Refactor: update the doc to support compute network v0.1.1 (#114)

Author: Ravenyjh

docs/build-with-0g/compute-network/provider.md

@@ -85,6 +85,9 @@ Please visit the [releases page](https://github.com/0glabs/0g-serving-broker/rel
 - Copy the `config.example.yaml` file.
 - Modify `servingUrl` to point to your publicly exposed URL.
 - Set `privateKeys` to your wallet's private key for the 0G blockchain.
+- Set `servingUrl` to your service's public URL.
+- Set `targetUrl` to your internal URL corresponding to the prepared LLM service.
+- Set `model` to the model name of your LLM service.
 - Save the file as `config.local.yaml`.
 - Replace `#PORT#` in `docker-compose.yml` with the port you want to use. It should be the same as the port of `servingUrl` in `config.local.yaml`.
 
@@ -94,36 +97,4 @@ Please visit the [releases page](https://github.com/0glabs/0g-serving-broker/rel
 docker compose -f docker-compose.yml up -d
 ```
 
-### Key Commands
-
-1. **Register the Service**
-
-   The compute network currently supports `chatbot` services. Additional services are in the pipeline to be released soon.
-
-   ```bash
-   curl -X POST http://127.0.0.1:<PORT>/v1/service \
-   -H "Content-Type: application/json" \
-   -d '{
-         "URL": "<endpoint_of_the_prepared_service>",
-         "inputPrice": "10000000",
-         "outputPrice": "20000000",
-         "Type": "chatbot",
-         "Name": "llama8Bb",
-         "Model": "llama-3.1-8B-Instruct",
-         "verifiability":"TeeML"
-   }'
-   ```
-
-   - `inputPrice` and `outputPrice` vary by service type, for `chatbot`, they represent the cost per token. The unit is in neuron. 1 A0GI = 1e18 neuron.
-
-2. **Settle the Fee**
-
-   ```bash
-   curl -X POST http://127.0.0.1:<PORT>/v1/settle
-   ```
-
-   - The provider broker has an automatic settlement engine that ensures you can collect fees promptly before your customer's account balance is insufficient, while also minimizing the frequency of charges to reduce gas consumption.
-
-### Additional API Information
-
-For more details, please refer to the <a href="/html/compute-network-provider-api.html" target="_blank" rel="noopener noreferrer">API Page</a>.
+The provider broker has an automatic settlement engine that ensures you can collect fees promptly before your customer's account balance is insufficient, while also minimizing the frequency of charges to reduce gas consumption.

docs/build-with-0g/compute-network/sdk.md

@@ -9,7 +9,7 @@ import TabItem from '@theme/TabItem';
 
 ## Overview
 
-The 0G Compute Network SDK enables developers to integrate AI inference services from the 0G Compute Network into their applications. Currently, the 0G Compute Network SDK supports Large Language Model (LLM) inference services, with fine-tuning and additional features planned for future releases. 
+The 0G Compute Network SDK enables developers to integrate AI inference services from the 0G Compute Network into their applications. Currently, the 0G Compute Network SDK supports Large Language Model (LLM) inference services, with fine-tuning and additional features planned for future releases.
 
 In just five minutes, you can initialize your broker to manage operations, set up and fund your account to pay for services, and learn how to send requests and handle responses.
 
@@ -35,13 +35,15 @@ pnpm add @0glabs/0g-serving-broker @types/[email protected] [email protected]
 The broker is your main interface to the 0G Compute Network. It handles authentication, billing, and service communication.
 
 Before initializing the broker, you need:
+
 1. A wallet signer (implements either `JsonRpcSigner` or `Wallet` from ethers package)
 2. (Optional) The contract address for the 0G Serving contract
 
 **Option 1: Using a private key**
+
 ```typescript
 const { ethers } = require("ethers");
-const { createZGServingNetworkBroker } = require("@0glabs/0g-serving-broker");
+const { createZGComputeNetworkBroker } = require("@0glabs/0g-serving-broker");
 
 const provider = new ethers.JsonRpcProvider("https://evmrpc-testnet.0g.ai");
 
@@ -50,25 +52,26 @@ const privateKey = "INPUT_PRIVATE_KEY_HERE";
 const wallet = new ethers.Wallet(privateKey, provider);
 
 // Initialize broker
-const broker = await createZGServingNetworkBroker(wallet);
+const broker = await createZGComputeNetworkBroker(wallet);
 ```
 
 **Option 2: Using a browser wallet**
+
 ```typescript
 import { BrowserProvider } from "ethers";
-import { createZGServingNetworkBroker } from "@0glabs/0g-serving-broker";
+import { createZGComputeNetworkBroker } from "@0glabs/0g-serving-broker";
 
 async function initializeBrokerWithWallet() {
   // Ensure wallet is installed
-  if (typeof window.ethereum !== 'undefined') {
+  if (typeof window.ethereum !== "undefined") {
     // Create a provider
     const provider = new BrowserProvider(window.ethereum);
-    
+
     // Get the signer
     const signer = await provider.getSigner();
-    
+
     // Initialize broker
-    const broker = await createZGServingNetworkBroker(signer);
+    const broker = await createZGComputeNetworkBroker(signer);
   }
 }
 ```
@@ -80,57 +83,70 @@ async function initializeBrokerWithWallet() {
 The 0G Compute Network hosts multiple AI service providers. The service discovery process helps you find and select the appropriate services for your needs.
 
 ```typescript
-const services = await broker.listService();
+const services = await broker.inference.listService();
 ```
 
 Each service contains the following information:
+
 ```typescript
 type ServiceStructOutput = {
-  provider: string;  // Provider's wallet address (unique identifier)
-  name: string;      // Service name
+  provider: string; // Provider's wallet address (unique identifier)
   serviceType: string; // Type of service
-  url: string;       // Service URL
+  url: string; // Service URL
   inputPrice: bigint; // Price for input processing
   outputPrice: bigint; // Price for output generation
-  updatedAt: bigint;  // Last update timestamp
-  model: string;      // Model identifier
-  verifiability: string // Indicates how the service's outputs can be verified. 'TeeML' means it runs with verification in a Trusted Execution Environment. An empty value means no verification.
+  updatedAt: bigint; // Last update timestamp
+  model: string; // Model identifier
+  verifiability: string; // Indicates how the service's outputs can be verified. 'TeeML' means it runs with verification in a Trusted Execution Environment. An empty value means no verification.
 };
 ```
 
+Currently, we provide two official services:
+
+1. **llama-3.3-70b-instruct**
+
+- Provider address: `0xf07240Efa67755B5311bc75784a061eDB47165Dd`
+
+2. **deepseek-r1-70b**
+
+- Provider address: `0x3feE5a4dd5FDb8a32dDA97Bed899830605dBD9D3`
+
 ### Account Management
 
 The 0G Compute Network uses a prepaid account system for each provider. Before using any services, you need to set up and fund an account for each provider you want to use.
 
 #### Create an Account
+
 ```typescript
-await broker.addAccount(providerAddress, initialBalance);
+await broker.ledger.addLedger(initialBalance);
 ```
+
 The `initialBalance` needs to be specified in A0GI units.
 
 #### Add Funds
+
 ```typescript
-await broker.depositFund(providerAddress, amount);
+await broker.ledger.depositFund(amount);
 ```
+
 The `amount` needs to be specified in A0GI units.
 
 ### Making Service Requests
 
 Service usage in the 0G Network involves two key steps:
+
 1. Retrieving service metadata
 2. Generating authenticated request headers
 
 ```typescript
 // Get service metadata
-const { endpoint, model } = await broker.getServiceMetadata(
-  providerAddress,
-  serviceName
+const { endpoint, model } = await broker.inference.getServiceMetadata(
+  providerAddress
 );
 
 // Generate request headers
-const headers = await broker.getRequestHeaders(
+const headers = await broker.inference.getRequestHeaders(
   providerAddress,
-  serviceName,
   content
 );
 ```
@@ -142,6 +158,7 @@ const headers = await broker.getRequestHeaders(
 You can make requests using either the native fetch API or the OpenAI SDK.
 
 **Using fetch:**
+
 ```typescript
 const response = await fetch(`${endpoint}/chat/completions`, {
   method: "POST",
@@ -157,6 +174,7 @@ const response = await fetch(`${endpoint}/chat/completions`, {
 ```
 
 **Using OpenAI SDK:**
+
 ```typescript
 const openai = new OpenAI({
   baseURL: endpoint,
@@ -180,10 +198,11 @@ const completion = await openai.chat.completions.create(
 
 This function is used to verify the response and settle the fee. If it is a verifiable service, it will return whether the response is valid.
 
+For streaming services, `content` should be the total content received from the service. And chatID can be any chat ID of the chunk.
+
 ```typescript
-const valid = await broker.processResponse(
+const valid = await broker.inference.processResponse(
   providerAddress,
-  serviceName,
   content,
   chatID // Optional: Only for verifiable services
 );
@@ -194,24 +213,27 @@ const valid = await broker.processResponse(
 If `processResponse` fails, you can settle fees manually by calling `settleFee` function.
 
 ```typescript
-await broker.settleFee(providerAddress, serviceName, fee);
+await broker.inference.settleFee(providerAddress, fee);
 ```
 
 ### Helper Functions
 
 #### Get Account Details
+
 This function is used to get account details (like balance) on the given provider address.
+
 ```typescript
-const accountDetails = await broker.getAccount(providerAddress);
+const accountDetails = await broker.ledger.getLedger();
 ```
 
 #### Request Refund
+
 This function is used to request a refund from your account.
+
 ```typescript
-await broker.requestRefund(user, providerAddress, amount);
+await broker.ledger.retrieveFund("inference", amount);
 ```
 
-
 </TabItem>
 
 <TabItem value="other" label="Other SDKs">