Skip to main content ホーム クリエイター jeremylongshore tons-of-skills-marketplace 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".
インストールへ移動 Skills Marketplace コミュニティが作成したAIスキルを発見・探索
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill cohere-sdk-patternsコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか?SkillsMP が現在取得できるファイルをダウンロードできます。
Zipをダウンロード ダウンロード中... このリポジトリの他の Skills langchain-deploy-integration Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — with timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, and Secret Manager over .env. Use when prepping a first production deploy, debugging a stream that hangs behind a proxy, or diagnosing p99 latency spikes. Trigger with "langchain deploy", "langchain cloud run", "langchain vercel python", "langchain langserve", or "langchain docker".
langchain-langgraph-agents Build a correct LangGraph 1.0 ReAct agent with create_react_agent — typed tools, error propagation, recursion caps, and stop conditions that actually stop. Use when writing a first tool-calling agent, migrating from AgentExecutor or initialize_agent, or diagnosing an agent that loops on vague prompts. Trigger with "langgraph agent", "create_react_agent", "langgraph tool calling", "AgentExecutor migration", or "agent loop cost".
langchain-langgraph-human-in-loop Build LangGraph 1.0 human-in-the-loop approval flows with interrupt_before /
interrupt_after and Command(resume=...) — JSON-serializable state, clean
resume semantics, and UI wiring for approval decisions. Use when adding an
approval gate before an expensive tool call, wiring a Slack/web UI for agent
approvals, or debugging a graph that crashes on interrupt.
Trigger with "langgraph human in loop", "langgraph interrupt_before",
"langgraph approval flow", "Command resume", "langgraph HITL".
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 1.5.0 license MIT author Jeremy Longshore <jeremy@intentsolutions.io> tags ["saas","ai","nlp","cohere"] compatibility Designed for 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.