diff --git a/packages/rag/default.nix b/packages/rag/default.nix index 423c53a..925a8cb 100644 --- a/packages/rag/default.nix +++ b/packages/rag/default.nix @@ -34,7 +34,9 @@ writers.writePython3Bin "rag" def embed(texts): - resp = client.embeddings.create(model=EMBED_MODEL, input=texts) + # encoding_format is explicit: llama.cpp rejects a null value, and + # LiteLLM forwards an unset one as JSON null. + resp = client.embeddings.create(model=EMBED_MODEL, input=texts, encoding_format="float") return [d.embedding for d in resp.data]