Summary

Inkeep Search and Chat API: Leverage the Inkeep APIs to create your own AI-powered search and chat experiences built on top of your own content.

Table of Contents

• SDK Installation
• Requirements
• SDK Example Usage
• Available Resources and Operations
• Standalone functions
• Server-sent event streaming
• Retries
• Error Handling
• Server Selection
• Custom HTTP Client
• Authentication
• Debugging

SDK Installation

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

NPM

1npm add @inkeep/ai-api

PNPM

1pnpm add @inkeep/ai-api

Bun

1bun add @inkeep/ai-api

Yarn

1yarn add @inkeep/ai-api zod
2
3# Note that Yarn does not install peer dependencies automatically. You will need
4# to install zod as shown above.

Requirements

For supported JavaScript runtimes, please consult RUNTIMES.md.

SDK Example Usage

Example

1import { InkeepAI } from "@inkeep/ai-api";
2
3const inkeepAI = new InkeepAI({
4  apiKey: "<YOUR_BEARER_TOKEN_HERE>",
5});
6
7async function run() {
8  const result = await inkeepAI.chatSession.create({
9    integrationId: "<value>",
10    chatSession: {
11      messages: [
12        {
13          content: "<value>",
14        },
15      ],
16    },
17  });
18
19  if (result.chatResultStream == null) {
20    throw new Error("failed to create stream: received null value");
21  }
22
23  for await (const event of result.chatResultStream) {
24    // Handle the event
25    console.log(event);
26  }
27}
28
29run();
30

Available Resources and Operations

Available methods

chatSession

• create - Create Chat Session
• continue - Continue Chat Session

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

• chatSessionContinue
• chatSessionCreate

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.

1import { InkeepAI } from "@inkeep/ai-api";
2
3const inkeepAI = new InkeepAI({
4  apiKey: "<YOUR_BEARER_TOKEN_HERE>",
5});
6
7async function run() {
8  const result = await inkeepAI.chatSession.create({
9    integrationId: "<value>",
10    chatSession: {
11      messages: [
12        {
13          content: "<value>",
14        },
15      ],
16    },
17  });
18
19  if (result.chatResultStream == null) {
20    throw new Error("failed to create stream: received null value");
21  }
22
23  for await (const event of result.chatResultStream) {
24    // Handle the event
25    console.log(event);
26  }
27}
28
29run();
30

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:

1import { InkeepAI } from "@inkeep/ai-api";
2
3const inkeepAI = new InkeepAI({
4  apiKey: "<YOUR_BEARER_TOKEN_HERE>",
5});
6
7async function run() {
8  const result = await inkeepAI.chatSession.create({
9    integrationId: "<value>",
10    chatSession: {
11      messages: [
12        {
13          content: "<value>",
14        },
15      ],
16    },
17  }, {
18    retries: {
19      strategy: "backoff",
20      backoff: {
21        initialInterval: 1,
22        maxInterval: 50,
23        exponent: 1.1,
24        maxElapsedTime: 100,
25      },
26      retryConnectionErrors: false,
27    },
28  });
29
30  if (result.chatResultStream == null) {
31    throw new Error("failed to create stream: received null value");
32  }
33
34  for await (const event of result.chatResultStream) {
35    // Handle the event
36    console.log(event);
37  }
38}
39
40run();
41

If you'd like to override the default retry strategy for all operations that support retries, you can provide a retryConfig at SDK initialization:

1import { InkeepAI } from "@inkeep/ai-api";
2
3const inkeepAI = new InkeepAI({
4  retryConfig: {
5    strategy: "backoff",
6    backoff: {
7      initialInterval: 1,
8      maxInterval: 50,
9      exponent: 1.1,
10      maxElapsedTime: 100,
11    },
12    retryConnectionErrors: false,
13  },
14  apiKey: "<YOUR_BEARER_TOKEN_HERE>",
15});
16
17async function run() {
18  const result = await inkeepAI.chatSession.create({
19    integrationId: "<value>",
20    chatSession: {
21      messages: [
22        {
23          content: "<value>",
24        },
25      ],
26    },
27  });
28
29  if (result.chatResultStream == null) {
30    throw new Error("failed to create stream: received null value");
31  }
32
33  for await (const event of result.chatResultStream) {
34    // Handle the event
35    console.log(event);
36  }
37}
38
39run();
40

Error Handling

All SDK methods return a response object or throw an error. If Error objects are specified in your OpenAPI Spec, the SDK will throw the appropriate Error type.

Error Object	Status Code	Content Type
errors.HTTPValidationError	422	application/json
errors.SDKError	4xx-5xx	/

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 string since validation errors can list many issues and the plain error string may be difficult read when debugging.

1import { InkeepAI } from "@inkeep/ai-api";
2import {
3  HTTPValidationError,
4  SDKValidationError,
5} from "@inkeep/ai-api/models/errors";
6
7const inkeepAI = new InkeepAI({
8  apiKey: "<YOUR_BEARER_TOKEN_HERE>",
9});
10
11async function run() {
12  let result;
13  try {
14    result = await inkeepAI.chatSession.create({
15      integrationId: "<value>",
16      chatSession: {
17        messages: [
18          {
19            content: "<value>",
20          },
21        ],
22      },
23    });
24
25    if (result.chatResultStream == null) {
26      throw new Error("failed to create stream: received null value");
27    }
28
29    for await (const event of result.chatResultStream) {
30      // Handle the event
31      console.log(event);
32    }
33  } catch (err) {
34    switch (true) {
35      case (err instanceof SDKValidationError): {
36        // Validation errors can be pretty-printed
37        console.error(err.pretty());
38        // Raw value may also be inspected
39        console.error(err.rawValue);
40        return;
41      }
42      case (err instanceof HTTPValidationError): {
43        // Handle err.data$: HTTPValidationErrorData
44        console.error(err);
45        return;
46      }
47      default: {
48        throw err;
49      }
50    }
51  }
52}
53
54run();
55

Server Selection

Select Server by Index

You can override the default server globally by passing a server index to the serverIdx 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 indexes associated with the available servers:

#	Server	Variables
0	https://api.inkeep.com	None

1import { InkeepAI } from "@inkeep/ai-api";
2
3const inkeepAI = new InkeepAI({
4  serverIdx: 0,
5  apiKey: "<YOUR_BEARER_TOKEN_HERE>",
6});
7
8async function run() {
9  const result = await inkeepAI.chatSession.create({
10    integrationId: "<value>",
11    chatSession: {
12      messages: [
13        {
14          content: "<value>",
15        },
16      ],
17    },
18  });
19
20  if (result.chatResultStream == null) {
21    throw new Error("failed to create stream: received null value");
22  }
23
24  for await (const event of result.chatResultStream) {
25    // Handle the event
26    console.log(event);
27  }
28}
29
30run();
31

Override Server URL Per-Client

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

1import { InkeepAI } from "@inkeep/ai-api";
2
3const inkeepAI = new InkeepAI({
4  serverURL: "https://api.inkeep.com",
5  apiKey: "<YOUR_BEARER_TOKEN_HERE>",
6});
7
8async function run() {
9  const result = await inkeepAI.chatSession.create({
10    integrationId: "<value>",
11    chatSession: {
12      messages: [
13        {
14          content: "<value>",
15        },
16      ],
17    },
18  });
19
20  if (result.chatResultStream == null) {
21    throw new Error("failed to create stream: received null value");
22  }
23
24  for await (const event of result.chatResultStream) {
25    // Handle the event
26    console.log(event);
27  }
28}
29
30run();
31

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:

1import { InkeepAI } from "@inkeep/ai-api";
2import { HTTPClient } from "@inkeep/ai-api/lib/http";
3
4const httpClient = new HTTPClient({
5  // fetcher takes a function that has the same signature as native `fetch`.
6  fetcher: (request) => {
7    return fetch(request);
8  }
9});
10
11httpClient.addHook("beforeRequest", (request) => {
12  const nextRequest = new Request(request, {
13    signal: request.signal || AbortSignal.timeout(5000)
14  });
15
16  nextRequest.headers.set("x-custom-header", "custom value");
17
18  return nextRequest;
19});
20
21httpClient.addHook("requestError", (error, request) => {
22  console.group("Request Error");
23  console.log("Reason:", `${error}`);
24  console.log("Endpoint:", `${request.method} ${request.url}`);
25  console.groupEnd();
26});
27
28const sdk = new InkeepAI({ httpClient });

Authentication

Per-Client Security Schemes

This SDK supports the following security scheme globally:

Name	Type	Scheme
apiKey	http	HTTP Bearer

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

1import { InkeepAI } from "@inkeep/ai-api";
2
3const inkeepAI = new InkeepAI({
4  apiKey: "<YOUR_BEARER_TOKEN_HERE>",
5});
6
7async function run() {
8  const result = await inkeepAI.chatSession.create({
9    integrationId: "<value>",
10    chatSession: {
11      messages: [
12        {
13          content: "<value>",
14        },
15      ],
16    },
17  });
18
19  if (result.chatResultStream == null) {
20    throw new Error("failed to create stream: received null value");
21  }
22
23  for await (const event of result.chatResultStream) {
24    // Handle the event
25    console.log(event);
26  }
27}
28
29run();
30

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.

1import { InkeepAI } from "@inkeep/ai-api";
2
3const sdk = new InkeepAI({ debugLogger: console });

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. Feel free to open a PR or a Github issue as a proof of concept and we'll do our best to include it in a future release!

SDK Created by Speakeasy