---
title: Fastembed → SIE
description: Move from in-process Fastembed (ONNX) to out-of-process SIE serving. Same checkpoint, GPU-shared, multi-model.
canonical_url: https://superlinked.com/docs/migrate/fastembed
last_updated: 2026-08-25
---

[Fastembed](https://github.com/qdrant/fastembed) is the
Qdrant-maintained library that runs ONNX embedding models in-process
via onnxruntime. SIE serves the same models out-of-process over HTTP.
The Node port [`fastembed-js`](https://github.com/Anush008/fastembed-js)
mirrors the same surface from TypeScript.

## Why migrate

- **Out-of-process serving.** Every Python worker that imports
  Fastembed gets its own copy of the model in RAM. SIE loads weights
  once per worker pod regardless of how many app processes connect.
- **Shared GPU.** Fastembed is CPU-only by default (GPU support
  requires a separate ONNX runtime build). SIE serves on CPU, MPS, or
  CUDA without changing client code.
- **Multi-model.** SIE can serve dense, sparse, ColBERT, rerankers, and
  vision models from one cluster. FastEmbed also covers dense, sparse,
  late-interaction and image embeddings plus cross-encoder reranking
  in-process; SIE is the move when those workloads need a shared service
  rather than another library copy in every worker.

## What stays the same

- Model checkpoint (e.g. `BAAI/bge-small-en-v1.5`).
- Vector dimension.
- Cosine semantics. Numerical drift between Fastembed (ONNX) and SIE
  (PyTorch) is small in practice; verify on a slice of your own corpus
  (see [Run it yourself](#run-it-yourself)) before deciding whether an
  existing index can stay.

## Before

#### Python

```python
from fastembed import TextEmbedding

encoder = TextEmbedding(model_name="BAAI/bge-small-en-v1.5")
[vec] = list(encoder.embed(["The mitochondrion is the powerhouse of the cell."]))
```

#### TypeScript

```typescript
import { EmbeddingModel, FlagEmbedding } from "fastembed";

const encoder = await FlagEmbedding.init({ model: EmbeddingModel.BGESmallEN15 });
const [vec] = await encoder.embed(["The mitochondrion is the powerhouse of the cell."]).next().then(r => r.value);
```

## After

#### Python

```python
from sie_sdk import SIEClient
from sie_sdk.types import Item

client = SIEClient("http://localhost:8080")
result = client.encode(
    "BAAI/bge-small-en-v1.5",
    Item(text="The mitochondrion is the powerhouse of the cell."),
)
vec = result["dense"]  # np.ndarray, shape [384]
```

#### TypeScript

```typescript
import { SIEClient } from "@superlinked/sie-sdk";

const client = new SIEClient("http://localhost:8080");
const result = await client.encode(
  "BAAI/bge-small-en-v1.5",
  { text: "The mitochondrion is the powerhouse of the cell." },
);
const vec = result.dense; // Float32Array, length 384

await client.close();
```

## Re-embed required?

**No** if you keep the same checkpoint **and** the drift check on a
slice of your own corpus passes (see
[Run it yourself](#run-it-yourself)). **Yes** if that comparison shows
an unacceptable retrieval regression, or if you take the migration as a
chance to upgrade to a stronger model.

## Run it yourself

`sentence-transformers/all-MiniLM-L6-v2` is the common-denominator
small model both Fastembed and SIE ship by default.

```bash
docker run -p 8080:8080 \
  -v sie-hf-cache:/app/.cache/huggingface \
  -e SIE_PRELOAD_MODELS=sentence-transformers/all-MiniLM-L6-v2 \
  ghcr.io/superlinked/sie-server:latest-cpu-default
uv add fastembed
```

Run the 'before' and 'after' snippets from this page. Expected:
identical dim (384), cosine at or above 0.999.

### Using `BAAI/bge-small-en-v1.5` (or any other model)

Most Fastembed users actually run `BAAI/bge-small-en-v1.5`. SIE ships
a model config for it at
`packages/sie_server/models/BAAI__bge-small-en-v1.5.yaml`, but that
config only defines a `candle` profile, so the `cpu-default` image
cannot serve it. Migration mechanics are otherwise identical. Either
run an image built with the `candle` bundle, or add a `default`
profile with the sentence-transformer adapter to the existing YAML:

```yaml
profiles:
  default:
    max_batch_tokens: 16384
    compute_precision: null
    adapter_path: sie_server.adapters.sentence_transformer:SentenceTransformerDenseAdapter
    adapter_options:
      loadtime:
        trust_remote_code: false
      runtime:
        pooling: cls
        normalize: true
```

Then `sie-server serve -m BAAI/bge-small-en-v1.5`. The
`sentence-transformers__all-MiniLM-L6-v2.yaml` model config is the
closest working reference; its `default` profile uses the same
adapter.