@bernierllc/ai-professor-harmanic (英语)

Anthropic Claude API 适配器 执行统一的 AI 提供者接口 @bernierllc/ai-provider-core。 。 。 .

特征

• 所有克洛德3型号:全力支持奥普斯,索内特和海库
• 流线: 基于 Async 生成器的流式完成
• 远景分析: 图像分析, 所有 Claude 3 模型
• 扩展上下文: 支持 200K 令牌上下文窗口
• 费用估计数: 准确计算成本,并按具体模式定价
• 类型脚本: 严格模式的完整类型安全
• 处理错误: 全面处理重试支持错误

安装

npm install @bernierllc/ai-provider-anthropic

基本用途

import { AnthropicProvider } from '@bernierllc/ai-provider-anthropic';

const provider = new AnthropicProvider({
  providerName: 'anthropic',
  apiKey: process.env.ANTHROPIC_API_KEY!,
  defaultModel: 'claude-3-opus-20240229'
});

// Generate completion
const response = await provider.complete({
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Explain TypeScript generics in simple terms.' }
  ],
  maxTokens: 500,
  temperature: 0.7
});

if (response.success) {
  console.log(response.content);
  console.log(`Tokens used: ${response.usage?.totalTokens}`);
}

API 参考

构造器

new AnthropicProvider(config: AnthropicProviderConfig)

配置选项 :

• providerName: 必须是 'anthropic'
• apiKey: Anthropic API 键(需要)
• defaultModel: 要使用的默认模式( 可选, 默认为 claude-3-opus-20240229(中文(简体) )
• baseURL: 自定义 API 基础 URL (可选)
• timeout: 请求超时以毫秒计( 可选, 默认为6000)
• maxRetries: 最多重试次数(可选,默认为3)

方法

complete(request: CompletionRequest): Promise<CompletionResponse>

生成文本补全 .

const response = await provider.complete({
  messages: [
    { role: 'user', content: 'Hello!' }
  ],
  maxTokens: 100,
  temperature: 0.7
});

streamComplete(request: CompletionRequest): AsyncGenerator<StreamChunk>

生成流式文本补全 .

for await (const chunk of provider.streamComplete({
  messages: [
    { role: 'user', content: 'Write a short poem about coding' }
  ]
})) {
  process.stdout.write(chunk.delta);

  if (chunk.finishReason) {
    console.log(`\n\nFinished: ${chunk.finishReason}`);
  }
}

analyzeImage(imageData, prompt, model?, maxTokens?, temperature?): Promise<CompletionResponse>

利用克洛德的视觉能力分析一幅图像.

const imageBuffer = fs.readFileSync('diagram.png');

const analysis = await provider.analyzeImage(
  imageBuffer,
  'Describe this architecture diagram in detail',
  'claude-3-opus-20240229'
);

if (analysis.success) {
  console.log(analysis.content);
}

extendedContextCompletion(request): Promise<CompletionResponse>

扩展上下文处理请求( 200K 令牌) .

const longDocument = fs.readFileSync('very-long-document.txt', 'utf-8');

const response = await provider.extendedContextCompletion({
  messages: [
    { role: 'user', content: `Summarize this document:\n\n${longDocument}` }
  ],
  enableExtendedContext: true
});

estimateCost(request: CompletionRequest): CostEstimate

在发出请求之前估计请求的费用.

const cost = provider.estimateCost({
  messages: [{ role: 'user', content: 'Hello world!' }],
  model: 'claude-3-opus-20240229',
  maxTokens: 100
});

console.log(`Estimated cost: $${cost.estimatedCostUSD.toFixed(4)}`);

getAvailableModels(): Promise<ModelInfo[]>

获取所有可用的克洛德模型的信息.

const models = await provider.getAvailableModels();

models.forEach(model => {
  console.log(`${model.name}: ${model.contextWindow} tokens`);
});

checkHealth(): Promise<HealthStatus>

请检查authropic API是否可用 .

const health = await provider.checkHealth();

if (health.status === 'healthy') {
  console.log(`API is healthy (latency: ${health.latency}ms)`);
}

可用模式

所有模型支持 :

• 文本补全
• 流线
• 远景分析
• 扩展上下文( 200K 令牌)

处理错误

提供者返回结构化错误响应 :

const response = await provider.complete({
  messages: [{ role: 'user', content: 'Test' }]
});

if (!response.success) {
  console.error('Error:', response.error);
}

限制

嵌入层

Anthropic 不提供嵌入式API. 使用 @bernierllc/ai-provider-openai 用于嵌入的:

const embeddingResponse = await provider.generateEmbeddings({
  input: 'test text'
});

// Returns: { success: false, error: 'Anthropic does not provide an embeddings API...' }

内容调和

Claude有内在的安全特征(宪法AI),所以不需要单独的节制API:

const moderation = await provider.moderate('content');

// Always returns: { success: true, flagged: false, ... }

一体化状况

• 锁定器: QQ综合 - 用途 @bernierllc/logger 错误记录
• 多克套装: QQ 准备 - 完整类型Doc/JSDoc 文档
• 从不:QQ 可选 - 可用于监测和衡量标准

高级使用

模型比较

const models = await provider.getAvailableModels();

models.forEach(model => {
  console.log(`${model.name}:`);
  console.log(`  Context: ${model.contextWindow.toLocaleString()} tokens`);
  console.log(`  Capabilities: ${model.capabilities.join(', ')}`);
  if (model.pricing) {
    console.log(`  Input: $${model.pricing.inputPricePerToken * 1000000}/M tokens`);
    console.log(`  Output: $${model.pricing.outputPricePerToken * 1000000}/M tokens`);
  }
});

复杂的原因任务

// Claude excels at complex reasoning and analysis
const response = await provider.complete({
  messages: [
    {
      role: 'user',
      content: `Analyze this code architecture and suggest improvements:

[Large codebase content...]

Consider: scalability, maintainability, security, performance`
    }
  ],
  model: 'claude-3-opus-20240229',
  maxTokens: 4096,
  temperature: 0.3 // Lower temperature for analytical tasks
});

具有多图像的视野

// Analyze multiple images in sequence
const images = ['image1.png', 'image2.png', 'image3.png'];

for (const imagePath of images) {
  const imageBuffer = fs.readFileSync(imagePath);

  const analysis = await provider.analyzeImage(
    imageBuffer,
    'What do you see in this image?'
  );

  console.log(`${imagePath}: ${analysis.content}`);
}

类型脚本

import type {
  AnthropicProviderConfig,
  AnthropicVisionRequest,
  AnthropicExtendedContextRequest
} from '@bernierllc/ai-provider-anthropic';

import type {
  CompletionRequest,
  CompletionResponse,
  StreamChunk,
  ModelInfo,
  HealthStatus,
  CostEstimate
} from '@bernierllc/ai-provider-core';

许可证

版权(c)2025 Bernier有限责任公司。 版权所有.

另见

• @bernierllc/ai-professor-core (英语) - 摘要提供者接口
• @bernierllc/ai-propei 提供商-openai - OpenAI 供应商执行
• @bernierllc/retry-policy (英语) - 重试此软件包所用的逻辑
• @ bernierllc/ 拖放器 - 这个软件包使用的日志