ChromaDB Vector Database for Large Language Models

🐍📺 Vector Databases and Embeddings With ChromaDB [Video] Learn how to use ChromaDB, an open-source vector database, to store embeddings and provide context for large language models in Python https://lnkd.in/gtNKjd4e

Day 37 / #120DaysOfCode – LeetCode Challenge ✅ Problem Solved: • Search a 2D Matrix 💻 Language: Python 📚 Key Learnings: • Applied Binary Search on a 2D matrix • Learned how to treat matrix as a flattened sorted array • Practiced converting 1D index → 2D index (row, col) • Improved understanding of search space reduction • Strengthened logarithmic time complexity (O(log n)) thinking Better logic → Faster execution 🚀 🔗 LeetCode Profile: https://lnkd.in/gbeMKcv5 #LeetCode #Python #DSA #BinarySearch #Algorithms #CodingJourney #Consistency #120DaysOfCode

I adapted Karpathy's microGPT to predict hourly temperatures using one year of real meteorological data from Basel. This project was built entirely in pure Python, without the use of any deep learning libraries. A full writeup is available on Medium.

Built a Sudoku Solver in Python using AI-based Constraint Satisfaction Problem (CSP) techniques 🧩💻 Implemented: - Backtracking - Forward Checking - AC-3 Algorithm - MRV Heuristic Great hands-on project for applying AI search and optimization concepts. 🚀 #Python #ArtificialIntelligence #Algorithms #CSP #SudokuSolver #Coding

I was building the 𝐌𝐚𝐜𝐡𝐢𝐧𝐞 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠 𝐦𝐨𝐝𝐞𝐥 and I encountered compatibility issue for installing the libraries. Here I got to know the importance of the 𝗩𝗶𝗿𝘁𝘂𝗮𝗹 𝗘𝗻𝘃𝗶𝗿𝗼𝗻𝗺𝗲𝗻𝘁 in 𝗣𝘆𝘁𝗵𝗼𝗻 to isolate the code/libraries for a new Project to avoid the compatibility issues. Also I had to install the libraries from the backend on Terminal which were not working from the 𝗝𝘂𝗽𝘆𝘁𝗲𝗿 𝗡𝗼𝘁𝗲𝗯𝗼𝗼𝗸 Please refer my 𝐁𝐥𝐨𝐠 for details of issues encountered and the steps I followed to solve the same :-  https://lnkd.in/drmifuGp #Python #MachineLearning #AI #VirtualEnviornments #LinearRegression

🐍📰 D-Strings Could End Your textwrap.dedent() Days and Other Python News for April 2026 D-strings proposed to kill textwrap.dedent(), Python 3.15 alpha 7 ships lazy imports, GPT-5.4 launches, and Python Insider moves home https://buff.ly/CwADE3I

How can you evaluate an AI model's robustness before real-world failures occur? In this webinar, we’ll demonstrate how to use the open source Natural Robustness Toolkit (NRTK) to create reproducible workflows for testing model performance. You’ll learn how to: ✅ Install and configure NRTK in Python ✅ Apply perturbations to expand existing datasets ✅ Design parameter sweeps to measure performance degradation ✅ Evaluate models under simulated operational conditions 📅 April 15, 2026 | 12–1 PM 👉 Register here: https://ow.ly/Ncnr50YBmK7 #AIResearch #MachineLearning #ModelValidation #NRTK #Python

Day 243 of #365DaysOfCode Solved Minimum Distance Between Three Equal Elements I using a hashmap-based indexing approach. Grouped indices of identical elements and evaluated triplets by scanning index lists to compute the minimum distance. This approach efficiently reduces redundant comparisons by leveraging value-based grouping. The solution runs in O(n) time with additional space for index storage. Continuing to refine problem solving through pattern recognition and efficient data organization. #365DaysOfCode #Day243 #DSA #LeetCode #Python #Algorithms #HashMap #ProblemSolving #Consistency

Day 248 of #365DaysOfCode Solved a problem involving mirror pairs and index distance minimization using a hashmap-based approach. For each element, computed its digit-reversed counterpart and tracked indices to identify valid mirror pairs. The minimum distance was updated by comparing current positions with previously stored indices. The solution runs in O(n · d) time, where d is the number of digits, and efficiently leverages hashing for constant-time lookups. Continuing to build intuition around number manipulation and indexing strategies. #365DaysOfCode #Day248 #DSA #LeetCode #Python #Algorithms #HashMap #ProblemSolving #Consistency

Before building models, there’s one thing every AI/ML practitioner needs — strong Python fundamentals. From handling data structures to writing efficient logic, these concepts form the base of every data pipeline. AI starts with data. And data starts with Python. #Python #DataScience #MachineLearning #AI #LearnToCode