Build a Local AI Search Tool with Python

🚀 Day 17 of My Generative & Agentic AI Journey! Today’s focus was on Passing Arguments to Functions and understanding how different data types behave. Here’s what I learned: 🔤 Passing Strings vs Lists: • Strings are immutable → cannot be changed inside a function 👉 Any modification creates a new value • Lists are mutable → can be updated inside a function 👉 Changes reflect outside the function as well 📥 Types of Arguments: • Positional Arguments → Values are passed in order 👉 Example: first value goes to first parameter, second to second • Keyword Arguments → Values are passed using parameter names 👉 Order doesn’t matter here ⚙️ *args and **kwargs: • *args → Used to pass multiple positional arguments 👉 Treated as a tuple inside the function • **kwargs → Used to pass multiple keyword arguments 👉 Treated as a dictionary inside the function 💡 Key takeaway: Understanding how arguments work helps in writing flexible and reusable functions. Getting more comfortable with writing dynamic and scalable Python code 🚀 #Day17 #Python #GenerativeAI #AgenticAI #LearningJourney #BuildInPublic

Day 15 of My AI Journey 🚀 Today I focused on making my code more reliable and error-resistant. Covered: 👉 Exception handling (try / except) 👉 Understanding common runtime errors 👉 Writing safer code with proper validations What I worked on: 👉 Updated previous programs to handle invalid inputs and edge cases 👉 Practiced debugging and fixing errors systematically Key takeaway: 👉 Writing code that works is one step — writing code that handles failures is real progress This phase is helping me build a stronger foundation for developing robust applications and AI systems. #Python #AI #LearningInPublic #BuildInPublic

🚀 Day 23 of My Generative & Agentic AI Journey! Today’s focus was on Different Types of Comprehensions in Python — making code more concise and powerful. Here’s what I learned: 📋 List Comprehension: • Denoted by [] brackets • Used to create lists in a single line 👉 Example: iced_tea = [tea for tea in menu if "Iced" in tea] 🔗 Set Comprehension: • Denoted by {} brackets • Stores only unique values 👉 Examples: {chai for chai in fav_chais} {spice for ingredients in recipes.values() for spice in ingredients} 📘 Dictionary Comprehension: • Also uses {} brackets with key:value pairs 👉 Example: tea_price_usd = {tea: price/80 for tea, price in tea_price_inr.items()} ⚡ Generator Expression: • Denoted by () brackets • Memory efficient, generates values on the fly 👉 Example: total_cups = sum(sale for sale in daily_sales) 💡 Key takeaway: Different types of comprehensions help write cleaner, faster, and more efficient Python code. Leveling up my coding style with more concise and optimized solutions 🚀 #Day23 #Python #GenerativeAI #AgenticAI #LearningJourney #BuildInPublic

Day 12 of My AI Journey 🚀 Today I continued working with data structures and focused on handling data more efficiently. Covered: 👉 Dictionaries (key-value pairs) 👉 Accessing and updating structured data 👉 Combining lists and dictionaries What I worked on: 👉 Built small programs to store and retrieve structured information 👉 Practiced organizing data in a more meaningful way Key takeaway: 👉 Choosing the right data structure makes code simpler and more efficient This step is helping me think in terms of structured data, which is essential for real-world applications and AI systems. #Python #AI #LearningInPublic #BuildInPublic

🧠 This is how AI actually works (no code, just thinking) - 🙃 See the Visual : mini demo - more insights. ◆ Python - Loop #ThinkFirst_8 Most people think AI is magic… 👉 It’s not. It’s just data + structure + iteration 📊 Look at the flow carefully 👇 • Data comes in (raw, messy) • Organized using structures (List / Dictionary) • Processed step-by-step (Loops) • Filtered → Patterns → Insights 💡 Pause & think: If you had this data… 👉 How would YOU find: • Total value? • Important signals? • Patterns? 🔁 That thinking = AI logic Not models. Not tools. 👉 Just structured problem solving at scale 🚀 Mini challenge: Can you map this flow to a real use case? (sales, users, logs…) Next: We’ll turn this thinking into actual code #FamAI #LearnFirst_BuildSmart #Python

The RAG Journey Begins: From Documents to Knowledge Graphs 🚀 I’m excited to share the first milestone in my journey of building advanced AI systems: DocQuery AI. 📄✨ This project is my "Step 1"—a solid foundation for document intelligence using a standard RAG pipeline. It’s been an incredible learning experience to integrate: 🔹 LangChain for orchestration 🔹 ChromaDB for local vector storage 🔹 Google Gemini 2.5 Flash for grounded reasoning What’s next?  While this "naive" RAG implementation is a great starting point, I’m already working on the next phases: ✅ Step 2: Graph RAG for complex relationship mapping. ✅ Step 3: Advanced Agentic workflows for autonomous document research. I’m documenting my progress as I dive deeper into the world of agentic AI. Check out the current source code here: 🔗 https://lnkd.in/g6Jp-A8K #BuildInPublic #GraphRAG #AIRevolution #Python #LearningJourney #MachineLearning

Most developers see a Decision Tree as a diagram… but it’s really just a series of if-else statements at scale. 🤯 When I first learned Decision Trees, I expected something complex and “AI-heavy.” But the moment it clicked was simple: It starts with a root and keeps splitting data based on conditions just like nested if-else logic in code. Each node = a condition Each branch = an outcome Each leaf = a final decision The real power isn’t the structure it’s how the algorithm picks the best condition at every step (using things like Gini or Entropy). That’s what turns simple logic into smart predictions. If you’re from a dev background, here’s the takeaway: Don’t overcomplicate ML concepts. A Decision Tree isn’t new it’s just optimized decision-making logic. What’s one AI/ML concept that felt hard at first… but became simple later? 👇 #MachineLearning #AI #SoftwareDevelopment #Python #DataScience

Built my first AI-based RAG (Retrieval-Augmented Generation) application 🚀 It’s a simple idea: 📄 Upload a PDF → 💬 Ask questions → 🤖 Get answers grounded in that document While building this, I got hands-on with how RAG actually works behind the scenes: • Extracting text from PDFs (including OCR for scanned files) • Chunking and generating embeddings • Storing vectors in a database for semantic search • Retrieving relevant context and generating answers using an LLM Tech stack: Python, FastAPI, Streamlit, Qdrant, Sentence Transformers, OpenRouter One key learning for me: 👉 The real challenge isn’t just generating answers, but retrieving the right context Still learning and improving, but this was a great first step into building AI systems. 🎥 Sharing a quick demo below 🔗 GitHub: https://lnkd.in/g4nTZu4S Would love your feedback! #AI #RAG #MachineLearning #LLM #Python #BuildInPublic

If you're building AI apps with LangChain, knowing the right document loader can save a lot of time. Here’s a quick guide to common file types and their loaders: 📁 .txt → TextLoader 📄 .pdf → PyPDFLoader 📊 .csv → CSVLoader 🧾 .json → JSONLoader 📝 .md → UnstructuredMarkdownLoader 🌐 URLs → WebBaseLoader Using the right loader helps clean, structure, and prepare data for RAG systems, chatbots, and AI workflows. Save this post for later and follow for more AI content. #LangChain #Python #AI #MachineLearning #DataScience #LLM #RAG #Chatbot

🧠 Learning NumPy for Machine Learning? Here’s the way I finally made sense of it — not by memorizing functions, but by understanding how it thinks. 🔹 1. Arrays NumPy arrays are the backbone. Think of them as fast, memory-efficient containers for numbers. 🔹 2. Shape & Dimensions Before doing anything, always check: a.shape → structure a.ndim → number of dimensions 🔹 3. Indexing & Slicing Access specific data easily: a[1] → single element a[1:3] → subset 🔹 4. Vectorization No loops needed. Just do: a * 2 → [2, 4, 6] 🔹 5. Broadcasting Operate between arrays of different shapes effortlessly. 🔹 6. Linear Algebra Core of machine learning: np.dot(), np.matmul() 💡 What changed my perspective: NumPy isn’t just a library — it’s how machines see and process numbers. #DataScience #Python #NumPy #MachineLearning #AI