pyds-ai

Data science and LLM work from a notebook, without writing much code.

pip install pyds-ai

The one rule that decides everything: the LLM never produces a number. It writes the query and it writes the words. A deterministic engine (DuckDB) computes the answer. Every result can show you the exact code that produced it via result.code().

Quickstart

import pyds_ai as pyds

pyds.setup()  # one-time key wizard, writes to ~/.pyds_ai/config.toml

d = pyds.load("sales.csv")
d.ask("which region grew fastest last quarter?")
d.chart("revenue by month, split by channel")

m = d.model(target="churn")
m.explain()
m.what_if(tenure=12, plan="premium")

k = pyds.knowledge("policies/")
k.ask("what is our refund window for enterprise?")

a = pyds.agent(uses=[d, k])
a.ask("did churn spike in any region where we changed the refund policy?")

e = pyds.evaluate(a, cases="qa_cases.csv")
e.watch()

Every result is the same shape

Every call returns a Result — never a bare DataFrame, never a dict:

result.explain()   # what was done and why, in sentences
result.code()       # the exact SQL/code that produced it
result.data()       # the underlying DataFrame
result.next()       # up to three suggested follow-up questions
result.why()        # trace: prompt version, model, cost, row counts
result.save(path)   # .html, .csv, .docx, .pptx, .pdf

A failed call returns a Failure (also a Result) instead of a raw traceback: what broke, what it looked like, and the one-line fix to try.

Privacy default

send_data_values = false by default: the model gets column names, types and summary statistics, not your raw rows. Your data does not leave the building unless you explicitly opt in. Set it via:

import pyds_ai as pyds
cfg = pyds.config.load_config()
cfg["privacy"]["send_data_values"] = True
pyds.config.save_config(cfg)

Installing extras

pip install pyds-ai[ml]          # AutoML: scikit-learn (+ joblib, shap)
pip install pyds-ai[rag]         # RAG: pdf/docx/html parsing
pip install pyds-ai[rag-chroma]  # persistent vector store (Chroma)
pip install pyds-ai[rag-faiss]   # in-process ANN vector store (FAISS)
pip install pyds-ai[rag-pgvector]# Postgres + pgvector vector store
pip install pyds-ai[report]      # result.save(): .pptx, .docx, .pdf
pip install pyds-ai[anthropic]   # or [openai], [gemini] — Ollama needs no extra
pip install pyds-ai[all]

Importing a missing extra returns a friendly message with the exact pip command, never a bare ImportError. The default pyds.knowledge() vector store is a zero-dependency in-memory hashing embedder — RAG works the moment pyds-ai[rag] is installed, no embedding API call required.

Plugins

Internal teams can register a company database reader or a private model provider without forking, via entry points:

[project.entry-points."pyds.providers"]
internal = "mycompany.pyds_plugin:InternalLLM"

Anything registered under the pyds.providers group is picked up by pyds.setup(provider="internal") / pyds.config.get_llm_client() the same way the four built-in providers are.

Development

git clone <this repo> && cd pyds-ai
python -m venv .venv && .venv/Scripts/activate   # or source .venv/bin/activate
pip install -e ".[all,test]"
pytest

The test suite runs fully offline: a fake LLM client (tests/support.py) stands in for every provider, so no API key or network access is needed to validate the package.

Publishing (maintainers)

python -m pip install --upgrade build twine
python -m build            # writes dist/*.whl and dist/*.tar.gz
twine check dist/*
twine upload dist/*        # or: twine upload --repository testpypi dist/*

License

Apache-2.0 — see LICENSE.