Query Engines

Overview

Query engines are used to search collections of text.

VectorQueryEngine

Used to query vector storages. You can set a custom prompt_driver and vector_store_driver. Uses LocalVectorStoreDriver by default.

Use the upsert_text_artifact method to insert TextArtifacts into vector storage with an optional namespace.

Use the VectorQueryEngine method to query the vector storage.

from griptape.drivers import OpenAiChatPromptDriver, LocalVectorStoreDriver, OpenAiEmbeddingDriver
from griptape.engines import VectorQueryEngine
from griptape.loaders import WebLoader

engine = VectorQueryEngine(
    prompt_driver=OpenAiChatPromptDriver(model="gpt-3.5-turbo"),
    vector_store_driver=LocalVectorStoreDriver(embedding_driver=OpenAiEmbeddingDriver())
)

engine.upsert_text_artifacts(
    WebLoader().load("https://www.griptape.ai"), namespace="griptape"
)

engine.query("what is griptape?", namespace="griptape")