Skip to content

Embedding Drivers


Embeddings in Griptape are multidimensional representations of text data. Embeddings carry semantic information, which makes them useful for extracting relevant chunks from large bodies of text for search and querying.

Griptape provides a way to build Embedding Drivers that are reused in downstream framework components. Every Embedding Driver has two basic methods that can be used to generate embeddings:


More embedding drivers are coming soon.

Embedding Drivers

OpenAI Embeddings

The OpenAiEmbeddingDriver uses OpenAI Embeddings API to generate embeddings for texts of arbitrary length. This driver automatically chunks the input text to fit into the token limit.

from griptape.drivers import OpenAiEmbeddingDriver

embeddings = OpenAiEmbeddingDriver().embed_string("Hello Griptape!")

# display the first 3 embeddings
[0.0017853748286142945, 0.006118456833064556, -0.005811543669551611]

Azure OpenAI Embeddings

The AzureOpenAiEmbeddingDriver uses the same parameters as OpenAiEmbeddingDriver with updated defaults.

Bedrock Titan Embeddings

The BedrockTitanEmbeddingDriver uses the Amazon Bedrock Embeddings API.

from griptape.drivers import BedrockTitanEmbeddingDriver

embeddings = BedrockTitanEmbeddingDriver().embed_string("Hello world!")

# display the first 3 embeddings
[-0.234375, -0.024902344, -0.14941406]

Override Default Structure Embedding Driver

Here is how you can override the Embedding Driver that is used by default in agents.

from griptape.structures import Agent
from import WebScraper
from griptape.drivers import LocalVectorStoreDriver, OpenAiEmbeddingDriver

agent = Agent(
)"based on, tell me what Griptape is")