---
title: AutogenMultiAgent
emoji: 👁
colorFrom: pink
colorTo: gray
sdk: streamlit
sdk_version: 1.36.0
app_file: app.py
pinned: false
license: apache-2.0
---
# AutogenMultiAgent
 Autogen Multiagent 
 AutoGen is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. AutoGen aims to provide an easy-to-use and flexible framework for accelerating development and research on agentic AI, like PyTorch for Deep Learning. It offers features such as agents that can converse with other agents, LLM and tool use support, autonomous and human-in-the-loop workflows, and multi-agent conversation patterns.

## AutoGen Overview
![alt text](image-2.png)



## Code execution 


## RAG Chat
 ![alt text](image-1.png)

 Qdrant is a high-performance vector search engine/database.

This notebook demonstrates the usage of QdrantRetrieveUserProxyAgent for RAG, based on agentchat_RetrieveChat.ipynb.

RetrieveChat is a conversational system for retrieve augmented code generation and question answering. In this notebook, we demonstrate how to utilize RetrieveChat to generate code and answer questions based on customized documentations that are not present in the LLM's training dataset. RetrieveChat uses the RetrieveAssistantAgent and QdrantRetrieveUserProxyAgent, which is similar to the usage of AssistantAgent and UserProxyAgent in other notebooks (e.g., Automated Task Solving with Code Generation, Execution & Debugging)

:::info Requirements
Some extra dependencies are needed for this notebook, which can be installed via pip:

```bash
pip install "pyautogen[retrievechat-qdrant]" "flaml[automl]"
```

For more information, please refer to the [installation guide](/docs/installation/).
:::


## Groupchat with Llamaindex agents
Llamaindex agents have the ability to use planning strategies to answer user questions. They can be integrated in Autogen in easy ways

Requirements
%pip install pyautogen llama-index llama-index-tools-wikipedia llama-index-readers-wikipedia wikipedia

## Defaults
### LLM_OPTIONS
    Groq
### USECASE_OPTIONS

#### Basic Example
![alt text](basic_example.png)

#### Teachable Agent
[Teachable Agent](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_teachability)
Prompt1: who is Sachin Tiwari
Prompt2: Sachin is from jharkhand working in uk
prompt3 : who is sachin
![alt text](teachable_agent.png)

### Chat with CAG
prompt1: what is dotnet
prompt2: what is python
prompt3: what is python
prompt4: what is dotnet
prompt5: what is python

![alt text](cag_chat.png)


#### MultiAgent Chat
prompt : As a user , create a asp.net form with razor view page for health insaurance feedback page
![alt text](multiagent_chat.png)

#### MultiAgent Code Execution

![alt text](multiagent_code_execution.png) 
![alt text](image-3.png)

#### RAG Chat
prompt : Explain
docs or filename path : https://github.com/microsoft/autogen/blob/main/python/samples/agentchat_chainlit/README.md
![alt text](rag_chat.png)

#### With LLamaIndex Tool
prompt: What can i find in Tokyo related to Hayao Miyazaki and its moveis like Spirited Away?.
![alt text](with_llamatool.png)



#### AgentChat Sql Spider

### GROQ_MODEL_OPTIONS
    mixtral-8x7b-32768
    llama3-8b-8192
    llama3-70b-8192
    gemma-7b-i

## Important links
https://microsoft.github.io/autogen/docs/notebooks
https://microsoft.github.io/autogen/docs/tutorial/code-executors
https://microsoft.github.io/autogen/docs/tutorial/tool-use