From 712abf0e7dc88ea8ab56e5e2dadee626a21c6e99 Mon Sep 17 00:00:00 2001
From: KaifAhmad1 <kaifahmad087@gmail.com>
Date: Fri, 19 Dec 2025 23:03:01 +0530
Subject: [PATCH] Update multi-source integration notebook and dependencies

---
 .../06_Multi_Source_Data_Integration.ipynb    | 45 ++++++++++++++++++-
 pyproject.toml                                |  3 +-
 2 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/cookbook/advanced/06_Multi_Source_Data_Integration.ipynb b/cookbook/advanced/06_Multi_Source_Data_Integration.ipynb
index a7b0a19d..70d77832 100644
--- a/cookbook/advanced/06_Multi_Source_Data_Integration.ipynb
+++ b/cookbook/advanced/06_Multi_Source_Data_Integration.ipynb
@@ -30,7 +30,7 @@
    "outputs": [],
    "source": [
     "# Installation & Setup\n",
-    "!pip install semantica mcp"
+    "!pip install semantica mcp fastmcp"
    ]
   },
   {
@@ -125,6 +125,49 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# --- Demonstration of Real Ingestion (Raw Data) ---\n",
+    "print(\"--- Ingesting Raw Data from Sources (Demonstration) ---\")\n",
+    "\n",
+    "# 1. Ingest from SQLite using DBIngestor\n",
+    "# We connect to the local SQLite database we just created\n",
+    "try:\n",
+    "    db_ingestor = DBIngestor()\n",
+    "    # SQLAlchemy connection string for SQLite\n",
+    "    db_connection = f\"sqlite:///{db_path}\"\n",
+    "    raw_db_data = db_ingestor.ingest_database(db_connection)\n",
+    "    print(f\"DBIngestor: Successfully connected to {db_path}\")\n",
+    "    print(f\"DBIngestor: Found tables: {list(raw_db_data.get('tables', {}).keys())}\")\n",
+    "except Exception as e:\n",
+    "    print(f\"DBIngestor Warning: {e}\")\n",
+    "\n",
+    "# 2. Ingest from Files using FileIngestor\n",
+    "# We load the Markdown and JSON files directly\n",
+    "try:\n",
+    "    file_ingestor = FileIngestor()\n",
+    "    \n",
+    "    # Ingest Markdown\n",
+    "    readme_file = file_ingestor.ingest_file(repo_path)\n",
+    "    print(f\"FileIngestor: Read {readme_file.name} ({readme_file.size} bytes)\")\n",
+    "    \n",
+    "    # Ingest JSON\n",
+    "    market_file = file_ingestor.ingest_file(api_path)\n",
+    "    print(f\"FileIngestor: Read {market_file.name} ({market_file.size} bytes)\")\n",
+    "except Exception as e:\n",
+    "    print(f\"FileIngestor Warning: {e}\")\n",
+    "\n",
+    "# 3. Ingest from Web using WebIngestor\n",
+    "# Since we created a local HTML file, we could use FileIngestor, \n",
+    "# but here we demonstrate WebIngestor initialization for URL-based sources.\n",
+    "try:\n",
+    "    web_ingestor = WebIngestor()\n",
+    "    # In a real scenario, we would call: \n",
+    "    # web_content = web_ingestor.ingest_url(\"https://nexus.ai/news\")\n",
+    "    print(f\"WebIngestor: Initialized and ready to crawl URLs.\")\n",
+    "except Exception as e:\n",
+    "    print(f\"WebIngestor Warning: {e}\")\n",
+    "\n",
+    "print(\"-\" * 50 + \"\\n\")\n",
+    "\n",
     "# Simulate extracted entities from our sources\n",
     "\n",
     "source_db = {\n",
diff --git a/pyproject.toml b/pyproject.toml
index 29510af2..ac343ec5 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -82,7 +82,8 @@ dependencies = [
     "boto3>=1.24.0",
     "azure-storage-blob>=12.12.0",
     "google-cloud-storage>=2.5.0",
-    "pydantic>=1.10.0",
+    "pydantic>=2.0.0",
+    "fastmcp>=0.1.0",
     "click>=8.1.0",
     "rich>=12.5.0",
     "tqdm>=4.64.0",