Ruby langchainrb gem and custom configuration for the model setup

题意 :Ruby 的 langchainrb gem 以及针对模型设置的自定义配置

问题背景:

I am working in a prototype using the gem langchainrb. I am using the module assistant module to implemente a basic RAG architecture.

我正在使用 langchainrb 这个 gem 来开发一个原型。我利用其中的 assistant 模块来实现一个基本的 RAG(Retrieval-Augmented Generation,检索增强生成)架构。

Everything works, and now I would like to customize the model configuration.

一切运行正常,现在我想自定义模型的配置。

In the documenation there is no clear way of setting up the Model. In my case, I would like to use OpenAi and use:

在文档中,没有明确的方法来设置模型。在我的情况下,我想使用 OpenAI 并使用以下配置:

  • temperature: 0.1
  • Model: gpt-4o

In the README, there is a mention about using llm_options.

在 README 文件中,提到了使用 llm_options

If I go to the OpenAI Module documentation:

如果我去查看 OpenAI 模块的文档:

It says I have to check here: 它说我要查看这里:

But there is not any mention of temperature, for example. Also, in the example in the Langchain::LLM::OpenAI documentation, the options are totally different.

但是在文档中并没有提到例如"温度"这样的设置。此外,在 Langchain::LLM::OpenAI 的文档示例中,给出的选项是完全不同的。

I am working in a prototype using the gem langchainrb. I am using the module assistant module to implemente a basic RAG architecture.

Everything works, and now I would like to customize the model configuration.

In the documenation there is no clear way of setting up the Model. In my case, I would like to use OpenAi and use:

In the README, there is a mention about using llm_options.

If I go to the OpenAI Module documentation:

It says I have to check here:

But there is not any mention of temperature, for example. Also, in the example in the Langchain::LLM::OpenAI documentation, the options are totally different.

ruby 复制代码
# ruby-openai options:

CONFIG_KEYS = %i[
  api_type
  api_version
  access_token
  log_errors
  organization_id
  uri_base
  request_timeout
  extra_headers
].freeze
python 复制代码
# Example in Class: Langchain::LLM::OpenAI documentation: 

{
  n: 1,
  temperature: 0.0,
  chat_completion_model_name: "gpt-3.5-turbo",
  embeddings_model_name: "text-embedding-3-small"
}.freeze

问题解决:

I have a conflict between llm_options and default_options. I thought it was the same with different priorities.

我在 llm_optionsdefault_options 之间遇到了冲突。我原本以为它们只是优先级不同的相同设置。

For the needs expressed in the question I have to use the default_options as in here:

针对问题中表达的需求,我必须按照这里的示例来使用 default_options

python 复制代码
llm =
  Langchain::LLM::OpenAI.new(
    api_key: <OPENAI_KEY>,
    default_options: {
      temperature: 0.0,
      chat_completion_model_name: "gpt-4o"
    }
  )
相关推荐
m0_738120724 分钟前
CTFshow系列——PHP特性Web93-96
开发语言·安全·web安全·php·ctfshow
m0_5704664115 分钟前
代码随想录算法训练营第二十八天 | 买卖股票的最佳实际、跳跃游戏、K次取反后最大化的数组和
java·开发语言·算法
程序喵大人16 分钟前
分享个C++线程池的实现源码
开发语言·c++·线程池
kobe_OKOK_34 分钟前
rabbitmq 入门知识点
分布式·rabbitmq·ruby
不会吃萝卜的兔子40 分钟前
go webrtc - 1 go基本概念
开发语言·golang·webrtc
豌豆花下猫1 小时前
Python 潮流周刊#118:Python 异步为何不够流行?(摘要)
后端·python·ai
要做朋鱼燕1 小时前
【C++】 priority_queue 容器模拟实现解析
开发语言·c++·笔记·职场和发展
jiaway1 小时前
【C语言】第四课 指针与内存管理
c语言·开发语言·算法
励志不掉头发的内向程序员1 小时前
C++进阶——继承 (1)
开发语言·c++·学习
秋难降2 小时前
SQL 索引突然 “罢工”?快来看看为什么
数据库·后端·sql