community[minor]: Add SelfQueryRetriever support to PGVector (#16991)

- **Description:** Add SelfQueryRetriever support to PGVector
  - **Issue:** -
  - **Dependencies:** -
  - **Twitter handle:** -

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>

docs/docs/integrations/retrievers/self_query/pgvector_self_query.ipynb

@@ -0,0 +1,308 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "13afcae7",
+   "metadata": {},
+   "source": [
+    "# PGVector\n",
+    "\n",
+    ">[PGVector](https://github.com/pgvector/pgvector) is a vector similarity search for Postgres.\n",
+    "\n",
+    "In the notebook, we'll demo the `SelfQueryRetriever` wrapped around a `PGVector` vector store."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "68e75fb9",
+   "metadata": {},
+   "source": [
+    "## Creating a PGVector vector store\n",
+    "First we'll want to create a PGVector 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 `` package."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "63a8af5b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  lark pgvector psycopg2-binary"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "83811610-7df3-4ede-b268-68a6a83ba9e2",
+   "metadata": {},
+   "source": [
+    "We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dd01b61b-7d32-4a55-85d6-b2d2d4f18840",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb4a5787",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.schema import Document\n",
+    "from langchain_community.vectorstores import PGVector\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "collection = \"Name of your collection\"\n",
+    "embeddings = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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",
+    "            \"director\": \"Andrei Tarkovsky\",\n",
+    "            \"genre\": \"science fiction\",\n",
+    "            \"rating\": 9.9,\n",
+    "        },\n",
+    "    ),\n",
+    "]\n",
+    "vectorstore = PGVector.from_documents(\n",
+    "    docs,\n",
+    "    embeddings,\n",
+    "    collection_name=collection,\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": 6,
+   "id": "86e34dbf",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chains.query_constructor.base import AttributeInfo\n",
+    "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
+    "from langchain_openai import OpenAI\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": null,
+   "id": "38a126e9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This example only specifies a relevant query\n",
+    "retriever.get_relevant_documents(\"What are some movies about dinosaurs\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fc3f1e6e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This example only specifies a filter\n",
+    "retriever.get_relevant_documents(\"I want to watch a movie rated higher than 8.5\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b19d4da0",
+   "metadata": {},
+   "outputs": [],
+   "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": null,
+   "id": "f900e40e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This example specifies a composite filter\n",
+    "retriever.get_relevant_documents(\n",
+    "    \"What's a highly rated (above 8.5) science fiction film?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "12a51522",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This example specifies a query and composite filter\n",
+    "retriever.get_relevant_documents(\n",
+    "    \"What's a movie after 1990 but before 2005 that's all about toys, and preferably is animated\"\n",
+    ")"
+   ]
+  },
+  {
+   "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": 7,
+   "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": null,
+   "id": "2758d229-4f97-499c-819f-888acaf8ee10",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "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": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

libs/langchain/langchain/retrievers/self_query/base.py

@@ -12,6 +12,7 @@ from langchain_community.vectorstores import (
     MongoDBAtlasVectorSearch,
     MyScale,
     OpenSearchVectorSearch,
+    PGVector,
     Pinecone,
     Qdrant,
     Redis,
@@ -43,6 +44,7 @@ from langchain.retrievers.self_query.milvus import MilvusTranslator
 from langchain.retrievers.self_query.mongodb_atlas import MongoDBAtlasTranslator
 from langchain.retrievers.self_query.myscale import MyScaleTranslator
 from langchain.retrievers.self_query.opensearch import OpenSearchTranslator
+from langchain.retrievers.self_query.pgvector import PGVectorTranslator
 from langchain.retrievers.self_query.pinecone import PineconeTranslator
 from langchain.retrievers.self_query.qdrant import QdrantTranslator
 from langchain.retrievers.self_query.redis import RedisTranslator
@@ -58,6 +60,7 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
     """Get the translator class corresponding to the vector store class."""
     BUILTIN_TRANSLATORS: Dict[Type[VectorStore], Type[Visitor]] = {
         AstraDB: AstraDBTranslator,
+        PGVector: PGVectorTranslator,
         Pinecone: PineconeTranslator,
         Chroma: ChromaTranslator,
         DashVector: DashvectorTranslator,

libs/langchain/langchain/retrievers/self_query/pgvector.py

@@ -0,0 +1,52 @@
+from typing import Dict, Tuple, Union
+
+from langchain.chains.query_constructor.ir import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+    Visitor,
+)
+
+
+class PGVectorTranslator(Visitor):
+    """Translate `PGVector` internal query language elements to valid filters."""
+
+    allowed_operators = [Operator.AND, Operator.OR]
+    """Subset of allowed logical operators."""
+    allowed_comparators = [
+        Comparator.EQ,
+        Comparator.NE,
+        Comparator.GT,
+        Comparator.LT,
+        Comparator.IN,
+        Comparator.NIN,
+        Comparator.CONTAIN,
+        Comparator.LIKE,
+    ]
+    """Subset of allowed logical comparators."""
+
+    def _format_func(self, func: Union[Operator, Comparator]) -> str:
+        self._validate_func(func)
+        return f"{func.value}"
+
+    def visit_operation(self, operation: Operation) -> Dict:
+        args = [arg.accept(self) for arg in operation.arguments]
+        return {self._format_func(operation.operator): args}
+
+    def visit_comparison(self, comparison: Comparison) -> Dict:
+        return {
+            comparison.attribute: {
+                self._format_func(comparison.comparator): 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

libs/langchain/tests/unit_tests/retrievers/self_query/test_pgvector.py

@@ -0,0 +1,87 @@
+from typing import Dict, Tuple
+
+import pytest as pytest
+
+from langchain.chains.query_constructor.ir import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+)
+from langchain.retrievers.self_query.pgvector import PGVectorTranslator
+
+DEFAULT_TRANSLATOR = PGVectorTranslator()
+
+
+def test_visit_comparison() -> None:
+    comp = Comparison(comparator=Comparator.LT, attribute="foo", value=1)
+    expected = {"foo": {"lt": 1}}
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+@pytest.mark.skip("Not implemented")
+def test_visit_operation() -> None:
+    op = Operation(
+        operator=Operator.AND,
+        arguments=[
+            Comparison(comparator=Comparator.LT, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+            Comparison(comparator=Comparator.GT, attribute="abc", value=2.0),
+        ],
+    )
+    expected = {
+        "foo": {"lt": 2},
+        "bar": {"eq": "baz"},
+        "abc": {"gt": 2.0},
+    }
+    actual = DEFAULT_TRANSLATOR.visit_operation(op)
+    assert expected == actual
+
+
+def test_visit_structured_query() -> None:
+    query = "What is the capital of France?"
+    structured_query = StructuredQuery(
+        query=query,
+        filter=None,
+    )
+    expected: Tuple[str, Dict] = (query, {})
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual
+
+    comp = Comparison(comparator=Comparator.LT, attribute="foo", value=1)
+    structured_query = StructuredQuery(
+        query=query,
+        filter=comp,
+    )
+    expected = (query, {"filter": {"foo": {"lt": 1}}})
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual
+
+    op = Operation(
+        operator=Operator.AND,
+        arguments=[
+            Comparison(comparator=Comparator.LT, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+            Comparison(comparator=Comparator.GT, attribute="abc", value=2.0),
+        ],
+    )
+    structured_query = StructuredQuery(
+        query=query,
+        filter=op,
+    )
+    expected = (
+        query,
+        {
+            "filter": {
+                "and": [
+                    {"foo": {"lt": 2}},
+                    {"bar": {"eq": "baz"}},
+                    {"abc": {"gt": 2.0}},
+                ]
+            }
+        },
+    )
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual