diff --git a/docs/extras/modules/data_connection/retrievers/self_query/opensearch_self_query.ipynb b/docs/extras/modules/data_connection/retrievers/self_query/opensearch_self_query.ipynb new file mode 100644 index 0000000000..947960c217 --- /dev/null +++ b/docs/extras/modules/data_connection/retrievers/self_query/opensearch_self_query.ipynb @@ -0,0 +1,439 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "13afcae7", + "metadata": {}, + "source": [ + "# OpenSearch\n", + "\n", + "> [OpenSearch](https://opensearch.org/) is a scalable, flexible, and extensible open-source software suite for search, analytics, and observability applications licensed under Apache 2.0. `OpenSearch` is a distributed search and analytics engine based on `Apache Lucene`.\n", + "\n", + "In this notebook, we'll demo the `SelfQueryRetriever` with an `OpenSearch` vector store." + ] + }, + { + "cell_type": "markdown", + "id": "68e75fb9", + "metadata": {}, + "source": [ + "## Creating an OpenSearch vector store\n", + "\n", + "First, we'll want to create an `OpenSearch` vector store and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n", + "\n", + "**Note:** The self-query retriever requires you to have `lark` installed (`pip install lark`). We also need the `opensearch-py` package." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "outputs": [], + "source": [ + "!pip install lark opensearch-py" + ], + "metadata": { + "collapsed": false, + "pycharm": { + "name": "#%%\n" + } + } + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "cb4a5787", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stdin", + "output_type": "stream", + "text": [ + "OpenAI API Key: ········\n" + ] + } + ], + "source": [ + "from langchain.schema import Document\n", + "from langchain.embeddings.openai import OpenAIEmbeddings\n", + "from langchain.vectorstores import OpenSearchVectorSearch\n", + "import os\n", + "import getpass\n", + "\n", + "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n", + "\n", + "embeddings = OpenAIEmbeddings()" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "bcbe04d9", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "docs = [\n", + " Document(\n", + " page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n", + " metadata={\"year\": 1993, \"rating\": 7.7, \"genre\": \"science fiction\"},\n", + " ),\n", + " Document(\n", + " page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\",\n", + " metadata={\"year\": 2010, \"director\": \"Christopher Nolan\", \"rating\": 8.2},\n", + " ),\n", + " Document(\n", + " page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n", + " metadata={\"year\": 2006, \"director\": \"Satoshi Kon\", \"rating\": 8.6},\n", + " ),\n", + " Document(\n", + " page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n", + " metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"rating\": 8.3},\n", + " ),\n", + " Document(\n", + " page_content=\"Toys come alive and have a blast doing so\",\n", + " metadata={\"year\": 1995, \"genre\": \"animated\"},\n", + " ),\n", + " Document(\n", + " page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n", + " metadata={\n", + " \"year\": 1979,\n", + " \"rating\": 9.9,\n", + " \"director\": \"Andrei Tarkovsky\",\n", + " \"genre\": \"science fiction\",\n", + " },\n", + " ),\n", + "]\n", + "vectorstore = OpenSearchVectorSearch.from_documents(\n", + " docs, embeddings, index_name=\"opensearch-self-query-demo\", opensearch_url=\"http://localhost:9200\"\n", + ")" + ] + }, + { + "cell_type": "markdown", + "id": "5ecaab6d", + "metadata": {}, + "source": [ + "## Creating our self-querying retriever\n", + "Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "86e34dbf", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "from langchain.llms import OpenAI\n", + "from langchain.retrievers.self_query.base import SelfQueryRetriever\n", + "from langchain.chains.query_constructor.base import AttributeInfo\n", + "\n", + "metadata_field_info = [\n", + " AttributeInfo(\n", + " name=\"genre\",\n", + " description=\"The genre of the movie\",\n", + " type=\"string or list[string]\",\n", + " ),\n", + " AttributeInfo(\n", + " name=\"year\",\n", + " description=\"The year the movie was released\",\n", + " type=\"integer\",\n", + " ),\n", + " AttributeInfo(\n", + " name=\"director\",\n", + " description=\"The name of the movie director\",\n", + " type=\"string\",\n", + " ),\n", + " AttributeInfo(\n", + " name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n", + " ),\n", + "]\n", + "document_content_description = \"Brief summary of a movie\"\n", + "llm = OpenAI(temperature=0)\n", + "retriever = SelfQueryRetriever.from_llm(\n", + " llm, vectorstore, document_content_description, metadata_field_info, verbose=True\n", + ")" + ] + }, + { + "cell_type": "markdown", + "id": "ea9df8d4", + "metadata": {}, + "source": [ + "## Testing it out\n", + "And now we can try actually using our retriever!" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "38a126e9", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "query='dinosaur' filter=None limit=None\n" + ] + }, + { + "data": { + "text/plain": [ + "[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}),\n", + " Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),\n", + " Document(page_content='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'year': 2010, 'director': 'Christopher Nolan', 'rating': 8.2}),\n", + " Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'rating': 9.9, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction'})]" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# This example only specifies a relevant query\n", + "retriever.get_relevant_documents(\"What are some movies about dinosaurs\")" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "60bf0074-e65e-4558-a4f2-8190f3e4e2f9", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "query=' ' filter=Comparison(comparator=, attribute='rating', value=8.5) limit=None\n" + ] + }, + { + "data": { + "text/plain": [ + "[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'rating': 9.9, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction'}),\n", + " Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006, 'director': 'Satoshi Kon', 'rating': 8.6})]" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# This example only specifies a filter\n", + "retriever.get_relevant_documents(\"I want to watch a movie rated higher than 8.5\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "b19d4da0", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "query='women' filter=Comparison(comparator=, attribute='director', value='Greta Gerwig') limit=None\n" + ] + }, + { + "data": { + "text/plain": [ + "[Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'year': 2019, 'director': 'Greta Gerwig', 'rating': 8.3})]" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# This example specifies a query and a filter\n", + "retriever.get_relevant_documents(\"Has Greta Gerwig directed any movies about women\")" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "a59f946b-78a1-4d3e-9942-63834c7d7589", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "query=' ' filter=Operation(operator=, arguments=[Comparison(comparator=, attribute='rating', value=8.5), Comparison(comparator=, attribute='genre', value='science fiction')]) limit=None\n" + ] + }, + { + "data": { + "text/plain": [ + "[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'rating': 9.9, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction'})]" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# This example specifies a composite filter\n", + "retriever.get_relevant_documents(\"What's a highly rated (above 8.5) science fiction film?\")" + ] + }, + { + "cell_type": "markdown", + "id": "39bd1de1-b9fe-4a98-89da-58d8a7a6ae51", + "metadata": {}, + "source": [ + "## Filter k\n", + "\n", + "We can also use the self query retriever to specify `k`: the number of documents to fetch.\n", + "\n", + "We can do this by passing `enable_limit=True` to the constructor." + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "bff36b88-b506-4877-9c63-e5a1a8d78e64", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "retriever = SelfQueryRetriever.from_llm(\n", + " llm,\n", + " vectorstore,\n", + " document_content_description,\n", + " metadata_field_info,\n", + " enable_limit=True,\n", + " verbose=True,\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "2758d229-4f97-499c-819f-888acaf8ee10", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "query='dinosaur' filter=None limit=2\n" + ] + }, + { + "data": { + "text/plain": [ + "[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}),\n", + " Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# This example only specifies a relevant query\n", + "retriever.get_relevant_documents(\"what are two movies about dinosaurs\")" + ] + }, + { + "cell_type": "markdown", + "id": "61a10294", + "metadata": {}, + "source": [ + "## Complex queries in Action!\n", + "We've tried out some simple queries, but what about more complex ones? Let's try out a few more complex queries that utilize the full power of OpenSearch." + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "e460da93", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "query='animated toys' filter=Operation(operator=, arguments=[Operation(operator=, arguments=[Comparison(comparator=, attribute='genre', value='animated'), Comparison(comparator=, attribute='genre', value='comedy')]), Comparison(comparator=, attribute='year', value=1990)]) limit=None\n" + ] + }, + { + "data": { + "text/plain": [ + "[Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "retriever.get_relevant_documents(\"what animated or comedy movies have been released in the last 30 years about animated toys?\")" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "0851fc42", + "metadata": { + "pycharm": { + "name": "#%%\n" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "{'acknowledged': True}" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "vectorstore.client.indices.delete(index=\"opensearch-self-query-demo\")\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": "3.9.18" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} \ No newline at end of file diff --git a/libs/langchain/langchain/retrievers/self_query/base.py b/libs/langchain/langchain/retrievers/self_query/base.py index 1ebf72a4da..713a461099 100644 --- a/libs/langchain/langchain/retrievers/self_query/base.py +++ b/libs/langchain/langchain/retrievers/self_query/base.py @@ -14,6 +14,7 @@ from langchain.retrievers.self_query.deeplake import DeepLakeTranslator from langchain.retrievers.self_query.elasticsearch import ElasticsearchTranslator from langchain.retrievers.self_query.milvus import MilvusTranslator from langchain.retrievers.self_query.myscale import MyScaleTranslator +from langchain.retrievers.self_query.opensearch import OpenSearchTranslator from langchain.retrievers.self_query.pinecone import PineconeTranslator from langchain.retrievers.self_query.qdrant import QdrantTranslator from langchain.retrievers.self_query.redis import RedisTranslator @@ -30,6 +31,7 @@ from langchain.vectorstores import ( ElasticsearchStore, Milvus, MyScale, + OpenSearchVectorSearch, Pinecone, Qdrant, Redis, @@ -56,6 +58,7 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor: Milvus: MilvusTranslator, SupabaseVectorStore: SupabaseVectorTranslator, TimescaleVector: TimescaleVectorTranslator, + OpenSearchVectorSearch: OpenSearchTranslator, } if isinstance(vectorstore, Qdrant): return QdrantTranslator(metadata_key=vectorstore.metadata_payload_key) diff --git a/libs/langchain/langchain/retrievers/self_query/opensearch.py b/libs/langchain/langchain/retrievers/self_query/opensearch.py new file mode 100644 index 0000000000..502ee8a872 --- /dev/null +++ b/libs/langchain/langchain/retrievers/self_query/opensearch.py @@ -0,0 +1,84 @@ +from typing import Dict, Tuple, Union + +from langchain.chains.query_constructor.ir import ( + Comparator, + Comparison, + Operation, + Operator, + StructuredQuery, + Visitor, +) + + +class OpenSearchTranslator(Visitor): + """Translate `OpenSearch` internal query domain-specific + language elements to valid filters.""" + + allowed_comparators = [ + Comparator.EQ, + Comparator.LT, + Comparator.LTE, + Comparator.GT, + Comparator.GTE, + Comparator.CONTAIN, + Comparator.LIKE, + ] + """Subset of allowed logical comparators.""" + + allowed_operators = [Operator.AND, Operator.OR, Operator.NOT] + """Subset of allowed logical operators.""" + + def _format_func(self, func: Union[Operator, Comparator]) -> str: + self._validate_func(func) + comp_operator_map = { + Comparator.EQ: "term", + Comparator.LT: "lt", + Comparator.LTE: "lte", + Comparator.GT: "gt", + Comparator.GTE: "gte", + Comparator.CONTAIN: "match", + Comparator.LIKE: "fuzzy", + Operator.AND: "must", + Operator.OR: "should", + Operator.NOT: "must_not", + } + return comp_operator_map[func] + + def visit_operation(self, operation: Operation) -> Dict: + args = [arg.accept(self) for arg in operation.arguments] + + return {"bool": {self._format_func(operation.operator): args}} + + def visit_comparison(self, comparison: Comparison) -> Dict: + field = f"metadata.{comparison.attribute}" + + if comparison.comparator in [ + Comparator.LT, + Comparator.LTE, + Comparator.GT, + Comparator.GTE, + ]: + return { + "range": { + field: {self._format_func(comparison.comparator): comparison.value} + } + } + + if comparison.comparator == Comparator.LIKE: + return { + self._format_func(comparison.comparator): { + field: {"value": comparison.value} + } + } + field = f"{field}.keyword" if isinstance(comparison.value, str) else field + + return {self._format_func(comparison.comparator): {field: comparison.value}} + + def visit_structured_query( + self, structured_query: StructuredQuery + ) -> Tuple[str, dict]: + if structured_query.filter is None: + kwargs = {} + else: + kwargs = {"filter": structured_query.filter.accept(self)} + return structured_query.query, kwargs diff --git a/libs/langchain/langchain/vectorstores/opensearch_vector_search.py b/libs/langchain/langchain/vectorstores/opensearch_vector_search.py index 0c3117ba58..74437d6d86 100644 --- a/libs/langchain/langchain/vectorstores/opensearch_vector_search.py +++ b/libs/langchain/langchain/vectorstores/opensearch_vector_search.py @@ -341,6 +341,7 @@ class OpenSearchVectorSearch(VectorStore): http_auth = _get_kwargs_value(kwargs, "http_auth", None) self.is_aoss = _is_aoss_enabled(http_auth=http_auth) self.client = _get_opensearch_client(opensearch_url, **kwargs) + self.engine = _get_kwargs_value(kwargs, "engine", None) @property def embeddings(self) -> Embeddings: @@ -528,6 +529,7 @@ class OpenSearchVectorSearch(VectorStore): search_type = _get_kwargs_value(kwargs, "search_type", "approximate_search") vector_field = _get_kwargs_value(kwargs, "vector_field", "vector_field") index_name = _get_kwargs_value(kwargs, "index_name", self.index_name) + filter = _get_kwargs_value(kwargs, "filter", {}) if ( self.is_aoss @@ -564,6 +566,17 @@ class OpenSearchVectorSearch(VectorStore): "is invalid. `lucene_filter` is deprecated" ) + if ( + efficient_filter == {} + and boolean_filter == {} + and lucene_filter == {} + and filter != {} + ): + if self.engine in ["faiss", "lucene"]: + efficient_filter = filter + else: + boolean_filter = filter + if boolean_filter != {}: search_query = _approximate_search_query_with_boolean_filter( embedding, @@ -745,6 +758,7 @@ class OpenSearchVectorSearch(VectorStore): max_chunk_bytes = _get_kwargs_value(kwargs, "max_chunk_bytes", 1 * 1024 * 1024) http_auth = _get_kwargs_value(kwargs, "http_auth", None) is_aoss = _is_aoss_enabled(http_auth=http_auth) + engine = None if is_aoss and not is_appx_search: raise ValueError( @@ -782,4 +796,5 @@ class OpenSearchVectorSearch(VectorStore): max_chunk_bytes=max_chunk_bytes, is_aoss=is_aoss, ) + kwargs["engine"] = engine return cls(opensearch_url, index_name, embedding, **kwargs) diff --git a/libs/langchain/tests/unit_tests/retrievers/self_query/test_opensearch.py b/libs/langchain/tests/unit_tests/retrievers/self_query/test_opensearch.py new file mode 100644 index 0000000000..629d195402 --- /dev/null +++ b/libs/langchain/tests/unit_tests/retrievers/self_query/test_opensearch.py @@ -0,0 +1,87 @@ +from langchain.chains.query_constructor.ir import ( + Comparator, + Comparison, + Operation, + Operator, + StructuredQuery, +) +from langchain.retrievers.self_query.opensearch import OpenSearchTranslator + +DEFAULT_TRANSLATOR = OpenSearchTranslator() + + +def test_visit_comparison() -> None: + comp = Comparison(comparator=Comparator.EQ, attribute="foo", value="10") + expected = {"term": {"metadata.foo.keyword": "10"}} + actual = DEFAULT_TRANSLATOR.visit_comparison(comp) + assert expected == actual + + +def test_visit_operation() -> None: + op = Operation( + operator=Operator.AND, + arguments=[ + Comparison(comparator=Comparator.GTE, attribute="bar", value=5), + Comparison(comparator=Comparator.LT, attribute="bar", value=10), + Comparison(comparator=Comparator.EQ, attribute="baz", value="abcd"), + ], + ) + expected = { + "bool": { + "must": [ + {"range": {"metadata.bar": {"gte": 5}}}, + {"range": {"metadata.bar": {"lt": 10}}}, + {"term": {"metadata.baz.keyword": "abcd"}}, + ] + } + } + actual = DEFAULT_TRANSLATOR.visit_operation(op) + assert expected == actual + + +def test_visit_structured_query() -> None: + query = "What is the capital of France?" + operation = Operation( + operator=Operator.AND, + arguments=[ + Comparison(comparator=Comparator.EQ, attribute="foo", value="20"), + Operation( + operator=Operator.OR, + arguments=[ + Comparison(comparator=Comparator.LTE, attribute="bar", value=7), + Comparison( + comparator=Comparator.LIKE, attribute="baz", value="abc" + ), + ], + ), + ], + ) + structured_query = StructuredQuery(query=query, filter=operation, limit=None) + expected = ( + query, + { + "filter": { + "bool": { + "must": [ + {"term": {"metadata.foo.keyword": "20"}}, + { + "bool": { + "should": [ + {"range": {"metadata.bar": {"lte": 7}}}, + { + "fuzzy": { + "metadata.baz": { + "value": "abc", + } + } + }, + ] + } + }, + ] + } + } + }, + ) + actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query) + assert expected == actual