Valyu API 最佳实践指南：搜索、内容提取、AI 答案与深度研究

valyu-best-practices by valyuai/skills

653 周安装量

12 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/valyuai/skills --skill valyu-best-practices

AI/机器学习自动化 API

🇨🇳中文介绍

Valyu 最佳实践

本技能提供了使用 Valyu API 执行搜索、内容提取、AI 驱动答案和深度研究任务的指南。

快速参考：选择合适的 API

使用此决策树选择适当的 Valyu API：

What do you need?

├─ Find information across multiple sources
│  └─ Use Search API
│
├─ Extract content from specific URLs
│  └─ Use Contents API
│
├─ Get an AI-synthesized answer with citations
│  └─ Use Answer API
│
├─ Generate a comprehensive research report
│  └─ Use DeepResearch API
│
└─ Discover available data sources
   └─ Use Datasources API

⚠️ 强制要求：使用官方 Valyu SDK 库

关键：编写使用 Valyu API 的代码时，必须使用官方 SDK 库。切勿直接向 Valyu API 端点发起原始的 HTTP/fetch 调用。

JavaScript/TypeScript: `valyu-js`

npm install valyu-js
# or
pnpm add valyu-js



import { Valyu } from 'valyu-js';

const valyu = new Valyu(process.env.VALYU_API_KEY);

// Now use valyu.search(), valyu.contents(), valyu.answer(), valyu.deepResearch

Python: `valyu`

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

为什么使用 SDK 而非原始 API 调用？

类型安全 - 所有参数和响应都有完整的 TypeScript/Python 类型提示
自动重试 - 内置针对瞬时故障的重试逻辑
流式支持 - 对流式响应提供适当的异步迭代器支持
错误处理 - 结构化的错误类型和有用的消息
未来兼容性 - SDK 更新会自动处理 API 变更

// DON'T make raw fetch calls
const response = await fetch('https://api.valyu.ai/v1/search', {
  method: 'POST',
  headers: {
    'x-api-key': apiKey,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({ query: '...' })
});

// DO use the SDK
import { Valyu } from 'valyu-js';

const valyu = new Valyu(process.env.VALYU_API_KEY);
const response = await valyu.search({ query: '...' });

用途： 在网页、学术、医疗、交通、金融、新闻和专有来源中查找信息。

查找任何主题的最新信息
学术研究（arXiv、PubMed、bioRxiv、medRxiv）
金融数据（SEC 文件、财报、股票数据）
新闻监测和时事
医疗保健数据（临床试验、药品标签）
预测市场（Polymarket、Kalshi）
交通（英国国家铁路、全球航运）

const response = await valyu.search({
  query: "transformer architecture attention mechanism 2024",
  searchType: "all",
  maxNumResults: 10
});

类型	用于
`all`	所有内容 - 网页、学术、金融、专有
`web`	仅通用互联网内容
`proprietary`	授权的学术论文和研究
`news`	新闻文章和时事

参数 (TS/JS)	参数 (Python)	用途	示例
`query`	`query`	搜索查询（少于 400 字符）	`"CRISPR gene editing 2024"`
`searchType`	`search_type`	来源范围	`"all"`, `"web"`, `"proprietary"`, `"news"`
`maxNumResults`	`max_num_results`	结果数量 (1-20)	`10`
`includedSources`	`included_sources`	限制为特定来源	`["valyu/valyu-arxiv", "valyu/valyu-pubmed"]`
`startDate` / `endDate`	`start_date` / `end_date`	日期过滤	`"2024-01-01"`
`relevanceThreshold`	`relevance_threshold`	最小相关性 (0-1)	`0.7`

特定领域搜索模式

await valyu.search({
  query: "CRISPR therapeutic applications clinical trials",
  searchType: "proprietary",
  includedSources: ["valyu/valyu-arxiv", "valyu/valyu-pubmed", "valyu/valyu-biorxiv"],
  startDate: "2024-01-01"
});

await valyu.search({
  query: "Apple revenue Q4 2024 earnings",
  searchType: "all",
  includedSources: ["valyu/valyu-sec-filings", "valyu/valyu-earnings-US"]
});

await valyu.search({
  query: "AI regulation EU",
  searchType: "news",
  startDate: "2024-06-01",
  countryCode: "EU"
});

有关详细模式，请参阅：

用途： 从网页中提取干净、结构化的内容，并针对 LLM 处理进行优化。

将网页转换为干净的 Markdown
提取文章文本用于摘要生成
为 RAG 系统解析文档
从产品页面提取结构化数据
处理学术论文

const response = await valyu.contents({
  urls: ["https://example.com/article"]
});

const response = await valyu.contents({
  urls: ["https://arxiv.org/abs/2401.12345"],
  summary: "Extract key findings in 3 bullet points"
});

结构化提取（JSON 模式）

const response = await valyu.contents({
  urls: ["https://example.com/product"],
  summary: {
    type: "object",
    properties: {
      product_name: { type: "string" },
      price: { type: "number" },
      features: { type: "array", items: { type: "string" } }
    },
    required: ["product_name", "price"]
  }
});

参数 (TS/JS)	参数 (Python)	用途	示例
`urls`	`urls`	要处理的 URL (1-10)	`["https://example.com"]`
`responseLength`	`response_length`	内容长度	`"short"`, `"medium"`, `"large"`, `"max"`
`extractEffort`	`extract_effort`	提取质量	`"normal"`, `"high"`, `"auto"`
`summary`	`summary`	AI 摘要生成	`true`, `"instructions"`, 或 JSON 模式
`screenshot`	`screenshot`	捕获屏幕截图	`true`

有关详细模式，请参阅：

用途： 获取基于实时搜索结果、带有引用的 AI 驱动答案。

需要当前信息综合的问题
多来源事实核查
技术文档问题
需要引用来源的研究
从搜索结果中提取结构化数据

const response = await valyu.answer({
  query: "What are the latest developments in quantum computing?"
});

使用快速模式（更低延迟）

const response = await valyu.answer({
  query: "Current Bitcoin price and 24h change",
  fastMode: true
});

使用自定义指令

const response = await valyu.answer({
  query: "Compare React and Vue for enterprise applications",
  systemInstructions: "Provide a balanced comparison with pros and cons. Format as a comparison table."
});

const stream = await valyu.answer({
  query: "Explain transformer architecture",
  streaming: true
});

for await (const chunk of stream) {
  // Handle: search_results, content, metadata, done, error
  console.log(chunk);
}

const response = await valyu.answer({
  query: "Apple Q4 2024 financial highlights",
  structuredOutput: {
    type: "object",
    properties: {
      revenue: { type: "string" },
      growthRate: { type: "string" },
      keyHighlights: { type: "array", items: { type: "string" } }
    }
  }
});

参数 (TS/JS)	参数 (Python)	用途	示例
`query`	`query`	要回答的问题	`"What is quantum computing?"`
`fastMode`	`fast_mode`	更低延迟	`true`
`systemInstructions`	`system_instructions`	AI 指令	`"Be concise"`
`structuredOutput`	`structured_output`	JSON 模式	`{type: "object", ...}`
`streaming`	`streaming`	启用 SSE 流式传输	`true`
`dataMaxPrice`	`data_max_price`	美元限制	`1.0`

有关详细模式，请参阅：

用途： 生成包含详细分析和引用的全面研究报告。

全面的市场分析
文献综述
竞争情报
技术深度剖析
需要多来源综合的主题

模式	持续时间	最适合
`fast`	~5 分钟	快速查找、简单问题
`standard`	~10-20 分钟	平衡的研究（最常见）
`heavy`	~90 分钟	全面分析、复杂主题

const task = await valyu.deepResearch.create({
  query: "AI chip market competitive landscape 2024",
  model: "standard"
});
// Returns: { deepresearch_id: "abc123", status: "queued" }

const status = await valyu.deepResearch.getStatus(task.deepresearch_id);
// status: "queued" | "running" | "completed" | "failed" | "cancelled"

if (status.status === "completed") {
  console.log(status.output);  // Markdown report
  console.log(status.sources); // Cited sources
  console.log(status.pdf_url); // PDF download link
}

参数 (TS/JS)	参数 (Python)	用途	示例
`query`	`query`	研究问题	`"AI market trends 2024"`
`model`	`model`	研究深度	`"fast"`, `"standard"`, `"heavy"`
`outputFormat`	`output_format`	报告格式	`"markdown"`, `"pdf"`
`includedSources`	`included_sources`	来源过滤	`["valyu/valyu-arxiv", "techcrunch.com"]`
`startDate` / `endDate`	`start_date` / `end_date`	日期范围	`"2024-01-01"`

有关详细模式，请参阅：

5. 查询编写最佳实践

具体明确 - 使用领域术语
简洁明了 - 查询保持在 400 字符以内
重点突出 - 每个查询一个主题
添加约束 - 包含时间范围、来源类型

元素	描述	示例
意图	你需要什么	"最新进展" vs "概述"
领域	主题术语	"transformer architecture"
约束	过滤器	"2024", "peer-reviewed"
来源类型	在哪里查找	学术论文、SEC 文件

好查询与坏查询

BAD:  "I want to know about AI"
GOOD: "transformer attention mechanism survey 2024"

BAD:  "Apple financial information"
GOOD: "Apple revenue growth Q4 2024 earnings SEC filing"

BAD:  "gene editing research"
GOOD: "CRISPR off-target effects therapeutic applications 2024"

# Don't do this
"Tesla stock performance, new products, and Elon Musk statements"

# Do this instead
Query 1: "Tesla stock performance Q4 2024"
Query 2: "Tesla Cybertruck production updates 2024"
Query 3: "Tesla FSD autonomous driving progress"

使用 includedSources 获取领域权威来源：金融研究集合。可包含的一些来源：

valyu/valyu-sec-filings - SEC 监管文件
valyu/valyu-stocks - 股票市场数据
valyu/valyu-earnings-US - 财报
reuters.com - 金融新闻
bloomberg.com - 市场分析医学研究集合。可包含的一些来源：
valyu/valyu-pubmed - 医学文献
valyu/valyu-clinical-trials - 临床试验数据
valyu/valyu-drug-labels - FDA 药品信息
nejm.org - 新英格兰医学杂志
thelancet.com - 柳叶刀技术文档集合。可包含的一些来源：
docs.aws.amazon.com - AWS 文档
cloud.google.com/docs - Google Cloud 文档
learn.microsoft.com - Microsoft 文档
kubernetes.io/docs - Kubernetes 文档
developer.mozilla.org - MDN Web 文档

// Academic includedSources: ["valyu/valyu-arxiv", "valyu/valyu-pubmed", "nature"]

// Financial includedSources: ["valyu/valyu-sec-filings", "bloomberg.com", "reuters.com"]

// Tech news includedSources: ["techcrunch.com", "theverge.com", "arstechnica.com"]

完整的提示指南，请参阅 references/prompting.md。

// 1. Quick search to find sources
const searchResults = await valyu.search({
  query: "CRISPR therapeutic applications",
  searchType: "proprietary",
  maxNumResults: 20
});

// 2. Extract key content from top results
const contents = await valyu.contents({
  urls: searchResults.results.slice(0, 3).map(r => r.url),
  summary: "Extract key findings"
});

// 3. Deep analysis for comprehensive report
const research = await valyu.deepResearch.create({
  query: "CRISPR therapeutic applications comprehensive review",
  model: "heavy"
});

财务分析工作流

// 1. Get SEC filings
const filings = await valyu.search({
  query: "Apple 10-K 2024",
  includedSources: ["valyu/valyu-sec-filings"]
});

// 2. Quick synthesis
const summary = await valyu.answer({
  query: "Apple Q4 2024 financial highlights",
  fastMode: true
});

// 3. Structured extraction
const metrics = await valyu.answer({
  query: "Apple financial metrics 2024",
  structuredOutput: {
    type: "object",
    properties: {
      revenue: { type: "string" },
      netIncome: { type: "string" },
      growthRate: { type: "string" }
    }
  }
});

Valyu 提供对 25+ 个专业数据集的访问：

类别	示例
学术	arXiv (250万+ 论文), PubMed (3700万+), bioRxiv, medRxiv
金融	SEC 文件, 财报电话会议记录, 股票数据, 加密货币
医疗保健	临床试验, DailyMed, PubChem, 药品标签, ChEMBL, DrugBank, Open Target, WHO ICD
经济	FRED, BLS, 世界银行, 美国财政部, Destatis
预测	Polymarket, Kalshi
专利	美国专利数据库
交通	英国铁路, 船舶追踪

完整的数据源参考，请参阅 references/datasources.md。

完整的 API 文档，包括所有参数、响应结构和错误代码，请参阅 references/api-guide.md。

特定平台的集成文档：

🇺🇸English

Valyu Best Practices

This skill provides instructions for using the Valyu API to perform search, content extraction, AI-powered answers, and deep research tasks.

Quick Reference: Choosing the Right API

Use this decision tree to select the appropriate Valyu API:

What do you need?

├─ Find information across multiple sources
│  └─ Use Search API
│
├─ Extract content from specific URLs
│  └─ Use Contents API
│
├─ Get an AI-synthesized answer with citations
│  └─ Use Answer API
│
├─ Generate a comprehensive research report
│  └─ Use DeepResearch API
│
└─ Discover available data sources
   └─ Use Datasources API

⚠️ MANDATORY: Use Official Valyu SDK Libraries

CRITICAL: When writing code that uses the Valyu API, you MUST use the official SDK libraries. NEVER make raw HTTP/fetch calls to the Valyu API endpoints.

JavaScript/TypeScript: `valyu-js`

npm install valyu-js
# or
pnpm add valyu-js



import { Valyu } from 'valyu-js';

const valyu = new Valyu(process.env.VALYU_API_KEY);

// Now use valyu.search(), valyu.contents(), valyu.answer(), valyu.deepResearch

Python: `valyu`

pip install valyu
# or
uv add valyu



from valyu import Valyu

valyu = Valyu(api_key=os.environ.get("VALYU_API_KEY"))

# Now use valyu.search(), valyu.contents(), valyu.answer(), valyu.deep_research

Why SDK Over Raw API Calls?

Type safety - Full TypeScript/Python type hints for all parameters and responses
Automatic retries - Built-in retry logic for transient failures
Streaming support - Proper async iterator support for streaming responses
Error handling - Structured error types with helpful messages
Future compatibility - SDK updates handle API changes automatically

❌ NEVER Do This

// DON'T make raw fetch calls
const response = await fetch('https://api.valyu.ai/v1/search', {
  method: 'POST',
  headers: {
    'x-api-key': apiKey,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({ query: '...' })
});

✅ Always Do This

// DO use the SDK
import { Valyu } from 'valyu-js';

const valyu = new Valyu(process.env.VALYU_API_KEY);
const response = await valyu.search({ query: '...' });

1. Search API

Purpose: Find information across web, academic, medical, transportation, financial, news, and proprietary sources.

When to Use

Finding recent information on any topic
Academic research (arXiv, PubMed, bioRxiv, medRxiv)
Financial data (SEC filings, earnings reports, stock data)
News monitoring and current events
Healthcare data (clinical trials, drug labels)
Prediction markets (Polymarket, Kalshi)
Transportation (UK National Rail, Global Shipping)

Basic Usage

const response = await valyu.search({
  query: "transformer architecture attention mechanism 2024",
  searchType: "all",
  maxNumResults: 10
});

Search Types

Type	Use For
`all`	Everything - web, academic, financial, proprietary
`web`	General internet content only
`proprietary`	Licensed academic papers and research
`news`	News articles and current events

Key Parameters

Parameter (TS/JS)	Parameter (Python)	Purpose	Example
`query`	`query`	Search query (under 400 chars)	`"CRISPR gene editing 2024"`
`searchType`	`search_type`	Source scope	`"all"`, `"web"`, ,

Domain-Specific Search Patterns

Academic Research:

await valyu.search({
  query: "CRISPR therapeutic applications clinical trials",
  searchType: "proprietary",
  includedSources: ["valyu/valyu-arxiv", "valyu/valyu-pubmed", "valyu/valyu-biorxiv"],
  startDate: "2024-01-01"
});

Financial Analysis:

await valyu.search({
  query: "Apple revenue Q4 2024 earnings",
  searchType: "all",
  includedSources: ["valyu/valyu-sec-filings", "valyu/valyu-earnings-US"]
});

News Monitoring:

await valyu.search({
  query: "AI regulation EU",
  searchType: "news",
  startDate: "2024-06-01",
  countryCode: "EU"
});

Search Recipes

For detailed patterns, see:

2. Contents API

Purpose: Extract clean, structured content from web pages optimized for LLM processing.

When to Use

Converting web pages to clean markdown
Extracting article text for summarization
Parsing documentation for RAG systems
Structured data extraction from product pages
Processing academic papers

Basic Usage

const response = await valyu.contents({
  urls: ["https://example.com/article"]
});

With Summarization

const response = await valyu.contents({
  urls: ["https://arxiv.org/abs/2401.12345"],
  summary: "Extract key findings in 3 bullet points"
});

Structured Extraction (JSON Schema)

const response = await valyu.contents({
  urls: ["https://example.com/product"],
  summary: {
    type: "object",
    properties: {
      product_name: { type: "string" },
      price: { type: "number" },
      features: { type: "array", items: { type: "string" } }
    },
    required: ["product_name", "price"]
  }
});

Key Parameters

Parameter (TS/JS)	Parameter (Python)	Purpose	Example
`urls`	`urls`	URLs to process (1-10)	`["https://example.com"]`
`responseLength`	`response_length`	Content length	`"short"`, `"medium"`, ,

Content Recipes

For detailed patterns, see:

3. Answer API

Purpose: Get AI-powered answers grounded in real-time search results with citations.

When to Use

Questions requiring current information synthesis
Multi-source fact verification
Technical documentation questions
Research requiring cited sources
Structured data extraction from search results

Basic Usage

const response = await valyu.answer({
  query: "What are the latest developments in quantum computing?"
});

With Fast Mode (Lower Latency)

const response = await valyu.answer({
  query: "Current Bitcoin price and 24h change",
  fastMode: true
});

With Custom Instructions

const response = await valyu.answer({
  query: "Compare React and Vue for enterprise applications",
  systemInstructions: "Provide a balanced comparison with pros and cons. Format as a comparison table."
});

With Streaming

const stream = await valyu.answer({
  query: "Explain transformer architecture",
  streaming: true
});

for await (const chunk of stream) {
  // Handle: search_results, content, metadata, done, error
  console.log(chunk);
}

Structured Output

const response = await valyu.answer({
  query: "Apple Q4 2024 financial highlights",
  structuredOutput: {
    type: "object",
    properties: {
      revenue: { type: "string" },
      growthRate: { type: "string" },
      keyHighlights: { type: "array", items: { type: "string" } }
    }
  }
});

Key Parameters

Parameter (TS/JS)	Parameter (Python)	Purpose	Example
`query`	`query`	Question to answer	`"What is quantum computing?"`
`fastMode`	`fast_mode`	Lower latency	`true`
`systemInstructions`

Answer Recipes

For detailed patterns, see:

4. DeepResearch API

Purpose: Generate comprehensive research reports with detailed analysis and citations.

When to Use

Comprehensive market analysis
Literature reviews
Competitive intelligence
Technical deep dives
Topics requiring multi-source synthesis

Research Modes

Mode	Duration	Best For
`fast`	~5 minutes	Quick lookups, simple questions
`standard`	~10-20 minutes	Balanced research (most common)
`heavy`	~90 minutes	Comprehensive analysis, complex topics

Create Research Task

const task = await valyu.deepResearch.create({
  query: "AI chip market competitive landscape 2024",
  model: "standard"
});
// Returns: { deepresearch_id: "abc123", status: "queued" }

Poll for Completion

const status = await valyu.deepResearch.getStatus(task.deepresearch_id);
// status: "queued" | "running" | "completed" | "failed" | "cancelled"

if (status.status === "completed") {
  console.log(status.output);  // Markdown report
  console.log(status.sources); // Cited sources
  console.log(status.pdf_url); // PDF download link
}

Key Parameters

Parameter (TS/JS)	Parameter (Python)	Purpose	Example
`query`	`query`	Research question	`"AI market trends 2024"`
`model`	`model`	Research depth	`"fast"`, `"standard"`,

DeepResearch Recipes

For detailed patterns, see:

5. Query Writing Best Practices

Core Principles

Be specific - Use domain terminology
Be concise - Keep queries under 400 characters
Be focused - One topic per query
Add constraints - Include timeframes, source types

Query Anatomy

Element	Description	Example
Intent	What you need	"latest advancements" vs "overview"
Domain	Topic terminology	"transformer architecture"
Constraints	Filters	"2024", "peer-reviewed"
Source type	Where to look	academic papers, SEC filings

Good vs Bad Queries

BAD:  "I want to know about AI"
GOOD: "transformer attention mechanism survey 2024"

BAD:  "Apple financial information"
GOOD: "Apple revenue growth Q4 2024 earnings SEC filing"

BAD:  "gene editing research"
GOOD: "CRISPR off-target effects therapeutic applications 2024"

Split Complex Requests

# Don't do this
"Tesla stock performance, new products, and Elon Musk statements"

# Do this instead
Query 1: "Tesla stock performance Q4 2024"
Query 2: "Tesla Cybertruck production updates 2024"
Query 3: "Tesla FSD autonomous driving progress"

Source Filtering

Use includedSources for domain authority: Financial Research Collection. Some sources to include:

valyu/valyu-sec-filings - SEC regulatory filings
valyu/valyu-stocks - Stock market data
valyu/valyu-earnings-US - Earnings reports
reuters.com - Financial news
bloomberg.com - Market analysis Medical Research Collection. Some sources to include:
valyu/valyu-pubmed - Medical literature
valyu/valyu-clinical-trials - Clinical trial data
valyu/valyu-drug-labels - FDA drug information

For complete prompting guide, see references/prompting.md.

6. Common Workflows

Research Workflow

// 1. Quick search to find sources
const searchResults = await valyu.search({
  query: "CRISPR therapeutic applications",
  searchType: "proprietary",
  maxNumResults: 20
});

// 2. Extract key content from top results
const contents = await valyu.contents({
  urls: searchResults.results.slice(0, 3).map(r => r.url),
  summary: "Extract key findings"
});

// 3. Deep analysis for comprehensive report
const research = await valyu.deepResearch.create({
  query: "CRISPR therapeutic applications comprehensive review",
  model: "heavy"
});

Financial Analysis Workflow

// 1. Get SEC filings
const filings = await valyu.search({
  query: "Apple 10-K 2024",
  includedSources: ["valyu/valyu-sec-filings"]
});

// 2. Quick synthesis
const summary = await valyu.answer({
  query: "Apple Q4 2024 financial highlights",
  fastMode: true
});

// 3. Structured extraction
const metrics = await valyu.answer({
  query: "Apple financial metrics 2024",
  structuredOutput: {
    type: "object",
    properties: {
      revenue: { type: "string" },
      netIncome: { type: "string" },
      growthRate: { type: "string" }
    }
  }
});

7. Available Data Sources

Valyu provides access to 25+ specialized datasets:

Category	Examples
Academic	arXiv (2.5M+ papers), PubMed (37M+), bioRxiv, medRxiv
Financial	SEC filings, earnings transcripts, stock data, crypto
Healthcare	Clinical trials, DailyMed, PubChem, drug labels, ChEMBL, DrugBank, Open Target, WHO ICD
Economic	FRED, BLS, World Bank, US Treasury, Destatis
Predictions	Polymarket, Kalshi
Patents	US patent database
Transportation	UK Rail, Ship Tracking

For complete datasource reference, see references/datasources.md.

8. API Reference

For complete API documentation including all parameters, response structures, and error codes, see references/api-guide.md.

9. Integration Guides

Platform-specific integration documentation:

Additional Resources

Weekly Installs

653

Repository

valyuai/skills

GitHub Stars

First Seen

Jan 21, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

cursor602

codex599

opencode598

gemini-cli596

github-copilot594

amp589

AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具

41,400 周安装

nejm.org - New England Journal of Medicine

thelancet.com - The Lancet Tech Documentation Collection. Some sources to include:

docs.aws.amazon.com - AWS documentation

cloud.google.com/docs - Google Cloud docs

learn.microsoft.com - Microsoft docs

kubernetes.io/docs - Kubernetes docs

developer.mozilla.org - MDN Web Docs

// Academic includedSources: ["valyu/valyu-arxiv", "valyu/valyu-pubmed", "nature"]

// Financial includedSources: ["valyu/valyu-sec-filings", "bloomberg.com", "reuters.com"]

// Tech news includedSources: ["techcrunch.com", "theverge.com", "arstechnica.com"]

Valyu API 最佳实践指南：搜索、内容提取、AI 答案与深度研究

🇨🇳中文介绍

Valyu 最佳实践

快速参考：选择合适的 API

⚠️ 强制要求：使用官方 Valyu SDK 库

JavaScript/TypeScript: valyu-js

Python: valyu

相关 Skills

为什么使用 SDK 而非原始 API 调用？

❌ 切勿这样做

✅ 始终这样做

1. Search API

何时使用

基本用法

搜索类型

关键参数

特定领域搜索模式

搜索配方

2. Contents API

何时使用

基本用法

带摘要功能

结构化提取（JSON 模式）

关键参数

内容配方

3. Answer API

何时使用

基本用法

使用快速模式（更低延迟）

使用自定义指令

使用流式传输

结构化输出

关键参数

答案配方

4. DeepResearch API

何时使用

研究模式

创建研究任务

轮询完成状态

关键参数

DeepResearch 配方

5. 查询编写最佳实践

核心原则

查询构成要素

好查询与坏查询

拆分复杂请求

来源过滤

6. 常见工作流

研究工作流

财务分析工作流

7. 可用数据源

8. API 参考

9. 集成指南

其他资源

🇺🇸English

Valyu Best Practices

Quick Reference: Choosing the Right API

⚠️ MANDATORY: Use Official Valyu SDK Libraries

JavaScript/TypeScript: valyu-js

Python: valyu

Why SDK Over Raw API Calls?

❌ NEVER Do This

✅ Always Do This

1. Search API

When to Use

Basic Usage

Search Types

Key Parameters

Domain-Specific Search Patterns

Search Recipes

2. Contents API

When to Use

Basic Usage

With Summarization

Structured Extraction (JSON Schema)

Key Parameters

Content Recipes

3. Answer API

When to Use

Basic Usage

JavaScript/TypeScript: `valyu-js`

Python: `valyu`

JavaScript/TypeScript: `valyu-js`

Python: `valyu`