diff --git a/ch3/jupyter-notebooks/data_classes.ipynb b/ch3/jupyter-notebooks/data_classes.ipynb
index 293b471..5fb82d8 100644
--- a/ch3/jupyter-notebooks/data_classes.ipynb
+++ b/ch3/jupyter-notebooks/data_classes.ipynb
@@ -38,7 +38,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -56,7 +56,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -65,7 +65,7 @@
        "Document(id='ca53157e450d009adb4c2217111faadc9e7c02aefb22717c4901e1c1c1ba314a', content='This is a simple document', dataframe=None, blob=None, meta={'name': 'test_doc'}, score=None)"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -77,7 +77,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -86,7 +86,7 @@
        "'ca53157e450d009adb4c2217111faadc9e7c02aefb22717c4901e1c1c1ba314a'"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -104,7 +104,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -113,7 +113,7 @@
        "'This is a simple document'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -124,7 +124,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -133,7 +133,7 @@
        "{'name': 'test_doc'}"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -151,7 +151,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -175,20 +175,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(id='22cf9396b67c1929c273ed65a6fcea5b8ba8b384ae45d5164be9ca7b6827c66c', content=None, dataframe=   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
-       "0                5.1               3.5                1.4               0.2   \n",
+       "Document(id='22cf9396b67c1929c273ed65a6fcea5b8ba8b384ae45d5164be9ca7b6827c66c', content=None, dataframe=   sepal length (cm)  sepal width (cm)  ...  petal width (cm)  target\n",
+       "0                5.1               3.5  ...               0.2     0.0\n",
        "\n",
-       "   target  \n",
-       "0     0.0  , blob=None, meta={}, score=None)"
+       "[1 rows x 5 columns], blob=None, meta={}, score=None)"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -199,7 +198,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -208,7 +207,7 @@
        "'22cf9396b67c1929c273ed65a6fcea5b8ba8b384ae45d5164be9ca7b6827c66c'"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -219,7 +218,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -264,14 +263,13 @@
        "</div>"
       ],
       "text/plain": [
-       "   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
-       "0                5.1               3.5                1.4               0.2   \n",
+       "   sepal length (cm)  sepal width (cm)  ...  petal width (cm)  target\n",
+       "0                5.1               3.5  ...               0.2     0.0\n",
        "\n",
-       "   target  \n",
-       "0     0.0  "
+       "[1 rows x 5 columns]"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -291,7 +289,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -300,7 +298,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -314,7 +312,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -323,7 +321,7 @@
        "ByteStream(data=b'Your binary data here', metadata={}, mime_type='application/pdf')"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -334,7 +332,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -343,7 +341,7 @@
        "'93c323201fc3b8509e51056dff8baee6ca9dec1c22cf2ce2f6cfc0bb04397c14'"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -377,7 +375,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -386,7 +384,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -406,7 +404,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -426,7 +424,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
@@ -446,7 +444,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -473,7 +471,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -482,7 +480,7 @@
        "'740dcdab24b6c171e89af1f1158056d6f09c6cd238a39866dfe7160a47eeba9a'"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -495,7 +493,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -504,7 +502,7 @@
        "ChatMessage(content='Can you show me the weather forecast?', role=<ChatRole.USER: 'user'>, name=None, metadata={})"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -524,7 +522,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -540,7 +538,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
@@ -577,7 +575,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [
     {
@@ -586,7 +584,7 @@
        "'55b3a7072cc30c752c726922b929f073bf377fb72dbe89431c323031cf5360cd'"
       ]
      },
-     "execution_count": 29,
+     "execution_count": 26,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -599,7 +597,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [
     {
@@ -608,7 +606,7 @@
        "'This is the first segment of the live stream.'"
       ]
      },
-     "execution_count": 32,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -630,7 +628,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -646,40 +644,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(id='22cf9396b67c1929c273ed65a6fcea5b8ba8b384ae45d5164be9ca7b6827c66c', content=None, dataframe=   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
-       " 0                5.1               3.5                1.4               0.2   \n",
+       "[Document(id='22cf9396b67c1929c273ed65a6fcea5b8ba8b384ae45d5164be9ca7b6827c66c', content=None, dataframe=   sepal length (cm)  sepal width (cm)  ...  petal width (cm)  target\n",
+       " 0                5.1               3.5  ...               0.2     0.0\n",
        " \n",
-       "    target  \n",
-       " 0     0.0  , blob=None, meta={}, score=None),\n",
-       " Document(id='c4852f58c6c65daaa7b11d7c009d8cbf7198c52c55f63fe27bf888beec64b673', content=None, dataframe=   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
-       " 1                4.9               3.0                1.4               0.2   \n",
+       " [1 rows x 5 columns], blob=None, meta={}, score=None),\n",
+       " Document(id='c4852f58c6c65daaa7b11d7c009d8cbf7198c52c55f63fe27bf888beec64b673', content=None, dataframe=   sepal length (cm)  sepal width (cm)  ...  petal width (cm)  target\n",
+       " 1                4.9               3.0  ...               0.2     0.0\n",
        " \n",
-       "    target  \n",
-       " 1     0.0  , blob=None, meta={}, score=None),\n",
-       " Document(id='109c0409cdbcf2343ee97efd3ec334e74e73b5eeed3ecc362cbcff8adda10603', content=None, dataframe=   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
-       " 2                4.7               3.2                1.3               0.2   \n",
+       " [1 rows x 5 columns], blob=None, meta={}, score=None),\n",
+       " Document(id='109c0409cdbcf2343ee97efd3ec334e74e73b5eeed3ecc362cbcff8adda10603', content=None, dataframe=   sepal length (cm)  sepal width (cm)  ...  petal width (cm)  target\n",
+       " 2                4.7               3.2  ...               0.2     0.0\n",
        " \n",
-       "    target  \n",
-       " 2     0.0  , blob=None, meta={}, score=None),\n",
-       " Document(id='3eef63e56ef7174a490478bd4147b70c113521fee93a13f430e14641a330fff3', content=None, dataframe=   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
-       " 3                4.6               3.1                1.5               0.2   \n",
+       " [1 rows x 5 columns], blob=None, meta={}, score=None),\n",
+       " Document(id='3eef63e56ef7174a490478bd4147b70c113521fee93a13f430e14641a330fff3', content=None, dataframe=   sepal length (cm)  sepal width (cm)  ...  petal width (cm)  target\n",
+       " 3                4.6               3.1  ...               0.2     0.0\n",
        " \n",
-       "    target  \n",
-       " 3     0.0  , blob=None, meta={}, score=None),\n",
-       " Document(id='eb5cd52bfc94cfc8fc3f750558e8f13cd9f0f69058994416850cba7c3ed8c895', content=None, dataframe=   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
-       " 4                5.0               3.6                1.4               0.2   \n",
+       " [1 rows x 5 columns], blob=None, meta={}, score=None),\n",
+       " Document(id='eb5cd52bfc94cfc8fc3f750558e8f13cd9f0f69058994416850cba7c3ed8c895', content=None, dataframe=   sepal length (cm)  sepal width (cm)  ...  petal width (cm)  target\n",
+       " 4                5.0               3.6  ...               0.2     0.0\n",
        " \n",
-       "    target  \n",
-       " 4     0.0  , blob=None, meta={}, score=None)]"
+       " [1 rows x 5 columns], blob=None, meta={}, score=None)]"
       ]
      },
-     "execution_count": 33,
+     "execution_count": 29,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -701,7 +694,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -719,7 +712,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [
     {
@@ -728,7 +721,7 @@
        "150"
       ]
      },
-     "execution_count": 36,
+     "execution_count": 31,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -746,7 +739,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [
     {
@@ -759,7 +752,7 @@
        "  'embedding_similarity_function': 'dot_product'}}"
       ]
      },
-     "execution_count": 42,
+     "execution_count": 32,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -768,6 +761,101 @@
     "iris_docstore.to_dict()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Answer, ExtractedAnswer and GeneratedAnswer\n",
+    "\n",
+    "The Answer, ExtractedAnswer, and GeneratedAnswer classes are data structures commonly used in natural language processing (NLP) pipelines, particularly in the context of question answering systems.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from haystack.preview.dataclasses import Answer, GeneratedAnswer, ExtractedAnswer"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### `Answer` is a base data class that represents a generic answer structure. It contains the fields: \n",
+    "\n",
+    "* data: The content of the answer. \n",
+    "\n",
+    "* query: The original question or query that prompted the answer. \n",
+    "\n",
+    "* metadata: A dictionary containing any additional information about the answer. \n",
+    "\n",
+    "#### `ExtractedAnswer` inherits from Answer and is more specific to scenarios where the answer is extracted from a text. It includes additional fields: \n",
+    "\n",
+    "* data: The text of the answer extracted from a document. \n",
+    "\n",
+    "* document: The Document object from which the answer was extracted. \n",
+    "\n",
+    "* probability: A float representing the confidence score of the extracted answer being correct. \n",
+    "\n",
+    "* start: The start index of the answer in the content of the Document. \n",
+    "\n",
+    "* end: The end index of the answer in the content of the Document. \n",
+    "\n",
+    "#### `GeneratedAnswer` also inherits from Answer and is used when the answer is generated (for example, by a language model) rather than extracted. Its fields are: \n",
+    "\n",
+    "* data: The generated text of the answer. \n",
+    "\n",
+    "* documents: A list of Document objects that were used as context or reference to generate the answer. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Extracted Answer: Berlin with probability 0.95\n",
+      "Generated Answer: Berlin is the capital of Germany.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Assume we have a document that contains the answer to a question\n",
+    "doc = Document(content=\"Berlin is the capital of Germany.\", id=\"123\")\n",
+    "\n",
+    "answer = Answer(data='Berlin',\n",
+    "                 query='What is the capital of Germany?',\n",
+    "                 metadata={})\n",
+    "\n",
+    "# After processing a query, we find the answer and create an ExtractedAnswer object\n",
+    "extracted_answer = ExtractedAnswer(\n",
+    "    data=\"Berlin\",\n",
+    "    query=\"What is the capital of Germany?\",\n",
+    "    metadata={},\n",
+    "    document=doc,\n",
+    "    probability=0.95,\n",
+    "    start=0,\n",
+    "    end=6\n",
+    ")\n",
+    "\n",
+    "# In another scenario, we might have a generated answer, not directly extracted from a specific location in a document\n",
+    "generated_answer = GeneratedAnswer(\n",
+    "    data=\"Berlin is the capital of Germany.\",\n",
+    "    documents=[doc],\n",
+    "    query=\"What is the capital of Germany?\",\n",
+    "    metadata={},\n",
+    ")\n",
+    "\n",
+    "# These objects can then be used to present answers, log results, or further processing\n",
+    "print(f\"Extracted Answer: {extracted_answer.data} with probability {extracted_answer.probability}\")\n",
+    "print(f\"Generated Answer: {generated_answer.data}\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},