Ollama Embeddings

Ollama Embeddings turns text into a numeric fingerprint of its meaning using a model installed in Ollama, the tool for running AI models on your own server. 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 you want the text to stay on a server your company controls.

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 server running Ollama and does not want to depend on an outside service.

Configuration

Field	What it does
Ollama Model	The name of the model installed on your Ollama server that calculates the fingerprints. Default: llama3.1. Type the name of an embeddings model you have installed.
Ollama Base URL	The address of your Ollama server. It must be reachable from NappAI.

Advanced options

Field	What it does
Model Temperature	A setting inherited from models that write text. Default: 0.1. You do not need to change it.

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.

Texts are sent to the model exactly as they are, with no prefix. Until October 2026 the component put passage: / query: in front of every text; if you created a vector database with it before then, add the documents again so searches compare like with like.

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), Neo4j. Also the Embedding input of Neo4j GraphRAG. Other components with an input of this type accept it too, such as Semantic Text Splitter or Text Embedder.

Use the same model to store and to search

Fingerprints from two different models cannot be compared with each other. Use the same component and the same model to store the documents and to search them. If you change the model, store the documents in the database again.

Example

A town council, Ayuntamiento de Villalba, wants its assistant to answer using its municipal bylaws, without them leaving its server.

1. 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.
2. Add Ollama Embeddings and connect its Embeddings output to the Embedding input of Chroma DB.
3. In the assistant flow, use the same Chroma DB collection with the same Ollama Embeddings component to find the chunks that answer each question.

Related components

• Chroma DB
• PGVector
• Text Embedder
• Embedding Similarity
• FastEmbed Embeddings (Local): fingerprints calculated inside NappAI, with no server of your own.

To choose a model and a vector database, see Vector databases in the RAG guide.