valentinus

Crates.iovalentinus
lib.rsvalentinus
version0.5.5
sourcesrc
created_at2024-07-12 12:34:04.957532
updated_at2024-12-06 11:44:27.827383
descriptionNext generation vector database built with LMDB bindings
homepage
repositoryhttps://github.com/kn0sys/valentinus
max_upload_size
id1300631
size311,387
n12n (kn0sys)

documentation

https://docs.rs/valentinus

README

.github/workflows/rust.yml test Crates.io Version Crates.io Downloads (latest version) docs.rs GitHub commit activity Matrix

alt text

valentinus

next generation vector db built with lmdb bindings

dependencies

  • bincode/serde - serialize/deserialize
  • lmdb-rs - database bindings
  • ndarray - numpy equivalent
  • ort/onnx - embeddings

getting started

git clone https://github.com/kn0sys/valentinus && cd valentinus

optional environment variables

var usage default
LMDB_USER working directory of the user for database $USER
LMDB_MAP_SIZE Sets max environment size, i.e. size in memory/disk of all data 20% of available memory
ONNX_PARALLEL_THREADS parallel execution mode for this session 1
VALENTINUS_CUSTOM_DIM embeddings dimensions for custom models all-mini-lm-6 -> 384
VALENTINUS_LMDB_ENV environment for the database (i.e. test, prod) test

tests

  • Note: all tests currently require the all-MiniLM-L6-v2_onnx directory
  • Get the model.onnx and tokenizer.json from huggingface or build them
mkdir all-MiniLM-L6-v2_onnx
cd all-MiniLM-L6-v2_onnx && wget https://huggingface.co/nigel-christian/all-MiniLM-L6-v2_onnx/resolve/main/config.json
wget https://huggingface.co/nigel-christian/all-MiniLM-L6-v2_onnx/resolve/main/model.onnx
wget https://huggingface.co/nigel-christian/all-MiniLM-L6-v2_onnx/resolve/main/special_tokens_map.json
wget https://huggingface.co/nigel-christian/all-MiniLM-L6-v2_onnx/resolve/main/tokenizer_config.json
wget https://huggingface.co/nigel-christian/all-MiniLM-L6-v2_onnx/resolve/main/tokenizer.json
wget https://huggingface.co/nigel-christian/all-MiniLM-L6-v2_onnx/resolve/main/vocab.txt

RUST_TEST_THREADS=1 cargo test

examples

see examples

reference

inspired by this chromadb python tutorial

Commit count: 107

cargo fmt