nœuds / builtin / ai / aidependencies / embeddings
OpenAI Embeddings
Turn text into OpenAI embeddings for knowledge bases.
Ce contenu n’est pas encore disponible dans votre langue.
Turn text into vectors with OpenAI’s embedding models, so a knowledge base can find passages by meaning.
What it does
Section titled “What it does”OpenAI Embeddings plugs into the Embeddings slot of a Local Knowledge node. It does not run on its own and has no output. When the knowledge base is filled or searched, the text is sent to OpenAI with your key and comes back as vectors (lists of numbers that capture meaning).
A knowledge base remembers the embedding model it was built with and always uses it. So this node decides the model when a new, empty knowledge base is first filled. After that, connect the same node to search it, or leave the slot empty.
Your passages and questions are sent to OpenAI. For text that must stay on your device, use Local Embeddings.
When to use it
Section titled “When to use it”- A knowledge base of large or many documents where you want good search quality.
- You already use OpenAI and want one account for everything.
Most knowledge bases work well with the free, on-device Local Embeddings, which is the default.
Inputs and settings
Section titled “Inputs and settings”| Réglage | Type | Ce que cela fait |
|---|---|---|
| Model (obligatoire) | Text | The model to use. |
| Authentication (obligatoire) | Credential | Use a Bearer Token. |
Type the Model id as OpenAI names it, for example text-embedding-3-small (cheaper) or text-embedding-3-large. Don’t change it on a knowledge base that already has content: vectors from different models can’t be compared.
Outputs
Section titled “Outputs”This node has no output port. It plugs into a slot on another node instead of passing items along.
- Embeddings slot of Local Knowledge
The vectors go to the knowledge base, not to the next node.
Dependencies and credentials
Section titled “Dependencies and credentials”- Authentication (connection): required. See Connect OpenAI.
In Authentication, save your OpenAI API key. Create it on the API keys page of the OpenAI platform (platform.openai.com/api-keys). See Create a credential.
Example workflow
Section titled “Example workflow”- A Context Menu trigger on the page.
- Get All Text with Output field name
pageText. - Indexer with Input
{{ $input.pageText }}, a Recursive Character Text Splitter in its Text Splitter slot, and a Local Knowledge pointing to a new knowledge base in its Knowledge slot. - OpenAI Embeddings in the Local Knowledge’s Embeddings slot, Model
text-embedding-3-small.
Later, a RAG Agent answers questions from that knowledge base.
Common issues
Section titled “Common issues”- “Model parameter is required and cannot be empty”. Fill in Model.
- “… was built with … embeddings. Connect that embeddings node to use it.” The knowledge base was built with this cloud model. Connect OpenAI Embeddings with the same Model to its Local Knowledge.
- A “Model mismatch” warning in the run log. The knowledge base was built with another model, so this node was ignored. Disconnect it, or re-embed the knowledge base with this model from its settings.
- A 401 or 429 error. The key is wrong, or your OpenAI account has no credit or hit its rate limit.
Related nodes
Section titled “Related nodes”- Local Knowledge: the knowledge base it plugs into.
- Local Embeddings: free and on your device.
- Indexer: fill a knowledge base from a workflow.