From 270b447bcfdcbc922691adc70c00bc46c1866359 Mon Sep 17 00:00:00 2001 From: Jacob Lee Date: Sat, 19 Oct 2024 14:55:48 -0700 Subject: [PATCH] docs: Update LlamaCPP install instructions (#7029) --- docs/core_docs/docs/integrations/chat/llama_cpp.mdx | 4 ++-- docs/core_docs/docs/integrations/llms/llama_cpp.mdx | 4 ++-- docs/core_docs/docs/integrations/text_embedding/llama_cpp.mdx | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/core_docs/docs/integrations/chat/llama_cpp.mdx b/docs/core_docs/docs/integrations/chat/llama_cpp.mdx index f68a709fb8e4..cd71225ef640 100644 --- a/docs/core_docs/docs/integrations/chat/llama_cpp.mdx +++ b/docs/core_docs/docs/integrations/chat/llama_cpp.mdx @@ -12,14 +12,14 @@ This module is based on the [node-llama-cpp](https://github.com/withcatai/node-l ## Setup -You'll need to install the [node-llama-cpp](https://github.com/withcatai/node-llama-cpp) module to communicate with your local model. +You'll need to install major version `2` of the [node-llama-cpp](https://github.com/withcatai/node-llama-cpp) module to communicate with your local model. import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx"; ```bash npm2yarn -npm install -S node-llama-cpp @langchain/community @langchain/core +npm install -S node-llama-cpp@2 @langchain/community @langchain/core ``` You will also need a local Llama 2 model (or a model supported by [node-llama-cpp](https://github.com/withcatai/node-llama-cpp)). You will need to pass the path to this model to the LlamaCpp module as a part of the parameters (see example). diff --git a/docs/core_docs/docs/integrations/llms/llama_cpp.mdx b/docs/core_docs/docs/integrations/llms/llama_cpp.mdx index 98371877d8a4..fe0673b79207 100644 --- a/docs/core_docs/docs/integrations/llms/llama_cpp.mdx +++ b/docs/core_docs/docs/integrations/llms/llama_cpp.mdx @@ -12,10 +12,10 @@ This module is based on the [node-llama-cpp](https://github.com/withcatai/node-l ## Setup -You'll need to install the [node-llama-cpp](https://github.com/withcatai/node-llama-cpp) module to communicate with your local model. +You'll need to install major version `2` of the [node-llama-cpp](https://github.com/withcatai/node-llama-cpp) module to communicate with your local model. ```bash npm2yarn -npm install -S node-llama-cpp +npm install -S node-llama-cpp@2 ``` import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx"; diff --git a/docs/core_docs/docs/integrations/text_embedding/llama_cpp.mdx b/docs/core_docs/docs/integrations/text_embedding/llama_cpp.mdx index 824db38cd589..59349a1e88bc 100644 --- a/docs/core_docs/docs/integrations/text_embedding/llama_cpp.mdx +++ b/docs/core_docs/docs/integrations/text_embedding/llama_cpp.mdx @@ -12,10 +12,10 @@ This module is based on the [node-llama-cpp](https://github.com/withcatai/node-l ## Setup -You'll need to install the [node-llama-cpp](https://github.com/withcatai/node-llama-cpp) module to communicate with your local model. +You'll need to install major version `2` of the [node-llama-cpp](https://github.com/withcatai/node-llama-cpp) module to communicate with your local model. ```bash npm2yarn -npm install -S node-llama-cpp +npm install -S node-llama-cpp@2 ``` import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";