programasweights-python: Instructions file for Codex

ProgramAsWeights (PAW)

PAW compiles natural language specifications into tiny neural functions that run locally. Each function takes a single text input and returns a single text output. Use it when you need fuzzy text processing — classification, extraction, format repair, search, triage — that regex can't handle but a full LLM is overkill for.

Website: https://programasweights.com Full documentation: https://programasweights.readthedocs.io

When to Use PAW

• Fuzzy search — typo-tolerant matching, semantic search, near-duplicate detection
• Format repair — fix broken JSON, normalize dates, repair malformed inputs
• Classification — sentiment, urgency, categories defined in your own words
• Extraction — emails, names, dates from messy unstructured text
• Log triage — extract errors from verbose output, filter noise
• Intent routing — map user descriptions to the closest URL, menu item, or setting
• Agent preprocessing — parse tool calls, validate outputs, route tasks

Install

pip install programasweights --extra-index-url https://pypi.programasweights.com/simple/

Quickstart

import programasweights as paw

# Compile your own function and save its ID
program = paw.compile(
    "Classify if a message needs immediate attention or can wait. "
    "Return only 'immediate' or 'wait'."
)
print(program.id)  # Save this ID for future runs

# Load once and reuse the function locally
fn = paw.function(program.id)
fn("Urgent: server is down!")  # "immediate"
fn("Newsletter: spring picnic")  # "wait"

On future runs, load the saved ID with paw.function(saved_program_id). Compile outside request handlers and reuse the loaded function across calls.

Load a local .paw file with paw.function("./classifier.paw") (SDK 0.4.5+).

If you want the smaller browser-compatible runtime explicitly, pass compiler="paw-4b-gpt2". Otherwise, omit compiler and let the server default decide.

Remote inference (optional)