add neo4j query constructor for self query (#25288)

- [x] **PR title - community: add neo4j query constructor for self
query**

- [x] **PR message**
- **Description:** adding a Neo4jTranslator so that the Neo4j vector
database can use SelfQueryRetriever
    - **Issue:** this issue had been raised before in #19748
    - **Dependencies:** none. 
    - **Twitter handle:** @moyi_dang
- p.s. I have not added the query constructor in BUILTIN_TRANSLATORS in
this PR, I want to make changes to only one package at a time.

- [x] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.


- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
This commit is contained in:
默奕 2024-08-30 07:54:33 -07:00 committed by GitHub
parent b5d670498f
commit 6377185291
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 556 additions and 0 deletions

View File

@ -0,0 +1,403 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Neo4j\n",
"\n",
">[Neo4j](https://neo4j.com/docs/) is a graph database that stores nodes and relationships, that also supports native vector search.\n",
"\n",
"In the notebook, we'll demo the `SelfQueryRetriever` wrapped around a `Neo4j` vector store. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Creating a Neo4j vector store\n",
"First we'll want to create a Neo4j vector store and seed it with some data. We've created a small demo set of documents that contain summaries of movies."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: neo4j in /Users/moyi/git/langchain/env/lib/python3.11/site-packages (5.24.0)\n",
"Requirement already satisfied: pytz in /Users/moyi/git/langchain/env/lib/python3.11/site-packages (from neo4j) (2024.1)\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"%pip install --upgrade neo4j"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdin",
"output_type": "stream",
"text": [
"OpenAI API Key: ········\n"
]
}
],
"source": [
"import getpass\n",
"import os\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdin",
"output_type": "stream",
"text": [
"Neo4j URL: ········\n",
"Neo4j User Name: ········\n",
"Neo4j Password: ········\n"
]
}
],
"source": [
"# To run this notebook, you can set up a free neo4j account on neo4j.com and input the following information.\n",
"# (If you are having trouble connecting to the database, try using neo4j+ssc: instead of neo4j+s)\n",
"\n",
"os.environ[\"NEO4J_URI\"] = getpass.getpass(\"Neo4j URL:\")\n",
"os.environ[\"NEO4J_USERNAME\"] = getpass.getpass(\"Neo4j User Name:\")\n",
"os.environ[\"NEO4J_PASSWORD\"] = getpass.getpass(\"Neo4j Password:\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.vectorstores import Neo4jVector\n",
"from langchain_core.documents import Document\n",
"from langchain_openai import OpenAIEmbeddings\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Received notification from DBMS server: {severity: WARNING} {code: Neo.ClientNotification.Statement.FeatureDeprecationWarning} {category: DEPRECATION} {title: This feature is deprecated and will be removed in future versions.} {description: CALL subquery without a variable scope clause is now deprecated. Use CALL (row) { ... }} {position: line: 1, column: 21, offset: 20} for query: \"UNWIND $data AS row CALL { WITH row MERGE (c:`Chunk` {id: row.id}) WITH c, row CALL db.create.setNodeVectorProperty(c, 'embedding', row.embedding) SET c.`text` = row.text SET c += row.metadata } IN TRANSACTIONS OF 1000 ROWS \"\n"
]
}
],
"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 = Neo4jVector.from_documents(docs, embeddings)"
]
},
{
"cell_type": "markdown",
"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,
"metadata": {},
"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",
"metadata": {},
"source": [
"## Testing it out\n",
"And now we can try actually using our retriever!"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(metadata={'genre': 'science fiction', 'year': 1993, 'rating': 7.7}, page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose'),\n",
" Document(metadata={'genre': 'animated', 'year': 1995}, page_content='Toys come alive and have a blast doing so'),\n",
" Document(metadata={'genre': 'science fiction', 'year': 1979, 'rating': 9.9, 'director': 'Andrei Tarkovsky'}, page_content='Three men walk into the Zone, three men walk out of the Zone'),\n",
" Document(metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'}, page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea')]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example only specifies a relevant query\n",
"retriever.invoke(\"What are some movies about dinosaurs\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(metadata={'genre': 'science fiction', 'year': 1979, 'rating': 9.9, 'director': 'Andrei Tarkovsky'}, page_content='Three men walk into the Zone, three men walk out of the Zone'),\n",
" Document(metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'}, page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea')]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example only specifies a filter\n",
"retriever.invoke(\"I want to watch a movie rated higher than 8.5\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(metadata={'year': 2019, 'rating': 8.3, 'director': 'Greta Gerwig'}, page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them')]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a query and a filter\n",
"retriever.invoke(\"Has Greta Gerwig directed any movies about women\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'}, page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea'),\n",
" Document(metadata={'genre': 'science fiction', 'year': 1979, 'rating': 9.9, 'director': 'Andrei Tarkovsky'}, page_content='Three men walk into the Zone, three men walk out of the Zone')]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a composite filter\n",
"retriever.invoke(\"What's a highly rated (above 8.5) science fiction film?\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(metadata={'genre': 'animated', 'year': 1995}, page_content='Toys come alive and have a blast doing so')]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a query and composite filter\n",
"retriever.invoke(\n",
" \"What's a movie after 1990 but before 2005 that's all about toys, and preferably is animated\"\n",
")"
]
},
{
"cell_type": "markdown",
"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": 12,
"metadata": {},
"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": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(metadata={'genre': 'science fiction', 'year': 1993, 'rating': 7.7}, page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose'),\n",
" Document(metadata={'genre': 'animated', 'year': 1995}, page_content='Toys come alive and have a blast doing so')]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example only specifies a relevant query\n",
"retriever.invoke(\"what are two movies about dinosaurs\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

View File

@ -0,0 +1,60 @@
from typing import Dict, Tuple, Union
from langchain_core.structured_query import (
Comparator,
Comparison,
Operation,
Operator,
StructuredQuery,
Visitor,
)
class Neo4jTranslator(Visitor):
"""Translate `Neo4j` 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.GTE,
Comparator.LTE,
Comparator.LT,
Comparator.GT,
]
def _format_func(self, func: Union[Operator, Comparator]) -> str:
self._validate_func(func)
map_dict = {
Operator.AND: "$and",
Operator.OR: "$or",
Comparator.EQ: "$eq",
Comparator.NE: "$ne",
Comparator.GTE: "$gte",
Comparator.LTE: "$lte",
Comparator.LT: "$lt",
Comparator.GT: "$gt",
}
return map_dict[func]
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

View File

@ -0,0 +1,90 @@
from typing import Dict, Tuple
from langchain_core.structured_query import (
Comparator,
Comparison,
Operation,
Operator,
StructuredQuery,
)
from langchain_community.query_constructors.neo4j import Neo4jTranslator
DEFAULT_TRANSLATOR = Neo4jTranslator()
def test_visit_comparison() -> None:
comp = Comparison(comparator=Comparator.LT, attribute="foo", value=["1", "2"])
expected = {"foo": {"$lt": ["1", "2"]}}
actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
assert expected == actual
def test_visit_operation() -> None:
op = Operation(
operator=Operator.AND,
arguments=[
Comparison(comparator=Comparator.LT, attribute="foo", value=2),
Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
Comparison(comparator=Comparator.LT, attribute="abc", value=["1", "2"]),
],
)
expected = {
"$and": [
{"foo": {"$lt": 2}},
{"bar": {"$eq": "baz"}},
{"abc": {"$lt": ["1", "2"]}},
]
}
actual = DEFAULT_TRANSLATOR.visit_operation(op)
assert expected == actual
def test_visit_structured_query() -> None:
query = "What is the capital of France?"
structured_query = StructuredQuery(
query=query,
filter=None,
)
expected: Tuple[str, Dict] = (query, {})
actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
assert expected == actual
comp = Comparison(comparator=Comparator.LT, attribute="foo", value=["1", "2"])
expected = (
query,
{"filter": {"foo": {"$lt": ["1", "2"]}}},
)
structured_query = StructuredQuery(
query=query,
filter=comp,
)
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.LT, attribute="abc", value=["1", "2"]),
],
)
structured_query = StructuredQuery(
query=query,
filter=op,
)
expected = (
query,
{
"filter": {
"$and": [
{"foo": {"$lt": 2}},
{"bar": {"$eq": "baz"}},
{"abc": {"$lt": ["1", "2"]}},
]
}
},
)
actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
assert expected == actual

View File

@ -48,6 +48,7 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
MongoDBAtlasTranslator,
)
from langchain_community.query_constructors.myscale import MyScaleTranslator
from langchain_community.query_constructors.neo4j import Neo4jTranslator
from langchain_community.query_constructors.opensearch import OpenSearchTranslator
from langchain_community.query_constructors.pgvector import PGVectorTranslator
from langchain_community.query_constructors.pinecone import PineconeTranslator
@ -70,6 +71,7 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
Dingo,
Milvus,
MyScale,
Neo4jVector,
OpenSearchVectorSearch,
PGVector,
Qdrant,
@ -111,6 +113,7 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
TimescaleVector: TimescaleVectorTranslator,
OpenSearchVectorSearch: OpenSearchTranslator,
CommunityMongoDBAtlasVectorSearch: MongoDBAtlasTranslator,
Neo4jVector: Neo4jTranslator,
}
if isinstance(vectorstore, DatabricksVectorSearch):
return DatabricksVectorSearchTranslator()