sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2025-02-17 08:04:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Use a better model for asymmetric semantic search

Browse source 
- The multi-qa-MiniLM-L6-cos-v1 is more extensively benchmarked[1]
- It has the right mix of model query speed, size and performance on benchmarks
- On hugging face it has way more downloads and likes than the msmarco model[2]
- On very preliminary evaluation of the model
  - It doubles the encoding speed of all entries (down from ~8min to 4mins)
  - It gave more entries that stay relevant to the query (3/5 vs 1/5 earlier)

[1]: https://www.sbert.net/docs/pretrained_models.html
[2]: https://huggingface.co/sentence-transformers
This commit is contained in:
Debanjum Singh Solanky 2022-07-18 20:00:19 +04:00
parent 5e302dbcda
commit 4a90972e38
5 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.org
View file

@ -100,7 +100,7 @@
#+end_src
** Acknowledgments
- [[https://huggingface.co/sentence-transformers/msmarco-MiniLM-L-6-v3][MiniLM Model]] for Asymmetric Text Search. See [[https://www.sbert.net/examples/applications/retrieve_rerank/README.html][SBert Documentation]]
- [[https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1][Multi-QA MiniLM Model]] for Asymmetric Text Search. See [[https://www.sbert.net/examples/applications/retrieve_rerank/README.html][SBert Documentation]]
- [[https://github.com/openai/CLIP][OpenAI CLIP Model]] for Image Search. See [[https://www.sbert.net/examples/applications/image-search/README.html][SBert Documentation]]
- Charles Cave for [[http://members.optusnet.com.au/~charles57/GTD/orgnode.html][OrgNode Parser]]
- Sven Marnach for [[https://github.com/smarnach/pyexiftool/blob/master/exiftool.py][PyExifTool]]

2
config/sample_config.yml
View file

@ -33,7 +33,7 @@ search-type:
model_directory: "/data/models/symmetric"
asymmetric:
encoder: "sentence-transformers/msmarco-MiniLM-L-6-v3"
encoder: "sentence-transformers/multi-qa-MiniLM-L6-cos-v1"
cross-encoder: "cross-encoder/ms-marco-MiniLM-L-6-v2"
model_directory: "/data/models/asymmetric"

2
src/utils/cli.py
View file

@ -85,7 +85,7 @@ default_config = {
},
'asymmetric':
{
'encoder': "sentence-transformers/msmarco-MiniLM-L-6-v3",
'encoder': "sentence-transformers/multi-qa-MiniLM-L6-cos-v1",
'cross-encoder': "cross-encoder/ms-marco-MiniLM-L-6-v2",
'model_directory': None
},

2
tests/conftest.py
View file

@ -20,7 +20,7 @@ def search_config(tmp_path_factory):
)
search_config.asymmetric = AsymmetricSearchConfig(
encoder = "sentence-transformers/msmarco-MiniLM-L-6-v3",
encoder = "sentence-transformers/multi-qa-MiniLM-L6-cos-v1",
cross_encoder = "cross-encoder/ms-marco-MiniLM-L-6-v2",
model_directory = model_dir
)

2
tests/data/notes/main_readme.org
View file

@ -42,6 +42,6 @@
#+end_src
** Acknowledgments
- [[https://huggingface.co/sentence-transformers/msmarco-MiniLM-L-6-v3][MiniLM Model]] for Asymmetric Text Search. See [[https://www.sbert.net/examples/applications/retrieve_rerank/README.html][SBert Documentation]]
- [[https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1][MiniLM Model]] for Asymmetric Text Search. See [[https://www.sbert.net/examples/applications/retrieve_rerank/README.html][SBert Documentation]]
- [[https://github.com/openai/CLIP][OpenAI CLIP Model]] for Image Search. See [[https://www.sbert.net/examples/applications/image-search/README.html][SBert Documentation]]
- Charles Cave for [[http://members.optusnet.com.au/~charles57/GTD/orgnode.html][OrgNode Parser]]