Tutorials

The following examples showcase many typical use cases of how to use the Imagine SDK. The code snippets are designed so that you can copy-paste and run them on your environment.

Basic usage

The tutorials about how to use the Imagine clients are a good starting point to unlock the potential of Imagine.

Basic usage

Tool calling

The tutorials about how to use the Tool Calling using Imagine clients

Tool Calling

LangChain

If you are familiar with LangChain, have a look at the LangChain examples.

LangChain

RAG

How the Imagine SDK can be used with LangChain for retrieval-augmented generation.

RAG with ChromaDB

LiteLLM

How to use liteLLM to make API calls with Imagine

LiteLLM

Agents

Use agentic frameworks like crewAI and Autogen to orchestrate powerful workflows.

CrewAI

Guarded LLM

How to introduce input and output guardrails.

Guarded LLM

Logging

How to enable logging.

Logging

Table of contents

• Basic usage
  • Available models
  • Chat
    • Streaming response
    • Asynchronous client
  • Code completion
  • Translation
  • Images
  • Transcribe audio
  • Embeddings
  • Reranking
• Tool Calling
  • Single Tool
  • Single Tool with helper functions
  • Multi-turn tool calling
  • Multiple-tools tool calling
  • Multiple-tools recursive tool calling
• LangChain
  • Using the language model
  • Chat
    • Streaming response
    • Asynchronous client
    • Prompt templates
    • Chains
  • LLM
  • Embeddings
  • RAG
  • Agents
  • Table of contents
    • LangChain Tools
      • Basic Example
      • Different ways for tools specification
      • 1. Agent Executor
      • 2. Agent Executor
      • Structured Output
    • LangChain Custom Tools
      • Perform an Internet search and summarize the results
      • Count the rows of a CSV file with a custom tool
      • Using GitHub with a custom tool
      • Using Jira with a custom tool
      • Using tools with Agents
• LiteLLM
  • Pre-requisites
  • Chat
    • Non-streaming
    • Streaming
  • Completion
  • Embedding
• CrewAI
  • Pre-requisites
  • Basic example
  • Agents with tools
• AutoGen
  • Installation
  • Basic example
• RAG with ChromaDB
  • Initial setup
  • Imports and configuration
  • RAG core functions
  • Ingestion phase
  • Query phase
• Guarded LLM
  • Create a RAG VectorDB
  • Define Input and Output checks
  • Setup the required variables
    • Create the vector store for disallowed content.
    • Completion Example
    • Normal Client Completion
    • Our Wrapped Completion
  • Applying GuardRails to other api calls
• Logging