🚀 Introducing a Parallel Workflow for UPSC Essay Evaluation 🚀 As part of my ongoing work to assist UPSC aspirants, I’ve created a simple yet powerful parallel workflow aimed at evaluating essays in the UPSC exam using LangGraph. 🔍 How It Works: This platform allows aspirants to submit their essay, which is then evaluated on multiple key aspects, ensuring a well-rounded feedback mechanism. 💡 The Process Includes: Start Node: The workflow receives an essay and begins the evaluation process. Evaluation on Key Aspects: The essay is evaluated in three areas: Clarity of Thought: How clear and coherent the essay's arguments and ideas are. (Score: 0-10) Depth of Analysis: The depth at which the topic is explored and the analysis presented. (Score: 0-10) Language: The quality of language, including grammar, vocabulary, and fluency. (Score: 0-10) Final Evaluation: After the individual assessments, all feedback is merged and summarized using LLM, resulting in: A final evaluation score based on the average of the three aspects. A comprehensive feedback report to help candidates improve their essays. 🔧 The Technology Behind the Scenes: This workflow was built using LangGraph, a powerful tool that allows me to design and manage parallel processes efficiently. LangGraph enables the independent evaluation of different aspects of the essay while seamlessly merging the results for a final, cohesive assessment. 🌟 Whether you’re preparing for UPSC or simply looking to improve your essay-writing skills, this tool can provide valuable insights into how well-rounded and impactful your essays are. Let me know if you have any thoughts or suggestions on this workflow.

I’ve developed an automated blog generation system that takes a simple topic and transforms it into a full-length blog post, using a two-step process powered by LangGraph. 🤖✨ How it Works: Step 1: Generate Outline 📝 The workflow first takes the topic provided by the user and generates a detailed blog outline. This helps structure the content by breaking it down into key sections. Step 2: Generate Blog Content 🖋️ With the outline in hand, the system then uses it to generate a detailed blog post, ensuring each section of the outline is fully fleshed out into a coherent and informative blog. LangGraph Workflow Design: The workflow is built with LangGraph and consists of two primary nodes: 🔧 Node 1: Create Outline 📋 Functionality: This node takes the user-provided topic and uses it to generate a structured outline for the blog. The model understands the topic and breaks it down into key points and sub-topics. Node 2: Create Blog Content 🖊️ Functionality: This node takes the topic and the outline and generates a full-length blog based on the outline. It ensures the content is well-organized and aligned with the initial structure, providing a comprehensive blog post. Key Features: Efficient Workflow 🚀: Seamlessly moves from generating a structured outline to creating a detailed blog. Node-based Process ⚙️: Clear and easy-to-understand flow with specific functionalities for each node. Real-Time Streaming ⏱️: The content is streamed progressively to the user, ensuring a dynamic and engaging experience. This system showcases the power of LangGraph in structuring complex workflows for content generation, allowing for automation and efficiency in content creation. 🌟 Check out the demo to see how the system works in action! 🎥 hashtag#AI hashtag#BlogGeneration hashtag#LangGraph hashtag#MachineLearning hashtag#Automation hashtag#ContentCreation hashtag#TechInnovation hashtag#Python hashtag#ArtificialIntelligence hashtag#NodeBasedWorkflow ✨

🧩Step-by-Step Breakdown: 🗨️Trigger: "When chat message received" --This node listens for incoming chat messages from the user, asking for a specific type of doctor on Facebook 🌐HTTP Request: "Searching from Apify" --Sends a POST request to the Apify API to search Facebook for the type of doctor mentioned by the user (e.g., “best gynecologist in Sukkur”). ⏳Wait: "Gather result" - Pauses the workflow until Apify completes the search. - Outputs 5 result items from Facebook. 🧠Code in JavaScript: "Make structured output" - Doctor’s name - Timings - Availability - Location ✏️Edit Fields: "Required output" --Get required output 📄Append row in sheet: "Saving results" --Appends the final structured data into a connected Google Sheet for record-keeping.

I’ve recently worked on an exciting project that involved building a chatbot with Streamlit UI and Short-Term Memory capabilities, powered by LangGraph. This chatbot doesn’t just provide natural language responses using an advanced language model but also integrates with various tools to enhance its functionality. 🔧 Key Features: 1. Numerical Calculations – The chatbot can perform complex calculations in real-time. Whether it's basic arithmetic or more advanced math, it's got you covered. 💡 2. Internet Search – By integrating with the DuckDuckGo search engine, it fetches real-time data from the web, making it your intelligent assistant for queries. 🌐 3. Stock Price Tool – Just provide the name of a company, and the bot retrieves the live stock price instantly. 📈 All of this is powered by SQLite for data persistence, Streaming for smooth interactions, and LangGraph to seamlessly integrate these capabilities into the chatbot. LangGraph made it much easier to handle tool integrations and memory management within the model. 🔄