Skip to content

Commit 1821cac

Browse files
authored
Update README.md
1 parent 0ec52ea commit 1821cac

File tree

1 file changed

+3
-1
lines changed

1 file changed

+3
-1
lines changed

README.md

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# SQLite Vector
22

3-
**SQLite Vector** is a cross-platform, ultra-efficient SQLite extension that brings vector search capabilities to your embedded database. It works seamlessly on **iOS, Android, Windows, Linux, and macOS**, using just **30MB of memory** by default. With support for **Float32, Float16, BFloat16, Int8, and UInt8**, and **highly optimized distance functions**, it's the ideal solution for **Edge AI** applications.
3+
**SQLite Vector** is a cross-platform, ultra-efficient SQLite extension that brings vector search capabilities to your embedded database. It works seamlessly on **iOS, Android, Windows, Linux, and macOS**, using just **30MB of memory** by default. With support for **Float32, Float16, BFloat16, Int8, UInt8 and 1Bit**, and **highly optimized distance functions**, it's the ideal solution for **Edge AI** applications.
44

55
## Highlights
66

@@ -175,6 +175,7 @@ You can store your vectors as `BLOB` columns in ordinary tables. Supported forma
175175
* `bfloat16` (2 bytes per element)
176176
* `int8` (1 byte per element)
177177
* `uint8` (1 byte per element)
178+
* `1bit` (1 bit per element)
178179

179180
Simply insert a vector as a binary blob into your table. No special table types or schemas are required.
180181

@@ -188,6 +189,7 @@ Optimized implementations available:
188189
* **L1 Distance (Manhattan)**
189190
* **Cosine Distance**
190191
* **Dot Product**
192+
* **Hamming Distance** (available only with 1bit vectors)
191193

192194
These are implemented in pure C and optimized for SIMD when available, ensuring maximum performance on modern CPUs and mobile devices.
193195

0 commit comments

Comments
 (0)