Firestore Demo#

This guide shows you how to directly use our DocumentStore abstraction backed by Google Firestore. By putting nodes in the docstore, this allows you to define multiple indices over the same underlying docstore, instead of duplicating data across indices.

Open In Colab

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

%pip install llama-index-storage-docstore-firestore
%pip install llama-index-storage-kvstore-firestore
%pip install llama-index-storage-index-store-firestore
%pip install llama-index-llms-openai
!pip install llama-index
import nest_asyncio

import logging
import sys

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
from llama_index.core import SimpleDirectoryReader, StorageContext
from llama_index.core import VectorStoreIndex, SimpleKeywordTableIndex
from llama_index.core import SummaryIndex
from llama_index.core import ComposableGraph
from llama_index.llms.openai import OpenAI
from llama_index.core.response.notebook_utils import display_response
from llama_index.core import Settings

Download Data#

!mkdir -p 'data/paul_graham/'
!wget '' -O 'data/paul_graham/paul_graham_essay.txt'

Load Documents#

reader = SimpleDirectoryReader("./data/paul_graham/")
documents = reader.load_data()

Parse into Nodes#

from llama_index.core.node_parser import SentenceSplitter

nodes = SentenceSplitter().get_nodes_from_documents(documents)

Add to Docstore#

from import FirestoreKVStore
from import FirestoreDocumentStore
from import FirestoreIndexStore
kvstore = FirestoreKVStore()

storage_context = StorageContext.from_defaults(

Define Multiple Indexes#

Each index uses the same underlying Node.

summary_index = SummaryIndex(nodes, storage_context=storage_context)
vector_index = VectorStoreIndex(nodes, storage_context=storage_context)
keyword_table_index = SimpleKeywordTableIndex(
    nodes, storage_context=storage_context
# NOTE: the docstore still has the same nodes

Test out saving and loading#

# NOTE: docstore and index_store is persisted in Firestore by default
# NOTE: here only need to persist simple vector store to disk
# note down index IDs
list_id = summary_index.index_id
vector_id = vector_index.index_id
keyword_id = keyword_table_index.index_id
from llama_index.core import load_index_from_storage

kvstore = FirestoreKVStore()

# re-create storage context
storage_context = StorageContext.from_defaults(

# load indices
summary_index = load_index_from_storage(
    storage_context=storage_context, index_id=list_id
vector_index = load_index_from_storage(
    storage_context=storage_context, vector_id=vector_id
keyword_table_index = load_index_from_storage(
    storage_context=storage_context, keyword_id=keyword_id

Test out some Queries#

chatgpt = OpenAI(temperature=0, model="gpt-3.5-turbo")
Settings.llm = chatgpt
Settings.chunk_size = 1024
query_engine = summary_index.as_query_engine()
list_response = query_engine.query("What is a summary of this document?")
query_engine = vector_index.as_query_engine()
vector_response = query_engine.query("What did the author do growing up?")
query_engine = keyword_table_index.as_query_engine()
keyword_response = query_engine.query(
    "What did the author do after his time at YC?"