diff --git a/docs/pinecone-quickstart.ipynb b/docs/pinecone-quickstart.ipynb index 899f691f..d5bfa7b2 100644 --- a/docs/pinecone-quickstart.ipynb +++ b/docs/pinecone-quickstart.ipynb @@ -30,28 +30,15 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 5, "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "4SudLike98WL", - "outputId": "f14a6133-7deb-40e3-968b-533c2e8f57ba" + "id": "4SudLike98WL" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/215.5 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━━━━━━━━━━━━━\u001b[0m \u001b[32m143.4/215.5 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m215.5/215.5 kB\u001b[0m \u001b[31m3.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25h" - ] - } - ], + "outputs": [], "source": [ "!pip install -qU \\\n", - " pinecone-client==4.1.0 \\\n", - " pinecone-notebooks==0.1.1" + " pinecone \\\n", + " pinecone-notebooks" ] }, { @@ -60,21 +47,18 @@ "id": "WoDXUiIkD1U7" }, "source": [ - "## Sign up or log in\n", + "## Get an API key\n", + "\n", + "You need an API key to make calls to your Pinecone project.\n", "\n", - "Sign up for a [free Pinecone account](https://www.pinecone.io/pricing/) and get an API key. Put your key in `PINECONE_API_KEY` below when initializing a new client instance:" + "Use the widget below to generate a key. If you don't have a Pinecone account, the widget will sign you up for the free Starter plan." ] }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 247 - }, - "id": "89S8G8oP61-t", - "outputId": "998abdfd-c528-4500-ff45-8344b6818e0a" + "id": "89S8G8oP61-t" }, "outputs": [], "source": [ @@ -85,15 +69,26 @@ " Authenticate()" ] }, + { + "cell_type": "markdown", + "source": [ + "## Initialize a client\n", + "\n", + "Use the generated API key to intialize a client connection to Pinecone:" + ], + "metadata": { + "id": "sbJFp5DO5ryT" + } + }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 7, "metadata": { "id": "e9rr_u6ZIvZ-" }, "outputs": [], "source": [ - "from pinecone import Pinecone\n", + "from pinecone import Pinecone, ServerlessSpec\n", "\n", "api_key = os.environ.get(\"PINECONE_API_KEY\")\n", "\n", @@ -102,28 +97,44 @@ }, { "cell_type": "markdown", - "metadata": { - "id": "qXBdv9IG06IU" - }, "source": [ - "Now we setup our index specification, this allows us to define the cloud provider and region where we want to deploy our index." - ] + "## Generate vectors\n", + "\n", + "A [vector embedding](https://www.pinecone.io/learn/vector-embeddings/) is a numerical representation of data that enables similarity-based search in vector databases like Pinecone. To convert data into this format, you use an embedding model.\n", + "\n", + "For this quickstart, use the [`multilingual-e5-large`](https://docs.pinecone.io/models/multilingual-e5-large) embedding model hosted by Pinecone to [create vector embeddings](https://docs.pinecone.io/guides/inference/generate-embeddings) for sentences related to the word \"apple\". Note that some sentences are about the tech company, while others are about the fruit.\n" + ], + "metadata": { + "id": "bN9Rl7GP258C" + } }, { "cell_type": "code", - "execution_count": 5, - "metadata": { - "id": "XYWFv-gw08WG" - }, - "outputs": [], "source": [ - "from pinecone import ServerlessSpec\n", + "# Define a sample dataset where each item has a unique ID and piece of text\n", + "data = [\n", + " {\"id\": \"vec1\", \"text\": \"Apple is a popular fruit known for its sweetness and crisp texture.\"},\n", + " {\"id\": \"vec2\", \"text\": \"The tech company Apple is known for its innovative products like the iPhone.\"},\n", + " {\"id\": \"vec3\", \"text\": \"Many people enjoy eating apples as a healthy snack.\"},\n", + " {\"id\": \"vec4\", \"text\": \"Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces.\"},\n", + " {\"id\": \"vec5\", \"text\": \"An apple a day keeps the doctor away, as the saying goes.\"},\n", + " {\"id\": \"vec6\", \"text\": \"Apple Computer Company was founded on April 1, 1976, by Steve Jobs, Steve Wozniak, and Ronald Wayne as a partnership.\"}\n", + "]\n", "\n", - "cloud = os.environ.get('PINECONE_CLOUD') or 'aws'\n", - "region = os.environ.get('PINECONE_REGION') or 'us-east-1'\n", + "# Convert the text into numerical vectors that Pinecone can index\n", + "embeddings = pc.inference.embed(\n", + " model=\"multilingual-e5-large\",\n", + " inputs=[d['text'] for d in data],\n", + " parameters={\"input_type\": \"passage\", \"truncate\": \"END\"}\n", + ")\n", "\n", - "spec = ServerlessSpec(cloud=cloud, region=region)" - ] + "print(embeddings)\n" + ], + "metadata": { + "id": "ZIclo2UK3NFE" + }, + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -131,16 +142,16 @@ "id": "VpgIIsLlJGFf" }, "source": [ - "## Create a serverless index\n", + "## Create an index\n", "\n", - "In Pinecone, an [index](https://docs.pinecone.io/guides/indexes/understanding-indexes) is the highest-level organizational unit of data, where you define the dimension of vectors to be stored and the [similarity metric](https://www.pinecone.io/learn/vector-similarity/) to be used when querying them. Normally, you choose a dimension and similarity metric based on the [embedding model](https://www.pinecone.io/models/) used to create your vectors. For this quickstart, however, you'll use a configuration that makes it easy to verify your query results.\n", + "In Pinecone, you store data in an [index](https://docs.pinecone.io/guides/indexes/understanding-indexes).\n", "\n", - "[Create a serverless index](https://docs.pinecone.io/guides/indexes/create-an-index#create-a-serverless-index) named `docs-quickstart-notebook` that stores vectors of 2 dimensions and performs nearest-neighbor search using the cosine similarity metric:" + "Create a serverless index that matches the dimension (`1024`) and similarity metric (`cosine`) of the `multilingual-e5-large` model you used in the previous step, and choose a [cloud and region](https://docs.pinecone.io/guides/indexes/understanding-indexes#cloud-regions) for hosting the index:" ] }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 9, "metadata": { "id": "Buo2K1h8O_fN" }, @@ -151,7 +162,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 10, "metadata": { "id": "MaqbcsI4I1gU" }, @@ -159,16 +170,20 @@ "source": [ "import time\n", "\n", - "if index_name not in pc.list_indexes().names():\n", + "if not pc.has_index(index_name):\n", " pc.create_index(\n", " name=index_name,\n", - " dimension=2,\n", + " dimension=1024,\n", " metric=\"cosine\",\n", - " spec=spec\n", + " spec=ServerlessSpec(\n", + " cloud='aws',\n", + " region='us-east-1'\n", + " )\n", " )\n", - " # wait for index to be ready\n", - " while not pc.describe_index(index_name).status['ready']:\n", - " time.sleep(1)" + "\n", + "# Wait for the index to be ready\n", + "while not pc.describe_index(index_name).status['ready']:\n", + " time.sleep(1)" ] }, { @@ -179,58 +194,37 @@ "source": [ "## Upsert vectors\n", "\n", - "Within an index, vectors are stored in [namespaces](https://docs.pinecone.io/guides/indexes/use-namespaces), and all upserts, queries, and other data operations always target one namespace:\n", - "\n", - "![multitenancy1.png](data:image/png;base64,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)\n", + "Target your index and use the [`upsert`](https://docs.pinecone.io/guides/data/upsert-data) operation to load your vector embeddings into a new namespace.\n", "\n", - "Now that you've created your index, target the `docs-quickstart-notebook` index and use the [`upsert`](https://docs.pinecone.io/reference/api/data-plane/upsert) operation to write six 2-dimensional vectors into 2 distinct namespaces:" + "**Note:** [Namespaces](https://docs.pinecone.io/guides/get-started/key-features#namespaces) let you partition records within an index and are essential for [implementing multitenancy](https://docs.pinecone.io/guides/get-started/implement-multitenancy) when you need to isolate the data of each customer/user.\n" ] }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "Ri6RX7FEiV4C", - "outputId": "a5bef5d5-6647-4946-f274-52b692c75e53" + "id": "Ri6RX7FEiV4C" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "{'upserted_count': 3}\n", - "{'upserted_count': 3}\n" - ] - } - ], + "outputs": [], "source": [ + "# Target the index where you'll store the vector embeddings\n", "index = pc.Index(index_name)\n", - "time.sleep(1)\n", - "\n", - "upsert1 = index.upsert(\n", - " vectors=[\n", - " {\"id\": \"vec1\", \"values\": [1.0, 1.5]},\n", - " {\"id\": \"vec2\", \"values\": [2.0, 1.0]},\n", - " {\"id\": \"vec3\", \"values\": [0.1, 3.0]},\n", - " ],\n", - " namespace=\"ns1\"\n", - ")\n", "\n", - "print(upsert1)\n", + "# Prepare the records for upsert\n", + "# Each contains an 'id', the embedding 'values', and the original text as 'metadata'\n", + "records = []\n", + "for d, e in zip(data, embeddings):\n", + " records.append({\n", + " \"id\": d['id'],\n", + " \"values\": e['values'],\n", + " \"metadata\": {'text': d['text']}\n", + " })\n", "\n", - "upsert2 = index.upsert(\n", - " vectors=[\n", - " {\"id\": \"vec1\", \"values\": [1.0, -2.5]},\n", - " {\"id\": \"vec2\", \"values\": [3.0, -2.0]},\n", - " {\"id\": \"vec3\", \"values\": [0.5, -1.5]},\n", - " ],\n", - " namespace=\"ns2\"\n", - ")\n", - "\n", - "print(upsert2)" + "# Upsert the records into the index\n", + "index.upsert(\n", + " vectors=records,\n", + " namespace=\"example-namespace\"\n", + ")" ] }, { @@ -239,7 +233,7 @@ "id": "fqVA4OrlidX2" }, "source": [ - "**Note:** When upserting larger amounts of data, [upsert data in batches](https://docs.pinecone.io/guides/data/upsert-data#upsert-records-in-batches) of 100-500 vectors over multiple upsert requests." + "**Note:** To load large amounts of data, [import from object storage](https://docs.pinecone.io/guides/data/understanding-imports) or [upsert in large batches](https://docs.pinecone.io/guides/data/upsert-data#upsert-records-in-batches)." ] }, { @@ -255,27 +249,14 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": null, "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "ANfVNxzDivEY", - "outputId": "6f77f8cf-ee64-42c7-964a-aaf03ba51b71" + "id": "ANfVNxzDivEY" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "{'dimension': 2,\n", - " 'index_fullness': 0.0,\n", - " 'namespaces': {},\n", - " 'total_vector_count': 0}\n" - ] - } - ], + "outputs": [], "source": [ + "time.sleep(10) # Wait for the upserted vectors to be indexed\n", + "\n", "print(index.describe_index_stats())" ] }, @@ -287,47 +268,41 @@ "source": [ "## Run a similarity search\n", "\n", - "Query each namespace in your index for the 3 vectors that are most similar to an example 2-dimensional vector using the cosine distance metric you specified for the index:" + "With data in your index, let's say you now want to search for information about \"Apple\" the tech company, not \"apple\" the fruit.\n", + "\n", + "Use the the `multilingual-e5-large` model to convert your query into a vector embedding, and then use the [`query`](https://docs.pinecone.io/guides/data/query-data) operation to search for the three vectors in the index that are most semantically similar to the query vector:" ] }, { "cell_type": "code", - "execution_count": 10, + "execution_count": null, "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "RyP4EQX8jcLn", - "outputId": "44a78289-eb69-44a9-d62b-225436ac164e" + "id": "RyP4EQX8jcLn" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "{'matches': [], 'namespace': 'ns1', 'usage': {'read_units': 1}}\n", - "{'matches': [], 'namespace': 'ns2', 'usage': {'read_units': 1}}\n" - ] - } - ], + "outputs": [], "source": [ - "query_results1 = index.query(\n", - " namespace=\"ns1\",\n", - " vector=[1.0, 1.5],\n", - " top_k=3,\n", - " include_values=True\n", - ")\n", + "# Define your query\n", + "query = \"Tell me about the tech company known as Apple.\"\n", "\n", - "print(query_results1)\n", + "# Convert the query into a numerical vector that Pinecone can search with\n", + "query_embedding = pc.inference.embed(\n", + " model=\"multilingual-e5-large\",\n", + " inputs=[query],\n", + " parameters={\n", + " \"input_type\": \"query\"\n", + " }\n", + ")\n", "\n", - "query_results2 = index.query(\n", - " namespace=\"ns2\",\n", - " vector=[1.0,-2.5],\n", + "# Search the index for the three most similar vectors\n", + "results = index.query(\n", + " namespace=\"example-namespace\",\n", + " vector=query_embedding[0].values,\n", " top_k=3,\n", - " include_values=True\n", + " include_values=False,\n", + " include_metadata=True\n", ")\n", "\n", - "print(query_results2)" + "print(results)" ] }, { @@ -336,17 +311,7 @@ "id": "9jAJDjSAjsvA" }, "source": [ - "
\n", - " Query results explained\n", - "\n", - " Your index uses the cosine distance metric, which measures similarity based on the angle between two vectors. Scores range between 1 and -1. The greater the score, the greater the similarity between the vectors.\n", - "\n", - " In the following graph, the upper and lower right quadrants show the query results from namespaces `ns1` and `ns2`, respectively. In each quadrant, blue represents the most similar vector, green the second most similar, and red the third most similar. In this case, the most similar vectors are identical to the query vectors, with a score of 1, and so the blue arrows represent both the query vectors and the nearest vectors.\n", - " \n", - " ![quickstart-cosine.png](data:image/png;base64,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)\n", - "
\n", - "\n", - "This is a simple example. As you put more demands on Pinecone, you’ll see it returning low-latency, accurate results at huge scales, with indexes of up to billions of vectors." + "Notice that the response includes only sentences about the tech company, not the fruit." ] }, { @@ -357,12 +322,12 @@ "source": [ "## Clean up\n", "\n", - "When you no longer need the “docs-quickstart-notebook” index, use the [`delete_index`](https://docs.pinecone.io/reference/api/control-plane/delete_index) operation to delete it:" + "When you no longer need the `docs-quickstart-notebook` index, use the [`delete_index`](https://docs.pinecone.io/reference/api/control-plane/delete_index) operation to delete it:" ] }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 15, "metadata": { "id": "1iHV2Y0ujy0y" }, @@ -395,4 +360,4 @@ }, "nbformat": 4, "nbformat_minor": 0 -} +} \ No newline at end of file