---
title: "How do I switch embedding models without a reindex script?"
description: "Switch embedding models with a schema update that drops the old index and adds the new one. Pass allow-destructive. There is no separate reindex script."
url: "https://www.pixeltable.com/learn/how-to/switch-embedding-models-without-a-reindex-script"
updated: "2026-10-28"
doc: "https://docs.pixeltable.com/platform/embedding-indexes"
---

# How do I switch embedding models without a reindex script?

Switching an embedding model is a schema change: the old index is dropped and a new one is added, then every stored row is embedded with the new function. There is no separate reindex script. A destructive schema plan applies nothing unless you pass allow-destructive. Changing the embedder is not the same as recomputing a stored computed column.

Updated: 2026-10-28
Part of [How do I ... in Python?](https://www.pixeltable.com/learn/how-to).

## Before you start

About 15 min.

- Python 3.11+
- pip install -U 'pixeltable[serve]'
- pxt init in the project root
- sentence-transformers for all-MiniLM-L6-v2 and all-mpnet-base-v2

## On this page

- [Before you start](https://www.pixeltable.com/learn/how-to/switch-embedding-models-without-a-reindex-script#before-you-start)
- [Start with the model you already index with](https://www.pixeltable.com/learn/how-to/switch-embedding-models-without-a-reindex-script#step-1)
- [Change the embedder on the class](https://www.pixeltable.com/learn/how-to/switch-embedding-models-without-a-reindex-script#step-2)
- [Apply the destructive plan](https://www.pixeltable.com/learn/how-to/switch-embedding-models-without-a-reindex-script#step-3)
- [Query with the new model only](https://www.pixeltable.com/learn/how-to/switch-embedding-models-without-a-reindex-script#step-4)
- [Comparison](https://www.pixeltable.com/learn/how-to/switch-embedding-models-without-a-reindex-script#comparison)
- [Where Pixeltable fits](https://www.pixeltable.com/learn/how-to/switch-embedding-models-without-a-reindex-script#where-pixeltable-fits)
- [Questions](https://www.pixeltable.com/learn/how-to/switch-embedding-models-without-a-reindex-script#questions)

## 1. Start with the model you already index with {#step-1}

The embedder is part of the index. all-MiniLM-L6-v2 is the documented fast local default. Query uses the same function. Do not keep a second model id in a worker.

```python
import pixeltable as pxt
from pixeltable.functions.huggingface import sentence_transformer

TableModel = pxt.model_base()
text_embed = sentence_transformer.using(model_id='all-MiniLM-L6-v2')

class Notes(TableModel, name='notes'):
    content: pxt.String
    __indexes__ = [
        pxt.EmbeddingIndex(content, string_embed=text_embed),
    ]

# pxt schema update app.py notes -f
```

## 2. Change the embedder on the class {#step-2}

Point string_embed at the new model. all-mpnet-base-v2 is stronger and slower. The schema diff will drop the old index and add the new one. Vectors from the old model cannot be reused.

```python
text_embed = sentence_transformer.using(model_id='all-mpnet-base-v2')

class Notes(TableModel, name='notes'):
    content: pxt.String
    __indexes__ = [
        pxt.EmbeddingIndex(content, string_embed=text_embed),
    ]
```

## 3. Apply the destructive plan {#step-3}

Dropping an index destroys its data. A plan that drops an index applies nothing unless you pass allow-destructive. Force skips the confirmation prompt. After it finishes, every stored row is embedded with the new function.

```python
# pxt schema diff app.py notes
# pxt schema update app.py notes --allow-destructive -f
```

## 4. Query with the new model only {#step-4}

similarity(string=) embeds the question with the index that now exists. Mixing an old query model with a new index ranks noise. pxt recompute is for a computed-column expression, not for this index swap.

```python
@pxt.query
def search_notes(query: str, limit: int = 5):
    sim = Notes.content.similarity(string=query)
    return (
        Notes.order_by(sim, asc=False)
        .limit(limit)
        .select(Notes.content, sim)
    )
```

## Reindex script versus a schema plan {#comparison}

| Job | A reindex script | Schema update |
| --- | --- | --- |
| What changes | A worker that rewrites a second store | string_embed on EmbeddingIndex |
| Old vectors | You delete or overwrite them | The dropped index is gone |
| Apply | A job you schedule | pxt schema update --allow-destructive -f |
| Without the flag | The script still runs | The plan applies nothing |
| pxt recompute | Not this job | Computed columns, not this index swap |

## Where Pixeltable fits {#where-pixeltable-fits}

In Pixeltable, changing the embedder replaces the embedding index: the schema diff drops the old index and adds the new one. Apply with pxt schema update --allow-destructive -f. The new index rebuilds embeddings for rows already stored. pxt recompute is for a computed-column expression, not for this index swap.

```python
import pixeltable as pxt
from pixeltable.functions.huggingface import sentence_transformer

TableModel = pxt.model_base()
text_embed = sentence_transformer.using(model_id='all-mpnet-base-v2')

class Notes(TableModel, name='notes'):
    content: pxt.String
    __indexes__ = [
        pxt.EmbeddingIndex(content, string_embed=text_embed),
    ]

@pxt.query
def search_notes(query: str, limit: int = 5):
    sim = Notes.content.similarity(string=query)
    return Notes.order_by(sim, asc=False).limit(limit).select(Notes.content, sim)

# pxt schema update app.py notes --allow-destructive -f
```

## Concepts

- [What is an embedding index?](https://www.pixeltable.com/learn/what-is-an-embedding-index)
- [What are multimodal embeddings?](https://www.pixeltable.com/learn/what-are-multimodal-embeddings)
- [What is semantic search?](https://www.pixeltable.com/learn/what-is-semantic-search)

## Use case

- [Multimodal AI Apps: Process Any Data Type in One System](https://www.pixeltable.com/use-cases/multimodal-ai-application-development)

## Questions {#questions}

### Why is allow-destructive required? {#faq-1}

Dropping an index destroys its data. A destructive plan applies nothing at all without that flag, so a missed confirmation cannot delete vectors by accident. -f skips the prompt once you have reviewed the diff.

### Is this pxt recompute? {#faq-2}

No. pxt recompute reruns a computed-column expression. Swapping an embedder drops and adds an embedding index. Use schema update --allow-destructive.

### Can I keep both models at once? {#faq-3}

Two indexes on two columns can coexist if you declare both. One index cannot hold two models. Query each column with the function that built it.

## Related

- [What is an embedding index?](https://www.pixeltable.com/learn/what-is-an-embedding-index)
- [What are multimodal embeddings?](https://www.pixeltable.com/learn/what-are-multimodal-embeddings)
- [What is semantic search?](https://www.pixeltable.com/learn/what-is-semantic-search)
- [How do I do semantic search in Python?](https://www.pixeltable.com/learn/how-to/semantic-search-in-python)
- [How do I embed images for search in Python?](https://www.pixeltable.com/learn/how-to/embed-images-for-search)
- [How do I migrate from FAISS?](https://www.pixeltable.com/learn/how-to/migrate-from-faiss)
- [Multimodal application development](https://www.pixeltable.com/use-cases/multimodal-ai-application-development)
- [Embedding indices](https://docs.pixeltable.com/platform/embedding-indexes)
- [Migrate to Pixeltable](https://docs.pixeltable.com/howto/coming-from)