Skip to main content 홈 크리에이터 comeonoliver skillshub cohere-sdk-patterns
cohere-sdk-patterns Apply production-ready Cohere SDK patterns for TypeScript and Python.
Use when implementing Cohere integrations, refactoring SDK usage,
or establishing team coding standards for Cohere API v2.
Trigger with phrases like "cohere SDK patterns", "cohere best practices",
"cohere code patterns", "idiomatic cohere", "cohere wrapper".
설치로 이동 Skills Marketplace 커뮤니티가 만든 AI 스킬을 발견하고 탐색하세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/ComeOnOliver/skillshub --skill cohere-sdk-patterns명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Zip 다운로드 다운로드 중... 이 저장소의 다른 Skills Review product and feature risk before an AI coding agent starts implementation.
Use Xquik for X data and confirmation-gated X actions: tweet search, user lookup, follower export, media download, monitors, webhooks, MCP, and SDK workflows.
Canton Network open-source ecosystem guide covering DAML SDK, Canton runtime, and Splice applications. Use when working with Canton Network, DAML smart contracts, or building decentralized applications.
name cohere-sdk-patterns description Apply production-ready Cohere SDK patterns for TypeScript and Python.
Use when implementing Cohere integrations, refactoring SDK usage,
or establishing team coding standards for Cohere API v2.
Trigger with phrases like "cohere SDK patterns", "cohere best practices",
"cohere code patterns", "idiomatic cohere", "cohere wrapper".
allowed-tools Read, Write, Edit version 1.0.0 license MIT author Jeremy Longshore <jeremy@intentsolutions.io> tags ["saas","ai","nlp","cohere"] compatible-with claude-code
Cohere SDK Patterns
Overview
Production-ready patterns for the cohere-ai TypeScript SDK (CohereClientV2) and Python cohere package. Real model names, real API shapes, real error types.
Prerequisites
cohere-ai v7+ installed (TypeScript) or cohere v5+ (Python)
Familiarity with async/await patterns
Understanding of Cohere API v2 endpoints
Instructions
Pattern 1: Singleton Client with Retry
import { CohereClientV2 , CohereError , CohereTimeoutError } from 'cohere-ai' ;
let instance : CohereClientV2 | null = null ;
export function getCohere ( ): CohereClientV2 {
if (!instance) {
if (!process.env .CO_API_KEY ) {
throw new Error ('CO_API_KEY environment variable is required' );
}
instance = new CohereClientV2 ({
token : process.env .CO_API_KEY ,
});
}
return instance;
}
export async function withRetry<T>(
operation : () => Promise <T>,
maxRetries = 3 ,
baseDelayMs = 1000
): <T> {
( attempt = ; attempt <= maxRetries; attempt++) {
{
();
} (err) {
(attempt === maxRetries) err;
(err ) {
status = err. ;
(status && status !== && status < ) err;
} (!(err )) {
err;
}
delay = baseDelayMs * . ( , attempt - );
jitter = . () * ;
( (r, delay + jitter));
}
}
( );
}
Promise
for
let
1
try
return
await
operation
catch
if
throw
if
instanceof
CohereError
const
statusCode
if
429
500
throw
else
if
instanceof
CohereTimeoutError
throw
const
Math
pow
2
1
const
Math
random
500
await
new
Promise
r =>
setTimeout
throw
new
Error
'Unreachable'
Pattern 2: Type-Safe Chat Wrapper
import { getCohere, withRetry } from './client' ;
interface ChatOptions {
message : string ;
systemPrompt ?: string ;
model ?: string ;
maxTokens ?: number ;
temperature ?: number ;
documents ?: Array <{ id ?: string ; data : Record <string , string > }>;
}
export async function chat (options : ChatOptions ): Promise <string > {
const cohere = getCohere ();
const messages : Array <{ role : string ; content : string }> = [];
if (options.systemPrompt ) {
messages.push ({ role : 'system' , content : options.systemPrompt });
}
messages.push ({ role : 'user' , content : options.message });
const response = await withRetry (() =>
cohere.chat ({
model : options.model ?? 'command-a-03-2025' ,
messages,
maxTokens : options.maxTokens ,
temperature : options.temperature ,
documents : options.documents ,
})
);
return response.message ?.content ?.[0 ]?.text ?? '' ;
}
Pattern 3: Streaming Chat
export async function * streamChat (
message : string ,
model = 'command-a-03-2025'
): AsyncGenerator <string > {
const cohere = getCohere ();
const stream = await cohere.chatStream ({
model,
messages : [{ role : 'user' , content : message }],
});
for await (const event of stream) {
if (event.type === 'content-delta' ) {
const text = event.delta ?.message ?.content ?.text ;
if (text) yield text;
}
}
}
for await (const chunk of streamChat ('Explain RAG in 3 sentences' )) {
process.stdout .write (chunk);
}
Pattern 4: Batch Embedding
type InputType = 'search_document' | 'search_query' | 'classification' | 'clustering' ;
export async function embedTexts (
texts : string [],
inputType : InputType = 'search_document' ,
model = 'embed-v4.0'
): Promise <number [][]> {
const cohere = getCohere ();
const BATCH_SIZE = 96 ;
const allEmbeddings : number [][] = [];
for (let i = 0 ; i < texts.length ; i += BATCH_SIZE ) {
const batch = texts.slice (i, i + BATCH_SIZE );
const response = await withRetry (() =>
cohere.embed ({
model,
texts : batch,
inputType,
embeddingTypes : ['float' ],
})
);
allEmbeddings.push (...response.embeddings .float );
}
return allEmbeddings;
}
Pattern 5: Rerank with Type Safety
interface RerankResult {
text : string ;
score : number ;
originalIndex : number ;
}
export async function rerankDocuments (
query : string ,
documents : string [],
topN = 5 ,
model = 'rerank-v3.5'
): Promise <RerankResult []> {
const cohere = getCohere ();
const response = await withRetry (() =>
cohere.rerank ({ model, query, documents, topN })
);
return response.results .map (r => ({
text : documents[r.index ],
score : r.relevanceScore ,
originalIndex : r.index ,
}));
}
Pattern 6: Structured JSON Output export async function chatJSON<T>(
message : string ,
schema ?: Record <string , unknown >
): Promise <T> {
const cohere = getCohere ();
const response = await cohere.chat ({
model : 'command-a-03-2025' ,
messages : [{ role : 'user' , content : `${message} \n\nRespond in valid JSON.` }],
responseFormat : schema
? { type : 'json_object' , jsonSchema : schema }
: { type : 'json_object' },
});
const text = response.message ?.content ?.[0 ]?.text ?? '{}' ;
return JSON .parse (text) as T;
}
Python Equivalents import cohere
from cohere import ClientV2
_client: ClientV2 | None = None
def get_cohere () -> ClientV2:
global _client
if _client is None :
_client = ClientV2()
return _client
def chat (message: str , model: str = "command-a-03-2025" ) -> str :
co = get_cohere()
response = co.chat(
model=model,
messages=[{"role" : "user" , "content" : message}],
)
return response.message.content[0 ].text
def embed (texts: list [str ], input_type: str = "search_document" ) -> list [list [float ]]:
co = get_cohere()
response = co.embed(
model="embed-v4.0" ,
texts=texts,
input_type=input_type,
embedding_types=["float" ],
)
return response.embeddings.float
Error Handling Error Type When Recovery CohereError (status 400)Bad request params Fix request, do not retry CohereError (status 401)Invalid API key Check CO_API_KEY CohereError (status 429)Rate limited Retry with backoff CohereError (status 5xx)Server error Retry with backoff CohereTimeoutErrorNetwork timeout Retry with backoff
Resources
Next Steps Apply patterns in cohere-core-workflow-a for RAG workflows.