How can I get document id(idColumnName) when using PGVector similaritySearch

[ExlauChen]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

const documents = await vectorStore.similaritySearch(query, limit);

Description

when I call "PGVectorStore.similaritySearch()" results are like this: [{metadata:{...},pageContent:"..."}], I want to get the document id also, how can I do that?

System Info

[dosubot[bot]]

Hello, @ExlauChen! I'm a bot designed to help you with bug fixes, answer questions, and even guide you to become a contributor. How can I assist you today?

To get the document id (idColumnName) when using PGVectorStore's similaritySearch, you can access the id field from the results returned by the similaritySearch method. Here is an example:

const results = await pgvectorVectorStore.similaritySearch(query, limit);

const documentIds = results.map(result => result[pgvectorVectorStore.idColumnName]);

console.log(documentIds);

In this example, results will contain the documents that match the similarity search, and documentIds will be an array of the id values of those documents. The idColumnName is dynamically accessed from the pgvectorVectorStore instance ^[1][2].

To continue talking to Dosu, mention @dosu.