Skip to content

Embeddings

Generate vector embeddings from input text using our embedding models.

Endpoint

POST /v1/embeddings

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID to use (e.g., `bge-m3`)
`input`	string/array	Yes	Text to embed (string or array of strings)
`encoding_format`	string	No	`float` (default) or `base64`

Example Request

Single Input

curl https://api.solidrust.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "bge-m3",
    "input": "What is semantic search?"
  }'

Batch Input

curl https://api.solidrust.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "bge-m3",
    "input": [
      "First document to embed",
      "Second document to embed",
      "Third document to embed"
    ]
  }'

Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0047, 0.0112, ...]
    }
  ],
  "model": "bge-m3",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

Embedding Dimensions

Model	Dimensions	Description
`bge-m3`	1024	Multilingual, high-quality embeddings

Use Cases

Semantic Search - Find similar documents by meaning
RAG Applications - Retrieve relevant context for LLM prompts
Clustering - Group related content together
Classification - Use embeddings as features for ML models

Best Practices

RAG Guide - Building retrieval-augmented generation systems
Document Q&A Example - Complete RAG implementation