Archives
/
langchain
mirror of https://github.com/hwchase17/langchain
2
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

SelfQuery support for deeplake (#7888)

Browse Source 
Added support SelfQuery for Deeplake
pull/8076/head^2
Adilkhan Sarsen 10 months ago committed by GitHub
parent c580c81cca
commit 3e7d2a1b64
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 631 additions and 192 deletions
Show Stats Download Patch File Download Diff File

490
docs/extras/modules/data_connection/retrievers/self_query/deeplake_self_query.ipynb
Unescape Escape View File

@ -0,0 +1,490 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "13afcae7",
"metadata": {},
"source": [
"# DeepLake self-querying \n",
"\n",
">[DeepLake](https://www.activeloop.ai) is a multimodal database for building AI applications.\n",
"\n",
"In the notebook we'll demo the `SelfQueryRetriever` wrapped around a DeepLake vector store. "
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "68e75fb9",
"metadata": {},
"source": [
"## Creating a DeepLake vectorstore\n",
"First we'll want to create a DeepLake 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 `deeplake` package."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "63a8af5b",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"#!pip install lark"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "22431060-52c4-48a7-a97b-9f542b8b0928",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"#!pip install 'deeplake[enterprise]'"
]
},
{
"attachments": {},
"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": 3,
"id": "dd01b61b-7d32-4a55-85d6-b2d2d4f18840",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"import getpass\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "cb4a5787",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.schema import Document\n",
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.vectorstores import DeepLake\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "bcbe04d9",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Your Deep Lake dataset has been successfully created!\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"-"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dataset(path='hub://adilkhan/self_queery', tensors=['embedding', 'id', 'metadata', 'text'])\n",
"\n",
" tensor htype shape dtype compression\n",
" ------- ------- ------- ------- ------- \n",
" embedding embedding (6, 1536) float32 None \n",
" id text (6, 1) str None \n",
" metadata json (6, 1) str None \n",
" text text (6, 1) str None \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" \r"
]
}
],
"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",
" \"rating\": 9.9,\n",
" },\n",
" ),\n",
"]\n",
"username_or_org = \"<USER_NAME_OR_ORG>\"\n",
"vectorstore = DeepLake.from_documents(\n",
" docs, embeddings, dataset_path=f\"hub://{username_or_org}/self_queery\"\n",
")"
]
},
{
"attachments": {},
"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": 7,
"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",
")"
]
},
{
"attachments": {},
"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": 8,
"id": "38a126e9",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/adilkhansarsen/Documents/work/LangChain/langchain/langchain/chains/llm.py:275: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
" warnings.warn(\n"
]
},
{
"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='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": 8,
"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": 9,
"id": "fc3f1e6e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5) limit=None\n"
]
},
{
"data": {
"text/plain": [
"[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='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": 9,
"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\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "b19d4da0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, 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": 10,
"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": 11,
"id": "f900e40e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.EQ: 'eq'>, 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": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"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": 12,
"id": "12a51522",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990), Comparison(comparator=<Comparator.LT: 'lt'>, attribute='year', value=2005), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='animated')]) 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": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"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",
")"
]
},
{
"attachments": {},
"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": 13,
"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": 14,
"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": 14,
"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": "code",
"execution_count": null,
"id": "c93f0847-cbd9-4c25-aed1-91588e856b5c",
"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": "3.9.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

3
libs/langchain/langchain/retrievers/self_query/base.py
Unescape Escape View File

@ -13,6 +13,7 @@ from langchain.chains.query_constructor.base import load_query_constructor_chain
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.deeplake import DeepLakeTranslator
from langchain.retrievers.self_query.myscale import MyScaleTranslator
from langchain.retrievers.self_query.pinecone import PineconeTranslator
from langchain.retrievers.self_query.qdrant import QdrantTranslator
@ -21,6 +22,7 @@ from langchain.schema import BaseRetriever, Document
from langchain.schema.language_model import BaseLanguageModel
from langchain.vectorstores import (
Chroma,
DeepLake,
MyScale,
Pinecone,
Qdrant,
@ -38,6 +40,7 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
Weaviate: WeaviateTranslator,
Qdrant: QdrantTranslator,
MyScale: MyScaleTranslator,
DeepLake: DeepLakeTranslator,
}
if vectorstore_cls not in BUILTIN_TRANSLATORS:
raise ValueError(

86
libs/langchain/langchain/retrievers/self_query/deeplake.py
Unescape Escape View File

@ -0,0 +1,86 @@
"""Logic for converting internal query language to a valid Chroma query."""
from typing import Tuple, Union
from langchain.chains.query_constructor.ir import (
Comparator,
Comparison,
Operation,
Operator,
StructuredQuery,
Visitor,
)
COMPARATOR_TO_TQL = {
Comparator.EQ: "==",
Comparator.GT: ">",
Comparator.GTE: ">=",
Comparator.LT: "<",
Comparator.LTE: "<=",
}
OPERATOR_TO_TQL = {
Operator.AND: "and",
Operator.OR: "or",
}
def can_cast_to_float(string: str) -> bool:
try:
float(string)
return True
except ValueError:
return False
class DeepLakeTranslator(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,
Comparator.GT,
Comparator.GTE,
Comparator.LT,
Comparator.LTE,
]
"""Subset of allowed logical comparators."""
def _format_func(self, func: Union[Operator, Comparator]) -> str:
self._validate_func(func)
if isinstance(func, Operator):
value = OPERATOR_TO_TQL[func.value] # type: ignore
elif isinstance(func, Comparator):
value = COMPARATOR_TO_TQL[func.value] # type: ignore
return f"{value}"
def visit_operation(self, operation: Operation) -> str:
args = [arg.accept(self) for arg in operation.arguments]
operator = self._format_func(operation.operator)
return "(" + (" " + operator + " ").join(args) + ")"
def visit_comparison(self, comparison: Comparison) -> str:
comparator = self._format_func(comparison.comparator)
values = comparison.value
if isinstance(values, list):
tql = []
for value in values:
comparison.value = value
tql.append(self.visit_comparison(comparison))
return "(" + (" or ").join(tql) + ")"
if not can_cast_to_float(comparison.value):
values = f"'{values}'"
return f"metadata['{comparison.attribute}'] {comparator} {values}"
def visit_structured_query(
self, structured_query: StructuredQuery
) -> Tuple[str, dict]:
if structured_query.filter is None:
kwargs = {}
else:
tqL = f"SELECT * WHERE {structured_query.filter.accept(self)}"
kwargs = {"tql": tqL}
return structured_query.query, kwargs

12
libs/langchain/langchain/vectorstores/deeplake.py
Unescape Escape View File

@ -219,14 +219,14 @@ class DeepLake(VectorStore):
def _search_tql(
self,
tql_query: Optional[str],
tql: Optional[str],
exec_option: Optional[str] = None,
**kwargs: Any,
) -> List[Document]:
"""Function for performing tql_search.
Args:
tql_query (str): TQL Query string for direct evaluation.
tql (str): TQL Query string for direct evaluation.
Available only for `compute_engine` and `tensor_db`.
exec_option (str, optional): Supports 3 ways to search.
Could be "python", "compute_engine" or "tensor_db". Default is "python".
@ -249,7 +249,7 @@ class DeepLake(VectorStore):
ValueError: If return_score is True but some condition is not met.
"""
result = self.vectorstore.search(
query=tql_query,
query=tql,
exec_option=exec_option,
)
metadatas = result["metadata"]
@ -328,9 +328,9 @@ class DeepLake(VectorStore):
ValueError: if both `embedding` and `embedding_function` are not specified.
"""
if kwargs.get("tql_query"):
if kwargs.get("tql"):
return self._search_tql(
tql_query=kwargs["tql_query"],
tql=kwargs["tql"],
exec_option=exec_option,
return_score=return_score,
embedding=embedding,
@ -423,7 +423,7 @@ class DeepLake(VectorStore):
>>> # Run tql search:
>>> data = vector_store.similarity_search(
... query=None,
... tql_query="SELECT * WHERE id == <id>",
... tql="SELECT * WHERE id == <id>",
... exec_option="compute_engine",
... )

33
libs/langchain/tests/unit_tests/retrievers/self_query/test_deeplake.py
Unescape Escape View File

@ -0,0 +1,33 @@
from langchain.chains.query_constructor.ir import (
Comparator,
Comparison,
Operation,
Operator,
)
from langchain.retrievers.self_query.deeplake import DeepLakeTranslator
DEFAULT_TRANSLATOR = DeepLakeTranslator()
def test_visit_comparison() -> None:
comp = Comparison(comparator=Comparator.LT, attribute="foo", value=["1", "2"])
expected = "(metadata['foo'] < 1 or metadata['foo'] < 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 = (
"(metadata['foo'] < 2 and metadata['bar'] == 'baz' "
"and (metadata['abc'] < 1 or metadata['abc'] < 2))"
)
actual = DEFAULT_TRANSLATOR.visit_operation(op)
assert expected == actual

199
poetry.lock generated
View File

File diff suppressed because it is too large Load Diff
Write Preview
Loading…
Cancel
Save