Skip to content

Commit

Permalink
added agentic workshop
Browse files Browse the repository at this point in the history
  • Loading branch information
rcarrata committed Dec 5, 2024
1 parent 8a52193 commit 71162b9
Show file tree
Hide file tree
Showing 12 changed files with 55 additions and 4 deletions.
Binary file modified content/modules/ROOT/assets/images/04/04-02-react-diagram.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
3 changes: 2 additions & 1 deletion content/modules/ROOT/nav.adoc
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,8 @@
** xref:06-01-multi-agents.adoc[6.1 Multi-Agent Collaboration]
** xref:06-02-building-supervisors.adoc[6.2 Building Supervisors]
** xref:06-03-human-loop.adoc[6.3 Human in the Loop]
** xref:06-04-hierarchical-team-agents.adoc[6.4 Hierarchical Team Agents]
** xref:06-04-planning-agents.adoc[6.4 Planning Agents]
** xref:06-05-reflection-agents.adoc[6.5 Reflection Agents]
* 7. Enhance RAG with Agentic AI
** xref:07-01-agentic-rag.adoc[7.1 Agentic RAG]
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ context, without the complexity of managing an entire control flow.
3. **Routing**: It selects the appropriate step or tool to proceed.
4. **Execution**: The selected tool or path is executed to complete the task.
![Router Architecture Diagram](02/02-03-router-architecture.png)
image::05/05-08-agent-routing.png[Agentic Routing]

## **Examples of Router Applications**

Expand Down
2 changes: 1 addition & 1 deletion content/modules/ROOT/pages/05-06-react-implementation.adoc
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,7 @@ image::04/04-07-react-final.png[ReAct Final]

Let's see the Tool Calling and Routing Agents in Action!

From the `agentic-workshop/lab-materials/05` folder, please open the notebook called `5.1-simple-agent-routing.ipynb` and follow the instructions.
From the `agentic-workshop/lab-materials/04` folder, please open the notebook called `4.2-react-agents.ipynb` and follow the instructions.

== Advantages of ReAct Agents

Expand Down
47 changes: 46 additions & 1 deletion content/modules/ROOT/pages/06-01-multi-agents.adoc
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,49 @@
include::_attributes.adoc[]
:slide:

TBD
== Overview

Multi-agent collaboration is a powerful design pattern in Agentic AI that enables multiple agents to work
together to solve complex tasks. Instead of relying on a single agent to handle all subtasks, this approach
assigns specific roles to different agents, allowing each to specialize and contribute effectively.

By breaking down a problem into smaller, manageable subtasks and assigning them to agents with specific expertise,
this pattern leverages the divide-and-conquer approach to tackle complex scenarios more efficiently.

== How Multi-Agent Collaboration Works

1. **Task Decomposition**:
A complex problem is divided into smaller subtasks. Each subtask is assigned to an agent specializing in that domain or task.

2. **Role Assignment**:
Agents are designed or prompted for specific roles, such as "researcher" and "chart generator," each with a clear objective and behavior.

3. **Interaction and Communication**:
Agents collaborate by passing messages, sharing data, or requesting assistance from other agents to ensure task completion.

4. **Execution and Coordination**:
The agents execute their assigned subtasks and combine their results to produce the final outcome.

image::05/05-09-multi-agent.png[Multi Agent]

== Benefits of Multi-Agent Collaboration

- **Scalability**: Allows large, complex tasks to be distributed among multiple agents for faster execution.
- **Specialization**: Enables agents to focus on specific subtasks, optimizing their effectiveness.
- **Robustness**: Reduces the likelihood of errors by isolating subtasks and handling them individually.

== Example Use Case

For a task like generating insights, multi-agent collaboration might involve:

- A **Researcher Agent** to gather relevant data or information through APIs or databases.
- A **Chart Generator Agent** to process the retrieved data and create visual representations like charts or graphs.
- A **Router Agent** to manage task flow and coordinate between the Researcher and Chart Generator agents.

This modular approach ensures a streamlined workflow where each agent’s expertise contributes to solving the overall problem.

== Exercise: Multi-Agent Pattern - Practical Example

Let's see the Multi-Agent Pattern in Action!

From the `agentic-workshop/lab-materials/05` folder, please open the notebook called `5.1-multi-agent-routing.ipynb` and follow the instructions.
5 changes: 5 additions & 0 deletions content/modules/ROOT/pages/06-05-reflection-agents.adoc
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
= Reflection agents
include::_attributes.adoc[]
:slide:

TBD

0 comments on commit 71162b9

Please sign in to comment.