Notebooks
W
Weaviate Rag Anthropic Claude 3 Opus

Rag Anthropic Claude 3 Opus

vector-searchvector-databaseretrieval-augmented-generationllm-frameworksweaviate-featuresfunction-callingweaviate-recipesmodel-providersPythongenerative-aianthropic
alph-notebooks/weaviate-recipes / rag_anthropic_claude-3-opus.ipynb

Open In Colab

Generative Search with Anthropic

Weaviate integrates with models from Anthropic through their API.

This recipe will show you how to generate embeddings using Voyage AI and use Anthropic's generative model.

Requirements

  1. Weaviate cluster

    1. You can create a 14-day free sandbox on WCD
    2. Embedded Weaviate
    3. Local deployment
    4. Other options

  2. Voyage AI API key. Grab one here.

  3. Anthropic API key. Grab one here.

[1]

Connect to Weaviate

Only choose one option from the below.

Weaviate Cloud Deployment

[ ]

Embedded Weaviate

[ ]

Local Deployment

[ ]

Create a collection

Collection stores your data and vector embeddings.

Full list of generative models

[ ]

Import the Data

[ ]

Generative Search Queries

Single Result

Single Result makes a generation for each individual search result.

In the below example, I want to create a Facebook ad from the Jeopardy question about Elephants.

[ ]

Grouped Result

Grouped Result generates a single response from all the search results.

The below example is creating a Facebook ad from the 2 retrieved Jeoprady questions about animals.

[ ]