Data

Tools

Indexes

Applications

Experiments

Open Source Science

tamingllms

Taming LLMs: A Practical Guide to LLM Pitfalls with Open Source Software

https://github.com/souzatharsis/tamingllms

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.7%) to scientific vocabulary

Keywords

book chatgpt genai huggingface langchain llama llm llms open-source outlines python qwen taming-llms

Keywords from Contributors

hack
Last synced: 6 months ago · JSON representation ·

Repository

Taming LLMs: A Practical Guide to LLM Pitfalls with Open Source Software

Basic Info
  • Host: GitHub
  • Owner: souzatharsis
  • License: other
  • Language: Jupyter Notebook
  • Default Branch: master
  • Homepage: https://www.tamingllms.com
  • Size: 97 MB
Statistics
  • Stars: 309
  • Watchers: 9
  • Forks: 26
  • Open Issues: 13
  • Releases: 0
Topics
book chatgpt genai huggingface langchain llama llm llms open-source outlines python qwen taming-llms
Created over 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation

README.md

Receive updates on new Chapters here.

Taming LLMs Cover

Please open an issue with your feedback or suggestions!

Taming LLMs

Publication Date: February 2, 2025

A Practical Guide to LLM Pitfalls with Open Source Software

Abstract: The current discourse around Large Language Models (LLMs) tends to focus heavily on their capabilities while glossing over fundamental challenges. Conversely, this book takes a critical look at the key limitations and implementation pitfalls that engineers and technical leaders encounter when building LLM-powered applications. Through practical Python examples and proven open source solutions, it provides an introductory yet comprehensive guide for navigating these challenges. The focus is on concrete problems with reproducible code examples and battle-tested open source tools. By understanding these pitfalls upfront, readers will be better equipped to build products that harness the power of LLMs while sidestepping their inherent limitations.

| Chapter | Website | Notebook | |-------------------------------------------|--------------|---------------| | Preface | html | N/A | | About the Book | html | N/A | | Chapter 1: The Evals Gap | html | ipynb | | Chapter 2: Structured Output| html | ipynb | | Chapter 3: Managing Input Data | html | ipynb | | Chapter 4: Safety | html | ipynb | | Chapter 5: Preference-Based Alignment | html | ipynb | | Chapter 6: Local LLMs in Practice | html | ipynb | | Chapter 7: The Falling Cost Paradox | | | | Chapter 8: Frontiers | | | | Appendix A: Tools and Resources | | |

Citation

CC BY-NC-SA 4.0

Owner

  • Name: Tharsis Souza
  • Login: souzatharsis
  • Kind: user
  • Location: New York, NY

writing data-driven stories.

Citation (CITATION.cff) 

cff-version: 1.2.0
title: "Taming LLMs: A Practical Guide to LLM Pitfalls with Open Source Software"
authors:
  - given-names: Tharsis
    name-particle: T. P.
    family-names: Souza
repository-code: 'https://github.com/souzatharsis/tamingLLMs'
license: CC BY NC SA

GitHub Events

Total
  • Issues event: 38
  • Watch event: 307
  • Delete event: 3
  • Member event: 1
  • Issue comment event: 25
  • Push event: 177
  • Pull request event: 12
  • Fork event: 25
  • Create event: 5
Last Year
  • Issues event: 38
  • Watch event: 307
  • Delete event: 3
  • Member event: 1
  • Issue comment event: 25
  • Push event: 177
  • Pull request event: 12
  • Fork event: 25
  • Create event: 5

Committers

Last synced: 9 months ago

All Time
  • Total Commits: 174
  • Total Committers: 4
  • Avg Commits per committer: 43.5
  • Development Distribution Score (DDS): 0.172
Past Year
  • Commits: 174
  • Committers: 4
  • Avg Commits per committer: 43.5
  • Development Distribution Score (DDS): 0.172
Top Committers
Name Email Commits
souzatharsis s****s@g****m 144
Tharsis Souza s****s@g****m 26
ImgBotApp I****p@g****m 3
babaniyi h****e@g****m 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 28
  • Total pull requests: 9
  • Average time to close issues: 11 days
  • Average time to close pull requests: 8 days
  • Total issue authors: 8
  • Total pull request authors: 2
  • Average comments per issue: 0.75
  • Average comments per pull request: 0.67
  • Merged pull requests: 5
  • Bot issues: 0
  • Bot pull requests: 5
Past Year
  • Issues: 28
  • Pull requests: 9
  • Average time to close issues: 11 days
  • Average time to close pull requests: 8 days
  • Issue authors: 8
  • Pull request authors: 2
  • Average comments per issue: 0.75
  • Average comments per pull request: 0.67
  • Merged pull requests: 5
  • Bot issues: 0
  • Bot pull requests: 5
View more stats
Top Authors
Issue Authors
  • souzatharsis (18)
  • babaniyi (2)
  • druce (2)
  • dylanjcastillo (1)
  • DidierRLopes (1)
  • impredicative (1)
  • ciwchris (1)
  • JackyXiao98 (1)
Pull Request Authors
  • imgbot[bot] (8)
  • babaniyi (4)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

pyproject.toml pypi
  • jupyter-book ^1.0.3
  • python ^3.11
poetry.lock pypi
  • accessible-pygments 0.0.5
  • alabaster 0.7.16
  • appnope 0.1.4
  • asttokens 2.4.1
  • attrs 24.2.0
  • babel 2.16.0
  • beautifulsoup4 4.12.3
  • certifi 2024.8.30
  • cffi 1.17.1
  • charset-normalizer 3.4.0
  • click 8.1.7
  • colorama 0.4.6
  • comm 0.2.2
  • debugpy 1.8.8
  • decorator 5.1.1
  • docutils 0.20.1
  • executing 2.1.0
  • fastjsonschema 2.20.0
  • greenlet 3.1.1
  • idna 3.10
  • imagesize 1.4.1
  • importlib-metadata 8.5.0
  • ipykernel 6.29.5
  • ipython 8.29.0
  • jedi 0.19.2
  • jinja2 3.1.4
  • jsonschema 4.23.0
  • jsonschema-specifications 2024.10.1
  • jupyter-book 1.0.3
  • jupyter-cache 1.0.0
  • jupyter-client 8.6.3
  • jupyter-core 5.7.2
  • latexcodec 3.0.0
  • linkify-it-py 2.0.3
  • markdown-it-py 3.0.0
  • markupsafe 3.0.2
  • matplotlib-inline 0.1.7
  • mdit-py-plugins 0.4.2
  • mdurl 0.1.2
  • myst-nb 1.1.2
  • myst-parser 2.0.0
  • nbclient 0.10.0
  • nbformat 5.10.4
  • nest-asyncio 1.6.0
  • packaging 24.2
  • parso 0.8.4
  • pexpect 4.9.0
  • platformdirs 4.3.6
  • prompt-toolkit 3.0.48
  • psutil 6.1.0
  • ptyprocess 0.7.0
  • pure-eval 0.2.3
  • pybtex 0.24.0
  • pybtex-docutils 1.0.3
  • pycparser 2.22
  • pydata-sphinx-theme 0.16.0
  • pygments 2.18.0
  • python-dateutil 2.9.0.post0
  • pywin32 308
  • pyyaml 6.0.2
  • pyzmq 26.2.0
  • referencing 0.35.1
  • requests 2.32.3
  • rpds-py 0.21.0
  • setuptools 75.4.0
  • six 1.16.0
  • snowballstemmer 2.2.0
  • soupsieve 2.6
  • sphinx 7.4.7
  • sphinx-book-theme 1.1.3
  • sphinx-comments 0.0.3
  • sphinx-copybutton 0.5.2
  • sphinx-design 0.6.1
  • sphinx-external-toc 1.0.1
  • sphinx-jupyterbook-latex 1.0.0
  • sphinx-multitoc-numbering 0.1.3
  • sphinx-thebe 0.3.1
  • sphinx-togglebutton 0.3.2
  • sphinxcontrib-applehelp 2.0.0
  • sphinxcontrib-bibtex 2.6.3
  • sphinxcontrib-devhelp 2.0.0
  • sphinxcontrib-htmlhelp 2.1.0
  • sphinxcontrib-jsmath 1.0.1
  • sphinxcontrib-qthelp 2.0.0
  • sphinxcontrib-serializinghtml 2.0.0
  • sqlalchemy 2.0.36
  • stack-data 0.6.3
  • tabulate 0.9.0
  • tornado 6.4.1
  • traitlets 5.14.3
  • typing-extensions 4.12.2
  • uc-micro-py 1.0.3
  • urllib3 2.2.3
  • wcwidth 0.2.13
  • wheel 0.45.0
  • zipp 3.21.0
.github/workflows/static.yml actions
  • actions/checkout v4 composite
  • actions/configure-pages v5 composite
  • actions/deploy-pages v4 composite
  • actions/upload-pages-artifact v3 composite
tamingllms/requirements.txt pypi
  • jupyter-book *
  • matplotlib *
  • numpy *
package-lock.json npm
  • 694 dependencies
package.json npm
  • promptfoo ^0.100.5