Embeddings

The Embeddings API (POST /v1/embeddings) converts text into high-dimensional vectors. Use them to build your own semantic search, clustering pipelines, or similarity scoring outside of PrivateGPT’s built-in retrieval.

Single input

curl -X POST http://localhost:8080/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mxbai-embed-large",
    "input": "The quick brown fox jumps over the lazy dog."
  }'

Response:

{
  "data": [
    {"index": 0, "embedding": [0.021, -0.013, ...], "object": "embedding"}
  ],
  "model": "mxbai-embed-large",
  "usage": {"input_tokens": 12, "total_tokens": 12}
}

Batch input

Pass an array of strings to embed multiple texts in one request. The response preserves input order — data[i] corresponds to input[i]:

curl -X POST http://localhost:8080/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mxbai-embed-large",
    "input": [
      "First document text",
      "Second document text",
      "Third document text"
    ]
  }'

Choosing a model

The model field must match the name of an embedding model registered in your PrivateGPT instance. Use GET /v1/models to list available models and their types.

For consistent similarity results, always use the same model to embed both your corpus and your queries. Mixing models produces incomparable vectors.