Overview
This node integrates with the VoyageAI service to generate text embeddings using specified models. It is designed to convert input text—either documents or queries—into vector representations that can be used for various natural language processing tasks such as semantic search, clustering, or recommendation systems.
Common scenarios where this node is beneficial include:
- Enhancing search functionality by embedding documents and queries into a vector space for similarity comparison.
- Preparing textual data for machine learning models that require numerical input.
- Analyzing and grouping large sets of text data based on semantic content.
For example, you might use this node to embed customer feedback documents to later find similar feedback entries or to embed user queries to match them against a knowledge base.
Properties
| Name | Meaning |
|---|---|
| Model | The specific embedding model to use. Default is "voyage-large-2-instruct". |
| Input Type | Specifies whether the input is a "document" or a "query" to configure embedding context. |
Output
The node outputs an object under the json field containing the generated embeddings. This output typically includes the vector representation of the input text as produced by the selected VoyageAI model.
The output is delivered through the ai_embedding output channel named "Embeddings".
No binary data output is indicated in the source code.
Dependencies
- Requires an API key credential for the VoyageAI service to authenticate requests.
- Uses the external
@langchain/community/embeddings/voyagepackage to interact with the VoyageAI embeddings API. - The node makes HTTP requests to
https://api.voyageai.com/v1.
Troubleshooting
- Authentication errors: If the API key is missing or invalid, the node will fail to connect to the VoyageAI service. Ensure a valid API key credential is configured.
- Model not found or unsupported: Using an incorrect or unsupported model name may cause errors. Verify the model name matches those supported by VoyageAI.
- Input type misconfiguration: Setting the input type incorrectly (e.g., specifying "query" when embedding documents) could affect embedding quality or cause unexpected results.
- Network issues: Since the node depends on external API calls, network connectivity problems can lead to timeouts or failures.
Links and References
- VoyageAI Official Website (for API documentation and model details)
- LangChain Community Embeddings - Voyage (source of the embedding implementation)