# `AshAi.EmbeddingModels.ReqLLM`
[🔗](https://github.com/ash-project/ash_ai/blob/v0.6.1/lib/ash_ai/embedding_models/req_llm.ex#L5)

ReqLLM-backed embedding model for AshAi vectorization.

Uses `ReqLLM.embed/2` to generate embeddings from text.

## Configuration

    vectorize do
      embedding_model {AshAi.EmbeddingModels.ReqLLM,
        model: "openai:text-embedding-3-small",
        dimensions: 1536
      }
    end

## Options

- `:model` (required) - ReqLLM model identifier (e.g., "openai:text-embedding-3-small")
- `:dimensions` (required) - Vector dimensions for the model
- `:req_opts` (optional) - Additional options passed to ReqLLM
- `:max_batch_size` (optional) - Maximum batch size for chunking (default: 100)

## Common Dimensions

- OpenAI text-embedding-3-small: 1536
- OpenAI text-embedding-3-large: 3072
- Google Gemini text-embedding-004: 768 or 3072
- Cohere embed-english-v3.0: 1024
- Voyage voyage-2: 1024

---

*Consult [api-reference.md](api-reference.md) for complete listing*