Generate Embeddings

Component Details

v1.0.0

Basic Information

appmixer.ai.requesty.GenerateEmbeddings

Generate Embeddings

1.0.0

Public

Generates embeddings for text data using a Requesty-routed embedding model. The text is split into chunks and an embedding is returned for each chunk.
The returned embeddings is an array of the form: [{ "index": 0, "text": "chunk1", "vector": [1.1, 1.2, 1.3] }].
TIP: use the JSONata modifier to convert the embeddings array into custom formats. For convenience, the component also returns the first vector in the embeddings array which is useful when querying vector databases to find relevant chunks.

Input Ports

in

FieldTypeDescription
Text textarea Enter the text to generate embeddings for. The text will be split into chunks and embeddings will be generated for each chunk. The maximum length is 512,000 characters. If you need more than 512,000 characters, use the 'Generate Embeddings From File' component.
Model text The provider-prefixed embedding model identifier to use (for example openai/text-embedding-3-small). The list is populated from your account's available models.
Chunk Size number Maximum size of each chunk for text splitting. The default is 500.
Chunk Overlap number Overlap between chunks for text splitting to maintain context. The default is 50.

Output Ports

out

FieldTypeDescription
Embeddings -
First Vector -

Full Metadata