Skip to content

opper-ai/opper-node

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

212 Commits
.devcontainer
.devcontainer
 
 
.github/workflows
.github/workflows
 
 
.speakeasy
.speakeasy
 
 
docs
docs
 
 
examples
examples
 
 
src
src
 
 
.genignore
.genignore
 
 
.gitattributes
.gitattributes
 
 
.gitignore
.gitignore
 
 
.npmignore
.npmignore
 
 
CLAUDE.md
CLAUDE.md
 
 
CONTRIBUTING.md
CONTRIBUTING.md
 
 
FUNCTIONS.md
FUNCTIONS.md
 
 
README.md
README.md
 
 
RUNTIMES.md
RUNTIMES.md
 
 
USAGE.md
USAGE.md
 
 
eslint.config.mjs
eslint.config.mjs
 
 
jsr.json
jsr.json
 
 
opper-node.mdc
opper-node.mdc
 
 
package-lock.json
package-lock.json
 
 
package.json
package.json
 
 
test-basic.ts
test-basic.ts
 
 
test-examples.ts
test-examples.ts
 
 
test-opper.ts
test-opper.ts
 
 
test-streaming.ts
test-streaming.ts
 
 
tsconfig.json
tsconfig.json
 
 

Repository files navigation

opperai

Developer-friendly & type-safe Typescript SDK specifically catered to leverage opperai API.

Summary

Sign Up and Start Using Opper

Welcome to the OpperAI python SDK

Opper is a task completion platform for building reliable AI integrations. The Opper platform builds a happy path for declarative programming with AI models, combined with in context reinforcement learning, observability and cost tracking all in one platform - for reliable results in no time!

This SDK is generated using Speakeasy — check out our detailed documentation with guides and examples: Explore Docs

Table of Contents

SDK Installation

The SDK can be installed with either npm, pnpm, bun or yarn package managers.

NPM

npm add opperai

PNPM

pnpm add opperai

Bun

bun add opperai

Yarn

yarn add opperai

# Note that Yarn does not install peer dependencies automatically. Run
# `yarn add zod@^3.23.8` as well if you haven't already.

Important

This SDK currently supports Zod v3.x. Ensure your project installs zod@^3.23.8 (or another 3.x release) and avoids Zod v4 releases.

Note

This package is published with CommonJS and ES Modules (ESM) support.

Model Context Protocol (MCP) Server

This SDK is also an installable MCP server where the various SDK methods are exposed as tools that can be invoked by AI applications.

Node.js v20 or greater is required to run the MCP server from npm.

Claude installation steps

Add the following server definition to your claude_desktop_config.json file:

{
  "mcpServers": {
    "Opper": {
      "command": "npx",
      "args": [
        "-y", "--package", "opperai",
        "--",
        "mcp", "start",
        "--http-bearer", "..."
      ]
    }
  }
}
Cursor installation steps

Create a .cursor/mcp.json file in your project root with the following content:

{
  "mcpServers": {
    "Opper": {
      "command": "npx",
      "args": [
        "-y", "--package", "opperai",
        "--",
        "mcp", "start",
        "--http-bearer", "..."
      ]
    }
  }
}
MCP standalone Binary You can also run MCP servers as a standalone binary with no additional dependencies. You must pull these binaries from available Github releases: 
curl -L -o mcp-server \
    https://github.com/{org}/{repo}/releases/download/{tag}/mcp-server-bun-darwin-arm64 && \
chmod +x mcp-server

If the repo is a private repo you must add your Github PAT to download a release -H "Authorization: Bearer {GITHUB_PAT}".

{
  "mcpServers": {
    "Todos": {
      "command": "./DOWNLOAD/PATH/mcp-server",
      "args": [
        "start"
      ]
    }
  }
}

For a full list of server arguments, run:

npx -y --package opperai -- mcp start --help
## Requirements

For supported JavaScript runtimes, please consult RUNTIMES.md.

SDK Example Usage

Explore Docs

First steps

Log in at opper and create your own API key in the top right menu. Each api key is associated with a project, you will have all calls, functions, indexes and traces associated with this project. There is a default project for each organization but it is recommended to create a new project to better being able to separate the different applications and environments.

There are plenty of guides and example code in our examples

Example

Minimal call

import { Opper } from "opperai";

const opper = new Opper({
  httpBearer: process.env["OPPER_HTTP_BEARER"] ?? "",
});

// Define the output structure (JSON Schema instead of Pydantic)
const roomDescriptionSchema = {
    type: "object",
    properties: {
        room_count: { type: "number" },
        view: { type: "string" },
        bed_size: { type: "string" },
        hotel_name: { type: "string" },
    },
    required: ["room_count", "view", "bed_size", "hotel_name"],
};

async function main() {
    // Complete a task
    const completion = await opper.call({
        name: "extractRoom",
        instructions: "Extract details about the room from the provided text",
        input: "The Grand Hotel offers a luxurious suite with 3 spacious rooms, each providing a breathtaking view of the ocean. The suite includes a king-sized bed, an en-suite bathroom, and a private balcony for an unforgettable stay.",
        outputSchema: roomDescriptionSchema,
    });

    console.log(completion.jsonPayload);
    // Expected: { room_count: 3, view: 'ocean', bed_size: 'king-sized', hotel_name: 'The Grand Hotel' }
}

main();

More advanced example

import { Opper } from "opperai";

const opper = new Opper({
  httpBearer: process.env["OPPER_HTTP_BEARER"] ?? "",
});

async function run() {
  const result = await opper.call({
    name: "add_numbers",
    instructions: "Calculate the sum of two numbers",
    inputSchema: {
      "properties": {
        "x": {
          "title": "X",
          "type": "integer",
        },
        "y": {
          "title": "Y",
          "type": "integer",
        },
      },
      "required": [
        "x",
        "y",
      ],
      "title": "OpperInputExample",
      "type": "object",
    },
    outputSchema: {
      "properties": {
        "sum": {
          "title": "Sum",
          "type": "integer",
        },
      },
      "required": [
        "sum",
      ],
      "title": "OpperOutputExample",
      "type": "object",
    },
    input: {
      "x": 4,
      "y": 5,
    },
    examples: [
      {
        input: {
          "x": 1,
          "y": 3,
        },
        output: {
          "sum": 4,
        },
        comment: "Adds two numbers",
      },
    ],
    parentSpanId: "123e4567-e89b-12d3-a456-426614174000", // Pass the id you need
    tags: {
      "project": "project_456",
      "user": "company_123",
    },
    configuration: {},
  });

  console.log(result);
}

run();

Authentication

See our authenthication docs Explore Docs

Per-Client Security Schemes

This SDK supports the following security scheme globally:

Name Type Scheme Environment Variable
httpBearer http HTTP Bearer OPPER_HTTP_BEARER

To authenticate with the API the httpBearer parameter must be set when initializing the SDK client instance. For example:

import { Opper } from "opperai";

const opper = new Opper({
  httpBearer: process.env["OPPER_HTTP_BEARER"] ?? "",
});

Available Resources and Operations

Available methods

analytics

datasets

datasets.entries

  • update - Update Dataset Entry

embeddings

functions

functions.revisions

  • list - List Function Revisions

knowledge

languageModels

Opper SDK

spanMetrics

spans

traces

  • list - List Traces
  • get - Get Trace

Standalone functions

All the methods listed above are available as standalone functions. These functions are ideal for use in applications running in the browser, serverless runtimes or other environments where application bundle size is a primary concern. When using a bundler to build your application, all unused functionality will be either excluded from the final bundle or tree-shaken away.

To read more about standalone functions, check FUNCTIONS.md.

Available standalone functions

Server-sent event streaming

Server-sent events are used to stream content from certain operations. These operations will expose the stream as an async iterable that can be consumed using a for await...of loop. The loop will terminate when the server no longer has any events to send and closes the underlying connection.

import { Opper } from "opperai";

const opper = new Opper({
  httpBearer: process.env["OPPER_HTTP_BEARER"] ?? "",
});

async function run() {
  const result = await opper.stream({
    name: "add_numbers",
    instructions: "Calculate the sum of two numbers",
    inputSchema: {
      "properties": {
        "x": {
          "title": "X",
          "type": "integer",
        },
        "y": {
          "title": "Y",
          "type": "integer",
        },
      },
      "required": [
        "x",
        "y",
      ],
      "title": "OpperInputExample",
      "type": "object",
    },
    outputSchema: {
      "properties": {
        "sum": {
          "title": "Sum",
          "type": "integer",
        },
      },
      "required": [
        "sum",
      ],
      "title": "OpperOutputExample",
      "type": "object",
    },
    input: {
      "x": 4,
      "y": 5,
    },
    examples: [
      {
        input: {
          "x": 1,
          "y": 3,
        },
        output: {
          "sum": 4,
        },
        comment: "Adds two numbers",
      },
    ],
    parentSpanId: "123e4567-e89b-12d3-a456-426614174000",
    tags: {
      "project": "project_456",
      "user": "company_123",
    },
  });

  for await (const event of result) {
    // Handle the event
    console.log(event);
  }
}

run();

Retries

Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.

Change Retry Strategy To change the default retry strategy for a single API call, simply provide a retryConfig object to the call: ```typescript import { Opper } from "opperai";

const opper = new Opper({ httpBearer: process.env["OPPER_HTTP_BEARER"] ?? "", });

async function run() { const result = await opper.call({ name: "add_numbers", instructions: "Calculate the sum of two numbers", inputSchema: { "properties": { "x": { "title": "X", "type": "integer", }, "y": { "title": "Y", "type": "integer", }, }, "required": [ "x", "y", ], "title": "OpperInputExample", "type": "object", }, outputSchema: { "properties": { "sum": { "title": "Sum", "type": "integer", }, }, "required": [ "sum", ], "title": "OpperOutputExample", "type": "object", }, input: { "x": 4, "y": 5, }, examples: [ { input: { "x": 1, "y": 3, }, output: { "sum": 4, }, comment: "Adds two numbers", }, ], parentSpanId: "123e4567-e89b-12d3-a456-426614174000", tags: { "project": "project_456", "user": "company_123", }, configuration: {}, }, { retries: { strategy: "backoff", backoff: { initialInterval: 1, maxInterval: 50, exponent: 1.1, maxElapsedTime: 100, }, retryConnectionErrors: false, }, });

console.log(result); }

run();


If you'd like to override the default retry strategy for all operations that support retries, you can provide a retryConfig at SDK initialization:
```typescript
import { Opper } from "opperai";

const opper = new Opper({
  retryConfig: {
    strategy: "backoff",
    backoff: {
      initialInterval: 1,
      maxInterval: 50,
      exponent: 1.1,
      maxElapsedTime: 100,
    },
    retryConnectionErrors: false,
  },
  httpBearer: process.env["OPPER_HTTP_BEARER"] ?? "",
});

async function run() {
  const result = await opper.call({
    name: "add_numbers",
    instructions: "Calculate the sum of two numbers",
    inputSchema: {
      "properties": {
        "x": {
          "title": "X",
          "type": "integer",
        },
        "y": {
          "title": "Y",
          "type": "integer",
        },
      },
      "required": [
        "x",
        "y",
      ],
      "title": "OpperInputExample",
      "type": "object",
    },
    outputSchema: {
      "properties": {
        "sum": {
          "title": "Sum",
          "type": "integer",
        },
      },
      "required": [
        "sum",
      ],
      "title": "OpperOutputExample",
      "type": "object",
    },
    input: {
      "x": 4,
      "y": 5,
    },
    examples: [
      {
        input: {
          "x": 1,
          "y": 3,
        },
        output: {
          "sum": 4,
        },
        comment: "Adds two numbers",
      },
    ],
    parentSpanId: "123e4567-e89b-12d3-a456-426614174000",
    tags: {
      "project": "project_456",
      "user": "company_123",
    },
    configuration: {},
  });

  console.log(result);
}

run();

Error Handling

Check our detailed docs for error handling

OpperError is the base class for all HTTP error responses. It has the following properties:

Property Type Description
error.message string Error message
error.statusCode number HTTP response status code eg 404
error.headers Headers HTTP response headers
error.body string HTTP body. Can be empty string if no body is returned.
error.rawResponse Response Raw HTTP response
error.data$ Optional. Some errors may contain structured data. See Error Classes.
Example Error Handling 
import { Opper } from "opperai";
import * as errors from "opperai/models/errors";

const opper = new Opper({
  httpBearer: process.env["OPPER_HTTP_BEARER"] ?? "",
});

async function run() {
  try {
    const result = await opper.call({
      name: "add_numbers",
      instructions: "Calculate the sum of two numbers",
      inputSchema: {
        "properties": {
          "x": {
            "title": "X",
            "type": "integer",
          },
          "y": {
            "title": "Y",
            "type": "integer",
          },
        },
        "required": [
          "x",
          "y",
        ],
        "title": "OpperInputExample",
        "type": "object",
      },
      outputSchema: {
        "properties": {
          "sum": {
            "title": "Sum",
            "type": "integer",
          },
        },
        "required": [
          "sum",
        ],
        "title": "OpperOutputExample",
        "type": "object",
      },
      input: {
        "x": 4,
        "y": 5,
      },
      examples: [
        {
          input: {
            "x": 1,
            "y": 3,
          },
          output: {
            "sum": 4,
          },
          comment: "Adds two numbers",
        },
      ],
      parentSpanId: "123e4567-e89b-12d3-a456-426614174000",
      tags: {
        "project": "project_456",
        "user": "company_123",
      },
      configuration: {},
    });

    console.log(result);
  } catch (error) {
    // The base class for HTTP error responses
    if (error instanceof errors.OpperError) {
      console.log(error.message);
      console.log(error.statusCode);
      console.log(error.body);
      console.log(error.headers);

      // Depending on the method different errors may be thrown
      if (error instanceof errors.BadRequestError) {
        console.log(error.data$.type); // string
        console.log(error.data$.message); // string
        console.log(error.data$.detail); // any
      }
    }
  }
}

run();

Error Classes

Primary errors:

Less common errors (8)

Network errors:

Inherit from OpperError:

  • ConflictError: Conflict. Status code 409. Applicable to 3 of 52 methods.*
  • ErrorT: Request validation error. Applicable to 1 of 52 methods.*
  • ResponseValidationError: Type mismatch between the data returned from the server and the structure expected by the SDK. See error.rawValue for the raw value and error.pretty() for a nicely formatted multi-line string.

* Check the method documentation to see if the error is applicable.

Server Selection

Server Selection ### Override Server URL Per-Client

The default server can be overridden globally by passing a URL to the serverURL: string optional parameter when initializing the SDK client instance. For example:

import { Opper } from "opperai";

const opper = new Opper({
  serverURL: "https://api.opper.ai/v2",
  httpBearer: process.env["OPPER_HTTP_BEARER"] ?? "",
});

async function run() {
  const result = await opper.call({
    name: "add_numbers",
    instructions: "Calculate the sum of two numbers",
    inputSchema: {
      "properties": {
        "x": {
          "title": "X",
          "type": "integer",
        },
        "y": {
          "title": "Y",
          "type": "integer",
        },
      },
      "required": [
        "x",
        "y",
      ],
      "title": "OpperInputExample",
      "type": "object",
    },
    outputSchema: {
      "properties": {
        "sum": {
          "title": "Sum",
          "type": "integer",
        },
      },
      "required": [
        "sum",
      ],
      "title": "OpperOutputExample",
      "type": "object",
    },
    input: {
      "x": 4,
      "y": 5,
    },
    examples: [
      {
        input: {
          "x": 1,
          "y": 3,
        },
        output: {
          "sum": 4,
        },
        comment: "Adds two numbers",
      },
    ],
    parentSpanId: "123e4567-e89b-12d3-a456-426614174000",
    tags: {
      "project": "project_456",
      "user": "company_123",
    },
    configuration: {},
  });

  console.log(result);
}

run();

Custom HTTP Client

Custom HTTP Client

The TypeScript SDK makes API calls using an HTTPClient that wraps the native Fetch API. This client is a thin wrapper around fetch and provides the ability to attach hooks around the request lifecycle that can be used to modify the request or handle errors and response.

The HTTPClient constructor takes an optional fetcher argument that can be used to integrate a third-party HTTP client or when writing tests to mock out the HTTP client and feed in fixtures.

The following example shows how to use the "beforeRequest" hook to to add a custom header and a timeout to requests and how to use the "requestError" hook to log errors:

import { Opper } from "opperai";
import { HTTPClient } from "opperai/lib/http";

const httpClient = new HTTPClient({
  // fetcher takes a function that has the same signature as native `fetch`.
  fetcher: (request) => {
    return fetch(request);
  }
});

httpClient.addHook("beforeRequest", (request) => {
  const nextRequest = new Request(request, {
    signal: request.signal || AbortSignal.timeout(5000)
  });

  nextRequest.headers.set("x-custom-header", "custom value");

  return nextRequest;
});

httpClient.addHook("requestError", (error, request) => {
  console.group("Request Error");
  console.log("Reason:", `${error}`);
  console.log("Endpoint:", `${request.method} ${request.url}`);
  console.groupEnd();
});

const sdk = new Opper({ httpClient });

Debugging

You can setup your SDK to emit debug logs for SDK requests and responses.

You can pass a logger that matches console's interface as an SDK option.

Warning

Beware that debug logging will reveal secrets, like API tokens in headers, in log messages printed to a console or files. It's recommended to use this feature only during local development and not in production.

import { Opper } from "opperai";

const sdk = new Opper({ debugLogger: console });

You can also enable a default debug logger by setting an environment variable OPPER_DEBUG to true.

Development

Maturity

This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally looking for the latest version.

Contributions

While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.

SDK Created by Speakeasy

About

Opper Node SDK

opper.ai

Resources

Readme

Contributing

Contributing
Activity
Custom properties

Stars

5 stars

Watchers

3 watching

Forks

0 forks
Report repository

Releases 51

🚀 Opper AI TypeScript SDK v3.4.0 Latest
Dec 9, 2025
+ 50 releases

Packages

No packages published

Contributors 6

Languages