A place for real developers
The gap between
knowing and building
closes here.
Structured notes on AI, Python, databases, DSA, and software engineering — written the way you'd explain it to a colleague who actually gets it.
"Every post earns its reading time before it goes up. Depth over frequency. Clarity over coverage."
Latest posts
The End-to-End RAG Pipeline: How Every Piece Fits Together
Assembling fourteen chapters into one coherent system — the offline indexing path, the online query path, and the error handling that separates a working demo from something production-ready.
Natural Language ProcessingLLM Integration for RAG: Context Windows, Token Budgets, and Tool Use
The engineering layer between your retrieval pipeline and the model itself — context windows, token budgeting, streaming, structured output, function calling, and what long-context models actually change.
Natural Language ProcessingPrompt Engineering for RAG: Turning Retrieved Chunks Into Grounded Answers
Retrieval can be perfect and the answer can still go wrong at the prompt. Context injection, templates, system prompts, few-shot examples, citation prompting, and concrete hallucination-prevention techniques.
Natural Language ProcessingReranking in RAG: Bi-Encoders, Cross-Encoders, and ColBERT Explained
Why a second, smarter ranking pass often matters more than the first retrieval pass — bi-encoders vs cross-encoders, ColBERT's late interaction, score fusion, and learned ranking models.
Natural Language ProcessingAdvanced Retrieval: Techniques for When Simple Similarity Search Isn't Enough
Beyond basic vector search — HyDE, multi-query retrieval, fusion, contextual retrieval, graph-based retrieval, and multi-hop reasoning, and what specific retrieval failure each one is built to fix.