Skip to content
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

Updated BM25, text and hybrid search for Activeloop Deeplake #534

Merged
merged 5 commits into from
Feb 3, 2025
Merged

Updated BM25, text and hybrid search for Activeloop Deeplake #534

Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f868c73
Updated BM25, text and hybrid search for Activeloop Deeplake
vahan-activeloop Jan 29, 2025
83a6ad7
Merge branch 'main' into vahan/activeloop-text
prrao87 Jan 30, 2025
e025810
Update docs/tools/vdb_table/data/activeloop.json
vahan-activeloop Jan 31, 2025
a0d67df
Apply suggestions from code review
prrao87 Feb 1, 2025
3c3f6b5
Merge branch 'main' into vahan/activeloop-text
vahan-activeloop Feb 3, 2025
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
16 changes: 8 additions & 8 deletions docs/tools/vdb_table/data/activeloop.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,9 +33,9 @@
"comment": ""
},
"hybrid_search": {
"support": "",
"source_url": "https://docs.activeloop.ai/performance-features/querying-datasets/query-syntax",
"comment": "While you can run embedding search + contains(text, 'keywoard') or multiple those (keyword search inside text tensor) since BM25 not available I wouldn't call a full hybrid search. https://docs.activeloop.ai/performance-features/querying-datasets/query-syntax"
"support": "full",
"source_url": "https://docs.deeplake.ai/4.0/guide/rag/",
prrao87 marked this conversation as resolved.
Show resolved Hide resolved
"comment": "BM25 with ANN"
},
"facets": {
"support": "",
Expand All @@ -58,14 +58,14 @@
"comment": "no native sparse vector support, although it supports all numpy arrays hence can also store sparse numpy arrays"
},
"bm25": {
"support": "none",
"source_url": "",
"support": "full",
"source_url": "https://docs.deeplake.ai/latest/#key-features",
"comment": ""
},
"full_text": {
"support": "partial",
"source_url": "",
"comment": "you can search keywords with TQL `contains(...)` function"
"support": "full",
"source_url": "https://docs.deeplake.ai/4.0/guide/rag/",
prrao87 marked this conversation as resolved.
Show resolved Hide resolved
prrao87 marked this conversation as resolved.
Show resolved Hide resolved
"comment": "via Inverted Index and BM25"
},
"embeddings_text": {
"support": "partial",
Expand Down