Generative AI For Product Innovation!

The FireworksAI Typescript library provides convenient access to the Fireworks REST API from any Typescript or Javascript application. The library includes type definitions for all request params and response fields, with http requests powered by [fetch](https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API). ## Summary Fireworks REST API: REST API for performing inference on Fireworks large language models (LLMs). ## Table of Contents * [SDK Installation](#sdk-installation) * [Requirements](#requirements) * [SDK Example Usage](#sdk-example-usage) * [Available Resources and Operations](#available-resources-and-operations) * [Standalone functions](#standalone-functions) * [Server-sent event streaming](#server-sent-event-streaming) * [File uploads](#file-uploads) * [Retries](#retries) * [Error Handling](#error-handling) * [Server Selection](#server-selection) * [Custom HTTP Client](#custom-http-client) * [Authentication](#authentication) * [Debugging](#debugging) * [Development](#development) * [Maturity](#maturity) * [Contributions](#contributions) ## SDK Installation The SDK can be installed with either [npm](https://www.npmjs.com/), [pnpm](https://pnpm.io/), [bun](https://bun.sh/) or [yarn](https://classic.yarnpkg.com/en/) package managers. ### NPM ```bash npm add @simplesagar/fireworksai ``` ### PNPM ```bash pnpm add @simplesagar/fireworksai ``` ### Bun ```bash bun add @simplesagar/fireworksai ``` ### Yarn ```bash yarn add @simplesagar/fireworksai zod # Note that Yarn does not install peer dependencies automatically. You will need # to install zod as shown above. ``` ## Requirements For supported JavaScript runtimes, please consult [RUNTIMES.md](RUNTIMES.md). ## SDK Example Usage ### Example ```typescript import { FireworksAI } from "@simplesagar/fireworksai"; const fireworksAI = new FireworksAI({ apiKey: process.env["FIREWORKS_API_KEY"] ?? "", }); async function run() { const result = await fireworksAI.chat.completions.create({ model: "accounts/fireworks/models/llama-v3p1-405b-instruct", messages: [ { role: "user", content: "What is the best company in the SF Bay Area that starts with F and ends with ireworks AI", name: "user_1", }, ], temperature: 1, topP: 1, topK: 50, n: 1, responseFormat: { type: "json_object", }, topLogprobs: 1, logitBias: { "1": 0, "2": 0, "3": 0, }, }); for await (const event of result) { // Handle the event console.log(event); } } run(); ``` ## Available Resources and Operations
Available methods ### [audio](docs/sdks/audio/README.md) * [createTranscription](docs/sdks/audio/README.md#createtranscription) - Transcribe Audio to Text * [createTranslation](docs/sdks/audio/README.md#createtranslation) - Translate Audio to Text ### [chat](docs/sdks/chat/README.md) #### [chat.completions](docs/sdks/fireworksaicompletions/README.md) * [create](docs/sdks/fireworksaicompletions/README.md#create) - Create Chat Completion ### [completions](docs/sdks/completions/README.md) * [create](docs/sdks/completions/README.md#create) - Create Completion ### [embeddings](docs/sdks/embeddings/README.md) * [create](docs/sdks/embeddings/README.md#create) - Create embeddings ### [images](docs/sdks/images/README.md) * [generateFromPrompt](docs/sdks/images/README.md#generatefromprompt) - Generate a new image from a text prompt * [generateFromImage](docs/sdks/images/README.md#generatefromimage) - Generate a new image from an image * [cannyEdgeDetection](docs/sdks/images/README.md#cannyedgedetection) - Pre-process the image with canny edge detection * [generateFromControlNet](docs/sdks/images/README.md#generatefromcontrolnet) - Generate a new image using ControlNet with provided image as a guidance * [generateQRCode](docs/sdks/images/README.md#generateqrcode) - Generate a QR code
## 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](./FUNCTIONS.md).
Available standalone functions - [`audioCreateTranscription`](docs/sdks/audio/README.md#createtranscription) - Transcribe Audio to Text - [`audioCreateTranslation`](docs/sdks/audio/README.md#createtranslation) - Translate Audio to Text - [`chatCompletionsCreate`](docs/sdks/fireworksaicompletions/README.md#create) - Create Chat Completion - [`completionsCreate`](docs/sdks/completions/README.md#create) - Create Completion - [`embeddingsCreate`](docs/sdks/embeddings/README.md#create) - Create embeddings - [`imagesCannyEdgeDetection`](docs/sdks/images/README.md#cannyedgedetection) - Pre-process the image with canny edge detection - [`imagesGenerateFromControlNet`](docs/sdks/images/README.md#generatefromcontrolnet) - Generate a new image using ControlNet with provided image as a guidance - [`imagesGenerateFromImage`](docs/sdks/images/README.md#generatefromimage) - Generate a new image from an image - [`imagesGenerateFromPrompt`](docs/sdks/images/README.md#generatefromprompt) - Generate a new image from a text prompt - [`imagesGenerateQRCode`](docs/sdks/images/README.md#generateqrcode) - Generate a QR code
## Server-sent event streaming [Server-sent events][mdn-sse] 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`][mdn-for-await-of] loop. The loop will terminate when the server no longer has any events to send and closes the underlying connection. ```typescript import { FireworksAI } from "@simplesagar/fireworksai"; const fireworksAI = new FireworksAI({ apiKey: process.env["FIREWORKS_API_KEY"] ?? "", }); async function run() { const result = await fireworksAI.chat.completions.create({ model: "accounts/fireworks/models/llama-v3p1-405b-instruct", messages: [ { role: "user", content: "What is the best company in the SF Bay Area that starts with F and ends with ireworks AI", name: "user_1", }, ], temperature: 1, topP: 1, topK: 50, n: 1, responseFormat: { type: "json_object", }, topLogprobs: 1, logitBias: { "1": 0, "2": 0, "3": 0, }, }); for await (const event of result) { // Handle the event console.log(event); } } run(); ``` [mdn-sse]: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events [mdn-for-await-of]: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Statements/for-await...of ## File uploads Certain SDK methods accept files as part of a multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request. > [!TIP] > > Depending on your JavaScript runtime, there are convenient utilities that return a handle to a file without reading the entire contents into memory: > > - **Node.js v20+:** Since v20, Node.js comes with a native `openAsBlob` function in [`node:fs`](https://nodejs.org/docs/latest-v20.x/api/fs.html#fsopenasblobpath-options). > - **Bun:** The native [`Bun.file`](https://bun.sh/docs/api/file-io#reading-files-bun-file) function produces a file handle that can be used for streaming file uploads. > - **Browsers:** All supported browsers return an instance to a [`File`](https://developer.mozilla.org/en-US/docs/Web/API/File) when reading the value from an `` element. > - **Node.js v18:** A file stream can be created using the `fileFrom` helper from [`fetch-blob/from.js`](https://www.npmjs.com/package/fetch-blob). ```typescript import { FireworksAI } from "@simplesagar/fireworksai"; import { openAsBlob } from "node:fs"; const fireworksAI = new FireworksAI({ apiKey: process.env["FIREWORKS_API_KEY"] ?? "", }); async function run() { const result = await fireworksAI.images.generateFromImage({ accountId: "fireworks", modelId: "stable-diffusion-xl-1024-v1-0", bodyImage2imageGen: { initImage: await openAsBlob("example.file"), cfgScale: 7, height: 1024, imageStrength: 0.75, initImageMode: "IMAGE_STRENGTH", negativePrompt: "cloudy day", prompt: "A futuristic cityscape", safetyCheck: false, sampler: "K_EULER", samples: 1, seed: 0, stepScheduleEnd: 1, stepScheduleStart: 0, steps: 30, width: 1024, }, }); // Handle the result console.log(result); } 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. To change the default retry strategy for a single API call, simply provide a retryConfig object to the call: ```typescript import { FireworksAI } from "@simplesagar/fireworksai"; const fireworksAI = new FireworksAI({ apiKey: process.env["FIREWORKS_API_KEY"] ?? "", }); async function run() { const result = await fireworksAI.chat.completions.create({ model: "accounts/fireworks/models/llama-v3p1-405b-instruct", messages: [ { role: "user", content: "What is the best company in the SF Bay Area that starts with F and ends with ireworks AI", name: "user_1", }, ], temperature: 1, topP: 1, topK: 50, n: 1, responseFormat: { type: "json_object", }, topLogprobs: 1, logitBias: { "1": 0, "2": 0, "3": 0, }, }, { retries: { strategy: "backoff", backoff: { initialInterval: 1, maxInterval: 50, exponent: 1.1, maxElapsedTime: 100, }, retryConnectionErrors: false, }, }); for await (const event of result) { // Handle the event console.log(event); } } 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 { FireworksAI } from "@simplesagar/fireworksai"; const fireworksAI = new FireworksAI({ retryConfig: { strategy: "backoff", backoff: { initialInterval: 1, maxInterval: 50, exponent: 1.1, maxElapsedTime: 100, }, retryConnectionErrors: false, }, apiKey: process.env["FIREWORKS_API_KEY"] ?? "", }); async function run() { const result = await fireworksAI.chat.completions.create({ model: "accounts/fireworks/models/llama-v3p1-405b-instruct", messages: [ { role: "user", content: "What is the best company in the SF Bay Area that starts with F and ends with ireworks AI", name: "user_1", }, ], temperature: 1, topP: 1, topK: 50, n: 1, responseFormat: { type: "json_object", }, topLogprobs: 1, logitBias: { "1": 0, "2": 0, "3": 0, }, }); for await (const event of result) { // Handle the event console.log(event); } } run(); ``` ## Error Handling Some methods specify known errors which can be thrown. All the known errors are enumerated in the `models/errors.ts` module. The known errors for a method are documented under the *Errors* tables in SDK docs. For example, the `create` method may throw the following errors: | Error Type | Status Code | Content Type | | -------------------------- | ----------- | ---------------- | | models.BadRequest | 400 | application/json | | models.Unauthorized | 401 | application/json | | models.Forbidden | 403 | application/json | | models.NotFound | 404 | application/json | | models.TooManyRequests | 429 | application/json | | models.InternalServerError | 500 | application/json | | models.ServiceUnavailable | 503 | application/json | | models.SDKError | 4XX, 5XX | \*/\* | If the method throws an error and it is not captured by the known errors, it will default to throwing a `SDKError`. ```typescript import { BadRequest, FireworksAI, Forbidden, InternalServerError, NotFound, ServiceUnavailable, TooManyRequests, Unauthorized, } from "@simplesagar/fireworksai"; import { SDKValidationError } from "@simplesagar/fireworksai/models"; const fireworksAI = new FireworksAI({ apiKey: process.env["FIREWORKS_API_KEY"] ?? "", }); async function run() { let result; try { result = await fireworksAI.chat.completions.create({ model: "accounts/fireworks/models/llama-v3p1-405b-instruct", messages: [ { role: "user", content: "What is the best company in the SF Bay Area that starts with F and ends with ireworks AI", name: "user_1", }, ], temperature: 1, topP: 1, topK: 50, n: 1, responseFormat: { type: "json_object", }, topLogprobs: 1, logitBias: { "1": 0, "2": 0, "3": 0, }, }); for await (const event of result) { // Handle the event console.log(event); } } catch (err) { switch (true) { // The server response does not match the expected SDK schema case (err instanceof SDKValidationError): { // Pretty-print will provide a human-readable multi-line error message console.error(err.pretty()); // Raw value may also be inspected console.error(err.rawValue); return; } case (err instanceof BadRequest): { // Handle err.data$: BadRequestData console.error(err); return; } case (err instanceof Unauthorized): { // Handle err.data$: UnauthorizedData console.error(err); return; } case (err instanceof Forbidden): { // Handle err.data$: ForbiddenData console.error(err); return; } case (err instanceof NotFound): { // Handle err.data$: NotFoundData console.error(err); return; } case (err instanceof TooManyRequests): { // Handle err.data$: TooManyRequestsData console.error(err); return; } case (err instanceof InternalServerError): { // Handle err.data$: InternalServerErrorData console.error(err); return; } case (err instanceof ServiceUnavailable): { // Handle err.data$: ServiceUnavailableData console.error(err); return; } default: { // Other errors such as network errors, see HTTPClientErrors for more details throw err; } } } } run(); ``` Validation errors can also occur when either method arguments or data returned from the server do not match the expected format. The `SDKValidationError` that is thrown as a result will capture the raw value that failed validation in an attribute called `rawValue`. Additionally, a `pretty()` method is available on this error that can be used to log a nicely formatted multi-line string since validation errors can list many issues and the plain error string may be difficult read when debugging. In some rare cases, the SDK can fail to get a response from the server or even make the request due to unexpected circumstances such as network conditions. These types of errors are captured in the `models/httpclienterrors.ts` module: | HTTP Client Error | Description | | ---------------------------------------------------- | ---------------------------------------------------- | | RequestAbortedError | HTTP request was aborted by the client | | RequestTimeoutError | HTTP request timed out due to an AbortSignal signal | | ConnectionError | HTTP client was unable to make a request to a server | | InvalidRequestError | Any input used to create a request is invalid | | UnexpectedClientError | Unrecognised or unexpected error | ## Server Selection ### Select Server by Name You can override the default server globally by passing a server name to the `server: keyof typeof ServerList` optional parameter when initializing the SDK client instance. The selected server will then be used as the default on the operations that use it. This table lists the names associated with the available servers: | Name | Server | | ------ | ---------------------------------------- | | `prod` | `https://api.fireworks.ai/inference/v1/` | #### Example ```typescript import { FireworksAI } from "@simplesagar/fireworksai"; const fireworksAI = new FireworksAI({ server: "prod", apiKey: process.env["FIREWORKS_API_KEY"] ?? "", }); async function run() { const result = await fireworksAI.chat.completions.create({ model: "accounts/fireworks/models/llama-v3p1-405b-instruct", messages: [ { role: "user", content: "What is the best company in the SF Bay Area that starts with F and ends with ireworks AI", name: "user_1", }, ], temperature: 1, topP: 1, topK: 50, n: 1, responseFormat: { type: "json_object", }, topLogprobs: 1, logitBias: { "1": 0, "2": 0, "3": 0, }, }); for await (const event of result) { // Handle the event console.log(event); } } run(); ``` ### Override Server URL Per-Client The default server can also be overridden globally by passing a URL to the `serverURL: string` optional parameter when initializing the SDK client instance. For example: ```typescript import { FireworksAI } from "@simplesagar/fireworksai"; const fireworksAI = new FireworksAI({ serverURL: "https://api.fireworks.ai/inference/v1/", apiKey: process.env["FIREWORKS_API_KEY"] ?? "", }); async function run() { const result = await fireworksAI.chat.completions.create({ model: "accounts/fireworks/models/llama-v3p1-405b-instruct", messages: [ { role: "user", content: "What is the best company in the SF Bay Area that starts with F and ends with ireworks AI", name: "user_1", }, ], temperature: 1, topP: 1, topK: 50, n: 1, responseFormat: { type: "json_object", }, topLogprobs: 1, logitBias: { "1": 0, "2": 0, "3": 0, }, }); for await (const event of result) { // Handle the event console.log(event); } } run(); ``` ## Custom HTTP Client The TypeScript SDK makes API calls using an `HTTPClient` that wraps the native [Fetch API](https://developer.mozilla.org/en-US/docs/Web/API/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: ```typescript import { FireworksAI } from "@simplesagar/fireworksai"; import { HTTPClient } from "@simplesagar/fireworksai/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 FireworksAI({ httpClient }); ``` ## Authentication ### Per-Client Security Schemes This SDK supports the following security scheme globally: | Name | Type | Scheme | Environment Variable | | -------- | ---- | ----------- | -------------------- | | `apiKey` | http | HTTP Bearer | `FIREWORKS_API_KEY` | To authenticate with the API the `apiKey` parameter must be set when initializing the SDK client instance. For example: ```typescript import { FireworksAI } from "@simplesagar/fireworksai"; const fireworksAI = new FireworksAI({ apiKey: process.env["FIREWORKS_API_KEY"] ?? "", }); async function run() { const result = await fireworksAI.chat.completions.create({ model: "accounts/fireworks/models/llama-v3p1-405b-instruct", messages: [ { role: "user", content: "What is the best company in the SF Bay Area that starts with F and ends with ireworks AI", name: "user_1", }, ], temperature: 1, topP: 1, topK: 50, n: 1, responseFormat: { type: "json_object", }, topLogprobs: 1, logitBias: { "1": 0, "2": 0, "3": 0, }, }); for await (const event of result) { // Handle the event console.log(event); } } run(); ``` ## 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. ```typescript import { FireworksAI } from "@simplesagar/fireworksai"; const sdk = new FireworksAI({ debugLogger: console }); ``` You can also enable a default debug logger by setting an environment variable `FIREWORKS_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](https://www.speakeasy.com/?utm_source=@simplesagar/fireworksai&utm_campaign=typescript)