Merge pull request #138 from fanweixiao/main

docs: add yomo framework readme
2025-02-22 13:48:59 -05:00 · 2025-02-08 14:35:35 +08:00 · 2025-02-08 14:35:35 +08:00 · 86d71cbd63
commit 86d71cbd63
parent 24b9eda729 9974dce9a1
3 changed files with 157 additions and 1 deletions
--- a/README.md
+++ b/README.md
@ -189,6 +189,11 @@ English/[简体中文](https://github.com/deepseek-ai/awesome-deepseek-integrati
 ### AI Agent frameworks

 <table>
+    <tr>
+        <td><img src="https://yomo.run/yomo-logo.png" alt="Icon" width="64" height="auto" /></td>
+        <td><a href="https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/yomo/README.md">YoMo</a></td>
+        <td>Stateful Serverless LLM Function Calling Framework with Strongly-typed Language Support</td>
+     </tr>
    <tr>
        <td> <img src="https://raw.githubusercontent.com/superagentxai/superagentX/refs/heads/master/docs/logo/icononly_transparent_nobuffer.png" alt="Icon" width="64" height="auto" /> </td>
        <td> <a href="https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/superagentx/README.md">SuperAgentX</a> </td>
@ -199,7 +204,7 @@ English/[简体中文](https://github.com/deepseek-ai/awesome-deepseek-integrati
        <td> <a href="https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/anda/README.md">Anda</a> </td>
        <td>A Rust framework for AI agent development, designed to build a highly composable, autonomous, and perpetually memorizing network of AI agents.</td>
    </tr>
-    <tr>
+     <tr>
        <td> <img src="https://raw.githubusercontent.com/longevity-genie/chat-ui/11c6647c83f9d2de21180b552474ac5ffcf53980/static/geneticsgenie/icon-128x128.png" alt="Icon" width="64" height="auto"/> </td>
        <td> <a href="https://github.com/longevity-genie/just-agents">Just-Agents</a> </td>
        <td>A lightweight, straightforward library for LLM agents - no over-engineering, just simplicity!</td>
--- a/README_cn.md
+++ b/README_cn.md
@ -152,6 +152,11 @@
        <td>一个专为 AI 智能体开发设计的 Rust 语言框架，致力于构建高度可组合、自主运行且具备永久记忆能力的 AI 智能体网络。</td>
    </tr>
    <tr>
+        <td><img src="https://yomo.run/yomo-logo.png" alt="Icon" width="64" height="auto" /></td>
+        <td><a href="https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/yomo/README.md">YoMo</a></td>
+        <td>Stateful Serverless LLM Function Calling Framework with Strongly-typed Language Support</td>
+  </tr>
+  <tr>
        <td> <img src="https://alice.fun/alice-logo.png" alt="图标" width="64" height="auto" /> </td>
        <td> <a href="https://github.com/bob-robert-ai/bob/blob/main/alice/readme.md">Alice</a> </td>
        <td>一个基于 ICP 的自主 AI 代理，利用 DeepSeek 等大型语言模型进行链上决策。Alice 结合实时数据分析和独特的个性，管理代币、挖掘 BOB 并参与生态系统治理。</td>
--- a/docs/yomo/README.md
+++ b/docs/yomo/README.md
@ -0,0 +1,146 @@
+# YoMo Framework - Deepseek Provider
+
+YoMo is an open-source LLM Function Calling Framework for building Geo-distributed AI agents. Built atop QUIC Transport Protocol and Strongly-typed Stateful Serverless architecture, makes your AI agents low-latency, reliable, secure, and easy.
+
+## 🚀 Getting Started
+
+Let's implement a function calling serverless `sfn-get-ip-latency`:
+
+### Step 1. Install CLI
+
+```bash
+curl -fsSL https://get.yomo.run | sh
+```
+
+### Step 2. Start the server
+
+Prepare the configuration as `my-agent.yaml`
+
+```yaml
+name: ai-zipper
+host: 0.0.0.0
+port: 9000
+
+auth:
+  type: token
+  token: SECRET_TOKEN
+
+bridge:
+  ai:
+    server:
+      addr: 0.0.0.0:9000 ## Restful API endpoint
+      provider: deepseek ## LLM API Service we will use
+
+    providers:
+      deepseek:
+        api_key: <DEEPSEEK_API_KEY>
+        model: deepseek-reasoner
+```
+
+Start the server:
+
+```sh
+YOMO_LOG_LEVEL=debug yomo serve -c my-agent.yaml
+```
+
+### Step 3. Write the function
+
+First, let's define what this function do and how's the parameters required, these will be combined to prompt when invoking LLM.
+
+```golang
+type Parameter struct {
+	Domain string `json:"domain" jsonschema:"description=Domain of the website,example=example.com"`
+}
+
+func Description() string {
+	return `if user asks ip or network latency of a domain, you should return the result of the giving domain. try your best to dissect user expressions to infer the right domain names`
+}
+
+func InputSchema() any {
+	return &Parameter{}
+}
+```
+
+Create a Stateful Serverless Function to get the IP and Latency of a domain:
+
+```golang
+func Handler(ctx serverless.Context) {
+	var msg Parameter
+	ctx.ReadLLMArguments(&msg)
+
+	// get ip of the domain
+	ips, _ := net.LookupIP(msg.Domain)
+
+	// get ip[0] ping latency
+	pinger, _ := ping.NewPinger(ips[0].String())
+	pinger.Count = 3
+	pinger.Run()
+	stats := pinger.Statistics()
+
+	val := fmt.Sprintf("domain %s has ip %s with average latency %s", msg.Domain, ips[0], stats.AvgRtt)
+	ctx.WriteLLMResult(val)
+}
+
+```
+
+Finally, let's run it
+
+```bash
+$ yomo run app.go
+
+time=2025-01-29T21:43:30.583+08:00 level=INFO msg="connected to zipper" component=StreamFunction sfn_id=B0ttNSEKLSgMjXidB11K1 sfn_name=fn-get-ip-from-domain zipper_addr=localhost:9000
+time=2025-01-29T21:43:30.584+08:00 level=INFO msg="register ai function success" component=StreamFunction sfn_id=B0ttNSEKLSgMjXidB11K1 sfn_name=fn-get-ip-from-domain zipper_addr=localhost:9000 name=fn-get-ip-from-domain tag=16
+```
+
+### Done, let's have a try
+
+```sh
+$ curl -i http://127.0.0.1:9000/v1/chat/completions -H "Content-Type: application/json" -d '{
+  "messages": [
+    {
+      "role": "system",
+      "content": "You are a test assistant."
+    },
+    {
+      "role": "user",
+      "content": "Compare website speed between Nike and Puma"
+    }
+  ],
+  "stream": false
+}'
+
+HTTP/1.1 200 OK
+Content-Length: 944
+Connection: keep-alive
+Content-Type: application/json
+Date: Wed, 29 Jan 2025 13:30:14 GMT
+Keep-Alive: timeout=4
+Proxy-Connection: keep-alive
+
+{
+  "Content": "Based on the data provided for the domains nike.com and puma.com which include IP addresses and average latencies, we can infer the following about their website speeds:
+  - Nike.com has an IP address of 13.225.183.84 with an average latency of 65.568333 milliseconds.
+  - Puma.com has an IP address of 151.101.194.132 with an average latency of 54.563666 milliseconds.
+  
+  Comparing these latencies, Puma.com is faster than Nike.com as it has a lower average latency. 
+  
+  Please be aware, however, that website speed can be influenced by many factors beyond latency, such as server processing time, content size, and delivery networks among others. To get a more comprehensive understanding of website speed, you would need to consider additional metrics and possibly conductreal-time speed tests.",
+  "FinishReason": "stop"
+}
+```
+
+### Full Example Code
+
+[Full LLM Function Calling Codes](https://github.com/yomorun/llm-function-calling-examples)
+
+## 🎯 Focuses on Geo-distributed AI Inference Infra
+
+It’s no secret that today’s users want instant AI inference, every AI 
+application is more powerful when it response quickly. But, currently, when we
+talk about `distribution`, it represents **distribution in data center**. The AI model is
+far away from their users from all over the world.
+
+If an application can be deployed anywhere close to their end users, solve the
+problem, this is **Geo-distributed System Architecture**:
+
+<img width="580" alt="yomo geo-distributed system" src="https://user-images.githubusercontent.com/65603/162367572-5a0417fa-e2b2-4d35-8c92-2c95d461706d.png">