mavenagi

Mavenagi TypeScript Library

The Mavenagi TypeScript library provides convenient access to the Mavenagi APIs from TypeScript.

Table of Contents

• Installation
• Reference
• Usage
• Aborting Requests
• Runtime Compatibility
• Request and Response Types
• Exception Handling
• Streaming Response
• Binary Response
• Advanced
  • Additional Headers
  • Additional Query String Parameters
  • Retries
  • Timeouts
  • Aborting Requests
  • Access Raw Response Data
  • Runtime Compatibility
• Contributing

Installation

npm i -s mavenagi

Reference

A full reference for this library is available here.

Usage

Instantiate and use the client with the following:

import { MavenAGIClient, MavenAGI } from "mavenagi";

const client = new MavenAGIClient({ appId: "YOUR_APP_ID", appSecret: "YOUR_APP_SECRET", organizationId: "YOUR_ORGANIZATION_ID", agentId: "YOUR_AGENT_ID" });
await client.actions.search({});

Aborting Requests

The SDK allows users to abort requests at any point by passing in an abort signal.

const controller = new AbortController();
const response = await client.initialize(..., {
    abortSignal: controller.signal
});
controller.abort(); // aborts the request

Runtime Compatibility

The SDK defaults to node-fetch but will use the global fetch client if present. The SDK works in the following runtimes:

• Node.js 18+
• Vercel
• Cloudflare Workers
• Deno v1.25+
• Bun 1.0+
• React Native

Customizing Fetch Client

The SDK provides a way for your to customize the underlying HTTP client / Fetch function. If you're running in an unsupported environment, this provides a way for you to break glass and ensure the SDK works.

import { MavenAGIClient } from "mavenagi";

const client = new MavenAGIClient({
    ...
    fetcher: // provide your implementation here
});

Request and Response Types

The SDK exports all request and response types as TypeScript interfaces. Simply import them with the following namespace:

import { MavenAGI } from "mavenagi";

const request: MavenAGI.ActionGetRequest = {
    ...
};

Exception Handling

When the API returns a non-success status code (4xx or 5xx response), a subclass of the following error will be thrown.

import { MavenAGIError } from "mavenagi";

try {
    await client.actions.search(...);
} catch (err) {
    if (err instanceof MavenAGIError) {
        console.log(err.statusCode);
        console.log(err.message);
        console.log(err.body);
        console.log(err.rawResponse);
    }
}

Streaming Response

Some endpoints return streaming responses instead of returning the full response at once. The SDK uses async iterators, so you can consume the responses using a for await...of loop.

import { MavenAGIClient } from "mavenagi";

const client = new MavenAGIClient({ appId: "YOUR_APP_ID", appSecret: "YOUR_APP_SECRET", organizationId: "YOUR_ORGANIZATION_ID", agentId: "YOUR_AGENT_ID" });
const response = await client.conversation.askStream("conversation-0", {
    conversationMessageId: {
        referenceId: "message-0"
    },
    userId: {
        referenceId: "user-0"
    },
    text: "How do I reset my password?",
    attachments: [{
            type: "image/png",
            content: "iVBORw0KGgo..."
        }],
    transientData: {
        "userToken": "abcdef123",
        "queryApiKey": "foobar456"
    },
    timezone: "America/New_York"
});
for await (const item of response) {
    console.log(item);
}

Binary Response

You can consume binary data from endpoints using the BinaryResponse type which lets you choose how to consume the data:

const response = await client.analytics.exportConversationTable(...);
const stream: ReadableStream<Uint8Array> = response.stream();
// const arrayBuffer: ArrayBuffer = await response.arrayBuffer();
// const blob: Blob = response.blob();
// const bytes: Uint8Array = response.bytes();
// You can only use the response body once, so you must choose one of the above methods.
// If you want to check if the response body has been used, you can use the following property.
const bodyUsed = response.bodyUsed;

Save binary response to a file

Node.js

ReadableStream (most-efficient)

import { createWriteStream } from 'fs';
import { Readable } from 'stream';
import { pipeline } from 'stream/promises';

const response = await client.analytics.exportConversationTable(...);

const stream = response.stream();
const nodeStream = Readable.fromWeb(stream);
const writeStream = createWriteStream('path/to/file');

await pipeline(nodeStream, writeStream);

ArrayBuffer

import { writeFile } from 'fs/promises';

const response = await client.analytics.exportConversationTable(...);

const arrayBuffer = await response.arrayBuffer();
await writeFile('path/to/file', Buffer.from(arrayBuffer));

Blob

import { writeFile } from 'fs/promises';

const response = await client.analytics.exportConversationTable(...);

const blob = await response.blob();
const arrayBuffer = await blob.arrayBuffer();
await writeFile('output.bin', Buffer.from(arrayBuffer));

Bytes (UIntArray8)

import { writeFile } from 'fs/promises';

const response = await client.analytics.exportConversationTable(...);

const bytes = await response.bytes();
await writeFile('path/to/file', bytes);

Bun

ReadableStream (most-efficient)

const response = await client.analytics.exportConversationTable(...);

const stream = response.stream();
await Bun.write('path/to/file', stream);

ArrayBuffer

const response = await client.analytics.exportConversationTable(...);

const arrayBuffer = await response.arrayBuffer();
await Bun.write('path/to/file', arrayBuffer);

Blob

const response = await client.analytics.exportConversationTable(...);

const blob = await response.blob();
await Bun.write('path/to/file', blob);

Bytes (UIntArray8)

const response = await client.analytics.exportConversationTable(...);

const bytes = await response.bytes();
await Bun.write('path/to/file', bytes);

Deno

ReadableStream (most-efficient)

const response = await client.analytics.exportConversationTable(...);

const stream = response.stream();
const file = await Deno.open('path/to/file', { write: true, create: true });
await stream.pipeTo(file.writable);

ArrayBuffer

const response = await client.analytics.exportConversationTable(...);

const arrayBuffer = await response.arrayBuffer();
await Deno.writeFile('path/to/file', new Uint8Array(arrayBuffer));

Blob

const response = await client.analytics.exportConversationTable(...);

const blob = await response.blob();
const arrayBuffer = await blob.arrayBuffer();
await Deno.writeFile('path/to/file', new Uint8Array(arrayBuffer));

Bytes (UIntArray8)

const response = await client.analytics.exportConversationTable(...);

const bytes = await response.bytes();
await Deno.writeFile('path/to/file', bytes);

Browser

Blob (most-efficient)

const response = await client.analytics.exportConversationTable(...);

const blob = await response.blob();
const url = URL.createObjectURL(blob);

// trigger download
const a = document.createElement('a');
a.href = url;
a.download = 'filename';
a.click();
URL.revokeObjectURL(url);

ReadableStream

const response = await client.analytics.exportConversationTable(...);

const stream = response.stream();
const reader = stream.getReader();
const chunks = [];

while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  chunks.push(value);
}

const blob = new Blob(chunks);
const url = URL.createObjectURL(blob);

// trigger download
const a = document.createElement('a');
a.href = url;
a.download = 'filename';
a.click();
URL.revokeObjectURL(url);

ArrayBuffer

const response = await client.analytics.exportConversationTable(...);

const arrayBuffer = await response.arrayBuffer();
const blob = new Blob([arrayBuffer]);
const url = URL.createObjectURL(blob);

// trigger download
const a = document.createElement('a');
a.href = url;
a.download = 'filename';
a.click();
URL.revokeObjectURL(url);

Bytes (UIntArray8)

const response = await client.analytics.exportConversationTable(...);

const bytes = await response.bytes();
const blob = new Blob([bytes]);
const url = URL.createObjectURL(blob);

// trigger download
const a = document.createElement('a');
a.href = url;
a.download = 'filename';
a.click();
URL.revokeObjectURL(url);

Convert binary response to text

ReadableStream

const response = await client.analytics.exportConversationTable(...);

const stream = response.stream();
const text = await new Response(stream).text();

ArrayBuffer

const response = await client.analytics.exportConversationTable(...);

const arrayBuffer = await response.arrayBuffer();
const text = new TextDecoder().decode(arrayBuffer);

Blob

const response = await client.analytics.exportConversationTable(...);

const blob = await response.blob();
const text = await blob.text();

Bytes (UIntArray8)

const response = await client.analytics.exportConversationTable(...);

const bytes = await response.bytes();
const text = new TextDecoder().decode(bytes);

Advanced

Additional Headers

If you would like to send additional headers as part of the request, use the headers request option.

const response = await client.actions.search(..., {
    headers: {
        'X-Custom-Header': 'custom value'
    }
});

Additional Query String Parameters

If you would like to send additional query string parameters as part of the request, use the queryParams request option.

const response = await client.actions.search(..., {
    queryParams: {
        'customQueryParamKey': 'custom query param value'
    }
});

Retries

The SDK is instrumented with automatic retries with exponential backoff. A request will be retried as long as the request is deemed retryable and the number of retry attempts has not grown larger than the configured retry limit (default: 2).

A request is deemed retryable when any of the following HTTP status codes is returned:

• 408 (Timeout)
• 429 (Too Many Requests)
• 5XX (Internal Server Errors)

Use the maxRetries request option to configure this behavior.

const response = await client.actions.search(..., {
    maxRetries: 0 // override maxRetries at the request level
});

Timeouts

The SDK defaults to a 60 second timeout. Use the timeoutInSeconds option to configure this behavior.

const response = await client.actions.search(..., {
    timeoutInSeconds: 30 // override timeout to 30s
});

Aborting Requests

The SDK allows users to abort requests at any point by passing in an abort signal.

const controller = new AbortController();
const response = await client.actions.search(..., {
    abortSignal: controller.signal
});
controller.abort(); // aborts the request

Access Raw Response Data

The SDK provides access to raw response data, including headers, through the .withRawResponse() method. The .withRawResponse() method returns a promise that results to an object with a data and a rawResponse property.

const { data, rawResponse } = await client.actions.search(...).withRawResponse();

console.log(data);
console.log(rawResponse.headers['X-My-Header']);

Runtime Compatibility

The SDK works in the following runtimes:

• Node.js 18+
• Vercel
• Cloudflare Workers
• Deno v1.25+
• Bun 1.0+
• React Native

Customizing Fetch Client

The SDK provides a way for you to customize the underlying HTTP client / Fetch function. If you're running in an unsupported environment, this provides a way for you to break glass and ensure the SDK works.

import { MavenAGIClient } from "mavenagi";

const client = new MavenAGIClient({
    ...
    fetcher: // provide your implementation here
});

Contributing

While we value open-source contributions to this SDK, this library is generated programmatically. Additions made directly to this library would have to be moved over to our generation code, otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept, but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!

On the other hand, contributions to the README are always very welcome!