https://github.com/carlesonielfa/qwen3_span_extraction
This is the code repository for the blog post "Can we assess span-level relevance with dense embedding models?".
https://github.com/carlesonielfa/qwen3_span_extraction
colbert embeddings jina qwen3 rag relevance retrieval semantic token
Last synced: 2 months ago
JSON representation
This is the code repository for the blog post "Can we assess span-level relevance with dense embedding models?".
- Host: GitHub
- URL: https://github.com/carlesonielfa/qwen3_span_extraction
- Owner: carlesonielfa
- Created: 2025-07-14T17:46:21.000Z (12 months ago)
- Default Branch: master
- Last Pushed: 2025-07-18T06:17:15.000Z (11 months ago)
- Last Synced: 2025-07-30T03:48:08.086Z (11 months ago)
- Topics: colbert, embeddings, jina, qwen3, rag, relevance, retrieval, semantic, token
- Language: Jupyter Notebook
- Homepage: https://onielfa.com/articles/qwen3_span_extraction
- Size: 1.9 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Can we assess span-level relevance with dense embedding models?
This is the code repository for the blog post [Can we assess span-level relevance with dense embedding models?](https://onielfa.com/articles/qwen3_span_extraction/).
It contains the jupyter notebook from which the web page was generated, as well as the code for the `manim` animations used in the post.
## How to run the notebook
The project's requirements are in the `pyproject.toml` file. You can install them using any Python package manager, such as `uv`, `poetry`, or `pdm`.
```bash
uv sync
```
or
```bash
poetry install
```
or
```bash
pdm install
```
If you wish to use `pip`, a `requirements.txt` file is also available:
```bash
pip install -r requirements.txt
```