Skip to content

Commit

Permalink
Reformat the README file of the example distributed_basic (modelsco…
Browse files Browse the repository at this point in the history
  • Loading branch information
zyzhang1130 authored Jun 7, 2024
1 parent 21c8826 commit 62bb5d8
Show file tree
Hide file tree
Showing 5 changed files with 23 additions and 7 deletions.
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -151,7 +151,7 @@ the following libraries.
- [Werewolf](https://github.com/modelscope/agentscope/blob/main/examples/game_werewolf)

- Distribution
- [Distributed Conversation](https://github.com/modelscope/agentscope/blob/main/examples/distributed_basic)
- [Distributed Conversation](https://github.com/modelscope/agentscope/blob/main/examples/distributed_conversation)
- [Distributed Debate](https://github.com/modelscope/agentscope/blob/main/examples/distributed_debate)
- [Distributed Parallel Search](https://github.com/modelscope/agentscope/blob/main/examples/distributed_search)
- [Distributed Large Scale Simulation](https://github.com/modelscope/agentscope/blob/main/examples/distributed_simulation)
Expand Down
2 changes: 1 addition & 1 deletion README_ZH.md
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@ AgentScope支持使用以下库快速部署本地模型服务。
- [狼人杀](./examples/game_werewolf)

- 分布式
- [分布式对话](./examples/distributed_basic)
- [分布式对话](./examples/distributed_conversation)
- [分布式辩论](./examples/distributed_debate)
- [分布式并行搜索](./examples/distributed_search)
- [分布式大规模仿真](./examples/distributed_simulation)
Expand Down
Original file line number Diff line number Diff line change
@@ -1,10 +1,26 @@
# Distributed Basic
# Distributed Conversation

This example run a assistant agent and a user agent as separate processes and use rpc to communicate between them.
This example will show
- How to set up and run a distributed conversation.
- How to configure and use different language models in the system.

## Background

This example demonstrates a distributed dialog system leveraging various language models. The system is designed to handle conversational AI tasks in a distributed manner, allowing for scalable and efficient dialog management.

## Tested Models

These models are tested in this example. For other models, some modifications may be needed.
- Ollama Chat (llama3_8b)
- Dashscope Chat (qwen-Max)
- Gemini Chat (gemini-pro)

## Prerequisites

Before running the example, please install the distributed version of Agentscope, fill in your model configuration correctly in `configs/model_configs.json`, and modify the `model_config_name` field in `distributed_dialog.py` accordingly.

Then, use the following command to start the assistant agent.
## Running the Example
Use the following command to start the assistant agent:

```
cd examples/distributed_basic
Expand All @@ -14,12 +30,12 @@ python distributed_dialog.py --role assistant --assistant-host localhost --assis
# please fill in the ip address of the assistant agent in the host field
```

Then, run the user agent.
Then, run the user agent:

```
python distributed_dialog.py --role user --assistant-host localhost --assistant-port 12010
# If the assistant agent is started on another machine,
# please fill in the ip address of the assistant agent in the host field
```

Now, you can chat with the assistant agent using the command line.
Now, you can chat with the assistant agent using the command line.

0 comments on commit 62bb5d8

Please sign in to comment.