docling-project / docling-project/docling

Offline usage: Unrecognized model in sentence-transformers/all-MiniLM-L6-v2

Open
#1,461 1 comment 0 reactions 0 assignees View on GitHub
question triage/close-stale
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

### Question
Hi Team, Community,

I need some help with offline usage.

I know it is possible to pre-fetch models using `docling-tools models download` and later use them via `DOCLING_ARTIFACTS_PATH` environment variable.

However when I am using a `HybridChunker`, it will try to create a default tokeniser using the following code:
```
HuggingFaceTokenizer.from_pretrained(
model_name="sentence-transformers/all-MiniLM-L6-v2"
)
```
As I understand it now, "sentence-transformers/all-MiniLM-L6-v2" is not a part of downloaded models from `docling-tools models download`.

As a result I have the following error:
```
[ERROR]: Unhandled exception: Unrecognized model in sentence-transformers/all-MiniLM-L6-v2.....

```
Do you have a recommendation on how should it be resolved?

versions I am using:
```
docling 2.30.0
docling-core 2.28.0
docling-ibm-models 3.4.2
docling-parse 4.0.1
```

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.