diff --git a/tamingllms/_build/.doctrees/environment.pickle b/tamingllms/_build/.doctrees/environment.pickle index 7a16309..e6c4b91 100644 Binary files a/tamingllms/_build/.doctrees/environment.pickle and b/tamingllms/_build/.doctrees/environment.pickle differ diff --git a/tamingllms/_build/.doctrees/markdown/toc.doctree b/tamingllms/_build/.doctrees/markdown/toc.doctree index 8329d5c..bf6d215 100644 Binary files a/tamingllms/_build/.doctrees/markdown/toc.doctree and b/tamingllms/_build/.doctrees/markdown/toc.doctree differ diff --git a/tamingllms/_build/.doctrees/notebooks/safety.doctree b/tamingllms/_build/.doctrees/notebooks/safety.doctree index ae5a669..f09b5d9 100644 Binary files a/tamingllms/_build/.doctrees/notebooks/safety.doctree and b/tamingllms/_build/.doctrees/notebooks/safety.doctree differ diff --git a/tamingllms/_build/html/.buildinfo b/tamingllms/_build/html/.buildinfo index 81d12cb..56b1850 100644 --- a/tamingllms/_build/html/.buildinfo +++ b/tamingllms/_build/html/.buildinfo @@ -1,4 +1,4 @@ # Sphinx build info version 1 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done. -config: b72ab834db8f31605e361f26c8f2a57b +config: fa8d6b99199a6b892b703f4c8078973c tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/tamingllms/_build/html/_images/design.png b/tamingllms/_build/html/_images/design.png new file mode 100644 index 0000000..c65ac43 Binary files /dev/null and b/tamingllms/_build/html/_images/design.png differ diff --git a/tamingllms/_build/html/_sources/markdown/toc.md b/tamingllms/_build/html/_sources/markdown/toc.md index 1731c8a..c75194c 100644 --- a/tamingllms/_build/html/_sources/markdown/toc.md +++ b/tamingllms/_build/html/_sources/markdown/toc.md @@ -14,6 +14,8 @@ date: "2024-12-16" 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.* +--- + (*) *The pdf version is preferred as it contains corrections and side notes.* | Chapter (*) | PDF | Podcast | Website | Notebook | Status | diff --git a/tamingllms/_build/html/_sources/notebooks/safety.ipynb b/tamingllms/_build/html/_sources/notebooks/safety.ipynb index 2d6d4ba..0414fc6 100644 --- a/tamingllms/_build/html/_sources/notebooks/safety.ipynb +++ b/tamingllms/_build/html/_sources/notebooks/safety.ipynb @@ -424,7 +424,7 @@ "\n", "Building safe and reliable AI systems requires a comprehensive safety plan that addresses potential risks and establishes clear guidelines for development and deployment. This section outlines a structured approach to designing such a plan, breaking down the process into key phases from initial policy definition through implementation and monitoring as depicted in {numref}`safety-plan`.\n", "\n", - "```{figure} ../_static/safety/design.svg\n", + "```{figure} ../_static/safety/design.png\n", "---\n", "name: safety-plan\n", "alt: Safety Plan Design Phases\n", diff --git a/tamingllms/_build/html/_static/taming.ico b/tamingllms/_build/html/_static/taming.ico new file mode 100644 index 0000000..1923663 Binary files /dev/null and b/tamingllms/_build/html/_static/taming.ico differ diff --git a/tamingllms/_build/html/genindex.html b/tamingllms/_build/html/genindex.html index 6b43854..f7d0e72 100644 --- a/tamingllms/_build/html/genindex.html +++ b/tamingllms/_build/html/genindex.html @@ -43,6 +43,7 @@ + diff --git a/tamingllms/_build/html/markdown/intro.html b/tamingllms/_build/html/markdown/intro.html index 47d48bd..edec3e0 100644 --- a/tamingllms/_build/html/markdown/intro.html +++ b/tamingllms/_build/html/markdown/intro.html @@ -35,6 +35,7 @@ + diff --git a/tamingllms/_build/html/markdown/preface.html b/tamingllms/_build/html/markdown/preface.html index d5b08ce..a4ea804 100644 --- a/tamingllms/_build/html/markdown/preface.html +++ b/tamingllms/_build/html/markdown/preface.html @@ -35,6 +35,7 @@ + diff --git a/tamingllms/_build/html/markdown/toc.html b/tamingllms/_build/html/markdown/toc.html index 0c42994..7901edd 100644 --- a/tamingllms/_build/html/markdown/toc.html +++ b/tamingllms/_build/html/markdown/toc.html @@ -35,6 +35,7 @@ + @@ -237,6 +238,7 @@

Taming LLMs<

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.

+

(*) The pdf version is preferred as it contains corrections and side notes.

diff --git a/tamingllms/_build/html/notebooks/alignment.html b/tamingllms/_build/html/notebooks/alignment.html index b7d0338..fe0d5e2 100644 --- a/tamingllms/_build/html/notebooks/alignment.html +++ b/tamingllms/_build/html/notebooks/alignment.html @@ -45,6 +45,7 @@ + diff --git a/tamingllms/_build/html/notebooks/cost.html b/tamingllms/_build/html/notebooks/cost.html index fb559dc..e85948a 100644 --- a/tamingllms/_build/html/notebooks/cost.html +++ b/tamingllms/_build/html/notebooks/cost.html @@ -37,6 +37,7 @@ + diff --git a/tamingllms/_build/html/notebooks/evals.html b/tamingllms/_build/html/notebooks/evals.html index a4ef15b..2dcc500 100644 --- a/tamingllms/_build/html/notebooks/evals.html +++ b/tamingllms/_build/html/notebooks/evals.html @@ -35,6 +35,7 @@ + diff --git a/tamingllms/_build/html/notebooks/input.html b/tamingllms/_build/html/notebooks/input.html index fa2d9ae..d8e65a3 100644 --- a/tamingllms/_build/html/notebooks/input.html +++ b/tamingllms/_build/html/notebooks/input.html @@ -35,6 +35,7 @@ + diff --git a/tamingllms/_build/html/notebooks/local.html b/tamingllms/_build/html/notebooks/local.html index e493529..6446fa1 100644 --- a/tamingllms/_build/html/notebooks/local.html +++ b/tamingllms/_build/html/notebooks/local.html @@ -37,6 +37,7 @@ + diff --git a/tamingllms/_build/html/notebooks/safety.html b/tamingllms/_build/html/notebooks/safety.html index 3a520c3..c165967 100644 --- a/tamingllms/_build/html/notebooks/safety.html +++ b/tamingllms/_build/html/notebooks/safety.html @@ -35,6 +35,7 @@ + @@ -707,7 +708,7 @@

6.5. Designing a Safety Plan

Building safe and reliable AI systems requires a comprehensive safety plan that addresses potential risks and establishes clear guidelines for development and deployment. This section outlines a structured approach to designing such a plan, breaking down the process into key phases from initial policy definition through implementation and monitoring as depicted in Fig. 6.9.

-Safety Plan Design Phases +Safety Plan Design Phases

Fig. 6.9 Safety Plan Design Phases.

diff --git a/tamingllms/_build/html/notebooks/structured_output.html b/tamingllms/_build/html/notebooks/structured_output.html index 31adade..8aee456 100644 --- a/tamingllms/_build/html/notebooks/structured_output.html +++ b/tamingllms/_build/html/notebooks/structured_output.html @@ -37,6 +37,7 @@ + diff --git a/tamingllms/_build/html/search.html b/tamingllms/_build/html/search.html index 3471427..6511d4a 100644 --- a/tamingllms/_build/html/search.html +++ b/tamingllms/_build/html/search.html @@ -45,6 +45,7 @@ + diff --git a/tamingllms/_build/jupyter_execute/markdown/intro.ipynb b/tamingllms/_build/jupyter_execute/markdown/intro.ipynb index 5ca89f7..6e12940 100644 --- a/tamingllms/_build/jupyter_execute/markdown/intro.ipynb +++ b/tamingllms/_build/jupyter_execute/markdown/intro.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "markdown", - "id": "0907576d", + "id": "b8ca7a3c", "metadata": {}, "source": [ "(intro)=\n", diff --git a/tamingllms/_build/jupyter_execute/notebooks/safety.ipynb b/tamingllms/_build/jupyter_execute/notebooks/safety.ipynb index 8988a53..991cbf3 100644 --- a/tamingllms/_build/jupyter_execute/notebooks/safety.ipynb +++ b/tamingllms/_build/jupyter_execute/notebooks/safety.ipynb @@ -424,7 +424,7 @@ "\n", "Building safe and reliable AI systems requires a comprehensive safety plan that addresses potential risks and establishes clear guidelines for development and deployment. This section outlines a structured approach to designing such a plan, breaking down the process into key phases from initial policy definition through implementation and monitoring as depicted in {numref}`safety-plan`.\n", "\n", - "```{figure} ../_static/safety/design.svg\n", + "```{figure} ../_static/safety/design.png\n", "---\n", "name: safety-plan\n", "alt: Safety Plan Design Phases\n", diff --git a/tamingllms/_config.yml b/tamingllms/_config.yml index 48c40fe..cc6ffb6 100644 --- a/tamingllms/_config.yml +++ b/tamingllms/_config.yml @@ -21,6 +21,13 @@ bibtex_bibfiles: - references.bib +repository: + url: https://github.com/souzatharsis/tamingllms + +html: + use_repository_button: true + favicon: "_static/taming.ico" + only_build_toc_files: true diff --git a/tamingllms/_static/taming.ico b/tamingllms/_static/taming.ico new file mode 100644 index 0000000..1923663 Binary files /dev/null and b/tamingllms/_static/taming.ico differ diff --git a/tamingllms/latex/local.tex b/tamingllms/latex/local.tex index 6e17a54..ddf8743 100644 --- a/tamingllms/latex/local.tex +++ b/tamingllms/latex/local.tex @@ -251,16 +251,20 @@ \subsection{Licensing} \centering \caption{Open Source LLMs.} \label{tab:open_source_llms} -\begin{tabular}{lll} +\begin{tabular}{p{2cm}p{2cm}p{8cm}} \hline Creator & LLM & License \\ \hline -Meta AI & LLaMA 3 & Custom - Free if under 700M users, cannot use outputs to train other non-LLaMA LLMs \\ +Meta AI & LLaMA 3 & Custom - Free if under 700M users,\\ +& & cannot use outputs to train other non-LLaMA LLMs \\ Microsoft & Phi-3 & MIT \\ Mistral AI & Mistral & Apache 2.0 \\ -Alibaba & Qwen2.5 & Custom - Free if under 100M users, cannot use outputs to train other non-Qwen LLMs \\ -Google & Gemma & Custom - Free with usage restrictions, models trained on outputs become Gemma derivatives \\ -DeepSeek & DeepSeek-V2 & Custom - Free with usage restrictions, models trained on outputs become DeepSeek derivatives \\ +Alibaba & Qwen2.5 & Custom - Free if under 100M users,\\ +& & cannot use outputs to train other non-Qwen LLMs \\ +Google & Gemma & Custom - Free with usage restrictions,\\ +& & models trained on outputs become Gemma derivatives \\ +DeepSeek & DeepSeek-V2 & Custom - Free with usage restrictions,\\ +& & models trained on outputs become DeepSeek derivatives \\ \hline \end{tabular} \end{table} diff --git a/tamingllms/markdown/toc.md b/tamingllms/markdown/toc.md index 1731c8a..c75194c 100644 --- a/tamingllms/markdown/toc.md +++ b/tamingllms/markdown/toc.md @@ -14,6 +14,8 @@ date: "2024-12-16" 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.* +--- + (*) *The pdf version is preferred as it contains corrections and side notes.* | Chapter (*) | PDF | Podcast | Website | Notebook | Status | diff --git a/tamingllms/notebooks/safety.ipynb b/tamingllms/notebooks/safety.ipynb index 2d6d4ba..0414fc6 100644 --- a/tamingllms/notebooks/safety.ipynb +++ b/tamingllms/notebooks/safety.ipynb @@ -424,7 +424,7 @@ "\n", "Building safe and reliable AI systems requires a comprehensive safety plan that addresses potential risks and establishes clear guidelines for development and deployment. This section outlines a structured approach to designing such a plan, breaking down the process into key phases from initial policy definition through implementation and monitoring as depicted in {numref}`safety-plan`.\n", "\n", - "```{figure} ../_static/safety/design.svg\n", + "```{figure} ../_static/safety/design.png\n", "---\n", "name: safety-plan\n", "alt: Safety Plan Design Phases\n",