VertexAI Embeddings
VertexAI Embeddings turns text into a numeric fingerprint of its meaning using the models of Vertex AI, the AI service of Google Cloud. With that fingerprint, NappAI can find the documents that say something similar to what you are looking for, even when they use different words, for example in a knowledge base.
You connect the component to a vector database, which uses it both to store your documents and to search them. Use it if your company works with Google Cloud and wants the text to be processed in its own project.
When to use it
- Give an agent the knowledge in your manuals, contracts or FAQs by storing them in a vector database.
- Build an internal search that finds documents by their meaning, not only by exact words.
- Your company already has a Google Cloud project with Vertex AI enabled.
Configuration
This component does not use your NappAI account’s credentials: it connects with the key file of a Google Cloud service account that you upload in Credentials.
| Field | What it does |
|---|---|
| Credentials | The key file (JSON) of your Google Cloud project’s service account. The person who manages the project downloads it. |
| Model Name | The name of the Vertex AI model that calculates the fingerprints. Default: text-embedding-005. |
Advanced options
| Field | What it does |
|---|---|
| Project | The ID of your Google Cloud project. Empty: the project of the credentials file. |
| Location | The Google Cloud region where the model is used. Default: us-central1. |
| Max Retries | How many times a failed request is retried. Default: 1. |
Batch processing
With the Batch Mode switch on, the component runs once for each item of the list you connect to Batch Input and returns all the results together as a list. Parallel Executions sets how many items are processed at the same time (1 to 5). Skip if Empty Batch Input skips the component when the list arrives empty, and Skip Branch if Empty Output stops the following components when the result is empty. More in Key concepts.
Output
- Embeddings: the model that calculates the fingerprints, ready to use. Connect it to the Embedding input of a vector database: Astra DB, Cassandra, Chroma DB, Couchbase, Elasticsearch, FAISS, Milvus, MongoDB Vector Store, PGVector, Pinecone, Qdrant, Redis, Supabase Vector Store, Upstash, Vectara, Weaviate Cloud (v4). Other components with an input of this type accept it too, such as Semantic Text Splitter or Text Embedder.
Example
An insurer, Seguros Arnau, wants its assistant to answer using the terms of its policies.
- In a loading flow, split the documents into chunks with Recursive Character Text Splitter and pass them to Chroma DB with Operation set to
Add. - Add VertexAI Embeddings and connect its Embeddings output to the Embedding input of Chroma DB.
- In the assistant flow, use the same Chroma DB collection with the same VertexAI Embeddings component to find the chunks that answer each question.