Skip to main content

Notebooks

This page contains a collection of notebooks that demonstrate how to use AutoGen. The notebooks are tagged with the topics they cover. For example, a notebook that demonstrates how to use function calling will be tagged with function call.

Mitigating Prompt hacking with JSON Mode in Autogen
Open In ColabStatic Badge
Use JSON mode and Agent Descriptions to mitigate prompt manipulation and control speaker transition.
JSONdescriptionprompt hackinggroup chatorchestration
Using RetrieveChat for Retrieve Augmented Code Generation and Question Answering
Open In ColabStatic Badge
Explore the use of AutoGen's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.
RAG
Using RetrieveChat Powered by PGVector for Retrieve Augmented Code Generation and Question Answering
Open In ColabStatic Badge
Explore the use of AutoGen's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.
RAG
Using RetrieveChat with Qdrant for Retrieve Augmented Code Generation and Question Answering
Open In ColabStatic Badge
This notebook demonstrates the usage of QdrantRetrieveUserProxyAgent for RAG.
rag
Agent Tracking with AgentOps
Open In ColabStatic Badge
Use AgentOps to simplify the development process and monitor your agents in production.
monitoringdebugging
AgentOptimizer: An Agentic Way to Train Your LLM Agent
Open In ColabStatic Badge
AgentOptimizer is able to prompt LLMs to iteratively optimize function/skills of AutoGen agents according to the historical conversation and performance.
optimizationtool/function
Task Solving with Code Generation, Execution and Debugging
Open In ColabStatic Badge
Use conversable language learning model agents to solve tasks and provide automatic feedback through a comprehensive example of writing, executing, and debugging Python code to compare stock price changes.
code generationdebugging
Assistants with Azure Cognitive Search and Azure Identity
Open In ColabStatic Badge
This notebook demonstrates the use of Assistant Agents in conjunction with Azure Cognitive Search and Azure Identity
RAGAzure IdentityAzure AI Search
Agent Chat with custom model loading
Open In ColabStatic Badge
Define and laod a custom model
custom model
Use AutoGen in Databricks with DBRX
Open In ColabStatic Badge
Use Databricks DBRX and Foundation Model APIs to build AutoGen applications backed by open-source LLMs.
code generationdbrxdatabricksopen sourcelakehousecustom modeldata intelligence
Task Solving with Provided Tools as Functions (Asynchronous Function Calls)
Open In ColabStatic Badge
Learn how to implement both synchronous and asynchronous function calls using AssistantAgent and UserProxyAgent in AutoGen, with examples of their application in individual and group chat settings for task execution with language models.
function calltool useasync
Writing a software application using function calls
Open In ColabStatic Badge
Equip your agent with functions that can efficiently implement features into your software application.
function callcode generationtool usesoftware engineering
Currency Calculator: Task Solving with Provided Tools as Functions
Open In ColabStatic Badge
Learn how to register function calls using AssistantAgent and UserProxyAgent in AutoGen.
function calltool use
Groupchat with Llamaindex agents
Open In ColabStatic Badge
Integrate llamaindex agents with Autogen.
reactllama indexsoftware engineering
Group Chat
Open In ColabStatic Badge
Explore the utilization of large language models in automated group chat scenarios, where agents perform tasks collectively, demonstrating how they can be configured, interact with each other, and retrieve specific information from external resources.
orchestrationgroup chat
Group Chat with Retrieval Augmented Generation
Open In ColabStatic Badge
Implement and manage a multi-agent chat system using AutoGen, where AI assistants retrieve information, generate code, and interact collaboratively to solve complex tasks, especially in areas not covered by their training data.
group chatorchestrationRAG
Group Chat with Customized Speaker Selection Method
Open In ColabStatic Badge
Introduce Group Chat with Customized Speaker Selection Method
orchestrationgroup chat
FSM - User can input speaker transition constraints
Open In ColabStatic Badge
Explore the demonstration of the Finite State Machine implementation, which allows the user to input speaker transition constraints.
orchestration
Perform Research with Multi-Agent Group Chat
Open In ColabStatic Badge
Perform research using a group chat with a number of specialized agents
group chat
StateFlow: Build Workflows through State-Oriented Actions
Open In ColabStatic Badge
StateFlow: Build Workflows through State-Oriented Actions
orchestrationgroup chatresearch
Group Chat with Coder and Visualization Critic
Open In ColabStatic Badge
Explore a group chat example using agents such as a coder and visualization agent.
group chat
Generate Dalle Images With Conversable Agents
Open In ColabStatic Badge
Generate images with conversable agents.
capabilitymultimodal
Engaging with Multimodal Models: GPT-4V in AutoGen
Open In ColabStatic Badge
In AutoGen, leveraging multimodal models can be done through two different methodologies: MultimodalConversableAgent and VisionCapability.
multimodalgpt-4v
Runtime Logging with AutoGen
Open In ColabStatic Badge
Provide capabilities of runtime logging for debugging and performance analysis.
loggingdebugging
Solving Multiple Tasks in a Sequence of Async Chats
Open In ColabStatic Badge
Use conversational agents to solve a set of tasks with a sequence of async chats.
orchestrationsequential chats
Solving Multiple Tasks in a Sequence of Chats
Open In ColabStatic Badge
Use conversational agents to solve a set of tasks with a sequence of chats.
orchestrationsequential chats
Nested Chats for Tool Use in Conversational Chess
Open In ColabStatic Badge
LLM-backed agents playing chess with each other using nested chats.
nested chattool useorchestration
Conversational Chess using non-OpenAI clients
Open In ColabStatic Badge
LLM-backed agents playing chess with each other using nested chats.
nested chattool useorchestration
Solving Complex Tasks with A Sequence of Nested Chats
Open In ColabStatic Badge
Solve complex tasks with one or more sequence chats nested as inner monologue.
nested chatsequential chatsorchestration
Solving Complex Tasks with Nested Chats
Open In ColabStatic Badge
Solve complex tasks with a chat nested as inner monologue.
nested chatorchestration
OptiGuide with Nested Chats in AutoGen
Open In ColabStatic Badge
This is a nested chat re-implementation of OptiGuide which is an LLM-based supply chain optimization framework.
nested chathierarchical chatorchestration
Chat with OpenAI Assistant using function call in AutoGen: OSS Insights for Advanced GitHub Data Analysis
Open In ColabStatic Badge
This Jupyter Notebook demonstrates how to leverage OSS Insight (Open Source Software Insight) for advanced GitHub data analysis by defining `Function calls` in AutoGen for the OpenAI Assistant.
OpenAI Assistantfunction call
Auto Generated Agent Chat: Group Chat with GPTAssistantAgent
Open In ColabStatic Badge
This Jupyter Notebook demonstrates how to use the GPTAssistantAgent in AutoGen's group chat mode, enabling collaborative task performance through automated chat with agents powered by LLMs, tools, or humans.
OpenAI Assistantgroup chat
Auto Generated Agent Chat: GPTAssistant with Code Interpreter
Open In ColabStatic Badge
This Jupyter Notebook showcases the integration of the Code Interpreter tool which executes Python code dynamically within applications.
OpenAI Assistantcode interpreter
SocietyOfMindAgent
Open In ColabStatic Badge
Explore the demonstration of the SocietyOfMindAgent in the AutoGen library, which runs a group chat as an internal monologue, but appears to the external world as a single agent, offering a structured way to manage complex interactions among multiple agents and handle issues such as extracting responses from complex dialogues and dealing with context window constraints.
orchestrationnested chat
Chatting with a teachable agent
Open In ColabStatic Badge
Learn how to persist memories across chat sessions using the Teachability capability
teachabilitycapability
Auto Generated Agent Chat: Teaching
Open In ColabStatic Badge
Teach the agent news skills using natural language
teaching
Preprocessing Chat History with `TransformMessages`
Open In ColabStatic Badge
Preprocessing chat history with `TransformMessages`
long context handlingcapability
Translating Video audio using Whisper and GPT-3.5-turbo
Open In ColabStatic Badge
Use tools to extract and translate the transcript of a video file.
whisperfunction call
Web Scraping using Apify Tools
Open In ColabStatic Badge
Scrapping web pages and summarizing the content using agents with tools.
web scrapingapifytool use
Websockets: Streaming input and output using websockets
Open In ColabStatic Badge
Websockets facilitate real-time, bidirectional communication between web clients and servers, enhancing the responsiveness and interactivity of AutoGen-powered applications.
websocketsstreaming
Solving Multiple Tasks in a Sequence of Chats with Different Conversable Agent Pairs
Open In ColabStatic Badge
Use AutoGen to solve a set of tasks with a sequence of chats.
orchestrationsequential chats
From Dad Jokes To Sad Jokes: Function Calling with GPTAssistantAgent
Open In ColabStatic Badge
This comprehensive example demonstrates the use of tools in a GPTAssistantAgent Multi-Agent System by utilizing functions such as calling an API and writing to a file.
open ai assistantgpt assistanttool use