Embeddings Local API

Use local embedding API for generating embeddings

Overview

This node integrates with a local embedding API to generate embeddings for text data. It is useful for scenarios where you want to convert text queries or documents into vector embeddings locally, such as for semantic search, recommendation systems, or natural language processing tasks. For example, you can embed user queries or large sets of documents to enable similarity comparisons or machine learning workflows.

Use Case Examples

  1. Embedding a user query to find similar documents.
  2. Generating embeddings for a batch of documents for downstream AI processing.

Properties

Name Meaning
Base URL The base URL of your local embedding API, used to send requests for generating embeddings.
Options Additional options to customize embedding generation.

Output

JSON

  • embeddings - An array of embeddings generated by the local API for the input text or documents.

Dependencies

  • Requires a local embedding API accessible via the specified Base URL.

Troubleshooting

  • Ensure the local embedding API is running and accessible at the specified Base URL.
  • Check network connectivity and firewall settings if requests fail.
  • If the API returns errors, verify the input format and options are correct.
  • Common error: 'Local API request failed' indicates the API did not respond with a successful status code; check the API server logs for details.

Links

Discussion