Skip to content
Nappai Documentation

PGVector

PGVector stores documents in a PostgreSQL database with the pgvector extension and searches it by meaning.

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

  • You already have PostgreSQL and do not want another database for search by meaning.
  • You want your knowledge base documents next to the rest of your data.

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 a Postgres SQL credential with your PostgreSQL connection address. See Credentials.

FieldWhat it does
Credential (required)The Postgres SQL credential with the connection details.
OperationWhat 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 QueryWith Search. The text to search for. If left empty, nothing is returned.
EmbeddingThe 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.
Table (required)The name of the collection where documents are stored.

Advanced options

FieldWhat it does
Number of ResultsHow many documents each search returns. Default: 4.
Filter by MetadataSearches 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 PGVector numbers compare as numbers and texts alphabetically, which works for dates such as 2026-08. Contains ignores upper/lower case.

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 town council wants an assistant that answers from its bylaws, kept in its PostgreSQL.

  1. Connect the bylaws, split into pieces, to Ingest Data of PGVector with Operation set to Add and Table bylaws.
  2. Connect an embeddings component and run the flow.
  3. In the assistant, use another PGVector with Operation set to Search in tool mode.

Good practices

  • For fixed filters or filters the agent fills in, use Filter by metadata; if you prefer a model to write the filter from the question, SelfQueryRetriever also works on this database.

See also

  • Vector databases: how FAISS, Chroma, Qdrant, PGVector and Neo4j differ, and which one to choose.