add corrections to input and output chapters

TESTIMONIALS.md

@@ -3,3 +3,6 @@
 
 > This is amazing content, thank you so much for sharing!!! 
 -- Didier Lopes, Founder of OpenBB
+
+> Easily one of the best resources on structured generation so far. Great resource for the AI engineer in your life!
+-- Cameron, Outlines, .txt

tamingllms/_build/html/_sources/markdown/toc.md

@@ -4,8 +4,6 @@ author: "Tharsis T. P. Souza"
 date: "2024-12-16"
 ---
 
-Sign-up to receive updates on [new Chapters here](https://tamingllm.substack.com/).
-
  <a href="https://www.tamingllms.com" target="_blank">
   <img src="../_static/cover_curve.png" style="background-color:white; width:50%;" alt="Taming LLMs Cover" />
  </a>
@@ -16,27 +14,22 @@ Sign-up to receive updates on [new Chapters here](https://tamingllm.substack.com
 
 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.*
 
-## [Preface](https://www.tamingllms.com/markdown/preface.html)
-
-## [About the Book](https://www.tamingllms.com/markdown/intro.html)
-
-## [Chapter 1: The Evals Gap](https://www.tamingllms.com/notebooks/evals.html)
-
-## [Chapter 2: Structured Output](https://www.tamingllms.com/notebooks/structured_output.html)
-
-## [Chapter 3: Managing Input Data](https://www.tamingllms.com/notebooks/input.html)
-
-## [Chapter 4: Safety](https://www.tamingllms.com/notebooks/safety.html)
-
-## [Chapter 5: Preference-Based Alignment](https://www.tamingllms.com/notebooks/alignment.html)
-
-## [Chapter 6: Local LLMs in Practice](https://www.tamingllms.com/notebooks/local.html)
-
-## Chapter 7: The Falling Cost Paradox
-
-## Chapter 8: Frontiers
+(*) *The pdf version is preferred as it contains corrections and side notes.*
+
+| Chapter (*)                                   | PDF          | Podcast      | Website      | Notebook      | Status               |
+|:-------------------------------------------|--------------|--------------|--------------|---------------|----------------------|
+| **Preface**                   | | | [html](https://www.tamingllms.com/markdown/preface.html) | N/A           | *Ready for Review*                   |
+| **About the Book**                  | | | [html](https://www.tamingllms.com/markdown/intro.html) | N/A           | *Ready for Review*                   |
+| **Chapter 1: The Evals Gap**                | [pdf](https://www.dropbox.com/scl/fi/voyhpqp0glkhijopyev71/DRAFT_Chapter-1-The-Evals-Gap.pdf?rlkey=ehzf6g4ngsssuoe471on8itu4&st=zqv98w2n&dl=0)  | [podcast](https://tamingllm.substack.com/p/chapter-1-podcast-the-evals-gap) | [html](https://www.tamingllms.com/notebooks/evals.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/evals.ipynb) | *Ready for Review*     |
+| **Chapter 2: Structured Output**| [pdf](https://www.dropbox.com/scl/fi/x3a84bm1ewcfemj4p7b5p/DRAFT_Chapter-2-Structured-Output.pdf?rlkey=zysw6mat7har133rs7am7bb8n&st=4ns4ak24&dl=0) | [podcast](https://tamingllm.substack.com/p/chapter-2-podcast-structured-output) | [html](https://www.tamingllms.com/notebooks/structured_output.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/structured_output.ipynb) |  *Ready for Review*  |
+| **Chapter 3: Managing Input Data** | | | [html](https://www.tamingllms.com/notebooks/input.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/input.ipynb) |     |
+| **Chapter 4: Safety**              | | | [html](https://www.tamingllms.com/notebooks/safety.html)  |  [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/safety.ipynb) |     |
+| **Chapter 5: Preference-Based Alignment**     | | | [html](https://www.tamingllms.com/notebooks/alignment.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/alignment.ipynb) |     |
+| **Chapter 6: Local LLMs in Practice** | | | [html](https://www.tamingllms.com/notebooks/local.html) | [ipynb](https://github.com/souzatharsis/tamingLLMs/blob/master/tamingllms/notebooks/local.ipynb) |    |
+| **Chapter 7: The Falling Cost Paradox**               | | |              |               |        WIP              |
+| **Chapter 8: Frontiers**                | | |              |               |                 |
+| **Appendix A: Tools and Resources**           | | |              |               |                      |
 
-## Appendix A: Tools and Resources
 
 
 [![CC BY-NC-SA 4.0][cc-by-nc-sa-image]][cc-by-nc-sa]

tamingllms/_build/html/_sources/notebooks/input.ipynb

@@ -1703,7 +1703,7 @@
     "\n",
     "Data extraction, parsing and chunking are also part of a canonical pipeline as we prepare the knowledge base. Those are concepts we explored in detail in Sections {ref}`parsing` and {ref}`chunking`, hence we will be succinct here. We will start by preparing the knowledge base.\n",
     "\n",
-    "```{figure} ../_static/input/rag.svg\n",
+    "```{figure} ../_static/input/rag.png\n",
     "---\n",
     "name: rag_pipeline\n",
     "alt: RAG Pipeline\n",
@@ -1872,24 +1872,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[['intro', 'input', 'structured_output']]\n"
+     ]
+    }
+   ],
    "source": [
     "q = \"What is the purpose of this book?\"\n",
     "res = query_collection(collection, q)\n",
     "res.get(\"ids\")"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print([['intro', 'input', 'structured_output']])"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -1920,7 +1919,7 @@
     "\n",
     "Behind the scenes, ChromaDB is using the model `all-MiniLM-L6-v2` by default [^chroma_embeddings] to create embeddings for the input documents and the query (see {numref}`embedding`). This model is available in `sentence_transformers` {cite}`sentencetransformers2024website`. Let's see how it works.\n",
     "\n",
-    "```{figure} ../_static/input/embedding.svg\n",
+    "```{figure} ../_static/input/embedding.png\n",
     "---\n",
     "name: embedding\n",
     "alt: Embedding\n",
@@ -2860,7 +2859,7 @@
    "outputs": [],
    "source": [
     "# Save the generated report to a local file\n",
-    "with open('data/apple_report.txt', 'w') as file:\n",
+    "with open('data/apple_report.md', 'w') as file:\n",
     "    file.write(report)\n"
    ]
   },
@@ -2926,7 +2925,7 @@
    ],
    "source": [
     "# Read and display the generated report\n",
-    "with open('../data/apple_report.txt', 'r') as file:\n",
+    "with open('../data/apple_report.md', 'r') as file:\n",
     "    report_content = file.read()\n",
     "    \n",
     "from IPython.display import Markdown\n",
@@ -2985,7 +2984,9 @@
    "source": [
     "### Case Study II: Quiz Generation with Citations\n",
     "\n",
-    "In this case study, we will build a Quiz generator with citations that explores additional input management techniques particularly useful with long context windows. The implementation includes prompt caching for efficiency and citation tracking to enhance accuracy and verifiability. We will use Gemini 1.5 Pro as our LLM model, which has a context window of 2M tokens.\n",
+    "This case study is motivated by the rise of long-context models (LCs). Readers are encouraged to consider leveraging long-context windows if suitable to application requirements instead of defaulting to a RAGs-based approach given the reasons we have discussed in previous sections where we go over RAGs limitations and trade-offs in relation with LCs.\n",
+    "\n",
+    "In this case study, we will build a Quiz generator with citations that explores additional input management techniques particularly useful with long context windows. The implementation includes prompt caching for efficiency and citation tracking to enhance accuracy and verifiability. We will use Gemini 1.5 Pro (experimental) as our LLM, which has a context window of 2M tokens.\n",
     "\n",
     "#### Use Case\n",
     "\n",