Vanna Source Tour: Inside the Text-to-SQL Agent Framework
Vanna is an open-source Python framework that turns natural-language questions into SQL queries and, ultimately, into charts and summaries. You feed it your schema (DDL), business documentation, and sample queries; it embeds and stores them, then retrieves the most relevant...
Ray Source Tour: How Tasks, Actors and the Object Store Fit Together
Ray began as a research project at UC Berkeley and grew into what its README now calls “a unified framework for scaling AI and Python applications.” The pitch is simple: the same Python you run on your laptop should run...
Pydantic source tour: how BaseModel turns type hints into validators and seri...
Pydantic is the quiet dependency under a remarkable amount of the modern Python stack. If you have ever declared a FastAPI endpoint, asked an LLM for structured output with instructor, defined tools with the MCP Python SDK, or let an...
Arize Phoenix Source Tour: Inside the Open-Source OTel-Native LLM Tracing Server
If you have ever shipped an LLM application and then asked “what did the model actually see, and what did it answer?”, you already understand the problem Arize set out to solve with Phoenix. Phoenix is an open-source, OpenTelemetry-native observability...
Opik: A Source Tour of Comet's Open-Source LLM Observability Stack
If you have shipped anything with an LLM in it, you know the feeling: the demo worked, and then production happened. Prompts drift, models get swapped, retrieval silently degrades, and nobody can say which call returned what. Opik is Comet’s...
MLflow Source Tour: From Fluent API to Backend Stores and the Model Registry
MLflow describes itself on its README as “The Open Source AI Engineering Platform for Agents, LLMs & Models,” and the claim is not marketing fluff: the project reports over 60 million monthly downloads, and the repository is one of the...
Inside Matplotlib: A Source-Level Architecture Tour of Python's Plotting Library
Matplotlib has been the default way to draw a picture of your data in Python for more than two decades. Its README describes it as a comprehensive library for creating static, animated, and interactive visualizations, one that produces publication-quality figures...
huggingface_hub: A Source Tour of the Python Client Behind the Hugging Face Hub
Every time you call from_pretrained in [transformers](/transformers/) — well, not quite. What actually fetches the weights is a smaller, quieter package underneath: huggingface_hub. It is the client library that speaks to the Hub's REST API, moves terabytes of model weights...
FastAPI Source Tour: How Requests, Dependencies and OpenAPI Are Wired Together
FastAPI has quietly become the default answer to “how do I expose this Python function over HTTP?” — for data science teams shipping models, for backend teams building microservices, and increasingly for LLM tooling that needs a clean JSON surface....
Apache Airflow Source Tour: How Airflow 3 Schedules, Executes, and Serves You...
Apache Airflow is the open-source orchestrator that turned “cron jobs with dependencies” into a programmable, observable discipline. If you have ever waited on a nightly data load, chained an extraction step to a training job, or retried a flaky API...
USearch Architecture: A Source Tour of Unum's Single-Header Vector Search Engine
Most vector databases you encounter are services: a server process, a network protocol, a deployment story. USearch from Unum-cloud takes the opposite path. It is a single-file C++11 header — include/usearch/index.hpp — that implements a multi-layer proximity graph for approximate...
txtai Source Tour: Inside the Embeddings Database Engine
Most vector-search libraries hand you an index and stop there. txtai, from NeuML, takes the wider view: it is an embeddings database — a Python platform where you index text, documents, audio, images and video, keep the original content in...
pgvector Source Tour: How Vector Search Lives Inside Postgres
Every retrieval-augmented application eventually faces the same storage question: where do the embeddings live? Many teams end up syncing a vector file with a relational database, and paying for two systems that drift apart. pgvector takes the opposite approach: it...
OpenAI Evals: A Source Tour of the LLM Evaluation Framework
Every serious LLM project eventually hits the same wall: you changed one word in a prompt, or swapped one model checkpoint for another, and you have no idea whether the output got better or worse. OpenAI’s answer is evals, the...
Modin Source Tour: How One Import Scales pandas Across Every Core
pandas has a scaling problem that every data scientist eventually hits: it is single-threaded, and the moment your dataset outgrows a fraction of your machine’s memory, workflows that felt snappy on a laptop become slow, swap-thrashing misery. Modin is a...
Marqo Source Tour: Inside the AI-Native Vector Search Engine's Architecture
Marqo is an open-source vector search engine with a simple pitch: you hand it documents — text, images, or mixed content — and it generates embeddings for you, stores them, and lets you query them in natural language through a...
Inside LM Evaluation Harness: How EleutherAI Turns a Model and a YAML File in...
Every benchmark leaderboard you have seen — MMLU, HellaSwag, GSM8K — is computed by software that has to make hundreds of small, boring decisions correctly: how the prompt is assembled, how many few-shot examples are drawn and from which split,...
LlamaIndex Source Tour: How the Data Framework for LLM Apps Is Assembled
Ask a room of Python developers how they wire private documents into large language models, and sooner or later the answer will be LlamaIndex. The run-llama/llama_index repository is the home of that framework: a data layer that connects files, APIs,...
Instructor Source Tour: How the Structured-Outputs Library Turns LLM JSON Int...
If you have ever extracted structured data from an LLM, you have probably met Instructor: define a Pydantic model, hand it to client.chat.completions.create(response_model=...), and get back a validated, typed object instead of a string of JSON you have to scrape...
Guidance Source Tour: The Architecture Behind Constrained LLM Generation
Most libraries that talk to language models treat the model as an oracle: you send a prompt, you get text back, and you pray it parses. Guidance — the open-source project maintained under the guidance-ai organization and originally developed at...
Coqui TTS Anatomy: the Zoo Facade, the Wrappers, the Vocoder Shelf - Inside c...
Text-to-speech is the rare field where the whole lineage of a decade still runs side by side: attention-based seq2seq models from 2017, flow-based generators from 2020, adversarial end-to-end systems, and the GPT-style voice cloners of the streaming era. The Coqui...
Polars Under the Hood: How a Rust DataFrame Engine Rebuilt Python Data Work
Every Python developer eventually hits the same wall: a table too big for memory, a join that takes twenty minutes, a group-by that spills into swap. The usual answer has been to rent a bigger machine or to retreat into...
OpenCV Source Tour: From the Mat Container to the DNN Engine Inside the World...
OpenCV is the library that every other computer vision tool gets compared to. Twenty-plus years in, it is the default import in tutorials, the runtime under countless factory robots and security cameras, and the compatibility target that newer frameworks measure...
Numba, From @jit to Machine Code: A Source Tour of the LLVM-Based JIT Compile...
Numba occupies a unique spot in the Python performance world: it is a compiler that ships as a pip package. You put a decorator on a plain Python function, call the function once, and by the time that call returns,...