Chroma vector store integration.
Setup:
Install @langchain/community and chromadb.
npm install @langchain/community chromadbimport { Chroma } from '@langchain/community/vectorstores/chroma';
// Or other embeddings
import { OpenAIEmbeddings } from '@langchain/openai';
const embeddings = new OpenAIEmbeddings({
model: "text-embedding-3-small",
})
const vectorStore = new Chroma(
embeddings,
{
collectionName: "foo",
host: "localhost",
}
);import type { Document } from '@langchain/core/documents';
const document1 = { pageContent: "foo", metadata: { baz: "bar" } };
const document2 = { pageContent: "thud", metadata: { bar: "baz" } };
const document3 = { pageContent: "I will be deleted :(", metadata: {} };
const documents: Document[] = [document1, document2, document3];
const ids = ["1", "2", "3"];
await vectorStore.addDocuments(documents, { ids });await vectorStore.delete({ ids: ["3"] });const results = await vectorStore.similaritySearch("thud", 1);
for (const doc of results) {
console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}
// Output: * thud [{"baz":"bar"}]const resultsWithFilter = await vectorStore.similaritySearch("thud", 1, { baz: "bar" });
for (const doc of resultsWithFilter) {
console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}
// Output: * foo [{"baz":"bar"}]const resultsWithScore = await vectorStore.similaritySearchWithScore("qux", 1);
for (const [doc, score] of resultsWithScore) {
console.log(`* [SIM=${score.toFixed(6)}] ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}
// Output: * [SIM=0.000000] qux [{"bar":"baz","baz":"bar"}]const retriever = vectorStore.asRetriever({
searchType: "mmr", // Leave blank for standard similarity search
k: 1,
});
const resultAsRetriever = await retriever.invoke("thud");
console.log(resultAsRetriever);
// Output: [Document({ metadata: { "baz":"bar" }, pageContent: "thud" })]Embeddings interface for generating vector embeddings from text queries, enabling vector-based similarity searches.
Returns a string representing the type of vector store, which subclasses must implement to identify their specific vector storage type.
Adds documents to the Chroma database. The documents are first
converted to vectors using the embeddings instance, and then added to
the database.
Adds vectors to the Chroma database. The vectors are associated with the provided documents.
Creates a VectorStoreRetriever instance with flexible configuration options.
Deletes documents from the Chroma database. The documents to be deleted
can be specified by providing an array of ids or a filter object.
Ensures that a collection exists in the Chroma database. If the collection does not exist, it is created.
Return documents selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to the query AND diversity among selected documents.
Searches for documents similar to a text query by embedding the query and performing a similarity search on the resulting vector.
Searches for vectors in the Chroma database that are similar to the
provided query vector. The search can be filtered using the provided
filter object or the filter property of the Chroma instance.
Searches for documents similar to a text query by embedding the query, and returns results with similarity scores.
Creates a new Chroma instance from an array of Document instances.
The documents are added to the Chroma database.
Creates a new Chroma instance from an existing collection in the
Chroma database.
Creates a new Chroma instance from an array of text strings. The text
strings are converted to Document instances and added to the Chroma
database.
The name of the serializable. Override to provide an alias or to preserve the serialized module name in minified environments.
Implemented as a static method to support loading logic.