/** @type {import('tailwindcss').Config} */
module.exports = {
  content: [
    "./pages/**/*.{js,ts,jsx,tsx,mdx}",
    "./components/**/*.{js,ts,jsx,tsx,mdx}",
    "./app/**/*.{js,ts,jsx,tsx,mdx}",
  ],
  theme: {
    extend: {
      colors: {
        primary: "#6f00ff",
        light: "#8075ff",
        dark: "#6f00ff",
      },
    },
  },
  plugins: [],
};


Quantitative metrics

Qualitative metrics

Weavel docs

Welcome

User Guides

Cookbooks

API Reference

SDK Reference

Dashboard

Discord

Guide to evaluating LLM generated outputs.

Evaluation

Weavel automates prompt engineering, 50x times faster than humans.

Overview

Get Started

Basic concepts to get you started with automated prompt engineering.

Concepts

Quickstart guide to get your first prompt optimized.

Quickstart

Guide to setting up and improving datasets for continuous prompt optimization.

Datasets

Continuous optimization of prompts based on user feedback.

CI/CD for Prompts

Capture Session

Capture Message

Capture Track Event

Capture Trace

Capture Span

Capture Log

Capture Generation

Identify User

Get Dataset

Create Dataset

Delete Dataset

Create Dataset Item

Upload Dataset Items

List Prompts

Fetch Prompt

Create Prompt

Delete Prompt

List Prompt Versions

Fetch Prompt Version

Create Prompt Version

Delete Prompt Version

Common types and utilities for programmatic prompt engineering.

ape-common

Utility class for storing and managing prompts for language models.

Prompt

A TypedDict class representing an item in a dataset.

DatasetItem

Abstract base class for generation tasks.

BaseGenerator

Class for generating responses from language models using prompts.

Generator

Abstract base class for individual metrics in prompt evaluation.

BaseMetric

A metric class that computes the similarity between two JSON-like structures.

JsonMatchMetric

A metric class that computes the Semantic F1 score between a prediction and a gold standard.

SemanticF1Metric

A metric class that computes the cosine similarity between two text inputs.

CosineSimilarityMetric

Abstract base class for global metrics in prompt evaluation.

BaseGlobalMetric

A class that computes the average of local scores as the global metric.

AverageGlobalMetric

A class for evaluating prompts using a given testset, metric, and global metric.

Evaluator

Utility class for tracking and managing API costs.

Prompt Optimization

​Quantitative metrics

​Qualitative metrics

Quantitative metrics

Qualitative metrics