DocArray InMemory Vector Store

DocArrayInMemoryVectorStore is a document index provided by Docarray that stores documents in memory. It is a great starting point for small datasets, where you may not want to launch a database server.

If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.

python

%pip install llama-index-vector-stores-docarray

python

!pip install llama-index

python

import os
import sys
import logging
import textwrap

import warnings

warnings.filterwarnings("ignore")

# stop huggingface warnings
os.environ["TOKENIZERS_PARALLELISM"] = "false"

# Uncomment to see debug logs
# logging.basicConfig(stream=sys.stdout, level=logging.INFO)
# logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

from llama_index.core import (
    GPTVectorStoreIndex,
    SimpleDirectoryReader,
    Document,
)
from llama_index.vector_stores.docarray import DocArrayInMemoryVectorStore
from IPython.display import Markdown, display

python

import os

os.environ["OPENAI_API_KEY"] = "<your openai key>"

Download Data

python

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

python

# load documents
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()
print(
    "Document ID:",
    documents[0].doc_id,
    "Document Hash:",
    documents[0].doc_hash,
)

Initialization and indexing

python

from llama_index.core import StorageContext


vector_store = DocArrayInMemoryVectorStore()
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = GPTVectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

Querying

python

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(textwrap.fill(str(response), 100))

python

response = query_engine.query("What was a hard moment for the author?")
print(textwrap.fill(str(response), 100))

Querying with filters

python

from llama_index.core.schema import TextNode

nodes = [
    TextNode(
        text="The Shawshank Redemption",
        metadata={
            "author": "Stephen King",
            "theme": "Friendship",
        },
    ),
    TextNode(
        text="The Godfather",
        metadata={
            "director": "Francis Ford Coppola",
            "theme": "Mafia",
        },
    ),
    TextNode(
        text="Inception",
        metadata={
            "director": "Christopher Nolan",
        },
    ),
]

python

from llama_index.core import StorageContext


vector_store = DocArrayInMemoryVectorStore()
storage_context = StorageContext.from_defaults(vector_store=vector_store)

index = GPTVectorStoreIndex(nodes, storage_context=storage_context)

python

from llama_index.core.vector_stores import ExactMatchFilter, MetadataFilters


filters = MetadataFilters(
    filters=[ExactMatchFilter(key="theme", value="Mafia")]
)

retriever = index.as_retriever(filters=filters)
retriever.retrieve("What is inception about?")