledFn<Tools>,
    signal?: AbortSignal,
    onEvent?: ({ event, data }: { event: StreamEventTypes, data: ChainEventDto }) => void,
    onFinished?: (data: GenerationResponse<S>) => void,
    onError?: (error: LatitudeApiError) => void
  }
): Promise<RunPromptResult<S, Background> | undefined>

// Chat with a prompt
latitude.prompts.chat<S extends AssertedStreamType = 'text', Tools extends ToolSpec = {}>(
  uuid: string,
  messages: Message[],
  options?: {
    stream?: boolean,
    tools?: ToolCalledFn<Tools>,
    signal?: AbortSignal,
    onEvent?: ({ event, data }: { event: StreamEventTypes, data: ChainEventDto }) => void,
    onFinished?: (data: GenerationResponse<S>) => void,
    onError?: (error: LatitudeApiError) => void
  }
): Promise<GenerationResponse<S> | undefined>

// Render a prompt
latitude.prompts.render<M extends AdapterMessageType = PromptlMessage>(
  options: {
    prompt: { content: string },
    parameters: Record<string, unknown>,
    adapter?: ProviderAdapter<M>
  }
): Promise<{ config: Config, messages: M[] }>

// Render a chain
latitude.prompts.renderChain<M extends AdapterMessageType = PromptlMessage>(
  options: {
    prompt: Prompt,
    parameters: Record<string, unknown>,
    adapter?: ProviderAdapter<M>,
    onStep: (args: { config: Config, messages: M[] }) => Promise<string | Omit<M, 'role'>>,
    tools?: RenderToolCalledFn<ToolSpec>,
    logResponses?: boolean
  }
): Promise<{ config: Config, messages: M[] }>

Runs Namespace

// Attach to a run
latitude.runs.attach<S extends AssertedStreamType = 'text', Tools extends ToolSpec = {}>(
  uuid: string,
  options?: {
    stream?: boolean,
    interactive?: boolean,
    tools?: ToolCalledFn<Tools>,
    signal?: AbortSignal,
    onEvent?: ({ event, data }: { event: StreamEventTypes, data: ChainEventDto }) => void,
    onFinished?: (data: GenerationResponse<S>) => void,
    onError?: (error: LatitudeApiError) => void
  }
): Promise<GenerationResponse<S> | undefined>

// Stop a run
latitude.runs.stop(uuid: string): Promise<void>

Projects Namespace

// Get all projects
latitude.projects.getAll(): Promise<Project[]>

// Create a project
latitude.projects.create(
  name: string
): Promise<{
  project: Project
  version: Version
}>

Logs Namespace

// Create a log
latitude.logs.create(
  path: string,
  messages: Message[],
  options?: {
    response?: string,
    projectId?: number,
    versionUuid?: string
  }
): Promise<DocumentLog>

Evaluations Namespace

// Annotate a log
latitude.evaluations.annotate(
  uuid: string,
  score: number,
  evaluationUuid: string,
  options?: {
    reason?: string,
    versionUuid?: string
  }
): Promise<PublicManualEvaluationResultV2>

Versions Namespace

// Get a version
latitude.versions.get(
  projectId: number,
  commitUuid: string
): Promise<Version>

// Get all versions
latitude.versions.getAll(projectId?: number): Promise<Version[]>

// Create a version
latitude.versions.create(
  name: string,
  options?: {
    projectId?: number
  }
): Promise<Version>

// Push version changes
latitude.versions.push(
  projectId: number,
  baseCommitUuid: string,
  changes: Array<{
    path: string
    content: string
    status: 'added' | 'modified' | 'deleted' | 'unchanged'
    contentHash?: string
  }>
): Promise<{ commitUuid: string }>

Error Handling

The SDK throws LatitudeApiError instances when API requests fail. You can catch and handle these errors:

import { LatitudeApiError } from '@latitude-data/sdk'

async function handleErrors() {
  try {
    const prompt = await latitude.prompts.get('non-existent-prompt')
  } catch (error) {
    if (error instanceof LatitudeApiError) {
      console.error('API Error:', error.message)
      console.error('Error Code:', error.errorCode)
      console.error('Status:', error.status)
    } else {
      console.error('Unexpected error:', error)
    }
  }
}

Logging Features

Automatic Logging: All runs through latitude.prompts.run() are automatically logged in Latitude, capturing inputs, outputs, performance metrics, and trace information.
Custom Identifiers: Use the optional customIdentifier parameter to tag runs for easier filtering and analysis in the Latitude dashboard.
Response Identification: Each response includes identifying information like uuid that can be used to reference the specific run later.

Getting started

Prompts

Agents

Evaluations

Datasets

Experiments

Deployment

Self-Hosting

Changelog

Support

​Installation

​Authentication and Initialization

​Examples

​SDK Structure

​Prompt Management

​Get a Prompt

​Get All Prompts

​Get or Create a Prompt

​Version Management

​Get All Versions

​Running Prompts

​Non-Streaming Run

​Handling Streaming Responses

​Using Tools with Prompts

​Prompts that return structured outputs

​Chat with a Prompt

​Running a Prompt in the Background

​Run Management

​Stop a Run

​Attach to a Run

​Rendering Prompts

​Prompt Rendering

​Chain Rendering

​Agent Rendering

​Logging

​Creating Logs

​Evaluations

​Annotate a log

​Complete Method Reference

​Initialization

​Prompts Namespace

​Runs Namespace

​Projects Namespace

​Logs Namespace

​Evaluations Namespace

​Versions Namespace

​Error Handling

​Logging Features

​Further Information

Installation

Authentication and Initialization

Examples

SDK Structure

Prompt Management

Get a Prompt

Get All Prompts

Get or Create a Prompt

Version Management

Get All Versions

Running Prompts

Non-Streaming Run

Handling Streaming Responses

Using Tools with Prompts

Prompts that return structured outputs

Chat with a Prompt

Running a Prompt in the Background

Run Management

Stop a Run

Attach to a Run

Rendering Prompts

Prompt Rendering

Chain Rendering

Agent Rendering

Logging

Creating Logs

Evaluations

Annotate a log

Complete Method Reference

Initialization

Prompts Namespace

Runs Namespace

Projects Namespace

Logs Namespace

Evaluations Namespace

Versions Namespace

Error Handling

Logging Features

Further Information