Embedding

Adapted from the Griptape AI Framework documentation.

Overview

Embeddings in Gen AI Builder are multidimensional representations of text or image data. Embeddings carry semantic information, making them powerful for use-cases like text or image similarity search in a Rag Engine.

Embedding Drivers

OpenAI

The OpenAiEmbeddingDriver uses the OpenAI Embeddings API.

Code
Logs

from griptape.drivers.embedding.openai import OpenAiEmbeddingDriver

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

# display the first 3 embeddings
print(embeddings[:3])

[0.025706132873892784, -0.00652786111459136, -0.05880141258239746]

[0.0017853748286142945, 0.006118456833064556, -0.005811543669551611]

OpenAI Compatible

Many services such as LMStudio and OhMyGPT provide OpenAI-compatible APIs. You can use the OpenAiEmbeddingDriver to interact with these services. Simply set the base_url to the service's API endpoint and the model to the model name. If the service requires an API key, you can set it in the api_key field.

from griptape.drivers.embedding.openai import OpenAiEmbeddingDriver

embedding_driver = OpenAiEmbeddingDriver(
    base_url="http://127.0.0.1:1234/v1",
    model="nomic-ai/nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.Q2_K",
)

embeddings = embedding_driver.embed("Hello world!")

# display the first 3 embeddings
print(embeddings[:3])

Tip

Make sure to include v1 at the end of the base_url to match the OpenAI API endpoint.

Azure OpenAI

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

Bedrock Titan

Info

This driver requires the drivers-embedding-amazon-bedrock extra.

The AmazonBedrockTitanEmbeddingDriver uses the Amazon Bedrock Embeddings API.

Code
Logs

from griptape.drivers.embedding.amazon_bedrock import AmazonBedrockTitanEmbeddingDriver
from griptape.loaders import ImageLoader

embedding_driver = AmazonBedrockTitanEmbeddingDriver()
embeddings = embedding_driver.embed("Hello world!")

print(embeddings[:3])

# Some models support images!
multi_modal_embedding_driver = AmazonBedrockTitanEmbeddingDriver(model="amazon.titan-embed-image-v1")
image = ImageLoader().load("tests/resources/cow.png")
image_embeddings = multi_modal_embedding_driver.embed(image)

print(image_embeddings[:3])

[0.10888671875, 0.291015625, 0.2265625]

[-0.234375, -0.024902344, -0.14941406]

Google

Info

This driver requires the drivers-embedding-google extra.

The GoogleEmbeddingDriver uses the Google Embeddings API.

Code
Logs

from griptape.drivers.embedding.google import GoogleEmbeddingDriver

embeddings = GoogleEmbeddingDriver().embed("Hello world!")

# display the first 3 embeddings
print(embeddings[:3])

[0.05886331, 0.0033929434, -0.072810836]

[0.0588633, 0.0033929371, -0.072810836]

Hugging Face Hub

Info

This driver requires the drivers-embedding-huggingface extra.

The HuggingFaceHubEmbeddingDriver connects to the Hugging Face Hub API. It supports models with the following tasks:

feature-extraction

Code
Logs

import os

from griptape.drivers.embedding.huggingface_hub import HuggingFaceHubEmbeddingDriver
from griptape.tokenizers import HuggingFaceTokenizer

driver = HuggingFaceHubEmbeddingDriver(
    api_token=os.environ["HUGGINGFACE_HUB_ACCESS_TOKEN"],
    model="sentence-transformers/all-MiniLM-L6-v2",
    tokenizer=HuggingFaceTokenizer(
        model="sentence-transformers/all-MiniLM-L6-v2",
        max_output_tokens=512,
    ),
)

embeddings = driver.embed("Hello world!")

# display the first 3 embeddings
print(embeddings[:3])

[-0.02038687840104103, 0.02528087981045246, -0.0005662207258865237]

Ollama

Info

This driver requires the drivers-embedding-ollama extra.

The OllamaEmbeddingDriver uses the Ollama Embeddings API.

from griptape.drivers.embedding.ollama import OllamaEmbeddingDriver

driver = OllamaEmbeddingDriver(
    model="all-minilm",
)

results = driver.embed("Hello world!")

# display the first 3 embeddings
print(results[:3])

Amazon SageMaker Jumpstart

The AmazonSageMakerJumpstartEmbeddingDriver uses the Amazon SageMaker Endpoints to generate embeddings on AWS.

Info

This driver requires the drivers-embedding-amazon-sagemaker extra.

import os

from griptape.drivers.embedding.amazon_sagemaker_jumpstart import AmazonSageMakerJumpstartEmbeddingDriver

driver = AmazonSageMakerJumpstartEmbeddingDriver(
    endpoint=os.environ["SAGEMAKER_ENDPOINT"],
    model=os.environ["SAGEMAKER_TENSORFLOW_HUB_MODEL"],
)

embeddings = driver.embed("Hello world!")

# display the first 3 embeddings
print(embeddings[:3])

VoyageAI

The VoyageAiEmbeddingDriver uses the VoyageAI Embeddings API.

Info

This driver requires the drivers-embedding-voyageai extra.

Code
Logs

import os

from griptape.drivers.embedding.voyageai import VoyageAiEmbeddingDriver
from griptape.loaders import ImageLoader

embedding_driver = VoyageAiEmbeddingDriver(api_key=os.environ["VOYAGE_API_KEY"])
embeddings = embedding_driver.embed("Hello world!")

print(embeddings[:3])

# Some models support images!
multi_modal_embedding_driver = VoyageAiEmbeddingDriver(
    api_key=os.environ["VOYAGE_API_KEY"], model="voyage-multimodal-3"
)
image = ImageLoader().load("tests/resources/cow.png")
image_embeddings = multi_modal_embedding_driver.embed(image)

print(image_embeddings[:3])

[-0.01390501856803894, 0.003788162022829056, 0.02040485292673111]

Cohere

The CohereEmbeddingDriver uses the Cohere Embeddings API.

Info

This driver requires the drivers-embedding-cohere extra.

Code
Logs

import os

from griptape.drivers.embedding.cohere import CohereEmbeddingDriver

embedding_driver = CohereEmbeddingDriver(
    model="embed-english-v3.0",
    api_key=os.environ["COHERE_API_KEY"],
    input_type="search_document",
)

embeddings = embedding_driver.embed("Hello world!")

# display the first 3 embeddings
print(embeddings[:3])

[-0.041656494, -0.025970459, -0.07055664]

Nvidia NIM

The NvidiaNimEmbeddingDriver uses the Nvidia NIM API.

Info

The Nvidia NIM API is OpenAI compatible, except for a single parameter: input_type. This parameter is controlled by the keyword argument vector_operation when calling the driver embed methods.

Override Default Structure Embedding Driver

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

Code
Logs

from griptape.configs import Defaults
from griptape.configs.drivers import DriversConfig
from griptape.drivers.embedding.voyageai import VoyageAiEmbeddingDriver
from griptape.drivers.prompt.openai import OpenAiChatPromptDriver
from griptape.structures import Agent
from griptape.tools import PromptSummaryTool, WebScraperTool

Defaults.drivers_config = DriversConfig(
    prompt_driver=OpenAiChatPromptDriver(model="gpt-4.1"),
    embedding_driver=VoyageAiEmbeddingDriver(),
)

Defaults.drivers_config = DriversConfig(
    prompt_driver=OpenAiChatPromptDriver(model="gpt-4.1"),
    embedding_driver=VoyageAiEmbeddingDriver(),
)

agent = Agent(
    tools=[WebScraperTool(off_prompt=True), PromptSummaryTool(off_prompt=False)],
)

agent.run("based on https://www.griptape.ai/, tell me what Griptape is")

[02/27/25 20:23:16] INFO     PromptTask 4b8f768651fd4ac39d06cd14238e4936        
                             Input: based on https://www.griptape.ai/, tell me  
                             what Griptape is                                   
[02/27/25 20:23:17] INFO     Subtask 732b03a0ea584eae96fa88b3939c7caa           
                             Actions: [                                         
                               {                                                
                                 "tag": "call_1Ojazp5tjlXr2dUReQysFYkD",        
                                 "name": "WebScraperTool",                      
                                 "path": "get_content",                         
                                 "input": {                                     
                                   "values": {                                  
                                     "url": "https://www.griptape.ai/"          
                                   }                                            
                                 }                                              
                               }                                                
                             ]                                                  
[02/27/25 20:23:19] INFO     Subtask 732b03a0ea584eae96fa88b3939c7caa           
                             Response: You have attempted to use a              
                             DummyVectorStoreDriver's upsert_vector method. This
                             likely originated from using a `DriversConfig`     
                             without providing a Driver required for this       
                             feature.                                           
[02/27/25 20:23:20] INFO     Subtask 48815995dad34e5ca0232348543d4832           
                             Thought: I encountered an issue while trying to    
                             access the content of the Griptape website. Let me 
                             try to summarize the content again.                
                             Actions: [                                         
                               {                                                
                                 "tag": "call_AD6qAAlDndUZ7upj3riWNppE",        
                                 "name": "WebScraperTool",                      
                                 "path": "get_content",                         
                                 "input": {                                     
                                   "values": {                                  
                                     "url": "https://www.griptape.ai/"          
                                   }                                            
                                 }                                              
                               }                                                
                             ]                                                  
                    INFO     Subtask 48815995dad34e5ca0232348543d4832           
                             Response: You have attempted to use a              
                             DummyVectorStoreDriver's upsert_vector method. This
                             likely originated from using a `DriversConfig`     
                             without providing a Driver required for this       
                             feature.                                           
[02/27/25 20:23:21] INFO     PromptTask 4b8f768651fd4ac39d06cd14238e4936        
                             Output: I am unable to access the content of the   
                             Griptape website directly due to a technical issue.
                             However, you can visit the website                 
                             [Griptape](https://www.griptape.ai/) to learn more 
                             about what Griptape is. If you have any specific   
                             questions or need information on a particular      
                             aspect, feel free to ask!

← Prev

Structure Run

↑ Up

Prompt

Rerank

Could this page be better? Report a problem or suggest an addition!

Embedding

Overview

Embedding Drivers

OpenAI

OpenAI Compatible

Tip

Azure OpenAI

Bedrock Titan

Info

Google

Info

Hugging Face Hub

Info

Ollama

Info

Amazon SageMaker Jumpstart

Info

VoyageAI

Info

Cohere

Info

Nvidia NIM

Info

Override Default Structure Embedding Driver

← Prev

↑ Up

Next →