@hamsa-ai/voice-agents-sdk 0.3.1 → 4.0.0-beta.1

package/README.md

@@ -1,6 +1,6 @@
 # Hamsa Voice Agents Web SDK
 
-Hamsa Voice Agents Web SDK is a JavaScript library for integrating voice agents from <https://dashboard.tryhamsa.com>. This SDK provides a seamless way to incorporate voice interactions into your web applications.
+Hamsa Voice Agents Web SDK is a JavaScript library for integrating voice agents from <https://dashboard.tryhamsa.com>. This SDK provides a seamless way to incorporate voice interactions into your web applications with high-quality real-time audio communication.
 
 ## Installation
 
@@ -17,7 +17,7 @@ npm i @hamsa-ai/voice-agents-sdk
 First, import the package in your code:
 
 ```javascript
-import { HamsaVoiceAgent } from '@hamsa-ai/voice-agents-sdk'
+import { HamsaVoiceAgent } from "@hamsa-ai/voice-agents-sdk";
 ```
 
 Initialize the SDK with your API key:
@@ -37,9 +37,11 @@ Include the script from a CDN:
 Then, you can initialize the agent like this:
 
 ```javascript
-const agent = new HamsaVoiceAgent('YOUR_API_KEY');
+const agent = new HamsaVoiceAgent("YOUR_API_KEY");
 
-agent.on("callStarted", () => { console.log("Conversation has started!"); });
+agent.on("callStarted", () => {
+	console.log("Conversation has started!");
+});
 
 // Example: Start a call
 // agent.start({ agentId: 'YOUR_AGENT_ID' });
@@ -53,11 +55,11 @@ Start a conversation with an existing agent by calling the "start" function. You
 
 ```javascript
 agent.start({
-    agentId: YOUR_AGENT_ID,
-    params: {
-        param1: "NAME",
-        param2: "NAME2"
-    }
+	agentId: YOUR_AGENT_ID,
+	params: {
+		param1: "NAME",
+		param2: "NAME2",
+	},
 });
 ```
 
@@ -92,29 +94,109 @@ During the conversation, the SDK emits events to update your application about t
 ### Conversation Status Events
 
 ```javascript
-agent.on("callStarted", () => { console.log("Conversation has started!"); });
-agent.on("callEnded", () => { console.log("Conversation has ended!"); });
-agent.on("callPaused", () => { console.log("The conversation is paused"); });
-agent.on("callResumed", () => { console.log("Conversation has resumed"); });
+agent.on("callStarted", () => {
+	console.log("Conversation has started!");
+});
+agent.on("callEnded", () => {
+	console.log("Conversation has ended!");
+});
+agent.on("callPaused", () => {
+	console.log("The conversation is paused");
+});
+agent.on("callResumed", () => {
+	console.log("Conversation has resumed");
+});
 ```
 
 ### Agent Status Events
 
 ```javascript
-agent.on("speaking", () => { console.log("The agent is speaking"); });
-agent.on("listening", () => { console.log("The agent is listening"); });
+agent.on("speaking", () => {
+	console.log("The agent is speaking");
+});
+agent.on("listening", () => {
+	console.log("The agent is listening");
+});
 ```
 
 ### Conversation Script Events
 
 ```javascript
-agent.on("transcriptionReceived", (text) => { console.log("User speech transcription received", text); });
-agent.on("answerReceived", (text) => { console.log("Agent answer received", text); });
+agent.on("transcriptionReceived", (text) => {
+	console.log("User speech transcription received", text);
+});
+agent.on("answerReceived", (text) => {
+	console.log("Agent answer received", text);
+});
 ```
 
 ### Error Events
 
 ```javascript
-agent.on("closed", () => { console.log("Conversation was closed"); });
-agent.on("error", (e) => { console.log("Error was received", e); });
+agent.on("closed", () => {
+	console.log("Conversation was closed");
+});
+agent.on("error", (e) => {
+	console.log("Error was received", e);
+});
+```
+
+## Configuration Options
+
+The SDK accepts optional configuration parameters:
+
+```javascript
+const agent = new HamsaVoiceAgent("YOUR_API_KEY", {
+	API_URL: "https://api.tryhamsa.com", // API endpoint (default)
+});
+```
+
+## Client-Side Tools
+
+You can register client-side tools that the agent can call during conversations:
+
+```javascript
+const tools = [
+	{
+		function_name: "getUserInfo",
+		description: "Get user information",
+		parameters: [
+			{
+				name: "userId",
+				type: "string",
+				description: "User ID to look up",
+			},
+		],
+		required: ["userId"],
+		fn: async (userId) => {
+			// Your tool implementation
+			const userInfo = await fetchUserInfo(userId);
+			return userInfo;
+		},
+	},
+];
+
+agent.start({
+	agentId: "YOUR_AGENT_ID",
+	tools: tools,
+	voiceEnablement: true,
+});
 ```
+
+## Migration from Previous Versions
+
+If you're upgrading from a previous version, see the [Migration Guide](./MIGRATION_GUIDE.md) for detailed instructions. Connection details are now automatically managed and no longer need to be configured.
+
+## Browser Compatibility
+
+This SDK supports modern browsers with WebRTC capabilities:
+
+-   Chrome 60+
+-   Firefox 60+
+-   Safari 12+
+-   Edge 79+
+
+## Dependencies
+
+-   **livekit-client**: Real-time communication infrastructure
+-   **events**: EventEmitter for browser compatibility