node-llama-cpp

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

MIT License

Downloads
37.6K
Stars
905
Committers
6

Bot releases are visible (Hide)

node-llama-cpp - v2.5.1

Published by github-actions[bot] about 1 year ago

2.5.1 (2023-09-27)

Bug Fixes

  • make disabling metal on build work (#55) (03ec18b)
node-llama-cpp - v2.5.0

Published by github-actions[bot] about 1 year ago

2.5.0 (2023-09-26)

Bug Fixes

  • adapt to llama.cpp interface change (#49) (9db72b0)

Features

  • add FalconChatPromptWrapper (#53) (656bf3c)
  • fall back to build from source if prebuilt binary loading fails (#54) (d99e3b0)
  • load conversation history into a LlamaChatSession (#51) (4e274ce)
  • only build one binary for all node versions (#50) (1e617cd)
node-llama-cpp - v2.4.1

Published by github-actions[bot] about 1 year ago

2.4.1 (2023-09-15)

node-llama-cpp - v2.4.0

Published by github-actions[bot] about 1 year ago

2.4.0 (2023-09-09)

Features

node-llama-cpp - v2.3.2

Published by github-actions[bot] about 1 year ago

2.3.2 (2023-09-02)

Bug Fixes

  • load image urls properly also outside GitHub (#35) (cf1f5f1)
node-llama-cpp - v2.3.1

Published by github-actions[bot] about 1 year ago

2.3.1 (2023-09-02)

node-llama-cpp - v2.3.0

Published by github-actions[bot] about 1 year ago

2.3.0 (2023-09-02)

Bug Fixes

  • handle stop words remainder properly in a chat session (#32) (9bdef11)
  • move default export to be the last one in package.json (#31) (dd49959)

Features

  • threads count setting on a model (#33) (47c3c5f)
node-llama-cpp - v2.2.0

Published by github-actions[bot] about 1 year ago

2.2.0 (2023-09-01)

Features

  • export class options types (#29) (74be398)
  • improve error message when llama.cpp source is not downloaded (#27) (7837af7)
  • make contributions and support more efficient via GitHub templates (#28) (5fc0d18)
node-llama-cpp - v2.1.2

Published by github-actions[bot] about 1 year ago

2.1.2 (2023-08-28)

Bug Fixes

node-llama-cpp - v2.1.1

Published by github-actions[bot] about 1 year ago

2.1.1 (2023-08-28)

node-llama-cpp - v2.1.0

Published by github-actions[bot] about 1 year ago

2.1.0 (2023-08-28)

Features

  • add grammar support (#13) (c28d2de)
  • add support for metal and cuda in the build command (#17) (1043596)
node-llama-cpp - v2.0.0

Published by github-actions[bot] about 1 year ago

2.0.0 (2023-08-25)

Bug Fixes

  • llama.cpp interface breaking change (#10) (8086c5f)

BREAKING CHANGES

  • only .gguf models are supported from now on
node-llama-cpp - v1.3.1

Published by github-actions[bot] about 1 year ago

1.3.1 (2023-08-17)

Bug Fixes

  • rename a param to match llama.cpp (#8) (54a1c6f)
node-llama-cpp - v1.3.0

Published by github-actions[bot] about 1 year ago

1.3.0 (2023-08-17)

Features

  • add support for some llama.cpp params on LlamaModel (#5) (c76ec48)
  • add TSDoc (#6) (560dd4e)
node-llama-cpp - v1.2.1

Published by github-actions[bot] about 1 year ago

1.2.1 (2023-08-16)

Bug Fixes

node-llama-cpp - v1.2.0

Published by github-actions[bot] about 1 year ago

1.2.0 (2023-08-16)

Features

node-llama-cpp - v1.1.1

Published by github-actions[bot] about 1 year ago

1.1.1 (2023-08-12)

Bug Fixes

  • use prebuilt binaries by default (6dd0d56)
node-llama-cpp - v1.1.0

Published by github-actions[bot] about 1 year ago

1.1.0 (2023-08-12)

Bug Fixes

  • spawnCommand support for Windows (c0e68f6)

Features

  • use spawn directly instead of $ to avoid redundant logs (ab3d10e)