Mihai Farcas
Full-stack developer with 5+ years streamlining healthcare processes. Proficient in NodeJS, VueJS, MongoDB, PostgreSQL, Kubernetes, and n8n. Ready to optimize your workflows – book a consult via my link.
Categories
Templates by Mihai Farcas
RAG chatbot for company documents using Google Drive and Gemini
This workflow implements a Retrieval Augmented Generation (RAG) chatbot that answers employee questions based on company documents stored in Google Drive. It automatically indexes new or updated documents in a Pinecone vector database, allowing the chatbot to provide accurate and up-to-date information. The workflow uses Google's Gemini AI for both embeddings and response generation. How it works The workflow uses two Google Drive Trigger nodes: one for detecting new files added to a specified Google Drive folder, and another for detecting file updates in that same folder. Automated Indexing: When a new or updated document is detected The Google Drive node downloads the file. The Default Data Loader node loads the document content. The Recursive Character Text Splitter node breaks the document into smaller text chunks. The Embeddings Google Gemini node generates embeddings for each text chunk using the text-embedding-004 model. The Pinecone Vector Store node indexes the text chunks and their embeddings in a specified Pinecone index. 7.The Chat Trigger node receives user questions through a chat interface. The user's question is passed to an AI Agent node. The AI Agent node uses a Vector Store Tool node, linked to a Pinecone Vector Store node in query mode, to retrieve relevant text chunks from Pinecone based on the user's question. The AI Agent sends the retrieved information and the user's question to the Google Gemini Chat Model (gemini-pro). The Google Gemini Chat Model generates a comprehensive and informative answer based on the retrieved documents. A Window Buffer Memory node connected to the AI Agent provides short-term memory, allowing for more natural and context-aware conversations. Set up steps Google Cloud Project and Vertex AI API: Create a Google Cloud project. Enable the Vertex AI API for your project. Google AI API Key: Obtain a Google AI API key from Google AI Studio. Pinecone Account: Create a free account on the Pinecone website. Obtain your API key from your Pinecone dashboard. Create an index named company-files in your Pinecone project. Google Drive: Create a dedicated folder in your Google Drive where company documents will be stored. Credentials in n8n: Configure credentials in your n8n environment for: Google Drive OAuth2 Google Gemini(PaLM) Api (using your Google AI API key) Pinecone API (using your Pinecone API key) Import the Workflow: Import this workflow into your n8n instance. Configure the Workflow: Update both Google Drive Trigger nodes to watch the specific folder you created in your Google Drive. Configure the Pinecone Vector Store nodes to use your company-files index.
By Mihai FarcasChat with local LLMs using n8n and Ollama
Chat with local LLMs using n8n and Ollama This n8n workflow allows you to seamlessly interact with your self-hosted Large Language Models (LLMs) through a user-friendly chat interface. By connecting to Ollama, a powerful tool for managing local LLMs, you can send prompts and receive AI-generated responses directly within n8n. Use cases Private AI Interactions Ideal for scenarios where data privacy and confidentiality are important. Cost-Effective LLM Usage Avoid ongoing cloud API costs by running models on your own hardware. Experimentation & Learning A great way to explore and experiment with different LLMs in a local, controlled environment. Prototyping & Development Build and test AI-powered applications without relying on external services. How it works When chat message received: Captures the user's input from the chat interface. Chat LLM Chain: Sends the input to the Ollama server and receives the AI-generated response. Delivers the LLM's response back to the chat interface. Set up steps Make sure Ollama is installed and running on your machine before executing this workflow. Edit the Ollama address if different from the default.
By Mihai FarcasAutomated web scraping: email a CSV, save to Google Sheets & Microsoft Excel
How it works: The workflow starts by sending a request to a website to retrieve its HTML content. It then parses the HTML extracting the relevant information The extracted data is storted and converted into a CSV file. The CSV file is attached to an email and sent to your specified address. The data is simultaneously saved to both Google Sheets and Microsoft Excel for further analysis or use. Set-up steps: Change the website to scrape in the "Fetch website content" node Configure Microsoft Azure credentials with Microsoft Graph permissions (required for the Save to Microsoft Excel 365 node) Configure Google Cloud credentials with access to Google Drive, Google Sheets and Gmail APIs (the latter is required for the Send CSV via e-mail node).
By Mihai FarcasChat with GitHub API documentation: RAG-powered chatbot with Pinecone & OpenAI
This workflow demonstrates a Retrieval Augmented Generation (RAG) chatbot that lets you chat with the GitHub API Specification (documentation) using natural language. Built with n8n, OpenAI's LLMs and the Pinecone vector database, it provides accurate and context-aware responses to your questions about how to use the GitHub API. You could adapt this to any OpenAPI specification for any public or private API, thus creating a documentation chatbout that anyone in your company can use. How it works: Data Ingestion: The workflow fetches the complete GitHub API OpenAPI 3 specification directly from the GitHub repository. Chunking and Embeddings: It splits the large API spec into smaller, manageable chunks. OpenAI's embedding models then generate vector embeddings for each chunk, capturing their semantic meaning. Vector Database Storage: These embeddings, along with the corresponding text chunks, are stored in a Pinecone vector database. Chat Interface and Query Processing: The workflow provides a simple chat interface. When you ask a question, it generates an embedding for your query using the same OpenAI model. Semantic Search and Retrieval: Pinecone is queried to find the most relevant text chunks from the API spec based on the query embedding. Response Generation: The retrieved chunks and your original question are fed to OpenAI's gpt-4o-mini LLM, which generates a concise, informative, and contextually relevant answer, including code snippets when applicable. Set up steps: Create accounts: You'll need accounts with OpenAI and Pinecone. API keys: Obtain API keys for both services. Configure credentials: In your n8n environment, configure credentials for OpenAI and Pinecone using your API keys. Import the workflow: Import this workflow into your n8n instance. Pinecone Index: Ensure you have a Pinecone index named "n8n-demo" or adjust the workflow accordingly. The workflow is set up to work with this index out of the box. Setup Time: Approximately 15-20 minutes. Why use this workflow? Learn RAG in Action: This is a practical, hands-on example of how to build a RAG-powered chatbot. Adaptable Template: Easily modify this workflow to create chatbots for other APIs or knowledge bases. n8n Made Easy: See how n8n simplifies complex integrations between data sources, vector databases, and LLMs.
By Mihai FarcasERP AI chatbot for Odoo sales module with OpenAI
Who is this for? This workflow is for everyone who wants to have easier access to their Odoo sales data without complex queries. Use Case To have a clear overview of your sales data in Odoo you typically needs to extract data from it manually to analyse it. This workflow uses OpenAI's language models to create an intelligent chatbot that provides conversational access to your Odoo sales opportunity data. How it works Creates a summary of all Odoo sales opportunities using OpenAI Uses that summary as context for the OpenAI chat model Keeps the summary up to date using a schedule trigger Set up steps: Configure the Odoo credentials Configure OpenAI credentials Toggle "Make Chat Publicly Available" from the Chat Trigger node.
By Mihai FarcasAI-powered RAG workflow for stock earnings report analysis
This n8n workflow creates a financial analysis tool that generates reports on a company's quarterly earnings using the capabilities of OpenAI GPT-4o-mini, Google's Gemini AI and Pinecone's vector search. By analyzing PDFs of any company's earnings reports from their Investor Relations page, this workflow can answer complex financial questions and automatically compile findings into a structured Google Doc. How it works: Data loading and indexing Fetches links to PDF earnings document from a Google Sheet containing a list of file links. Downloads the PDFs from Google Drive. Parses the PDFs, splits the text into chunks, and generates embeddings using the Embeddings Google AI node (text-embedding-004 model). Stores the embeddings and corresponding text chunks in a Pinecone vector database for semantic search. Report generation with AI agent Utilizes an AI Agent node with a specifically crafted system prompt. The agent orchestrates the entire process. The agent uses a Vector Store Tool to access and retrieve information from the Pinecone database. Report delivery Saves the generated report as a Google Doc in a specified Google Drive location. Set up steps Google Cloud Project & Vertex AI API: Create a Google Cloud project. Enable the Vertex AI API for your project. Google AI API key: Obtain a Google AI API key from Google AI Studio. Pinecone account and API key: Create a free account on the Pinecone website. Obtain your API key from your Pinecone dashboard. Create an index named company-earnings in your Pinecone project. Google Drive - download and save financial documents: Go to a company you want to analize and download their quarterly earnings PDFs Save the PDFs in Google Drive Create a Google Sheet that stores a list of file URLs pointing to the PDFs you downloaded and saved to Google Drive Configure credentials in your n8n environment for: Google Sheets OAuth2 Google Drive OAuth2 Google Docs OAuth2 Google Gemini(PaLM) Api (using your Google AI API key) Pinecone API (using your Pinecone API key) Import and configure the workflow: Import this workflow into your n8n instance. Update the List Of Files To Load (Google Sheets) node to point to your Google Sheet. Update the Download File From Google Drive to point to the column where the file URLs are Update the Save Report to Google Docs node to point to your Google Doc where you want the report saved.
By Mihai FarcasNews research and sentiment analysis AI agent with Gemini and SearXNG
This n8n workflow operates as a two-agent system where each agent has a specialized task. The process flows from initial user input to a final analysis, with a seamless handoff between the agents. How it works The Chat Trigger The entire process begins when you send a message using n8n's chat interface. This message serves as the initial prompt or query for the system. The Research Agent Takes Over The user's message is first sent to the Research Agent. This agent's job is to understand the query and gather relevant information. To do this, it has access to: LLM: Google Gemini, which acts as the agent's "brain" to process language and make decisions. Tools: web_search: It uses this tool (powered by your self-hosted SearXNG instance) to perform live searches on the internet. getcurrentdate: It can access the current date, which is useful for context-aware or time-sensitive research. The Research Agent uses these tools to find the most relevant information related to your query and then compiles it into a concise summary. Handoff to the Sentiment Analysis Agent Once the Research Agent has completed its task, it passes its findings directly to the Sentiment Analysis Agent. The Final Analysis The Sentiment Analysis Agent receives the text from the Research Agent. Its sole purpose, as defined by its system prompt, is to analyze the sentiment of the provided information. It determines if the content is positive, negative, or neutral and formulates a final response. This final analysis is then sent back to you in the chat, completing the workflow. Set up steps Select the Language Model (LLM): This workflow is pre-configured with Google Gemini. You can select a different model for the agents as needed. Configure LLM Credentials: Ensure that valid credentials for your chosen LLM are correctly set up within your n8n instance. Set Up the SearXNG Connection: Configure the node to connect to your self-hosted SearXNG instance. This enables the agent's web search capabilities. Define the Research Agent's Task: Customize the system prompt for the "Research Agent" to define its role, instructions, and how it should conduct its research. Define the Sentiment Analysis Agent's Task: Adjust the system prompt for the "Sentiment Analysis Agent" to specify how it should analyze the information provided by the Research Agent. Test the Workflow: Use the built-in chat interface in the n8n canvas to send a message and verify that the agents are functioning correctly.
By Mihai FarcasSales lead routing with Gemini Sentiment Analysis & Model Evaluation Framework
This n8n template demonstrates how to deploy an AI workflow in production while simultaneously running a robust, data-driven Evaluation Framework to ensure quality and optimize costs. Use Cases Model Comparison: Quickly A/B test different LLM models (e.g., Gemini 3 Pro vs. Flash Lite) for speed and cost efficiency against your specific task. Prompt Regression: Ensure that tweaks to your system prompt do not introduce new errors or lower the accuracy of your lead categorization. Production Safety: Guarantee that test runs never trigger real-world actions like sending emails to a client or sales team. Requirements A configured Gmail Trigger (or equivalent email trigger). A Google Gemini account for the LLM models. An n8n Data Table containing your "Golden Dataset" of test cases and ground truths. How it Works The workflow contains two distinct, parallel execution paths: Production Path: The Gmail Trigger monitors for new emails. The email text is routed through the Sentiment Analysis node, which categorizes the lead as Positive, Neutral, or Negative. Check if Evaluating nodes verify the current execution mode. If it is not an evaluation run (the Fail branch), the lead is routed to the corresponding Send Email node for action. Evaluation Path: The When fetching a dataset row trigger pulls test cases (input text and expected sentiment/ground truth) from an n8n Data Table. Each test case loops through the same Sentiment Analysis node. The Check if Evaluating nodes route this path to the Success branch, skipping the real email actions. The Save Output node writes the model's prediction to the Data Table. The Set Metrics node uses the Categorization metric to compare the prediction against the ground truth, returning a score (0 or 1) to measure accuracy. Key Technical Details Model Switching: Multiple Google Gemini Chat Model nodes are connected via the Model input on the Sentiment Analysis node, allowing you to easily swap and compare models without changing the core logic. Edge Case Handling: The System Prompt Template in the Sentiment Analysis node is customized to handle tricky inputs, such as negative feedback about a competitor that should be classified as a Positive lead. Metrics: The workflow uses the built-in Categorization metric, which is ideal for classification tasks like sentiment analysis, to provide objective evidence of performance.
By Mihai Farcas