Skip to main content

Elasticsearch

Elasticsearch is a distributed, RESTful search and analytics engine. It provides a distributed, multi-tenant-capable full-text search engine with an HTTP web interface and schema-free JSON documents.

In this notebook, we'll demo the SelfQueryRetriever with an Elasticsearch vector store.

Creating an Elasticsearch vector store​

First, we'll want to create an Elasticsearch vector store and seed it with some data. We've created a small demo set of documents that contain summaries of movies.

Note: The self-query retriever requires you to have lark installed (pip install lark). We also need the elasticsearch package.

%pip install --upgrade --quiet  U lark langchain langchain-elasticsearch
WARNING: You are using pip version 22.0.4; however, version 23.3 is available.
You should consider upgrading via the '/Users/joe/projects/elastic/langchain/libs/langchain/.venv/bin/python3 -m pip install --upgrade pip' command.

import getpass
import os

from langchain_core.documents import Document
from langchain_elasticsearch import ElasticsearchStore
from langchain_openai import OpenAIEmbeddings

os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")

embeddings = OpenAIEmbeddings()
docs = [
    Document(
        page_content="A bunch of scientists bring back dinosaurs and mayhem breaks loose",
        metadata={"year": 1993, "rating": 7.7, "genre": "science fiction"},
    ),
    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},
    ),
    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},
    ),
    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},
    ),
    Document(
        page_content="Toys come alive and have a blast doing so",
        metadata={"year": 1995, "genre": "animated"},
    ),
    Document(
        page_content="Three men walk into the Zone, three men walk out of the Zone",
        metadata={
            "year": 1979,
            "director": "Andrei Tarkovsky",
            "genre": "science fiction",
            "rating": 9.9,
        },
    ),
]
vectorstore = ElasticsearchStore.from_documents(
    docs,
    embeddings,
    index_name="elasticsearch-self-query-demo",
    es_url="http://localhost:9200",
)

Creating our self-querying retriever​

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.

from langchain.chains.query_constructor.base import AttributeInfo
from langchain.retrievers.self_query.base import SelfQueryRetriever
from langchain_openai import OpenAI

metadata_field_info = [
    AttributeInfo(
        name="genre",
        description="The genre of the movie",
        type="string or list[string]",
    ),
    AttributeInfo(
        name="year",
        description="The year the movie was released",
        type="integer",
    ),
    AttributeInfo(
        name="director",
        description="The name of the movie director",
        type="string",
    ),
    AttributeInfo(
        name="rating", description="A 1-10 rating for the movie", type="float"
    ),
]
document_content_description = "Brief summary of a movie"
llm = OpenAI(temperature=0)
retriever = SelfQueryRetriever.from_llm(
    llm, vectorstore, document_content_description, metadata_field_info, verbose=True
)

Testing it out​

And now we can try actually using our retriever!

# This example only specifies a relevant query
retriever.invoke("What are some movies about dinosaurs")
[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}),
 Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),
 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'}),
 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})]
# This example specifies a query and a filter
retriever.invoke("Has Greta Gerwig directed any movies about women")
[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})]

Filter k​

We can also use the self query retriever to specify k: the number of documents to fetch.

We can do this by passing enable_limit=True to the constructor.

retriever = SelfQueryRetriever.from_llm(
    llm,
    vectorstore,
    document_content_description,
    metadata_field_info,
    enable_limit=True,
    verbose=True,
)
# This example only specifies a relevant query
retriever.invoke("what are two movies about dinosaurs")
[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}),
 Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]

Complex queries in Action!​

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 Elasticsearch.

retriever.invoke(
    "what animated or comedy movies have been released in the last 30 years about animated toys?"
)
[Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]
vectorstore.client.indices.delete(index="elasticsearch-self-query-demo")

Help us out by providing feedback on this documentation page: