Documentation

Prompt Engineering Guide

Platform

Support

3) Control Output Format

This guide is designed to provide you with an in-depth understanding of our product's functions and capabilities, along with best practices we have gathered over time.

Introduction

Functionalities

Description of the different chat capabilities like image generation, document search or data analysis.

Chat capabilities

Learn what the difference between chats and assistants is.

Assistants vs. Chat

The Assistant library is the pplace where you can find your assistants and the assistants others created and shared.

Assistant Library

Simplify your daily tasks together with our Assistants. This guide will help you to build your first with assistant.

Building an Assistant

Prompt Library

One of our core-values is to build a tool which is model-agnostic. That means, that we do not want to trap the user in one model, but give the choice which model to use. Each model has different strengths and we encourage you to test the different models to find the best models for your specific need.

Models

Provide custom instructions to improve responses.

Custom instructions

Use Langdock models and Assistants directly in Slack

Slack Bot

Creates a model response for the given chat conversation.

Chat Completion

Learn how to use Integrations in the chat and in assistants.

How to use Integrations

Langdock supports personal integrations and workspace integrations.  Both provide similar functionality to the Langdock user, but they differ in capability and setup complexity. In the following, we will provide guidance on when to use which integration type.

Personal vs. Workspace Integrations

Connect Integrations for one individual user only.

Personal Integrations (OAuth2)

Connect Google Drive for every user in your workspace.

Google Drive

Connect Confluence for every user in your workspace.

Confluence

Install the Langdock App in Slack and use your models and Assistants directly in Slack

We distinguish between Account Settings, which influence only your personal account, and Workspace Settings, which impact the entire workspace. 

Account Settings

We distinguish between Account Settings, which influence only your personal account, and Workspace Settings, which impact the entire workspace.

Workspace Settings

Enable your users to sign in into Langdock using their Entra ID (formerly Azure Active Directory) accounts via SAML.

Microsoft Entra ID

Enable your users to sign in into Langdock using their Google accounts via SAML.

Google SAML

This page is under constructions. Stay tuned!

SCIM

Prompt engineering is a relatively new discipline that gained popularity in the early 2020s as researchers and practitioners sought to optimize the performance of large language models (LLMs) like GPT-3 and GPT-4.

Before you start exploring our guide, you might wonder what level of knowledge in Prompt Engineering you have. We have defined three levels so you can immediately jump into the most relevant section for you.

Types of Prompt Engineers

Prompt elements are components used to craft effective prompts for interactions with LLMs. These elements help structure the prompt to ensure the LLM provides useful, relevant, and personalized responses. You don’t need to use all five elements every time, but using a few will help.

Prompt Elements

1) Clear and Specific Instructions

2) Structure Your Prompt

4) Chain Prompts

5) Context Window Tricks

6) Give the LLM a Role

Zero-shot Prompting

Few-shot Prompting

Chain-of-Thought Prompting

Discover some valuable insights we have gathered over time and are excited to share with you. Dive in to discover how to craft clear, effective prompts and avoid common pitfalls, ensuring you get the best possible responses every time.

Tips & Tricks

If you want to deepen your understanding further, we have collected some additional resources for you.

Further Resources

Here we have collected key terms and concepts in prompt engineering and AI for you.

Getting started

Prompt Engineering

Knowledge

3) Control Output Format