embeddings: true
name: text-embedding-ada-002
backend: llama-cpp
# nomic-embed-text-v1.5 has a 2048-token context, unlike the previous 512-token
# granite model. The larger context is what makes the long-input embedding test
# (e2e_test.go) meaningful: it exercises the auto-batch fix where n_batch is
# sized up to the context window (core/backend/options.go EffectiveBatchSize) so
# a >512-token input embeds in a single pass instead of failing with "input is
# too large to process" against the default 512 batch.
context_size: 2048
parameters:
  model: huggingface://nomic-ai/nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.f16.gguf