openevidence-hello-world
Create a minimal working OpenEvidence clinical query example. Use when starting a new OpenEvidence integration, testing your setup, or learning basic clinical query patterns. Trigger with phrases like "openevidence hello world", "openevidence example", "openevidence quick start", "first clinical query".
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 2.0k
- Forks
- 233
01 前言 Front Matter
- name
- openevidence-hello-world
- author
- Jeremy Longshore <jeremy@intentsolutions.io>
- license
- MIT
- version
- 1.0.0
- description
- Create a minimal working OpenEvidence clinical query example. Use when starting a new OpenEvidence integration, testing your setup, or learning basic clinical query patterns. Trigger with phrases like "openevidence hello world", "openevidence example", "openevidence quick start", "first clinical query".
- allowed-tools
- Read, Write, Edit
03 SKILL.md 正文
OpenEvidence Hello World
Overview
Minimal working example demonstrating core OpenEvidence clinical query functionality.
Prerequisites
- Completed
openevidence-install-authsetup - Valid API credentials configured
- Development environment ready
Instructions
Step 1: Create Entry File
// src/openevidence-demo.ts
import { OpenEvidenceClient } from '@openevidence/sdk';
const client = new OpenEvidenceClient({
apiKey: process.env.OPENEVIDENCE_API_KEY,
orgId: process.env.OPENEVIDENCE_ORG_ID,
});
Step 2: Make Your First Clinical Query
async function firstClinicalQuery() {
// Simple clinical question
const response = await client.query({
question: "What are the first-line treatments for type 2 diabetes in adults?",
context: {
specialty: "internal-medicine",
urgency: "routine",
},
});
console.log('Answer:', response.answer);
console.log('Sources:', response.citations.map(c => c.source));
console.log('Confidence:', response.confidence);
}
firstClinicalQuery().catch(console.error);
Step 3: Run the Example
# With TypeScript
npx ts-node src/openevidence-demo.ts
# With Node.js (after compilation)
node dist/openevidence-demo.js
Output
- Working code file with OpenEvidence client initialization
- Successful API response with evidence-based answer
- Console output showing:
Answer: First-line treatment for type 2 diabetes in adults typically includes...
Sources: ["NEJM 2024", "ADA Standards of Care 2025", "JAMA Internal Medicine"]
Confidence: 0.95
Response Structure
interface ClinicalQueryResponse {
answer: string; // Evidence-based clinical answer
citations: Citation[]; // Peer-reviewed sources
confidence: number; // 0-1 confidence score
lastUpdated: string; // When evidence was last reviewed
disclaimer: string; // Clinical use disclaimer
deepConsultAvailable: boolean; // Whether DeepConsult can provide more detail
}
interface Citation {
source: string; // Journal/guideline name
title: string; // Article title
authors: string[]; // Author list
year: number; // Publication year
doi?: string; // DOI if available
url?: string; // Link to source
}
Error Handling
| Error | Cause | Solution |
|---|---|---|
| Import Error | SDK not installed | Verify with npm list @openevidence/sdk |
| Auth Error | Invalid credentials | Check environment variables are set |
| Timeout | Complex query or network issues | Increase timeout or retry |
| Rate Limit | Too many requests | Wait and retry with exponential backoff |
| Invalid Query | Question not clinical | Ensure query is medically relevant |
Examples
TypeScript Example with Error Handling
import { OpenEvidenceClient, OpenEvidenceError } from '@openevidence/sdk';
const client = new OpenEvidenceClient({
apiKey: process.env.OPENEVIDENCE_API_KEY,
orgId: process.env.OPENEVIDENCE_ORG_ID,
});
async function queryClinicalEvidence(question: string) {
try {
const response = await client.query({
question,
context: {
specialty: "family-medicine",
urgency: "routine",
},
options: {
maxCitations: 5,
includeGuidelines: true,
},
});
return {
answer: response.answer,
sources: response.citations,
confidence: response.confidence,
};
} catch (error) {
if (error instanceof OpenEvidenceError) {
console.error(`OpenEvidence Error [${error.code}]:`, error.message);
}
throw error;
}
}
// Example usage
queryClinicalEvidence(
"What is the recommended antibiotic for community-acquired pneumonia?"
).then(result => {
console.log('Clinical Answer:', result.answer);
console.log('Evidence Sources:', result.sources.length);
});
Python Example
from openevidence import OpenEvidenceClient, OpenEvidenceError
client = OpenEvidenceClient()
def query_clinical_evidence(question: str) -> dict:
try:
response = client.query(
question=question,
context={
"specialty": "emergency-medicine",
"urgency": "urgent"
}
)
return {
"answer": response.answer,
"sources": [c.source for c in response.citations],
"confidence": response.confidence
}
except OpenEvidenceError as e:
print(f"Error [{e.code}]: {e.message}")
raise
# Example usage
result = query_clinical_evidence(
"What are the contraindications for tPA in acute ischemic stroke?"
)
print(f"Answer: {result['answer']}")
Resources
Next Steps
Proceed to openevidence-local-dev-loop for development workflow setup.
04 同仓库更多 Skills
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
neuropixels-analysis
Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
notebooklm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.