txtai Vector Store¶

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

In [ ]:

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

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

In [ ]:

!pip install llama-index

!pip install llama-index

Creating a Faiss Index¶

In [ ]:

import logging
import sys

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

import logging import sys logging.basicConfig(stream=sys.stdout, level=logging.INFO) logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

In [ ]:

import txtai

# Create txtai ann index
txtai_index = txtai.ann.ANNFactory.create({"backend": "numpy"})

import txtai # Create txtai ann index txtai_index = txtai.ann.ANNFactory.create({"backend": "numpy"})

Load documents, build the VectorStoreIndex¶

In [ ]:

from llama_index.core import (
    SimpleDirectoryReader,
    load_index_from_storage,
    VectorStoreIndex,
    StorageContext,
)
from llama_index.vector_stores.txtai import TxtaiVectorStore
from IPython.display import Markdown, display

from llama_index.core import ( SimpleDirectoryReader, load_index_from_storage, VectorStoreIndex, StorageContext, ) from llama_index.vector_stores.txtai import TxtaiVectorStore from IPython.display import Markdown, display

Download Data

In [ ]:

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

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

In [ ]:

# load documents
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

# load documents documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

In [ ]:

vector_store = TxtaiVectorStore(txtai_index=txtai_index)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

vector_store = TxtaiVectorStore(txtai_index=txtai_index) storage_context = StorageContext.from_defaults(vector_store=vector_store) index = VectorStoreIndex.from_documents( documents, storage_context=storage_context )

In [ ]:

# save index to disk
index.storage_context.persist()

# save index to disk index.storage_context.persist()

In [ ]:

# load index from disk
vector_store = TxtaiVectorStore.from_persist_dir("./storage")
storage_context = StorageContext.from_defaults(
    vector_store=vector_store, persist_dir="./storage"
)
index = load_index_from_storage(storage_context=storage_context)

# load index from disk vector_store = TxtaiVectorStore.from_persist_dir("./storage") storage_context = StorageContext.from_defaults( vector_store=vector_store, persist_dir="./storage" ) index = load_index_from_storage(storage_context=storage_context)

Query Index¶

In [ ]:

# 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?")

# 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?")

In [ ]:

display(Markdown(f"<b>{response}</b>"))

display(Markdown(f"{response}"))

In [ ]:

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query(
    "What did the author do after his time at Y Combinator?"
)

# set Logging to DEBUG for more detailed outputs query_engine = index.as_query_engine() response = query_engine.query( "What did the author do after his time at Y Combinator?" )

In [ ]:

display(Markdown(f"<b>{response}</b>"))

display(Markdown(f"{response}"))