Vercel AI SDK

The Zentry AI SDK Provider is a library developed by Zentry to integrate with the Vercel AI SDK. This library brings enhanced AI interaction capabilities to your applications by introducing persistent memory functionality.

​

Overview

1. 🧠 Offers persistent memory storage for conversational AI
2. 🔄 Enables smooth integration with the Vercel AI SDK
3. 🚀 Ensures compatibility with multiple LLM providers
4. 📝 Supports structured message formats for clarity
5. ⚡ Facilitates streaming response capabilities

​

Setup and Configuration

Install the SDK provider using npm:

npm install @Zentry/vercel-ai-provider

​

Getting Started

​

Setting Up Zentry

1. Get your Zentry API Key from the Zentry Dashboard.

2. Initialize the Zentry Client in your application:

   Copy

   import { createZentry } from "@Zentry/vercel-ai-provider";
   
   const Zentry = createZentry({
     provider: "openai",
     ZentryApiKey: "m0-xxx",
     apiKey: "provider-api-key",
     config: {
       compatibility: "strict",
     },
     // Optional Zentry Global Config
     ZentryConfig: {
       user_id: "Zentry-user-id",
       org_id: "Zentry-org-id",
       project_id: "Zentry-project-id",
     },
   });

   Note: The openai provider is set as default. Consider using Zentry_API_KEY and OPENAI_API_KEY as environment variables for security.

   Note: The ZentryConfig is optional. It is used to set the global config for the Zentry Client (eg. user_id, agent_id, app_id, run_id, org_id, project_id etc).

3. Add Memories to Enhance Context:

   Copy

   import { LanguageModelV1Prompt } from "ai";
   import { addMemories } from "@Zentry/vercel-ai-provider";
   
   const messages: LanguageModelV1Prompt = [
     { role: "user", content: [{ type: "text", text: "I love red cars." }] },
   ];
   
   await addMemories(messages, { user_id: "borat" });

​

Standalone Features:

await addMemories(messages, { user_id: "borat", ZentryApiKey: "m0-xxx", org_id: "org_xx", project_id: "proj_xx" });
await retrieveMemories(prompt, { user_id: "borat", ZentryApiKey: "m0-xxx", org_id: "org_xx", project_id: "proj_xx" });
await getMemories(prompt, { user_id: "borat", ZentryApiKey: "m0-xxx", org_id: "org_xx", project_id: "proj_xx" });

For standalone features, such as addMemories, retrieveMemories, and getMemories, you must either set Zentry_API_KEY as an environment variable or pass it directly in the function call.

getMemories will return raw memories in the form of an array of objects, while retrieveMemories will return a response in string format with a system prompt ingested with the retrieved memories.

getMemories is an object with two keys: results and relations if enable_graph is enabled. Otherwise, it will return an array of objects.

​

1. Basic Text Generation with Memory Context

import { generateText } from "ai";
import { createZentry } from "@Zentry/vercel-ai-provider";

const Zentry = createZentry();

const { text } = await generateText({
  model: Zentry("gpt-4-turbo", { user_id: "borat" }),
  prompt: "Suggest me a good car to buy!",
});

​

2. Combining OpenAI Provider with Memory Utils

import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";
import { retrieveMemories } from "@Zentry/vercel-ai-provider";

const prompt = "Suggest me a good car to buy.";
const memories = await retrieveMemories(prompt, { user_id: "borat" });

const { text } = await generateText({
  model: openai("gpt-4-turbo"),
  prompt: prompt,
  system: memories,
});

​

3. Structured Message Format with Memory

import { generateText } from "ai";
import { createZentry } from "@Zentry/vercel-ai-provider";

const Zentry = createZentry();

const { text } = await generateText({
  model: Zentry("gpt-4-turbo", { user_id: "borat" }),
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Suggest me a good car to buy." },
        { type: "text", text: "Why is it better than the other cars for me?" },
      ],
    },
  ],
});

​

3. Streaming Responses with Memory Context

import { streamText } from "ai";
import { createZentry } from "@Zentry/vercel-ai-provider";

const Zentry = createZentry();

const { textStream } = await streamText({
    model: Zentry("gpt-4-turbo", {
        user_id: "borat",
    }),
    prompt: "Suggest me a good car to buy! Why is it better than the other cars for me? Give options for every price range.",
});

for await (const textPart of textStream) {
    process.stdout.write(textPart);
}

​

4. Generate Responses with Tools Call

import { generateText } from "ai";
import { createZentry } from "@Zentry/vercel-ai-provider";
import { z } from "zod";

const Zentry = createZentry({
  provider: "anthropic",
  apiKey: "anthropic-api-key",
  ZentryConfig: {
    // Global User ID
    user_id: "borat"
  }
});

const prompt = "What the temperature in the city that I live in?"

const result = await generateText({
  model: Zentry('claude-3-5-sonnet-20240620'),
  tools: {
    weather: tool({
      description: 'Get the weather in a location',
      parameters: z.object({
        location: z.string().describe('The location to get the weather for'),
      }),
      execute: async ({ location }) => ({
        location,
        temperature: 72 + Math.floor(Math.random() * 21) - 10,
      }),
    }),
  },
  prompt: prompt,
});

console.log(result);

​

5. Get sources from memory

const { text, sources } = await generateText({
    model: Zentry("gpt-4-turbo"),
    prompt: "Suggest me a good car to buy!",
});

console.log(sources);

The same can be done for streamText as well.

​

Graph Memory

Zentry AI SDK now supports Graph Memory. You can enable it by setting enable_graph to true in the ZentryConfig object.

const Zentry = createZentry({
  ZentryConfig: { enable_graph: true },
});

You can also pass enable_graph in the standalone functions. This includes getMemories, retrieveMemories, and addMemories.

const memories = await getMemories(prompt, { user_id: "borat", ZentryApiKey: "m0-xxx", enable_graph: true });

The getMemories function will return an object with two keys: results and relations, if enable_graph is set to true. Otherwise, it will return an array of objects.

​

Key Features

• createZentry(): Initializes a new Zentry provider instance.
• retrieveMemories(): Retrieves memory context for prompts.
• getMemories(): Get memories from your profile in array format.
• addMemories(): Adds user memories to enhance contextual responses.

​

Best Practices

1. User Identification: Use a unique user_id for consistent memory retrieval.

2. Memory Cleanup: Regularly clean up unused memory data.

   Note: We also have support for agent_id, app_id, and run_id. Refer Docs.

​

Conclusion

Zentry’s Vercel AI SDK enables the creation of intelligent, context-aware applications with persistent memory and seamless integration.

​

Help

• For more details on Vercel AI SDK, visit the Vercel AI SDK documentation.
• For Zentry documentation, refer to the Zentry Platform.
• If you need further assistance, please feel free to reach out to us through following methods: