New Tools for Langchain Community: Calculator, Web Scraper, Code Executor

✅ Day 95 of 100 Days LeetCode Challenge Problem: 🔹 #869 – Reordered Power of 2 🔗 https://lnkd.in/gkNXaSFM Learning Journey: 🔹 Today’s problem focused on checking whether the digits of a number can be rearranged to form a power of 2. 🔹 I created a helper function to extract and store the digits of a number. 🔹 Then I sorted the digits of the input number for comparison. 🔹 Next, I generated powers of 2 iteratively and compared their sorted digit lists with the input. 🔹 If any match was found, I returned True. Otherwise, continued until the digit length exceeded the input. Concepts Used: 🔹 Digit Extraction 🔹 Sorting 🔹 Simulation of Powers of 2 🔹 Brute Force Optimization Key Insight: 🔹 Instead of generating permutations (which is expensive), sorting digits allows quick comparison. 🔹 Any valid rearrangement must have the same digit frequency as some power of 2. Complexity: 🔹 Time: O(log n * d log d) 🔹 Space: O(d) #LeetCode #Algorithms #DataStructures #CodingInterview #100DaysOfCode #Python #ProblemSolving #LearningInPublic #TechCareers

Spent the last few weeks building a 10-part LangChain tutorial series. It’s finally complete. This series focuses on the internal mechanics of LangChain while building practical applications. The final 3 tutorials just dropped: → Conversational Memory (5 memory types, explained and compared clearly) → Agents & Custom Tools (ReAct agents, structured inputs, multi-tool routing) → Callbacks & Tracing (Custom handlers, cost tracking, LangSmith integration) Each tutorial follows this flow: Problem → Solution → Analogy → Code Architecture diagrams included in every module. 🔗 https://lnkd.in/epvYCJeY #LangChain #Python #AI #LLM #RAG #OpenSource #BuildInPublic #GenerativeAI

Code that writes code. 🌌 There is a point in every developer's journey where you stop thinking about Logic and start thinking about Patterns. Advanced Python is about: ~Abstraction: Using Protocols and Generics for structural typing. ~Automation: Using advanced Decorators to inject behavior across entire systems. ~Reliability: Understanding the memory manager so you can prevent leaks before they start. We use these "hidden" features not to make the code more complex, but to make the usage of our code more simple for everyone else. Which part of the "Advanced Mindset" was the hardest for you to learn? For me, it was finally mastering asyncio flow control. #CleanCode #Pythonic #ProgrammingPrinciples #SystemDesign #AdvancedCoding

✅ Day 99 of 100 Days LeetCode Challenge Problem: 🔹 #999 – Available Captures for Rook 🔗 https://lnkd.in/gAw_XpbJ Learning Journey: 🔹 Today’s problem focused on simulating rook movement on a chessboard. 🔹 First, I located the position of the rook 'R' on the board. 🔹 Then, I explored all four directions: up, down, left, and right. 🔹 In each direction, I moved step-by-step until: • I hit a bishop 'B' → stop (blocked) • I found a pawn 'p' → increment count and stop • Or reached the board boundary 🔹 Summed all valid captures and returned the result. Concepts Used: 🔹 Matrix Traversal 🔹 Simulation 🔹 Direction Vectors 🔹 Boundary Checking Key Insight: 🔹 The rook’s movement is linear in 4 directions, and each direction is independent. 🔹 Early stopping (on bishop or pawn) is critical for correctness and efficiency. Complexity: 🔹 Time: O(1) (fixed 8×8 board, constant work) 🔹 Space: O(1) #LeetCode #Algorithms #DataStructures #100DaysOfCode #Python #CodingJourney #ProblemSolving #LearningInPublic

Your agents deserve fresh context. CocoIndex turns codebases, PDFs, Slack, inboxes, and videos into a continuously updated index your LLM app can actually reason over … no stale nightly batches, no context gap. Python on a Rust delta engine: edit a chunker or swap embedding models, only the affected rows re-run. Pgvector, LanceDB, Neo4j as targets. Byte-level lineage per row. Production agent ready in 10 minutes. #CocoIndex #RAG #AgentMemory #DataEngineering #OpenSource

The death of stale context: CocoIndex kills the RAG "context gap" with a Rust-powered delta engine that enables real-time syncing, hyper-efficient partial re-indexing, and byte-level lineage for total production traceability. 🥇

✅ Day 97 of 100 Days LeetCode Challenge Problem: 🔹 #1281 – Subtract the Product and Sum of Digits of an Integer 🔗 https://lnkd.in/gxTAZc6U Learning Journey: 🔹 Today’s problem involved extracting digits of a number and performing two operations simultaneously. 🔹 I initialized two variables: one for product (pr) and one for sum (sm). 🔹 Using a while loop, I extracted each digit using n % 10. 🔹 Updated the product by multiplying the digit and updated the sum by adding it. 🔹 Reduced the number using integer division (n //= 10) after each step. 🔹 Finally returned the difference between product and sum. Concepts Used: 🔹 Digit Extraction 🔹 While Loop 🔹 Arithmetic Operations 🔹 Number Manipulation Key Insight: 🔹 Both product and sum can be computed in a single traversal of digits. 🔹 Efficient use of modulus and division avoids converting the number to a string. Complexity: 🔹 Time: O(d) 🔹 Space: O(1) #LeetCode #Algorithms #DataStructures #CodingInterview #100DaysOfCode #Python #ProblemSolving #LearningInPublic #TechCareers

Day 56 of #GeekStreak60: The Phantom Pointer Trick! 🕵️♂️📈 Tackled the "Sorted subsequence of size 3" problem on @GeeksforGeeks today. Key Learning: Finding an increasing triplet is easy if you use extra arrays to track minimums and maximums, but that violates the O(1) space constraint. The optimal solution is to use "Greedy State Tracking." By iterating through the array in a single pass, I maintained three variables: the absolute smallest number seen (num1), a valid middle number (num2), and a snapshot of num1 locked in at the exact moment num2 was discovered. If the loop encounters any number strictly greater than num2, the valid triplet is instantly formed! This perfectly eliminates the need for O(n) memory arrays while keeping the time complexity to a strict O(n). Just 4 days left! The logic is feeling sharper than ever. 🚀 #geekstreak60 #npci #coding #Algorithms #Python #DataStructures #Optimization #SoftwareEngineering

✅ Day 92 of 100 Days LeetCode Challenge Problem: 🔹 #2011 – Final Value of Variable After Performing Operations 🔗 https://lnkd.in/gX-JQNUJ Learning Journey: 🔹 Today’s problem was about evaluating a sequence of increment and decrement operations. 🔹 I initialized a variable ans = 0 to track the value. 🔹 Used a hashmap to map each operation to its effect: • "++X" and "X++" → +1 • "--X" and "X--" → -1 🔹 Iterated through the operations and updated ans accordingly. 🔹 Returned the final computed value. Concepts Used: 🔹 HashMap / Dictionary 🔹 String Matching 🔹 Simple Simulation Key Insight: 🔹 Instead of using multiple condition checks, mapping operations to values simplifies logic and improves readability. Complexity: 🔹 Time: O(n) 🔹 Space: O(1) #LeetCode #Algorithms #DataStructures #CodingInterview #100DaysOfCode #Python #ProblemSolving #LearningInPublic #TechCareers

✅ Day 98 of 100 Days LeetCode Challenge Problem: 🔹 #338 – Counting Bits 🔗 https://lnkd.in/gXdNxX66 Learning Journey: 🔹 Today’s problem focused on counting the number of 1s in the binary representation of numbers from 0 to n. 🔹 I initialized an array ans of size n+1. 🔹 For each number i, I converted it to binary using bin(i)[2:]. 🔹 Counted the number of '1' bits by iterating through the binary string. 🔹 Stored the count in ans[i] and returned the final array. Concepts Used: 🔹 Bit Manipulation (Binary Representation) 🔹 Array Traversal 🔹 String Processing 🔹 Brute Force Approach Key Insight: 🔹 Each number’s bit count can be computed independently. 🔹 Converting to binary and counting '1' works, but can be optimized further using DP or bit tricks. Complexity: 🔹 Time: O(n log n) (binary conversion for each number) 🔹 Space: O(n) #LeetCode #Algorithms #DataStructures #100DaysOfCode #Python #CodingJourney #ProblemSolving #LearningInPublic