๐Ÿง  Embeddings

LocalAI supports generating embeddings for text or list of tokens.

For the API documentation you can refer to the OpenAI docs: https://platform.openai.com/docs/api-reference/embeddings

Model compatibility

The embedding endpoint is compatible with llama.cpp models, bert.cpp models and sentence-transformers models available in huggingface.

Manual Setup

Create a YAML config file in the models directory. Specify the backend and the model file.

name: text-embedding-ada-002 # The model name used in the API
  model: <model_file>
backend: "<backend>"
embeddings: true
# .. other parameters

Bert embeddings

To use bert.cpp models you can use the bert embedding backend.

An example model config file:

name: text-embedding-ada-002
  model: bert
backend: bert-embeddings
embeddings: true
# .. other parameters

The bert backend uses bert.cpp and uses ggml models.

For instance you can download the ggml quantized version of all-MiniLM-L6-v2 from https://huggingface.co/skeskinen/ggml:

wget https://huggingface.co/skeskinen/ggml/resolve/main/all-MiniLM-L6-v2/ggml-model-q4_0.bin -O models/bert

To test locally (LocalAI server running on localhost), you can use curl (and jq at the end to prettify):

curl http://localhost:8080/embeddings -X POST -H "Content-Type: application/json" -d '{
  "input": "Your text string goes here",
  "model": "text-embedding-ada-002"
}' | jq "."

Huggingface embeddings

To use sentence-transformers and models in huggingface you can use the sentencetransformers embedding backend.

name: text-embedding-ada-002
backend: sentencetransformers
embeddings: true
  model: all-MiniLM-L6-v2

The sentencetransformers backend uses Python sentence-transformers. For a list of all pre-trained models available see here: https://github.com/UKPLab/sentence-transformers#pre-trained-models

  • The sentencetransformers backend is an optional backend of LocalAI and uses Python. If you are running LocalAI from the containers you are good to go and should be already configured for use.
  • If you are running LocalAI manually you must install the python dependencies (make prepare-extra-conda-environments). This requires conda to be installed.
  • For local execution, you also have to specify the extra backend in the EXTERNAL_GRPC_BACKENDS environment variable.
    • Example: EXTERNAL_GRPC_BACKENDS="sentencetransformers:/path/to/LocalAI/backend/python/sentencetransformers/sentencetransformers.py"
  • The sentencetransformers backend does support only embeddings of text, and not of tokens. If you need to embed tokens you can use the bert backend or llama.cpp.
  • No models are required to be downloaded before using the sentencetransformers backend. The models will be downloaded automatically the first time the API is used.

Llama.cpp embeddings

Embeddings with llama.cpp are supported with the llama backend.

name: my-awesome-model
backend: llama
embeddings: true
  model: ggml-file.bin
# ...

๐Ÿ’ก Examples

  • Example that uses LLamaIndex and LocalAI as embedding: here.