All Notebooks
This page contains a collection of notebooks that demonstrate how to use AG2. The notebooks are tagged with the topics they cover. For example, a notebook that demonstrates how to use function calling will be tagged with tool/function.
Structured output from json configuration
Structured output from json configuration
OpenAI offers a functionality for defining a structure of the messages generated by LLMs, AutoGen enables this functionality by propagating response_format passed to your agents to the underlying client.
Agent Chat with Multimodal Models: LLaVA
Agent Chat with Multimodal Models: LLaVA
Leveraging multimodal models like llava.
Auto Generated Agent Chat: Teaching AI New Skills via Natural Language Interaction
Auto Generated Agent Chat: Teaching AI New Skills via Natural Language Interaction
Teach the agent news skills using natural language.
Group Chat with Coder and Visualization Critic
Group Chat with Coder and Visualization Critic
Explore a group chat example using agents such as a coder and visualization agent.
Auto Generated Agent Chat: Task Solving with Code Generation, Execution, Debugging & Human Feedback
Auto Generated Agent Chat: Task Solving with Code Generation, Execution, Debugging & Human Feedback
Code generation, execution, debugging and human feedback.
Group Chat
Group Chat
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.
Writing a software application using function calls
Writing a software application using function calls
Equip your agent with functions that can efficiently implement features into your software application.
DeepSeek: Adding Browsing Capabilities to AG2
DeepSeek: Adding Browsing Capabilities to AG2
DeepSeek: Adding Browsing Capabilities to AG2
Chat with OpenAI Assistant using function call in AG2: OSS Insights for Advanced GitHub Data Analysis
Chat with OpenAI Assistant using function call in AG2: OSS Insights for Advanced GitHub Data Analysis
This Jupyter Notebook demonstrates how to leverage OSS Insight (Open Source Software Insight) for advanced GitHub data analysis by defining `Function calls` in AG2 for the OpenAI Assistant.
Agent with memory using Mem0
Agent with memory using Mem0
Use Mem0 to create agents with memory.
Adding Google Search Capability to AG2
Adding Google Search Capability to AG2
Google Search
RAG OpenAI Assistants in AG2
RAG OpenAI Assistants in AG2
OpenAI Assistant with retrieval augmentation.
Translating Video audio using Whisper and GPT-3.5-turbo
Translating Video audio using Whisper and GPT-3.5-turbo
Use tools to extract and translate the transcript of a video file.
Use AG2 in Databricks with DBRX
Use AG2 in Databricks with DBRX
Use Databricks DBRX and Foundation Model APIs to build AG2 applications backed by open-source LLMs.
Use MongoDBQueryEngine to query Markdown files
Use MongoDBQueryEngine to query Markdown files
Mongo DB Query Engine
Google Drive Tools
Google Drive Tools
Google Drive Tools
Usage tracking with AG2
Usage tracking with AG2
cost calculation
Nested Chats for Tool Use in Conversational Chess
Nested Chats for Tool Use in Conversational Chess
LLM-backed agents playing chess with each other using nested chats.
Task Solving with Provided Tools as Functions (Asynchronous Function Calls)
Task Solving with Provided Tools as Functions (Asynchronous Function Calls)
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.
CaptainAgent
CaptainAgent
Introducing CaptainAgent, a powerful agent that can manage and orchestrate other agents and tools to solve complex tasks.
Group Chat with Retrieval Augmented Generation
Group Chat with Retrieval Augmented Generation
Implement and manage a multi-agent chat system using AG2, where AI assistants retrieve information, generate code, and interact collaboratively to solve complex tasks, especially in areas not covered by their training data.
Auto Generated Agent Chat: Task Solving with Langchain Provided Tools as Functions
Auto Generated Agent Chat: Task Solving with Langchain Provided Tools as Functions
Use Langchain tools.
Task Solving with Code Generation, Execution and Debugging
Task Solving with Code Generation, Execution and Debugging
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.
Config loader utility functions
Config loader utility functions
Config loader utility functions
Conversational Chess using non-OpenAI clients
Conversational Chess using non-OpenAI clients
LLM-backed agents playing chess with each other using nested chats.
Runtime Logging with AG2
Runtime Logging with AG2
Provide capabilities of runtime logging for debugging and performance analysis.
FSM - User can input speaker transition constraints
FSM - User can input speaker transition constraints
Explore the demonstration of the Finite State Machine implementation, which allows the user to input speaker transition constraints.
Tavily Search Tool
Tavily Search Tool
Tavily Search Integration with AG2
Trip planning with a FalkorDB GraphRAG agent using a Swarm
Trip planning with a FalkorDB GraphRAG agent using a Swarm
FalkorDB GraphRAG utilises a knowledge graph and can be added as a capability to agents. Together with a swarm orchestration of agents is highly effective at providing a RAG capability.
RAG with DocAgent
RAG with DocAgent
Query documents and web pages with DocAgent
Wikipedia Agent
Wikipedia Agent
Search Wikipedia with WikipediaAgent
DeepResearchAgent
DeepResearchAgent
DeepResearch Agent
`run` function examples with event processing
`run` function examples with event processing
Using run and event processing
Auto Generated Agent Chat: Collaborative Task Solving with Coding and Planning Agent
Auto Generated Agent Chat: Collaborative Task Solving with Coding and Planning Agent
Use planning agent in a function call.
Automatically Build Multi-agent System from Agent Library
Automatically Build Multi-agent System from Agent Library
Automatically build multi-agent system from agent library
From Dad Jokes To Sad Jokes: Function Calling with GPTAssistantAgent
From Dad Jokes To Sad Jokes: Function Calling with GPTAssistantAgent
Use tools in a GPTAssistantAgent Multi-Agent System by utilizing functions such as calling an API and writing to a file.
Agentic RAG workflow on tabular data from a PDF file
Agentic RAG workflow on tabular data from a PDF file
Agentic RAG workflow on tabular data from a PDF file
Auto Generated Agent Chat: Solving Tasks Requiring Web Info
Auto Generated Agent Chat: Solving Tasks Requiring Web Info
Solve tasks requiring web info.
Groupchat with Llamaindex agents
Groupchat with Llamaindex agents
Integrate llamaindex agents with Autogen.
A Uniform interface to call different LLMs
A Uniform interface to call different LLMs
Uniform interface to call different LLM.
Use ChromaDBQueryEngine to query Markdown files
Use ChromaDBQueryEngine to query Markdown files
ChromaDB Query Engine for document queries
Using Neo4j's graph database with AG2 agents for Question & Answering
Using Neo4j's graph database with AG2 agents for Question & Answering
Neo4j GraphRAG utilises a knowledge graph and can be added as a capability to agents.
Using FalkorGraphRagCapability with agents for GraphRAG Question & Answering
Using FalkorGraphRagCapability with agents for GraphRAG Question & Answering
Using FalkorGraphRagCapability with agents for GraphRAG Question & Answering
OptiGuide with Nested Chats in AG2
OptiGuide with Nested Chats in AG2
This is a nested chat re-implementation of OptiGuide which is an LLM-based supply chain optimization framework.
Use AG2 to Tune ChatGPT
Use AG2 to Tune ChatGPT
Use AG2 to Tune ChatGPT
AgentOptimizer: An Agentic Way to Train Your LLM Agent
AgentOptimizer: An Agentic Way to Train Your LLM Agent
AgentOptimizer is able to prompt LLMs to iteratively optimize function/skills of AutoGen agents according to the historical conversation and performance.
Adding Browsing Capabilities to AG2
Adding Browsing Capabilities to AG2
Adding Browsing Capabilities to AG2
Agent with memory using Mem0
Agent with memory using Mem0
Use Mem0 to create agents with memory.
Auto Generated Agent Chat: GPTAssistant with Code Interpreter
Auto Generated Agent Chat: GPTAssistant with Code Interpreter
This Jupyter Notebook showcases the integration of the Code Interpreter tool which executes Python code dynamically within applications.
RealtimeAgent in a Swarm Orchestration
RealtimeAgent in a Swarm Orchestration
Swarm Ochestration
RealtimeAgent in a Swarm Orchestration
RealtimeAgent in a Swarm Orchestration
Swarm Ochestration
RealtimeAgent in a Swarm Orchestration
RealtimeAgent in a Swarm Orchestration
Swarm Ochestration
Solving Multiple Tasks in a Sequence of Chats
Solving Multiple Tasks in a Sequence of Chats
Use conversational agents to solve a set of tasks with a sequence of chats.
SocietyOfMindAgent
SocietyOfMindAgent
Explore the demonstration of the SocietyOfMindAgent in the AG2 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.
Interactive LLM Agent Dealing with Data Stream
Interactive LLM Agent Dealing with Data Stream
Automated continual learning from new data.
Wikipedia Search Tools
Wikipedia Search Tools
Perplexity Search Integration with AG2
RealtimeAgent with local websocket connection
RealtimeAgent with local websocket connection
RealtimeAgent using websockets
Engaging with Multimodal Models: GPT-4V in AG2
Engaging with Multimodal Models: GPT-4V in AG2
Leveraging multimodal models through two different methodologies: MultimodalConversableAgent and VisionCapability.
Agent Chat with Multimodal Models: DALLE and GPT-4V
Agent Chat with Multimodal Models: DALLE and GPT-4V
Multimodal agent chat with DALL-E and GPT-4v.
Language Agent Tree Search
Language Agent Tree Search
Language Agent Tree Search.
Group Chat with Customized Speaker Selection Method
Group Chat with Customized Speaker Selection Method
Introduce group chat with customized speaker selection method.
Agent Tracking with AgentOps
Agent Tracking with AgentOps
Use AgentOps to simplify the development process and monitor your agents in production.
Using Guidance with AG2
Using Guidance with AG2
Constrained responses via guidance.
Preprocessing Chat History with `TransformMessages`
Preprocessing Chat History with `TransformMessages`
Preprocessing chat history with `TransformMessages`
Cross-Framework LLM Tool Integration with AG2
Cross-Framework LLM Tool Integration with AG2
Cross-Framework LLM Tool Integration with AG2
Making OpenAI Assistants Teachable
Making OpenAI Assistants Teachable
Teach OpenAI assistants.
Swarm Orchestration with AG2
Swarm Orchestration with AG2
Swarm Ochestration
Load the configuration including the response format
Load the configuration including the response format
Agent Quickstart Examples
Using RetrieveChat Powered by Couchbase Capella for Retrieve Augmented Code Generation and Question Answering
Using RetrieveChat Powered by Couchbase Capella for Retrieve Augmented Code Generation and Question Answering
Explore the use of AG2'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.
Use AG2 to Tune OpenAI Models
Use AG2 to Tune OpenAI Models
Use AG2 to Tune OpenAI Models
StateFlow: Build Workflows through State-Oriented Actions
StateFlow: Build Workflows through State-Oriented Actions
StateFlow: Build workflows through state-oriented actions.
Solving Complex Tasks with A Sequence of Nested Chats
Solving Complex Tasks with A Sequence of Nested Chats
Solve complex tasks with one or more sequence chats nested as inner monologue.
Structured output
Structured output
LLM providers offer functionality for defining a structure of the messages generated by LLMs, AG2 enables this functionality by propagating a `response_format`, in the LLM configuration for your agents, to the underlying client.
Auto Generated Agent Chat: Collaborative Task Solving with Multiple Agents and Human Users
Auto Generated Agent Chat: Collaborative Task Solving with Multiple Agents and Human Users
Involve multiple human users via function calls and nested chat.
Tools with Dependency Injection
Tools with Dependency Injection
Tools Dependency Injection
Generate Dalle Images With Conversable Agents
Generate Dalle Images With Conversable Agents
Generate images with conversable agents.
Auto Generated Agent Chat: Task Solving with Provided Tools as Functions
Auto Generated Agent Chat: Task Solving with Provided Tools as Functions
Register function calls using AssistantAgent and UserProxyAgent to execute python or shell code in customized ways. Demonstrating two ways of registering functions.
Auto Generated Agent Chat: Group Chat with GPTAssistantAgent
Auto Generated Agent Chat: Group Chat with GPTAssistantAgent
Use GPTAssistantAgent in group chat.
Use AG2 in Microsoft Fabric
Use AG2 in Microsoft Fabric
Use AG2 in Microsoft Fabric
(Legacy) Implement Swarm-style orchestration with GroupChat
(Legacy) Implement Swarm-style orchestration with GroupChat
(Legacy) Implement Swarm-style orchestration with GroupChat
RealtimeAgent with gemini client
RealtimeAgent with gemini client
RealtimeAgent with gemini client using websockets
Using RetrieveChat with Qdrant for Retrieve Augmented Code Generation and Question Answering
Using RetrieveChat with Qdrant for Retrieve Augmented Code Generation and Question Answering
This notebook demonstrates the usage of QdrantRetrieveUserProxyAgent for RAG.
Solving Multiple Tasks in a Sequence of Chats with Different Conversable Agent Pairs
Solving Multiple Tasks in a Sequence of Chats with Different Conversable Agent Pairs
Use AG2 to solve a set of tasks with a sequence of chats.
Perplexity Search Tool
Perplexity Search Tool
Perplexity Search Integration with AG2
Adding YouTube Search Capability to AG2
Adding YouTube Search Capability to AG2
YouTube Search Integration with AG2
Websockets: Streaming input and output using websockets
Websockets: Streaming input and output using websockets
Websockets facilitate real-time, bidirectional communication between web clients and servers, enhancing the responsiveness and interactivity of AG2-powered applications.
RealtimeAgent in a Swarm Orchestration using WebRTC
RealtimeAgent in a Swarm Orchestration using WebRTC
Swarm Ochestration
Run a standalone AssistantAgent
Run a standalone AssistantAgent
Run a standalone AssistantAgent, browsing the web using the BrowserUseTool
WebSurferAgent
WebSurferAgent
WebSurfer Agent
Chat Context Dependency Injection
Chat Context Dependency Injection
Chat Context Dependency Injection
MCP Clients
MCP Clients
MCP Clients
RealtimeAgent with WebRTC connection
RealtimeAgent with WebRTC connection
RealtimeAgent using websockets
Solving Multiple Tasks in a Sequence of Async Chats
Solving Multiple Tasks in a Sequence of Async Chats
Use conversational agents to solve a set of tasks with a sequence of async chats.
Discord, Slack, and Telegram messaging tools
Discord, Slack, and Telegram messaging tools
Adding Browsing Capabilities to AG2
Using RetrieveChat for Retrieve Augmented Code Generation and Question Answering
Using RetrieveChat for Retrieve Augmented Code Generation and Question Answering
Explore the use of AG2'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.
Assistants with Azure Cognitive Search and Azure Identity
Assistants with Azure Cognitive Search and Azure Identity
This notebook demonstrates the use of Assistant Agents in conjunction with Azure Cognitive Search and Azure Identity
Enhanced Swarm Orchestration with AG2
Enhanced Swarm Orchestration with AG2
Swarm Ochestration
Agent Chat with custom model loading
Agent Chat with custom model loading
Define and load a custom model
Perform Research with Multi-Agent Group Chat
Perform Research with Multi-Agent Group Chat
Perform research using a group chat with a number of specialized agents.
Use LLamaIndexQueryEngine to query Markdown files
Use LLamaIndexQueryEngine to query Markdown files
Use any LlamaIndex vector store as a Query Engine
Demonstrating the `AgentEval` framework using the task of solving math problems as an example
Demonstrating the `AgentEval` framework using the task of solving math problems as an example
AgentEval: a multi-agent system for assessing utility of LLM-powered applications
Agent Chat with Async Human Inputs
Agent Chat with Async Human Inputs
Async human inputs.
Group Chat with Tools
Group Chat with Tools
Group Chat with Tools
Chatting with a teachable agent
Chatting with a teachable agent
Learn how to persist memories across chat sessions using the Teachability capability
Agent Observability with OpenLIT
Agent Observability with OpenLIT
Use OpenLIT to easily monitor AI agents in production with OpenTelemetry.
ReasoningAgent - Advanced LLM Reasoning with Multiple Search Strategies
ReasoningAgent - Advanced LLM Reasoning with Multiple Search Strategies
Use ReasoningAgent for o1 style reasoning in Agentic workflows with LLMs using AG2
SQL Agent for Spider text-to-SQL benchmark
SQL Agent for Spider text-to-SQL benchmark
Natural language text to SQL query using the Spider text-to-SQL benchmark.
Supercharging Web Crawling with Crawl4AI
Supercharging Web Crawling with Crawl4AI
Supercharging Web Crawling with Crawl4AI
Solving Complex Tasks with Nested Chats
Solving Complex Tasks with Nested Chats
Solve complex tasks with a chat nested as inner monologue.
Using a local Telemetry server to monitor a GraphRAG agent
Using a local Telemetry server to monitor a GraphRAG agent
FalkorDB GraphRAG utilises a knowledge graph and can be added as a capability to agents. Together with a swarm orchestration of agents is highly effective at providing a RAG capability.
Currency Calculator: Task Solving with Provided Tools as Functions
Currency Calculator: Task Solving with Provided Tools as Functions
Learn how to register function calls using AssistantAgent and UserProxyAgent.
Auto Generated Agent Chat: Using MathChat to Solve Math Problems
Auto Generated Agent Chat: Using MathChat to Solve Math Problems
Using MathChat to Solve Math Problems
AutoBuild
AutoBuild
Automatically build multi-agent system with AgentBuilder
Using RetrieveChat Powered by MongoDB Atlas for Retrieve Augmented Code Generation and Question Answering
Using RetrieveChat Powered by MongoDB Atlas for Retrieve Augmented Code Generation and Question Answering
Explore the use of AG2'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.
OpenAI Assistants in AG2
OpenAI Assistants in AG2
Two-agent chat with OpenAI assistants.
Using RetrieveChat Powered by PGVector for Retrieve Augmented Code Generation and Question Answering
Using RetrieveChat Powered by PGVector for Retrieve Augmented Code Generation and Question Answering
Explore the use of AG2'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.
Small, Local Model (IBM Granite) Multi-Agent RAG
Small, Local Model (IBM Granite) Multi-Agent RAG
Optimizing Small, Local LLMs in Multi-Agent RAG Workflows using IBM Granite, Document Retrieval, Web Search, and Ollama
Web Scraping using Apify Tools
Web Scraping using Apify Tools
Scrapping web pages and summarizing the content using agents with tools.
Cross-Framework LLM Tool for CaptainAgent
Cross-Framework LLM Tool for CaptainAgent
Cross-Framework LLM Tool for CaptainAgent
Auto Generated Agent Chat: Function Inception
Auto Generated Agent Chat: Function Inception
Function Inception: Enable AG2 agents to update/remove functions during conversations.
Using Neo4j's native GraphRAG SDK with AG2 agents for Question & Answering
Using Neo4j's native GraphRAG SDK with AG2 agents for Question & Answering
Neo4j Native GraphRAG utilizes a knowledge graph and can be added as a capability to agents.