@aigne/example-workflow-sequential 1.17.87-beta → 1.17.87-beta.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +43 -25
  2. package/package.json +6 -6
package/README.md CHANGED
@@ -40,9 +40,9 @@ class formatProof processing
40
40
 
41
41
  ## Quick Start (No Installation Required)
42
42
 
43
- ```bash
44
- export OPENAI_API_KEY=YOUR_OPENAI_API_KEY # Set your OpenAI API key
43
+ ### Run the Example
45
44
 
45
+ ```bash
46
46
  # Run in one-shot mode (default)
47
47
  npx -y @aigne/example-workflow-sequential
48
48
 
@@ -53,44 +53,62 @@ npx -y @aigne/example-workflow-sequential --chat
53
53
  echo "Create marketing content for our new AI-powered fitness app" | npx -y @aigne/example-workflow-sequential
54
54
  ```
55
55
 
56
- ## Installation
56
+ ### Connect to an AI Model
57
57
 
58
- ### Clone the Repository
58
+ As an example, running `npx -y @aigne/example-workflow-sequential --chat` requires an AI model. If this is your first run, you need to connect one.
59
+
60
+ ![run example](./run-example.png)
61
+
62
+ - Connect via the official AIGNE Hub
63
+
64
+ Choose the first option and your browser will open the official AIGNE Hub page. Follow the prompts to complete the connection. If you're a new user, the system automatically grants 400,000 tokens for you to use.
65
+
66
+ ![connect to official aigne hub](../images/connect-to-aigne-hub.png)
67
+
68
+ - Connect via a self-hosted AIGNE Hub
69
+
70
+ Choose the second option, enter the URL of your self-hosted AIGNE Hub, and follow the prompts to complete the connection. If you need to set up a self-hosted AIGNE Hub, visit the Blocklet Store to install and deploy it: [Blocklet Store](https://store.blocklet.dev/blocklets/z8ia3xzq2tMq8CRHfaXj1BTYJyYnEcHbqP8cJ?utm_source=www.arcblock.io&utm_medium=blog_link&utm_campaign=default&utm_content=store.blocklet.dev#:~:text=%F0%9F%9A%80%20Get%20Started%20in%20Minutes).
71
+
72
+ ![connect to self hosted aigne hub](../images/connect-to-self-hosted-aigne-hub.png)
73
+
74
+ - Connect via a third-party model provider
75
+
76
+ Using OpenAI as an example, you can configure the provider's API key via environment variables. After configuration, run the example again:
59
77
 
60
78
  ```bash
61
- git clone https://github.com/AIGNE-io/aigne-framework
79
+ export OPENAI_API_KEY="" # Set your OpenAI API key here
62
80
  ```
81
+ For more details on third-party model configuration (e.g., OpenAI, DeepSeek, Google Gemini), see [.env.local.example](./.env.local.example).
63
82
 
64
- ### Install Dependencies
83
+ After configuration, run the example again.
65
84
 
66
- ```bash
67
- cd aigne-framework/examples/workflow-sequential
85
+ ### Debugging
68
86
 
69
- pnpm install
70
- ```
87
+ The `aigne observe` command starts a local web server to monitor and analyze agent execution data. It provides a user-friendly interface to inspect traces, view detailed call information, and understand your agent’s behavior during runtime. This tool is essential for debugging, performance tuning, and gaining insight into how your agent processes information and interacts with tools and models.
88
+
89
+ Start the observation server.
71
90
 
72
- ### Setup Environment Variables
91
+ ![aigne-observe-execute](../images/aigne-observe-execute.png)
92
+
93
+ View a list of recent executions.
94
+
95
+ ![aigne-observe-list](../images/aigne-observe-list.png)
96
+
97
+ ## Installation
73
98
 
74
- Setup your OpenAI API key in the `.env.local` file:
99
+ ### Clone the Repository
75
100
 
76
101
  ```bash
77
- OPENAI_API_KEY="" # Set your OpenAI API key here
102
+ git clone https://github.com/AIGNE-io/aigne-framework
78
103
  ```
79
104
 
80
- #### Using Different Models
81
-
82
- You can use different AI models by setting the `MODEL` environment variable along with the corresponding API key. The framework supports multiple providers:
105
+ ### Install Dependencies
83
106
 
84
- * **OpenAI**: `MODEL="openai:gpt-4.1"` with `OPENAI_API_KEY`
85
- * **Anthropic**: `MODEL="anthropic:claude-3-7-sonnet-latest"` with `ANTHROPIC_API_KEY`
86
- * **Google Gemini**: `MODEL="gemini:gemini-2.0-flash"` with `GEMINI_API_KEY`
87
- * **AWS Bedrock**: `MODEL="bedrock:us.amazon.nova-premier-v1:0"` with AWS credentials
88
- * **DeepSeek**: `MODEL="deepseek:deepseek-chat"` with `DEEPSEEK_API_KEY`
89
- * **OpenRouter**: `MODEL="openrouter:openai/gpt-4o"` with `OPEN_ROUTER_API_KEY`
90
- * **xAI**: `MODEL="xai:grok-2-latest"` with `XAI_API_KEY`
91
- * **Ollama**: `MODEL="ollama:llama3.2"` with `OLLAMA_DEFAULT_BASE_URL`
107
+ ```bash
108
+ cd aigne-framework/examples/workflow-sequential
92
109
 
93
- For detailed configuration examples, please refer to the `.env.local.example` file in this directory.
110
+ pnpm install
111
+ ```
94
112
 
95
113
  ### Run the Example
96
114
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@aigne/example-workflow-sequential",
3
- "version": "1.17.87-beta",
3
+ "version": "1.17.87-beta.1",
4
4
  "description": "A demonstration of using AIGNE Framework to build a sequential workflow",
5
5
  "author": "Arcblock <blocklet@arcblock.io> https://github.com/blocklet",
6
6
  "homepage": "https://github.com/AIGNE-io/aigne-framework/tree/main/examples/workflow-sequential",
@@ -16,14 +16,14 @@
16
16
  "README.md"
17
17
  ],
18
18
  "dependencies": {
19
- "@aigne/agent-library": "^1.23.0-beta",
20
- "@aigne/cli": "^1.58.0-beta",
21
- "@aigne/core": "^1.71.0-beta",
22
- "@aigne/openai": "^0.16.15-beta"
19
+ "@aigne/agent-library": "^1.23.0-beta.1",
20
+ "@aigne/cli": "^1.58.0-beta.1",
21
+ "@aigne/core": "^1.71.0-beta.1",
22
+ "@aigne/openai": "^0.16.15-beta.1"
23
23
  },
24
24
  "devDependencies": {
25
25
  "@types/bun": "^1.2.22",
26
- "@aigne/test-utils": "^0.5.68-beta"
26
+ "@aigne/test-utils": "^0.5.68-beta.1"
27
27
  },
28
28
  "scripts": {
29
29
  "start": "bun run index.ts",