diff --git a/docs/modules/indexes/retrievers/examples/weaviate_self_query.ipynb b/docs/modules/indexes/retrievers/examples/weaviate_self_query.ipynb new file mode 100644 index 00000000..07242280 --- /dev/null +++ b/docs/modules/indexes/retrievers/examples/weaviate_self_query.ipynb @@ -0,0 +1,277 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "13afcae7", + "metadata": {}, + "source": [ + "# Self-querying with Weaviate" + ] + }, + { + "cell_type": "markdown", + "id": "68e75fb9", + "metadata": {}, + "source": [ + "## Creating a Weaviate vectorstore\n", + "First we'll want to create a Weaviate VectorStore 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 `weaviate-client` package." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "63a8af5b", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "#!pip install lark weaviate-client" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "cb4a5787", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "from langchain.schema import Document\n", + "from langchain.embeddings.openai import OpenAIEmbeddings\n", + "from langchain.vectorstores import Weaviate\n", + "import os\n", + "\n", + "embeddings = OpenAIEmbeddings()" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "bcbe04d9", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "docs = [\n", + " 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=\"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=\"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}),\n", + " 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}),\n", + " Document(page_content=\"Toys come alive and have a blast doing so\", metadata={\"year\": 1995, \"genre\": \"animated\"}),\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\", \"rating\": 9.9})\n", + "]\n", + "vectorstore = Weaviate.from_documents(\n", + " docs, embeddings, weaviate_url=\"http://127.0.0.1:8080\"\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": 23, + "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\",\n", + " description=\"A 1-10 rating for the movie\",\n", + " type=\"float\"\n", + " ),\n", + "]\n", + "document_content_description = \"Brief summary of a movie\"\n", + "llm = OpenAI(temperature=0)\n", + "retriever = SelfQueryRetriever.from_llm(llm, vectorstore, document_content_description, metadata_field_info, verbose=True)" + ] + }, + { + "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": 24, + "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={'genre': 'science fiction', 'rating': 7.7, 'year': 1993}),\n", + " Document(page_content='Toys come alive and have a blast doing so', metadata={'genre': 'animated', 'rating': None, 'year': 1995}),\n", + " Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'genre': 'science fiction', 'rating': 9.9, 'year': 1979}),\n", + " Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'genre': None, 'rating': 8.6, 'year': 2006})]" + ] + }, + "execution_count": 24, + "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": 26, + "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={'genre': None, 'rating': 8.3, 'year': 2019})]" + ] + }, + "execution_count": 26, + "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": "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": 27, + "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": 28, + "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={'genre': 'science fiction', 'rating': 7.7, 'year': 1993}),\n", + " Document(page_content='Toys come alive and have a blast doing so', metadata={'genre': 'animated', 'rating': None, 'year': 1995})]" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# This example only specifies a relevant query\n", + "retriever.get_relevant_documents(\"what are two movies about dinosaurs\")" + ] + } + ], + "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": "3.8.10" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/langchain/retrievers/self_query/base.py b/langchain/retrievers/self_query/base.py index ffe45721..ccd69f6c 100644 --- a/langchain/retrievers/self_query/base.py +++ b/langchain/retrievers/self_query/base.py @@ -10,8 +10,9 @@ from langchain.chains.query_constructor.ir import StructuredQuery, Visitor from langchain.chains.query_constructor.schema import AttributeInfo from langchain.retrievers.self_query.chroma import ChromaTranslator from langchain.retrievers.self_query.pinecone import PineconeTranslator +from langchain.retrievers.self_query.weaviate import WeaviateTranslator from langchain.schema import BaseRetriever, Document -from langchain.vectorstores import Chroma, Pinecone, VectorStore +from langchain.vectorstores import Chroma, Pinecone, VectorStore, Weaviate def _get_builtin_translator(vectorstore_cls: Type[VectorStore]) -> Visitor: @@ -19,6 +20,7 @@ def _get_builtin_translator(vectorstore_cls: Type[VectorStore]) -> Visitor: BUILTIN_TRANSLATORS: Dict[Type[VectorStore], Type[Visitor]] = { Pinecone: PineconeTranslator, Chroma: ChromaTranslator, + Weaviate: WeaviateTranslator, } if vectorstore_cls not in BUILTIN_TRANSLATORS: raise ValueError( diff --git a/langchain/retrievers/self_query/weaviate.py b/langchain/retrievers/self_query/weaviate.py new file mode 100644 index 00000000..e1faf7d4 --- /dev/null +++ b/langchain/retrievers/self_query/weaviate.py @@ -0,0 +1,60 @@ +"""Logic for converting internal query language to a valid Weaviate query.""" +from typing import Dict, Tuple, Union + +from langchain.chains.query_constructor.ir import ( + Comparator, + Comparison, + Operation, + Operator, + StructuredQuery, + Visitor, +) + + +class WeaviateTranslator(Visitor): + """Logic for converting internal query language elements to valid filters.""" + + allowed_operators = [Operator.AND, Operator.OR] + """Subset of allowed logical operators.""" + + allowed_comparators = [Comparator.EQ] + + def _map_func(self, func: Union[Operator, Comparator]) -> str: + # https://weaviate.io/developers/weaviate/api/graphql/filters + map_dict = {Operator.AND: "And", Operator.OR: "Or", Comparator.EQ: "Equal"} + return map_dict[func] + + def _format_func(self, func: Union[Operator, Comparator]) -> str: + if isinstance(func, Operator) and self.allowed_operators is not None: + if func not in self.allowed_operators: + raise ValueError( + f"Received disallowed operator {func}. Allowed " + f"comparators are {self.allowed_operators}" + ) + if isinstance(func, Comparator) and self.allowed_comparators is not None: + if func not in self.allowed_comparators: + raise ValueError( + f"Received disallowed comparator {func}. Allowed " + f"comparators are {self.allowed_comparators}" + ) + return self._map_func(func) + + def visit_operation(self, operation: Operation) -> Dict: + args = [arg.accept(self) for arg in operation.arguments] + return {"operator": self._format_func(operation.operator), "operands": args} + + def visit_comparison(self, comparison: Comparison) -> Dict: + return { + "path": [comparison.attribute], + "operator": self._format_func(comparison.comparator), + "valueText": comparison.value, + } + + def visit_structured_query( + self, structured_query: StructuredQuery + ) -> Tuple[str, dict]: + if structured_query.filter is None: + kwargs = {} + else: + kwargs = {"where_filter": structured_query.filter.accept(self)} + return structured_query.query, kwargs