Site Map
11 courses · 255 lessons · 16 posts · 7 benchmarks. Lessons open after you sign in.
RecallRun
Your account
Benchmarks
- All benchmarks
- Chunk size sweep: 200 to 2,000 characters
- Five chunking strategies on real docs
- Hybrid search: BM25 + vectors, alpha swept 0 to 1
- Exact vector search vs HNSW, 10k to 1M vectors
- Golden-set evals in CI: catching retrieval regressions
- A TF-IDF router instead of an LLM call
- Predicting embeddings vs tokens with less data
Blog
- All posts
- Reciprocal Rank Fusion k=60: what the constant does, measured on real BM25 + vector runs
- Build an MCP server in Python for your docs: stdio and HTTP, with measured payload sizes
- Metadata filtering in vector search: post-filter loses results, measured
- Databricks control plane vs compute plane (data plane), explained
- FastAPI headers: read, validate and set them (and the underscore trap)
- OpenAI Responses API vs Chat Completions: what changes in your code
- Does chunk overlap help? Measured at 0, 10, 20 and 40 percent
- Chunk size sweep: 200 to 2,000 characters on real docs
- RAG evals that fail CI: a golden-set harness in about 100 lines of Python
- JEPA vs LLMs: what LeCun's world models actually change for engineers
- Do you need a vector database? Brute-force search benchmarked from 10k to 1M vectors
- Hybrid search in Python: BM25 + vectors with Reciprocal Rank Fusion, alpha swept 0 to 1
- Jev vs LLMs: when a decision model beats a chat model (and when it doesn't)
- RAG chunking, measured: heading-aware chunks doubled hit@1 on the FastAPI docs
- The RAG production checklist: 25 checks before real users see it
- Stop fake citations in RAG: validate them server-side in 25 lines of Python
- Topics
Community
- Community blog
- asyncio, threads or processes? Choosing Python concurrency by workload
- Idempotency keys: making POST requests safe to retry
- Composite indexes in SQL: why column order decides everything
- Prompt injection: practical defences for LLM apps that read untrusted text
- Caching for backend engineers: cache-aside, TTLs and the stampede problem
- Logs, metrics and traces: a practical introduction to observability with OpenTelemetry
- Git workflows for small teams: trunk-based development vs feature branches
- Vector embeddings explained for developers: similarity, normalisation and the mistakes that hurt search
- uv: one fast tool for Python packages, virtual environments and versions
- Ruff: replacing Flake8, isort and Black with one fast linter and formatter
- DuckDB: fast SQL analytics on Parquet, CSV and DataFrames without a server
- pgvector: vector search inside the Postgres you already run
- Ollama: run open LLMs locally for development, privacy and offline work
- Pydantic v2: validate data at the edges of your Python application
- gitcollect: group GitHub and GitLab repos into collections, with per-repo access control
- Write for RecallRun
Learn
- All courses
- Core Python
- Getting started
- Control flow & collections
- Functions & modules
- Files, errors & the standard library
- Object-oriented Python
- Writing real programs
- Advanced Python
- How Python really works
- Functions & iteration
- Object-oriented Python
- Robust code
- Concurrency & performance
- Shipping Python
- DSA in Python
- Foundations
- Linear structures
- Searching & sorting
- Trees & heaps
- Graphs
- Algorithmic paradigms
- Interview-ready
- SQL
- Foundations
- Shaping results
- Combining tables
- Analytics
- Designing databases
- Changing data
- Performance
- Hands-on project
- MySQL
- The server
- InnoDB internals
- Indexing & query tuning
- MySQL SQL features
- Operations
- Hands-on project
- FastAPI
- How FastAPI works
- Structuring a real service
- Async, concurrency & streaming
- Data & security
- Quality & production
- Hands-on project
- System Design
- Thinking in scale
- Stage 0–1: one server
- Stage 2–3: 1K to 100K users
- Stage 4: 100K to 1M users
- Operating at a million
- Putting it together
- PySpark
- Foundations & Architecture
- Core APIs
- Analytics in Spark
- Under the hood
- Performance engineering
- Beyond batch & production
- Hands-on project
- Databricks
- The platform
- Data & governance
- Workloads
- Production
- Hands-on project
- OpenAI SDK
- Foundations
- Core capabilities
- Production engineering
- Agents & evaluation
- Hands-on project
- AI Engineering
- How LLMs work
- Retrieval-augmented generation
- Agents & MCP
- Observability & operations
- Hands-on project