environment-setup-guide
Guide developers through setting up development environments with proper tools, dependencies, and configurations
openevidence-upgrade-migration
Upgrade OpenEvidence SDK versions and migrate between API versions. Use when upgrading SDK, migrating to new API version, or planning OpenEvidence version updates. Trigger with phrases like "openevidence upgrade", "openevidence migrate", "update openevidence sdk", "openevidence new version", "ope...
Full skill instructions
Safely upgrade OpenEvidence SDK versions and migrate between API versions with minimal disruption to clinical workflows.
| SDK Version | API Version | Node.js | Python | Status |
|---|---|---|---|---|
| 3.x | v3 | 20+ | 3.11+ | Current |
| 2.x | v2 | 18+ | 3.10+ | Maintained |
| 1.x | v1 | 16+ | 3.8+ | Deprecated |
# Check current version
npm list @openevidence/sdk
# or
pip show openevidence
# Review changelog
# https://docs.openevidence.com/changelog
# Node.js - specific version
npm install @openevidence/[email protected]
# Node.js - latest
npm install @openevidence/sdk@latest
# Python - specific version
pip install openevidence==3.0.0
# Python - latest
pip install --upgrade openevidence
Client Initialization Changes:
// v2 (deprecated)
import { OpenEvidence } from '@openevidence/sdk';
const client = new OpenEvidence(process.env.OPENEVIDENCE_API_KEY);
// v3 (current)
import { OpenEvidenceClient } from '@openevidence/sdk';
const client = new OpenEvidenceClient({
apiKey: process.env.OPENEVIDENCE_API_KEY,
orgId: process.env.OPENEVIDENCE_ORG_ID, // Now required
});
Query Method Changes:
// v2 (deprecated)
const response = await client.query('What is the treatment for...');
// v3 (current)
const response = await client.query({
question: 'What is the treatment for...',
context: {
specialty: 'internal-medicine',
urgency: 'routine',
},
});
Response Structure Changes:
// v2 response
interface V2Response {
answer: string;
sources: string[];
}
// v3 response
interface V3Response {
answer: string;
citations: Citation[]; // Renamed and expanded
confidence: number; // New field
lastUpdated: string; // New field
id: string; // New field for tracking
}
DeepConsult Changes:
// v2 (synchronous, limited)
const report = await client.research('complex question');
// v3 (async with status polling)
const consultId = await client.deepConsult.create({
question: 'complex question',
context: { specialty: 'oncology', researchFocus: 'treatment' },
});
// Poll for completion or use webhooks
const status = await client.deepConsult.status(consultId);
// src/migration/openevidence-adapter.ts
// Temporary adapter for gradual migration
import { OpenEvidenceClient } from '@openevidence/sdk';
interface V2QueryResponse {
answer: string;
sources: string[];
}
interface V3QueryResponse {
answer: string;
citations: { source: string; title: string; year: number }[];
confidence: number;
}
export class OpenEvidenceMigrationAdapter {
private client: OpenEvidenceClient;
private useV3Response: boolean;
constructor(config: { apiKey: string; orgId: string; useV3Response?: boolean }) {
this.client = new OpenEvidenceClient({
apiKey: config.apiKey,
orgId: config.orgId,
});
this.useV3Response = config.useV3Response ?? false;
}
// Maintains v2-compatible interface during migration
async query(
question: string,
options?: { specialty?: string }
): Promise<V2QueryResponse | V3QueryResponse> {
const response = await this.client.query({
question,
context: {
specialty: options?.specialty || 'internal-medicine',
urgency: 'routine',
},
});
// Return v2-compatible response if not ready for v3
if (!this.useV3Response) {
return {
answer: response.answer,
sources: response.citations.map(c => c.source),
};
}
return response;
}
}
// src/types/openevidence.ts
// Update types for v3 API
export interface ClinicalQueryRequest {
question: string;
context: ClinicalContext;
options?: QueryOptions;
}
export interface ClinicalContext {
specialty: string;
urgency: 'stat' | 'urgent' | 'routine' | 'research';
patientAge?: number;
patientSex?: 'male' | 'female' | 'other';
relevantConditions?: string[];
currentMedications?: string[];
}
export interface QueryOptions {
maxCitations?: number;
includeGuidelines?: boolean;
includeDrugInfo?: boolean;
preferredSources?: string[];
}
export interface Citation {
source: string;
title: string;
authors: string[];
year: number;
doi?: string;
url?: string;
type?: 'journal' | 'guideline' | 'textbook';
evidenceLevel?: string;
}
export interface ClinicalQueryResponse {
id: string;
answer: string;
citations: Citation[];
confidence: number;
lastUpdated: string;
deepConsultAvailable: boolean;
}
// tests/migration/v2-to-v3.test.ts
import { describe, it, expect } from 'vitest';
import { OpenEvidenceMigrationAdapter } from '../../src/migration/openevidence-adapter';
describe('v2 to v3 Migration', () => {
const adapter = new OpenEvidenceMigrationAdapter({
apiKey: process.env.OPENEVIDENCE_API_KEY!,
orgId: process.env.OPENEVIDENCE_ORG_ID!,
useV3Response: false, // Test v2 compatibility
});
it('should return v2-compatible response format', async () => {
const response = await adapter.query('What is the treatment for hypertension?');
expect(response).toHaveProperty('answer');
expect(response).toHaveProperty('sources');
expect(Array.isArray((response as any).sources)).toBe(true);
});
it('should support specialty parameter', async () => {
const response = await adapter.query(
'What is the treatment for hypertension?',
{ specialty: 'cardiology' }
);
expect(response.answer).toBeDefined();
});
});
// src/config/feature-flags.ts
export const featureFlags = {
// Start at 0, gradually increase to 100
openevidence_v3_percentage: parseInt(process.env.OE_V3_PERCENTAGE || '0'),
};
export function shouldUseV3(): boolean {
return Math.random() * 100 < featureFlags.openevidence_v3_percentage;
}
// Usage in service
async function clinicalQuery(question: string) {
if (shouldUseV3()) {
return v3ClinicalQuery(question);
}
return v2ClinicalQuery(question);
}
| Migration Issue | Cause | Solution |
|---|---|---|
| Type errors | Changed response format | Update type definitions |
| Auth failures | New required fields | Add orgId to configuration |
| Missing methods | Renamed or removed | Check changelog for replacements |
| Test failures | Changed behavior | Update test expectations |
#!/bin/bash
# scripts/migrate-openevidence.sh
echo "=== OpenEvidence SDK Migration ==="
# 1. Check current version
echo "Current version:"
npm list @openevidence/sdk
# 2. Backup package-lock.json
cp package-lock.json package-lock.json.backup
# 3. Update SDK
echo "Updating to latest version..."
npm install @openevidence/sdk@latest
# 4. Run type check
echo "Running type check..."
npx tsc --noEmit || {
echo "Type errors found. Review and fix before continuing."
exit 1
}
# 5. Run tests
echo "Running tests..."
npm test || {
echo "Tests failed. Review and fix before continuing."
exit 1
}
echo "=== Migration Complete ==="
echo "New version:"
npm list @openevidence/sdk
For CI/CD integration, see openevidence-ci-integration.
Guide developers through setting up development environments with proper tools, dependencies, and configurations
Implement Exa lint rules, policy enforcement, and automated guardrails. Use when setting up code quality rules for Exa integrations, implementing pre-commit hooks, or configuring CI policy checks for Exa best practices. Trigger with phrases like "exa policy", "exa lint", "exa guardrails", "exa be...
Configure CI/CD pipelines for Documenso integrations. Use when setting up automated testing, deployment pipelines, or continuous integration for Documenso projects. Trigger with phrases like "documenso CI", "documenso GitHub Actions", "documenso pipeline", "documenso automated testing".
Build check model availability and implement fallback chains. Use when building resilient systems or handling model outages. Trigger with phrases like 'openrouter availability', 'openrouter fallback', 'openrouter model down', 'openrouter health check'.
Configure Langfuse enterprise organization management and access control. Use when implementing team access controls, configuring organization settings, or setting up role-based permissions for Langfuse projects. Trigger with phrases like "langfuse RBAC", "langfuse teams", "langfuse organization"...
Execute compliance and security auditing for Cursor usage. Triggers on "cursor compliance", "cursor audit", "cursor security review", "cursor soc2", "cursor gdpr". Use when analyzing or auditing cursor compliance audit. Trigger with phrases like "cursor compliance audit", "cursor audit", "cursor".
Configure Apollo.io CI/CD integration. Use when setting up automated testing, continuous integration, or deployment pipelines for Apollo integrations. Trigger with phrases like "apollo ci", "apollo github actions", "apollo pipeline", "apollo ci/cd", "apollo automated tests".
Create robust Python automation with full logging and safety checks. Use when tasks need complex data processing, authenticated API work, conditional file operations, or error handling beyond simple shell commands.
Configure PostHog across development, staging, and production environments. Use when setting up multi-environment deployments, configuring per-environment secrets, or implementing environment-specific PostHog configurations. Trigger with phrases like "posthog environments", "posthog staging", "po...
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.
Validate insecure deserialization checker operations. Auto-activating skill for Security Fundamentals. Triggers on: insecure deserialization checker, insecure deserialization checker Part of the Security Fundamentals skill category. Use when working with insecure deserialization checker functiona...
Manage path traversal finder operations. Auto-activating skill for Security Fundamentals. Triggers on: path traversal finder, path traversal finder Part of the Security Fundamentals skill category. Use when working with path traversal finder functionality. Trigger with phrases like "path traversa...
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience