Embeddings → Create
AI-generatedOverview
This node creates embeddings from input text using a specified AI model. It is useful for converting text into numerical vector representations that can be used for tasks like semantic search, clustering, or machine learning. For example, you can embed product descriptions to enable similarity searches or analyze customer feedback by embedding sentences.
Use Case Examples
- Embedding a product description to find similar products.
- Converting customer reviews into embeddings for sentiment analysis.
Properties
| Name | Meaning |
|---|---|
| Model | The AI model used to generate embeddings from the input text. |
| Input | The text input to be converted into embeddings. |
| Additional Fields.Encoding Format | The format in which the embeddings are returned, either as floats or base64 encoded. |
Output
JSON
embeddings- Array of embedding vectors generated from the input text.model- The model used to generate the embeddings.usage- Token usage statistics for the embedding request._rawResponse- The full raw response from the embedding API.
Dependencies
- An API key credential for SiliconFlow AI service
Troubleshooting
- Ensure the input text is not empty as the node requires input to generate embeddings.
- Verify the selected model supports the input text language and token length.
- Check that the API key credential is correctly configured and has access to the SiliconFlow API.
- If the node throws errors related to response format, verify the encoding format option matches the expected output.