OllamaDocumentEmbedder

Calculate document embeddings using Ollama models. Document embedders are used to embed documents in your indexes.

Basic Information

• Type: haystack_integrations.components.embedders.ollama.document_embedder.OllamaDocumentEmbedder
• Components it can connect with:
  • Converters and Preprocessors: OllamaDocumentEmbedder can receive documents to embed from a converter, such as TextFileToDocument or a preprocessor, such as DocumentSplitter.
  • DocumentWriter: OllamaDocumentEmbedder sends embedded documents to DocumentWriter that writes them into a document store.

Inputs

Parameter	Type	Default	Description
documents	List[Document]		Documents to be converted to an embedding.
generation_kwargs	Optional[Dict[str, Any]]	None	Optional arguments to pass to the Ollama generation endpoint, such as temperature, top_p, etc. See the Ollama docs.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		Documents with their embeddings added to the embedding field.
meta	Dict[str, Any]		Metadata about the request, including the model name.

Overview

OllamaDocumentEmbedder computes the embeddings of a list of documents and stores the obtained vectors in the embedding field of each document. It uses embedding models compatible with the Ollama Library.

Ollama is a project focused on running LLMs locally. This means you can run embedding models on your own infrastructure without relying on external API services.

This component embeds documents. To embed a string (like a query), use the OllamaTextEmbedder.

Embedding Models in Query Pipelines and Indexes

The embedding model you use to embed documents in your indexing pipeline must be the same as the embedding model you use to embed the query in your query pipeline.

This means the embedders for your indexing and query pipelines must match. For example, if you use CohereDocumentEmbedder to embed your documents, you should use CohereTextEmbedder with the same model to embed your queries.

Compatible Models

Unless specified otherwise, the default embedding model is nomic-embed-text. See other pre-built models in Ollama's library. To load your own custom model, follow the instructions from Ollama.

Prerequisites

You need a running Ollama instance with the embedding model pulled. The component uses http://localhost:11434 as the default URL.

Usage Example

Using the Component in an Index

In this index, OllamaDocumentEmbedder receives documents from DocumentSplitter and embeds them. It then sends the embedded documents to DocumentWriter that writes them into a document store. The index is configured to use the nomic-embed-text model, which means OllamaTextEmbedder used in the query pipeline must also use the same model.

components:
  TextFileToDocument:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8
      store_full_path: false
  DocumentSplitter:
    type: haystack.components.preprocessors.document_splitter.DocumentSplitter
    init_parameters:
      split_by: word
      split_length: 200
      split_overlap: 0
      split_threshold: 0
      splitting_function:
  OllamaDocumentEmbedder:
    type: haystack_integrations.components.embedders.ollama.document_embedder.OllamaDocumentEmbedder
    init_parameters:
      model: nomic-embed-text
      url: http://localhost:11434
      generation_kwargs:
      timeout: 120
      prefix: ''
      suffix: ''
      progress_bar: true
      meta_fields_to_embed:
      embedding_separator: "\n"
      batch_size: 32
  DocumentWriter:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: ollama-embeddings-index
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
          similarity: cosine
      policy: NONE

connections:
- sender: TextFileToDocument.documents
  receiver: DocumentSplitter.documents
- sender: DocumentSplitter.documents
  receiver: OllamaDocumentEmbedder.documents
- sender: OllamaDocumentEmbedder.documents
  receiver: DocumentWriter.documents

max_runs_per_component: 100

metadata: {}

inputs:
  files:
  - TextFileToDocument.sources

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model	str	nomic-embed-text	The name of the model to use. The model should be available in the running Ollama instance.
url	str	http://localhost:11434	The URL of a running Ollama instance.
generation_kwargs	Optional[Dict[str, Any]]	None	Optional arguments to pass to the Ollama generation endpoint, such as temperature, top_p, and others. See the available arguments in Ollama docs.
timeout	int	120	The number of seconds before throwing a timeout error from the Ollama API.
prefix	str		A string to add at the beginning of each text.
suffix	str		A string to add at the end of each text.
progress_bar	bool	True	If True, shows a progress bar when running.
meta_fields_to_embed	Optional[List[str]]	None	List of metadata fields to embed along with the document text.
embedding_separator	str	\n	Separator used to concatenate the metadata fields to the document text.
batch_size	int	32	Number of documents to process at once.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
documents	List[Document]		Documents to be converted to an embedding.
generation_kwargs	Optional[Dict[str, Any]]	None	Optional arguments to pass to the Ollama generation endpoint, such as temperature, top_p, etc. See the Ollama docs.