@samchon/openapi

1flowchart
2  subgraph "OpenAPI Specification"
3    v20("Swagger v2.0") --upgrades--> emended[["OpenAPI v3.1 (emended)"]]
4    v30("OpenAPI v3.0") --upgrades--> emended
5    v31("OpenAPI v3.1") --emends--> emended
6  end
7  subgraph "OpenAPI Generator"
8    emended --normalizes--> migration[["Migration Schema"]]
9    migration --"Artificial Intelligence"--> lfc{{"LLM Function Calling"}}
10    lfc --"OpenAI"--> chatgpt("ChatGPT")
11    lfc --"Google"--> gemini("Gemini")
12    lfc --"Anthropic"--> claude("Claude")
13    lfc --"High-Flyer"--> deepseek("DeepSeek")
14    lfc --"Meta"--> llama("Llama")
15    chatgpt --"3.1"--> custom(["Custom JSON Schema"])
16    gemini --"3.0"--> custom(["Custom JSON Schema"])
17    claude --"3.1"--> standard(["Standard JSON Schema"])
18    deepseek --"3.1"--> standard
19    llama --"3.1"--> standard
20  end

OpenAPI definitions, converters and LLM function calling application composer.

@samchon/openapi is a collection of OpenAPI types for every versions, and converters for them. In the OpenAPI types, there is an "emended" OpenAPI v3.1 specification, which has removed ambiguous and duplicated expressions for the clarity. Every conversions are based on the emended OpenAPI v3.1 specification.

1. Swagger v2.0
2. OpenAPI v3.0
3. OpenAPI v3.1
4. OpenAPI v3.1 emended

@samchon/openapi also provides LLM (Large Language Model) function calling application composer from the OpenAPI document with many strategies. With the HttpLlm module, you can perform the LLM function calling extremely easily just by delivering the OpenAPI (Swagger) document.

• HttpLlm.application()
• IHttpLlmApplication<Model>
• IHttpLlmFunction<Model>
• Supported schemas
  • IChatGptSchema: OpenAI ChatGPT
  • IClaudeSchema: Anthropic Claude
  • IDeepSeekSchema: High-Flyer DeepSeek
  • IGeminiSchema: Google Gemini
  • ILlamaSchema: Meta Llama
• Midldle layer schemas
  • ILlmSchemaV3: middle layer based on OpenAPI v3.0 specification
  • ILlmSchemaV3_1: middle layer based on OpenAPI v3.1 specification

Additionally, @samchon/openapi supports MCP (Model Context Protocol) function calling. Due to model specification, validation feedback, and selector agent reasons, function calling to MCP server is much better than directly using mcp_servers property of LLM API.

• McpLlm.application()
• IMcpLlmApplication
• IMcpLlmFunction

https://github.com/user-attachments/assets/e1faf30b-c703-4451-b68b-2e7a8170bce5

Demonstration video composing A.I. chatbot with @samchon/openapi and @agentica

• Shopping A.I. Chatbot Application: https://nestia.io/chat/shopping
• Shopping Backend Repository: https://github.com/samchon/shopping-backend
• Shopping Swagger Document (@nestia/editor): https://nestia.io/editor/?url=...

Setup

1npm install @samchon/openapi

Just install by npm i @samchon/openapi command.

Here is an example code utilizing the @samchon/openapi for LLM function calling purpose.

1import {
2  HttpLlm,
3  IChatGptSchema,
4  IHttpLlmApplication,
5  IHttpLlmFunction,
6  OpenApi,
7  OpenApiV3,
8  OpenApiV3_1,
9  SwaggerV2,
10} from "@samchon/openapi";
11import fs from "fs";
12import typia from "typia";
13
14const main = async (): Promise<void> => {
15  // read swagger document and validate it
16  const swagger:
17    | SwaggerV2.IDocument
18    | OpenApiV3.IDocument
19    | OpenApiV3_1.IDocument = JSON.parse(
20    await fs.promises.readFile("swagger.json", "utf8"),
21  );
22  typia.assert(swagger); // recommended
23
24  // convert to emended OpenAPI document,
25  // and compose LLM function calling application
26  const document: OpenApi.IDocument = OpenApi.convert(swagger);
27  const application: IHttpLlmApplication<"chatgpt"> = HttpLlm.application({
28    model: "chatgpt",
29    document,
30  });
31
32  // Let's imagine that LLM has selected a function to call
33  const func: IHttpLlmFunction<"chatgpt"> | undefined = 
34    application.functions.find(
35      // (f) => f.name === "llm_selected_function_name"
36      (f) => f.path === "/bbs/articles" && f.method === "post",
37    );
38  if (func === undefined) throw new Error("No matched function exists.");
39
40  // actual execution is by yourself
41  const article = await HttpLlm.execute({
42    connection: {
43      host: "http://localhost:3000",
44    },
45    application,
46    function: func,
47    arguments: {
48      // arguments composed by LLM 
49      body: {
50        title: "Hello, world!",
51        body: "Let's imagine that this argument is composed by LLM.",
52        thumbnail: null,
53      },
54    },
55  });
56  console.log("article", article);
57};
58main().catch(console.error);

OpenAPI Definitions

1flowchart
2  v20(Swagger v2.0) --upgrades--> emended[["<b><u>OpenAPI v3.1 (emended)</u></b>"]]
3  v30(OpenAPI v3.0) --upgrades--> emended
4  v31(OpenAPI v3.1) --emends--> emended
5  emended --downgrades--> v20d(Swagger v2.0)
6  emended --downgrades--> v30d(Swagger v3.0)

@samchon/openapi support every versions of OpenAPI specifications with detailed TypeScript types.

• Swagger v2.0
• OpenAPI v3.0
• OpenAPI v3.1
• OpenAPI v3.1 emended

Also, @samchon/openapi provides "emended OpenAPI v3.1 definition" which has removed ambiguous and duplicated expressions for clarity. It has emended original OpenAPI v3.1 specification like above. You can compose the "emended OpenAPI v3.1 document" by calling the OpenApi.convert() function.

• Operation
  • Merge OpenApiV3_1.IPathItem.parameters to OpenApi.IOperation.parameters
  • Resolve references of OpenApiV3_1.IOperation members
  • Escape references of OpenApiV3_1.IComponents.examples
• JSON Schema
  • Decompose mixed type: OpenApiV3_1.IJsonSchema.IMixed
  • Resolve nullable property: OpenApiV3_1.IJsonSchema.__ISignificant.nullable
  • Array type utilizes only single OpenAPI.IJsonSchema.IArray.items
  • Tuple type utilizes only OpenApi.IJsonSchema.ITuple.prefixItems
  • Merge OpenApiV3_1.IJsonSchema.IAnyOf to OpenApi.IJsonSchema.IOneOf
  • Merge OpenApiV3_1.IJsonSchema.IRecursiveReference to OpenApi.IJsonSchema.IReference
  • Merge OpenApiV3_1.IJsonSchema.IAllOf to OpenApi.IJsonSchema.IObject

Conversions to another version's OpenAPI document is also based on the "emended OpenAPI v3.1 specification" like above diagram. You can do it through OpenApi.downgrade() function. Therefore, if you want to convert Swagger v2.0 document to OpenAPI v3.0 document, you have to call two functions; OpenApi.convert() and then OpenApi.downgrade().

At last, if you utilize typia library with @samchon/openapi types, you can validate whether your OpenAPI document is following the standard specification or not. Just visit one of below playground links, and paste your OpenAPI document URL address. This validation strategy would be superior than any other OpenAPI validator libraries.

• Playground Links
  • 💻 Type assertion
  • 💻 Detailed validation

1import { OpenApi, OpenApiV3, OpenApiV3_1, SwaggerV2 } from "@samchon/openapi";
2import typia from "typia";
3 
4const main = async (): Promise<void> => {
5  // GET YOUR OPENAPI DOCUMENT
6  const response: Response = await fetch(
7    "https://raw.githubusercontent.com/samchon/openapi/master/examples/v3.0/openai.json"
8  );
9  const document: any = await response.json();
10 
11  // TYPE VALIDATION
12  const result = typia.validate<
13    | OpenApiV3_1.IDocument
14    | OpenApiV3.IDocument
15    | SwaggerV2.IDocument
16  >(document);
17  if (result.success === false) {
18    console.error(result.errors);
19    return;
20  }
21 
22  // CONVERT TO EMENDED
23  const emended: OpenApi.IDocument = OpenApi.convert(document);
24  console.info(emended);
25};
26main().catch(console.error);

LLM Function Calling

Preface

1flowchart
2  subgraph "OpenAPI Specification"
3    v20("Swagger v2.0") --upgrades--> emended[["OpenAPI v3.1 (emended)"]]
4    v30("OpenAPI v3.0") --upgrades--> emended
5    v31("OpenAPI v3.1") --emends--> emended
6  end
7  subgraph "OpenAPI Generator"
8    emended --normalizes--> migration[["Migration Schema"]]
9    migration --"Artificial Intelligence"--> lfc{{"<b><u>LLM Function Calling</u></b>"}}
10    lfc --"OpenAI"--> chatgpt("ChatGPT")
11    lfc --"Google"--> gemini("Gemini")
12    lfc --"Anthropic"--> claude("Claude")
13    lfc --"High-Flyer"--> deepseek("DeepSeek")
14    lfc --"Meta"--> llama("Llama")
15    chatgpt --"3.1"--> custom(["Custom JSON Schema"])
16    gemini --"3.0"--> custom(["Custom JSON Schema"])
17    claude --"3.1"--> standard(["Standard JSON Schema"])
18    deepseek --"3.1"--> standard
19    llama --"3.1"--> standard
20  end

LLM function calling application from OpenAPI document.

@samchon/openapi provides LLM (Large Language Model) function calling application from the "emended OpenAPI v3.1 document". Therefore, if you have any HTTP backend server and succeeded to build an OpenAPI document, you can easily make the A.I. chatbot application.

In the A.I. chatbot, LLM will select proper function to remotely call from the conversations with user, and fill arguments of the function automatically. If you actually execute the function call through the HttpLlm.execute() function, it is the "LLM function call."

Let's enjoy the fantastic LLM function calling feature very easily with @samchon/openapi.

• Application
  • HttpLlm.application()
  • IHttpLlmApplication
  • IHttpLlmFunction
• Schemas
  • IChatGptSchema: OpenAI ChatGPT
  • IClaudeSchema: Anthropic Claude
  • IDeepSeekSchema: High-Flyer DeepSeek
  • IGeminiSchema: Google Gemini
  • ILlamaSchema: Meta Llama
  • ILlmSchemaV3: middle layer based on OpenAPI v3.0 specification
  • ILlmSchemaV3_1: middle layer based on OpenAPI v3.1 specification
• Type Checkers
  • ChatGptTypeChecker
  • ClaudeTypeChecker
  • GeminiTypeChecker
  • LlamaTypeChecker
  • LlmTypeCheckerV3
  • LlmTypeCheckerV3_1

[!NOTE]

You also can compose ILlmApplication from a class type with typia.

https://typia.io/docs/llm/application

1import { ILlmApplication } from "@samchon/openapi";
2import typia from "typia";
3
4const app: ILlmApplication<"chatgpt"> =
5  typia.llm.application<YourClassType, "chatgpt">();

[!TIP]

LLM selects proper function and fill arguments.

In nowadays, most LLM (Large Language Model) like OpenAI are supporting "function calling" feature. The "LLM function calling" means that LLM automatically selects a proper function and fills parameter values from conversation with the user (may by chatting text).

https://platform.openai.com/docs/guides/function-calling

Execution

Actual function call execution is by yourself.

LLM (Large Language Model) providers like OpenAI selects a proper function to call from the conversations with users, and fill arguments of it. However, function calling feature supported by LLM providers do not perform the function call execution. The actual execution responsibility is on you.

In @samchon/openapi, you can execute the LLM function calling by HttpLlm.execute() (or HttpLlm.propagate()) function. Here is an example code executing the LLM function calling through the HttpLlm.execute() function. As you can see, to execute the LLM function call, you have to deliver these information:

• Connection info to the HTTP server
• Application of the LLM function calling
• LLM function schema to call
• Arguments for the function call (maybe composed by LLM)

Here is the example code executing the LLM function call with @samchon/openapi.

• Example Code: test/examples/chatgpt-function-call-to-sale-create.ts
• Prompt describing the produc to create: Microsoft Surface Pro 9
• Result of the Function Calling: examples/arguments/chatgpt.microsoft-surface-pro-9.input.json

1import {
2  HttpLlm,
3  IChatGptSchema,
4  IHttpLlmApplication,
5  IHttpLlmFunction,
6  OpenApi,
7  OpenApiV3,
8  OpenApiV3_1,
9  SwaggerV2,
10} from "@samchon/openapi";
11import OpenAI from "openai";
12import typia from "typia";
13
14const main = async (): Promise<void> => {
15  // Read swagger document and validate it
16  const swagger:
17    | SwaggerV2.IDocument
18    | OpenApiV3.IDocument
19    | OpenApiV3_1.IDocument = JSON.parse(
20    await fetch(
21      "https://github.com/samchon/shopping-backend/blob/master/packages/api/swagger.json",
22    ).then((r) => r.json()),
23  );
24  typia.assert(swagger); // recommended
25
26  // convert to emended OpenAPI document,
27  // and compose LLM function calling application
28  const document: OpenApi.IDocument = OpenApi.convert(swagger);
29  const application: IHttpLlmApplication<"chatgpt"> = HttpLlm.application({
30    model: "chatgpt",
31    document,
32  });
33
34  // Let's imagine that LLM has selected a function to call
35  const func: IHttpLlmFunction<"chatgpt"> | undefined =
36    application.functions.find(
37      // (f) => f.name === "llm_selected_function_name"
38      (f) => f.path === "/shoppings/sellers/sale" && f.method === "post",
39    );
40  if (func === undefined) throw new Error("No matched function exists.");
41
42  // Get arguments by ChatGPT function calling
43  const client: OpenAI = new OpenAI({
44    apiKey: "<YOUR_OPENAI_API_KEY>",
45  });
46  const completion: OpenAI.ChatCompletion =
47    await client.chat.completions.create({
48      model: "gpt-4o",
49      messages: [
50        {
51          role: "assistant",
52          content:
53            "You are a helpful customer support assistant. Use the supplied tools to assist the user.",
54        },
55        {
56          role: "user",
57          content: "<DESCRIPTION ABOUT THE SALE>",
58          // https://github.com/samchon/openapi/blob/master/examples/function-calling/prompts/microsoft-surface-pro-9.md
59        },
60      ],
61      tools: [
62        {
63          type: "function",
64          function: {
65            name: func.name,
66            description: func.description,
67            parameters: func.parameters as Record<string, any>,
68          },
69        },
70      ],
71    });
72  const toolCall: OpenAI.ChatCompletionMessageToolCall =
73    completion.choices[0].message.tool_calls![0];
74
75  // Actual execution by yourself
76  const article = await HttpLlm.execute({
77    connection: {
78      host: "http://localhost:37001",
79    },
80    application,
81    function: func,
82    input: JSON.parse(toolCall.function.arguments),
83  });
84  console.log("article", article);
85};
86main().catch(console.error);

Validation Feedback

1import { IHttpLlmFunction, IValidation } from "@samchon/openapi";
2import { FunctionCall } from "pseudo";
3
4export const correctFunctionCall = (p: {
5  call: FunctionCall;
6  functions: Array<IHttpLlmFunction<"chatgpt">>;
7  retry: (reason: string, errors?: IValidation.IError[]) => Promise<unknown>;
8}): Promise<unknown> => {
9  // FIND FUNCTION
10  const func: IHttpLlmFunction<"chatgpt"> | undefined =
11    p.functions.find((f) => f.name === p.call.name);
12  if (func === undefined) {
13    // never happened in my experience
14    return p.retry(
15      "Unable to find the matched function name. Try it again.",
16    );
17  }
18
19  // VALIDATE
20  const result: IValidation<unknown> = func.validate(p.call.arguments);
21  if (result.success === false) {
22    // 1st trial: 70% (gpt-4o-mini in shopping mall chatbot)
23    // 2nd trial with validation feedback: 98%
24    // 3rd trial with validation feedback again: never have failed
25    return p.retry(
26      "Type errors are detected. Correct it through validation errors",
27      {
28        errors: result.errors,
29      },
30    );
31  }
32  return result.data;
33}

Is LLM Function Calling perfect? No, absolutely not.

LLM (Large Language Model) service vendor like OpenAI takes a lot of type level mistakes when composing the arguments of function calling or structured output. Even though target schema is super simple like Array<string> type, LLM often fills it just by a string typed value.

In my experience, OpenAI gpt-4o-mini (8b parameters) is taking about 70% of type level mistakes when filling the arguments of function calling to Shopping Mall service. To overcome the imperfection of such LLM function calling, @samchon/openapi supports validation feedback strategy.

The key concept of validation feedback strategy is, let LLM function calling to construct invalid typed arguments first, and informing detailed type errors to the LLM, so that induce LLM to emend the wrong typed arguments at the next turn by using IHttpLlmFunction<Model>.validate() function.

Embedded validator function in IHttpLlmFunction<Model>.validate() is exactly the same as typia.validate<T>() and is more detailed and accurate than other validators. By using this validation feedback strategy, the 70% success rate of the first function calling trial increased to 98% on the second trial and has never failed from the third trial onward.

Components	typia	TypeBox	ajv	io-ts	zod	C.V.
Easy to use	✅	❌	❌	❌	❌	❌
Object (simple)	✔	✔	✔	✔	✔	✔
Object (hierarchical)	✔	✔	✔	✔	✔	✔
Object (recursive)	✔	❌	✔	✔	✔	✔
Object (union, implicit)	✅	❌	❌	❌	❌	❌
Object (union, explicit)	✔	✔	✔	✔	✔	❌
Object (additional tags)	✔	✔	✔	✔	✔	✔
Object (template literal types)	✔	✔	✔	❌	❌	❌
Object (dynamic properties)	✔	✔	✔	❌	❌	❌
Array (rest tuple)	✅	❌	❌	❌	❌	❌
Array (hierarchical)	✔	✔	✔	✔	✔	✔
Array (recursive)	✔	✔	✔	✔	✔	❌
Array (recursive, union)	✔	✔	❌	✔	✔	❌
Array (R+U, implicit)	✅	❌	❌	❌	❌	❌
Array (repeated)	✅	❌	❌	❌	❌	❌
Array (repeated, union)	✅	❌	❌	❌	❌	❌
Ultimate Union Type	✅	❌	❌	❌	❌	❌

C.V. means class-validator

Separation

Arguments from both Human and LLM sides.

When composing parameter arguments through the LLM (Large Language Model) function calling, there can be a case that some parameters (or nested properties) must be composed not by LLM, but by Human. File uploading feature, or sensitive information like secret key (password) cases are the representative examples.

In that case, you can configure the LLM function calling schemas to exclude such Human side parameters (or nested properties) by IHttpLlmApplication.options.separate property. Instead, you have to merge both Human and LLM composed parameters into one by calling the HttpLlm.mergeParameters() before the LLM function call execution of HttpLlm.execute() function.

Here is the example code separating the file uploading feature from the LLM function calling schema, and combining both Human and LLM composed parameters into one before the LLM function call execution.

• Example Code: test/examples/claude-function-call-separate-to-sale-create.ts
• Prompt describing the produc to create: Microsoft Surpace Pro 9
• Result of the Function Calling: examples/arguments/claude.microsoft-surface-pro-9.input.json

1import Anthropic from "@anthropic-ai/sdk";
2import {
3  ClaudeTypeChecker,
4  HttpLlm,
5  IClaudeSchema,
6  IHttpLlmApplication,
7  IHttpLlmFunction,
8  OpenApi,
9  OpenApiV3,
10  OpenApiV3_1,
11  SwaggerV2,
12} from "@samchon/openapi";
13import typia from "typia";
14
15const main = async (): Promise<void> => {
16  // Read swagger document and validate it
17  const swagger:
18    | SwaggerV2.IDocument
19    | OpenApiV3.IDocument
20    | OpenApiV3_1.IDocument = JSON.parse(
21    await fetch(
22      "https://github.com/samchon/shopping-backend/blob/master/packages/api/swagger.json",
23    ).then((r) => r.json()),
24  );
25  typia.assert(swagger); // recommended
26
27  // convert to emended OpenAPI document,
28  // and compose LLM function calling application
29  const document: OpenApi.IDocument = OpenApi.convert(swagger);
30  const application: IHttpLlmApplication<"claude"> = HttpLlm.application({
31    model: "claude",
32    document,
33    options: {
34      reference: true,
35      separate: (schema) =>
36        ClaudeTypeChecker.isString(schema) &&
37        !!schema.contentMediaType?.startsWith("image"),
38    },
39  });
40
41  // Let's imagine that LLM has selected a function to call
42  const func: IHttpLlmFunction<"claude"> | undefined =
43    application.functions.find(
44      // (f) => f.name === "llm_selected_function_name"
45      (f) => f.path === "/shoppings/sellers/sale" && f.method === "post",
46    );
47  if (func === undefined) throw new Error("No matched function exists.");
48
49  // Get arguments by ChatGPT function calling
50  const client: Anthropic = new Anthropic({
51    apiKey: "<YOUR_ANTHROPIC_API_KEY>",
52  });
53  const completion: Anthropic.Message = await client.messages.create({
54    model: "claude-3-5-sonnet-latest",
55    max_tokens: 8_192,
56    messages: [
57      {
58        role: "assistant",
59        content:
60          "You are a helpful customer support assistant. Use the supplied tools to assist the user.",
61      },
62      {
63        role: "user",
64        content: "<DESCRIPTION ABOUT THE SALE>",
65        // https://github.com/samchon/openapi/blob/master/examples/function-calling/prompts/microsoft-surface-pro-9.md
66      },
67    ],
68    tools: [
69      {
70        name: func.name,
71        description: func.description,
72        input_schema: func.separated!.llm as any,
73      },
74    ],
75  });
76  const toolCall: Anthropic.ToolUseBlock = completion.content.filter(
77    (c) => c.type === "tool_use",
78  )[0]!;
79
80  // Actual execution by yourself
81  const article = await HttpLlm.execute({
82    connection: {
83      host: "http://localhost:37001",
84    },
85    application,
86    function: func,
87    input: HttpLlm.mergeParameters({
88      function: func,
89      llm: toolCall.input as any,
90      human: {
91        // Human composed parameter values
92        content: {
93          files: [],
94          thumbnails: [
95            {
96              name: "thumbnail",
97              extension: "jpeg",
98              url: "https://serpapi.com/searches/673d3a37e45f3316ecd8ab3e/images/1be25e6e2b1fb7509f1af89c326cb41749301b94375eb5680b9bddcdf88fabcb.jpeg",
99            },
100            // ...
101          ],
102        },
103      },
104    }),
105  });
106  console.log("article", article);
107};
108main().catch(console.error);

Model Context Protocol

1flowchart
2  subgraph "JSON Schema Specification"
3    schemav4("JSON Schema v4 ~ v7") --upgrades--> emended[["OpenAPI v3.1 (emended)"]]
4    schema2910("JSON Schema 2019-03") --upgrades--> emended
5    schema2020("JSON Schema 2020-12") --emends--> emended
6  end
7  subgraph "Model Context Protocol"
8    emended --"Artificial Intelligence"--> lfc{{"LLM Function Calling"}}
9    lfc --"OpenAI"--> chatgpt("ChatGPT")
10    lfc --"Google"--> gemini("Gemini")
11    lfc --"Anthropic"--> claude("Claude")
12    lfc --"High-Flyer"--> deepseek("DeepSeek")
13    lfc --"Meta"--> llama("Llama")
14    chatgpt --"3.1"--> custom(["Custom JSON Schema"])
15    gemini --"3.0"--> custom(["Custom JSON Schema"])
16    claude --"3.1"--> standard(["Standard JSON Schema"])
17    deepseek --"3.1"--> standard
18    llama --"3.1"--> standard
19  end

LLM function calling schema from MCP document.

As MCP (Model Context Protocol) contains function caller itself, it is possible to execute MCP server's functions without any extra dedication just by using mcp_servers property of LLM API. However, due to JSON schema model specification, validation feedback and selector agent's filtering for context reducing, @samchon/openapi recommends to use function calling instead of using the mcp_servers.

For example, if you bring a GitHub MCP server to Claude Desktop and request it to do something, you will often see the AI ​​agent crash immediately. This is because there are 30 functions in the GitHub MCP server, and if you put them all by using mcp_servers, the context will be huge and hallucination will occur.

https://github.com/user-attachments/assets/72390cb4-d9b1-4d31-a6dd-d866da5a433b

GitHub MCP server to mcp_servers often breaks down AI agent.

However, if call the function of GitHub MCP server by function calling with @agentica, it works properly without any problem.

• Function calling to GitHub MCP: https://www.youtube.com/watch?v=rLlHkc24cJs

To make function calling schemas, call McpLlm.application() function. IMcpLlmApplication typed application instance would be returned, and it will contain the IMcpLlmFunction.validate() function utilized for the validation feedback strategy.

Don't worry about the JSON schema specification. As MCP (Model Context Protocol) does not restrict any JSON schema specification, the McpLlm.application() function has been designed to support every JSON schema specifications.

• JSON Schema v4, v5, v6, v7
• JSON Schema 2019-03
• JSON Schema 2020-12

1import {
2  IMcpApplication,
3  IMcpFunction,
4  IValidation,
5  McpLlm,
6} from "@samchon/openapi";
7
8const application: IMcpLlmApplication<"chatgpt"> = McpLlm.application({
9  model: "chatgpt",
10  tools: [...],
11});
12const func: IMcpLlmFunction<"chatgpt"> = application.functions.find(
13  (f) => f.name === "create",
14);
15const result: IValidation<unknown> = func.validate({
16  title: "Hello World",
17  body: "Nice to meet you AI developers",
18  thumbnail: "https://wrtnlabs.io/agentica/thumbnail.jpg",
19});
20console.log(result);

Agentica

https://github.com/wrtnlabs/agentica

Agentic AI framework specialized in AI Function Calling using @samchon/openapi.

Don't be afraid of AI agent development. Just list functions from three protocols below. This is everything you should do for AI agent development.

• TypeScript Class
• Swagger/OpenAPI Document
• MCP (Model Context Protocol) Server

Wanna make an e-commerce agent? Bring in e-commerce functions. Need a newspaper agent? Get API functions from the newspaper company. Just prepare any functions that you need, then it becomes an AI agent.

Are you a TypeScript developer? Then you're already an AI developer. Familiar with backend development? You're already well-versed in AI development. Anyone who can make functions can make AI agents.

1import { Agentica, assertHttpController } from "@agentica/core";
2import OpenAI from "openai";
3import typia from "typia";
4
5import { MobileFileSystem } from "./services/MobileFileSystem";
6
7const agent = new Agentica({
8  vendor: {
9    api: new OpenAI({ apiKey: "********" }),
10    model: "gpt-4o-mini",
11  },
12  controllers: [
13    // functions from TypeScript class
14    typia.llm.controller<MobileFileSystem, "chatgpt">(
15      "filesystem",
16      new MobileFileSystem(),
17    ),
18    // functions from Swagger/OpenAPI
19    assertHttpController({
20      name: "shopping",
21      model: "chatgpt",
22      document: await fetch(
23        "https://shopping-be.wrtn.ai/editor/swagger.json",
24      ).then(r => r.json()),
25      connection: {
26        host: "https://shopping-be.wrtn.ai",
27        headers: { Authorization: "Bearer ********" },
28      },
29    }),
30  ],
31});
32await agent.conversate("I wanna buy MacBook Pro");