search

meta-llama / llama-recipes

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.
15.35k stars 2.22k forks source link

add support for ingesting content from websites, audio files, YouTube, etc. #750

Open evanjcosgrove opened 4 weeks ago

evanjcosgrove commented 4 weeks ago

This update include adding support for multiple input formats, improving documentation, and updating dependencies.

Major Enhancements:

Support for Multiple Input Formats:

  1. Ingestion Module: Added an ingestion module (ingestion.py) that supports PDF, website, YouTube, and audio file formats. This module includes classes like PDFIngestor, WebsiteIngestor, YouTubeIngestor, and AudioIngestor to handle different types of input sources.
  2. Usage Examples: Updated README.md with detailed usage examples for ingesting content from various sources, including code snippets for each input type.

Documentation Improvements:

  1. Quickstart Guide: Enhanced the quickstart guide in recipes/quickstart/NotebookLlama/README.md with step-by-step instructions, updated terminology, and added links to relevant resources.

Dependency Updates:

  1. Requirements: Updated requirements.txt to include new dependencies like langchain, openai-whisper, and youtube-dl, and updated versions for existing dependencies.

Detailed Changes:

Ingestion Module:

Documentation:

Dependencies:

facebook-github-bot commented 4 weeks ago

Hi @evanjcosgrove!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

init27 commented 4 weeks ago

@evanjcosgrove Thank you very much for the PR-this is awesome stuff!

Can you please sign the CLA so that I may review it?

evanjcosgrove commented 4 weeks ago

@init27 thank you for the reminder, I've signed the CLA and look forward to hearing your feedback!