Set up steps

1. Google Cloud Project and Vertex AI API:

   • Create a Google Cloud project.
   • Enable the Vertex AI API for your project.

2. Google AI API Key:

   • Obtain a Google AI API key from Google AI Studio.

3. Pinecone Account:

   • Create a free account on the Pinecone website.
   • Obtain your API key from your Pinecone dashboard.
   • Create an index named seanrag or any other name in your Pinecone project.

4. Google Drive:

   • Create a dedicated folder in your Google Drive to store company documents.

5. Credentials in n8n:

   • Configure the following credentials in your n8n environment:
     • Google Drive OAuth2
     • Google Gemini (PaLM) API (using your Google AI API key)
     • Pinecone API (using your Pinecone API key)

6. Import the Workflow:

   • Import this workflow into your n8n instance.

7. Configure the Workflow:

   • Update both Google Drive Trigger nodes to watch the specific folder you created in Google Drive.
   • Configure the Pinecone Vector Store nodes to use your company-files index.

8. Optional

   • Set up NocoDB and create a table with the same fields. Map the fields exactly or as preferred. ConversationHistory - user,email,ai,sessionid,date,datetime

• Remember to map the table name and fields according to your customizations.

(optional) Chatting Stage : SAVE CONVERSATION TO DATABASE NOCODB

Purpose

This endpoint api is intentionally decoupled. It optionally allows your frontend app to save the conversation history from the frontend app with more control of the event from ui perspective.

How to integrate

1. Connect your frontend interface to this api below. You may change the base endpoint to webhook or webhook-test depending on your environment.

** How to test

curl -X POST 'https://n8n.io/webhook-test/update-conversation' -H 'Content-Type: application/json' -d '{
  "user": "Hi who is sean",
  "email": "user@example.com",
  "ai": "sean is a skilled engineer...",
  "sessionid": "your_session_custom_id" 
}'

EMAIL REPORT - DAILY CONVERSATIONS

Purpose

This scheduler will run daily scheduler. It will get all the daily conversation history daily from the database nocodb and then send an email summary.

How to integrate or modify

1. Connect your google gmail credentials.
2. Configure scheduler accordingly
3. Change the HTML display format to your liking

Chatting Stage : CHAT ENDPOINT

Purpose

This endpoint api allows you to chat with the ai agent. The ai agent will answer based on the vector database index seanrag. You may change the indexname seanrag to your own index name yourcv

How to integrate

1. Connect your frontend interface to this api below. You may change the base endpoint to webhook or webhook-test depending on your environment.

You can also change the based the endpoint 'https://n8n.io' to your own hosted domain like 'https://mycustomdomain.io/'

curl -X POST 'https://n8n.io/webhook-test/chat' -H 'Content-Type: application/json' -d '{
  "chatInput": "Hi who is sean? "
}'

2. You will see a sample output response:

[{"output":"Sean is a skilled engineer who has worked 15 years in the industry \n"}]

Setup Stage: TRAINING AUTOMATICALLY

Purpose

This trigger auto detects when a resume is updated or created. Then it will automatically convert the content data into chunks to be stored into the vector database.

How to integrate

1. Setup your google drive credential and then choose which folder you will place your resume document.
2. Setup your pinecone or an similar vector database credential
3. Please create a database index seanrag. You may change the indexname seanrag to your own index name yourcv.
4. You can also manually run it.

Personal Portfolio Resume CV Chatbot

Purpose and structure

This folder contains the Personal Portfolio Resume CV Chatbot workflow. Its executable nodes use agent, code, documentDefaultDataLoader, embeddingsGoogleGemini, gmail, googleDrive, googleDriveTrigger, html, lmChatGoogleGemini, memoryBufferWindow, nocoDb, respondToWebhook, scheduleTrigger, textSplitterRecursiveCharacterTextSplitter, toolVectorStore, vectorStorePinecone, webhook. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

Schedule Trigger, Google Drive - Resume CV File Created, Google Drive - Resume CV File Updated, Chat API - webhook, Save Conversation API - Webhook

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Webhook/1881_Webhook_Code_Automate_Webhook.json MIT; preserve source notices.