diff options
| author | nexxeln <[email protected]> | 2025-12-14 01:19:52 +0000 |
|---|---|---|
| committer | nexxeln <[email protected]> | 2025-12-14 01:19:52 +0000 |
| commit | c42248ff350294de5d11f7cba03a819683c5247a (patch) | |
| tree | d23904b418d53e03a1508f2bcb989ea24ea52d07 | |
| parent | fix: another react vulnerability (#615) (diff) | |
| download | supermemory-mintlify/custom-github-oauth-docs-86732.tar.xz supermemory-mintlify/custom-github-oauth-docs-86732.zip | |
add the addMemory option docs (#616)mintlify/custom-github-oauth-docs-86732mintlify/custom-github-oauth-docs-8054812-13-add_the_addmemory_option_docs
| -rw-r--r-- | apps/docs/ai-sdk/overview.mdx | 15 | ||||
| -rw-r--r-- | apps/docs/ai-sdk/user-profiles.mdx | 10 |
2 files changed, 24 insertions, 1 deletions
diff --git a/apps/docs/ai-sdk/overview.mdx b/apps/docs/ai-sdk/overview.mdx index f084aba9..667ae5c7 100644 --- a/apps/docs/ai-sdk/overview.mdx +++ b/apps/docs/ai-sdk/overview.mdx @@ -26,7 +26,7 @@ import { withSupermemory } from "@supermemory/tools/ai-sdk" import { openai } from "@ai-sdk/openai" // Wrap your model with Supermemory - profiles are automatically injected -const modelWithMemory = withSupermemory(openai("gpt-4"), "user-123") +const modelWithMemory = withSupermemory(openai("gpt-5"), "user-123") const result = await generateText({ model: modelWithMemory, @@ -35,6 +35,19 @@ const result = await generateText({ // The model automatically has the user's profile context! ``` +<Note> + **Memory saving is disabled by default.** The middleware only retrieves existing memories. To automatically save new memories from conversations, enable it explicitly: + + ```typescript + const modelWithMemory = withSupermemory(openai("gpt-5"), "user-123", { + addMemory: "always" + }) + ``` +</Note> + +```typescript +``` + ## Memory Tools Add memory capabilities to AI agents with search, add, and fetch operations. diff --git a/apps/docs/ai-sdk/user-profiles.mdx b/apps/docs/ai-sdk/user-profiles.mdx index ce8f5398..68ba819a 100644 --- a/apps/docs/ai-sdk/user-profiles.mdx +++ b/apps/docs/ai-sdk/user-profiles.mdx @@ -45,6 +45,16 @@ The `withSupermemory` middleware: All of this happens transparently - you write code as if using a normal model, but get personalized responses. +<Note> + **Memory saving is disabled by default.** The middleware only retrieves existing memories. To automatically save new memories from conversations, set `addMemory: "always"`: + + ```typescript + const model = withSupermemory(openai("gpt-5"), "user-123", { + addMemory: "always" + }) + ``` +</Note> + ## Memory Search Modes Configure how the middleware retrieves and uses memory: |