Skip to content

Implement hybrid retrieval pipeline with Snowflake Arctic embeddings + BM25 + reranker #13

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
chaman56 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Implement hybrid retrieval pipeline with Snowflake Arctic embeddings + BM25 + reranker #13

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,10 @@ build/

# Large binary files
embeddings.npy
embeddings_local.npy
*.pkl
faiss_index/
faiss_index_local/
data/

# Jupyter
Expand Down
42 changes: 42 additions & 0 deletions ablation_metrics.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
{
"dense": {
"label": "1. Dense Only (Snowflake)",
"n_queries": 291,
"recall@10": 4.851334223739128,
"precision@10": 3.917525773195876,
"mrr@10": 0.09586401570937654,
"recall@50": 9.163617965228665,
"precision@50": 2.4810996563573884,
"mrr@50": 0.1009837095287339
},
"bm25": {
"label": "2. BM25 Only",
"n_queries": 291,
"recall@10": 14.627901634011073,
"precision@10": 10.171821305841924,
"mrr@10": 0.2755891016200295,
"recall@50": 28.38137139557614,
"precision@50": 4.646048109965636,
"mrr@50": 0.2846851723685098
},
"rrf": {
"label": "3. Dense + BM25 (RRF)",
"n_queries": 291,
"recall@10": 12.5553924399447,
"precision@10": 9.450171821305842,
"mrr@10": 0.23299378170512194,
"recall@50": 27.67073722181615,
"precision@50": 4.769759450171822,
"mrr@50": 0.24438704511082662
},
"rerank": {
"label": "4. Dense + BM25 + Reranker",
"n_queries": 291,
"recall@10": 20.662017850264203,
"precision@10": 14.810996563573884,
"mrr@10": 0.42721185839742537,
"recall@50": 31.233461742332192,
"precision@50": 5.876288659793815,
"mrr@50": 0.43146615262450533
}
}
Loading
Loading