Adding an example using sequential coordinator qwith 2 agents and a w…

…eb interface. Fixes wise-agents#168

README.md

@@ -10,7 +10,7 @@ Gartner’s definition of a multi-agent system is:
 
 For more details refer to our [documentation](https://wise-agents.github.io/multi_agents/#)
 
-For more information on how to build, test and experiment with the project please refer to [GETTING_STARTED.md](GETTING_STARTED.md)
+A good starting point to put the hands in the jam is checking our examples directory and follow the instructions to play with them
 
 If you want to contribute, please have a look to [CONTRIBUTING.md](CONTRIBUTING.md)
 

docs/sequential_coordinator_example.md

@@ -0,0 +1,3 @@
+{%
+    include-markdown "../examples/sequential_coordinator/README.md"
+%}

examples/README.md

@@ -1,3 +1,16 @@
 This directory contains examples of how to use the `wise-agents` multi-agent framework.
 
-1. [memory_agentic_chatbot](./memory_agentic_chatbot/README.md)
+* [memory_agentic_chatbot](./memory_agentic_chatbot/README.md)
+The example consists of two main agents:
+
+    1. **Web Interface Agent**: Simulates a web-based client for interacting with other agents.
+    2. **Intelligent Agent**: Handles requests and provides intelligent responses based on memory and context.
+* [sequential_coordinator](./sequential_coordinator/README.md)
+The example consists of four agents:
+
+    1. **Web Interface Agent**: Simulates a web-based client for interacting with coordinator agent.
+    2. **Literature Agent**: Handles requests and provides intelligent responses. Its system message says: 
+    *"You are an english literature expert. Answer questions about english literature. Try to give context to your answers and provide quote from the books described. Your user is a native english speaker, with limited background in english literature."*
+    3. **Transaltor Agent**: Handles requests and provides intelligent responses. Its system message says: 
+    *"You are an expert translator from english to italian. Translate the provided text from english to italian. "*
+    4. **SequentialCoordinator**: Take care of coordinating the request handling from the user delagating the work to other agents in a predetermined order.

examples/sequential_coordinator/README.md

@@ -0,0 +1,127 @@
+
+# Sequential Coordinator Example: Answer and Translate Chatbot
+
+This guide walks you through running a practical example of a multi-agent system using Wise Agents. In this example, four agents (a web interface agent, a sequential agent coordinator, and two intelligent agents) are started, allowing you to experiment with agent communication and interaction in a simulated environment, with a sequential coordination.
+
+
+## Example Overview
+
+The example consists of four agents:
+
+1. **Web Interface Agent**: Simulates a web-based client for interacting with coordinator agent.
+2. **Literature Agent**: Handles requests and provides intelligent responses. Its system message says: 
+*"You are an english literature expert. Answer questions about english literature. Try to give context to your answers and provide quote from the books described. Your user is a native english speaker, with limited background in english literature."*
+3. **Transaltor Agent**: Handles requests and provides intelligent responses. Its system message says: 
+*"You are an expert translator from english to italian. Translate the provided text from english to italian. "*
+4* **SequentialCoordinator**: Take care of coordinating the request handling from the user delagating the work to other agents in a predetermined order.
+
+These agents are defined in YAML configuration files located in the `examples/answer_and_translate_chatbot` directory.
+
+## Running the Example
+
+### Step 1: Clone the Repository
+
+If you haven't already, clone the Wise Agents repository from GitHub:
+
+```bash
+git clone https://github.com/wise-agents/wise-agents.git
+cd wise-agents
+```
+
+### Step 2: Configure and Start Redis
+
+In this step, we will set up Redis for agent context and registry.
+
+1. **Create a hidden directory `.wise-agents`** in the root of your project:
+
+   ```bash
+   mkdir .wise-agents
+   ```
+
+2. **Copy the Redis configuration file** as shown in the [`.wise-agents` directory](https://github.com/wise-agents/wise-agents/tree/main/.wise-agents) from the GitHub repo. Create a file named `redis-config.yaml` inside `.wise-agents`:
+
+   ```yaml
+   redis:
+     host: localhost
+     port: 6379
+   ```
+
+3. **Ensure Redis is installed and running**. You can start redis as podman/docker image following instruction in [redis README.MD](../../redis/README.MD)
+
+### Step 3: Start artemis 
+
+To support async communication between agents you need to have artemis up and running
+
+1. Start artemis podman/docker image following instructions in [artemis README.MD](../../artemis/README.MD)
+
+2. Set the environment variables for artemis secure login. If you haven't changed any configuration, starting artemis following the previous point instructions they are:
+
+```bash
+export STOMP_USER=artemis
+export STOMP_PASSWORD=artemis
+```
+
+### Step 4: Start Ollama with Llama 3.1
+
+To support the Llama model, you need to ensure that Ollama is installed and running:
+
+1. **Install Ollama** if it’s not installed already by following the [Ollama installation instructions](https://ollama.com).
+
+2. **Start Ollama with Llama 3.1**:
+
+   ```bash
+   ollama run llama3.1
+   ```
+
+This will load the Llama 3.1 model into Ollama, which is necessary for running the intelligent agent.
+
+### Step 5: Start the Intelligent Agent
+
+In a first console, run the intelligent agents and coordinator agent, also from the project’s home directory, using the following command:
+
+```bash
+python src/wiseagents/cli/wise_agent_cli.py examples/memory_agentic_chatbot/intelligent-agent.yaml
+```
+
+This will initialize the intelligent agents and coordinator agent, which will be ready to respond to requests sent by the web interface agent.
+
+
+### Step 6: Start the Web Interface Agent
+
+In your second console, navigate to the project’s home directory and run the web interface agent using the provided YAML configuration file:
+
+```bash
+python src/wiseagents/cli/wise_agent_cli.py examples/memory_agentic_chatbot/web-interface.yaml
+```
+
+This will initialize the Assitant agent with its web interface. You should see logs indicating that the agent is started and waiting for requests. You will see in the console also a web server listening at [http://127.0.0.1:7860](http://127.0.0.1:7860)
+
+```plain-text
+Running on local URL:  http://127.0.0.1:7860
+```
+
+### Step 7: Interaction
+
+Once both agents are up and running, you can use the web interface agent as a chatbot and it will start sending requests to the intelligent agent. You will be able to see the interaction between the agents through the logs in both consoles.
+Try as an example to ask something like "Can you give me detailed information about Harry Potter". You will get the detailed information about Rowling's books translated in Italian :)
+
+### Step 8: Experiment
+
+You can experiment with different agent configurations or modify the agent behaviors by editing the YAML files located in the `examples/memory_agentic_chatbot` directory. These configuration files define the agents' properties, including memory, communication methods, and response patterns. You can do that without restarting everything, just edit the yaml file(s) and use CLI's /reload command (see our documentation for more details on how to use CLI)
+
+## Understanding the YAML Configuration
+
+- **web-interface.yaml**: Defines the web interface agent, which serves as the client interface for interacting with other agents.
+- **intelligent-agent.yaml**: Defines the intelligent agents and coordinator agent, which processes the requests and generates responses based on the provided input.
+
+These YAML files include the specific `WiseAgent` classes and configuration needed to run the agents. Feel free to explore and modify these files to customize the agents' behavior.
+
+## Additional Resources
+
+For more information about the architecture and advanced configurations of wise-agents, refer to the [Wise Agents Architecture Document](wise_agents_architecture.md), which provides insights into how the system can be scaled and deployed in distributed environments.
+
+## Conclusion
+
+By following these steps, you have successfully run a simple sequential coordinated multi-agent chatbot using Wise Agents. You can now explore further by modifying agent behaviors, adding new agents, or experimenting with different message flows.
+
+For any further assistance, feel free to refer to the official Wise Agents documentation or reach out to the repository maintainers.

examples/sequential_coordinator/intelligent-agents.yaml

@@ -0,0 +1,33 @@
+---
+!wiseagents.agents.ChatWiseAgent
+_description: This is an agent that can answer questions about english licterature
+_llm: !wiseagents.llm.OpenaiAPIWiseAgentLLM
+  _model_name: llama3.1
+  _remote_address: http://localhost:11434/v1
+  _system_message: You are an english literature expert. Answer questions about english literature. Try to give context to your answers and provide quote from the books described. Your user is a native english speaker, with limited background in english literature.
+_name: LiterateAgent
+_transport:  !wiseagents.transports.StompWiseAgentTransport
+    _host: localhost
+    _port: 61616
+    _agent_name: LiterateAgent
+---
+!wiseagents.agents.ChatWiseAgent
+_description: 1This is an agent that can translate from english to italian
+_llm: !wiseagents.llm.OpenaiAPIWiseAgentLLM
+  _model_name: llama3.1
+  _remote_address: http://localhost:11434/v1
+  _system_message: You are an expert translator from english to italian. Translate the provided text from english to italian. 
+_name: TranslatorAgent
+_transport:  !wiseagents.transports.StompWiseAgentTransport
+    _host: localhost
+    _port: 61616
+    _agent_name: TranslatorAgent
+---
+!wiseagents.agents.SequentialCoordinatorWiseAgent
+_description: This is a coordinator agent
+_name: SequentialCoordinator
+_agents: ["LiterateAgent", "TranslatorAgent"]
+_transport:  !wiseagents.transports.StompWiseAgentTransport
+    _host: localhost
+    _port: 61616
+    _agent_name: SequentialCoordinator

examples/sequential_coordinator/web-interface.yaml

@@ -0,0 +1,11 @@
+---
+!wiseagents.agents.AssistantAgent
+_description: This is a test agent
+_name: AssistantAgent
+_destination_agent_name: SequentialCoordinator
+_transport:  !wiseagents.transports.StompWiseAgentTransport
+    _host: localhost
+    _port: 61616
+    _agent_name: AssistantAgent
+
+

mkdocs.yml

@@ -11,7 +11,7 @@ nav:
     - Declare agents in YAML: declare_agents.md
   - Examples:
     - Example 1: example_1.md
-    - Example 2: example_2.md
+    - Sequential Coordinator Example: sequential_coordinator_example.md
   - API Reference: reference/
   - About:
     - Community: community.md

src/wiseagents/agents/__init__.py

@@ -6,7 +6,7 @@
 
 # Optionally, you can define __all__ to specify the public interface of the package
 # __all__ = ['module1', 'module2', 'subpackage']
-from .collaboration_wise_agents import PhasedCoordinatorWiseAgent, SequentialCoordinatorWiseAgent
+from .coordinator_wise_agents import PhasedCoordinatorWiseAgent, SequentialCoordinatorWiseAgent
 from .rag_wise_agents import CoVeChallengerRAGWiseAgent, GraphRAGWiseAgent, RAGWiseAgent
 from .utility_wise_agents import PassThroughClientAgent, LLMOnlyWiseAgent, LLMWiseAgentWithTools
 from .assistant import AssistantAgent

src/wiseagents/agents/utility_wise_agents.py

@@ -388,7 +388,7 @@ def __init__(self, name: str, description: str, llm: WiseAgentLLM, transport: Wi
             description (str): a description of the agent
             llm (WiseAgentLLM): the LLM agent to use for processing requests
             transport (WiseAgentTransport): the transport to use for communication
-            system_message (Optional[str]): the optional system message to be used by the collaborator when processing
+            system_message (Optional[str]): the optional system message to be used by the agent when processing
             chat completions using its LLM
         """
         self._name = name

src/wiseagents/cli/wise_agent_cli.py

@@ -52,10 +52,10 @@ def main():
         if (user_input == '/reload-agents' or user_input == '/r'):
             for agent in agent_list:
                 agent.stop_agent()
-                reload_path = input(f'Enter the file path (ENTER for default {file_path} ): ')
-                if reload_path:
-                    file_path = reload_path
-                user_input = '/load-agents'
+            reload_path = input(f'Enter the file path (ENTER for default {file_path} ): ')
+            if reload_path:
+                file_path = reload_path
+            user_input = '/load-agents'
         if (user_input == '/load-agents' or user_input == '/l'):
             if not file_path:
                 file_path = input(f'Enter the file path (ENTER for default {default_file_path} ): ')