Console SDK

@cognipeer/console-sdk · Around Console

stable

Official TypeScript/JavaScript SDK for Cognipeer Console. Provides type-safe access to chat completions, embeddings, vector operations, file management, agent tracing, and guardrails.

Quickstart GitHub Full docs

License · MITTypeScript · 100%Audience · Application teams integrating…Fits · Console APIs from TypeScript

Console APIs from TypeScriptRAG and vector workflowsTyped platform integrationBrowse recipes

Production install

$npm install @cognipeer/console-sdk

What's in the box

Application teams integrating with a Cognipeer Console deployment for chat, embeddings, vector, files, tracing, and guardrails. Each capability is opt-in — use the parts that fit, leave the rest.

Chat Completions

OpenAI-compatible chat API with streaming support for real-time responses.

Embeddings

Text vectorization for semantic search and RAG pipelines.

Vector Operations

Manage vector databases (Pinecone, Chroma, Qdrant, etc.) through a unified API.

File Management

Upload and manage files with optional markdown conversion for RAG ingestion.

Agent Tracing

Observability for agent executions with structured session data.

Guardrails

Evaluate content against tenant guardrail policies.

Type-Safe

Full TypeScript support with comprehensive types and ESM + CJS compatibility.

How it runs

A typed TypeScript client that wraps the Console API surface — chat, embeddings, vectors, files, tracing, and guardrails — with full streaming support.

Step 1

Configure

API key · base URL

Step 2

Chat / Embed

Step 3

Vectors / Files

Step 4

Guardrails

Step 5

Trace

Modules

chat.completions
embeddings
vectors
files

Operational

tracing
guardrails
Streaming
Typed errors

Compatibility

Node + Bun + Deno
ESM + CJS
OpenAI-compatible
Console gateway

Quickstart

Install, configure, run. The example below is the smallest piece of code that does something useful in production.

import  { Cognipeer } from "@cognipeer/console-sdk";
 
const cp = new Cognipeer({
  baseUrl: env.CP_BASE_URL,
  apiKey: env.CP_API_KEY,
});
 
const res = await cp.chat.completions.create({
  model: "gpt-4.1",
  messages: [{ role: "user", content: "Hi" }],
});

How it compares

Against the around console options teams most often weigh — focused on operational concerns, not feature inventories.

Capability	Console SDK	OpenAI Node SDK	LangChain JS
Chat API	● native	● native	● native
Embeddings	● native	● native	● native
Vector Ops	● native	○ missing	◐ partial
File Mgmt	● native	● native	○ missing
Tracing	● native	○ missing	◐ partial
Guardrails	● native	○ missing	○ missing