Practical Guides
How-To Guides
Step-by-step guides on embeddings, AI tools, and code intelligence. Practical, complete, no fluff.
How to Discover Connections in Your Reading Library with Clip
Using the knowledge graph to find clusters, navigate ideas, and uncover what your reading is really about
A step-by-step guide to using Clip's knowledge graph — from building your first library to reading the graph and acting on what you find.
Getting Started with the Pyckle Embeddings API
Zero to First Request in 10 Minutes
Complete quickstart: getting a key (free via MCPize, Pro via direct checkout), first request in Python/Node.js/cURL, batch embedding, rate limit handling, async indexing, cosine similarity, and full API reference.
How to Migrate from OpenAI Embeddings to Pyckle
Drop-in Replacement for Code Search - LangChain, LlamaIndex, ChromaDB, Pinecone, Qdrant, Weaviate
Why migrate (L1 query gap), compatibility notes, re-index time estimation, migration code for httpx/LangChain/LlamaIndex, vector store migration for ChromaDB/Pinecone/Qdrant/Weaviate, validation query set, and rollback plan.
How to Build Production Embedding Pipelines
Infrastructure, Latency, and Reliability for Teams That Can't Afford to Guess
Most embedding pipeline tutorials end where the hard problems begin. They show you how to call `model.encode()`, store the result in a list, and retrieve the top-k nearest neighbors — then declare vic...
How to Build Semantic Search for Your Codebase
From Raw Code to Meaning-Based Retrieval
This book exists because every sufficiently large codebase eventually becomes hostile to the people who work in it. Not because the code is bad — it might be excellent — but because the mechanisms we...
How to Cut Your LLM Bill in Half
Token Optimization, Caching, and Routing Strategies That Work
Most teams discover their LLM costs are out of control the same way: the billing alert fires, someone opens the dashboard, and the number staring back at them is three to five times what anyone expect...
How to Evaluate and Select an Embedding Model
The Benchmark Results Are Lying to You — Here's How to Find the Truth
A practical guide to evaluating embedding models on your own data — covering eval methodology, benchmark interpretation, model comparison, cost-quality tradeoffs, and the fine-tuned vs. general decision.
How to Manage Context Windows Effectively
What Goes In, What Stays Out, and Why It Matters
Every senior developer eventually hits the same wall. You've been running a long session with an LLM — code review, refactor, architecture discussion. The responses start drifting. The model loses tra...
How to Navigate a Large Codebase with AI
From Lost to Located in Any Codebase
The first day on a large codebase is one of the most disorienting experiences in software development. You have a repository with tens of thousands of files, a thousand commits, scattered documentatio...
How to Onboard Engineers with AI Tools
Cut Ramp Time Without Cutting Corners
The average time for a software engineer to reach full productivity at a new company is between three and six months. At a senior level, it can stretch longer — the more complex the codebase, the more...
How to Use AI for Code Review
A Practical Playbook for Faster, Higher-Quality Reviews
Code review is one of the highest-leverage activities in software development. It's also one of the most inconsistent. The same pull request reviewed by two different engineers can yield wildly differ...