Update RAG notebook with latest improvements

- Enhanced API key configuration with environment variable fallback
- Improved error handling and resource management
- Added comprehensive setup instructions and prerequisites
- Included detailed Milvus installation guide with Docker commands
- Enhanced modular architecture with better separation of concerns
- Added support for both sample documents and PDF processing workflows
- Improved logging and debugging capabilities
- Added interactive session functions with better user experience
- Enhanced documentation with step-by-step explanations
- Optimized vector search and embedding generation processes

Author: behroozazarkhalili

bootcamp/RAG/RAG_Milvus_LangChain_Anthropic.ipynb

@@ -511,10 +511,14 @@
     "        # Format results\n",
     "        formatted_results = []\n",
     "        for hit in results[0]:\n",
+    "            # For COSINE metric, Milvus returns similarity scores (higher = more similar)\n",
+    "            # No need to convert - use the score directly\n",
+    "            similarity_score = hit[\"distance\"]  # This is actually similarity for COSINE\n",
+    "            \n",
     "            formatted_results.append({\n",
     "                \"text\": hit[\"text\"],\n",
     "                \"metadata\": json.loads(hit[\"metadata\"]),\n",
-    "                \"score\": 1.0 - hit[\"distance\"],  # Convert distance to similarity score for COSINE\n",
+    "                \"score\": similarity_score,  # Use direct similarity score\n",
     "                \"id\": hit[\"id\"]\n",
     "            })\n",
     "        \n",
@@ -851,31 +855,47 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Test Sample Queries\n",
-    "queries = [\n",
-    "    \"What is artificial intelligence?\",\n",
-    "    \"How does Milvus work as a vector database?\",\n",
-    "    \"Explain the RAG pipeline steps\",\n",
-    "    \"What are the differences between machine learning and deep learning?\"\n",
-    "]\n",
+    "# Debug Sample Queries - Test one specific query with detailed logging\n",
+    "print(\"🔍 Debug: Testing specific query with detailed logging\\n\")\n",
     "\n",
-    "print(\"Testing RAG Pipeline with sample queries...\\n\")\n",
+    "# Test the Milvus query that should definitely work\n",
+    "test_query = \"How does Milvus work as a vector database?\"\n",
+    "print(f\"Query: {test_query}\")\n",
+    "print(\"-\" * 50)\n",
     "\n",
-    "for i, query in enumerate(queries, 1):\n",
-    "    print(f\"Query {i}: {query}\")\n",
-    "    print(\"-\" * 50)\n",
-    "    \n",
-    "    result = rag.query(query, top_k=3)\n",
-    "    \n",
-    "    print(f\"Answer: {result['answer']}\")\n",
-    "    print(f\"\\nRetrieved {result['num_retrieved']} documents:\")\n",
-    "    \n",
-    "    for j, doc in enumerate(result['retrieved_documents'], 1):\n",
-    "        print(f\"  {j}. Score: {doc['score']:.4f}\")\n",
-    "        print(f\"     Text: {doc['text'][:100]}...\")\n",
-    "        print(f\"     Source: {doc['metadata'].get('source', 'Unknown')}\")\n",
+    "# Get query embedding\n",
+    "query_embedding = rag.embedding_generator.embed_text(test_query)\n",
+    "print(f\"✅ Generated query embedding: shape {query_embedding.shape}\")\n",
+    "\n",
+    "# Test direct search on vector store\n",
+    "print(\"🔍 Testing direct vector store search...\")\n",
+    "try:\n",
+    "    search_results = rag.vector_store.search(query_embedding, top_k=5)\n",
+    "    print(f\"✅ Direct search returned {len(search_results)} results\")\n",
     "    \n",
-    "    print(\"\\n\" + \"=\" * 80 + \"\\n\")"
+    "    if search_results:\n",
+    "        for i, result in enumerate(search_results):\n",
+    "            print(f\"  Result {i+1}:\")\n",
+    "            print(f\"    Score: {result.get('score', 'N/A')}\")\n",
+    "            print(f\"    Text preview: {str(result.get('text', 'N/A'))[:100]}...\")\n",
+    "            print(f\"    ID: {result.get('id', 'N/A')}\")\n",
+    "    else:\n",
+    "        print(\"  ❌ No results from direct search\")\n",
+    "        \n",
+    "except Exception as e:\n",
+    "    print(f\"❌ Direct search failed: {e}\")\n",
+    "\n",
+    "print(\"\\n\" + \"=\" * 50)\n",
+    "\n",
+    "# Now test full RAG pipeline\n",
+    "print(\"🔍 Testing full RAG pipeline...\")\n",
+    "result = rag.query(test_query, top_k=5)\n",
+    "print(f\"Full pipeline returned {result['num_retrieved']} documents\")\n",
+    "print(f\"Answer: {result['answer'][:200]}...\")\n",
+    "\n",
+    "print(\"\\n🔍 Let's also test a simple keyword match:\")\n",
+    "keyword_result = rag.query(\"Milvus vector database\", top_k=5)  \n",
+    "print(f\"Keyword query returned {keyword_result['num_retrieved']} documents\")"
    ]
   },
   {