https://github.com/dtch1997/awesome-ml-dev-tools

Collection of development tools for ML engineering or research
https://github.com/dtch1997/awesome-ml-dev-tools

List: awesome-ml-dev-tools

Last synced: 16 days ago
JSON representation

Collection of development tools for ML engineering or research

• Host: GitHub
• URL: https://github.com/dtch1997/awesome-ml-dev-tools
• Owner: dtch1997
• Created: 2023-02-12T20:56:58.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-02-21T09:50:23.000Z (almost 2 years ago)
• Last Synced: 2024-11-20T11:47:04.975Z (about 1 month ago)
• Size: 5.86 KB
• Stars: 3
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• ultimate-awesome - awesome-ml-dev-tools - Collection of development tools for ML engineering or research. (Other Lists / Monkey C Lists)

README

        
# awesome-ml-dev-tools

Collection of resources and tools for ML engineering or research development

## LLMs

- [OpenAI GPT-3 API](https://openai.com/api/)

  - [Quickstart with Python example app](https://platform.openai.com/docs/quickstart/build-your-application) 

- [OpenAI GPT-2 open-source](https://openai.com/blog/gpt-2-1-5b-release/)

  - [HuggingFace API](https://huggingface.co/gpt2)

  - [Official Python API](https://github.com/openai/gpt-2)

  - [Simplified Python API](https://github.com/minimaxir/gpt-2-simple)

  - [Dataset](https://github.com/openai/gpt-2-output-dataset)

- [Cohere AI](https://cohere.ai/generate)  

## Q&A over documents

- [Unstructured](https://github.com/Unstructured-IO/unstructured) - Python library for preprocessing of PDFs, images, HTML, Word documents etc.

- [GPT Index](https://gpt-index.readthedocs.io/en/latest/index.html) for constructing index

- [ColBertV2](https://github.com/stanford-futuredata/ColBERT) for searching index

## Embedding Databases

- [Pinecone](https://www.pinecone.io/)

- [Weaviate](https://weaviate.io/)

- [pgvector](https://github.com/pgvector/pgvector)

## LLMs using external APIs

- [LangChain](https://github.com/hwchase17/langchain)

- [Dust.tt](https://dust.tt/)

## Prompt-engineering

- [Microsoft LMOps](https://www.infoq.com/news/2023/02/microsoft-lmops-tools/)

- [Humanloop](https://humanloop.com/)

- [Everyprompt](https://www.everyprompt.com/)

## Deploying ML-powered apps

- [Streamlit](https://streamlit.io/)

- [Gradio](https://gradio.app/)

## MLOps

- [Chip Huyenn's MLOps discord](https://discord.com/invite/Mw77HPrgjF)

- [MLFlow](https://mlflow.org/)

- [Kubeflow](https://www.kubeflow.org/)

- [Metaflow](https://metaflow.org/)

- [TFServing](https://www.tensorflow.org/tfx/guide/serving)

## ML Frameworks

- PyTorch

- Jax

- TensorFlow

## Example applications

- [Pinecone OP Stack](https://gkogan.notion.site/gkogan/The-OP-Stack-aafcab0005e3445a8ad8491aac80446c)

- [LangChain README](https://github.com/hwchase17/langchain)

  - [Q&A over Notion database](https://github.com/hwchase17/notion-qa)

  - [Chat-LangChain](https://github.com/hwchase17/chat-langchain)

  - [GPT + WolframAlpha](https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain)

- [OpenAI Cookbook](https://github.com/openai/openai-cookbook)