Add Jupyter Notebook for Fine Tuning Dataset with Question Generation

- Created a new notebook `07_Fine_Tuning_Dataset.ipynb` for fine-tuning tasks.
- Implemented code to load blog posts, update metadata, and split documents.
- Integrated LangChain's ChatOpenAI for generating questions based on document context.
- Added functions for extracting questions from the generated responses.
- Included asynchronous processing for creating questions from multiple documents.
- Handled potential kernel crashes during execution.

py-src/lets_talk/utils/blog.py

@@ -12,6 +12,7 @@ from pathlib import Path
 from typing import List, Dict, Any, Optional
 from datetime import datetime
 
+from langchain_community.document_loaders.text import TextLoader
 from langchain_community.document_loaders import DirectoryLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.schema.document import Document
@@ -48,7 +49,9 @@ def load_blog_posts(data_dir: str = DATA_DIR,
         data_dir, 
         glob=glob_pattern, 
         show_progress=show_progress,
-        recursive=recursive
+        recursive=recursive,
+        loader_cls=TextLoader
+        
     )
     
     documents = text_loader.load()
@@ -85,8 +88,12 @@ def update_document_metadata(documents: List[Document],
         if len(path_parts) > 1:
             # Use the directory name as post_slug
             doc.metadata["post_slug"] = path_parts[-2]
-            doc.metadata["post_title"] = path_parts[-2].replace("-", " ").title()
-            
+            try:
+                #extract title from `doc.page_content`'s front matter like `title:`
+                doc.metadata["post_title"] = doc.page_content.split("title:")[1].split("\n")[0].strip()
+            except Exception as e:
+                doc.metadata["post_title"] = path_parts[-2].replace("-", " ").title()
+
         # Add document length as metadata
         doc.metadata["content_length"] = len(doc.page_content)
     
@@ -249,7 +256,9 @@ def load_vector_store(storage_path: str = VECTOR_STORAGE_PATH,
 def process_blog_posts(data_dir: str = DATA_DIR,
                       create_embeddings: bool = True,
                       force_recreate_embeddings: bool = False,
-                      storage_path: str = VECTOR_STORAGE_PATH):
+                      storage_path: str = VECTOR_STORAGE_PATH,
+                      split_docs: bool = True,
+                      display_stats:bool = False) -> Dict[str, Any]:
     """
     Complete pipeline to process blog posts and optionally create vector embeddings.
     
@@ -267,11 +276,17 @@ def process_blog_posts(data_dir: str = DATA_DIR,
     
     # Update metadata
     documents = update_document_metadata(documents)
+
+    if split_docs:
+        # Split documents into smaller chunks
+        documents = split_documents(documents)
     
 
     # Get and display stats
     stats = get_document_stats(documents)
-    display_document_stats(stats)
+
+    if display_stats:
+        display_document_stats(stats)
     
     result = {
         "documents": documents,
@@ -284,7 +299,8 @@ def process_blog_posts(data_dir: str = DATA_DIR,
         # Using in-memory vector store to avoid pickling issues
         vector_store = create_vector_store(
             documents, 
-            force_recreate=force_recreate_embeddings
+            force_recreate=force_recreate_embeddings,
+            storage_path=storage_path
         )
         result["vector_store"] = vector_store
     

py-src/notebooks/{05_SGD_Eval.ipynb → 05_SDG_Eval.ipynb}

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "ca8bd0e4",
    "metadata": {},
    "outputs": [
@@ -10,7 +10,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Adding project root to sys.path: /home/mafzaal/source/lets-talk/py-src\n"
+      "Adding package root to sys.path: /home/mafzaal/source/lets-talk/py-src\n",
+      "Current notebook directory: /home/mafzaal/source/lets-talk/py-src/notebooks\n",
+      "Project root: /home/mafzaal/source/lets-talk\n"
      ]
     }
    ],
@@ -20,14 +22,21 @@
     "\n",
     "# Add the project root to the Python path\n",
     "package_root = os.path.abspath(os.path.join(os.getcwd(), \"../\"))\n",
-    "print(f\"Adding project root to sys.path: {package_root}\")\n",
+    "print(f\"Adding package root to sys.path: {package_root}\")\n",
     "if package_root not in sys.path:\n",
-    "\tsys.path.append(package_root)"
+    "\tsys.path.append(package_root)\n",
+    "\n",
+    "notebook_dir = os.getcwd()\n",
+    "print(f\"Current notebook directory: {notebook_dir}\")\n",
+    "# change to the directory to the root of the project\n",
+    "project_root = os.path.abspath(os.path.join(os.getcwd(), \"../../\"))\n",
+    "print(f\"Project root: {project_root}\")\n",
+    "os.chdir(project_root)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 3,
    "id": "b48fa7d4",
    "metadata": {},
    "outputs": [],
@@ -38,7 +47,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "cd3c7329",
    "metadata": {},
    "outputs": [],
@@ -50,48 +59,47 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
-   "id": "c8c9ef46",
+   "execution_count": 5,
+   "id": "1f9f2076",
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Current notebook directory: /home/mafzaal/source/lets-talk/py-src/notebooks\n",
-      "Project root: /home/mafzaal/source/lets-talk\n"
-     ]
+     "data": {
+      "text/plain": [
+       "<module 'lets_talk.utils.blog' from '/home/mafzaal/source/lets-talk/py-src/lets_talk/utils/blog.py'>"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "# We already have project_root from the first cell, so we can use that\n",
-    "# or get the current notebook directory\n",
-    "notebook_dir = os.getcwd()\n",
-    "print(f\"Current notebook directory: {notebook_dir}\")\n",
-    "# change to the directory to the root of the project\n",
-    "project_root = os.path.abspath(os.path.join(os.getcwd(), \"../../\"))\n",
-    "print(f\"Project root: {project_root}\")\n",
-    "os.chdir(project_root)"
+    "# hot reload the module\n",
+    "import importlib\n",
+    "importlib.reload(eval)\n",
+    "importlib.reload(blog)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
-   "id": "21d9a2df",
+   "execution_count": 3,
+   "id": "cc282d9c",
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 14/14 [00:00<00:00, 41.59it/s]"
+      "100%|██████████| 14/14 [00:00<00:00, 3266.23it/s]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Loaded 14 documents from data/\n"
+      "Loaded 14 documents from data/\n",
+      "Split 14 documents into 162 chunks\n"
      ]
     },
     {
@@ -103,75 +111,67 @@
     }
    ],
    "source": [
-    "docs = blog.load_blog_posts()\n",
-    "docs = blog.update_document_metadata(docs)"
+    "#docs = blog.load_blog_posts()\n",
+    "#docs = blog.update_document_metadata(docs)\n",
+    "\n",
+    "blog_posts = blog.process_blog_posts(create_embeddings=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
-   "id": "33949cc9",
+   "execution_count": 7,
+   "id": "e768b97b",
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "Document(metadata={'source': 'data/introduction-to-ragas/index.md', 'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'post_slug': 'introduction-to-ragas', 'post_title': 'Introduction To Ragas', 'content_length': 6071}, page_content='title: \"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\" date: 2025-04-26T18:00:00-06:00 layout: blog description: \"Explore the essential evaluation framework for LLM applications with Ragas. Learn how to assess performance, ensure accuracy, and improve reliability in Retrieval-Augmented Generation systems.\" categories: [\"AI\", \"RAG\", \"Evaluation\",\"Ragas\"] coverImage: \"https://images.unsplash.com/photo-1593642634367-d91a135587b5?q=80&w=1770&auto=format&fit=crop&ixlib=rb-4.0.3\" readingTime: 7 published: true\\n\\nAs Large Language Models (LLMs) become fundamental components of modern applications, effectively evaluating their performance becomes increasingly critical. Whether you\\'re building a question-answering system, a document retrieval tool, or a conversational agent, you need reliable metrics to assess how well your application performs. This is where Ragas steps in.\\n\\nWhat is Ragas?\\n\\nRagas is an open-source evaluation framework specifically designed for LLM applications, with particular strengths in Retrieval-Augmented Generation (RAG) systems. Unlike traditional NLP evaluation methods, Ragas provides specialized metrics that address the unique challenges of LLM-powered systems.\\n\\nAt its core, Ragas helps answer crucial questions: - Is my application retrieving the right information? - Are the responses factually accurate and consistent with the retrieved context? - Does the system appropriately address the user\\'s query? - How well does my application handle multi-turn conversations?\\n\\nWhy Evaluate LLM Applications?\\n\\nLLMs are powerful but imperfect. They can hallucinate facts, misinterpret queries, or generate convincing but incorrect responses. For applications where accuracy and reliability matter—like healthcare, finance, or education—proper evaluation is non-negotiable.\\n\\nEvaluation serves several key purposes: - Quality assurance: Identify and fix issues before they reach users - Performance tracking: Monitor how changes impact system performance - Benchmarking: Compare different approaches objectively - Continuous improvement: Build feedback loops to enhance your application\\n\\nKey Features of Ragas\\n\\n🎯 Specialized Metrics\\n\\nRagas offers both LLM-based and computational metrics tailored to evaluate different aspects of LLM applications:\\n\\nFaithfulness: Measures if the response is factually consistent with the retrieved context\\n\\nContext Relevancy: Evaluates if the retrieved information is relevant to the query\\n\\nAnswer Relevancy: Assesses if the response addresses the user\\'s question\\n\\nTopic Adherence: Gauges how well multi-turn conversations stay on topic\\n\\n🧪 Test Data Generation\\n\\nCreating high-quality test data is often a bottleneck in evaluation. Ragas helps you generate comprehensive test datasets automatically, saving time and ensuring thorough coverage.\\n\\n🔗 Seamless Integrations\\n\\nRagas works with popular LLM frameworks and tools: - LangChain - LlamaIndex - Haystack - OpenAI\\n\\nObservability platforms - Phoenix - LangSmith - Langfuse\\n\\n📊 Comprehensive Analysis\\n\\nBeyond simple scores, Ragas provides detailed insights into your application\\'s strengths and weaknesses, enabling targeted improvements.\\n\\nGetting Started with Ragas\\n\\nInstalling Ragas is straightforward:\\n\\nbash uv init && uv add ragas\\n\\nHere\\'s a simple example of evaluating a response using Ragas:\\n\\n```python from ragas.metrics import Faithfulness from ragas.evaluation import EvaluationDataset from ragas.dataset_schema import SingleTurnSample from langchain_openai import ChatOpenAI from ragas.llms import LangchainLLMWrapper from langchain_openai import ChatOpenAI\\n\\nInitialize the LLM, you are going to new OPENAI API key\\n\\nevaluator_llm = LangchainLLMWrapper(ChatOpenAI(model=\"gpt-4o\"))\\n\\nYour evaluation data\\n\\ntest_data = { \"user_input\": \"What is the capital of France?\", \"retrieved_contexts\": [\"Paris is the capital and most populous city of France.\"], \"response\": \"The capital of France is Paris.\" }\\n\\nCreate a sample\\n\\nsample = SingleTurnSample(**test_data) # Unpack the dictionary into the constructor\\n\\nCreate metric\\n\\nfaithfulness = Faithfulness(llm=evaluator_llm)\\n\\nCalculate the score\\n\\nresult = await faithfulness.single_turn_ascore(sample) print(f\"Faithfulness score: {result}\") ```\\n\\n💡 Try it yourself: Explore the hands-on notebook for this workflow: 01_Introduction_to_Ragas\\n\\nWhat\\'s Coming in This Blog Series\\n\\nThis introduction is just the beginning. In the upcoming posts, we\\'ll dive deeper into all aspects of evaluating LLM applications with Ragas:\\n\\nPart 2: Basic Evaluation Workflow We\\'ll explore each metric in detail, explaining when and how to use them effectively.\\n\\nPart 3: Evaluating RAG Systems Learn specialized techniques for evaluating retrieval-augmented generation systems, including context precision, recall, and relevance.\\n\\nPart 4: Test Data Generation Discover how to create high-quality test datasets that thoroughly exercise your application\\'s capabilities.\\n\\nPart 5: Advanced Evaluation Techniques Go beyond basic metrics with custom evaluations, multi-aspect analysis, and domain-specific assessments.\\n\\nPart 6: Evaluating AI Agents Learn how to evaluate complex AI agents that engage in multi-turn interactions, use tools, and work toward specific goals.\\n\\nPart 7: Integrations and Observability Connect Ragas with your existing tools and platforms for streamlined evaluation workflows.\\n\\nPart 8: Building Feedback Loops Learn how to implement feedback loops that drive continuous improvement in your LLM applications. Transform evaluation insights into concrete improvements for your LLM applications.\\n\\nConclusion\\n\\nIn a world increasingly powered by LLMs, robust evaluation is the difference between reliable applications and unpredictable ones. Ragas provides the tools you need to confidently assess and improve your LLM applications.\\n\\nReady to Elevate Your LLM Applications?\\n\\nStart exploring Ragas today by visiting the official documentation. Share your thoughts, challenges, or success stories. If you\\'re facing specific evaluation hurdles, don\\'t hesitate to reach out—we\\'d love to help!')"
-      ]
-     },
-     "execution_count": 22,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'total_documents': 162, 'total_characters': 127917, 'min_length': 172, 'max_length': 998, 'avg_length': 789.6111111111111, 'documents': [{'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'source': 'data/introduction-to-ragas/index.md', 'title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'text_length': 6994}, {'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'source': 'data/introduction-to-ragas/index.md', 'title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'text_length': 6994}, {'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'source': 'data/introduction-to-ragas/index.md', 'title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'text_length': 6994}, {'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'source': 'data/introduction-to-ragas/index.md', 'title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'text_length': 6994}, {'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'source': 'data/introduction-to-ragas/index.md', 'title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'text_length': 6994}, {'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'source': 'data/introduction-to-ragas/index.md', 'title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'text_length': 6994}, {'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'source': 'data/introduction-to-ragas/index.md', 'title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'text_length': 6994}, {'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'source': 'data/introduction-to-ragas/index.md', 'title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'text_length': 6994}, {'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'source': 'data/introduction-to-ragas/index.md', 'title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'text_length': 6994}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/generating-test-data-with-ragas/', 'source': 'data/generating-test-data-with-ragas/index.md', 'title': '\"Part 4: Generating Test Data with Ragas\"', 'text_length': 14680}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/', 'source': 'data/advanced-metrics-and-customization-with-ragas/index.md', 'title': '\"Part 5: Advanced Metrics and Customization with Ragas\"', 'text_length': 11530}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/building-research-agent/', 'source': 'data/building-research-agent/index.md', 'title': 'Building a Research Agent with RSS Feed Support', 'text_length': 7320}, {'url': 'https://thedataguy.pro/blog/rss-feed-announcement/', 'source': 'data/rss-feed-announcement/index.md', 'title': '\"Subscribe to Our Blog via RSS\"', 'text_length': 2139}, {'url': 'https://thedataguy.pro/blog/rss-feed-announcement/', 'source': 'data/rss-feed-announcement/index.md', 'title': '\"Subscribe to Our Blog via RSS\"', 'text_length': 2139}, {'url': 'https://thedataguy.pro/blog/rss-feed-announcement/', 'source': 'data/rss-feed-announcement/index.md', 'title': '\"Subscribe to Our Blog via RSS\"', 'text_length': 2139}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/metric-driven-development/', 'source': 'data/metric-driven-development/index.md', 'title': '\"Metric-Driven Development: Make Smarter Decisions, Faster\"', 'text_length': 12450}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/', 'source': 'data/basic-evaluation-workflow-with-ragas/index.md', 'title': '\"Part 2: Basic Evaluation Workflow with Ragas\"', 'text_length': 11222}, {'url': 'https://thedataguy.pro/blog/langchain-experience-csharp-perspective/', 'source': 'data/langchain-experience-csharp-perspective/index.md', 'title': \"A C# Programmer's Perspective on LangChain Expression Language\", 'text_length': 3361}, {'url': 'https://thedataguy.pro/blog/langchain-experience-csharp-perspective/', 'source': 'data/langchain-experience-csharp-perspective/index.md', 'title': \"A C# Programmer's Perspective on LangChain Expression Language\", 'text_length': 3361}, {'url': 'https://thedataguy.pro/blog/langchain-experience-csharp-perspective/', 'source': 'data/langchain-experience-csharp-perspective/index.md', 'title': \"A C# Programmer's Perspective on LangChain Expression Language\", 'text_length': 3361}, {'url': 'https://thedataguy.pro/blog/langchain-experience-csharp-perspective/', 'source': 'data/langchain-experience-csharp-perspective/index.md', 'title': \"A C# Programmer's Perspective on LangChain Expression Language\", 'text_length': 3361}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/', 'source': 'data/evaluating-ai-agents-with-ragas/index.md', 'title': '\"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\"', 'text_length': 9821}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/integrations-and-observability-with-ragas/', 'source': 'data/integrations-and-observability-with-ragas/index.md', 'title': '\"Part 7: Integrations and Observability with Ragas\"', 'text_length': 9098}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/building-feedback-loops-with-ragas/', 'source': 'data/building-feedback-loops-with-ragas/index.md', 'title': '\"Part 8: Building Feedback Loops with Ragas\"', 'text_length': 8160}, {'url': 'https://thedataguy.pro/blog/coming-back-to-ai-roots/', 'source': 'data/coming-back-to-ai-roots/index.md', 'title': 'Coming Back to AI Roots - My Professional Journey', 'text_length': 5827}, {'url': 'https://thedataguy.pro/blog/coming-back-to-ai-roots/', 'source': 'data/coming-back-to-ai-roots/index.md', 'title': 'Coming Back to AI Roots - My Professional Journey', 'text_length': 5827}, {'url': 'https://thedataguy.pro/blog/coming-back-to-ai-roots/', 'source': 'data/coming-back-to-ai-roots/index.md', 'title': 'Coming Back to AI Roots - My Professional Journey', 'text_length': 5827}, {'url': 'https://thedataguy.pro/blog/coming-back-to-ai-roots/', 'source': 'data/coming-back-to-ai-roots/index.md', 'title': 'Coming Back to AI Roots - My Professional Journey', 'text_length': 5827}, {'url': 'https://thedataguy.pro/blog/coming-back-to-ai-roots/', 'source': 'data/coming-back-to-ai-roots/index.md', 'title': 'Coming Back to AI Roots - My Professional Journey', 'text_length': 5827}, {'url': 'https://thedataguy.pro/blog/coming-back-to-ai-roots/', 'source': 'data/coming-back-to-ai-roots/index.md', 'title': 'Coming Back to AI Roots - My Professional Journey', 'text_length': 5827}, {'url': 'https://thedataguy.pro/blog/coming-back-to-ai-roots/', 'source': 'data/coming-back-to-ai-roots/index.md', 'title': 'Coming Back to AI Roots - My Professional Journey', 'text_length': 5827}, {'url': 'https://thedataguy.pro/blog/coming-back-to-ai-roots/', 'source': 'data/coming-back-to-ai-roots/index.md', 'title': 'Coming Back to AI Roots - My Professional Journey', 'text_length': 5827}, {'url': 'https://thedataguy.pro/blog/data-is-king/', 'source': 'data/data-is-king/index.md', 'title': '\"Data is King: Why Your Data Strategy IS Your Business Strategy\"', 'text_length': 6197}, {'url': 'https://thedataguy.pro/blog/data-is-king/', 'source': 'data/data-is-king/index.md', 'title': '\"Data is King: Why Your Data Strategy IS Your Business Strategy\"', 'text_length': 6197}, {'url': 'https://thedataguy.pro/blog/data-is-king/', 'source': 'data/data-is-king/index.md', 'title': '\"Data is King: Why Your Data Strategy IS Your Business Strategy\"', 'text_length': 6197}, {'url': 'https://thedataguy.pro/blog/data-is-king/', 'source': 'data/data-is-king/index.md', 'title': '\"Data is King: Why Your Data Strategy IS Your Business Strategy\"', 'text_length': 6197}, {'url': 'https://thedataguy.pro/blog/data-is-king/', 'source': 'data/data-is-king/index.md', 'title': '\"Data is King: Why Your Data Strategy IS Your Business Strategy\"', 'text_length': 6197}, {'url': 'https://thedataguy.pro/blog/data-is-king/', 'source': 'data/data-is-king/index.md', 'title': '\"Data is King: Why Your Data Strategy IS Your Business Strategy\"', 'text_length': 6197}, {'url': 'https://thedataguy.pro/blog/data-is-king/', 'source': 'data/data-is-king/index.md', 'title': '\"Data is King: Why Your Data Strategy IS Your Business Strategy\"', 'text_length': 6197}, {'url': 'https://thedataguy.pro/blog/data-is-king/', 'source': 'data/data-is-king/index.md', 'title': '\"Data is King: Why Your Data Strategy IS Your Business Strategy\"', 'text_length': 6197}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}, {'url': 'https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/', 'source': 'data/evaluating-rag-systems-with-ragas/index.md', 'title': '\"Part 3: Evaluating RAG Systems with Ragas\"', 'text_length': 8811}]}\n"
+     ]
     }
    ],
    "source": [
-    "docs[0]"
+    "print(blog_posts[\"stats\"])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
-   "id": "83f7166c",
+   "execution_count": 4,
+   "id": "21d9a2df",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs =  blog_posts[\"documents\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "33949cc9",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<module 'lets_talk.utils.eval' from '/home/mafzaal/source/lets-talk/py-src/lets_talk/utils/eval.py'>"
+       "Document(metadata={'source': 'data/introduction-to-ragas/index.md', 'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'post_slug': 'introduction-to-ragas', 'post_title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'content_length': 6994}, page_content='---\\ntitle: \"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"\\ndate: 2025-04-26T18:00:00-06:00\\nlayout: blog\\ndescription: \"Explore the essential evaluation framework for LLM applications with Ragas. Learn how to assess performance, ensure accuracy, and improve reliability in Retrieval-Augmented Generation systems.\"\\ncategories: [\"AI\", \"RAG\", \"Evaluation\",\"Ragas\"]\\ncoverImage: \"https://images.unsplash.com/photo-1593642634367-d91a135587b5?q=80&w=1770&auto=format&fit=crop&ixlib=rb-4.0.3\"\\nreadingTime: 7\\npublished: true\\n---\\n\\nAs Large Language Models (LLMs) become fundamental components of modern applications, effectively evaluating their performance becomes increasingly critical. Whether you\\'re building a question-answering system, a document retrieval tool, or a conversational agent, you need reliable metrics to assess how well your application performs. This is where Ragas steps in.\\n\\n## What is Ragas?')"
       ]
      },
-     "execution_count": 44,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# hot reload the module\n",
-    "import importlib\n",
-    "importlib.reload(eval)"
+    "docs[0]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": null,
    "id": "03663a91",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Applying HeadlineSplitter:   0%|          | 0/14 [00:00<?, ?it/s]           unable to apply transformation: 'headlines' property not found in this node\n",
-      "Applying SummaryExtractor:  20%|██        | 3/15 [00:02<00:09,  1.20it/s]Property 'summary' already exists in node 'ed7c49'. Skipping!\n",
-      "Applying SummaryExtractor:  33%|███▎      | 5/15 [00:06<00:15,  1.58s/it]Property 'summary' already exists in node 'f14d00'. Skipping!\n",
-      "Applying [EmbeddingExtractor, ThemesExtractor, NERExtractor]:   0%|          | 0/71 [00:00<?, ?it/s]Property 'summary_embedding' already exists in node 'ed7c49'. Skipping!\n",
-      "Property 'summary_embedding' already exists in node 'f14d00'. Skipping!\n",
-      "Generating personas: 100%|██████████| 3/3 [00:00<00:00,  3.11it/s]                                           \n",
-      "Generating Scenarios: 100%|██████████| 3/3 [00:13<00:00,  4.46s/it]\n",
-      "Generating Samples: 100%|██████████| 12/12 [00:53<00:00,  4.50s/it]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from lets_talk.config import EMBEDDING_MODEL,SDG_LLM_MODLEL,EVAL_LLM_MODEL\n",
     "testset = eval.generate_testset(docs=docs,llm_model = SDG_LLM_MODLEL, embedding_model = EMBEDDING_MODEL,testset_size=10)"
@@ -490,12 +490,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": null,
    "id": "4ae903d8",
    "metadata": {},
    "outputs": [],
    "source": [
-    "df.to_csv(\"evals/testset.csv\",index=False)"
+    "df.to_csv(\"evals/testset_2.csv\",index=False)"
    ]
   },
   {
@@ -918,12 +918,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": null,
    "id": "f5d50d7b",
    "metadata": {},
    "outputs": [],
    "source": [
-    "eval_df.to_csv(\"evals/rag_eval.csv\",index=False)"
+    "eval_df.to_csv(\"evals/rag_eval_2.csv\",index=False)"
    ]
   },
   {
@@ -1003,12 +1003,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": null,
    "id": "49fa29f2",
    "metadata": {},
    "outputs": [],
    "source": [
-    "result.to_pandas().to_csv(\"evals/rag_eval_result.csv\",index=False)"
+    "result.to_pandas().to_csv(\"evals/rag_eval_result_2.csv\",index=False)"
    ]
   }
  ],

py-src/notebooks/07_Fine_Tuning_Dataset.ipynb

@@ -0,0 +1,298 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c95ab233",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Adding package root to sys.path: /home/mafzaal/source/lets-talk/py-src\n",
+      "Current notebook directory: /home/mafzaal/source/lets-talk/py-src/notebooks\n",
+      "Project root: /home/mafzaal/source/lets-talk\n"
+     ]
+    }
+   ],
+   "source": [
+    "import sys\n",
+    "import os\n",
+    "\n",
+    "# Add the project root to the Python path\n",
+    "package_root = os.path.abspath(os.path.join(os.getcwd(), \"../\"))\n",
+    "print(f\"Adding package root to sys.path: {package_root}\")\n",
+    "if package_root not in sys.path:\n",
+    "\tsys.path.append(package_root)\n",
+    "\n",
+    "\n",
+    "notebook_dir = os.getcwd()\n",
+    "print(f\"Current notebook directory: {notebook_dir}\")\n",
+    "# change to the directory to the root of the project\n",
+    "project_root = os.path.abspath(os.path.join(os.getcwd(), \"../../\"))\n",
+    "print(f\"Project root: {project_root}\")\n",
+    "os.chdir(project_root)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "15e97530",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b4f2ddc0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import lets_talk.utils.blog as blog\n",
+    "import lets_talk.utils.eval as eval"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "123779af",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 14/14 [00:00<00:00, 16100.98it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Loaded 14 documents from data/\n",
+      "Split 14 documents into 162 chunks\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "docs = blog.load_blog_posts()\n",
+    "docs = blog.update_document_metadata(docs)\n",
+    "split_docs = blog.split_documents(docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b0f749db",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "qa_chat_model = ChatOpenAI(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    temperature=0,\n",
+    ")\n",
+    "\n",
+    "qa_prompt = \"\"\"\\\n",
+    "Given the following context, you must generate questions based on only the provided context.\n",
+    "You are to generate {n_questions} questions which should be provided in the following format:\n",
+    "\n",
+    "1. QUESTION #1\n",
+    "2. QUESTION #2\n",
+    "...\n",
+    "\n",
+    "Context:\n",
+    "{context}\n",
+    "\"\"\"\n",
+    "\n",
+    "qa_prompt_template = ChatPromptTemplate.from_template(qa_prompt)\n",
+    "question_generation_chain = qa_prompt_template | qa_chat_model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "adb3ae7b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "context = split_docs[0].page_content\n",
+    "n_questions = 3\n",
+    "response = question_generation_chain.invoke({\"context\": context, \"n_questions\": n_questions})\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "6df35cfd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'1. What is the primary purpose of the Ragas evaluation framework in LLM applications?  \\n2. Why is it important to have reliable metrics when assessing the performance of LLM-based systems?  \\n3. In what types of applications can Ragas be used to evaluate performance?'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "response.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dcd0bf6d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Extracted questions:\n",
+      "1 -  What is the primary purpose of the Ragas evaluation framework in LLM applications?\n",
+      "2 -  Why is it important to have reliable metrics when assessing the performance of LLM-based systems?\n",
+      "3 -  In what types of applications can Ragas be used to evaluate performance?\n"
+     ]
+    }
+   ],
+   "source": [
+    "questions = extract_questions(response.content)\n",
+    "print(\"Extracted questions:\")\n",
+    "for i, question in enumerate(questions):\n",
+    "    print(f\"{i + 1}.  {question}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "e78f93b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tqdm\n",
+    "import asyncio\n",
+    "\n",
+    "\n",
+    "def extract_questions(response_text):\n",
+    "    # Split the response text into lines\n",
+    "    lines = response_text.strip().split('\\n')\n",
+    "\n",
+    "    # Extract questions (format: \"1. QUESTION\")\n",
+    "    extracted_questions = []\n",
+    "    for line in lines:\n",
+    "        line = line.strip()\n",
+    "        if line and any(line.startswith(f\"{i}.\") for i in range(1, n_questions+1)):\n",
+    "            # Remove the number prefix and get just the question\n",
+    "            question = line.split('.', 1)[1].strip()\n",
+    "            extracted_questions.append(question)\n",
+    "\n",
+    "    return extracted_questions\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "async def create_questions(documents, n_questions):\n",
+    "    question_set = []\n",
+    "    \n",
+    "\n",
+    "    for doc in tqdm.tqdm(documents):\n",
+    "        \n",
+    "        context = doc.page_content\n",
+    "\n",
+    "        # Generate questions using the question generation chain\n",
+    "        response = await question_generation_chain.ainvoke({\n",
+    "            \"context\": context,\n",
+    "            \"n_questions\": n_questions\n",
+    "        })\n",
+    "\n",
+    "        questions = extract_questions(response.content)\n",
+    "        \n",
+    "        for i, question in enumerate(questions):\n",
+    "            questions.append({\"question\":question, \"context\": context})\n",
+    "        \n",
+    "\n",
+    "       \n",
+    "\n",
+    "    return question_set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1ece53b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ds = await create_questions(split_docs[:2], 3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aa92dd7d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|          | 0/2 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
+      "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
+      "\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
+      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
+     ]
+    }
+   ],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

py-src/notebooks/update_blog_data.ipynb

@@ -12,25 +12,57 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "6ec048b4",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Adding package root to sys.path: /home/mafzaal/source/lets-talk/py-src\n"
+     ]
+    }
+   ],
    "source": [
     "import sys\n",
     "import os\n",
     "from pathlib import Path\n",
     "from dotenv import load_dotenv\n",
-    "import importlib.util\n",
+    "\n",
     "\n",
     "import sys\n",
     "import os\n",
     "\n",
     "# Add the project root to the Python path\n",
-    "project_root = os.path.abspath(os.path.join(os.getcwd(), \"../\"))\n",
-    "print(f\"Adding project root to sys.path: {project_root}\")\n",
-    "if project_root not in sys.path:\n",
-    "\tsys.path.append(project_root)\n"
+    "package_root = os.path.abspath(os.path.join(os.getcwd(), \"../\"))\n",
+    "print(f\"Adding package root to sys.path: {package_root}\")\n",
+    "if package_root not in sys.path:\n",
+    "\tsys.path.append(package_root)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7a7a9f3f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Current notebook directory: /home/mafzaal/source/lets-talk/py-src/notebooks\n",
+      "Project root: /home/mafzaal/source/lets-talk\n"
+     ]
+    }
+   ],
+   "source": [
+    "notebook_dir = os.getcwd()\n",
+    "print(f\"Current notebook directory: {notebook_dir}\")\n",
+    "# change to the directory to the root of the project\n",
+    "project_root = os.path.abspath(os.path.join(os.getcwd(), \"../../\"))\n",
+    "print(f\"Project root: {project_root}\")\n",
+    "os.chdir(project_root)"
    ]
   },
   {
@@ -56,7 +88,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 14/14 [00:00<00:00, 42.05it/s]"
+      "100%|██████████| 14/14 [00:00<00:00, 4617.46it/s]"
      ]
     },
     {
@@ -76,11 +108,8 @@
    ],
    "source": [
     "import lets_talk.utils.blog as  blog_utils\n",
-    "\n",
     "docs = blog_utils.load_blog_posts()\n",
-    "docs = blog_utils.update_document_metadata(docs)\n",
-    "\n",
-    "\n"
+    "docs = blog_utils.update_document_metadata(docs)\n"
    ]
   },
   {
@@ -88,11 +117,29 @@
    "execution_count": null,
    "id": "a14c70dc",
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Split 14 documents into 162 chunks\n"
+     ]
+    }
+   ],
+   "source": [
+    "split_docs = blog_utils.split_documents(docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "1c40c587",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(metadata={'source': 'data/introduction-to-ragas/index.md', 'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'post_slug': 'introduction-to-ragas', 'post_title': 'Introduction To Ragas', 'content_length': 6071}, page_content='title: \"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\" date: 2025-04-26T18:00:00-06:00 layout: blog description: \"Explore the essential evaluation framework for LLM applications with Ragas. Learn how to assess performance, ensure accuracy, and improve reliability in Retrieval-Augmented Generation systems.\" categories: [\"AI\", \"RAG\", \"Evaluation\",\"Ragas\"] coverImage: \"https://images.unsplash.com/photo-1593642634367-d91a135587b5?q=80&w=1770&auto=format&fit=crop&ixlib=rb-4.0.3\" readingTime: 7 published: true\\n\\nAs Large Language Models (LLMs) become fundamental components of modern applications, effectively evaluating their performance becomes increasingly critical. Whether you\\'re building a question-answering system, a document retrieval tool, or a conversational agent, you need reliable metrics to assess how well your application performs. This is where Ragas steps in.\\n\\nWhat is Ragas?\\n\\nRagas is an open-source evaluation framework specifically designed for LLM applications, with particular strengths in Retrieval-Augmented Generation (RAG) systems. Unlike traditional NLP evaluation methods, Ragas provides specialized metrics that address the unique challenges of LLM-powered systems.\\n\\nAt its core, Ragas helps answer crucial questions: - Is my application retrieving the right information? - Are the responses factually accurate and consistent with the retrieved context? - Does the system appropriately address the user\\'s query? - How well does my application handle multi-turn conversations?\\n\\nWhy Evaluate LLM Applications?\\n\\nLLMs are powerful but imperfect. They can hallucinate facts, misinterpret queries, or generate convincing but incorrect responses. For applications where accuracy and reliability matter—like healthcare, finance, or education—proper evaluation is non-negotiable.\\n\\nEvaluation serves several key purposes: - Quality assurance: Identify and fix issues before they reach users - Performance tracking: Monitor how changes impact system performance - Benchmarking: Compare different approaches objectively - Continuous improvement: Build feedback loops to enhance your application\\n\\nKey Features of Ragas\\n\\n🎯 Specialized Metrics\\n\\nRagas offers both LLM-based and computational metrics tailored to evaluate different aspects of LLM applications:\\n\\nFaithfulness: Measures if the response is factually consistent with the retrieved context\\n\\nContext Relevancy: Evaluates if the retrieved information is relevant to the query\\n\\nAnswer Relevancy: Assesses if the response addresses the user\\'s question\\n\\nTopic Adherence: Gauges how well multi-turn conversations stay on topic\\n\\n🧪 Test Data Generation\\n\\nCreating high-quality test data is often a bottleneck in evaluation. Ragas helps you generate comprehensive test datasets automatically, saving time and ensuring thorough coverage.\\n\\n🔗 Seamless Integrations\\n\\nRagas works with popular LLM frameworks and tools: - LangChain - LlamaIndex - Haystack - OpenAI\\n\\nObservability platforms - Phoenix - LangSmith - Langfuse\\n\\n📊 Comprehensive Analysis\\n\\nBeyond simple scores, Ragas provides detailed insights into your application\\'s strengths and weaknesses, enabling targeted improvements.\\n\\nGetting Started with Ragas\\n\\nInstalling Ragas is straightforward:\\n\\nbash uv init && uv add ragas\\n\\nHere\\'s a simple example of evaluating a response using Ragas:\\n\\n```python from ragas.metrics import Faithfulness from ragas.evaluation import EvaluationDataset from ragas.dataset_schema import SingleTurnSample from langchain_openai import ChatOpenAI from ragas.llms import LangchainLLMWrapper from langchain_openai import ChatOpenAI\\n\\nInitialize the LLM, you are going to new OPENAI API key\\n\\nevaluator_llm = LangchainLLMWrapper(ChatOpenAI(model=\"gpt-4o\"))\\n\\nYour evaluation data\\n\\ntest_data = { \"user_input\": \"What is the capital of France?\", \"retrieved_contexts\": [\"Paris is the capital and most populous city of France.\"], \"response\": \"The capital of France is Paris.\" }\\n\\nCreate a sample\\n\\nsample = SingleTurnSample(**test_data) # Unpack the dictionary into the constructor\\n\\nCreate metric\\n\\nfaithfulness = Faithfulness(llm=evaluator_llm)\\n\\nCalculate the score\\n\\nresult = await faithfulness.single_turn_ascore(sample) print(f\"Faithfulness score: {result}\") ```\\n\\n💡 Try it yourself: Explore the hands-on notebook for this workflow: 01_Introduction_to_Ragas\\n\\nWhat\\'s Coming in This Blog Series\\n\\nThis introduction is just the beginning. In the upcoming posts, we\\'ll dive deeper into all aspects of evaluating LLM applications with Ragas:\\n\\nPart 2: Basic Evaluation Workflow We\\'ll explore each metric in detail, explaining when and how to use them effectively.\\n\\nPart 3: Evaluating RAG Systems Learn specialized techniques for evaluating retrieval-augmented generation systems, including context precision, recall, and relevance.\\n\\nPart 4: Test Data Generation Discover how to create high-quality test datasets that thoroughly exercise your application\\'s capabilities.\\n\\nPart 5: Advanced Evaluation Techniques Go beyond basic metrics with custom evaluations, multi-aspect analysis, and domain-specific assessments.\\n\\nPart 6: Evaluating AI Agents Learn how to evaluate complex AI agents that engage in multi-turn interactions, use tools, and work toward specific goals.\\n\\nPart 7: Integrations and Observability Connect Ragas with your existing tools and platforms for streamlined evaluation workflows.\\n\\nPart 8: Building Feedback Loops Learn how to implement feedback loops that drive continuous improvement in your LLM applications. Transform evaluation insights into concrete improvements for your LLM applications.\\n\\nConclusion\\n\\nIn a world increasingly powered by LLMs, robust evaluation is the difference between reliable applications and unpredictable ones. Ragas provides the tools you need to confidently assess and improve your LLM applications.\\n\\nReady to Elevate Your LLM Applications?\\n\\nStart exploring Ragas today by visiting the official documentation. Share your thoughts, challenges, or success stories. If you\\'re facing specific evaluation hurdles, don\\'t hesitate to reach out—we\\'d love to help!')"
+       "Document(metadata={'source': 'data/introduction-to-ragas/index.md', 'url': 'https://thedataguy.pro/blog/introduction-to-ragas/', 'post_slug': 'introduction-to-ragas', 'post_title': '\"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"', 'content_length': 6994}, page_content='---\\ntitle: \"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\"\\ndate: 2025-04-26T18:00:00-06:00\\nlayout: blog\\ndescription: \"Explore the essential evaluation framework for LLM applications with Ragas. Learn how to assess performance, ensure accuracy, and improve reliability in Retrieval-Augmented Generation systems.\"\\ncategories: [\"AI\", \"RAG\", \"Evaluation\",\"Ragas\"]\\ncoverImage: \"https://images.unsplash.com/photo-1593642634367-d91a135587b5?q=80&w=1770&auto=format&fit=crop&ixlib=rb-4.0.3\"\\nreadingTime: 7\\npublished: true\\n---\\n\\nAs Large Language Models (LLMs) become fundamental components of modern applications, effectively evaluating their performance becomes increasingly critical. Whether you\\'re building a question-answering system, a document retrieval tool, or a conversational agent, you need reliable metrics to assess how well your application performs. This is where Ragas steps in.\\n\\n## What is Ragas?')"
       ]
      },
      "execution_count": 8,
@@ -101,17 +148,17 @@
     }
    ],
    "source": [
-    "docs[0]\n"
+    "split_docs[0]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "id": "72dd14b5",
    "metadata": {},
    "outputs": [],
    "source": [
-    "vector_store = blog_utils = blog_utils.create_vector_store(docs,'./db/vector_store_4')"
+    "vector_store = blog_utils = blog_utils.create_vector_store(split_docs,'./db/vector_store_5')"
    ]
   },
   {
@@ -126,7 +173,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 11,
    "id": "8b552e6b",
    "metadata": {},
    "outputs": [
@@ -137,27 +184,27 @@
       "\n",
       "Query: What is RAGAS?\n",
       "Retrieved 3 documents:\n",
-      "1. Introduction To Ragas (https://thedataguy.pro/blog/introduction-to-ragas/)\n",
-      "2. Evaluating Rag Systems With Ragas (https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/)\n",
-      "3. Advanced Metrics And Customization With Ragas (https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/)\n",
+      "1. \"Part 3: Evaluating RAG Systems with Ragas\" (https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/)\n",
+      "2. \"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\" (https://thedataguy.pro/blog/introduction-to-ragas/)\n",
+      "3. \"Part 4: Generating Test Data with Ragas\" (https://thedataguy.pro/blog/generating-test-data-with-ragas/)\n",
       "\n",
       "Query: How to build research agents?\n",
       "Retrieved 3 documents:\n",
-      "1. Building Research Agent (https://thedataguy.pro/blog/building-research-agent/)\n",
-      "2. Advanced Metrics And Customization With Ragas (https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/)\n",
-      "3. Evaluating Rag Systems With Ragas (https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/)\n",
+      "1. Building a Research Agent with RSS Feed Support (https://thedataguy.pro/blog/building-research-agent/)\n",
+      "2. \"Part 1: Introduction to Ragas: The Essential Evaluation Framework for LLM Applications\" (https://thedataguy.pro/blog/introduction-to-ragas/)\n",
+      "3. Building a Research Agent with RSS Feed Support (https://thedataguy.pro/blog/building-research-agent/)\n",
       "\n",
       "Query: What is metric driven development?\n",
       "Retrieved 3 documents:\n",
-      "1. Metric Driven Development (https://thedataguy.pro/blog/metric-driven-development/)\n",
-      "2. Advanced Metrics And Customization With Ragas (https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/)\n",
-      "3. Coming Back To Ai Roots (https://thedataguy.pro/blog/coming-back-to-ai-roots/)\n",
+      "1. \"Metric-Driven Development: Make Smarter Decisions, Faster\" (https://thedataguy.pro/blog/metric-driven-development/)\n",
+      "2. \"Metric-Driven Development: Make Smarter Decisions, Faster\" (https://thedataguy.pro/blog/metric-driven-development/)\n",
+      "3. \"Part 5: Advanced Metrics and Customization with Ragas\" (https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/)\n",
       "\n",
       "Query: Who is TheDataGuy?\n",
       "Retrieved 3 documents:\n",
-      "1. Advanced Metrics And Customization With Ragas (https://thedataguy.pro/blog/advanced-metrics-and-customization-with-ragas/)\n",
-      "2. Langchain Experience Csharp Perspective (https://thedataguy.pro/blog/langchain-experience-csharp-perspective/)\n",
-      "3. Evaluating Rag Systems With Ragas (https://thedataguy.pro/blog/evaluating-rag-systems-with-ragas/)\n"
+      "1. \"Part 2: Basic Evaluation Workflow with Ragas\" (https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/)\n",
+      "2. \"Part 2: Basic Evaluation Workflow with Ragas\" (https://thedataguy.pro/blog/basic-evaluation-workflow-with-ragas/)\n",
+      "3. \"Part 6: Evaluating AI Agents: Beyond Simple Answers with Ragas\" (https://thedataguy.pro/blog/evaluating-ai-agents-with-ragas/)\n"
      ]
     }
    ],
@@ -185,7 +232,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 12,
    "id": "4cdd6899",
    "metadata": {},
    "outputs": [],

scripts/build-vector-db.sh

@@ -1,6 +0,0 @@
-#!/bin/bash
-
-
-uv run python ./utils/pipeline.py
-    
-