langchain/docs/versioned_docs/version-0.2.x/integrations/vectorstores/vespa.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "ce0f17b9",
   "metadata": {},
   "source": [
    "# Vespa\n",
    "\n",
    ">[Vespa](https://vespa.ai/) is a fully featured search engine and vector database. It supports vector search (ANN), lexical search, and search in structured data, all in the same query.\n",
    "\n",
    "This notebook shows how to use `Vespa.ai` as a LangChain vector store.\n",
    "\n",
    "In order to create the vector store, we use\n",
    "[pyvespa](https://pyvespa.readthedocs.io/en/latest/index.html) to create a\n",
    "connection a `Vespa` service."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7e6a11ab-38bd-4920-ba11-60cb2f075754",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "%pip install --upgrade --quiet  pyvespa"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "283b49c9",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "Using the `pyvespa` package, you can either connect to a\n",
    "[Vespa Cloud instance](https://pyvespa.readthedocs.io/en/latest/deploy-vespa-cloud.html)\n",
    "or a local\n",
    "[Docker instance](https://pyvespa.readthedocs.io/en/latest/deploy-docker.html).\n",
    "Here, we will create a new Vespa application and deploy that using Docker.\n",
    "\n",
    "#### Creating a Vespa application\n",
    "\n",
    "First, we need to create an application package:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "91150665",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from vespa.package import ApplicationPackage, Field, RankProfile\n",
    "\n",
    "app_package = ApplicationPackage(name=\"testapp\")\n",
    "app_package.schema.add_fields(\n",
    "    Field(\n",
    "        name=\"text\", type=\"string\", indexing=[\"index\", \"summary\"], index=\"enable-bm25\"\n",
    "    ),\n",
    "    Field(\n",
    "        name=\"embedding\",\n",
    "        type=\"tensor<float>(x[384])\",\n",
    "        indexing=[\"attribute\", \"summary\"],\n",
    "        attribute=[\"distance-metric: angular\"],\n",
    "    ),\n",
    ")\n",
    "app_package.schema.add_rank_profile(\n",
    "    RankProfile(\n",
    "        name=\"default\",\n",
    "        first_phase=\"closeness(field, embedding)\",\n",
    "        inputs=[(\"query(query_embedding)\", \"tensor<float>(x[384])\")],\n",
    "    )\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "15477106",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "This sets up a Vespa application with a schema for each document that contains\n",
    "two fields: `text` for holding the document text and `embedding` for holding\n",
    "the embedding vector. The `text` field is set up to use a BM25 index for\n",
    "efficient text retrieval, and we'll see how to use this and hybrid search a\n",
    "bit later.\n",
    "\n",
    "The `embedding` field is set up with a vector of length 384 to hold the\n",
    "embedding representation of the text. See\n",
    "[Vespa's Tensor Guide](https://docs.vespa.ai/en/tensor-user-guide.html)\n",
    "for more on tensors in Vespa.\n",
    "\n",
    "Lastly, we add a [rank profile](https://docs.vespa.ai/en/ranking.html) to\n",
    "instruct Vespa how to order documents. Here we set this up with a\n",
    "[nearest neighbor search](https://docs.vespa.ai/en/nearest-neighbor-search.html).\n",
    "\n",
    "Now we can deploy this application locally:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c10dd962",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from vespa.deployment import VespaDocker\n",
    "\n",
    "vespa_docker = VespaDocker()\n",
    "vespa_app = vespa_docker.deploy(application_package=app_package)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3df4ce53",
   "metadata": {},
   "source": [
    "This deploys and creates a connection to a `Vespa` service. In case you\n",
    "already have a Vespa application running, for instance in the cloud,\n",
    "please refer to the PyVespa application for how to connect.\n",
    "\n",
    "#### Creating a Vespa vector store\n",
    "\n",
    "Now, let's load some documents:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7abde491",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from langchain_community.document_loaders import TextLoader\n",
    "from langchain_text_splitters import CharacterTextSplitter\n",
    "\n",
    "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
    "documents = loader.load()\n",
    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
    "docs = text_splitter.split_documents(documents)\n",
    "\n",
    "from langchain_community.embeddings.sentence_transformer import (\n",
    "    SentenceTransformerEmbeddings,\n",
    ")\n",
    "\n",
    "embedding_function = SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d42365c7",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Here, we also set up local sentence embedder to transform the text to embedding\n",
    "vectors. One could also use OpenAI embeddings, but the vector length needs to\n",
    "be updated to `1536` to reflect the larger size of that embedding.\n",
    "\n",
    "To feed these to Vespa, we need to configure how the vector store should map to\n",
    "fields in the Vespa application. Then we create the vector store directly from\n",
    "this set of documents:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0b647878",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "vespa_config = dict(\n",
    "    page_content_field=\"text\",\n",
    "    embedding_field=\"embedding\",\n",
    "    input_field=\"query_embedding\",\n",
    ")\n",
    "\n",
    "from langchain_community.vectorstores import VespaStore\n",
    "\n",
    "db = VespaStore.from_documents(docs, embedding_function, app=vespa_app, **vespa_config)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d6bd0aab",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "This creates a Vespa vector store and feeds that set of documents to Vespa.\n",
    "The vector store takes care of calling the embedding function for each document\n",
    "and inserts them into the database.\n",
    "\n",
    "We can now query the vector store:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7ccca1f4",
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "results = db.similarity_search(query)\n",
    "\n",
    "print(results[0].page_content)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e7e34e1",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "This will use the embedding function given above to create a representation\n",
    "for the query and use that to search Vespa. Note that this will use the\n",
    "`default` ranking function, which we set up in the application package\n",
    "above. You can use the `ranking` argument to `similarity_search` to\n",
    "specify which ranking function to use.\n",
    "\n",
    "Please refer to the [pyvespa documentation](https://pyvespa.readthedocs.io/en/latest/getting-started-pyvespa.html#Query)\n",
    "for more information.\n",
    "\n",
    "This covers the basic usage of the Vespa store in LangChain.\n",
    "Now you can return the results and continue using these in LangChain.\n",
    "\n",
    "#### Updating documents\n",
    "\n",
    "An alternative to calling `from_documents`, you can create the vector\n",
    "store directly and call `add_texts` from that. This can also be used to update\n",
    "documents:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a5256284",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "results = db.similarity_search(query)\n",
    "result = results[0]\n",
    "\n",
    "result.page_content = \"UPDATED: \" + result.page_content\n",
    "db.add_texts([result.page_content], [result.metadata], result.metadata[\"id\"])\n",
    "\n",
    "results = db.similarity_search(query)\n",
    "print(results[0].page_content)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2526b50e",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "However, the `pyvespa` library contains methods to manipulate\n",
    "content on Vespa which you can use directly.\n",
    "\n",
    "#### Deleting documents\n",
    "\n",
    "You can delete documents using the `delete` function:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "52cab87e",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "result = db.similarity_search(query)\n",
    "# docs[0].metadata[\"id\"] == \"id:testapp:testapp::32\"\n",
    "\n",
    "db.delete([\"32\"])\n",
    "result = db.similarity_search(query)\n",
    "# docs[0].metadata[\"id\"] != \"id:testapp:testapp::32\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "deffaba5",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Again, the `pyvespa` connection contains methods to delete documents as well.\n",
    "\n",
    "### Returning with scores\n",
    "\n",
    "The `similarity_search` method only returns the documents in order of\n",
    "relevancy. To retrieve the actual scores:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cd9ae173",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "results = db.similarity_search_with_score(query)\n",
    "result = results[0]\n",
    "# result[1] ~= 0.463"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7257d67a",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "This is a result of using the `\"all-MiniLM-L6-v2\"` embedding model using the\n",
    "cosine distance function (as given by the argument `angular` in the\n",
    "application function).\n",
    "\n",
    "Different embedding functions need different distance functions, and Vespa\n",
    "needs to know which distance function to use when orderings documents.\n",
    "Please refer to the\n",
    "[documentation on distance functions](https://docs.vespa.ai/en/reference/schema-reference.html#distance-metric)\n",
    "for more information.\n",
    "\n",
    "### As retriever\n",
    "\n",
    "To use this vector store as a\n",
    "[LangChain retriever](/docs/modules/data_connection/retrievers/)\n",
    "simply call the `as_retriever` function, which is a standard vector store\n",
    "method:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7fb717a9",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "db = VespaStore.from_documents(docs, embedding_function, app=vespa_app, **vespa_config)\n",
    "retriever = db.as_retriever()\n",
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "results = retriever.get_relevant_documents(query)\n",
    "\n",
    "# results[0].metadata[\"id\"] == \"id:testapp:testapp::32\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fba7f07e",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "This allows for more general, unstructured, retrieval from the vector store.\n",
    "\n",
    "### Metadata\n",
    "\n",
    "In the example so far, we've only used the text and the embedding for that\n",
    "text. Documents usually contain additional information, which in LangChain\n",
    "is referred to as metadata.\n",
    "\n",
    "Vespa can contain many fields with different types by adding them to the application\n",
    "package:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "59cffcf2",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "app_package.schema.add_fields(\n",
    "    # ...\n",
    "    Field(name=\"date\", type=\"string\", indexing=[\"attribute\", \"summary\"]),\n",
    "    Field(name=\"rating\", type=\"int\", indexing=[\"attribute\", \"summary\"]),\n",
    "    Field(name=\"author\", type=\"string\", indexing=[\"attribute\", \"summary\"]),\n",
    "    # ...\n",
    ")\n",
    "vespa_app = vespa_docker.deploy(application_package=app_package)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eebef70c",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "We can add some metadata fields in the documents:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b21efbfa",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "# Add metadata\n",
    "for i, doc in enumerate(docs):\n",
    "    doc.metadata[\"date\"] = f\"2023-{(i % 12)+1}-{(i % 28)+1}\"\n",
    "    doc.metadata[\"rating\"] = range(1, 6)[i % 5]\n",
    "    doc.metadata[\"author\"] = [\"Joe Biden\", \"Unknown\"][min(i, 1)]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9b42bd4d",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "And let the Vespa vector store know about these fields:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6bb272f6",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "vespa_config.update(dict(metadata_fields=[\"date\", \"rating\", \"author\"]))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "43818655",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Now, when searching for these documents, these fields will be returned.\n",
    "Also, these fields can be filtered on:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "831759f3",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "db = VespaStore.from_documents(docs, embedding_function, app=vespa_app, **vespa_config)\n",
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "results = db.similarity_search(query, filter=\"rating > 3\")\n",
    "# results[0].metadata[\"id\"] == \"id:testapp:testapp::34\"\n",
    "# results[0].metadata[\"author\"] == \"Unknown\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a49aad6e",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Custom query\n",
    "\n",
    "If the default behavior of the similarity search does not fit your\n",
    "requirements, you can always provide your own query. Thus, you don't\n",
    "need to provide all of the configuration to the vector store, but\n",
    "rather just write this yourself.\n",
    "\n",
    "First, let's add a BM25 ranking function to our application:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d0fb0562",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from vespa.package import FieldSet\n",
    "\n",
    "app_package.schema.add_field_set(FieldSet(name=\"default\", fields=[\"text\"]))\n",
    "app_package.schema.add_rank_profile(RankProfile(name=\"bm25\", first_phase=\"bm25(text)\"))\n",
    "vespa_app = vespa_docker.deploy(application_package=app_package)\n",
    "db = VespaStore.from_documents(docs, embedding_function, app=vespa_app, **vespa_config)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fe607747",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Then, to perform a regular text search based on BM25:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cee245c3",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "custom_query = {\n",
    "    \"yql\": \"select * from sources * where userQuery()\",\n",
    "    \"query\": query,\n",
    "    \"type\": \"weakAnd\",\n",
    "    \"ranking\": \"bm25\",\n",
    "    \"hits\": 4,\n",
    "}\n",
    "results = db.similarity_search_with_score(query, custom_query=custom_query)\n",
    "# results[0][0].metadata[\"id\"] == \"id:testapp:testapp::32\"\n",
    "# results[0][1] ~= 14.384"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "41a4c081",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "All of the powerful search and query capabilities of Vespa can be used\n",
    "by using a custom query. Please refer to the Vespa documentation on it's\n",
    "[Query API](https://docs.vespa.ai/en/query-api.html) for more details.\n",
    "\n",
    "### Hybrid search\n",
    "\n",
    "Hybrid search means using both a classic term-based search such as\n",
    "BM25 and a vector search and combining the results. We need to create\n",
    "a new rank profile for hybrid search on Vespa:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bf73efc1",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "app_package.schema.add_rank_profile(\n",
    "    RankProfile(\n",
    "        name=\"hybrid\",\n",
    "        first_phase=\"log(bm25(text)) + 0.5 * closeness(field, embedding)\",\n",
    "        inputs=[(\"query(query_embedding)\", \"tensor<float>(x[384])\")],\n",
    "    )\n",
    ")\n",
    "vespa_app = vespa_docker.deploy(application_package=app_package)\n",
    "db = VespaStore.from_documents(docs, embedding_function, app=vespa_app, **vespa_config)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "40f48711",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Here, we score each document as a combination of it's BM25 score and its\n",
    "distance score. We can query using a custom query:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d2e289f0",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "query_embedding = embedding_function.embed_query(query)\n",
    "nearest_neighbor_expression = (\n",
    "    \"{targetHits: 4}nearestNeighbor(embedding, query_embedding)\"\n",
    ")\n",
    "custom_query = {\n",
    "    \"yql\": f\"select * from sources * where {nearest_neighbor_expression} and userQuery()\",\n",
    "    \"query\": query,\n",
    "    \"type\": \"weakAnd\",\n",
    "    \"input.query(query_embedding)\": query_embedding,\n",
    "    \"ranking\": \"hybrid\",\n",
    "    \"hits\": 4,\n",
    "}\n",
    "results = db.similarity_search_with_score(query, custom_query=custom_query)\n",
    "# results[0][0].metadata[\"id\"], \"id:testapp:testapp::32\")\n",
    "# results[0][1] ~= 2.897"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "958e269f",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Native embedders in Vespa\n",
    "\n",
    "Up until this point we've used an embedding function in Python to provide\n",
    "embeddings for the texts. Vespa supports embedding function natively, so\n",
    "you can defer this calculation in to Vespa. One benefit is the ability to use\n",
    "GPUs when embedding documents if you have a large collections.\n",
    "\n",
    "Please refer to [Vespa embeddings](https://docs.vespa.ai/en/embedding.html)\n",
    "for more information.\n",
    "\n",
    "First, we need to modify our application package:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "56b9686c",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from vespa.package import Component, Parameter\n",
    "\n",
    "app_package.components = [\n",
    "    Component(\n",
    "        id=\"hf-embedder\",\n",
    "        type=\"hugging-face-embedder\",\n",
    "        parameters=[\n",
    "            Parameter(\"transformer-model\", {\"path\": \"...\"}),\n",
    "            Parameter(\"tokenizer-model\", {\"url\": \"...\"}),\n",
    "        ],\n",
    "    )\n",
    "]\n",
    "Field(\n",
    "    name=\"hfembedding\",\n",
    "    type=\"tensor<float>(x[384])\",\n",
    "    is_document_field=False,\n",
    "    indexing=[\"input text\", \"embed hf-embedder\", \"attribute\", \"summary\"],\n",
    "    attribute=[\"distance-metric: angular\"],\n",
    ")\n",
    "app_package.schema.add_rank_profile(\n",
    "    RankProfile(\n",
    "        name=\"hf_similarity\",\n",
    "        first_phase=\"closeness(field, hfembedding)\",\n",
    "        inputs=[(\"query(query_embedding)\", \"tensor<float>(x[384])\")],\n",
    "    )\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5cd721a8",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Please refer to the embeddings documentation on adding embedder models\n",
    "and tokenizers to the application. Note that the `hfembedding` field\n",
    "includes instructions for embedding using the `hf-embedder`.\n",
    "\n",
    "Now we can query with a custom query:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "da631d13",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "nearest_neighbor_expression = (\n",
    "    \"{targetHits: 4}nearestNeighbor(internalembedding, query_embedding)\"\n",
    ")\n",
    "custom_query = {\n",
    "    \"yql\": f\"select * from sources * where {nearest_neighbor_expression}\",\n",
    "    \"input.query(query_embedding)\": f'embed(hf-embedder, \"{query}\")',\n",
    "    \"ranking\": \"internal_similarity\",\n",
    "    \"hits\": 4,\n",
    "}\n",
    "results = db.similarity_search_with_score(query, custom_query=custom_query)\n",
    "# results[0][0].metadata[\"id\"], \"id:testapp:testapp::32\")\n",
    "# results[0][1] ~= 0.630"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a333b553",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Note that the query here includes an `embed` instruction to embed the query\n",
    "using the same model as for the documents.\n",
    "\n",
    "### Approximate nearest neighbor\n",
    "\n",
    "In all of the above examples, we've used exact nearest neighbor to\n",
    "find results. However, for large collections of documents this is\n",
    "not feasible as one has to scan through all documents to find the\n",
    "best matches. To avoid this, we can use\n",
    "[approximate nearest neighbors](https://docs.vespa.ai/en/approximate-nn-hnsw.html).\n",
    "\n",
    "First, we can change the embedding field to create a HNSW index:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9ee955c8",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from vespa.package import HNSW\n",
    "\n",
    "app_package.schema.add_fields(\n",
    "    Field(\n",
    "        name=\"embedding\",\n",
    "        type=\"tensor<float>(x[384])\",\n",
    "        indexing=[\"attribute\", \"summary\", \"index\"],\n",
    "        ann=HNSW(\n",
    "            distance_metric=\"angular\",\n",
    "            max_links_per_node=16,\n",
    "            neighbors_to_explore_at_insert=200,\n",
    "        ),\n",
    "    )\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2ed1c224",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "This creates a HNSW index on the embedding data which allows for efficient\n",
    "searching. With this set, we can easily search using ANN by setting\n",
    "the `approximate` argument to `True`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7981739a",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "results = db.similarity_search(query, approximate=True)\n",
    "# results[0][0].metadata[\"id\"], \"id:testapp:testapp::32\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "24791204",
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "This covers most of the functionality in the Vespa vector store in LangChain.\n",
    "\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}