Homepage
Open in app
Sign in
Get started
Tagged in
Vector Database
LanceDB
Serverless, low-latency vector database for AI applications
More information
Followers
151
Elsewhere
More, on Medium
Vector Database
Mahesh Deshwal
in
LanceDB
Feb 22
Hybrid search: RAG for real-life production-grade applications
What is Hybrid Search, and what’s the…
Read more…
318
1 response
Prashant Dixit
in
LanceDB
Feb 13
Benchmarking New OpenAI Embedding Models with LanceDB
Read more…
105
1 response
Weston Pace
in
LanceDB
Jan 31
Substrait Powered Filter Pushdown in Lance
Exploiting the Power of Standardized Expressions
Read more…
56
Shawn Gordon
in
LanceDB
Jan 31
LanceDB Community News — January 2024
We’re kicking off 2024 with a new LanceDB community newsletter to showcase all the updates in…
Read more…
35
Chang She
in
LanceDB
Jan 19
LanceDB + Polars
A (near) perfect match
Read more…
215
2 responses
Kaushal Choudhary
in
LanceDB
Jan 9
🎫 Enhance RAG: Integrate Contextual Compression and Filtering for Precision
Read more…
87
2 responses
Will Jones
in
LanceDB
Dec 20, 2023
Using column statistics to make Lance scans 30x faster
Read more…
6
1 response
Chang She
in
LanceDB
Dec 18, 2023
Benchmarking LanceDB
How to optimize recall vs latency for RAG
Read more…
169
Prashant Dixit
in
LanceDB
Dec 17, 2023
Inverted File Product Quantization (IVF_PQ)
: Accelerate vector search by creating indices
Read more…
35
Kaushal Choudhary
in
LanceDB
Dec 12, 2023
Search within an Image 🔎
Use SAM-and-CLIP to search anything on an image
Read more…
61