Track Usage Metrics in Chat API. Track Running Cost, Accuracy in Evals (#985)

- Track, return cost and usage metrics in chat api response
  Track input, output token usage and cost of interactions with 
  openai, anthropic and google chat models for each call to the khoj chat api
- Collect, display and store costs & accuracy of eval run currently in progress
  This provides more insight into eval runs during execution 
  instead of having to wait until the eval run completes.

src/interface/obsidian/src/chat_view.ts

@@ -945,7 +945,7 @@ export class KhojChatView extends KhojPaneView {
             console.log("Started streaming", new Date());
         } else if (chunk.type === 'end_llm_response') {
             console.log("Stopped streaming", new Date());
-
+        } else if (chunk.type === 'end_response') {
             // Automatically respond with voice if the subscribed user has sent voice message
             if (this.chatMessageState.isVoice && this.setting.userInfo?.is_active)
                 this.textToSpeech(this.chatMessageState.rawResponse);

src/interface/web/app/common/chatFunctions.ts

@@ -133,7 +133,7 @@ export function processMessageChunk(
         console.log(`Started streaming: ${new Date()}`);
     } else if (chunk.type === "end_llm_response") {
         console.log(`Completed streaming: ${new Date()}`);
-
+    } else if (chunk.type === "end_response") {
         // Append any references after all the data has been streamed
         if (codeContext) currentMessage.codeContext = codeContext;
         if (onlineContext) currentMessage.onlineContext = onlineContext;