smart_prompt 0.3.2 → 0.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e8afddc47f83b453b4b7165520beac3a59583b7324eb6f7f41b6cc55fd4b5a4a
-  data.tar.gz: e8a430a5068ca9b1f40cf5bdf42dbb4aae762d991308c5049ee7f3ea781a09f8
+  metadata.gz: ced076006bec94a02a4612d9d86794c6a1468b50b386ce99e67f9905631db289
+  data.tar.gz: f815ef18d7a297552db4aeb679d4213d03662f532876f2780b6374b59d9fb40a
 SHA512:
-  metadata.gz: 3f0ca77b523017030b53fa562229d93b7f297ec118a1ad5f19b8af912e630a84a4251a0f73fc2800bdfe4c0bb6522154872aae105a57c4d405f83b807d662467
-  data.tar.gz: '0946bfb17ec34230af139fa39b9adfbfc6d3b37d714b312a9df123d18ab73a5fe711ed7818b77d6f2c8e28de1edd478d0061bea790872c799fca55d7cc54cdaf'
+  metadata.gz: 003dbe0204b9eb84a04de6ac3520903fdf92e8621fe79cc7c9fd4360e1f4bb845a425ebd59b82cfe82b8c726ada32ba5dfc7576c2b66a16bf3f95f1e5f6fd9a0
+  data.tar.gz: ef2887559b141422b9704a5f80076d10037b25c3d0d1d0d27fbb9d6b9a772419789c5d43bc9f68a15c429f19402ef99fe002cf11cfcf719082d37753f1aa8d6e

data/README.cn.md

@@ -1,27 +1,394 @@
+[English](./README.md) | 中文
+
 # SmartPrompt
 
-SmartPrompt 是一个强大的 Ruby gem，提供了一种领域特定语言（DSL），使其他 Ruby 程序能够更加方便、自然地调用各种大型语言模型（LLM）的能力。
+[![Gem Version](https://badge.fury.io/rb/smart_prompt.svg)](https://badge.fury.io/rb/smart_prompt)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+SmartPrompt 是一个强大的 Ruby gem，提供了优雅的领域特定语言（DSL），用于构建基于大型语言模型（LLM）的智能应用程序。它使 Ruby 程序能够无缝地与各种 LLM 服务提供商交互，同时保持清晰、可组合和高度可定制的代码架构。
+
+## 🚀 核心特性
 
-## 主要特性
+### 多 LLM 支持
+- **OpenAI API 兼容**: 完全支持 OpenAI GPT 模型和兼容的 API
+- **Llama.cpp 集成**: 直接集成本地 Llama.cpp 服务器  
+- **可扩展适配器**: 易于扩展的适配器系统，支持新的 LLM 提供商
+- **统一接口**: 无论底层 LLM 提供商如何，都使用相同的 API
 
-- 灵活的任务组合：以特定服务提供商 + 特定 LLM + 特定 prompt 的方式组合各种任务
-- 子任务嵌套：支持以 DSL 形式组合调用其他子任务
-- 性能优化：在保证质量的同时，提供性能最优或成本最低的解决方案
+### 灵活架构
+- **基于 Worker 的任务**: 为特定 AI 任务定义可重用的 Worker
+- **模板系统**: 基于 ERB 的提示词模板，支持参数注入
+- **对话管理**: 内置对话历史和上下文管理
+- **流式支持**: 实时响应流，提供更好的用户体验
 
-## 安装
+### 高级功能
+- **工具调用**: 原生支持函数调用和工具集成
+- **重试逻辑**: 强大的错误处理机制，支持可配置的重试
+- **嵌入向量**: 文本嵌入生成，用于语义搜索和 RAG 应用
+- **配置驱动**: 基于 YAML 的配置，便于部署管理
 
-将 gem 安装并添加到应用程序的 Gemfile 中，执行以下命令：
+### 生产就绪
+- **全面日志记录**: 详细的日志记录，用于调试和监控
+- **错误处理**: 优雅的错误处理，包含自定义异常类型  
+- **性能优化**: 高效的资源使用和响应缓存
+- **线程安全**: 支持多线程应用中的并发使用
 
+## 📦 安装
+
+添加到你的 Gemfile：
+
+```ruby
+gem 'smart_prompt'
 ```
-$ bundle add smart_prompt
+
+然后执行：
+```bash
+$ bundle install
+```
+
+或直接安装：
+```bash
+$ gem install smart_prompt
+```
+
+## 🛠️ 快速开始
+
+### 1. 配置
+
+创建 YAML 配置文件（`config/smart_prompt.yml`）：
+
+```yaml
+# 适配器定义
+adapters:
+  openai: OpenAIAdapter
+# LLM 配置
+llms:
+  SiliconFlow:
+    adapter: openai
+    url: https://api.siliconflow.cn/v1/
+    api_key: ENV["APIKey"]
+    default_model: Qwen/Qwen2.5-7B-Instruct
+  llamacpp:
+    adapter: openai
+    url: http://localhost:8080/    
+  ollama:
+    adapter: openai
+    url: http://localhost:11434/
+    default_model: deepseek-r1
+  deepseek:
+    adapter: openai
+    url: https://api.deepseek.com
+    api_key: ENV["DSKEY"]
+    default_model: deepseek-reasoner
+
+# 默认设置
+default_llm: SiliconFlow
+template_path: "./templates"
+worker_path: "./workers"
+logger_file: "./logs/smart_prompt.log"
 ```
 
-如果不使用 bundler 来管理依赖，可以通过执行以下命令来安装 gem：
+### 2. 创建提示词模板
+
+在 `templates/` 目录中创建模板文件：
+
+**templates/chat.erb**:
+```erb
+你是一个有用的助手。请回答以下问题：
 
+问题：<%= question %>
+
+背景：<%= context || "未提供额外背景信息" %>
 ```
-$ gem install smart_prompt
+
+### 3. 定义 Worker
+
+在 `workers/` 目录中创建 worker 文件：
+
+**workers/chat_worker.rb**:
+```ruby
+SmartPrompt.define_worker :chat_assistant do
+  # 使用特定的 LLM
+  use "SiliconFlow"
+  model "deepseek-ai/DeepSeek-V3"
+  # 设置系统消息
+  sys_msg("你是一个有用的 AI 助手。", params)
+  # 使用模板和参数  
+  prompt(:chat, {
+    question: params[:question],
+    context: params[:context]
+  })
+  # 发送消息并返回响应
+  send_msg
+end
+```
+
+### 4. 在应用中使用
+
+```ruby
+require 'smart_prompt'
+
+# 使用配置初始化引擎
+engine = SmartPrompt::Engine.new('config/smart_prompt.yml')
+
+# 执行 worker
+result = engine.call_worker(:chat_assistant, {
+  question: "什么是机器学习？",
+  context: "我们正在讨论 AI 技术"
+})
+
+puts result
+```
+
+## 📚 高级用法
+
+### 流式响应
+
+```ruby
+# 定义流式 worker
+SmartPrompt.define_worker :streaming_chat do
+  use "deepseek"
+  model "deepseek-chat"
+  sys_msg("你是一个有用的助手。")
+  prompt(params[:message])
+  send_msg
+end
+
+# 使用流式处理
+engine.call_worker_by_stream(:streaming_chat, {
+  message: "给我讲个故事"
+}) do |chunk, bytesize|
+  print chunk.dig("choices", 0, "delta", "content")
+end
+```
+
+### 工具集成
+
+```ruby
+# 定义带工具的 worker
+SmartPrompt.define_worker :assistant_with_tools do
+  use "SiliconFlow"
+  model "Qwen/Qwen3-235B-A22B"
+  tools = [
+    {
+      type: "function",
+      function: {
+        name: "get_weather",
+        description: "获取指定位置的天气信息",
+        parameters: {
+          type: "object",
+          properties: {
+            location: {
+              type: "string", 
+              description: "城市和省份"
+            }
+          },
+          required: ["location"]
+        }
+      }
+    }
+  ]
+  
+  sys_msg("你可以使用可用的工具帮助处理天气查询。", params)
+  prompt(params[:message])
+  params.merge(tools: tools)
+  send_msg
+end
+```
+
+### 对话历史
+
+```ruby
+SmartPrompt.define_worker :conversational_chat do
+  use "deepseek"
+  model "deepseek-chat"
+  sys_msg("你是一个记住对话上下文的有用助手。")
+  prompt(params[:message], with_history: true)
+  send_msg
+end
+```
+
+### 嵌入向量生成
+
+```ruby
+SmartPrompt.define_worker :text_embedder do
+  use "SiliconFlow"
+  model "BAAI/bge-m3"
+  prompt params[:text]  
+  embeddings(params[:dimensions] || 1024)
+end
+
+# 使用方法
+embeddings = engine.call_worker(:text_embedder, {
+  text: "将此文本转换为嵌入向量",
+  dimensions: 1024
+})
+```
+
+## 🏗️ 架构概述
+
+SmartPrompt 采用模块化架构：
+
+```
+┌─────────────────┐    ┌──────────────────┐    ┌─────────────────┐
+│     应用程序     │    │   SmartPrompt    │    │   LLM 提供商    │
+│                 │◄──►│      引擎        │◄──►│   (OpenAI/      │
+│                 │    │                  │    │    Llama.cpp)   │
+└─────────────────┘    └──────────────────┘    └─────────────────┘
+                                │
+                       ┌────────┼────────┐
+                       │        │        │
+                   ┌───▼───┐ ┌──▼──┐ ┌───▼────┐
+                   │Worker │ │对话 │ │ 模板   │
+                   │       │ │管理 │ │ 系统   │
+                   └───────┘ └─────┘ └────────┘
+```
+
+### 核心组件
+
+- **引擎（Engine）**: 中央编排器，管理配置、适配器和 Worker
+- **Worker**: 包含嵌入业务逻辑的可重用任务定义
+- **对话（Conversation）**: 上下文和消息历史管理
+- **适配器（Adapters）**: LLM 提供商集成（OpenAI、Llama.cpp 等）
+- **模板（Templates）**: 基于 ERB 的提示词模板系统
+
+## 🔧 配置参考
+
+### 适配器配置
+
+```yaml
+adapters:
+  openai: "OpenAIAdapter"      # 用于 OpenAI API
+```
+
+### LLM 配置
+
+```yaml
+llms:
+  model_name:
+    adapter: "adapter_name"
+    api_key: "your_api_key"     # 可以使用 ENV['KEY_NAME']
+    url: "https://api.url"
+    model: "model_identifier"
+    temperature: 0.7
+    # 其他提供商特定选项
+```
+
+### 路径配置
+
+```yaml
+template_path: "./templates"   # .erb 模板目录
+worker_path: "./workers"       # worker 定义目录  
+logger_file: "./logs/app.log"  # 日志文件位置
+```
+
+## 🧪 测试
+
+运行测试套件：
+
+```bash
+bundle exec rake test
+```
+
+开发时，可以使用控制台：
+
+```bash
+bundle exec bin/console
+```
+
+## 🤝 集成示例
+
+### 与 Rails 应用集成
+
+```ruby
+# config/initializers/smart_prompt.rb
+class SmartPromptService
+  def self.engine
+    @engine ||= SmartPrompt::Engine.new(
+      Rails.root.join('config', 'smart_prompt.yml')
+    )
+  end
+  
+  def self.chat(message, context: nil)
+    engine.call_worker(:chat_assistant, {
+      question: message,
+      context: context
+    })
+  end
+end
+
+# 在控制器中使用
+class ChatController < ApplicationController
+  def create
+    response = SmartPromptService.chat(
+      params[:message],
+      context: session[:conversation_context]
+    )
+    
+    render json: { response: response }
+  end
+end
 ```
 
-## 用法
+### 与 Sidekiq 后台任务集成
+
+```ruby
+class LLMProcessingJob < ApplicationJob
+  def perform(task_type, parameters)
+    engine = SmartPrompt::Engine.new('config/smart_prompt.yml')
+    result = engine.call_worker(task_type.to_sym, parameters)
+    
+    # 处理结果...
+    NotificationService.send_completion(result)
+  end
+end
+```
+
+## 🚀 实际应用场景
+
+- **聊天机器人和对话式 AI**: 构建具有上下文感知能力的复杂聊天机器人
+- **内容生成**: 基于模板驱动的提示词进行自动化内容创建  
+- **代码分析**: AI 驱动的代码审查和文档生成
+- **客户支持**: 智能工单路由和响应建议
+- **数据处理**: LLM 驱动的数据提取和转换
+- **教育工具**: AI 导师和学习辅助系统
+
+## 🛣️ 发展路线图
+
+- [ ] 新增 LLM 提供商适配器（Anthropic Claude、Google PaLM）
+- [ ] 可视化提示词构建器和管理界面
+- [ ] 增强缓存和性能优化
+- [ ] 与向量数据库集成，支持 RAG 应用
+- [ ] 内置提示词评估和测试框架
+- [ ] 分布式 worker 执行支持
+
+## 🤝 贡献
+
+我们欢迎贡献！请查看 [CONTRIBUTING.md](CONTRIBUTING.md) 了解指南。
+
+1. Fork 本仓库
+2. 创建你的功能分支（`git checkout -b feature/amazing-feature`）
+3. 提交你的更改（`git commit -am 'Add amazing feature'`）
+4. 推送到分支（`git push origin feature/amazing-feature`）
+5. 开启一个 Pull Request
+
+## 📄 许可证
+
+本项目使用 MIT 许可证 - 详情请查看 [LICENSE.txt](LICENSE.txt) 文件。
+
+## 🙏 致谢
+
+- 由 SmartPrompt 团队用 ❤️ 构建
+- 受到在 Ruby 应用中优雅集成 LLM 需求的启发
+- 感谢所有贡献者和 Ruby 社区
+
+## 📞 支持
+
+- 📖 [文档](https://github.com/zhuangbiaowei/smart_prompt/wiki)
+- 🐛 [问题追踪](https://github.com/zhuangbiaowei/smart_prompt/issues)
+- 💬 [讨论区](https://github.com/zhuangbiaowei/smart_prompt/discussions)
+- 📧 邮箱：zbw@kaiyuanshe.org
+
+---
 
-更多示例请看项目 [SmartPromptDemo](https://github.com/zhuangbiaowei/SmartPromptDemo)
+**SmartPrompt** - 让 Ruby 应用中的 LLM 集成变得简单、强大且优雅。

data/README.md

@@ -2,28 +2,393 @@ EN | [中文](./README.cn.md)
 
 # SmartPrompt
 
-SmartPrompt is a powerful Ruby gem that provides a domain-specific language (DSL), enabling other Ruby programs to conveniently and naturally call upon the capabilities of various large language models (LLMs).
+[![Gem Version](https://badge.fury.io/rb/smart_prompt.svg)](https://badge.fury.io/rb/smart_prompt)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-## Key Features
+SmartPrompt is a powerful Ruby gem that provides an elegant domain-specific language (DSL) for building intelligent applications with Large Language Models (LLMs). It enables Ruby programs to seamlessly interact with various LLM providers while maintaining clean, composable, and highly customizable code architecture.
 
-- Flexible task composition: Combine various tasks using specific service providers + specific LLMs + specific prompts
-- Nested subtasks: Support for composing and calling other subtasks in DSL form
-- Performance optimization: Provide performance-optimal or cost-effective solutions while ensuring quality
+## 🚀 Key Features
 
-## Installation
+### Multi-LLM Support
+- **OpenAI API Compatible**: Full support for OpenAI GPT models and compatible APIs
+- **Llama.cpp Integration**: Direct integration with local Llama.cpp servers  
+- **Extensible Adapters**: Easy-to-extend adapter system for new LLM providers
+- **Unified Interface**: Same API regardless of the underlying LLM provider
 
-To install the gem and add it to your application's Gemfile, execute the following command:
+### Flexible Architecture
+- **Worker-based Tasks**: Define reusable workers for specific AI tasks
+- **Template System**: ERB-based prompt templates with parameter injection
+- **Conversation Management**: Built-in conversation history and context management
+- **Streaming Support**: Real-time response streaming for better user experience
 
+### Advanced Features
+- **Tool Calling**: Native support for function calling and tool integration
+- **Retry Logic**: Robust error handling with configurable retry mechanisms
+- **Embeddings**: Text embedding generation for semantic search and RAG applications
+- **Configuration-driven**: YAML-based configuration for easy deployment management
+
+### Production Ready
+- **Comprehensive Logging**: Detailed logging for debugging and monitoring
+- **Error Handling**: Graceful error handling with custom exception types  
+- **Performance Optimized**: Efficient resource usage and response caching
+- **Thread Safe**: Safe for concurrent usage in multi-threaded applications
+
+## 📦 Installation
+
+Add to your Gemfile:
+
+```ruby
+gem 'smart_prompt'
+```
+
+Then execute:
+```bash
+$ bundle install
+```
+
+Or install directly:
+```bash
+$ gem install smart_prompt
+```
+
+## 🛠️ Quick Start
+
+### 1. Configuration
+
+Create a YAML configuration file (`config/smart_prompt.yml`):
+
+```yaml
+# Adapter definitions
+adapters:
+  openai: OpenAIAdapter
+# LLM configurations
+llms:
+  SiliconFlow:
+    adapter: openai
+    url: https://api.siliconflow.cn/v1/
+    api_key: ENV["APIKey"]
+    default_model: Qwen/Qwen2.5-7B-Instruct
+  llamacpp:
+    adapter: openai
+    url: http://localhost:8080/    
+  ollama:
+    adapter: openai
+    url: http://localhost:11434/
+    default_model: deepseek-r1
+  deepseek:
+    adapter: openai
+    url: https://api.deepseek.com
+    api_key: ENV["DSKEY"]
+    default_model: deepseek-reasoner
+
+# Default settings
+default_llm: SiliconFlow
+template_path: "./templates"
+worker_path: "./workers"
+logger_file: "./logs/smart_prompt.log"
 ```
-$ bundle add smart_prompt
+
+### 2. Create Prompt Templates
+
+Create template files in your `templates/` directory:
+
+**templates/chat.erb**:
+```erb
+You are a helpful assistant. Please respond to the following question:
+
+Question: <%= question %>
+
+Context: <%= context || "No additional context provided" %>
 ```
 
-If you don't use a bundler to manage dependencies, you can install the gem by executing the following command:
+### 3. Define Workers
 
+Create worker files in your `workers/` directory:
+
+**workers/chat_worker.rb**:
+```ruby
+SmartPrompt.define_worker :chat_assistant do
+  # Use a specific LLM
+  use "SiliconFlow"
+  model "deepseek-ai/DeepSeek-V3"
+  # Set system message
+  sys_msg("You are a helpful AI assistant.", params)
+  # Use template with parameters  
+  prompt(:chat, {
+    question: params[:question],
+    context: params[:context]
+  })
+  # Send message and return response
+  send_msg
+end
 ```
-$ gem install smart_prompt
+
+### 4. Use in Your Application
+
+```ruby
+require 'smart_prompt'
+
+# Initialize engine with config
+engine = SmartPrompt::Engine.new('config/smart_prompt.yml')
+
+# Execute worker
+result = engine.call_worker(:chat_assistant, {
+  question: "What is machine learning?",
+  context: "We're discussing AI technologies"
+})
+
+puts result
+```
+
+## 📚 Advanced Usage
+
+### Streaming Responses
+
+```ruby
+# Define streaming worker
+SmartPrompt.define_worker :streaming_chat do
+  use "deepseek"
+  model "deepseek-chat"
+  sys_msg("You are a helpful assistant.")
+  prompt(params[:message])
+  send_msg
+end
+
+# Use with streaming
+engine.call_worker_by_stream(:streaming_chat, {
+  message: "Tell me a story"
+}) do |chunk, bytesize|
+  print chunk.dig("choices", 0, "delta", "content")
+end
+```
+
+### Tool Integration
+
+```ruby
+# Define worker with tools
+SmartPrompt.define_worker :assistant_with_tools do
+  use "SiliconFlow"
+  model "Qwen/Qwen3-235B-A22B"
+  tools = [
+    {
+      type: "function",
+      function: {
+        name: "get_weather",
+        description: "Get weather information for a location",
+        parameters: {
+          type: "object",
+          properties: {
+            location: {
+              type: "string", 
+              description: "The city and state"
+            }
+          },
+          required: ["location"]
+        }
+      }
+    }
+  ]
+  
+  sys_msg("You can help with weather queries using available tools.", params)
+  prompt(params[:message])
+  params.merge(tools: tools)
+  send_msg
+end
+```
+
+### Conversation History
+
+```ruby
+SmartPrompt.define_worker :conversational_chat do
+  use "deepseek"
+  model "deepseek-chat"
+  sys_msg("You are a helpful assistant that remembers conversation context.")
+  prompt(params[:message], with_history: true)
+  send_msg
+end
 ```
 
-## Usage
+### Embeddings Generation
+
+```ruby
+SmartPrompt.define_worker :text_embedder do
+  use "SiliconFlow"
+  model "BAAI/bge-m3"
+  prompt params[:text]  
+  embeddings(params[:dimensions] || 1024)
+end
+
+# Usage
+embeddings = engine.call_worker(:text_embedder, {
+  text: "Convert this text to embeddings",
+  dimensions: 1024
+})
+```
+
+## 🏗️ Architecture Overview
+
+SmartPrompt follows a modular architecture:
+
+```
+┌─────────────────┐    ┌──────────────────┐    ┌─────────────────┐
+│   Application   │    │   SmartPrompt    │    │   LLM Provider  │
+│                 │◄──►│     Engine       │◄──►│   (OpenAI/      │
+│                 │    │                  │    │    Llama.cpp)   │
+└─────────────────┘    └──────────────────┘    └─────────────────┘
+                                │
+                       ┌────────┼────────┐
+                       │        │        │
+                   ┌───▼───┐ ┌──▼──┐ ┌───▼────┐
+                   │Workers│ │Conv.│ │Template│
+                   │       │ │Mgmt │ │ System │
+                   └───────┘ └─────┘ └────────┘
+```
+
+### Core Components
+
+- **Engine**: Central orchestrator managing configuration, adapters, and workers
+- **Workers**: Reusable task definitions with embedded business logic
+- **Conversation**: Context and message history management
+- **Adapters**: LLM provider integrations (OpenAI, Llama.cpp, etc.)
+- **Templates**: ERB-based prompt template system
+
+## 🔧 Configuration Reference
+
+### Adapter Configuration
+
+```yaml
+adapters:
+  openai: "OpenAIAdapter"      # For OpenAI API
+```
+
+### LLM Configuration
+
+```yaml
+llms:
+  model_name:
+    adapter: "adapter_name"
+    api_key: "your_api_key"     # Can use ENV['KEY_NAME']
+    url: "https://api.url"
+    model: "model_identifier"
+    temperature: 0.7
+    # Additional provider-specific options
+```
+
+### Path Configuration
+
+```yaml
+template_path: "./templates"   # Directory for .erb templates
+worker_path: "./workers"       # Directory for worker definitions  
+logger_file: "./logs/app.log"  # Log file location
+```
+
+## 🧪 Testing
+
+Run the test suite:
+
+```bash
+bundle exec rake test
+```
+
+For development, you can use the console:
+
+```bash
+bundle exec bin/console
+```
+
+## 🤝 Integration Examples
+
+### With Rails Applications
+
+```ruby
+# config/initializers/smart_prompt.rb
+class SmartPromptService
+  def self.engine
+    @engine ||= SmartPrompt::Engine.new(
+      Rails.root.join('config', 'smart_prompt.yml')
+    )
+  end
+  
+  def self.chat(message, context: nil)
+    engine.call_worker(:chat_assistant, {
+      question: message,
+      context: context
+    })
+  end
+end
+
+# In your controller
+class ChatController < ApplicationController
+  def create
+    response = SmartPromptService.chat(
+      params[:message],
+      context: session[:conversation_context]
+    )
+    
+    render json: { response: response }
+  end
+end
+```
+
+### With Sidekiq Background Jobs
+
+```ruby
+class LLMProcessingJob < ApplicationJob
+  def perform(task_type, parameters)
+    engine = SmartPrompt::Engine.new('config/smart_prompt.yml')
+    result = engine.call_worker(task_type.to_sym, parameters)
+    
+    # Process result...
+    NotificationService.send_completion(result)
+  end
+end
+```
+
+## 🚀 Real-world Use Cases
+
+- **Chatbots and Conversational AI**: Build sophisticated chatbots with context awareness
+- **Content Generation**: Automated content creation with template-driven prompts  
+- **Code Analysis**: AI-powered code review and documentation generation
+- **Customer Support**: Intelligent ticket routing and response suggestions
+- **Data Processing**: LLM-powered data extraction and transformation
+- **Educational Tools**: AI tutors and learning assistance systems
+
+## 🛣️ Roadmap
+
+- [ ] Additional LLM provider adapters (Anthropic Claude, Google PaLM)
+- [ ] Visual prompt builder and management interface
+- [ ] Enhanced caching and performance optimizations
+- [ ] Integration with vector databases for RAG applications
+- [ ] Built-in evaluation and testing framework for prompts
+- [ ] Distributed worker execution support
+
+## 🤝 Contributing
+
+We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+
+1. Fork the repository
+2. Create your feature branch (`git checkout -b feature/amazing-feature`)
+3. Commit your changes (`git commit -am 'Add amazing feature'`)
+4. Push to the branch (`git push origin feature/amazing-feature`)
+5. Open a Pull Request
+
+## 📄 License
+
+This project is licensed under the MIT License - see the [LICENSE.txt](LICENSE.txt) file for details.
+
+## 🙏 Acknowledgments
+
+- Built with ❤️ by the SmartPrompt team
+- Inspired by the need for elegant LLM integration in Ruby applications
+- Thanks to all contributors and the Ruby community
+
+## 📞 Support
+
+- 📖 [Documentation](https://github.com/zhuangbiaowei/smart_prompt/wiki)
+- 🐛 [Issue Tracker](https://github.com/zhuangbiaowei/smart_prompt/issues)
+- 💬 [Discussions](https://github.com/zhuangbiaowei/smart_prompt/discussions)
+- 📧 Email: zbw@kaiyuanshe.org
+
+---
 
-See project [SmartPromptDemo](https://github.com/zhuangbiaowei/SmartPromptDemo) for more examples.
+**SmartPrompt** - Making LLM integration in Ruby applications simple, powerful, and elegant.

data/lib/smart_prompt/conversation.rb

@@ -6,6 +6,7 @@ module SmartPrompt
   class Conversation
     include APIHandler
     attr_reader :messages, :last_response, :config_file
+    attr_reader :last_call_id
 
     def initialize(engine, tools = nil)
       SmartPrompt.logger.info "Create Conversation"
@@ -13,7 +14,9 @@ module SmartPrompt
       @engine = engine
       @adapters = engine.adapters
       @llms = engine.llms
+      @current_llm_name = nil
       @templates = engine.templates
+      @temperature = 0.7
       @current_adapter = engine.current_adapter
       @last_response = nil
       @tools = tools
@@ -22,11 +25,15 @@ module SmartPrompt
     def use(llm_name)
       raise "Adapter #{adapter_name} not configured" unless @llms.key?(llm_name)
       @current_llm = @llms[llm_name]
+      @current_llm_name = llm_name
       self
     end
 
     def model(model_name)
       @model_name = model_name
+      if @engine.config["better_prompt_db"]
+        BetterPrompt.add_model(@current_llm_name, @model_name)
+      end
     end
 
     def temperature(temperature)
@@ -51,9 +58,15 @@ module SmartPrompt
         raise "Template #{template_name} not found" unless @templates.key?(template_name)
         content = @templates[template_name].render(params)
         add_message({ role: "user", content: content }, with_history)
+        if @engine.config["better_prompt_db"]
+          BetterPrompt.add_prompt(template_name, "user", content)
+        end
         self
       else
         add_message({ role: "user", content: template_name }, with_history)
+        if @engine.config["better_prompt_db"]
+          BetterPrompt.add_prompt("NULL", "user", template_name)
+        end
         self
       end
     end
@@ -61,6 +74,9 @@ module SmartPrompt
     def sys_msg(message, params)
       @sys_msg = message
       add_message({ role: "system", content: message }, params[:with_history])
+      if @engine.config["better_prompt_db"]
+        BetterPrompt.add_prompt("NULL", "system", message)
+      end
       self
     end
 
@@ -75,6 +91,13 @@ module SmartPrompt
     def send_msg(params = {})
       Retriable.retriable(RETRY_OPTIONS) do
         raise ConfigurationError, "No LLM selected" if @current_llm.nil?
+        if @engine.config["better_prompt_db"]
+          if params[:with_history]
+            @last_call_id = BetterPrompt.add_model_call(@current_llm_name, @model_name, history_messages, false, @temperature, 0, 0.0, 0, @tools)
+          else
+            @last_call_id = BetterPrompt.add_model_call(@current_llm_name, @model_name, @messages, false, @temperature, 0, 0.0, 0, @tools)
+          end
+        end
         if params[:with_history]
           @last_response = @current_llm.send_request(history_messages, @model_name, @temperature, @tools, nil)
         else
@@ -83,6 +106,9 @@ module SmartPrompt
         if @last_response == ""
           @last_response = @current_llm.last_response
         end
+        if @engine.config["better_prompt_db"]
+          BetterPrompt.add_response(@last_call_id, @last_response, false)
+        end
         @messages = []
         @messages << { role: "system", content: @sys_msg }
         @last_response
@@ -94,11 +120,21 @@ module SmartPrompt
     def send_msg_by_stream(params = {}, &proc)
       Retriable.retriable(RETRY_OPTIONS) do
         raise ConfigurationError, "No LLM selected" if @current_llm.nil?
+        if @engine.config["better_prompt_db"]
+          if params[:with_history]
+            @last_call_id = BetterPrompt.add_model_call(@current_llm_name, @model_name, history_messages, true, @temperature, 0, 0.0, 0, @tools)
+          else
+            @last_call_id = BetterPrompt.add_model_call(@current_llm_name, @model_name, @messages, true, @temperature, 0, 0.0, 0, @tools)
+          end
+        end
         if params[:with_history]
           @current_llm.send_request(history_messages, @model_name, @temperature, @tools, proc)
         else
           @current_llm.send_request(@messages, @model_name, @temperature, @tools, proc)
         end
+        if @engine.config["better_prompt_db"]
+          BetterPrompt.add_response(@last_call_id, @engine.stream_response, true)
+        end
         @messages = []
         @messages << { role: "system", content: @sys_msg }
       end

data/lib/smart_prompt/engine.rb

@@ -64,6 +64,10 @@ module SmartPrompt
           SmartPrompt.logger = Logger.new(@config["logger_file"])
         end
         SmartPrompt.logger.info "Loading configuration from file: #{config_file}"
+        if @config["better_prompt_db"]
+          require "better_prompt"
+          BetterPrompt.setup(db_path: @config["better_prompt_db"])
+        end
         @config["adapters"].each do |adapter_name, adapter_class|
           adapter_class = SmartPrompt.const_get(adapter_class)
           @adapters[adapter_name] = adapter_class

data/lib/smart_prompt/version.rb

@@ -1,3 +1,3 @@
 module SmartPrompt
-  VERSION = "0.3.2"
+  VERSION = "0.3.3"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: smart_prompt
 version: !ruby/object:Gem::Version
-  version: 0.3.2
+  version: 0.3.3
 platform: ruby
 authors:
 - zhuang biaowei
@@ -137,7 +137,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.8
+rubygems_version: 3.6.9
 specification_version: 4
 summary: A smart prompt management and LLM interaction gem
 test_files: []