valyu-best-practices

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Valyu Best Practices

Valyu 最佳实践

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

本工具提供了使用Valyu API执行搜索、内容提取、AI生成答案及深度研究任务的操作指南。

Quick Reference: Choosing the Right API

快速参考：选择合适的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

使用以下决策树来选择对应的Valyu API：

你需要什么？

├─ 跨多数据源查找信息
│  └─ 使用Search API
│
├─ 从特定URL提取内容
│  └─ 使用Contents API
│
├─ 获取带引用的AI合成答案
│  └─ 使用Answer API
│
├─ 生成综合性研究报告
│  └─ 使用DeepResearch API
│
└─ 发现可用数据源
   └─ 使用Datasources API

⚠️ MANDATORY: Use Official Valyu SDK Libraries

⚠️ 强制要求：使用官方Valyu SDK库

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.

重要提示：编写调用Valyu API的代码时，必须使用官方SDK库。绝对不要直接对Valyu API端点发起原始HTTP/fetch请求。

JavaScript/TypeScript:

valyu-js

JavaScript/TypeScript：

valyu-js

bash

npm install valyu-js

bash

npm install valyu-js

or

或

pnpm add valyu-js


```typescript
import { Valyu } from 'valyu-js';

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

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

pnpm add valyu-js


```typescript
import { Valyu } from 'valyu-js';

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

// 现在可以使用valyu.search(), valyu.contents(), valyu.answer(), valyu.deepResearch

Python:

valyu

Python：

valyu

bash

pip install valyu

bash

pip install valyu

or

或

uv add valyu


```python
from valyu import Valyu

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

uv add valyu


```python
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

现在可以使用valyu.search(), valyu.contents(), valyu.answer(), valyu.deep_research

undefined

undefined

Why SDK Over Raw API Calls?

为什么选择SDK而非原始API调用？

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

类型安全 - 为所有参数和响应提供完整的TypeScript/Python类型提示
自动重试 - 内置针对临时故障的重试逻辑
流式支持 - 为流式响应提供完善的异步迭代器支持
错误处理 - 带有实用提示信息的结构化错误类型
未来兼容性 - SDK更新会自动处理API变更

❌ NEVER Do This

❌ 绝对不要这么做

typescript

// 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: '...' })
});

typescript

// 不要发起原始fetch请求
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

✅ 正确的做法

typescript

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

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

typescript

// 务必使用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.

用途： 跨网页、学术、医疗、交通、金融、新闻及专有数据源查找信息。

When to Use

使用场景

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)

查找任意主题的最新信息
学术研究（arXiv、PubMed、bioRxiv、medRxiv）
金融数据（SEC文件、收益报告、股票数据）
新闻监测与时事追踪
医疗健康数据（临床试验、药品说明书）
预测市场（Polymarket、Kalshi）
交通数据（英国国家铁路、全球航运）

Basic Usage

基础用法

typescript

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

typescript

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

Search Types

搜索类型

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

类型	适用场景
`all`	所有数据源 - 网页、学术、金融、专有
`web`	仅通用互联网内容
`proprietary`	授权学术论文与研究资料
`news`	新闻文章与时事内容

Key Parameters

关键参数

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"` , `"proprietary"` , `"news"`
`maxNumResults`	`max_num_results`	Number of results (1-20)	`10`
`includedSources`	`included_sources`	Limit to specific sources	`["valyu/valyu-arxiv", "valyu/valyu-pubmed"]`
`startDate` / `endDate`	`start_date` / `end_date`	Date filtering	`"2024-01-01"`
`relevanceThreshold`	`relevance_threshold`	Minimum relevance (0-1)	`0.7`

参数（TS/JS）	参数（Python）	用途	示例
`query`	`query`	搜索查询（不超过400字符）	`"CRISPR gene editing 2024"`
`searchType`	`search_type`	数据源范围	`"all"` , `"web"` , `"proprietary"` , `"news"`
`maxNumResults`	`max_num_results`	结果数量（1-20）	`10`
`includedSources`	`included_sources`	限定特定数据源	`["valyu/valyu-arxiv", "valyu/valyu-pubmed"]`
`startDate` / `endDate`	`start_date` / `end_date`	日期过滤	`"2024-01-01"`
`relevanceThreshold`	`relevance_threshold`	最低相关度（0-1）	`0.7`

Domain-Specific Search Patterns

特定领域搜索模式

Academic Research:

typescript

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:

typescript

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

News Monitoring:

typescript

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

学术研究：

typescript

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"
});

金融分析：

typescript

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

新闻监测：

typescript

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

Search Recipes

搜索示例

For detailed patterns, see:

Basic Search Patterns
Academic Search
Finance Search
News Search
Healthcare Search

如需详细模式，请查看：

基础搜索模式
学术搜索
金融搜索
新闻搜索
医疗健康搜索

2. Contents API

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

用途： 从网页提取干净、结构化的内容，优化LLM处理效果。

When to Use

使用场景

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

将网页转换为简洁的Markdown格式
提取文章文本用于摘要生成
解析文档以构建RAG系统
从产品页面提取结构化数据
处理学术论文

Basic Usage

基础用法

typescript

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

typescript

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

With Summarization

带摘要功能

typescript

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

typescript

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

Structured Extraction (JSON Schema)

结构化提取（JSON Schema）

typescript

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"]
  }
});

typescript

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

关键参数

Parameter (TS/JS)	Parameter (Python)	Purpose	Example
`urls`	`urls`	URLs to process (1-10)	`["https://example.com"]`
`responseLength`	`response_length`	Content length	`"short"` , `"medium"` , `"large"` , `"max"`
`extractEffort`	`extract_effort`	Extraction quality	`"normal"` , `"high"` , `"auto"`
`summary`	`summary`	AI summarization	`true` , `"instructions"` , or JSON schema
`screenshot`	`screenshot`	Capture screenshots	`true`

参数（TS/JS）	参数（Python）	用途	示例
`urls`	`urls`	待处理的URL（1-10个）	`["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	`true` , `"instructions"` , 或JSON Schema
`screenshot`	`screenshot`	捕获截图	`true`

Content Recipes

内容提取示例

For detailed patterns, see:

Basic Content Extraction
Extraction with Summary
Structured Extraction
Research Paper Extraction

如需详细模式，请查看：

基础内容提取
【带摘要的内容提取】(references/content-recipes/basic-content-extraction-from-web-with-summary.md)
结构化内容提取
研究论文提取

3. Answer API

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

用途： 获取基于实时搜索结果的AI生成答案，并附带引用来源。

When to Use

使用场景

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

需要综合当前信息的问题
多来源事实核查
技术文档相关问题
需要引用来源的研究
从搜索结果中提取结构化数据

Basic Usage

基础用法

typescript

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

typescript

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

With Fast Mode (Lower Latency)

快速模式（低延迟）

typescript

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

typescript

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

With Custom Instructions

自定义指令

typescript

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."
});

typescript

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

流式输出

typescript

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);
}

typescript

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

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

Structured Output

结构化输出

typescript

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" } }
    }
  }
});

typescript

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

关键参数

Parameter (TS/JS)	Parameter (Python)	Purpose	Example
`query`	`query`	Question to answer	`"What is quantum computing?"`
`fastMode`	`fast_mode`	Lower latency	`true`
`systemInstructions`	`system_instructions`	AI directives	`"Be concise"`
`structuredOutput`	`structured_output`	JSON schema	`{type: "object", ...}`
`streaming`	`streaming`	Enable SSE streaming	`true`
`dataMaxPrice`	`data_max_price`	Dollar limit	`1.0`

参数（TS/JS）	参数（Python）	用途	示例
`query`	`query`	待回答的问题	`"What is quantum computing?"`
`fastMode`	`fast_mode`	低延迟模式	`true`
`systemInstructions`	`system_instructions`	AI指令	`"Be concise"`
`structuredOutput`	`structured_output`	JSON Schema	`{type: "object", ...}`
`streaming`	`streaming`	启用SSE流式输出	`true`
`dataMaxPrice`	`data_max_price`	费用上限（美元）	`1.0`

Answer Recipes

答案生成示例

For detailed patterns, see:

Basic Answer
Fast Mode
Streaming
Custom Instructions

如需详细模式，请查看：

基础答案生成
快速模式
流式输出
自定义指令

4. DeepResearch API

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

用途： 生成包含详细分析与引用来源的综合性研究报告。

When to Use

使用场景

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

综合性市场分析
文献综述
竞争情报
技术深度解析
需要多来源综合的主题

Research Modes

研究模式

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

模式	耗时	最佳适用场景
`fast`	~5分钟	快速查询、简单问题
`standard`	~10-20分钟	均衡性研究（最常用）
`heavy`	~90分钟	综合性分析、复杂主题

Create Research Task

创建研究任务

typescript

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

typescript

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

Poll for Completion

查询任务完成状态

typescript

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
}

typescript

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

if (status.status === "completed") {
  console.log(status.output);  // Markdown报告
  console.log(status.sources); // 引用来源
  console.log(status.pdf_url); // PDF下载链接
}

Key Parameters

关键参数

Parameter (TS/JS)	Parameter (Python)	Purpose	Example
`query`	`query`	Research question	`"AI market trends 2024"`
`model`	`model`	Research depth	`"fast"` , `"standard"` , `"heavy"`
`outputFormat`	`output_format`	Report format	`"markdown"` , `"pdf"`
`includedSources`	`included_sources`	Source filtering	`["valyu/valyu-arxiv", "techcrunch.com"]`
`startDate` / `endDate`	`start_date` / `end_date`	Date range	`"2024-01-01"`

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`	数据源过滤	`["valyu/valyu-arxiv", "techcrunch.com"]`
`startDate` / `endDate`	`start_date` / `end_date`	日期范围	`"2024-01-01"`

DeepResearch Recipes

深度研究示例

For detailed patterns, see:

Fast Research
Standard Research
Heavy Research

如需详细模式，请查看：

快速研究
标准研究
深度研究

5. Query Writing Best Practices

5. 查询编写最佳实践

Core Principles

核心原则

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

具体明确 - 使用领域术语
简洁精炼 - 查询不超过400字符
聚焦主题 - 每个查询对应一个主题
添加约束 - 包含时间范围、数据源类型

Query Anatomy

查询结构

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

元素	说明	示例
意图	你的需求	"latest advancements" vs "overview"
领域	主题术语	"transformer architecture"
约束条件	过滤条件	"2024", "peer-reviewed"
数据源类型	查找范围	学术论文、SEC文件

Good vs Bad Queries

优质与劣质查询对比

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"

劣质：  "I want to know about AI"
优质： "transformer attention mechanism survey 2024"

劣质：  "Apple financial information"
优质： "Apple revenue growth Q4 2024 earnings SEC filing"

劣质：  "gene editing research"
优质： "CRISPR off-target effects therapeutic applications 2024"

Split Complex Requests

拆分复杂请求

undefined

undefined

Don't do this

不要这样做

"Tesla stock performance, new products, and Elon Musk statements"

Do this instead

应该这样拆分

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

undefined

查询1："Tesla stock performance Q4 2024" 查询2："Tesla Cybertruck production updates 2024" 查询3："Tesla FSD autonomous driving progress"

undefined

Source Filtering

数据源过滤

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
```
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

javascript

// 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"]

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

使用

includedSources

获取领域权威内容：金融研究推荐数据源：

```
valyu/valyu-sec-filings
```
- SEC监管文件
```
valyu/valyu-stocks
```
- 股票市场数据
```
valyu/valyu-earnings-US
```
- 美国公司收益报告
```
reuters.com
```
- 金融新闻
```
bloomberg.com
```
- 市场分析医疗研究推荐数据源：
```
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》技术文档推荐数据源：
```
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

javascript

// 学术研究
includedSources: ["valyu/valyu-arxiv", "valyu/valyu-pubmed", "nature"]

// 金融研究
includedSources: ["valyu/valyu-sec-filings", "bloomberg.com", "reuters.com"]

// 科技新闻
includedSources: ["techcrunch.com", "theverge.com", "arstechnica.com"]

如需完整提示指南，请查看references/prompting.md。

6. Common Workflows

6. 常见工作流

Research Workflow

研究工作流

typescript

// 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"
});

typescript

// 1. 快速搜索查找数据源
const searchResults = await valyu.search({
  query: "CRISPR therapeutic applications",
  searchType: "proprietary",
  maxNumResults: 20
});

// 2. 从顶级结果中提取关键内容
const contents = await valyu.contents({
  urls: searchResults.results.slice(0, 3).map(r => r.url),
  summary: "Extract key findings"
});

// 3. 深度分析生成综合性报告
const research = await valyu.deepResearch.create({
  query: "CRISPR therapeutic applications comprehensive review",
  model: "heavy"
});

Financial Analysis Workflow

金融分析工作流

typescript

// 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" }
    }
  }
});

typescript

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

// 2. 快速内容综合
const summary = await valyu.answer({
  query: "Apple Q4 2024 financial highlights",
  fastMode: true
});

// 3. 结构化提取指标
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

7. 可用数据源

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.

Valyu提供25+个专业数据集的访问权限：

分类	示例
学术	arXiv（250万+论文）、PubMed（3700万+）、bioRxiv、medRxiv
金融	SEC文件、收益记录、股票数据、加密货币数据
医疗健康	临床试验、DailyMed、PubChem、药品说明书、ChEMBL、DrugBank、Open Target、WHO ICD
经济	FRED、BLS、世界银行、美国财政部、Destatis
预测市场	Polymarket、Kalshi
专利	美国专利数据库
交通	英国铁路、船舶追踪

如需完整数据源参考，请查看references/datasources.md。

8. API Reference

8. API参考

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

如需包含所有参数、响应结构及错误代码的完整API文档，请查看references/api-guide.md。

9. Integration Guides

9. 集成指南

Platform-specific integration documentation:

Anthropic Claude
OpenAI
Vercel AI SDK
LangChain
LlamaIndex
MCP Server

平台特定的集成文档：

Anthropic Claude
OpenAI
Vercel AI SDK
LangChain
LlamaIndex
MCP Server

Additional Resources

额外资源

All Recipes Index
Design Philosophy
Prompting Guide
Full API Reference

所有示例索引
设计理念
提示指南
完整API参考

valyu-best-practices

Original

Translation

Valyu Best Practices

Valyu 最佳实践

Quick Reference: Choosing the Right API

快速参考：选择合适的API

⚠️ MANDATORY: Use Official Valyu SDK Libraries

⚠️ 强制要求：使用官方Valyu SDK库

JavaScript/TypeScript: valyu-js

JavaScript/TypeScript：valyu-js

or

或

Python: valyu

Python：valyu

or

或

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

现在可以使用valyu.search(), valyu.contents(), valyu.answer(), valyu.deep_research

Why SDK Over Raw API Calls?

为什么选择SDK而非原始API调用？

❌ NEVER Do This

❌ 绝对不要这么做

✅ Always Do This

✅ 正确的做法

1. Search API

1. Search API

When to Use

使用场景

Basic Usage

基础用法

Search Types

搜索类型

Key Parameters

关键参数

Domain-Specific Search Patterns

特定领域搜索模式

Search Recipes

搜索示例

2. Contents API

2. Contents API

When to Use

使用场景

Basic Usage

基础用法

With Summarization

带摘要功能

Structured Extraction (JSON Schema)

结构化提取（JSON Schema）

Key Parameters

关键参数

Content Recipes

内容提取示例

3. Answer API

3. Answer API

When to Use

使用场景

Basic Usage

基础用法

With Fast Mode (Lower Latency)

快速模式（低延迟）

With Custom Instructions

自定义指令

With Streaming

流式输出

Structured Output

结构化输出

Key Parameters

关键参数

Answer Recipes

答案生成示例

4. DeepResearch API

4. DeepResearch API

When to Use

使用场景

Research Modes

研究模式

Create Research Task

创建研究任务

Poll for Completion

JavaScript/TypeScript:
`valyu-js`

JavaScript/TypeScript：
`valyu-js`

Python:
`valyu`

Python：
`valyu`