@llamaindex/llama-cloud 1.6.0 → 1.8.0

package/CHANGELOG.md

@@ -1,5 +1,60 @@
 # Changelog
 
+## 1.8.0 (2026-03-05)
+
+Full Changelog: [v1.7.0...v1.8.0](https://github.com/run-llama/llama-cloud-ts/compare/v1.7.0...v1.8.0)
+
+### Features
+
+* **api:** add better deprecation messages ([249c29c](https://github.com/run-llama/llama-cloud-ts/commit/249c29c7eae0343136d84180305dfa4c9c833200))
+* **api:** Add Classify V2 API ([466e946](https://github.com/run-llama/llama-cloud-ts/commit/466e946aa23b0d00ede11608a3d1b136560ed9bc))
+* **api:** api update ([fffb54f](https://github.com/run-llama/llama-cloud-ts/commit/fffb54f32b7a4e31cd3631d8a150e6aecd0509c4))
+* **api:** better deprecation config ([222f946](https://github.com/run-llama/llama-cloud-ts/commit/222f946dda7d71c29788c64c58f89d70e2c84800))
+* support LLAMA_PARSE_API_KEY as fallback env var for authentication ([756b8de](https://github.com/run-llama/llama-cloud-ts/commit/756b8dedcf354cb28a981bf341eb0a442b1d39e5))
+
+
+### Bug Fixes
+
+* fix request delays for retrying to be more respectful of high requested delays ([b191726](https://github.com/run-llama/llama-cloud-ts/commit/b191726c37e8eaf7870151a4e6cdebc1f27294c8))
+
+
+### Chores
+
+* **internal:** use x-stainless-mcp-client-envs header for MCP remote code tool calls ([43a1bf2](https://github.com/run-llama/llama-cloud-ts/commit/43a1bf2fe8d25742442815b42e3b22305b89a33b))
+
+## 1.7.0 (2026-03-03)
+
+Full Changelog: [v1.6.0...v1.7.0](https://github.com/run-llama/llama-cloud-ts/compare/v1.6.0...v1.7.0)
+
+### Features
+
+* **api:** api update ([1118a71](https://github.com/run-llama/llama-cloud-ts/commit/1118a71e1a81b008a0f010171055363fff91d029))
+* **api:** api update ([3e86820](https://github.com/run-llama/llama-cloud-ts/commit/3e868203b1802b41fab57d8c23a8b929c7a31abe))
+* **api:** api update ([e53cdc7](https://github.com/run-llama/llama-cloud-ts/commit/e53cdc779e95a2b7a3cfb0e1cff5603f6dfbd8ec))
+* **mcp:** add an option to disable code tool ([59a4382](https://github.com/run-llama/llama-cloud-ts/commit/59a43823a951cf488f29da4af3136a71eec9d437))
+
+
+### Bug Fixes
+
+* **docs/contributing:** correct pnpm link command ([8ebcd1e](https://github.com/run-llama/llama-cloud-ts/commit/8ebcd1eb8a1276b5d774d4a7c35a99dc58de767e))
+* **mcp:** initialize SDK lazily to avoid failing the connection on init errors ([586ef99](https://github.com/run-llama/llama-cloud-ts/commit/586ef99cc38543cae92003a6ad3c076b97b5e15a))
+* **mcp:** update prompt ([51ff157](https://github.com/run-llama/llama-cloud-ts/commit/51ff1578bb202b50c9df2d900ae868f918bec825))
+
+
+### Chores
+
+* **internal:** cache fetch instruction calls in MCP server ([1910716](https://github.com/run-llama/llama-cloud-ts/commit/1910716b6965286951b05e2cbae6839117df7d81))
+* **internal:** fix MCP Dockerfiles so they can be built without buildkit ([c71507a](https://github.com/run-llama/llama-cloud-ts/commit/c71507adf02a899adb554e0feadfa161477253c9))
+* **internal:** fix MCP Dockerfiles so they can be built without buildkit ([8cafa3b](https://github.com/run-llama/llama-cloud-ts/commit/8cafa3b5ebdcf3cde636edacb5a8fe81c1537df7))
+* **internal:** make MCP code execution location configurable via a flag ([753240c](https://github.com/run-llama/llama-cloud-ts/commit/753240c9d3e0e813ca22b999076cd86bcb923107))
+* **internal:** move stringifyQuery implementation to internal function ([c5931c5](https://github.com/run-llama/llama-cloud-ts/commit/c5931c55cd5e961173c4ffbf7485496bc6280579))
+* **internal:** remove mock server code ([28fd07f](https://github.com/run-llama/llama-cloud-ts/commit/28fd07f362276fbda68955d0ef27ea3e53f2380e))
+* **internal:** switch MCP servers to use pino for logging ([f4b2326](https://github.com/run-llama/llama-cloud-ts/commit/f4b232620c447f2043b3ccc4a7eda0799f6e38dc))
+* **internal:** upgrade @modelcontextprotocol/sdk and hono ([4161193](https://github.com/run-llama/llama-cloud-ts/commit/4161193bf554873976f442c0f62511af9a2dfbca))
+* **mcp-server:** return access instructions for 404 without API key ([fe1526d](https://github.com/run-llama/llama-cloud-ts/commit/fe1526d4d9e09feb074affe5c2690bc0ca0167d8))
+* **mcp:** correctly update version in sync with sdk ([89f6113](https://github.com/run-llama/llama-cloud-ts/commit/89f6113e42525fd8533b18e58a77d8b859b85d39))
+* update mock server docs ([9536239](https://github.com/run-llama/llama-cloud-ts/commit/9536239d4291dac002823d687ba74055ed7e175d))
+
 ## 1.6.0 (2026-02-18)
 
 Full Changelog: [v1.5.0...v1.6.0](https://github.com/run-llama/llama-cloud-ts/compare/v1.5.0...v1.6.0)

package/README.md

@@ -1,21 +1,22 @@
-# Llama Cloud TypeScript API Library
+# Llama Cloud TypeScript SDK
 
 [![NPM version](<https://img.shields.io/npm/v/@llamaindex/llama-cloud.svg?label=npm%20(stable)>)](https://npmjs.org/package/@llamaindex/llama-cloud) ![npm bundle size](https://img.shields.io/bundlephobia/minzip/@llamaindex/llama-cloud)
 
-This library provides convenient access to the Llama Cloud REST API from server-side TypeScript or JavaScript.
+The official TypeScript SDK for [LlamaParse](https://cloud.llamaindex.ai) - the enterprise platform for agentic OCR and document processing.
 
-The REST API documentation can be found on [developers.llamaindex.ai](https://developers.llamaindex.ai/). The full API of this library can be found in [api.md](api.md).
+With this SDK, create powerful workflows across many features:
 
-It is generated with [Stainless](https://www.stainless.com/).
+- **Parse** - Agentic OCR and parsing for 130+ formats
+- **Extract** - Structured data extraction with custom schemas
+- **Classify** - Document categorization with natural-language rules
+- **Agents** - Deploy document agents as APIs
+- **Index** - Document ingestion and embedding for RAG
 
-## MCP Server
-
-Use the Llama Cloud MCP Server to enable AI assistants to interact with this API, allowing them to explore endpoints, make test requests, and use documentation to help integrate this SDK into your application.
-
-[![Add to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en-US/install-mcp?name=%40llamaindex%2Fllama-cloud-mcp&config=eyJuYW1lIjoiQGxsYW1haW5kZXgvbGxhbWEtY2xvdWQtbWNwIiwidHJhbnNwb3J0IjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbGxhbWFjbG91ZC1wcm9kLnN0bG1jcC5jb20iLCJoZWFkZXJzIjp7IngtbGxhbWEtY2xvdWQtYXBpLWtleSI6Ik15IEFQSSBLZXkifX0)
-[![Install in VS Code](https://img.shields.io/badge/_-Add_to_VS_Code-blue?style=for-the-badge&logo=data:image/svg%2bxml;base64,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)](https://vscode.stainless.com/mcp/%7B%22name%22%3A%22%40llamaindex%2Fllama-cloud-mcp%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fllamacloud-prod.stlmcp.com%22%2C%22headers%22%3A%7B%22x-llama-cloud-api-key%22%3A%22My%20API%20Key%22%7D%7D)
+## Documentation
 
-> Note: You may need to set environment variables in your MCP client.
+- [Get an API Key](https://cloud.llamaindex.ai)
+- [Getting Started Guide](https://developers.llamaindex.ai/typescript/cloud/)
+- [Full API Reference](https://developers.api.llamaindex.ai/api/typescript)
 
 ## Installation
 
@@ -23,103 +24,66 @@ Use the Llama Cloud MCP Server to enable AI assistants to interact with this API
 npm install @llamaindex/llama-cloud
 ```
 
-## Usage
+## Quick Start
 
-The full API of this library can be found in [api.md](api.md).
-
-<!-- prettier-ignore -->
-```js
+```ts
 import LlamaCloud from '@llamaindex/llama-cloud';
 
 const client = new LlamaCloud({
   apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted
 });
 
-const parsing = await client.parsing.create({
+// Parse a document
+const job = await client.parsing.create({
   tier: 'agentic',
   version: 'latest',
-  file_id: 'abc1234',
+  file_id: 'your-file-id',
 });
 
-console.log(parsing.id);
+console.log(job.id);
 ```
 
-### Request & Response types
-
-This library includes TypeScript definitions for all request params and response fields. You may import and use them like so:
-
-<!-- prettier-ignore -->
-```ts
-import LlamaCloud from '@llamaindex/llama-cloud';
-
-const client = new LlamaCloud({
-  apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted
-});
-
-const params: LlamaCloud.PipelineListParams = { project_id: 'my-project-id' };
-const pipelines: LlamaCloud.PipelineListResponse = await client.pipelines.list(params);
-```
-
-Documentation for each method, request param, and response field are available in docstrings and will appear on hover in most modern editors.
-
-## File uploads
-
-Request parameters that correspond to file uploads can be passed in many different forms:
-
-- `File` (or an object with the same structure)
-- a `fetch` `Response` (or an object with the same structure)
-- an `fs.ReadStream`
-- the return value of our `toFile` helper
+## File Uploads
 
 ```ts
 import fs from 'fs';
-import LlamaCloud, { toFile } from '@llamaindex/llama-cloud';
+import LlamaCloud from '@llamaindex/llama-cloud';
 
 const client = new LlamaCloud();
 
-// If you have access to Node `fs` we recommend using `fs.createReadStream()`:
-await client.files.create({ file: fs.createReadStream('/path/to/file'), purpose: 'purpose' });
-
-// Or if you have the web `File` API you can pass a `File` instance:
-await client.files.create({ file: new File(['my bytes'], 'file'), purpose: 'purpose' });
-
-// You can also pass a `fetch` `Response`:
-await client.files.create({ file: await fetch('https://somesite/file'), purpose: 'purpose' });
-
-// Finally, if none of the above are convenient, you can use our `toFile` helper:
+// Upload using a file stream
 await client.files.create({
-  file: await toFile(Buffer.from('my bytes'), 'file'),
+  file: fs.createReadStream('/path/to/document.pdf'),
   purpose: 'purpose',
 });
+
+// Or using a File object
 await client.files.create({
-  file: await toFile(new Uint8Array([0, 1, 2]), 'file'),
+  file: new File(['content'], 'document.txt'),
   purpose: 'purpose',
 });
 ```
 
-## Handling errors
+## MCP Server
+
+Use the Llama Cloud MCP Server to enable AI assistants to interact with the API:
 
-When the library is unable to connect to the API,
-or if the API returns a non-success status code (i.e., 4xx or 5xx response),
-a subclass of `APIError` will be thrown:
+[![Add to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en-US/install-mcp?name=%40llamaindex%2Fllama-cloud-mcp&config=eyJuYW1lIjoiQGxsYW1haW5kZXgvbGxhbWEtY2xvdWQtbWNwIiwidHJhbnNwb3J0IjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbGxhbWFjbG91ZC1wcm9kLnN0bG1jcC5jb20iLCJoZWFkZXJzIjp7IngtbGxhbWEtY2xvdWQtYXBpLWtleSI6Ik15IEFQSSBLZXkifX0)
+[![Install in VS Code](https://img.shields.io/badge/_-Add_to_VS_Code-blue?style=for-the-badge&logo=data:image/svg%2bxml;base64,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)](https://vscode.stainless.com/mcp/%7B%22name%22%3A%22%40llamaindex%2Fllama-cloud-mcp%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fllamacloud-prod.stlmcp.com%22%2C%22headers%22%3A%7B%22x-llama-cloud-api-key%22%3A%22My%20API%20Key%22%7D%7D)
+
+## Error Handling
+
+When the API returns a non-success status code, an `APIError` subclass is thrown:
 
-<!-- prettier-ignore -->
 ```ts
-const pipelines = await client.pipelines
-  .list({ project_id: 'my-project-id' })
-  .catch(async (err) => {
-    if (err instanceof LlamaCloud.APIError) {
-      console.log(err.status); // 400
-      console.log(err.name); // BadRequestError
-      console.log(err.headers); // {server: 'nginx', ...}
-    } else {
-      throw err;
-    }
-  });
+await client.pipelines.list({ project_id: 'my-project-id' }).catch((err) => {
+  if (err instanceof LlamaCloud.APIError) {
+    console.log(err.status); // 400
+    console.log(err.name); // BadRequestError
+  }
+});
 ```
 
-Error codes are as follows:
-
 | Status Code | Error Type                 |
 | ----------- | -------------------------- |
 | 400         | `BadRequestError`          |
@@ -131,318 +95,58 @@ Error codes are as follows:
 | >=500       | `InternalServerError`      |
 | N/A         | `APIConnectionError`       |
 
-### Retries
-
-Certain errors will be automatically retried 2 times by default, with a short exponential backoff.
-Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict,
-429 Rate Limit, and >=500 Internal errors will all be retried by default.
-
-You can use the `maxRetries` option to configure or disable this:
-
-<!-- prettier-ignore -->
-```js
-// Configure the default for all requests:
-const client = new LlamaCloud({
-  maxRetries: 0, // default is 2
-});
-
-// Or, configure per-request:
-await client.pipelines.list({ project_id: 'my-project-id' }, {
-  maxRetries: 5,
-});
-```
-
-### Timeouts
+## Retries and Timeouts
 
-Requests time out after 1 minute by default. You can configure this with a `timeout` option:
+The SDK automatically retries requests 2 times on connection errors, timeouts, rate limits, and 5xx errors. Requests timeout after 1 minute by default. Functions that combine multiple API calls (e.g. `client.parsing.parse()`) will have larger timeouts by default to account for the multiple requests and polling.
 
-<!-- prettier-ignore -->
 ```ts
-// Configure the default for all requests:
 const client = new LlamaCloud({
-  timeout: 20 * 1000, // 20 seconds (default is 1 minute)
-});
-
-// Override per-request:
-await client.pipelines.list({ project_id: 'my-project-id' }, {
-  timeout: 5 * 1000,
+  maxRetries: 0, // Disable retries (default: 2)
+  timeout: 30 * 1000, // 30 second timeout (default: 1 minute)
 });
 ```
 
-On timeout, an `APIConnectionTimeoutError` is thrown.
-
-Note that requests which time out will be [retried twice by default](#retries).
+## Pagination
 
-## Auto-pagination
-
-List methods in the LlamaCloud API are paginated.
-You can use the `for await … of` syntax to iterate through items across all pages:
+List methods support auto-pagination with `for await...of`:
 
 ```ts
-async function fetchAllExtractRuns(params) {
-  const allExtractRuns = [];
-  // Automatically fetches more pages as needed.
-  for await (const extractRun of client.extraction.runs.list({
-    extraction_agent_id: '30988414-9163-4a0b-a7e0-35dd760109d7',
-    limit: 20,
-  })) {
-    allExtractRuns.push(extractRun);
-  }
-  return allExtractRuns;
+for await (const run of client.extraction.runs.list({
+  extraction_agent_id: 'agent-id',
+  limit: 20,
+})) {
+  console.log(run);
 }
 ```
 
-Alternatively, you can request a single page at a time:
+Or fetch one page at a time:
 
 ```ts
-let page = await client.extraction.runs.list({
-  extraction_agent_id: '30988414-9163-4a0b-a7e0-35dd760109d7',
-  limit: 20,
-});
-for (const extractRun of page.items) {
-  console.log(extractRun);
+let page = await client.extraction.runs.list({ extraction_agent_id: 'agent-id', limit: 20 });
+for (const run of page.items) {
+  console.log(run);
 }
 
-// Convenience methods are provided for manually paginating:
 while (page.hasNextPage()) {
   page = await page.getNextPage();
-  // ...
 }
 ```
 
-## Advanced Usage
-
-### Accessing raw Response data (e.g., headers)
-
-The "raw" `Response` returned by `fetch()` can be accessed through the `.asResponse()` method on the `APIPromise` type that all methods return.
-This method returns as soon as the headers for a successful response are received and does not consume the response body, so you are free to write custom parsing or streaming logic.
-
-You can also use the `.withResponse()` method to get the raw `Response` along with the parsed data.
-Unlike `.asResponse()` this method consumes the body, returning once it is parsed.
-
-<!-- prettier-ignore -->
-```ts
-const client = new LlamaCloud();
-
-const response = await client.pipelines.list({ project_id: 'my-project-id' }).asResponse();
-console.log(response.headers.get('X-My-Header'));
-console.log(response.statusText); // access the underlying Response object
-
-const { data: pipelines, response: raw } = await client.pipelines
-  .list({ project_id: 'my-project-id' })
-  .withResponse();
-console.log(raw.headers.get('X-My-Header'));
-console.log(pipelines);
-```
-
-### Logging
-
-> [!IMPORTANT]
-> All log messages are intended for debugging only. The format and content of log messages
-> may change between releases.
-
-#### Log levels
-
-The log level can be configured in two ways:
-
-1. Via the `LLAMA_CLOUD_LOG` environment variable
-2. Using the `logLevel` client option (overrides the environment variable if set)
-
-```ts
-import LlamaCloud from '@llamaindex/llama-cloud';
-
-const client = new LlamaCloud({
-  logLevel: 'debug', // Show all log messages
-});
-```
-
-Available log levels, from most to least verbose:
-
-- `'debug'` - Show debug messages, info, warnings, and errors
-- `'info'` - Show info messages, warnings, and errors
-- `'warn'` - Show warnings and errors (default)
-- `'error'` - Show only errors
-- `'off'` - Disable all logging
-
-At the `'debug'` level, all HTTP requests and responses are logged, including headers and bodies.
-Some authentication-related headers are redacted, but sensitive data in request and response bodies
-may still be visible.
-
-#### Custom logger
-
-By default, this library logs to `globalThis.console`. You can also provide a custom logger.
-Most logging libraries are supported, including [pino](https://www.npmjs.com/package/pino), [winston](https://www.npmjs.com/package/winston), [bunyan](https://www.npmjs.com/package/bunyan), [consola](https://www.npmjs.com/package/consola), [signale](https://www.npmjs.com/package/signale), and [@std/log](https://jsr.io/@std/log). If your logger doesn't work, please open an issue.
-
-When providing a custom logger, the `logLevel` option still controls which messages are emitted, messages
-below the configured level will not be sent to your logger.
-
-```ts
-import LlamaCloud from '@llamaindex/llama-cloud';
-import pino from 'pino';
-
-const logger = pino();
-
-const client = new LlamaCloud({
-  logger: logger.child({ name: 'LlamaCloud' }),
-  logLevel: 'debug', // Send all messages to pino, allowing it to filter
-});
-```
-
-### Making custom/undocumented requests
-
-This library is typed for convenient access to the documented API. If you need to access undocumented
-endpoints, params, or response properties, the library can still be used.
-
-#### Undocumented endpoints
-
-To make requests to undocumented endpoints, you can use `client.get`, `client.post`, and other HTTP verbs.
-Options on the client, such as retries, will be respected when making these requests.
-
-```ts
-await client.post('/some/path', {
-  body: { some_prop: 'foo' },
-  query: { some_query_arg: 'bar' },
-});
-```
-
-#### Undocumented request params
-
-To make requests using undocumented parameters, you may use `// @ts-expect-error` on the undocumented
-parameter. This library doesn't validate at runtime that the request matches the type, so any extra values you
-send will be sent as-is.
-
-```ts
-client.parsing.create({
-  // ...
-  // @ts-expect-error baz is not yet public
-  baz: 'undocumented option',
-});
-```
-
-For requests with the `GET` verb, any extra params will be in the query, all other requests will send the
-extra param in the body.
-
-If you want to explicitly send an extra argument, you can do so with the `query`, `body`, and `headers` request
-options.
-
-#### Undocumented response properties
-
-To access undocumented response properties, you may access the response object with `// @ts-expect-error` on
-the response object, or cast the response object to the requisite type. Like the request params, we do not
-validate or strip extra properties from the response from the API.
-
-### Customizing the fetch client
-
-By default, this library expects a global `fetch` function is defined.
-
-If you want to use a different `fetch` function, you can either polyfill the global:
-
-```ts
-import fetch from 'my-fetch';
-
-globalThis.fetch = fetch;
-```
-
-Or pass it to the client:
-
-```ts
-import LlamaCloud from '@llamaindex/llama-cloud';
-import fetch from 'my-fetch';
-
-const client = new LlamaCloud({ fetch });
-```
-
-### Fetch options
-
-If you want to set custom `fetch` options without overriding the `fetch` function, you can provide a `fetchOptions` object when instantiating the client or making a request. (Request-specific options override client options.)
-
-```ts
-import LlamaCloud from '@llamaindex/llama-cloud';
-
-const client = new LlamaCloud({
-  fetchOptions: {
-    // `RequestInit` options
-  },
-});
-```
-
-#### Configuring proxies
-
-To modify proxy behavior, you can provide custom `fetchOptions` that add runtime-specific proxy
-options to requests:
+## Logging
 
-<img src="https://raw.githubusercontent.com/stainless-api/sdk-assets/refs/heads/main/node.svg" align="top" width="18" height="21"> **Node** <sup>[[docs](https://github.com/nodejs/undici/blob/main/docs/docs/api/ProxyAgent.md#example---proxyagent-with-fetch)]</sup>
+Configure logging via the `LLAMA_CLOUD_LOG` environment variable or the `logLevel` option:
 
 ```ts
-import LlamaCloud from '@llamaindex/llama-cloud';
-import * as undici from 'undici';
-
-const proxyAgent = new undici.ProxyAgent('http://localhost:8888');
 const client = new LlamaCloud({
-  fetchOptions: {
-    dispatcher: proxyAgent,
-  },
+  logLevel: 'debug', // 'debug' | 'info' | 'warn' | 'error' | 'off'
 });
 ```
 
-<img src="https://raw.githubusercontent.com/stainless-api/sdk-assets/refs/heads/main/bun.svg" align="top" width="18" height="21"> **Bun** <sup>[[docs](https://bun.sh/guides/http/proxy)]</sup>
-
-```ts
-import LlamaCloud from '@llamaindex/llama-cloud';
-
-const client = new LlamaCloud({
-  fetchOptions: {
-    proxy: 'http://localhost:8888',
-  },
-});
-```
-
-<img src="https://raw.githubusercontent.com/stainless-api/sdk-assets/refs/heads/main/deno.svg" align="top" width="18" height="21"> **Deno** <sup>[[docs](https://docs.deno.com/api/deno/~/Deno.createHttpClient)]</sup>
-
-```ts
-import LlamaCloud from 'npm:@llamaindex/llama-cloud';
-
-const httpClient = Deno.createHttpClient({ proxy: { url: 'http://localhost:8888' } });
-const client = new LlamaCloud({
-  fetchOptions: {
-    client: httpClient,
-  },
-});
-```
-
-## Frequently Asked Questions
-
-## Semantic versioning
-
-This package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions, though certain backwards-incompatible changes may be released as minor versions:
-
-1. Changes that only affect static types, without breaking runtime behavior.
-2. Changes to library internals which are technically public but not intended or documented for external use. _(Please open a GitHub issue to let us know if you are relying on such internals.)_
-3. Changes that we do not expect to impact the vast majority of users in practice.
-
-We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.
-
-We are keen for your feedback; please open an [issue](https://www.github.com/run-llama/llama-cloud-ts/issues) with questions, bugs, or suggestions.
-
 ## Requirements
 
-TypeScript >= 4.9 is supported.
-
-The following runtimes are supported:
-
-- Web browsers (Up-to-date Chrome, Firefox, Safari, Edge, and more)
-- Node.js 20 LTS or later ([non-EOL](https://endoflife.date/nodejs)) versions.
-- Deno v1.28.0 or higher.
-- Bun 1.0 or later.
-- Cloudflare Workers.
-- Vercel Edge Runtime.
-- Jest 28 or greater with the `"node"` environment (`"jsdom"` is not supported at this time).
-- Nitro v2.6 or greater.
-
-Note that React Native is not supported at this time.
-
-If you are interested in other runtime environments, please open or upvote an issue on GitHub.
+- TypeScript >= 4.9
+- Node.js 20+, Deno 1.28+, Bun 1.0+, or modern browsers
 
 ## Contributing
 
-See [the contributing documentation](./CONTRIBUTING.md).
+See [CONTRIBUTING.md](./CONTRIBUTING.md).

package/client.d.mts

@@ -8,6 +8,7 @@ import { type PaginatedBatchItemsParams, PaginatedBatchItemsResponse, type Pagin
 import * as Uploads from "./core/uploads.mjs";
 import * as API from "./resources/index.mjs";
 import { APIPromise } from "./core/api-promise.mjs";
+import { Classify, ClassifyConfiguration, ClassifyCreateParams, ClassifyCreateRequest, ClassifyCreateResponse, ClassifyGetParams, ClassifyGetResponse, ClassifyListParams, ClassifyListResponse, ClassifyListResponsesPaginatedCursor, ClassifyResult } from "./resources/classify.mjs";
 import { DataSink, DataSinkCreateParams, DataSinkListParams, DataSinkListResponse, DataSinkUpdateParams, DataSinks } from "./resources/data-sinks.mjs";
 import { DataSource, DataSourceCreateParams, DataSourceListParams, DataSourceListResponse, DataSourceReaderVersionMetadata, DataSourceUpdateParams, DataSources } from "./resources/data-sources.mjs";
 import { File, FileCreate, FileCreateParams, FileCreateResponse, FileDeleteParams, FileGetParams, FileListParams, FileListResponse, FileListResponsesPaginatedCursor, FileQueryParams, FileQueryResponse, Files, PresignedURL } from "./resources/files.mjs";
@@ -24,7 +25,7 @@ import { FinalRequestOptions, RequestOptions } from "./internal/request-options.
 import { type LogLevel, type Logger } from "./internal/utils/log.mjs";
 export interface ClientOptions {
     /**
-     * Defaults to process.env['LLAMA_CLOUD_API_KEY'].
+     * Defaults to process.env['LLAMA_CLOUD_API_KEY'] or process.env['LLAMA_PARSE_API_KEY'].
      */
     apiKey?: string | undefined;
     /**
@@ -106,7 +107,7 @@ export declare class LlamaCloud {
     /**
      * API Client for interfacing with the Llama Cloud API.
      *
-     * @param {string | undefined} [opts.apiKey=process.env['LLAMA_CLOUD_API_KEY'] ?? undefined]
+     * @param {string | undefined} [opts.apiKey=process.env['LLAMA_CLOUD_API_KEY'] ?? process.env['LLAMA_PARSE_API_KEY'] ?? undefined]
      * @param {string} [opts.baseURL=process.env['LLAMA_CLOUD_BASE_URL'] ?? https://api.cloud.llamaindex.ai] - Override the default base URL for the API.
      * @param {number} [opts.timeout=1 minute] - The maximum amount of time (in milliseconds) the client will wait for a response before timing out.
      * @param {MergedRequestInit} [opts.fetchOptions] - Additional `RequestInit` options to be passed to `fetch` calls.
@@ -123,7 +124,7 @@ export declare class LlamaCloud {
     protected defaultQuery(): Record<string, string | undefined> | undefined;
     protected validateHeaders({ values, nulls }: NullableHeaders): void;
     protected authHeaders(opts: FinalRequestOptions): Promise<NullableHeaders | undefined>;
-    protected stringifyQuery(query: Record<string, unknown>): string;
+    protected stringifyQuery(query: object | Record<string, unknown>): string;
     private getUserAgent;
     protected defaultIdempotencyKey(): string;
     protected makeStatusError(status: number, error: Object, message: string | undefined, headers: Headers): Errors.APIError;
@@ -186,6 +187,7 @@ export declare class LlamaCloud {
     parsing: API.Parsing;
     extraction: API.Extraction;
     classifier: API.Classifier;
+    classify: API.Classify;
     projects: API.Projects;
     dataSinks: API.DataSinks;
     dataSources: API.DataSources;
@@ -215,6 +217,7 @@ export declare namespace LlamaCloud {
     export { Parsing as Parsing, type BBox as BBox, type CodeItem as CodeItem, type FailPageMode as FailPageMode, type FooterItem as FooterItem, type HeaderItem as HeaderItem, type HeadingItem as HeadingItem, type ImageItem as ImageItem, type LinkItem as LinkItem, type ListItem as ListItem, type LlamaParseSupportedFileExtensions as LlamaParseSupportedFileExtensions, type ParsingJob as ParsingJob, type ParsingLanguages as ParsingLanguages, type ParsingMode as ParsingMode, type StatusEnum as StatusEnum, type TableItem as TableItem, type TextItem as TextItem, type ParsingCreateResponse as ParsingCreateResponse, type ParsingListResponse as ParsingListResponse, type ParsingGetResponse as ParsingGetResponse, type ParsingListResponsesPaginatedCursor as ParsingListResponsesPaginatedCursor, type ParsingCreateParams as ParsingCreateParams, type ParsingListParams as ParsingListParams, type ParsingGetParams as ParsingGetParams, };
     export { Extraction as Extraction, type ExtractionRunParams as ExtractionRunParams };
     export { Classifier as Classifier };
+    export { Classify as Classify, type ClassifyConfiguration as ClassifyConfiguration, type ClassifyCreateRequest as ClassifyCreateRequest, type ClassifyResult as ClassifyResult, type ClassifyCreateResponse as ClassifyCreateResponse, type ClassifyListResponse as ClassifyListResponse, type ClassifyGetResponse as ClassifyGetResponse, type ClassifyListResponsesPaginatedCursor as ClassifyListResponsesPaginatedCursor, type ClassifyCreateParams as ClassifyCreateParams, type ClassifyListParams as ClassifyListParams, type ClassifyGetParams as ClassifyGetParams, };
     export { Projects as Projects, type Project as Project, type ProjectListResponse as ProjectListResponse, type ProjectListParams as ProjectListParams, type ProjectGetParams as ProjectGetParams, };
     export { DataSinks as DataSinks, type DataSink as DataSink, type DataSinkListResponse as DataSinkListResponse, type DataSinkCreateParams as DataSinkCreateParams, type DataSinkUpdateParams as DataSinkUpdateParams, type DataSinkListParams as DataSinkListParams, };
     export { DataSources as DataSources, type DataSource as DataSource, type DataSourceReaderVersionMetadata as DataSourceReaderVersionMetadata, type DataSourceListResponse as DataSourceListResponse, type DataSourceCreateParams as DataSourceCreateParams, type DataSourceUpdateParams as DataSourceUpdateParams, type DataSourceListParams as DataSourceListParams, };