
# embedding_search

[LangChain](https://js.langchain.com/docs/) is a framework for developing applications powered by language models with a plugable architecture.

`langchain-embedding_search` uses a Supabase Postgres database as its vector store.

## Installation

```sql
select dbdev.install('langchain-embedding_search');
create extension if not exists vector;
create extension "langchain-embedding_search"
    schema public
    version '1.1.0';
```
Note:

`vector` is a dependency of `langchain-embedding_search`.
Dependency resolution is currently under development.
In the near future it will not be necessary to manually create dependencies.


### Standard Usage

The below example shows how to perform a basic similarity search with Supabase:

Once created, you can access the vector store for search using langchain as shown below:

```js
import { SupabaseVectorStore } from "langchain/vectorstores/supabase";
import { OpenAIEmbeddings } from "langchain/embeddings/openai";
import { createClient } from "@supabase/supabase-js";

const privateKey = process.env.SUPABASE_PRIVATE_KEY;
if (!privateKey) throw new Error(`Expected env var SUPABASE_PRIVATE_KEY`);

const url = process.env.SUPABASE_URL;
if (!url) throw new Error(`Expected env var SUPABASE_URL`);

export const run = async () => {
  const client = createClient(url, privateKey);

  const vectorStore = await SupabaseVectorStore.fromTexts(
    ["Hello world", "Bye bye", "What's this?"],
    [{ id: 2 }, { id: 1 }, { id: 3 }],
    new OpenAIEmbeddings(),
    {
      client,
      tableName: "documents",
      queryName: "match_documents",
    }
  );

  const resultOne = await vectorStore.similaritySearch("Hello world", 1);

  console.log(resultOne);
};
```

### Metadata Filtering

Given the above `match_documents` Postgres function, you can also pass a filter parameter to only documents with a specific metadata field value.

```js
import { SupabaseVectorStore } from "langchain/vectorstores/supabase";
import { OpenAIEmbeddings } from "langchain/embeddings/openai";
import { createClient } from "@supabase/supabase-js";

// First, follow set-up instructions at
// https://js.langchain.com/docs/modules/indexes/vector_stores/integrations/supabase

const privateKey = process.env.SUPABASE_PRIVATE_KEY;
if (!privateKey) throw new Error(`Expected env var SUPABASE_PRIVATE_KEY`);

const url = process.env.SUPABASE_URL;
if (!url) throw new Error(`Expected env var SUPABASE_URL`);

export const run = async () => {
  const client = createClient(url, privateKey);

  const vectorStore = await SupabaseVectorStore.fromTexts(
    ["Hello world", "Hello world", "Hello world"],
    [{ user_id: 2 }, { user_id: 1 }, { user_id: 3 }],
    new OpenAIEmbeddings(),
    {
      client,
      tableName: "documents",
      queryName: "match_documents",
    }
  );

  const result = await vectorStore.similaritySearch("Hello world", 1, {
    user_id: 3,
  });

  console.log(result);
};
```

For more details, checkout the LangChain Supabase integration docs: https://js.langchain.com/docs/modules/indexes/vector_stores/integrations/supabase


Search documents by embedding and full text


# hybrid_search

Langchain supports hybrid search with a Supabase Postgres database. The hybrid search combines the postgres pgvector extension (similarity search) and Full-Text Search (keyword search) to retrieve documents. You can add documents via SupabaseVectorStore addDocuments function. SupabaseHybridKeyWordSearch accepts embedding, supabase client, number of results for similarity search, and number of results for keyword search as parameters. The getRelevantDocuments function produces a list of documents that has duplicates removed and is sorted by relevance score.

## Installation

```sql
select dbdev.install('langchain-hybrid_search');
create extension if not exists vector;
create extension "langchain-hybrid_search"
    schema public
    version '1.1.0';
```
Note:

`vector` is a dependency of `langchain-hybrid_search`.
Dependency resolution is currently under development.
In the near future it will not be necessary to manually create dependencies.


Once created, you can access the vector store for search using langchain as shown below:

```js
import { OpenAIEmbeddings } from "langchain/embeddings/openai";
import { createClient } from "@supabase/supabase-js";
import { SupabaseHybridSearch } from "langchain/retrievers/supabase";

const privateKey = process.env.SUPABASE_PRIVATE_KEY;
if (!privateKey) throw new Error(`Expected env var SUPABASE_PRIVATE_KEY`);

const url = process.env.SUPABASE_URL;
if (!url) throw new Error(`Expected env var SUPABASE_URL`);

export const run = async () => {
  const client = createClient(url, privateKey);

  const embeddings = new OpenAIEmbeddings();

  const retriever = new SupabaseHybridSearch(embeddings, {
    client,
    //  Below are the defaults, expecting that you set up your supabase table and functions according to the guide above. Please change if necessary.
    similarityK: 2,
    keywordK: 2,
    tableName: "documents",
    similarityQueryName: "match_documents",
    keywordQueryName: "kw_match_documents",
  });

  const results = await retriever.getRelevantDocuments("hello bye");

  console.log(results);
};
```

For more details, checkout the LangChain Supabase Hybrid Search docs: https://js.langchain.com/docs/modules/indexes/retrievers/supabase-hybrid


langchain

Packages