[Astra DB, vector store] Upgrade to astrapy 1.0 usage

examples/vector_databases/cassandra_astradb/Philosophical_Quotes_AstraPy.ipynb

@@ -50,7 +50,7 @@
     "\n",
     "To find a quote similar to the provided search quote, the latter is made into an embedding vector on the fly, and this vector is used to query the store for similar vectors ... i.e. similar quotes that were previously indexed. The search can optionally be constrained by additional metadata (\"find me quotes by Spinoza similar to this one ...\").\n",
     "\n",
-    "![2_vector_search](https://user-images.githubusercontent.com/14221764/282422033-0a1297c4-63bb-4e04-b120-dfd98dc1a689.png)\n",
+    "![2_vector_search](https://gist.github.com/assets/14221764/6c883c5b-defd-44d6-a64e-082255e66b57)\n",
     "\n",
     "The key point here is that \"quotes similar in content\" translates, in vector space, to vectors that are metrically close to each other: thus, vector similarity search effectively implements semantic similarity. _This is the key reason vector embeddings are so powerful._\n",
     "\n",
@@ -92,7 +92,7 @@
    },
    "outputs": [],
    "source": [
-    "!pip install --quiet \"astrapy>=0.6.0\" \"openai>=1.0.0\" datasets"
+    "!pip install --quiet \"astrapy>=1.1.0\" \"openai>=1.0.0\" \"datasets>=2.19.1\""
    ]
   },
   {
@@ -105,7 +105,7 @@
     "from getpass import getpass\n",
     "from collections import Counter\n",
     "\n",
-    "from astrapy.db import AstraDB\n",
+    "from astrapy import DataAPIClient\n",
     "import openai\n",
     "from datasets import load_dataset"
    ]
@@ -123,7 +123,7 @@
    "id": "65a8edc1-4633-491b-9ed3-11163ec24e46",
    "metadata": {},
    "source": [
-    "Please retrieve your database credentials on your Astra dashboard ([info](https://docs.datastax.com/en/astra/astra-db-vector/)): you will supply them momentarily.\n",
+    "Please retrieve your database credentials on your Astra dashboard ([info](https://docs.datastax.com/en/astra-db-serverless/index.html)): you will supply them momentarily.\n",
     "\n",
     "Example values:\n",
     "\n",
@@ -138,25 +138,30 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
+     "name": "stdin",
      "output_type": "stream",
      "text": [
-      "Please enter your API Endpoint: https://4f835778-ec78-42b0-9ae3-29e3cf45b596-us-east1.apps.astra.datastax.com\n",
-      "Please enter your Token ········\n"
+      "Please enter your API Endpoint: https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com\n",
+      "Please enter your Token: ········\n",
+      "Please enter your namespace. Leave empty for default: \n"
      ]
     }
    ],
    "source": [
     "ASTRA_DB_API_ENDPOINT = input(\"Please enter your API Endpoint:\")\n",
-    "ASTRA_DB_APPLICATION_TOKEN = getpass(\"Please enter your Token\")"
+    "ASTRA_DB_APPLICATION_TOKEN = getpass(\"Please enter your Token:\")\n",
+    "\n",
+    "ASTRA_DB_KEYSPACE = input(\"Please enter your namespace. Leave empty for default:\")\n",
+    "if not ASTRA_DB_KEYSPACE:\n",
+    "    ASTRA_DB_KEYSPACE = None"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "f8c4e5ec-2ab2-4d41-b3ec-c946469fed8b",
    "metadata": {},
    "source": [
-    "### Instantiate an Astra DB client"
+    "### Connect to your Astra DB"
    ]
   },
   {
@@ -166,10 +171,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "astra_db = AstraDB(\n",
-    "    api_endpoint=ASTRA_DB_API_ENDPOINT,\n",
-    "    token=ASTRA_DB_APPLICATION_TOKEN,\n",
-    ")"
+    "astra_db_client = DataAPIClient(token=ASTRA_DB_APPLICATION_TOKEN)\n",
+    "database = astra_db_client.get_database_by_api_endpoint(ASTRA_DB_API_ENDPOINT, namespace=ASTRA_DB_KEYSPACE)"
    ]
   },
   {
@@ -196,7 +199,7 @@
    "outputs": [],
    "source": [
     "coll_name = \"philosophers_astra_db\"\n",
-    "collection = astra_db.create_collection(coll_name, dimension=1536)"
+    "collection = database.create_collection(coll_name, dimension=1536)"
    ]
   },
   {
@@ -222,7 +225,7 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
+     "name": "stdin",
      "output_type": "stream",
      "text": [
       "Please enter your OpenAI API Key:  ········\n"
@@ -281,7 +284,7 @@
      "output_type": "stream",
      "text": [
       "len(result.data)              = 2\n",
-      "result.data[1].embedding      = [-0.0108176339417696, 0.0013546717818826437, 0.00362232...\n",
+      "result.data[1].embedding      = [0.009454815648496151, 0.0015082946047186852, -0.036191...\n",
       "len(result.data[1].embedding) = 1536\n"
      ]
     }
@@ -408,13 +411,13 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Starting to store entries: [20][20][20][20][20][20][20][20][20][20][20][20][20][20][20][20][20][20][20][20][20][20][10]\n",
+      "Starting to store entries: [100][100][100][100][50]\n",
       "Finished storing entries.\n"
      ]
     }
    ],
    "source": [
-    "BATCH_SIZE = 20\n",
+    "BATCH_SIZE = 100\n",
     "\n",
     "num_batches = ((len(philo_dataset) + BATCH_SIZE - 1) // BATCH_SIZE)\n",
     "\n",
@@ -492,11 +495,11 @@
     "        for tag in tags:\n",
     "            filter_clause[\"tags\"][tag] = True\n",
     "    #\n",
-    "    results = collection.vector_find(\n",
-    "        query_vector,\n",
+    "    results = collection.find(\n",
+    "        vector=query_vector,\n",
     "        limit=n,\n",
     "        filter=filter_clause,\n",
-    "        fields=[\"quote\", \"author\"]\n",
+    "        projection={\"quote\": True, \"author\": True},\n",
     "    )\n",
     "    return [\n",
     "        (result[\"quote\"], result[\"author\"])\n",
@@ -531,10 +534,10 @@
       "text/plain": [
        "[('Life to the great majority is only a constant struggle for mere existence, with the certainty of losing it at last.',\n",
        "  'schopenhauer'),\n",
-       " ('We give up leisure in order that we may have leisure, just as we go to war in order that we may have peace.',\n",
-       "  'aristotle'),\n",
-       " ('Perhaps the gods are kind to us, by making life more disagreeable as we grow older. In the end death seems less intolerable than the manifold burdens we carry',\n",
-       "  'freud')]"
+       " ('To endure life remains, when all is said, the first duty of all living being Illusion can have no value if it makes this more difficult for us.',\n",
+       "  'freud'),\n",
+       " ('To live is to suffer, to survive is to find some meaning in the suffering.',\n",
+       "  'nietzsche')]"
       ]
      },
      "execution_count": 14,
@@ -596,8 +599,8 @@
      "data": {
       "text/plain": [
        "[('He who seeks equality between unequals seeks an absurdity.', 'spinoza'),\n",
-       " ('The people are that part of the state that does not know what it wants.',\n",
-       "  'hegel')]"
+       " ('One... gets an impression that civilization is something which was imposed on a resisting majority by a minority which understood how to obtain possession of the means to power and coercion. It is, of course, natural to assume that these difficulties are not inherent in the nature of civilization itself but are determined by the imperfections of the cultural forms which have so far been developed.',\n",
+       "  'freud')]"
       ]
      },
      "execution_count": 16,
@@ -636,10 +639,11 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "3 quotes within the threshold:\n",
-      "    0. [similarity=0.927] \"The assumption that animals are without rights, and the illusion that ...\"\n",
-      "    1. [similarity=0.922] \"Animals are in possession of themselves; their soul is in possession o...\"\n",
-      "    2. [similarity=0.920] \"At his best, man is the noblest of all animals; separated from law and...\"\n"
+      "4 quotes within the threshold:\n",
+      "    0. [similarity=0.746] \"The assumption that animals are without rights, and the illusion that ...\"\n",
+      "    1. [similarity=0.728] \"Man is the only animal that must be encouraged to live....\"\n",
+      "    2. [similarity=0.727] \"Animals are in possession of themselves; their soul is in possession o...\"\n",
+      "    3. [similarity=0.725] \"At his best, man is the noblest of all animals; separated from law and...\"\n"
      ]
     }
    ],
@@ -648,17 +652,18 @@
     "# quote = \"Be good.\"\n",
     "# quote = \"This teapot is strange.\"\n",
     "\n",
-    "metric_threshold = 0.92\n",
+    "metric_threshold = 0.72\n",
     "\n",
     "quote_vector = client.embeddings.create(\n",
     "    input=[quote],\n",
     "    model=embedding_model_name,\n",
     ").data[0].embedding\n",
     "\n",
-    "results_full = collection.vector_find(\n",
-    "    quote_vector,\n",
+    "results_full = collection.find(\n",
+    "    vector=quote_vector,\n",
     "    limit=8,\n",
-    "    fields=[\"quote\"]\n",
+    "    projection={\"quote\": True},\n",
+    "    include_similarity=True,\n",
     ")\n",
     "results = [res for res in results_full if res[\"$similarity\"] >= metric_threshold]\n",
     "\n",
@@ -780,12 +785,12 @@
      "output_type": "stream",
      "text": [
       "** quotes found:\n",
-      "**    - Happiness is the reward of virtue. (aristotle)\n",
       "**    - Our moral virtues benefit mainly other people; intellectual virtues, on the other hand, benefit primarily ourselves; therefore the former make us universally popular, the latter unpopular. (schopenhauer)\n",
+      "**    - Happiness is the reward of virtue. (aristotle)\n",
       "** end of logging\n",
       "\n",
       "A new generated quote:\n",
-      "True politics lies in the virtuous pursuit of justice, for it is through virtue that we build a better world for all.\n"
+      "- In politics, true virtue is the compass that guides us towards a better society.\n"
      ]
     }
    ],
@@ -814,12 +819,12 @@
      "output_type": "stream",
      "text": [
       "** quotes found:\n",
-      "**    - Because Christian morality leaves animals out of account, they are at once outlawed in philosophical morals; they are mere 'things,' mere means to any ends whatsoever. They can therefore be used for vivisection, hunting, coursing, bullfights, and horse racing, and can be whipped to death as they struggle along with heavy carts of stone. Shame on such a morality that is worthy of pariahs, and that fails to recognize the eternal essence that exists in every living thing, and shines forth with inscrutable significance from all eyes that see the sun! (schopenhauer)\n",
       "**    - The assumption that animals are without rights, and the illusion that our treatment of them has no moral significance, is a positively outrageous example of Western crudity and barbarity. Universal compassion is the only guarantee of morality. (schopenhauer)\n",
+      "**    - Because Christian morality leaves animals out of account, they are at once outlawed in philosophical morals; they are mere 'things,' mere means to any ends whatsoever. They can therefore be used for vivisection, hunting, coursing, bullfights, and horse racing, and can be whipped to death as they struggle along with heavy carts of stone. Shame on such a morality that is worthy of pariahs, and that fails to recognize the eternal essence that exists in every living thing, and shines forth with inscrutable significance from all eyes that see the sun! (schopenhauer)\n",
       "** end of logging\n",
       "\n",
       "A new generated quote:\n",
-      "Excluding animals from ethical consideration reveals a moral blindness that allows for their exploitation and suffering. True morality embraces universal compassion.\n"
+      "The true measure of humanity lies in our treatment of animals, for compassion towards all living beings reflects our moral essence.\n"
      ]
     }
    ],
@@ -848,7 +853,7 @@
     {
      "data": {
       "text/plain": [
-       "{'status': {'ok': 1}}"
+       "{'ok': 1}"
       ]
      },
      "execution_count": 22,
@@ -857,7 +862,7 @@
     }
    ],
    "source": [
-    "astra_db.delete_collection(coll_name)"
+    "collection.drop()"
    ]
   }
  ],
@@ -877,7 +882,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

examples/vector_databases/cassandra_astradb/README.md

@@ -8,8 +8,8 @@ These example notebooks demonstrate implementation of
 the same GenAI standard RAG workload with different libraries and APIs.
 
 To use [Astra DB](https://docs.datastax.com/en/astra/home/astra.html)
-with its HTTP API interface, head to the "AstraPy" notebook (`astrapy`
-is the Python client to interact with the database).
+through its Data API interface, head to the "AstraPy" notebook (`astrapy`
+is the Python client for the Data API).
 
 If you prefer CQL access to the database (either with
 [Astra DB](https://docs.datastax.com/en/astra-serverless/docs/vector-search/overview.html)

registry.yaml

@@ -612,6 +612,16 @@
     - embeddings
     - completions
 
+- title: Philosophy with Vector Embeddings, OpenAI and Cassandra / Astra DB
+  path: >-
+    examples/vector_databases/cassandra_astradb/Philosophical_Quotes_AstraPy.ipynb
+  date: 2023-11-13
+  authors:
+    - hemidactylus
+  tags:
+    - embeddings
+    - completions
+
 - title: Cassandra / Astra DB
   path: examples/vector_databases/cassandra_astradb/README.md
   date: 2023-08-29