Document: Embeddings Retry Generate v1
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.
You need to regenerate document embeddings in a memory before you can use them. The retry
document API endpoint allows you to retry generating document embeddings in a memory on Langbase with API. This endpoint requires a User or Org API key.
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.
Retry generating document embeddings in a memory
Retry generate document embeddings in a memory by sending a GET request to this endpoint.
Headers
- Name
Content-Type
- Type
- string
- Required
- Required
- Description
Request content type. Needs to be
application/json
.
- Name
Authorization
- Type
- string
- Required
- Required
- Description
Replace
<YOUR_API_KEY>
with your user/org API key.
Path Parameters
- Name
memoryName
- Type
- string
- Required
- Required
- Description
The name of memory to which the document belongs.
Replace
{memoryName}
with the name of the memory.
- Name
documentName
- Type
- string
- Required
- Required
- Description
The name of the document.
Replace
{documentName}
with the name of the document.
import {Langbase} from 'langbase';
const langbase = new Langbase({
apiKey: '<YOUR_API_KEY>', // Replace with your API key
});
await langbase.memory.documents.embedding.retry({
memoryName: 'knowledge-base',
documentName: 'technical-doc.pdf'
});
Response
- Name
Response
- Type
- object
- Description
The response object returned by the API endpoint.
Response
interface Response { success: boolean; }
- Name
success
- Type
- boolean
- Description
Indicates whether the embedding retry was successfully initiated.
API Response
{
"success": true
}