AgentisLabs commited on
Commit
cb94c77
·
verified ·
1 Parent(s): 3fb3652

Delete readme.md

Browse files
Files changed (1) hide show
  1. readme.md +0 -43
readme.md DELETED
@@ -1,43 +0,0 @@
1
- ---
2
- title: multi-agent
3
- app_file: company_info_search.py
4
- sdk: gradio
5
- sdk_version: 5.1.0
6
- ---
7
- # Multi-Agent Swarm
8
-
9
- This example demonstrates a multi-agent swarm with three agents: an Enhancer, an Executor, and a Checker. The agents work together to process user queries and provide well-thought-out, verified responses.
10
-
11
- ## Setup
12
-
13
- To run this example:
14
-
15
- 1. Ensure you have installed the Swarm framework as described in the main README.
16
- 2. Set up your `.env` file in the root directory with the necessary API key:
17
- ```
18
- OPENAI_API_KEY=your_openai_api_key_here
19
- ```
20
- 3. Navigate to this directory:
21
- ```
22
- cd examples/multi_agent_swarm
23
- ```
24
- 4. Run the example:
25
- ```
26
- python multi_agent_swarm.py
27
- ```
28
-
29
- ## Agents
30
-
31
- 1. **Enhancer Agent**: Enhances user prompts by adding instructions for reasoning steps and chain of thought.
32
- 2. **Executor Agent**: Executes the enhanced prompts and provides detailed, well-thought-out responses.
33
- 3. **Checker Agent**: Checks responses for correctness, approves correct ones, and edits/improves incorrect ones.
34
-
35
- ## Process Flow
36
-
37
- 1. User input is received by the Enhancer Agent.
38
- 2. Enhancer Agent enhances the prompt and transfers to the Executor Agent.
39
- 3. Executor Agent processes the enhanced prompt and transfers the response to the Checker Agent.
40
- 4. Checker Agent verifies the response. If correct, it's shown to the user. If not, it's edited and the process restarts from the Enhancer Agent.
41
-
42
- This example uses the `run_demo_loop` helper function to create an interactive Swarm session.
43
-