Elasticsearch

Elasticsearch stores documents in an Elasticsearch index and searches it by meaning, with filters on each document’s data.

A vector database stores texts so they can be searched by meaning, not just by exact words. That way an agent can find the paragraph of a manual that answers a question even if it uses different words.

When to use it

• Your company already has Elasticsearch and wants to use it as an agent’s knowledge base.
• You want to filter searches by dates, categories or other data.
• You need to create the index from the flow itself if it does not exist yet.

Configuration

The Operation field decides what the component does, and the fields and outputs change with your choice:

• Add (default): stores in the database the documents it receives in Ingest Data.
• Search: finds the documents closest to the text in Search Query.
• Retriever: offers the database as a search engine for another component to use, for example an agent or a question-answering chain.

You need an Elasticsearch credential with your Elasticsearch address and its key or user. See Credentials.

Field	What it does
Credential (required)	The Elasticsearch credential with the connection details.
Operation	What the component does: Add, Search or Retriever.
Ingest Data (required)	With Add. The documents to store, usually those coming out of a text splitter or a file loader.
Search Query	With Search. The text to search for. If left empty, nothing is returned.
Embedding	The connector where you plug the component that turns texts into numbers to compare them by meaning, such as OpenAI Embeddings. Always use the same one to store and to search.
Index Name (required)	The Elasticsearch index.

Advanced options

Field	What it does
Number Of Results	How many documents each search returns. Default: 4.
Distance Strategy	How similarity is measured: COSINE (default), EUCLIDEAN_DISTANCE or DOT_PRODUCT.
Verify SSL Certificates	Checks the server’s security certificate. On by default.
Create Index If Not Exists	Creates the index if it does not exist. When on, Embedding Dimensions appears: the vector size of the embeddings component.
Search Type	How to search: Similarity, Similarity with score threshold, MMR (Max Marginal Relevance). Similarity returns the closest; with a threshold, only those above Search Score Threshold; MMR looks for close but varied results.
Search Score Threshold	Minimum similarity score, only with the threshold search. Default: 0.0.
Filter by Metadata	Searches only among the documents whose data meet some conditions, for example brand equal to Vellani. Works with Search, Retriever and in tool mode. See Filter by metadata.

Filter by metadata

Besides its text, each document keeps some data (its metadata): the brand, the document type, the month… The filter makes the search look only at the documents whose data meet some conditions. It applies the same way to Results, to Retriever and when an agent uses the component as a tool.

Turn on Filter by Metadata (in the advanced options) and choose Filter Mode:

• Manual: you write the conditions on the node. In Number of Conditions you choose how many rows you want, and each row has:

  • Field: the data to check, for example brand.
  • Operator: Equal, NotEqual, GreaterThan, GreaterThanEqual, LessThan, LessThanEqual, In (one of a comma-separated list, such as Q90, S80), NotIn (none of the list) and Contains (the text or the list contains the value).
  • Type: Text, Int (whole number), Number (with decimals) or Boolean (true or false).
  • Value: the value to compare with. Left empty, that row does not filter.

  Combine Conditions decides whether all of them must match (AND) or one is enough (OR).

• Dynamic: the conditions arrive as JSON in Metadata Filter (JSON), from another component or written by an agent:

  • {"brand": "Vellani"}: exact value.
  • {"model": ["Q90", "S80"]}: any of the list.
  • {"year": {">=": 2024}, "status": {"!=": "archived"}}: with the operators =, !=, >, >=, <, <=, in, not in and contains.

  With several fields, all of them must match. Empty, it does not filter. A badly written JSON gives an error instead of searching without the filter.

Let the agent fill it in. With the component in tool mode, turn on tool mode for Value (with Field and Operator fixed, for example model and Equal) or for Metadata Filter (JSON). The agent writes the value when the question asks for it (“only the Q90 machine”) and leaves it empty when not. Tell it in the tool description which fields and values exist.

Lists. When a piece of data is a list, like the tags Metadata Tagger writes, Equal and In match when one of its items does, and Contains looks inside them.

In Elasticsearch texts compare exactly, Contains ignores upper/lower case and date-like texts (2026-08) compare as text. Indexes the component creates keep those values as text so the filter finds them.

Example: only one brand’s manuals

1. When storing, each chunk carries its data, for example type: manual and brand: Vellani (set by the file loader or by Metadata Tagger).
2. On the node with Operation set to Search, turn on Filter by Metadata, leave Filter Mode on Manual and fill in the row: Field brand, Operator Equal, Type Text, Value Vellani.
3. Search for “what does error E07 mean”: only chunks from Vellani documents come back.

The same filter in Dynamic mode is {"brand": "Vellani"}. Nodes saved earlier keep their filters; the new field names appear when you update the node.

Output

The outputs depend on Operation:

• Results: with Add and Search. With Search, the list of documents found, which you can pass to a prompt or an agent.
• Vector Store: with Add. The database, to connect it to components that work with a vector database.
• Retriever: with Retriever. The search engine, to connect it to components that ask for one.

In tool mode, an agent can use the component to search by itself. See Tool Mode.

Example

A law firm keeps rulings in Elasticsearch.

1. Add Elasticsearch with Operation set to Search and the rulings index.
2. Connect the embeddings component they were stored with.
3. Turn on Filter by Metadata to search only rulings from a given year.

Related components

• Recursive Character Text Splitter: cuts documents into pieces before storing them.
• OpenAI Embeddings: converts texts so they can be searched by meaning.