Retry Doc Embedding langbase.memory.documents.embedding.retry()
Retry the embedding process for a failed document using the langbase.memory.documents.embedding.retry()
function.
Document embeddings generation may fail due to various reasons such as OpenAI API rate limits, invalid API keys, document parsing errors, special characters, corrupted or locked PDFs, and excessively large documents. If the issue is related to the API key, it needs to be corrected; before retrying, ensure that the document is accessible and can be parsed correctly.
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.memory.documents.embedding.retry(options)
Function Signature
langbase.memory.documents.embedding.retry(options);
// with types.
langbase.memory.documents.embedding.retry(options: MemoryRetryDocEmbedOptions);
options
- Name
options
- Type
- MemoryRetryDocEmbedOptions
- Description
MemoryRetryDocEmbedOptions Object
interface MemoryRetryDocEmbedOptions { memoryName: string; documentName: string; }
Following are the properties of the options object.
- Name
memoryName
- Type
- string
- Required
- Required
- Description
The name of memory to which the document belongs.
- Name
documentName
- Type
- string
- Required
- Required
- Description
The name of the document.
Usage example
Install the SDK
npm i langbase
pnpm i langbase
yarn add langbase
Environment variables
.env file
LANGBASE_API_KEY="<USER/ORG-API-KEY>"
Retry document embedding
Retry document embedding on Langbase
import {Langbase} from 'langbase';
const langbase = new Langbase({
apiKey: process.env.LANGBASE_API_KEY!,
});
await langbase.memory.documents.embedding.retry({
memoryName: 'knowledge-base',
documentName: 'technical-doc.pdf'
});
Response
- Name
MemoryRetryDocEmbedResponse
- Type
- object
- Description
The response object returned by the
langbase.memory.documents.embedding.retry()
function.MemoryRetryDocEmbedResponse
interface MemoryRetryDocEmbedResponse { success: boolean; }
- Name
success
- Type
- boolean
- Description
Indicates whether the embedding retry was successfully initiated.
Response of langbase.memory.documents.embedding.retry()
{
"success": true
}