Create Memory langbase.memories.create()

Create a new AI memory on Langbase using the langbase.memories.create() function.

Generate a User/Org API key

You will need to generate an API key to authenticate your requests. For more information, visit the User/Org API key documentation.

API reference

`langbase.memories.create(options)`

Function Signature

langbase.memories.create(options);

// with types.
langbase.memories.create(options: MemoryCreateOptions);

options

Name

options

Type

MemoryCreateOptions

Description

MemoryCreateOptions Object

interface MemoryCreateOptions {
	name: string;
	description?: string;
	top_k?: number;
	chunk_size?: number;
	chunk_overlap?: number;
	embedding_model?:
		| 'openai:text-embedding-3-large'
		| 'cohere:embed-multilingual-v3.0'
		| 'cohere:embed-multilingual-light-v3.0'
		| 'google:text-embedding-004';
}

Following are the properties of the options object.

Name
name
Type
string
Required
Required
Description
Name of the memory.
Name
description
Type
string
Description
Description of the memory.
Name
top_k
Type
number
Description
Number of chunks to return.
Default: 10
Minimum: 1 Maximum: 100
Name
chunk_size
Type
number
Description
Maximum number of characters in a single chunk.
Default: 10000
Maximum: 30000
Appropriate value
Cohere has a limit of 512 tokens (1 token ~= 4 characters in English). If you are using Cohere models, adjust the chunk_size accordingly. For most use cases, default values should work fine.
Name
chunk_overlap
Type
number
Description
Number of characters to overlap between chunks.
Default: 2048
Maximum: Less than chunk_size
Name
embedding_model
Type
string
Description
The model to use for text embeddings. Available options:
- openai:text-embedding-3-large
- cohere:embed-multilingual-v3.0
- cohere:embed-multilingual-light-v3.0
- google:text-embedding-004
Default: openai:text-embedding-3-large

Usage example

Install the SDK

npm i langbase

Environment variables

.env file

LANGBASE_API_KEY="<USER/ORG-API-KEY>"

Create memory

Create memory on Langbase

import {Langbase} from 'langbase';

const langbase = new Langbase({
	apiKey: process.env.LANGBASE_API_KEY!,
});

async function main() {
	const memory = await langbase.memories.create({
		name: 'knowledge-base',
		description: 'An AI memory for storing company internal docs.',
	});

	console.log('Memory created:', memory);
}

main();

Response

Name
MemoryCreateResponse
Type
object
Description
The response object returned by the langbase.memories.create() function.
MemoryCreateResponse
interface MemoryCreateResponse { name: string; description: string; owner_login: string; url: string; embedding_model: | 'openai:text-embedding-3-large' | 'cohere:embed-multilingual-v3.0' | 'cohere:embed-multilingual-light-v3.0'; chunk_size: number; chunk_overlap: number; top_k: number; }
- Name
  name
  Type
  string
  Description
  Name of the memory.
- Name
  description
  Type
  string
  Description
  Description of the AI memory.
- Name
  owner_login
  Type
  string
  Description
  Login of the memory owner.
- Name
  url
  Type
  string
  Description
  Memory access URL.
- Name
  embedding_model
  Type
  string
  Description
  The embedding model used by the AI memory.
  
  openai:text-embedding-3-large
  
  cohere:embed-multilingual-v3.0
  
  cohere:embed-multilingual-light-v3.0

Response of langbase.memories.create()

{
	"name": "knowledge-base",
	"description": "An AI memory for storing company internal docs.",
	"owner_login": "user123",
	"url": "https://langbase.com/user123/document-memory",
	"embedding_model": "openai:text-embedding-3-large",
	"chunk_size": 10000,
	"chunk_overlap": 2048,
	"top_k": 10,
}

Memory