From bbc8c8787dd066f5cc608bce60dc65b600cd08dc Mon Sep 17 00:00:00 2001
From: Thuc Pham <51660321+thucpn@users.noreply.github.com>
Date: Thu, 6 Mar 2025 16:24:05 +0700
Subject: [PATCH] fix: prefer using embedding model from vector store (#1708)
---
.changeset/tame-chairs-shake.md | 9 +++
.../available_embeddings/jinaai.mdx | 5 +-
.../available_embeddings/together.mdx | 5 +-
.../modules/llms/available_llms/deepseek.mdx | 6 +-
.../modules/llms/available_llms/fireworks.mdx | 3 +-
.../modules/llms/available_llms/together.mdx | 3 +-
examples/deepseek.ts | 46 +++++++++++++
examples/multimodal/jina.ts | 8 +--
examples/package.json | 4 ++
examples/qdrantdb/with-gemini.ts | 33 +++++++++
examples/qdrantdb/with-jina.ts | 27 ++++++++
examples/readers/src/pdf_fw.ts | 3 +-
examples/together-ai.ts | 2 +-
examples/together-ai/vector-index.ts | 9 +--
.../src/embeddings/OpenAIEmbedding.ts | 1 -
packages/llamaindex/src/embeddings/index.ts | 5 --
packages/llamaindex/src/index.edge.ts | 4 +-
packages/llamaindex/src/index.ts | 3 -
.../src/indices/vectorStore/index.ts | 2 +-
packages/llamaindex/src/llm/index.ts | 4 --
packages/llamaindex/src/llm/openai.ts | 1 -
.../tests/MetadataExtractors.test.ts | 4 +-
packages/llamaindex/tests/Selectors.test.ts | 2 +-
.../tests/indices/SummaryIndex.test.ts | 8 +--
.../tests/indices/VectorStoreIndex.test.ts | 35 ++++++++--
.../llamaindex/tests/utility/mockOpenAI.ts | 6 +-
.../tests/utility/mockStorageContext.ts | 21 ++++--
packages/providers/deepseek/package.json | 39 +++++++++++
packages/providers/deepseek/src/index.ts | 1 +
.../deepseek/src/llm.ts} | 0
packages/providers/deepseek/tsconfig.json | 19 ++++++
packages/providers/fireworks/package.json | 39 +++++++++++
.../fireworks/src/embedding.ts} | 0
packages/providers/fireworks/src/index.ts | 2 +
.../fireworks/src/llm.ts} | 0
packages/providers/fireworks/tsconfig.json | 19 ++++++
packages/providers/jinaai/package.json | 40 +++++++++++
.../jinaai/src/embedding.ts} | 4 +-
packages/providers/jinaai/src/index.ts | 1 +
packages/providers/jinaai/tsconfig.json | 19 ++++++
packages/providers/together/package.json | 39 +++++++++++
.../together/src/embedding.ts} | 0
packages/providers/together/src/index.ts | 2 +
.../together/src/llm.ts} | 0
packages/providers/together/tsconfig.json | 19 ++++++
pnpm-lock.yaml | 67 +++++++++++++++++++
tsconfig.json | 12 ++++
47 files changed, 518 insertions(+), 63 deletions(-)
create mode 100644 .changeset/tame-chairs-shake.md
create mode 100644 examples/deepseek.ts
create mode 100644 examples/qdrantdb/with-gemini.ts
create mode 100644 examples/qdrantdb/with-jina.ts
delete mode 100644 packages/llamaindex/src/embeddings/OpenAIEmbedding.ts
delete mode 100644 packages/llamaindex/src/embeddings/index.ts
delete mode 100644 packages/llamaindex/src/llm/index.ts
delete mode 100644 packages/llamaindex/src/llm/openai.ts
create mode 100644 packages/providers/deepseek/package.json
create mode 100644 packages/providers/deepseek/src/index.ts
rename packages/{llamaindex/src/llm/deepseek.ts => providers/deepseek/src/llm.ts} (100%)
create mode 100644 packages/providers/deepseek/tsconfig.json
create mode 100644 packages/providers/fireworks/package.json
rename packages/{llamaindex/src/embeddings/fireworks.ts => providers/fireworks/src/embedding.ts} (100%)
create mode 100644 packages/providers/fireworks/src/index.ts
rename packages/{llamaindex/src/llm/fireworks.ts => providers/fireworks/src/llm.ts} (100%)
create mode 100644 packages/providers/fireworks/tsconfig.json
create mode 100644 packages/providers/jinaai/package.json
rename packages/{llamaindex/src/embeddings/JinaAIEmbedding.ts => providers/jinaai/src/embedding.ts} (97%)
create mode 100644 packages/providers/jinaai/src/index.ts
create mode 100644 packages/providers/jinaai/tsconfig.json
create mode 100644 packages/providers/together/package.json
rename packages/{llamaindex/src/embeddings/together.ts => providers/together/src/embedding.ts} (100%)
create mode 100644 packages/providers/together/src/index.ts
rename packages/{llamaindex/src/llm/together.ts => providers/together/src/llm.ts} (100%)
create mode 100644 packages/providers/together/tsconfig.json
diff --git a/.changeset/tame-chairs-shake.md b/.changeset/tame-chairs-shake.md
new file mode 100644
index 000000000..7e9e02b1d
--- /dev/null
+++ b/.changeset/tame-chairs-shake.md
@@ -0,0 +1,9 @@
+---
+"llamaindex": patch
+"@llamaindex/deepseek": patch
+"@llamaindex/fireworks": patch
+"@llamaindex/together": patch
+"@llamaindex/jinaai": patch
+---
+
+fix: prefer using embedding model from vector store
diff --git a/apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/jinaai.mdx b/apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/jinaai.mdx
index 6a308ec0d..0af1e1af2 100644
--- a/apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/jinaai.mdx
+++ b/apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/jinaai.mdx
@@ -2,10 +2,11 @@
title: Jina AI
---
-To use Jina AI embeddings, you need to import `JinaAIEmbedding` from `llamaindex`.
+To use Jina AI embeddings, you need to import `JinaAIEmbedding` from `@llamaindex/jinaai`.
```ts
-import { JinaAIEmbedding, Settings } from "llamaindex";
+import { Settings } from "llamaindex";
+import { JinaAIEmbedding } from "@llamaindex/jinaai";
Settings.embedModel = new JinaAIEmbedding();
diff --git a/apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/together.mdx b/apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/together.mdx
index 7d5a6a832..30c83e0fa 100644
--- a/apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/together.mdx
+++ b/apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/together.mdx
@@ -2,10 +2,11 @@
title: Together
---
-To use together embeddings, you need to import `TogetherEmbedding` from `llamaindex`.
+To use together embeddings, you need to import `TogetherEmbedding` from `@llamaindex/together`.
```ts
-import { TogetherEmbedding, Settings } from "llamaindex";
+import { Settings } from "llamaindex";
+import { TogetherEmbedding } from "@llamaindex/together";
Settings.embedModel = new TogetherEmbedding({
apiKey: "<YOUR_API_KEY>",
diff --git a/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/deepseek.mdx b/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/deepseek.mdx
index 928164ec8..e197eff56 100644
--- a/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/deepseek.mdx
+++ b/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/deepseek.mdx
@@ -7,7 +7,8 @@ title: DeepSeek LLM
## Usage
```ts
-import { DeepSeekLLM, Settings } from "llamaindex";
+import { Settings } from "llamaindex";
+import { DeepSeekLLM } from "@llamaindex/deepseek";
Settings.llm = new DeepSeekLLM({
apiKey: "<YOUR_API_KEY>",
@@ -18,7 +19,8 @@ Settings.llm = new DeepSeekLLM({
## Example
```ts
-import { DeepSeekLLM, Document, VectorStoreIndex, Settings } from "llamaindex";
+import { Document, VectorStoreIndex, Settings } from "llamaindex";
+import { DeepSeekLLM } from "@llamaindex/deepseek";
const deepseekLlm = new DeepSeekLLM({
apiKey: "<YOUR_API_KEY>",
diff --git a/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/fireworks.mdx b/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/fireworks.mdx
index 1680de683..328ba4e24 100644
--- a/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/fireworks.mdx
+++ b/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/fireworks.mdx
@@ -7,7 +7,8 @@ title: Fireworks LLM
## Usage
```ts
-import { FireworksLLM, Settings } from "llamaindex";
+import { Settings } from "llamaindex";
+import { FireworksLLM } from "@llamaindex/fireworks";
Settings.llm = new FireworksLLM({
apiKey: "<YOUR_API_KEY>",
diff --git a/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/together.mdx b/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/together.mdx
index 65cc58c41..a9877cfa3 100644
--- a/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/together.mdx
+++ b/apps/next/src/content/docs/llamaindex/modules/llms/available_llms/together.mdx
@@ -23,7 +23,8 @@ import { Tab, Tabs } from "fumadocs-ui/components/tabs";
## Usage
```ts
-import { Settings, TogetherLLM } from "llamaindex";
+import { Settings } from "llamaindex";
+import { TogetherLLM } from "@llamaindex/together";
Settings.llm = new TogetherLLM({
apiKey: "<YOUR_API_KEY>",
diff --git a/examples/deepseek.ts b/examples/deepseek.ts
new file mode 100644
index 000000000..1a9b49444
--- /dev/null
+++ b/examples/deepseek.ts
@@ -0,0 +1,46 @@
+import { DeepSeekLLM } from "@llamaindex/deepseek";
+
+// process.env.DEEPSEEK_API_KEY is required
+const deepseek = new DeepSeekLLM({
+ apiKey: process.env.DEEPSEEK_API_KEY,
+ model: "deepseek-coder", // or "deepseek-chat"
+});
+
+(async () => {
+ // Example of non-streaming chat
+ const response = await deepseek.chat({
+ messages: [
+ {
+ role: "system",
+ content: "You are an AI assistant",
+ },
+ {
+ role: "user",
+ content: "Tell me about San Francisco",
+ },
+ ],
+ stream: false,
+ });
+ console.log("Response from DeepSeek AI:");
+ console.log(response);
+
+ // Example of streaming chat
+ const generator = await deepseek.chat({
+ messages: [
+ {
+ role: "system",
+ content: "You are an AI assistant",
+ },
+ {
+ role: "user",
+ content: "Write a short poem about San Francisco",
+ },
+ ],
+ stream: true,
+ });
+ console.log("\nStreaming response from DeepSeek AI...");
+ for await (const message of generator) {
+ process.stdout.write(message.delta);
+ }
+ console.log("\n");
+})();
diff --git a/examples/multimodal/jina.ts b/examples/multimodal/jina.ts
index 1c3081d0f..e5adc1042 100644
--- a/examples/multimodal/jina.ts
+++ b/examples/multimodal/jina.ts
@@ -1,10 +1,6 @@
+import { JinaAIEmbedding } from "@llamaindex/jinaai";
import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
-import {
- ImageDocument,
- JinaAIEmbedding,
- similarity,
- SimilarityType,
-} from "llamaindex";
+import { ImageDocument, similarity, SimilarityType } from "llamaindex";
import path from "path";
async function main() {
diff --git a/examples/package.json b/examples/package.json
index 16672acaf..4e439d460 100644
--- a/examples/package.json
+++ b/examples/package.json
@@ -44,6 +44,10 @@
"@llamaindex/voyage-ai": "^1.0.3",
"@llamaindex/weaviate": "^0.0.11",
"@llamaindex/workflow": "^0.0.13",
+ "@llamaindex/deepseek": "^0.0.1",
+ "@llamaindex/fireworks": "^0.0.1",
+ "@llamaindex/together": "^0.0.1",
+ "@llamaindex/jinaai": "^0.0.1",
"@notionhq/client": "^2.2.15",
"@pinecone-database/pinecone": "^4.0.0",
"@vercel/postgres": "^0.10.0",
diff --git a/examples/qdrantdb/with-gemini.ts b/examples/qdrantdb/with-gemini.ts
new file mode 100644
index 000000000..0c199a55d
--- /dev/null
+++ b/examples/qdrantdb/with-gemini.ts
@@ -0,0 +1,33 @@
+import {
+ GEMINI_EMBEDDING_MODEL,
+ GeminiEmbedding,
+ GeminiSession,
+} from "@llamaindex/google";
+import { QdrantVectorStore } from "@llamaindex/qdrant";
+import {
+ Document,
+ storageContextFromDefaults,
+ VectorStoreIndex,
+} from "llamaindex";
+
+const embedding = new GeminiEmbedding({
+ model: GEMINI_EMBEDDING_MODEL.EMBEDDING_001,
+ session: new GeminiSession({
+ apiKey: process.env.GEMINI_API_KEY,
+ }),
+});
+
+async function main() {
+ const docs = [new Document({ text: "Lorem ipsum dolor sit amet" })];
+ const vectorStore = new QdrantVectorStore({
+ url: process.env.QDRANT_URL,
+ apiKey: process.env.QDRANT_API_KEY,
+ embeddingModel: embedding,
+ collectionName: "gemini_test",
+ });
+ const storageContext = await storageContextFromDefaults({ vectorStore });
+ await VectorStoreIndex.fromDocuments(docs, { storageContext });
+ console.log("Inizialized vector store successfully");
+}
+
+void main().catch((err) => console.error(err));
diff --git a/examples/qdrantdb/with-jina.ts b/examples/qdrantdb/with-jina.ts
new file mode 100644
index 000000000..f51f27e4e
--- /dev/null
+++ b/examples/qdrantdb/with-jina.ts
@@ -0,0 +1,27 @@
+import { JinaAIEmbedding } from "@llamaindex/jinaai";
+import { QdrantVectorStore } from "@llamaindex/qdrant";
+import {
+ Document,
+ storageContextFromDefaults,
+ VectorStoreIndex,
+} from "llamaindex";
+
+const embedding = new JinaAIEmbedding({
+ apiKey: process.env.JINAAI_API_KEY,
+ model: "jina-embeddings-v3",
+});
+
+async function main() {
+ const docs = [new Document({ text: "Lorem ipsum dolor sit amet" })];
+ const vectorStore = new QdrantVectorStore({
+ url: process.env.QDRANT_URL,
+ apiKey: process.env.QDRANT_API_KEY,
+ embeddingModel: embedding,
+ collectionName: "jina_test",
+ });
+ const storageContext = await storageContextFromDefaults({ vectorStore });
+ await VectorStoreIndex.fromDocuments(docs, { storageContext });
+ console.log("Inizialized vector store successfully");
+}
+
+void main().catch((err) => console.error(err));
diff --git a/examples/readers/src/pdf_fw.ts b/examples/readers/src/pdf_fw.ts
index cad617fa8..78efad1f7 100644
--- a/examples/readers/src/pdf_fw.ts
+++ b/examples/readers/src/pdf_fw.ts
@@ -1,5 +1,6 @@
+import { FireworksEmbedding, FireworksLLM } from "@llamaindex/fireworks";
import { PDFReader } from "@llamaindex/readers/pdf";
-import { FireworksEmbedding, FireworksLLM, VectorStoreIndex } from "llamaindex";
+import { VectorStoreIndex } from "llamaindex";
import { Settings } from "llamaindex";
diff --git a/examples/together-ai.ts b/examples/together-ai.ts
index 300627659..3823d5998 100644
--- a/examples/together-ai.ts
+++ b/examples/together-ai.ts
@@ -1,4 +1,4 @@
-import { TogetherEmbedding, TogetherLLM } from "llamaindex";
+import { TogetherEmbedding, TogetherLLM } from "@llamaindex/together";
// process.env.TOGETHER_API_KEY is required
const together = new TogetherLLM({
diff --git a/examples/together-ai/vector-index.ts b/examples/together-ai/vector-index.ts
index 001c3448e..a38fbbac3 100644
--- a/examples/together-ai/vector-index.ts
+++ b/examples/together-ai/vector-index.ts
@@ -1,12 +1,7 @@
import fs from "node:fs/promises";
-import {
- Document,
- Settings,
- TogetherEmbedding,
- TogetherLLM,
- VectorStoreIndex,
-} from "llamaindex";
+import { TogetherEmbedding, TogetherLLM } from "@llamaindex/together";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
// Update llm to use TogetherAI
Settings.llm = new TogetherLLM({
diff --git a/packages/llamaindex/src/embeddings/OpenAIEmbedding.ts b/packages/llamaindex/src/embeddings/OpenAIEmbedding.ts
deleted file mode 100644
index 02781efcb..000000000
--- a/packages/llamaindex/src/embeddings/OpenAIEmbedding.ts
+++ /dev/null
@@ -1 +0,0 @@
-export * from "@llamaindex/openai";
diff --git a/packages/llamaindex/src/embeddings/index.ts b/packages/llamaindex/src/embeddings/index.ts
deleted file mode 100644
index 5467f2add..000000000
--- a/packages/llamaindex/src/embeddings/index.ts
+++ /dev/null
@@ -1,5 +0,0 @@
-export * from "@llamaindex/core/embeddings";
-export { FireworksEmbedding } from "./fireworks.js";
-export * from "./JinaAIEmbedding.js";
-export * from "./OpenAIEmbedding.js";
-export { TogetherEmbedding } from "./together.js";
diff --git a/packages/llamaindex/src/index.edge.ts b/packages/llamaindex/src/index.edge.ts
index 63c6993b3..3a79a2080 100644
--- a/packages/llamaindex/src/index.edge.ts
+++ b/packages/llamaindex/src/index.edge.ts
@@ -22,6 +22,7 @@ export {
export * from "@llamaindex/core/agent";
export * from "@llamaindex/core/chat-engine";
export * from "@llamaindex/core/data-structs";
+export * from "@llamaindex/core/embeddings";
export {
CallbackManager,
DEFAULT_BASE_URL,
@@ -65,10 +66,10 @@ export * from "@llamaindex/core/storage/doc-store";
export * from "@llamaindex/core/storage/index-store";
export * from "@llamaindex/core/storage/kv-store";
export * from "@llamaindex/core/utils";
+export * from "@llamaindex/openai";
export * from "@llamaindex/workflow/agent";
export * from "./agent/index.js";
export * from "./cloud/index.js";
-export * from "./embeddings/index.js";
export * from "./engines/chat/index.js";
export * from "./engines/query/index.js";
export * from "./evaluation/index.js";
@@ -76,7 +77,6 @@ export * from "./extractors/index.js";
export * from "./indices/index.js";
export * from "./ingestion/index.js";
export { imageToDataUrl } from "./internal/utils.js";
-export * from "./llm/index.js";
export * from "./node-parser.js";
export * from "./objects/index.js";
export * from "./OutputParser.js";
diff --git a/packages/llamaindex/src/index.ts b/packages/llamaindex/src/index.ts
index ccdd367ae..84a40464e 100644
--- a/packages/llamaindex/src/index.ts
+++ b/packages/llamaindex/src/index.ts
@@ -1,8 +1,5 @@
export * from "./index.edge.js";
-// TODO: clean up, move to jinaai package
-export { JinaAIEmbedding } from "./embeddings/JinaAIEmbedding.js";
-
// Don't export file-system stores for non-node.js runtime on top level,
// as we cannot guarantee that they will work in other environments
export * from "./storage/index.js";
diff --git a/packages/llamaindex/src/indices/vectorStore/index.ts b/packages/llamaindex/src/indices/vectorStore/index.ts
index fc03b6e19..92be0bcb3 100644
--- a/packages/llamaindex/src/indices/vectorStore/index.ts
+++ b/packages/llamaindex/src/indices/vectorStore/index.ts
@@ -175,7 +175,7 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
for (const type in nodeMap) {
const nodes = nodeMap[type as ModalityType];
const embedModel =
- this.embedModel ?? this.vectorStores[type as ModalityType]?.embedModel;
+ this.vectorStores[type as ModalityType]?.embedModel ?? this.embedModel;
if (embedModel && nodes) {
await embedModel(nodes, {
logProgress: options?.logProgress,
diff --git a/packages/llamaindex/src/llm/index.ts b/packages/llamaindex/src/llm/index.ts
deleted file mode 100644
index dec9f0801..000000000
--- a/packages/llamaindex/src/llm/index.ts
+++ /dev/null
@@ -1,4 +0,0 @@
-export { DeepSeekLLM } from "./deepseek.js";
-export { FireworksLLM } from "./fireworks.js";
-export * from "./openai.js";
-export { TogetherLLM } from "./together.js";
diff --git a/packages/llamaindex/src/llm/openai.ts b/packages/llamaindex/src/llm/openai.ts
deleted file mode 100644
index 02781efcb..000000000
--- a/packages/llamaindex/src/llm/openai.ts
+++ /dev/null
@@ -1 +0,0 @@
-export * from "@llamaindex/openai";
diff --git a/packages/llamaindex/tests/MetadataExtractors.test.ts b/packages/llamaindex/tests/MetadataExtractors.test.ts
index 29bb117ab..47f560e97 100644
--- a/packages/llamaindex/tests/MetadataExtractors.test.ts
+++ b/packages/llamaindex/tests/MetadataExtractors.test.ts
@@ -1,13 +1,11 @@
import { Document } from "@llamaindex/core/schema";
-import { Settings } from "llamaindex";
-import { OpenAIEmbedding } from "llamaindex/embeddings/index";
+import { OpenAI, OpenAIEmbedding, Settings } from "llamaindex";
import {
KeywordExtractor,
QuestionsAnsweredExtractor,
SummaryExtractor,
TitleExtractor,
} from "llamaindex/extractors/index";
-import { OpenAI } from "llamaindex/llm/openai";
import { SentenceSplitter } from "llamaindex/node-parser";
import { afterAll, beforeAll, describe, expect, test, vi } from "vitest";
import {
diff --git a/packages/llamaindex/tests/Selectors.test.ts b/packages/llamaindex/tests/Selectors.test.ts
index 9fe1ace17..5eec85a5b 100644
--- a/packages/llamaindex/tests/Selectors.test.ts
+++ b/packages/llamaindex/tests/Selectors.test.ts
@@ -1,7 +1,7 @@
import { describe, expect, test } from "vitest";
// from unittest.mock import patch
-import { OpenAI } from "llamaindex/llm/index";
+import { OpenAI } from "llamaindex";
import { LLMSingleSelector } from "llamaindex/selectors/index";
import { mocStructuredkLlmGeneration } from "./utility/mockOpenAI.js";
diff --git a/packages/llamaindex/tests/indices/SummaryIndex.test.ts b/packages/llamaindex/tests/indices/SummaryIndex.test.ts
index c2a523e95..287dc5838 100644
--- a/packages/llamaindex/tests/indices/SummaryIndex.test.ts
+++ b/packages/llamaindex/tests/indices/SummaryIndex.test.ts
@@ -20,13 +20,13 @@ describe("SummaryIndex", () => {
let storageContext: StorageContext;
beforeAll(async () => {
- storageContext = await storageContextFromDefaults({
- persistDir: testDir,
- });
-
const embedModel = new OpenAIEmbedding();
mockEmbeddingModel(embedModel);
Settings.embedModel = embedModel;
+
+ storageContext = await storageContextFromDefaults({
+ persistDir: testDir,
+ });
});
afterAll(() => {
diff --git a/packages/llamaindex/tests/indices/VectorStoreIndex.test.ts b/packages/llamaindex/tests/indices/VectorStoreIndex.test.ts
index 61c8299a2..5a755ec71 100644
--- a/packages/llamaindex/tests/indices/VectorStoreIndex.test.ts
+++ b/packages/llamaindex/tests/indices/VectorStoreIndex.test.ts
@@ -9,7 +9,7 @@ import { DocStoreStrategy } from "llamaindex/ingestion/strategies/index";
import { mkdtemp, rm } from "node:fs/promises";
import { tmpdir } from "node:os";
import { join } from "node:path";
-import { afterAll, beforeAll, describe, expect, test, vi } from "vitest";
+import { afterAll, beforeAll, describe, expect, it, test, vi } from "vitest";
const testDir = await mkdtemp(join(tmpdir(), "test-"));
@@ -24,6 +24,10 @@ describe("VectorStoreIndex", () => {
) => Promise<Array<number>>;
beforeAll(async () => {
+ const embedModel = new OpenAIEmbedding();
+ mockEmbeddingModel(embedModel);
+ Settings.embedModel = embedModel;
+
storageContext = await mockStorageContext(testDir);
testStrategy = async (
strategy: DocStoreStrategy,
@@ -41,10 +45,6 @@ describe("VectorStoreIndex", () => {
}
return entries;
};
-
- const embedModel = new OpenAIEmbedding();
- mockEmbeddingModel(embedModel);
- Settings.embedModel = embedModel;
});
afterAll(() => {
@@ -65,3 +65,28 @@ describe("VectorStoreIndex", () => {
await rm(testDir, { recursive: true });
});
});
+
+describe("[VectorStoreIndex] use embedding model", () => {
+ it("should use embedding model passed in options instead of Settings", async () => {
+ const documents = [new Document({ text: "This needs to be embedded" })];
+
+ // Create mock embedding models
+ const settingsEmbedModel = new OpenAIEmbedding();
+ const customEmbedModel = new OpenAIEmbedding();
+
+ // Mock the embedding models using the utility function
+ mockEmbeddingModel(settingsEmbedModel);
+ mockEmbeddingModel(customEmbedModel);
+
+ // Add spies to track calls
+ const settingsSpy = vi.spyOn(settingsEmbedModel, "getTextEmbeddings");
+ const customSpy = vi.spyOn(customEmbedModel, "getTextEmbeddings");
+
+ Settings.embedModel = settingsEmbedModel;
+
+ const storageContext = await mockStorageContext(testDir, customEmbedModel); // setup custom embedding model
+ await VectorStoreIndex.fromDocuments(documents, { storageContext });
+ expect(customSpy).toHaveBeenCalled();
+ expect(settingsSpy).not.toHaveBeenCalled();
+ });
+});
diff --git a/packages/llamaindex/tests/utility/mockOpenAI.ts b/packages/llamaindex/tests/utility/mockOpenAI.ts
index 102ce43b0..e6d90a3bf 100644
--- a/packages/llamaindex/tests/utility/mockOpenAI.ts
+++ b/packages/llamaindex/tests/utility/mockOpenAI.ts
@@ -1,8 +1,6 @@
import type { CallbackManager } from "@llamaindex/core/global";
-import type { LLMChatParamsBase } from "llamaindex";
-import { Settings } from "llamaindex";
-import type { OpenAIEmbedding } from "llamaindex/embeddings/OpenAIEmbedding";
-import { OpenAI } from "llamaindex/llm/openai";
+import type { LLMChatParamsBase, OpenAIEmbedding } from "llamaindex";
+import { OpenAI, Settings } from "llamaindex";
import { vi } from "vitest";
export const DEFAULT_LLM_TEXT_OUTPUT = "MOCK_TOKEN_1-MOCK_TOKEN_2";
diff --git a/packages/llamaindex/tests/utility/mockStorageContext.ts b/packages/llamaindex/tests/utility/mockStorageContext.ts
index 4a8c0f880..dab379d7d 100644
--- a/packages/llamaindex/tests/utility/mockStorageContext.ts
+++ b/packages/llamaindex/tests/utility/mockStorageContext.ts
@@ -1,14 +1,27 @@
-import { OpenAIEmbedding, storageContextFromDefaults } from "llamaindex";
+import {
+ BaseEmbedding,
+ OpenAIEmbedding,
+ storageContextFromDefaults,
+} from "llamaindex";
import { mockEmbeddingModel } from "./mockOpenAI.js";
-export async function mockStorageContext(testDir: string) {
+export async function mockStorageContext(
+ testDir: string,
+ embeddingModel?: BaseEmbedding,
+) {
const storageContext = await storageContextFromDefaults({
persistDir: testDir,
});
for (const store of Object.values(storageContext.vectorStores)) {
- store.embedModel = new OpenAIEmbedding();
- mockEmbeddingModel(store.embedModel as OpenAIEmbedding);
+ if (embeddingModel) {
+ // use embeddingModel if it is passed in
+ store.embedModel = embeddingModel;
+ } else {
+ // mock an embedding model for testing
+ store.embedModel = new OpenAIEmbedding();
+ mockEmbeddingModel(store.embedModel as OpenAIEmbedding);
+ }
}
return storageContext;
}
diff --git a/packages/providers/deepseek/package.json b/packages/providers/deepseek/package.json
new file mode 100644
index 000000000..02d3edf33
--- /dev/null
+++ b/packages/providers/deepseek/package.json
@@ -0,0 +1,39 @@
+{
+ "name": "@llamaindex/deepseek",
+ "description": "DeepSeek Adapter for LlamaIndex",
+ "version": "0.0.1",
+ "type": "module",
+ "main": "./dist/index.cjs",
+ "module": "./dist/index.js",
+ "exports": {
+ ".": {
+ "require": {
+ "types": "./dist/index.d.cts",
+ "default": "./dist/index.cjs"
+ },
+ "import": {
+ "types": "./dist/index.d.ts",
+ "default": "./dist/index.js"
+ }
+ }
+ },
+ "files": [
+ "dist"
+ ],
+ "repository": {
+ "type": "git",
+ "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
+ "directory": "packages/providers/deepseek"
+ },
+ "scripts": {
+ "build": "bunchee",
+ "dev": "bunchee --watch"
+ },
+ "devDependencies": {
+ "bunchee": "6.3.4"
+ },
+ "dependencies": {
+ "@llamaindex/env": "workspace:*",
+ "@llamaindex/openai": "workspace:*"
+ }
+}
diff --git a/packages/providers/deepseek/src/index.ts b/packages/providers/deepseek/src/index.ts
new file mode 100644
index 000000000..e6679f111
--- /dev/null
+++ b/packages/providers/deepseek/src/index.ts
@@ -0,0 +1 @@
+export * from "./llm";
diff --git a/packages/llamaindex/src/llm/deepseek.ts b/packages/providers/deepseek/src/llm.ts
similarity index 100%
rename from packages/llamaindex/src/llm/deepseek.ts
rename to packages/providers/deepseek/src/llm.ts
diff --git a/packages/providers/deepseek/tsconfig.json b/packages/providers/deepseek/tsconfig.json
new file mode 100644
index 000000000..bd8900e3a
--- /dev/null
+++ b/packages/providers/deepseek/tsconfig.json
@@ -0,0 +1,19 @@
+{
+ "extends": "../../../tsconfig.json",
+ "compilerOptions": {
+ "target": "ESNext",
+ "module": "ESNext",
+ "moduleResolution": "bundler",
+ "outDir": "./lib",
+ "tsBuildInfoFile": "./lib/.tsbuildinfo"
+ },
+ "include": ["./src"],
+ "references": [
+ {
+ "path": "../openai/tsconfig.json"
+ },
+ {
+ "path": "../../env/tsconfig.json"
+ }
+ ]
+}
diff --git a/packages/providers/fireworks/package.json b/packages/providers/fireworks/package.json
new file mode 100644
index 000000000..de5a063e6
--- /dev/null
+++ b/packages/providers/fireworks/package.json
@@ -0,0 +1,39 @@
+{
+ "name": "@llamaindex/fireworks",
+ "description": "Fireworks Adapter for LlamaIndex",
+ "version": "0.0.1",
+ "type": "module",
+ "main": "./dist/index.cjs",
+ "module": "./dist/index.js",
+ "exports": {
+ ".": {
+ "require": {
+ "types": "./dist/index.d.cts",
+ "default": "./dist/index.cjs"
+ },
+ "import": {
+ "types": "./dist/index.d.ts",
+ "default": "./dist/index.js"
+ }
+ }
+ },
+ "files": [
+ "dist"
+ ],
+ "repository": {
+ "type": "git",
+ "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
+ "directory": "packages/providers/fireworks"
+ },
+ "scripts": {
+ "build": "bunchee",
+ "dev": "bunchee --watch"
+ },
+ "devDependencies": {
+ "bunchee": "6.3.4"
+ },
+ "dependencies": {
+ "@llamaindex/env": "workspace:*",
+ "@llamaindex/openai": "workspace:*"
+ }
+}
diff --git a/packages/llamaindex/src/embeddings/fireworks.ts b/packages/providers/fireworks/src/embedding.ts
similarity index 100%
rename from packages/llamaindex/src/embeddings/fireworks.ts
rename to packages/providers/fireworks/src/embedding.ts
diff --git a/packages/providers/fireworks/src/index.ts b/packages/providers/fireworks/src/index.ts
new file mode 100644
index 000000000..90b741f1e
--- /dev/null
+++ b/packages/providers/fireworks/src/index.ts
@@ -0,0 +1,2 @@
+export * from "./embedding";
+export * from "./llm";
diff --git a/packages/llamaindex/src/llm/fireworks.ts b/packages/providers/fireworks/src/llm.ts
similarity index 100%
rename from packages/llamaindex/src/llm/fireworks.ts
rename to packages/providers/fireworks/src/llm.ts
diff --git a/packages/providers/fireworks/tsconfig.json b/packages/providers/fireworks/tsconfig.json
new file mode 100644
index 000000000..bd8900e3a
--- /dev/null
+++ b/packages/providers/fireworks/tsconfig.json
@@ -0,0 +1,19 @@
+{
+ "extends": "../../../tsconfig.json",
+ "compilerOptions": {
+ "target": "ESNext",
+ "module": "ESNext",
+ "moduleResolution": "bundler",
+ "outDir": "./lib",
+ "tsBuildInfoFile": "./lib/.tsbuildinfo"
+ },
+ "include": ["./src"],
+ "references": [
+ {
+ "path": "../openai/tsconfig.json"
+ },
+ {
+ "path": "../../env/tsconfig.json"
+ }
+ ]
+}
diff --git a/packages/providers/jinaai/package.json b/packages/providers/jinaai/package.json
new file mode 100644
index 000000000..deb2cdd89
--- /dev/null
+++ b/packages/providers/jinaai/package.json
@@ -0,0 +1,40 @@
+{
+ "name": "@llamaindex/jinaai",
+ "description": "JinaAI Adapter for LlamaIndex",
+ "version": "0.0.1",
+ "type": "module",
+ "main": "./dist/index.cjs",
+ "module": "./dist/index.js",
+ "exports": {
+ ".": {
+ "require": {
+ "types": "./dist/index.d.cts",
+ "default": "./dist/index.cjs"
+ },
+ "import": {
+ "types": "./dist/index.d.ts",
+ "default": "./dist/index.js"
+ }
+ }
+ },
+ "files": [
+ "dist"
+ ],
+ "repository": {
+ "type": "git",
+ "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
+ "directory": "packages/providers/jinaai"
+ },
+ "scripts": {
+ "build": "bunchee",
+ "dev": "bunchee --watch"
+ },
+ "devDependencies": {
+ "bunchee": "6.3.4"
+ },
+ "dependencies": {
+ "@llamaindex/core": "workspace:*",
+ "@llamaindex/env": "workspace:*",
+ "@llamaindex/openai": "workspace:*"
+ }
+}
diff --git a/packages/llamaindex/src/embeddings/JinaAIEmbedding.ts b/packages/providers/jinaai/src/embedding.ts
similarity index 97%
rename from packages/llamaindex/src/embeddings/JinaAIEmbedding.ts
rename to packages/providers/jinaai/src/embedding.ts
index 9f7f3d705..6ad09293a 100644
--- a/packages/llamaindex/src/embeddings/JinaAIEmbedding.ts
+++ b/packages/providers/jinaai/src/embedding.ts
@@ -1,7 +1,7 @@
import { MultiModalEmbedding } from "@llamaindex/core/embeddings";
+import type { ImageType } from "@llamaindex/core/schema";
+import { imageToDataUrl } from "@llamaindex/core/utils";
import { getEnv } from "@llamaindex/env";
-import { imageToDataUrl } from "../internal/utils.js";
-import type { ImageType } from "../Node.js";
function isLocal(url: ImageType): boolean {
if (url instanceof Blob) return true;
diff --git a/packages/providers/jinaai/src/index.ts b/packages/providers/jinaai/src/index.ts
new file mode 100644
index 000000000..5b00d3610
--- /dev/null
+++ b/packages/providers/jinaai/src/index.ts
@@ -0,0 +1 @@
+export * from "./embedding";
diff --git a/packages/providers/jinaai/tsconfig.json b/packages/providers/jinaai/tsconfig.json
new file mode 100644
index 000000000..bd8900e3a
--- /dev/null
+++ b/packages/providers/jinaai/tsconfig.json
@@ -0,0 +1,19 @@
+{
+ "extends": "../../../tsconfig.json",
+ "compilerOptions": {
+ "target": "ESNext",
+ "module": "ESNext",
+ "moduleResolution": "bundler",
+ "outDir": "./lib",
+ "tsBuildInfoFile": "./lib/.tsbuildinfo"
+ },
+ "include": ["./src"],
+ "references": [
+ {
+ "path": "../openai/tsconfig.json"
+ },
+ {
+ "path": "../../env/tsconfig.json"
+ }
+ ]
+}
diff --git a/packages/providers/together/package.json b/packages/providers/together/package.json
new file mode 100644
index 000000000..6a5fce0de
--- /dev/null
+++ b/packages/providers/together/package.json
@@ -0,0 +1,39 @@
+{
+ "name": "@llamaindex/together",
+ "description": "Together Adapter for LlamaIndex",
+ "version": "0.0.1",
+ "type": "module",
+ "main": "./dist/index.cjs",
+ "module": "./dist/index.js",
+ "exports": {
+ ".": {
+ "require": {
+ "types": "./dist/index.d.cts",
+ "default": "./dist/index.cjs"
+ },
+ "import": {
+ "types": "./dist/index.d.ts",
+ "default": "./dist/index.js"
+ }
+ }
+ },
+ "files": [
+ "dist"
+ ],
+ "repository": {
+ "type": "git",
+ "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
+ "directory": "packages/providers/together"
+ },
+ "scripts": {
+ "build": "bunchee",
+ "dev": "bunchee --watch"
+ },
+ "devDependencies": {
+ "bunchee": "6.3.4"
+ },
+ "dependencies": {
+ "@llamaindex/env": "workspace:*",
+ "@llamaindex/openai": "workspace:*"
+ }
+}
diff --git a/packages/llamaindex/src/embeddings/together.ts b/packages/providers/together/src/embedding.ts
similarity index 100%
rename from packages/llamaindex/src/embeddings/together.ts
rename to packages/providers/together/src/embedding.ts
diff --git a/packages/providers/together/src/index.ts b/packages/providers/together/src/index.ts
new file mode 100644
index 000000000..90b741f1e
--- /dev/null
+++ b/packages/providers/together/src/index.ts
@@ -0,0 +1,2 @@
+export * from "./embedding";
+export * from "./llm";
diff --git a/packages/llamaindex/src/llm/together.ts b/packages/providers/together/src/llm.ts
similarity index 100%
rename from packages/llamaindex/src/llm/together.ts
rename to packages/providers/together/src/llm.ts
diff --git a/packages/providers/together/tsconfig.json b/packages/providers/together/tsconfig.json
new file mode 100644
index 000000000..3fad47fb7
--- /dev/null
+++ b/packages/providers/together/tsconfig.json
@@ -0,0 +1,19 @@
+{
+ "extends": "../../../tsconfig.json",
+ "compilerOptions": {
+ "target": "ESNext",
+ "module": "ESNext",
+ "moduleResolution": "bundler",
+ "outDir": "./lib",
+ "tsBuildInfoFile": "./lib/.tsbuildinfo"
+ },
+ "include": ["./src"],
+ "references": [
+ {
+ "path": "../../core/tsconfig.json"
+ },
+ {
+ "path": "../../env/tsconfig.json"
+ }
+ ]
+}
diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml
index 925315405..4114b9a56 100644
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -622,12 +622,18 @@ importers:
'@llamaindex/deepinfra':
specifier: ^0.0.42
version: link:../packages/providers/deepinfra
+ '@llamaindex/deepseek':
+ specifier: ^0.0.1
+ version: link:../packages/providers/deepseek
'@llamaindex/env':
specifier: ^0.1.29
version: link:../packages/env
'@llamaindex/firestore':
specifier: ^1.0.4
version: link:../packages/providers/storage/firestore
+ '@llamaindex/fireworks':
+ specifier: ^0.0.1
+ version: link:../packages/providers/fireworks
'@llamaindex/google':
specifier: ^0.0.13
version: link:../packages/providers/google
@@ -637,6 +643,9 @@ importers:
'@llamaindex/huggingface':
specifier: ^0.0.42
version: link:../packages/providers/huggingface
+ '@llamaindex/jinaai':
+ specifier: ^0.0.1
+ version: link:../packages/providers/jinaai
'@llamaindex/milvus':
specifier: ^0.1.6
version: link:../packages/providers/storage/milvus
@@ -676,6 +685,9 @@ importers:
'@llamaindex/replicate':
specifier: ^0.0.39
version: link:../packages/providers/replicate
+ '@llamaindex/together':
+ specifier: ^0.0.1
+ version: link:../packages/providers/together
'@llamaindex/upstash':
specifier: ^0.0.11
version: link:../packages/providers/storage/upstash
@@ -1218,6 +1230,32 @@ importers:
specifier: 6.3.4
version: 6.3.4(patch_hash=pavboztthlgni7m5gzw7643oru)(typescript@5.7.3)
+ packages/providers/deepseek:
+ dependencies:
+ '@llamaindex/env':
+ specifier: workspace:*
+ version: link:../../env
+ '@llamaindex/openai':
+ specifier: workspace:*
+ version: link:../openai
+ devDependencies:
+ bunchee:
+ specifier: 6.3.4
+ version: 6.3.4(patch_hash=pavboztthlgni7m5gzw7643oru)(typescript@5.7.3)
+
+ packages/providers/fireworks:
+ dependencies:
+ '@llamaindex/env':
+ specifier: workspace:*
+ version: link:../../env
+ '@llamaindex/openai':
+ specifier: workspace:*
+ version: link:../openai
+ devDependencies:
+ bunchee:
+ specifier: 6.3.4
+ version: 6.3.4(patch_hash=pavboztthlgni7m5gzw7643oru)(typescript@5.7.3)
+
packages/providers/google:
dependencies:
'@google-cloud/vertexai':
@@ -1275,6 +1313,22 @@ importers:
specifier: 6.3.4
version: 6.3.4(patch_hash=pavboztthlgni7m5gzw7643oru)(typescript@5.7.3)
+ packages/providers/jinaai:
+ dependencies:
+ '@llamaindex/core':
+ specifier: workspace:*
+ version: link:../../core
+ '@llamaindex/env':
+ specifier: workspace:*
+ version: link:../../env
+ '@llamaindex/openai':
+ specifier: workspace:*
+ version: link:../openai
+ devDependencies:
+ bunchee:
+ specifier: 6.3.4
+ version: 6.3.4(patch_hash=pavboztthlgni7m5gzw7643oru)(typescript@5.7.3)
+
packages/providers/mistral:
dependencies:
'@llamaindex/core':
@@ -1607,6 +1661,19 @@ importers:
specifier: 6.3.4
version: 6.3.4(patch_hash=pavboztthlgni7m5gzw7643oru)(typescript@5.7.3)
+ packages/providers/together:
+ dependencies:
+ '@llamaindex/env':
+ specifier: workspace:*
+ version: link:../../env
+ '@llamaindex/openai':
+ specifier: workspace:*
+ version: link:../openai
+ devDependencies:
+ bunchee:
+ specifier: 6.3.4
+ version: 6.3.4(patch_hash=pavboztthlgni7m5gzw7643oru)(typescript@5.7.3)
+
packages/providers/vercel:
dependencies:
'@llamaindex/core':
diff --git a/tsconfig.json b/tsconfig.json
index cca56fe09..8af5db8f3 100644
--- a/tsconfig.json
+++ b/tsconfig.json
@@ -175,6 +175,18 @@
},
{
"path": "./packages/providers/voyage-ai/tsconfig.json"
+ },
+ {
+ "path": "./packages/providers/deepseek/tsconfig.json"
+ },
+ {
+ "path": "./packages/providers/fireworks/tsconfig.json"
+ },
+ {
+ "path": "./packages/providers/together/tsconfig.json"
+ },
+ {
+ "path": "./packages/providers/jinaai/tsconfig.json"
}
]
}
--
GitLab