Update chromasdk peer dep, fix issues with using existing collections…

…, update docs

docs/docs/modules/indexes/vector_stores/integrations/chroma.mdx

@@ -0,0 +1,32 @@
+import CodeBlock from "@theme/CodeBlock";
+
+# Chroma
+
+Chroma is an open-source Apache 2.0 embedding database.
+
+## Setup
+
+1. Run chroma with Docker on your computer [docs](https://docs.trychroma.com/api-reference)
+2. Install the Chroma JS SDK.
+
+```bash npm2yarn
+npm install -S chromadb
+```
+
+## Usage, Index and query Documents
+
+import FromDocs from "@examples/indexes/vector_stores/chroma/fromDocs.ts";
+
+<CodeBlock language="typescript">{FromDocs}</CodeBlock>
+
+## Usage, Index and query texts
+
+import FromTexts from "@examples/indexes/vector_stores/chroma/fromTexts.ts";
+
+<CodeBlock language="typescript">{FromTexts}</CodeBlock>
+
+## Usage, Query docs from existing collection
+
+import Search from "@examples/indexes/vector_stores/chroma/search.ts";
+
+<CodeBlock language="typescript">{Search}</CodeBlock>

examples/package.json

@@ -29,7 +29,7 @@
     "@supabase/supabase-js": "^2.10.0",
     "@zilliz/milvus2-sdk-node": "^2.2.0",
     "axios": "^0.26.0",
-    "chromadb": "^1.3.0",
+    "chromadb": "^1.4.0",
     "graphql": "^16.6.0",
     "js-yaml": "^4.1.0",
     "langchain": "workspace:*",

examples/src/indexes/vector_stores/chroma/fromDocs.ts

@@ -0,0 +1,25 @@
+import { Chroma } from "langchain/vectorstores/chroma";
+import { OpenAIEmbeddings } from "langchain/embeddings/openai";
+import { TextLoader } from "langchain/document_loaders/fs/text";
+
+// Create docs with a loader
+const loader = new TextLoader("src/document_loaders/example_data/example.txt");
+const docs = await loader.load();
+
+// Create vector store and index the docs
+const vectorStore = await Chroma.fromDocuments(docs, new OpenAIEmbeddings(), {
+  collectionName: "a-test-collection",
+});
+
+// Search for the most similar document
+const response = await vectorStore.similaritySearch("hello", 1);
+
+console.log(response);
+/*
+[
+  Document {
+    pageContent: 'Foo\nBar\nBaz\n\n',
+    metadata: { source: 'src/document_loaders/example_data/example.txt' }
+  }
+]
+*/

examples/src/indexes/vector_stores/chroma/fromTexts.ts

@@ -0,0 +1,36 @@
+import { Chroma } from "langchain/vectorstores/chroma";
+import { OpenAIEmbeddings } from "langchain/embeddings/openai";
+
+// text sample from Godel, Escher, Bach
+const vectorStore = await Chroma.fromTexts(
+  [
+    `Tortoise: Labyrinth? Labyrinth? Could it Are we in the notorious Little
+        Harmonic Labyrinth of the dreaded Majotaur?`,
+    "Achilles: Yiikes! What is that?",
+    `Tortoise: They say-although I person never believed it myself-that an I
+        Majotaur has created a tiny labyrinth sits in a pit in the middle of
+        it, waiting innocent victims to get lost in its fears complexity.
+        Then, when they wander and dazed into the center, he laughs and
+        laughs at them-so hard, that he laughs them to death!`,
+    "Achilles: Oh, no!",
+    "Tortoise: But it's only a myth. Courage, Achilles.",
+  ],
+  [{ id: 2 }, { id: 1 }, { id: 3 }],
+  new OpenAIEmbeddings(),
+  {
+    collectionName: "godel-escher-bach",
+  }
+);
+
+const response = await vectorStore.similaritySearch("scared", 2);
+
+console.log(response);
+/*
+[
+  Document { pageContent: 'Achilles: Oh, no!', metadata: {} },
+  Document {
+    pageContent: 'Achilles: Yiikes! What is that?',
+    metadata: { id: 1 }
+  }
+]
+*/

examples/src/indexes/vector_stores/chroma/search.ts

@@ -0,0 +1,19 @@
+import { Chroma } from "langchain/vectorstores/chroma";
+import { OpenAIEmbeddings } from "langchain/embeddings/openai";
+
+const vectorStore = await Chroma.fromExistingCollection(
+  new OpenAIEmbeddings(),
+  { collectionName: "godel-escher-bach" }
+);
+
+const response = await vectorStore.similaritySearch("scared", 2);
+console.log(response);
+/*
+[
+  Document { pageContent: 'Achilles: Oh, no!', metadata: {} },
+  Document {
+    pageContent: 'Achilles: Yiikes! What is that?',
+    metadata: { id: 1 }
+  }
+]
+*/

examples/src/indexes/vector_stores/hnswlib_fromdocs.ts

@@ -2,17 +2,13 @@ import { HNSWLib } from "langchain/vectorstores/hnswlib";
 import { OpenAIEmbeddings } from "langchain/embeddings/openai";
 import { TextLoader } from "langchain/document_loaders/fs/text";
 
-export const run = async () => {
-  // Create docs with a loader
-  const loader = new TextLoader(
-    "src/document_loaders/example_data/example.txt"
-  );
-  const docs = await loader.load();
+// Create docs with a loader
+const loader = new TextLoader("src/document_loaders/example_data/example.txt");
+const docs = await loader.load();
 
-  // Load the docs into the vector store
-  const vectorStore = await HNSWLib.fromDocuments(docs, new OpenAIEmbeddings());
+// Load the docs into the vector store
+const vectorStore = await HNSWLib.fromDocuments(docs, new OpenAIEmbeddings());
 
-  // Search for the most similar document
-  const resultOne = await vectorStore.similaritySearch("hello world", 1);
-  console.log(resultOne);
-};
+// Search for the most similar document
+const result = await vectorStore.similaritySearch("hello world", 1);
+console.log(result);

langchain/package.json

@@ -302,6 +302,7 @@
     "@typescript-eslint/parser": "^5.51.0",
     "axios": "^0.26.0",
     "cheerio": "^1.0.0-rc.12",
+    "chromadb": "^1.4.0",
     "cohere-ai": "^5.0.2",
     "d3-dsv": "^2.0.0",
     "dotenv": "^16.0.3",
@@ -346,7 +347,7 @@
     "@zilliz/milvus2-sdk-node": "^2.2.0",
     "axios": "^0.26.0",
     "cheerio": "^1.0.0-rc.12",
-    "chromadb": "^1.3.0",
+    "chromadb": "^1.4.0",
     "cohere-ai": "^5.0.2",
     "d3-dsv": "^2.0.0",
     "epub2": "^3.0.1",

langchain/src/vectorstores/chroma.ts

@@ -1,20 +1,27 @@
 import { v4 as uuidv4 } from "uuid";
-import type { ChromaClient as ChromaClientT } from "chromadb";
+import type { ChromaClient as ChromaClientT, Collection } from "chromadb";
 
 import { Embeddings } from "../embeddings/base.js";
 import { VectorStore } from "./base.js";
 import { Document } from "../document.js";
 
-export interface ChromaLibArgs {
-  url?: string;
-  numDimensions?: number;
-  collectionName?: string;
-  index?: ChromaClientT;
-}
+export type ChromaLibArgs =
+  | {
+      url?: string;
+      numDimensions?: number;
+      collectionName?: string;
+    }
+  | {
+      index?: ChromaClientT;
+      numDimensions?: number;
+      collectionName?: string;
+    };
 
 export class Chroma extends VectorStore {
   index?: ChromaClientT;
 
+  collection?: Collection;
+
   collectionName: string;
 
   numDimensions?: number;
@@ -23,11 +30,14 @@ export class Chroma extends VectorStore {
 
   constructor(embeddings: Embeddings, args: ChromaLibArgs) {
     super(embeddings, args);
-    this.index = args.index;
     this.numDimensions = args.numDimensions;
     this.embeddings = embeddings;
     this.collectionName = ensureCollectionName(args.collectionName);
-    this.url = args.url || "http://localhost:8000";
+    if ("index" in args) {
+      this.index = args.index;
+    } else if ("url" in args) {
+      this.url = args.url || "http://localhost:8000";
+    }
   }
 
   async addDocuments(documents: Document[]): Promise<void> {
@@ -38,33 +48,26 @@ export class Chroma extends VectorStore {
     );
   }
 
-  async ensureCollection() {
-    if (!this.index) {
-      const { ChromaClient } = await Chroma.imports();
-      this.index = new ChromaClient(this.url);
-      try {
-        await this.index.createCollection(this.collectionName);
-      } catch {
-        // ignore error
+  async ensureCollection(): Promise<Collection> {
+    if (!this.collection) {
+      if (!this.index) {
+        const { ChromaClient } = await Chroma.imports();
+        this.index = new ChromaClient(this.url);
       }
+      this.collection = await this.index.getOrCreateCollection(
+        this.collectionName
+      );
     }
+
+    return this.collection;
   }
 
   async addVectors(vectors: number[][], documents: Document[]) {
     if (vectors.length === 0) {
       return;
     }
-    if (!this.index) {
-      if (this.numDimensions === undefined) {
-        this.numDimensions = vectors[0].length;
-      }
-      const { ChromaClient } = await Chroma.imports();
-      this.index = new ChromaClient(this.url);
-      try {
-        await this.index.createCollection(this.collectionName);
-      } catch {
-        // ignore error
-      }
+    if (this.numDimensions === undefined) {
+      this.numDimensions = vectors[0].length;
     }
     if (vectors.length !== documents.length) {
       throw new Error(`Vectors and metadatas must have the same length`);
@@ -75,7 +78,7 @@ export class Chroma extends VectorStore {
       );
     }
 
-    const collection = await this.index.getCollection(this.collectionName);
+    const collection = await this.ensureCollection();
     const docstoreSize = await collection.count();
     await collection.add(
       Array.from({ length: vectors.length }, (_, i) =>
@@ -88,12 +91,7 @@ export class Chroma extends VectorStore {
   }
 
   async similaritySearchVectorWithScore(query: number[], k: number) {
-    if (!this.index) {
-      throw new Error(
-        "Vector store not initialised yet. Try calling `addTexts` first."
-      );
-    }
-    const collection = await this.index.getCollection(this.collectionName);
+    const collection = await this.ensureCollection();
 
     // similaritySearchVectorWithScore supports one query vector at a time
     // chroma supports multiple query vectors at a time

yarn.lock

@@ -9858,12 +9858,12 @@ __metadata:
   languageName: node
   linkType: hard
 
-"chromadb@npm:^1.3.0":
-  version: 1.3.1
-  resolution: "chromadb@npm:1.3.1"
+"chromadb@npm:^1.4.0":
+  version: 1.4.1
+  resolution: "chromadb@npm:1.4.1"
   dependencies:
     axios: ^0.26.0
-  checksum: c3d2f766708d8a23f484717fa73fd2c255350652a4706b1b96becb031501648bff243337982190d0cd7d57c706df96a7de1c3ce331385dc452f183ed734957ee
+  checksum: 2b8e02e86577947e9f32d3faadb614b1a0ce60114d383ba7dd9997b519b1ff8e0b38f1a5c132371636ab07ed53f57b45cde3b454bcaa6710d5468358e1634114
   languageName: node
   linkType: hard
 
@@ -13008,7 +13008,7 @@ __metadata:
     "@typescript-eslint/parser": ^5.51.0
     "@zilliz/milvus2-sdk-node": ^2.2.0
     axios: ^0.26.0
-    chromadb: ^1.3.0
+    chromadb: ^1.4.0
     dotenv: ^16.0.3
     eslint: ^8.33.0
     eslint-config-airbnb-base: ^15.0.0
@@ -17151,6 +17151,7 @@ __metadata:
     binary-extensions: ^2.2.0
     browser-or-node: ^2.1.1
     cheerio: ^1.0.0-rc.12
+    chromadb: ^1.4.0
     cohere-ai: ^5.0.2
     d3-dsv: ^2.0.0
     dotenv: ^16.0.3
@@ -17206,7 +17207,7 @@ __metadata:
     "@zilliz/milvus2-sdk-node": ^2.2.0
     axios: ^0.26.0
     cheerio: ^1.0.0-rc.12
-    chromadb: ^1.3.0
+    chromadb: ^1.4.0
     cohere-ai: ^5.0.2
     d3-dsv: ^2.0.0
     epub2: ^3.0.1