Back to Details

pubmed-search

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

PubMed Search

PubMed文献搜索

Search the complete PubMed database of biomedical literature using natural language queries powered by Valyu's semantic search API.
借助Valyu的语义搜索API，使用自然语言查询搜索完整的PubMed生物医学文献数据库。

Why This Skill is Powerful

该搜索功能的强大特性

  • No API Parameter Parsing: Just pass natural language queries directly - no need to construct complex search parameters
  • Semantic Search: Understands the meaning of your query, not just keyword matching
  • Full-Text Access: Returns complete article content, not just abstracts
  • Image Links: Includes figures and images from papers
  • Comprehensive Coverage: Access to all of PubMed's biomedical literature
  • 无需解析API参数：直接传入自然语言查询即可，无需构建复杂的搜索参数
  • 语义搜索：理解查询的含义，而非仅进行关键词匹配
  • 全文访问：返回完整的文章内容，而非仅摘要
  • 图片链接：包含论文中的图表和图片
  • 全面覆盖：可访问PubMed的所有生物医学文献

Requirements

环境要求

  1. Node.js 18+ (uses built-in fetch)
  2. Valyu API key from https://platform.valyu.ai ($10 free credits)
  1. Node.js 18+（使用内置的fetch功能）
  2. 从https://platform.valyu.ai获取Valyu API密钥（赠送10美元免费额度）

CRITICAL: Script Path Resolution

重要提示：脚本路径解析

The 
scripts/search
commands in this documentation are relative to this skill's installation directory.
Before running any command, locate the script using:
bash
PUBMED_SCRIPT=$(find ~/.claude/plugins/cache -name "search" -path "*/pubmed-search/*/scripts/*" -type f 2>/dev/null | head -1)
Then use the full path for all commands:
bash
$PUBMED_SCRIPT "CRISPR gene editing" 15
本文档中的
scripts/search
命令是相对于该功能的安装目录的。
运行任何命令前，请使用以下命令定位脚本：
bash
PUBMED_SCRIPT=$(find ~/.claude/plugins/cache -name "search" -path "*/pubmed-search/*/scripts/*" -type f 2>/dev/null | head -1)
然后使用完整路径执行所有命令：
bash
$PUBMED_SCRIPT "CRISPR基因编辑" 15

API Key Setup Flow

API密钥设置流程

When you run a search and receive 
"setup_required": true
, follow this flow:
  1. Ask the user for their API key: "To search PubMed, I need your Valyu API key. Get one free ($10 credits) at https://platform.valyu.ai"
  2. Once the user provides the key, run:
    bash
    scripts/search setup <api-key>
  3. Retry the original search.
当你执行搜索并收到
"setup_required": true
的响应时，请按照以下步骤操作：
  1. 向用户索要API密钥： "要搜索PubMed，我需要你的Valyu API密钥。可前往https://platform.valyu.ai免费获取（赠送10美元额度）"
  2. 用户提供密钥后，执行以下命令：
    bash
    scripts/search setup <api-key>
  3. 重新执行最初的搜索。

Example Flow:

示例流程：

User: Search PubMed for CAR-T cell therapy advances
→ Response: {"success": false, "setup_required": true, ...}
→ Claude asks: "Please provide your Valyu API key from https://platform.valyu.ai"
→ User: "val_abc123..."
→ Claude runs: scripts/search setup val_abc123...
→ Response: {"success": true, "type": "setup", ...}
→ Claude retries: scripts/search "CAR-T cell therapy advances" 10
→ Success!
用户：搜索PubMed中关于CAR-T细胞疗法进展的内容
→ 响应：{"success": false, "setup_required": true, ...}
→ Claude询问："请提供你从https://platform.valyu.ai获取的Valyu API密钥"
→ 用户："val_abc123..."
→ Claude执行：scripts/search setup val_abc123...
→ 响应：{"success": true, "type": "setup", ...}
→ Claude重新执行：scripts/search "CAR-T细胞疗法进展" 10
→ 成功！

Usage

使用方法

Basic Search

基础搜索

bash
scripts/search "your natural language query" [maxResults]
bash
scripts/search "你的自然语言查询" [最大结果数]

Examples

示例

bash
undefined
bash
undefined

Search for recent COVID-19 research

搜索最新的COVID-19研究

scripts/search "COVID-19 vaccine efficacy studies" 15
scripts/search "COVID-19疫苗有效性研究" 15

Find papers on a specific gene

查找关于特定基因的论文

scripts/search "BRCA1 mutations and breast cancer risk" 20
scripts/search "BRCA1突变与乳腺癌风险" 20

Search for treatment approaches

搜索治疗方法

scripts/search "immunotherapy for melanoma clinical trials" 10
scripts/search "黑色素瘤免疫疗法临床试验" 10

Drug mechanism research

药物机制研究

scripts/search "mechanism of action of metformin in type 2 diabetes" 12
undefined
scripts/search "二甲双胍治疗2型糖尿病的作用机制" 12
undefined

Setup Command

设置命令

bash
scripts/search setup <api-key>
bash
scripts/search setup <api-key>

Output Format

输出格式

json
{
  "success": true,
  "type": "pubmed_search",
  "query": "CRISPR gene editing",
  "result_count": 10,
  "results": [
    {
      "title": "Article Title",
      "url": "https://pubmed.ncbi.nlm.nih.gov/...",
      "content": "Full article text with figures...",
      "source": "pubmed",
      "relevance_score": 0.95,
      "images": ["https://example.com/figure1.jpg"]
    }
  ],
  "cost": 0.025
}
json
{
  "success": true,
  "type": "pubmed_search",
  "query": "CRISPR基因编辑",
  "result_count": 10,
  "results": [
    {
      "title": "文章标题",
      "url": "https://pubmed.ncbi.nlm.nih.gov/...",
      "content": "包含图表的完整文章文本...",
      "source": "pubmed",
      "relevance_score": 0.95,
      "images": ["https://example.com/figure1.jpg"]
    }
  ],
  "cost": 0.025
}

Processing Results

结果处理

With jq

使用jq工具

bash
undefined
bash
undefined

Get article titles

获取文章标题

scripts/search "query" 10 | jq -r '.results[].title'
scripts/search "查询内容" 10 | jq -r '.results[].title'

Get URLs

获取链接地址

scripts/search "query" 10 | jq -r '.results[].url'
scripts/search "查询内容" 10 | jq -r '.results[].url'

Extract full content

提取全文内容

scripts/search "query" 10 | jq -r '.results[].content'
undefined
scripts/search "查询内容" 10 | jq -r '.results[].content'
undefined

Common Use Cases

常见使用场景

Literature Review

文献综述

bash
undefined
bash
undefined

Find all papers on a topic

查找某一主题的所有论文

scripts/search "mechanisms of aging in humans" 50
undefined
scripts/search "人类衰老机制" 50
undefined

Drug Discovery

药物研发

bash
undefined
bash
undefined

Search for drug targets

搜索药物靶点

scripts/search "novel targets for Alzheimer's disease treatment" 20
undefined
scripts/search "阿尔茨海默病治疗的新靶点" 20
undefined

Clinical Research

临床研究

bash
undefined
bash
undefined

Find clinical trial results

查找临床试验结果

scripts/search "phase 3 trials for rheumatoid arthritis biologics" 15
undefined
scripts/search "类风湿关节炎生物制剂的3期临床试验" 15
undefined

Gene Function

基因功能研究

bash
undefined
bash
undefined

Research gene function

研究基因功能

scripts/search "role of TP53 in cancer development" 25
undefined
scripts/search "TP53在癌症发展中的作用" 25
undefined

Error Handling

错误处理

All commands return JSON with 
success
field:
json
{
  "success": false,
  "error": "Error message"
}
Exit codes:
  • 0
    - Success
  • 1
    - Error (check JSON for details)
所有命令都会返回包含
success
字段的JSON：
json
{
  "success": false,
  "error": "错误信息"
}
退出码：
  • 0
    - 成功
  • 1
    - 错误（查看JSON获取详细信息）

API Endpoint

API端点

  • Base URL: 
    https://api.valyu.ai/v1
  • Endpoint: 
    /search
  • Authentication: X-API-Key header
  • 基础URL: 
    https://api.valyu.ai/v1
  • 端点: 
    /search
  • 认证方式: X-API-Key请求头

Architecture

架构

scripts/
├── search          # Bash wrapper
└── search.mjs      # Node.js CLI
Direct API calls using Node.js built-in 
fetch()
, zero external dependencies.
scripts/
├── search          # Bash包装器
└── search.mjs      # Node.js命令行工具
使用Node.js内置的
fetch()
直接调用API，无外部依赖。

Adding to Your Project

集成到你的项目中

If you're building an AI project and want to integrate PubMed search directly into your application, use the Valyu SDK:
如果你正在构建AI项目，并希望将PubMed搜索直接集成到你的应用中，可以使用Valyu SDK：

Python Integration

Python集成

python
from valyu import Valyu

client = Valyu(api_key="your-api-key")

response = client.search(
    query="immunotherapy for melanoma",
    included_sources=["valyu/valyu-pubmed"],
    max_results=20
)

for result in response["results"]:
    print(f"Title: {result['title']}")
    print(f"URL: {result['url']}")
    print(f"Content: {result['content'][:500]}...")
python
from valyu import Valyu

client = Valyu(api_key="你的API密钥")

response = client.search(
    query="黑色素瘤免疫疗法",
    included_sources=["valyu/valyu-pubmed"],
    max_results=20
)

for result in response["results"]:
    print(f"标题: {result['title']}")
    print(f"链接: {result['url']}")
    print(f"内容: {result['content'][:500]}...")

TypeScript Integration

TypeScript集成

typescript
import { Valyu } from "valyu-js";

const client = new Valyu("your-api-key");

const response = await client.search({
  query: "immunotherapy for melanoma",
  includedSources: ["valyu/valyu-pubmed"],
  maxResults: 20
});

response.results.forEach((result) => {
  console.log(`Title: ${result.title}`);
  console.log(`URL: ${result.url}`);
  console.log(`Content: ${result.content.substring(0, 500)}...`);
});
See the Valyu docs for full integration examples and SDK reference.
typescript
import { Valyu } from "valyu-js";

const client = new Valyu("你的API密钥");

const response = await client.search({
  query: "黑色素瘤免疫疗法",
  includedSources: ["valyu/valyu-pubmed"],
  maxResults: 20
});

response.results.forEach((result) => {
  console.log(`标题: ${result.title}`);
  console.log(`链接: ${result.url}`);
  console.log(`内容: ${result.content.substring(0, 500)}...`);
});
如需完整的集成示例和SDK参考文档，请查看Valyu文档。