JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(vercel-ai-sdk): migrate to Vercel AI SDK v6 (#4741)

Browse Source 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
This commit is contained in:
Abhishek Chauhan
2026-06-10 18:41:15 +05:30
committed by GitHub
parent b819d95d18
commit b4a50e3dc8
24 changed files with 1766 additions and 1418 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/changelog/sdk.mdx
+23
View File
@@ -1489,6 +1489,29 @@ A full-featured command-line interface for Mem0, available in both Python and No
</Update>
<Update label="2026-06-10" description="Vercel AI SDK v3.0.0">
**Major Release** — Migrated to Vercel AI SDK v6 (`LanguageModelV3` / `ProviderV3`) and Mem0 v3 API.
**Breaking Changes:**
- **AI SDK v6:** Upgraded from AI SDK v5 (`LanguageModelV2`) to v6 (`LanguageModelV3`). Users must upgrade `ai` to `^6.0.199` and all `@ai-sdk/*` provider packages to `^3.x` ([#4741](https://github.com/mem0ai/mem0/pull/4741))
- **Mem0 v3 API:** Memory endpoints migrated from `/v1/memories/` and `/v2/memories/search/` to `/v3/memories/add/` and `/v3/memories/search/`. Entity IDs (`user_id`, `agent_id`, `run_id`) now go inside the `filters` object for search requests ([#4741](https://github.com/mem0ai/mem0/pull/4741))
- **Graph memory removed:** All `enable_graph`, graph prompts, and relation-extraction code removed. Graph memory is now a project-level setting on the Platform ([#4741](https://github.com/mem0ai/mem0/pull/4741))
- **Deprecated params removed:** `org_id`, `project_id`, `org_name`, `project_name`, `output_format`, `filter_memories`, `async_mode`, `enable_graph`, `version`, `api_version` removed from `Mem0ConfigSettings` ([#4741](https://github.com/mem0ai/mem0/pull/4741))
**New Features:**
- **V3 provider contract:** `specificationVersion: 'v3'`, `supportedUrls` property, V3 content array in `doGenerate`, V3 stream lifecycle events in `doStream` ([#4741](https://github.com/mem0ai/mem0/pull/4741))
- **Mem0 source in responses:** Memories are attached as a `source` in `generateText`/`streamText` responses with `providerMetadata.mem0.memories` for programmatic access ([#4741](https://github.com/mem0ai/mem0/pull/4741))
**Bug Fixes:**
- **Async memory storage:** `addMemories` is now properly `await`ed — memories no longer silently fail to store ([#4741](https://github.com/mem0ai/mem0/pull/4741))
- **Prompt mutation:** Prompt array is now cloned before injecting memory context, preventing side effects on the caller's array ([#4741](https://github.com/mem0ai/mem0/pull/4741))
- **Null guard on content:** `doGenerate` guards against null `content` from upstream providers ([#4741](https://github.com/mem0ai/mem0/pull/4741))
- **Stream response:** `doStream` now returns the full `LanguageModelV3StreamResult` object preserving all V3 fields ([#4741](https://github.com/mem0ai/mem0/pull/4741))
- **Response normalization:** `getMemories` and `retrieveMemories` now handle both array and `{results: [...]}` envelope responses from the v3 API ([#4741](https://github.com/mem0ai/mem0/pull/4741))
</Update>
<Update label="2026-06-01" description="Vercel AI SDK v2.0.6">
**Security:**
docs/integrations/vercel-ai-sdk.mdx
+151 -116
View File
@@ -6,25 +6,33 @@ description: "Use the Mem0 AI SDK Provider with Vercel AI SDK for persistent mem
The [**Mem0 AI SDK Provider**](https://www.npmjs.com/package/@mem0/vercel-ai-provider) is a library developed by **Mem0** to integrate with the Vercel AI SDK. This library brings enhanced AI interaction capabilities to your applications by introducing persistent memory functionality.
<Note type="info">
Mem0 AI SDK now supports <strong>Vercel AI SDK V5</strong>.
Mem0 AI SDK Provider v3.0.0 supports <strong>Vercel AI SDK v6</strong> (<code>LanguageModelV3</code> / <code>ProviderV3</code>). If you are upgrading from v2.x, see the <a href="https://ai-sdk.dev/docs/migration-guides/migration-guide-6-0">AI SDK v6 migration guide</a>.
</Note>
## 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
2. Enables smooth integration with the Vercel AI SDK v6
3. Ensures compatibility with multiple LLM providers (OpenAI, Anthropic, Google, Groq, Cohere)
4. Supports structured message formats for clarity
5. Facilitates streaming response capabilities
6. Attaches Mem0 memories as sources in responses for programmatic access
## Setup and Configuration
Install the SDK provider using npm:
Install the SDK provider and AI SDK:
```bash
npm install @mem0/vercel-ai-provider
npm install @mem0/vercel-ai-provider ai@^6
```
### Peer Dependencies
`@mem0/vercel-ai-provider` v3.0.0 requires:
- `ai` v6+ (`^6.0.199`)
- `@ai-sdk/provider` v3+ (`^3.0.10`)
- Provider packages at v3+: `@ai-sdk/openai@^3`, `@ai-sdk/anthropic@^3`, `@ai-sdk/google@^3`, `@ai-sdk/groq@^3`, `@ai-sdk/cohere@^3`
## Getting Started
### Setting Up Mem0
@@ -41,7 +49,7 @@ npm install @mem0/vercel-ai-provider
mem0ApiKey: "m0-xxx",
apiKey: "provider-api-key",
config: {
// Options for LLM Provider
// Options for the upstream LLM provider (e.g. baseURL)
},
// Optional Mem0 Global Config
mem0Config: {
@@ -57,154 +65,153 @@ npm install @mem0/vercel-ai-provider
3. Add Memories to Enhance Context:
```typescript
import { LanguageModelV2Prompt } from "@ai-sdk/provider";
import { addMemories } from "@mem0/vercel-ai-provider";
const messages: LanguageModelV2Prompt = [
const messages = [
{ role: "user", content: [{ type: "text", text: "I love red cars." }] },
];
await addMemories(messages, { user_id: "borat" });
```
### Standalone Features:
### Standalone Features
```typescript
await addMemories(messages, { user_id: "borat", mem0ApiKey: "m0-xxx" });
await retrieveMemories(prompt, { user_id: "borat", mem0ApiKey: "m0-xxx" });
await getMemories(prompt, { user_id: "borat", mem0ApiKey: "m0-xxx" });
```
> For standalone features, such as `addMemories`, `retrieveMemories`, and `getMemories`, you must either set `MEM0_API_KEY` as an environment variable or pass it directly in the function call.
```typescript
await addMemories(messages, { user_id: "borat", mem0ApiKey: "m0-xxx" });
await retrieveMemories(prompt, { user_id: "borat", mem0ApiKey: "m0-xxx" });
await getMemories(prompt, { user_id: "borat", mem0ApiKey: "m0-xxx" });
```
> `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.
> For standalone features, such as `addMemories`, `retrieveMemories`, and `getMemories`, you must either set `MEM0_API_KEY` as an environment variable or pass it directly in the function call.
> `getMemories` returns an array of memory objects.
> `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.
### 1. Basic Text Generation with Memory Context
```typescript
import { generateText } from "ai";
import { createMem0 } from "@mem0/vercel-ai-provider";
```typescript
import { generateText } from "ai";
import { createMem0 } from "@mem0/vercel-ai-provider";
const mem0 = createMem0();
const mem0 = createMem0();
const { text } = await generateText({
model: mem0("gpt-4-turbo", { user_id: "borat" }),
prompt: "Suggest me a good car to buy!",
});
```
const { text } = await generateText({
model: mem0("gpt-5-mini", { user_id: "borat" }),
prompt: "Suggest me a good car to buy!",
});
```
### 2. Combining OpenAI Provider with Memory Utils
```typescript
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";
import { retrieveMemories } from "@mem0/vercel-ai-provider";
```typescript
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";
import { retrieveMemories } from "@mem0/vercel-ai-provider";
const prompt = "Suggest me a good car to buy.";
const memories = await retrieveMemories(prompt, { user_id: "borat" });
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,
});
```
const { text } = await generateText({
model: openai("gpt-5-mini"),
prompt: prompt,
system: memories,
});
```
### 3. Structured Message Format with Memory
```typescript
import { generateText } from "ai";
import { createMem0 } from "@mem0/vercel-ai-provider";
```typescript
import { generateText } from "ai";
import { createMem0 } from "@mem0/vercel-ai-provider";
const mem0 = createMem0();
const mem0 = createMem0();
const { text } = await generateText({
model: mem0("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?" },
],
},
const { text } = await generateText({
model: mem0("gpt-5-mini", { 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
### 4. Streaming Responses with Memory Context
```typescript
import { streamText } from "ai";
import { createMem0 } from "@mem0/vercel-ai-provider";
```typescript
import { streamText } from "ai";
import { createMem0 } from "@mem0/vercel-ai-provider";
const mem0 = createMem0();
const mem0 = createMem0();
const { textStream } = streamText({
model: mem0("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.",
});
const { textStream } = streamText({
model: mem0("gpt-5-mini", {
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);
}
```
for await (const textPart of textStream) {
process.stdout.write(textPart);
}
```
### 4. Generate Responses with Tools Call
### 5. Generate Responses with Tools Call
```typescript
import { generateText } from "ai";
import { createMem0 } from "@mem0/vercel-ai-provider";
import { z } from "zod";
```typescript
import { generateText, tool } from "ai";
import { createMem0 } from "@mem0/vercel-ai-provider";
import { z } from "zod";
const mem0 = createMem0({
provider: "anthropic",
apiKey: "anthropic-api-key",
mem0Config: {
// Global User ID
user_id: "borat"
}
});
const mem0 = createMem0({
provider: "anthropic",
apiKey: "anthropic-api-key",
mem0Config: {
user_id: "borat"
}
});
const prompt = "What the temperature in the city that I live in?"
const result = await generateText({
model: mem0('claude-sonnet-4-20250514'),
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: "What the temperature in the city that I live in?",
});
const result = await generateText({
model: mem0('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);
```
console.log(result);
```
### 6. Get Sources from Memory
### 5. Get sources from memory
`generateText` and `streamText` responses include Mem0 memories as a source, giving you programmatic access to the memories that influenced the response:
```typescript
const { text, sources } = await generateText({
model: mem0("gpt-4-turbo"),
prompt: "Suggest me a good car to buy!",
model: mem0("gpt-5-mini", { user_id: "borat" }),
prompt: "Suggest me a good car to buy!",
});
// sources[0].title === "Mem0 Memories"
// sources[0].providerMetadata.mem0.memories — array of memory objects
console.log(sources);
```
The same can be done for `streamText` as well.
### 6. File Support with Memory Context
### 7. File Support with Memory Context
Mem0 AI SDK supports file processing with memory context. Here's an example of analyzing a PDF file:
@@ -226,15 +233,11 @@ const mem0 = createMem0({
});
async function main() {
// Read the PDF file
const filePath = join(process.cwd(), 'my_pdf.pdf');
const fileBuffer = readFileSync(filePath);
// Convert the file's arrayBuffer to a Base64 data URL
const arrayBuffer = fileBuffer.buffer.slice(fileBuffer.byteOffset, fileBuffer.byteOffset + fileBuffer.byteLength);
const uint8Array = new Uint8Array(arrayBuffer);
// Convert Uint8Array to an array of characters
const charArray = Array.from(uint8Array, byte => String.fromCharCode(byte));
const binaryString = charArray.join('');
const base64Data = Buffer.from(binaryString, 'binary').toString('base64');
@@ -274,24 +277,56 @@ main();
| Provider | Configuration Value |
|----------|-------------------|
| OpenAI | openai |
| Anthropic | anthropic |
| Google | google |
| Groq | groq |
| OpenAI | `openai` |
| Anthropic | `anthropic` |
| Google / Gemini | `google` or `gemini` |
| Groq | `groq` |
| Cohere | `cohere` |
> **Note**: You can use `google` as provider for Gemini (Google) models. They are same and internally they use `@ai-sdk/google` package.
> **Note**: You can use either `google` or `gemini` as the provider value for Google Gemini models. Both map to the `@ai-sdk/google` package internally.
## Configuration Options
### Mem0ConfigSettings
These options can be passed per-request when creating a model instance:
| Option | Type | Description |
|--------|------|-------------|
| `user_id` | `string` | User identifier for memory scoping |
| `agent_id` | `string` | Agent identifier |
| `app_id` | `string` | Application identifier |
| `run_id` | `string` | Run/session identifier |
| `metadata` | `object` | Custom metadata for memories |
| `filters` | `object` | Filters for memory search |
| `infer` | `boolean` | Enable inference-based retrieval |
| `top_k` | `number` | Number of memories to retrieve (default: 10) |
| `threshold` | `number` | Relevance threshold for search |
| `rerank` | `boolean` | Enable reranking of results |
| `page` | `number` | Page number for pagination |
| `page_size` | `number` | Results per page |
## Key Features
- `createMem0()`: Initializes a new Mem0 provider instance.
- `retrieveMemories()`: Retrieves memory context for prompts.
- `createMem0()`: Initializes a new Mem0 provider instance implementing `ProviderV3`.
- `retrieveMemories()`: Retrieves memory context for prompts as a formatted system prompt string.
- `getMemories()`: Get memories from your profile in array format.
- `addMemories()`: Adds user memories to enhance contextual responses.
## Migrating from v2.x
If you're upgrading from `@mem0/vercel-ai-provider` v2.x:
1. **Upgrade AI SDK**: `npm install ai@^6` and update all `@ai-sdk/*` provider packages to `^3.x`
2. **Remove deprecated params**: Remove `org_id`, `project_id`, `output_format`, `filter_memories`, `async_mode`, `enable_graph` from your config
3. **Remove graph memory**: All graph-related options (`enable_graph`, graph prompts) have been removed. Graph memory is now a project-level setting on the Mem0 Platform
4. **Update imports**: `LanguageModelV2Prompt` is now `LanguageModelV3Prompt` if you import types directly
## Best Practices
1. **User Identification**: Use a unique `user_id` for consistent memory retrieval.
2. **Memory Cleanup**: Regularly clean up unused memory data.
3. **Sources**: Access `result.sources` to inspect which memories influenced the response.
> **Note**: We also have support for `agent_id`, `app_id`, and `run_id`. Refer [Docs](/api-reference/memory/add-memories).