github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-04 04:07:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

[OpenSearch] Add Self Query Retriever Support to OpenSearch (#11184)

Browse Source 
### Description
Add Self Query Retriever Support to OpenSearch

### Maintainers
@rlancemartin, @eyurtsev, @navneet1v

### Twitter Handle
@OpenSearchProj

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
This commit is contained in:
Naveen Tatikonda 2023-09-28 14:36:52 -05:00 committed by GitHub
parent 0da484be2c
commit 9b0029b9c2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 628 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

439
docs/extras/modules/data_connection/retrievers/self_query/opensearch_self_query.ipynb Normal file
View File

@ -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=<Comparator.GT: 'gt'>, 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=<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": 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=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.CONTAIN: 'contain'>, 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=<Operator.AND: 'and'>, arguments=[Operation(operator=<Operator.OR: 'or'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='animated'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='comedy')]), Comparison(comparator=<Comparator.GTE: 'gte'>, 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
}

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

@ -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.elasticsearch import ElasticsearchTranslator
from langchain.retrievers.self_query.milvus import MilvusTranslator from langchain.retrievers.self_query.milvus import MilvusTranslator
from langchain.retrievers.self_query.myscale import MyScaleTranslator 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.pinecone import PineconeTranslator
from langchain.retrievers.self_query.qdrant import QdrantTranslator from langchain.retrievers.self_query.qdrant import QdrantTranslator
from langchain.retrievers.self_query.redis import RedisTranslator from langchain.retrievers.self_query.redis import RedisTranslator
@ -30,6 +31,7 @@ from langchain.vectorstores import (
ElasticsearchStore, ElasticsearchStore,
Milvus, Milvus,
MyScale, MyScale,
OpenSearchVectorSearch,
Pinecone, Pinecone,
Qdrant, Qdrant,
Redis, Redis,
@ -56,6 +58,7 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
Milvus: MilvusTranslator, Milvus: MilvusTranslator,
SupabaseVectorStore: SupabaseVectorTranslator, SupabaseVectorStore: SupabaseVectorTranslator,
TimescaleVector: TimescaleVectorTranslator, TimescaleVector: TimescaleVectorTranslator,
OpenSearchVectorSearch: OpenSearchTranslator,
} }
if isinstance(vectorstore, Qdrant): if isinstance(vectorstore, Qdrant):
return QdrantTranslator(metadata_key=vectorstore.metadata_payload_key) return QdrantTranslator(metadata_key=vectorstore.metadata_payload_key)

84
libs/langchain/langchain/retrievers/self_query/opensearch.py Normal file
View File

@ -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

15
libs/langchain/langchain/vectorstores/opensearch_vector_search.py
View File

@ -341,6 +341,7 @@ class OpenSearchVectorSearch(VectorStore):
http_auth = _get_kwargs_value(kwargs, "http_auth", None) http_auth = _get_kwargs_value(kwargs, "http_auth", None)
self.is_aoss = _is_aoss_enabled(http_auth=http_auth) self.is_aoss = _is_aoss_enabled(http_auth=http_auth)
self.client = _get_opensearch_client(opensearch_url, **kwargs) self.client = _get_opensearch_client(opensearch_url, **kwargs)
self.engine = _get_kwargs_value(kwargs, "engine", None)
@property @property
def embeddings(self) -> Embeddings: def embeddings(self) -> Embeddings:
@ -528,6 +529,7 @@ class OpenSearchVectorSearch(VectorStore):
search_type = _get_kwargs_value(kwargs, "search_type", "approximate_search") search_type = _get_kwargs_value(kwargs, "search_type", "approximate_search")
vector_field = _get_kwargs_value(kwargs, "vector_field", "vector_field") vector_field = _get_kwargs_value(kwargs, "vector_field", "vector_field")
index_name = _get_kwargs_value(kwargs, "index_name", self.index_name) index_name = _get_kwargs_value(kwargs, "index_name", self.index_name)
filter = _get_kwargs_value(kwargs, "filter", {})
if ( if (
self.is_aoss self.is_aoss
@ -564,6 +566,17 @@ class OpenSearchVectorSearch(VectorStore):
"is invalid. `lucene_filter` is deprecated" "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 != {}: if boolean_filter != {}:
search_query = _approximate_search_query_with_boolean_filter( search_query = _approximate_search_query_with_boolean_filter(
embedding, embedding,
@ -745,6 +758,7 @@ class OpenSearchVectorSearch(VectorStore):
max_chunk_bytes = _get_kwargs_value(kwargs, "max_chunk_bytes", 1 * 1024 * 1024) max_chunk_bytes = _get_kwargs_value(kwargs, "max_chunk_bytes", 1 * 1024 * 1024)
http_auth = _get_kwargs_value(kwargs, "http_auth", None) http_auth = _get_kwargs_value(kwargs, "http_auth", None)
is_aoss = _is_aoss_enabled(http_auth=http_auth) is_aoss = _is_aoss_enabled(http_auth=http_auth)
engine = None
if is_aoss and not is_appx_search: if is_aoss and not is_appx_search:
raise ValueError( raise ValueError(
@ -782,4 +796,5 @@ class OpenSearchVectorSearch(VectorStore):
max_chunk_bytes=max_chunk_bytes, max_chunk_bytes=max_chunk_bytes,
is_aoss=is_aoss, is_aoss=is_aoss,
) )
kwargs["engine"] = engine
return cls(opensearch_url, index_name, embedding, **kwargs) return cls(opensearch_url, index_name, embedding, **kwargs)

87
libs/langchain/tests/unit_tests/retrievers/self_query/test_opensearch.py Normal file
View File

@ -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