> ## Documentation Index
> Fetch the complete documentation index at: https://docs.co-mind.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> End-to-end playbook — one Personal Access Token, everything the API offers. Follow the steps in order.

This walkthrough is the developer playbook for the co-mind.ai API. Follow the steps in order: you sign in, mint one Personal Access Token, then use that single token for every capability the platform exposes — discovery, chat, embeddings, knowledge bases with retrieval-augmented chat, web research, and translation.

Every step shows what to send and the response you should see. When something looks different in your terminal, you know exactly which step to revisit.

<Note>
  Endpoints referenced under `/v1/`. Replace `{BASE_URL}` with your deployment URL (given to you by your administrator).
</Note>

## The playbook

<CardGroup cols={2}>
  <Card title="1. Log in" icon="right-to-bracket" href="/guides/api-walkthrough/login">
    Sign in with email + password to receive a session JWT, then confirm the workspace your session is scoped to.
  </Card>

  <Card title="2. Create a PAT" icon="key" href="/guides/api-walkthrough/personal-access-token">
    Use the session JWT to mint a long-lived Personal Access Token with the scopes you need. Every step from here uses the PAT.
  </Card>

  <Card title="3. Discover models" icon="list" href="/guides/api-walkthrough/models">
    List every chat and embedding model available on your deployment.
  </Card>

  <Card title="4. Compute embeddings" icon="chart-scatter" href="/guides/api-walkthrough/embeddings">
    Turn text into vectors with an embedding-class model.
  </Card>

  <Card title="5. Chat completions" icon="comments" href="/guides/api-walkthrough/chat-completions">
    OpenAI-compatible chat — stateless, single-request-single-response.
  </Card>

  <Card title="6. Knowledge bases" icon="book" href="/guides/api-walkthrough/knowledge-bases">
    Create a KB, upload files, query for context, and chat with retrieval-augmented generation.
  </Card>

  <Card title="7. Research" icon="magnifying-glass" href="/guides/api-walkthrough/research">
    Single-shot web search and multi-step research sessions.
  </Card>

  <Card title="8. Translation" icon="language" href="/guides/api-walkthrough/translation">
    Translate text between languages with automatic source detection.
  </Card>

  <Card title="9. Manage tokens" icon="rotate" href="/guides/api-walkthrough/manage-tokens">
    List, rotate, and revoke your Personal Access Tokens.
  </Card>
</CardGroup>

## Before you start

* A running co-mind.ai deployment you can reach (see [Installation](/guides/installation))
* User credentials — email and password, or an SSO session
* `curl` in a terminal (any HTTP client works)
* Background reading (optional but useful): [Authentication](/guides/authentication), [API Tokens](/guides/api-tokens)

Ready? Start with [Log in](/guides/api-walkthrough/login).