Embedding Model
On this page
Purpose
Embedding Model configures an embeddings client for semantic search and retrieval. It does not receive source text directly or return raw vectors.
When to use it
- Configure embeddings for a ChromaDB retrieval workflow.
- Choose Arkus or OpenAI embeddings for a vector store.
- Tune provider batching and retry behavior.
Required setup
Arkus is the default provider and uses text-embedding-3-small. It shows no API key or base URL, because you supply neither. OpenAI requires an OpenAI API key.
How to use it
- Add Embedding Model and select a provider and model.
- Connect Embedding Model to ChromaDB.
- Connect prepared Data to the vector store for ingestion.
- Run the vector store search path.
Configuration
| Setting | What it controls | Recommended starting point |
|---|---|---|
| Model Provider | Selects Arkus or OpenAI. | Start with Arkus. |
| Model Name | Selects the model for the chosen provider. | Keep the default unless the flow needs another model. |
| OpenAI API Key | Authenticates OpenAI embeddings. Required, and shown only when Model Provider is OpenAI. | Use a saved Credential. |
| OpenAI API Base URL | Sets the OpenAI endpoint. Shown only when Model Provider is OpenAI. | Leave empty to use the default endpoint. |
| Dimensions | Requests a compatible vector size for supported models. | Leave blank unless the vector store requires a size. |
| Chunk Size | Number of text chunks in one embedding request. | Leave at 36. |
| Request Timeout | Seconds to wait for the provider to respond. | Leave empty to use the provider default. |
| Max Retries | Provider retry count. | Leave at 3. |
| Model Kwargs | Extra provider options sent with each embedding request, entered as key-value pairs. | Leave empty unless the provider documents an option you need. |
OpenAI API Base URL and every setting from Dimensions down are advanced settings.
Expected result
The component returns a configured Embeddings client. ChromaDB uses it to create and search vectors. Chunk Size batches provider requests. It does not split source documents, so use a preparation component before vector-store ingestion.
Reference details
OpenAI validates its client with a small test embedding during build. Arkus does not make that validation call.
Provider credentials and credits
Arkus embedding calls use Arkus credits based on input tokens. OpenAI uses the selected OpenAI account and bypasses Arkus embedding metering. For a deployed flow, an OpenAI key must be a saved Credential rather than a value typed into the node.
Related components
- ChromaDB requires the Embeddings client.
- Data Operations can prepare Data before it reaches a vector store.