> ## Documentation Index > Fetch the complete documentation index at: https://langchain.idochub.dev/llms.txt > Use this file to discover all available pages before exploring further. # Chroma > [Chroma](https://docs.trychroma.com/getting-started) is a vector database for building AI applications with embeddings. In the notebook, we'll demo the `SelfQueryRetriever` wrapped around a `Chroma` vector store. ## Creating a Chroma vector store First we'll want to create a Chroma 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 `langchain-chroma` package. ```python theme={null} %pip install -qU lark ``` ```python theme={null} %pip install -qU langchain-chroma ``` We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key. ```python theme={null} import getpass import os if "OPENAI_API_KEY" not in os.environ: os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:") ``` ```output theme={null} OpenAI API Key: ········ ``` ```python theme={null} from langchain_chroma import Chroma from langchain_core.documents import Document from langchain_openai import OpenAIEmbeddings embeddings = OpenAIEmbeddings() ``` ```python theme={null} 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 = Chroma.from_documents(docs, embeddings) ``` ```output theme={null} Using embedded DuckDB without persistence: data will be transient ``` ## 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. ```python theme={null} from langchain.chains.query_constructor.schema 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! ```python theme={null} # This example only specifies a relevant query retriever.invoke("What are some movies about dinosaurs") ``` ```output theme={null} query='dinosaur' filter=None ``` ```output theme={null} [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='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='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'year': 2010, 'director': 'Christopher Nolan', 'rating': 8.2})] ``` ```python theme={null} # This example only specifies a filter retriever.invoke("I want to watch a movie rated higher than 8.5") ``` ```output theme={null} query=' ' filter=Comparison(comparator=, attribute='rating', value=8.5) ``` ```output theme={null} [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='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'})] ``` ```python theme={null} # This example specifies a query and a filter retriever.invoke("Has Greta Gerwig directed any movies about women") ``` ```output theme={null} query='women' filter=Comparison(comparator=, attribute='director', value='Greta Gerwig') ``` ```output theme={null} [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})] ``` ```python theme={null} # This example specifies a composite filter retriever.invoke("What's a highly rated (above 8.5) science fiction film?") ``` ```output theme={null} query=' ' filter=Operation(operator=, arguments=[Comparison(comparator=, attribute='genre', value='science fiction'), Comparison(comparator=, attribute='rating', value=8.5)]) ``` ```output theme={null} [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'})] ``` ```python theme={null} # This example specifies a query and composite filter retriever.invoke( "What's a movie after 1990 but before 2005 that's all about toys, and preferably is animated" ) ``` ```output theme={null} query='toys' filter=Operation(operator=, arguments=[Comparison(comparator=, attribute='year', value=1990), Comparison(comparator=, attribute='year', value=2005), Comparison(comparator=, attribute='genre', value='animated')]) ``` ```output theme={null} [Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})] ``` ## 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. ```python theme={null} retriever = SelfQueryRetriever.from_llm( llm, vectorstore, document_content_description, metadata_field_info, enable_limit=True, verbose=True, ) ``` ```python theme={null} # This example only specifies a relevant query retriever.invoke("what are two movies about dinosaurs") ``` ```output theme={null} query='dinosaur' filter=None ``` ```output theme={null} [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='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='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'year': 2010, 'director': 'Christopher Nolan', 'rating': 8.2})] ``` ```python theme={null} ```