Skip to main content

Transform session artifacts into structured knowledge

Project description

Rewind.Learn

Transform session artifacts into structured knowledge.

PyPI version Python 3.10+ License

Installation

pip install rewindlearn

Quick Start

# Set your API key
export ANTHROPIC_API_KEY="your-key"

# Process a session
rewindlearn process run \
    --template online-course \
    --transcript lecture.vtt \
    --chat chat.txt \
    --course "AI Engineering" \
    --session 5 \
    --output study-guides/

Python API

import asyncio
from rewindlearn import process_session

async def main():
    results = await process_session(
        template="online-course",
        transcript_path="lecture.vtt",
        chat_path="chat.txt",
        course_name="AI Engineering",
        session_number=5
    )
    print(results["session_summary"])

asyncio.run(main())

Features

  • Session Summary: Comprehensive overview of the session content
  • Concept Timeline: Chronological breakdown of concepts with timestamps
  • Friction Analysis: Identifies potential confusion points and questions
  • Coverage Gaps: Topics that could use more coverage
  • Learning Resources: Curated resources for each topic
  • Action Items: Prioritized tasks for students
  • Concept Chunks: CSV with video clip markers for splitting

CLI Commands

# Show help
rewindlearn --help

# Show version
rewindlearn --version

# Process a session
rewindlearn process run --template online-course --transcript lecture.vtt --output ./output

# List available templates
rewindlearn template list

# Show template details
rewindlearn template show online-course

# Validate a template
rewindlearn template validate custom-template.yaml

# Show current configuration
rewindlearn config show

# Check configuration validity
rewindlearn config check

Configuration

Create a .env file or set environment variables:

# Required: At least one LLM API key
ANTHROPIC_API_KEY=sk-ant-...
OPENAI_API_KEY=sk-...

# Optional: LangSmith for observability
LANGSMITH_API_KEY=lsv2_...
LANGSMITH_TRACING=true

# Optional: Override defaults
REWINDLEARN_DEFAULT_PROVIDER=anthropic
REWINDLEARN_DEFAULT_MODEL=claude-sonnet-4-20250514
REWINDLEARN_TEMPLATES_DIR=./templates
REWINDLEARN_OUTPUT_DIR=./output

Development

# Clone the repository
git clone https://github.com/knightsri/rewind.learn.git
cd rewind.learn

# Install in development mode
pip install -e ".[dev]"

# Run tests
pytest -v

# Type checking
mypy src/

# Linting
ruff check src/

License

Apache 2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rewindlearn-0.1.1.tar.gz (24.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

rewindlearn-0.1.1-py3-none-any.whl (33.3 kB view details)

Uploaded Python 3

File details

Details for the file rewindlearn-0.1.1.tar.gz.

File metadata

  • Download URL: rewindlearn-0.1.1.tar.gz
  • Upload date:
  • Size: 24.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for rewindlearn-0.1.1.tar.gz
Algorithm Hash digest
SHA256 c6689dc2d1be2a0dd46020105fd3580db2e1591639c7da9efec97288034dca4f
MD5 0cb961e3e921817b6f8e243ed21e5ad4
BLAKE2b-256 ab26b569a23f7efde2066ac6f46ef7fcf73058e0fc2daf15f29808afbe2c43af

See more details on using hashes here.

File details

Details for the file rewindlearn-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: rewindlearn-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 33.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for rewindlearn-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 5cab603fcdd0e189b7bd856cdf21c1b2f442e2ca333edff989da72db3293ea9d
MD5 9459567dfa2befef0911ab0c89681051
BLAKE2b-256 22eb4276983c7083a330c18a9cdab013a2a71d4a5e54455f39d85b79830a011d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page