ragie

ragie

Summary

Table of Contents

• ragie
  • SDK Installation
  • Requirements
  • SDK Example Usage
  • Available Resources and Operations
  • File uploads
  • Error Handling
  • Server Selection
  • Custom HTTP Client
  • Authentication
  • Retries
  • Retries
  • Standalone functions
  • Pagination
  • Debugging
• Development
  • Versioning
  • Contributions

SDK Installation

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

NPM

npm add ragie

PNPM

pnpm add ragie

Bun

bun add ragie

Yarn

yarn add ragie

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": {
    "Ragie": {
      "command": "npx",
      "args": [
        "-y", "--package", "ragie",
        "--",
        "mcp", "start",
        "--api-auth", "..."
      ]
    }
  }
}

Cursor installation steps

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

{
  "mcpServers": {
    "Ragie": {
      "command": "npx",
      "args": [
        "-y", "--package", "ragie",
        "--",
        "mcp", "start",
        "--api-auth", "..."
      ]
    }
  }
}

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 ragie -- mcp start --help

Requirements

For supported JavaScript runtimes, please consult RUNTIMES.md.

SDK Example Usage

Example 1

import { openAsBlob } from "node:fs";
import { Ragie } from "ragie";

const ragie = new Ragie({
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.documents.create({
    file: await openAsBlob("example.file"),
  });

  console.log(result);
}

run();

Example 2

import { Ragie } from "ragie";

const ragie = new Ragie({
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.connections.createConnection({
    partitionStrategy: {},
    pageLimit: null,
    config: null,
    connection: {
      provider: "gcs",
      data: {
        bucket: "<value>",
        importFileMetadata: false,
      },
      credentials: {
        "key": "<value>",
        "key1": "<value>",
      },
    },
  });

  console.log(result);
}

run();

Example 3

import { Ragie } from "ragie";

const ragie = new Ragie({
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.authenticators.create({
    provider: "atlassian",
    name: "<value>",
    clientId: "<id>",
    clientSecret: "<value>",
  });

  console.log(result);
}

run();

Example 4

import { Ragie } from "ragie";

const ragie = new Ragie({
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.authenticators.createAuthenticatorConnection({
    authenticatorId: "84b0792c-1330-4854-b4f2-5d9c7bf9a385",
    createAuthenticatorConnection: {
      partitionStrategy: {},
      pageLimit: null,
      config: null,
      connection: {
        provider: "dropbox",
        data: {
          folderId: "<id>",
          folderName: "<value>",
        },
        email: "[e-mail]",
        credentials: {
          refreshToken: "<value>",
        },
      },
    },
  });

  console.log(result);
}

run();

Available Resources and Operations

Available methods

Authenticators

• create - Create Authenticator
• list - List Authenticators
• createAuthenticatorConnection - Create Authenticator Connection
• deleteAuthenticatorConnection - Delete Authenticator

Connections

• createConnection - Create Connection
• list - List Connections
• createOAuthRedirectUrl - Create Oauth Redirect Url
• listConnectionSourceTypes - List Connection Source Types
• setEnabled - Set Connection Enabled
• update - Update Connection
• get - Get Connection
• getStats - Get Connection Stats
• setLimits - Set Connection Limits
• delete - Delete Connection
• sync - Sync Connection

Documents

• create - Create Document
• list - List Documents
• createRaw - Create Document Raw
• createDocumentFromUrl - Create Document From Url
• get - Get Document
• delete - Delete Document
• updateFile - Update Document File
• updateRaw - Update Document Raw
• updateDocumentFromUrl - Update Document Url
• patchMetadata - Patch Document Metadata
• getChunks - Get Document Chunks
• getChunk - Get Document Chunk
• getChunkContent - Get Document Chunk Content
• getContent - Get Document Content
• getSource - Get Document Source
• getSummary - Get Document Summary

Entities

• listInstructions - List Instructions
• createInstruction - Create Instruction
• updateInstruction - Update Instruction
• delete - Delete Instruction
• listByInstruction - Get Instruction Extracted Entities
• listByDocument - Get Document Extracted Entities

Partitions

• list - List Partitions
• create - Create Partition
• get - Get Partition
• update - Update Partition
• delete - Delete Partition
• setLimits - Set Partition Limits

Responses

• create - Create Response
• get - Get Response

Retrievals

• retrieve - Retrieve

WebhookEndpoints

• list - List Webhook Endpoints
• create - Create Webhook Endpoint
• get - Get Webhook Endpoint
• update - Update Webhook Endpoint
• delete - Delete Webhook Endpoint

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.
• Bun: The native 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 when reading the value from an <input type="file"> element.
• Node.js v18: A file stream can be created using the fileFrom helper from fetch-blob/from.js.

import { openAsBlob } from "node:fs";
import { Ragie } from "ragie";

const ragie = new Ragie({
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.documents.create({
    file: await openAsBlob("example.file"),
  });

  console.log(result);
}

run();

Error Handling

RagieError 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

import { openAsBlob } from "node:fs";
import { Ragie } from "ragie";
import * as errors from "ragie/models/errors";

const ragie = new Ragie({
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  try {
    const result = await ragie.documents.create({
      file: await openAsBlob("example.file"),
    });

    console.log(result);
  } catch (error) {
    // The base class for HTTP error responses
    if (error instanceof errors.RagieError) {
      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.HTTPValidationError) {
        console.log(error.data$.detail); // ValidationError[]
      }
    }
  }
}

run();

Error Classes

Primary errors:

• RagieError: The base class for HTTP error responses.
  • ErrorMessage: Unauthorized.
  • HTTPValidationError: Validation Error. Status code 422. *

Less common errors (6)

Network errors:

• ConnectionError: HTTP client was unable to make a request to a server.
• RequestTimeoutError: HTTP request timed out due to an AbortSignal signal.
• RequestAbortedError: HTTP request was aborted by the client.
• InvalidRequestError: Any input used to create a request is invalid.
• UnexpectedClientError: Unrecognised or unexpected error.

Inherit from RagieError:

• 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

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 { openAsBlob } from "node:fs";
import { Ragie } from "ragie";

const ragie = new Ragie({
  serverURL: "https://api.ragie.ai",
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.documents.create({
    file: await openAsBlob("example.file"),
  });

  console.log(result);
}

run();

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 { Ragie } from "ragie";
import { HTTPClient } from "ragie/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 Ragie({ httpClient: httpClient });

Authentication

Per-Client Security Schemes

This SDK supports the following security scheme globally:

Name	Type	Scheme
auth	http	HTTP Bearer

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

import { openAsBlob } from "node:fs";
import { Ragie } from "ragie";

const ragie = new Ragie({
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.documents.create({
    file: await openAsBlob("example.file"),
  });

  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:

import { openAsBlob } from "node:fs";
import { Ragie } from "ragie";

const ragie = new Ragie({
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.documents.create({
    file: await openAsBlob("example.file"),
  }, {
    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:

import { openAsBlob } from "node:fs";
import { Ragie } from "ragie";

const ragie = new Ragie({
  retryConfig: {
    strategy: "backoff",
    backoff: {
      initialInterval: 1,
      maxInterval: 50,
      exponent: 1.1,
      maxElapsedTime: 100,
    },
    retryConnectionErrors: false,
  },
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.documents.create({
    file: await openAsBlob("example.file"),
  });

  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:

import { openAsBlob } from "node:fs";
import { Ragie } from "ragie";

const ragie = new Ragie({
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.documents.create({
    file: await openAsBlob("example.file"),
  }, {
    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:

import { openAsBlob } from "node:fs";
import { Ragie } from "ragie";

const ragie = new Ragie({
  retryConfig: {
    strategy: "backoff",
    backoff: {
      initialInterval: 1,
      maxInterval: 50,
      exponent: 1.1,
      maxElapsedTime: 100,
    },
    retryConnectionErrors: false,
  },
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.documents.create({
    file: await openAsBlob("example.file"),
  });

  console.log(result);
}

run();

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

• authenticatorsCreate - Create Authenticator
• authenticatorsCreateAuthenticatorConnection - Create Authenticator Connection
• authenticatorsDeleteAuthenticatorConnection - Delete Authenticator
• authenticatorsList - List Authenticators
• connectionsCreateConnection - Create Connection
• connectionsCreateOAuthRedirectUrl - Create Oauth Redirect Url
• connectionsDelete - Delete Connection
• connectionsGet - Get Connection
• connectionsGetStats - Get Connection Stats
• connectionsList - List Connections
• connectionsListConnectionSourceTypes - List Connection Source Types
• connectionsSetEnabled - Set Connection Enabled
• connectionsSetLimits - Set Connection Limits
• connectionsSync - Sync Connection
• connectionsUpdate - Update Connection
• documentsCreate - Create Document
• documentsCreateDocumentFromUrl - Create Document From Url
• documentsCreateRaw - Create Document Raw
• documentsDelete - Delete Document
• documentsGet - Get Document
• documentsGetChunk - Get Document Chunk
• documentsGetChunkContent - Get Document Chunk Content
• documentsGetChunks - Get Document Chunks
• documentsGetContent - Get Document Content
• documentsGetSource - Get Document Source
• documentsGetSummary - Get Document Summary
• documentsList - List Documents
• documentsPatchMetadata - Patch Document Metadata
• documentsUpdateDocumentFromUrl - Update Document Url
• documentsUpdateFile - Update Document File
• documentsUpdateRaw - Update Document Raw
• entitiesCreateInstruction - Create Instruction
• entitiesDelete - Delete Instruction
• entitiesListByDocument - Get Document Extracted Entities
• entitiesListByInstruction - Get Instruction Extracted Entities
• entitiesListInstructions - List Instructions
• entitiesUpdateInstruction - Update Instruction
• partitionsCreate - Create Partition
• partitionsDelete - Delete Partition
• partitionsGet - Get Partition
• partitionsList - List Partitions
• partitionsSetLimits - Set Partition Limits
• partitionsUpdate - Update Partition
• responsesCreate - Create Response
• responsesGet - Get Response
• retrievalsRetrieve - Retrieve
• webhookEndpointsCreate - Create Webhook Endpoint
• webhookEndpointsDelete - Delete Webhook Endpoint
• webhookEndpointsGet - Get Webhook Endpoint
• webhookEndpointsList - List Webhook Endpoints
• webhookEndpointsUpdate - Update Webhook Endpoint

Pagination

Some of the endpoints in this SDK support pagination. To use pagination, you make your SDK calls as usual, but the returned response object will also be an async iterable that can be consumed using the for await...of syntax.

Here's an example of one such pagination call:

import { Ragie } from "ragie";

const ragie = new Ragie({
  auth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await ragie.documents.list({
    filter: "{\"department\":{\"$in\":[\"sales\",\"marketing\"]}}",
    partition: "acme_customer_id",
  });

  for await (const page of result) {
    console.log(page);
  }
}

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.

import { Ragie } from "ragie";

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

Development

Versioning

This SDK follows semantic versioning.

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