Chore/refractor (#4454)

* markdown files and env examples cleanup

* components update

* update jsonlines description

* server refractor

* update telemetry

* add execute custom node

* add ui refractor

* add username and password authenticate

* correctly retrieve past images in agentflowv2

* disable e2e temporarily

* add existing username and password authenticate

* update migration to default workspace

* update todo

* blob storage migrating

* throw error on agent tool call error

* add missing execution import

* add referral

* chore: add error message when importData is undefined

* migrate api keys to db

* fix: data too long for column executionData

* migrate api keys from json to db at init

* add info on account setup

* update docstore missing fields

---------

Co-authored-by: chungyau97 <chungyau97@gmail.com>

packages/components/nodes/engine/ChatEngine/ContextChatEngine.ts

@@ -10,6 +10,7 @@ import {
 } from '../../../src/Interface'
 import { Metadata, BaseRetriever, LLM, ContextChatEngine, ChatMessage, NodeWithScore } from 'llamaindex'
 import { reformatSourceDocuments } from '../EngineUtils'
+import { EvaluationRunTracerLlama } from '../../../evaluation/EvaluationRunTracerLlama'
 
 class ContextChatEngine_LlamaIndex implements INode {
     label: string
@@ -93,6 +94,9 @@ class ContextChatEngine_LlamaIndex implements INode {
 
         const chatEngine = new ContextChatEngine({ chatModel: model, retriever: vectorStoreRetriever })
 
+        // these are needed for evaluation runs
+        await EvaluationRunTracerLlama.injectEvaluationMetadata(nodeData, options, chatEngine)
+
         const msgs = (await memory.getChatMessages(this.sessionId, false, prependMessages)) as IMessage[]
         for (const message of msgs) {
             if (message.type === 'apiMessage') {