chore: update import to workspace pages for examples and docs

apps/next/src/content/docs/llamaindex/examples/context_aware_agent.mdx

@@ -13,8 +13,8 @@ import {
   Document,
   VectorStoreIndex,
   OpenAIContextAwareAgent,
-  OpenAI,
 } from "llamaindex";
+import { OpenAI } from "@llamaindex/openai";
 
 async function createContextAwareAgent() {
   // Create and index some documents

apps/next/src/content/docs/llamaindex/examples/other_llms.mdx

@@ -14,7 +14,8 @@ If you don't want to use an API at all you can [run a local model](../../example
 You can specify what LLM LlamaIndex.TS will use on the `Settings` object, like this:
 
 ```typescript
-import { MistralAI, Settings } from "llamaindex";
+import { MistralAI } from "@llamaindex/mistral";
+import { Settings } from "llamaindex";
 
 Settings.llm = new MistralAI({
   model: "mistral-tiny",
@@ -29,7 +30,8 @@ You can see examples of other APIs we support by checking out "Available LLMs" i
 A frequent gotcha when trying to use a different API as your LLM is that LlamaIndex will also by default index and embed your data using OpenAI's embeddings. To completely switch away from OpenAI you will need to set your embedding model as well, for example:
 
 ```typescript
-import { MistralAIEmbedding, Settings } from "llamaindex";
+import { MistralAIEmbedding } from "@llamaindex/mistral";
+import { Settings } from "llamaindex";
 
 Settings.embedModel = new MistralAIEmbedding();
 ```

apps/next/src/content/docs/llamaindex/guide/agents/2_create_agent.mdx

@@ -31,7 +31,8 @@ First we'll need to pull in our dependencies. These are:
 - Dotenv to load our API key from the .env file
 
 ```javascript
-import { OpenAI, FunctionTool, OpenAIAgent, Settings } from "llamaindex";
+import { FunctionTool, Settings } from "llamaindex";
+import { OpenAI, OpenAIAgent } from "@llamaindex/openai";
 import "dotenv/config";
 ```
 

apps/next/src/content/docs/llamaindex/guide/agents/4_agentic_rag.mdx

@@ -18,17 +18,10 @@ We're going to start with the same agent we [built in step 1](https://github.com
 We'll be bringing in `SimpleDirectoryReader`, `HuggingFaceEmbedding`, `VectorStoreIndex`, and `QueryEngineTool`, `OpenAIContextAwareAgent` from LlamaIndex.TS, as well as the dependencies we previously used.
 
 ```javascript
-import {
-  OpenAI,
-  FunctionTool,
-  OpenAIAgent,
-  OpenAIContextAwareAgent,
-  Settings,
-  SimpleDirectoryReader,
-  HuggingFaceEmbedding,
-  VectorStoreIndex,
-  QueryEngineTool,
-} from "llamaindex";
+import { FunctionTool, QueryEngineTool, Settings, VectorStoreIndex } from "llamaindex";
+import { OpenAI, OpenAIAgent } from "@llamaindex/openai";
+import { HuggingFaceEmbedding } from "@llamaindex/huggingface";
+import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
 ```
 
 ### Add an embedding model

apps/next/src/content/docs/llamaindex/guide/loading/index.mdx

@@ -33,11 +33,11 @@ We offer readers for different file formats.
 
 <Tabs groupId="llamaindex-or-readers" items={["llamaindex", "@llamaindex/readers"]} persist>
 	```ts twoslash tab="llamaindex"
-	import { CSVReader } from 'llamaindex'
-	import { PDFReader } from 'llamaindex'
-	import { JSONReader } from 'llamaindex'
-	import { MarkdownReader } from 'llamaindex'
-	import { HTMLReader } from 'llamaindex'
+	import { CSVReader } from '@llamaindex/readers/csv'
+	import { PDFReader } from '@llamaindex/readers/pdf'
+	import { JSONReader } from '@llamaindex/readers/json'
+	import { MarkdownReader } from '@llamaindex/readers/markdown'
+	import { HTMLReader } from '@llamaindex/readers/html'
 	// you can find more readers in the documentation
 	```
 
@@ -59,7 +59,7 @@ We offer readers for different file formats.
 <Tabs groupId="llamaindex-or-readers" items={["llamaindex", "@llamaindex/readers"]} persist>
 
 	```ts twoslash tab="llamaindex"
-	import { SimpleDirectoryReader } from "llamaindex";
+	import { SimpleDirectoryReader } from "@llamaindex/readers/directory";
 
 	const reader = new SimpleDirectoryReader()
 	const documents = await reader.loadData("./data")

apps/next/src/content/docs/llamaindex/integration/vercel.mdx

@@ -69,7 +69,7 @@ streamText({
 For production deployments, you can use LlamaCloud to store and manage your documents:
 
 ```typescript
-import { LlamaCloudIndex } from "llamaindex";
+import { LlamaCloudIndex } from "@llamaindex/cloud";
 
 // Create a LlamaCloud index
 const index = await LlamaCloudIndex.fromDocuments({

apps/next/src/content/docs/llamaindex/modules/data_loaders/json.mdx

@@ -9,7 +9,7 @@ Supports streaming of large JSON data using [@discoveryjs/json-ext](https://gith
 ## Usage
 
 ```ts
-import { JSONReader } from "llamaindex";
+import { JSONReader } from "@llamaindex/readers/json";
 
 const file = "../../PATH/TO/FILE";
 const content = new TextEncoder().encode("JSON_CONTENT");

apps/next/src/content/docs/llamaindex/modules/data_loaders/llama_parse/images.mdx

@@ -19,14 +19,10 @@ const imageDicts = await reader.getImages(jsonObjs, "images");
 You can create an index across both text and image nodes by requesting alternative text for the image from a multimodal LLM.
 
 ```ts
-import {
-  Document,
-  ImageNode,
-  LlamaParseReader,
-  OpenAI,
-  VectorStoreIndex,
-} from "llamaindex";
-import { createMessageContent } from "llamaindex/synthesizers/utils";
+import { Document, ImageNode, VectorStoreIndex } from "llamaindex";
+import { LlamaParseReader } from "@llamaindex/cloud/reader";
+import { OpenAI } from "@llamaindex/openai";
+import { createMessageContent } from "@llamaindex/core/synthesizers";
 
 const reader = new LlamaParseReader();
 async function main() {

apps/next/src/content/docs/llamaindex/modules/data_loaders/llama_parse/json_mode.mdx

@@ -10,6 +10,8 @@ For Json mode, you need to use `loadJson`. The `resultType` is automatically set
 More information about indexing the results on the next page.
 
 ```ts
+import { LlamaParseReader } from "@llamaindex/cloud/reader";
+
 const reader = new LlamaParseReader();
 async function main() {
   // Load the file and return an array of json objects
@@ -59,7 +61,8 @@ All Readers share a `loadData` method with `SimpleDirectoryReader` that promises
 However, a simple work around is to create a new reader class that extends `LlamaParseReader` and adds a new method or overrides `loadData`, wrapping around JSON mode, extracting the required values, and returning a Document object.
 
 ```ts
-import { LlamaParseReader, Document } from "llamaindex";
+import { Document } from "llamaindex";
+import { LlamaParseReader } from "@llamaindex/cloud/reader";
 
 class LlamaParseReaderWithJson extends LlamaParseReader {
   // Override the loadData method

apps/next/src/content/docs/llamaindex/modules/data_stores/index.mdx

@@ -34,13 +34,8 @@ provided, it will use the environment variables `PGHOST`, `PGUSER`,
 `PGPASSWORD`, `PGDATABASE` and `PGPORT`.
 
 ```typescript
-import {
-  Document,
-  VectorStoreIndex,
-  PostgresDocumentStore,
-  PostgresIndexStore,
-  storageContextFromDefaults,
-} from "llamaindex";
+import { Document, VectorStoreIndex, storageContextFromDefaults } from "llamaindex";
+import { PostgresDocumentStore, PostgresIndexStore } from "@llamaindex/postgres";
 
 const storageContext = await storageContextFromDefaults({
   docStore: new PostgresDocumentStore(),

apps/next/src/content/docs/llamaindex/modules/data_stores/vector_stores/qdrant.mdx

@@ -15,7 +15,8 @@ docker run -p 6333:6333 qdrant/qdrant
 
 ```ts
 import fs from "node:fs/promises";
-import { Document, VectorStoreIndex, QdrantVectorStore } from "llamaindex";
+import { Document, VectorStoreIndex } from "llamaindex";
+import { QdrantVectorStore } from "@llamaindex/qdrant";
 ```
 
 ## Load the documents
@@ -60,7 +61,8 @@ console.log(response.toString());
 
 ```ts
 import fs from "node:fs/promises";
-import { Document, VectorStoreIndex, QdrantVectorStore } from "llamaindex";
+import { Document, VectorStoreIndex } from "llamaindex";
+import { QdrantVectorStore } from "@llamaindex/qdrant";
 
 async function main() {
   const path = "node_modules/llamaindex/examples/abramov.txt";

apps/next/src/content/docs/llamaindex/modules/documents_and_nodes/metadata_extraction.mdx

@@ -14,13 +14,8 @@ Our metadata extractor modules include the following "feature extractors":
 Then you can chain the `Metadata Extractors` with the `IngestionPipeline` to extract metadata from a set of documents.
 
 ```ts
-import {
-  IngestionPipeline,
-  TitleExtractor,
-  QuestionsAnsweredExtractor,
-  Document,
-  OpenAI,
-} from "llamaindex";
+import { Document, IngestionPipeline, TitleExtractor, QuestionsAnsweredExtractor } from "llamaindex";
+import { OpenAI } from "@llamaindex/openai";
 
 async function main() {
   const pipeline = new IngestionPipeline({

apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/deepinfra.mdx

@@ -6,12 +6,8 @@ To use DeepInfra embeddings, you need to import `DeepInfraEmbedding` from llamai
 Check out available embedding models [here](https://deepinfra.com/models/embeddings).
 
 ```ts
-import {
-  DeepInfraEmbedding,
-  Settings,
-  Document,
-  VectorStoreIndex,
-} from "llamaindex";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
+import { DeepInfraEmbedding } from "@llamaindex/deepinfra";
 
 // Update Embed Model
 Settings.embedModel = new DeepInfraEmbedding();
@@ -33,7 +29,7 @@ By default, DeepInfraEmbedding is using the sentence-transformers/clip-ViT-B-32
 For example:
 
 ```ts
-import { DeepInfraEmbedding } from "llamaindex";
+import { DeepInfraEmbedding } from "@llamaindex/deepinfra";
 
 const model = "intfloat/e5-large-v2";
 Settings.embedModel = new DeepInfraEmbedding({
@@ -46,7 +42,8 @@ You can also set the `maxRetries` and `timeout` parameters when initializing `De
 For example:
 
 ```ts
-import { DeepInfraEmbedding, Settings } from "llamaindex";
+import { Settings } from "llamaindex";
+import { DeepInfraEmbedding } from "@llamaindex/deepinfra";
 
 const model = "intfloat/e5-large-v2";
 const maxRetries = 5;
@@ -62,7 +59,7 @@ Settings.embedModel = new DeepInfraEmbedding({
 Standalone usage:
 
 ```ts
-import { DeepInfraEmbedding } from "llamaindex";
+import { DeepInfraEmbedding } from "@llamaindex/deepinfra";
 import { config } from "dotenv";
 // For standalone usage, you need to configure DEEPINFRA_API_TOKEN in .env file
 config();

apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/gemini.mdx

@@ -2,10 +2,11 @@
 title: Gemini
 ---
 
-To use Gemini embeddings, you need to import `GeminiEmbedding` from `llamaindex`.
+To use Gemini embeddings, you need to import `GeminiEmbedding` from `@llamaindex/google`.
 
 ```ts
-import { GeminiEmbedding, Settings } from "llamaindex";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
+import { GeminiEmbedding, GEMINI_MODEL } from "@llamaindex/google";
 
 // Update Embed Model
 Settings.embedModel = new GeminiEmbedding();
@@ -27,7 +28,7 @@ Per default, `GeminiEmbedding` is using the `gemini-pro` model. You can change t
 For example:
 
 ```ts
-import { GEMINI_MODEL, GeminiEmbedding } from "llamaindex";
+import { GEMINI_MODEL, GeminiEmbedding } from "@llamaindex/google";
 
 Settings.embedModel = new GeminiEmbedding({
   model: GEMINI_MODEL.GEMINI_PRO_LATEST,

apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/huggingface.mdx

@@ -2,10 +2,11 @@
 title: HuggingFace
 ---
 
-To use HuggingFace embeddings, you need to import `HuggingFaceEmbedding` from `llamaindex`.
+To use HuggingFace embeddings, you need to import `HuggingFaceEmbedding` from `@llamaindex/huggingface`.
 
 ```ts
-import { HuggingFaceEmbedding, Settings } from "llamaindex";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
+import { HuggingFaceEmbedding } from "@llamaindex/huggingface";
 
 // Update Embed Model
 Settings.embedModel = new HuggingFaceEmbedding();
@@ -29,6 +30,8 @@ If you're not using a quantized model, set the `quantized` parameter to `false`.
 For example, to use the not quantized `BAAI/bge-small-en-v1.5` model, you can use the following code:
 
 ```ts
+import { HuggingFaceEmbedding } from "@llamaindex/huggingface";
+
 Settings.embedModel = new HuggingFaceEmbedding({
   modelType: "BAAI/bge-small-en-v1.5",
   quantized: false,

apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/mistral.mdx

@@ -2,10 +2,11 @@
 title: MistralAI
 ---
 
-To use MistralAI embeddings, you need to import `MistralAIEmbedding` from `llamaindex`.
+To use MistralAI embeddings, you need to import `MistralAIEmbedding` from `@llamaindex/mistral`.
 
 ```ts
-import { MistralAIEmbedding, Settings } from "llamaindex";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
+import { MistralAIEmbedding } from "@llamaindex/mistral";
 
 // Update Embed Model
 Settings.embedModel = new MistralAIEmbedding({

apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/mixedbreadai.mdx

@@ -23,7 +23,8 @@ pnpm install llamaindex
 Next, sign up for an API key at [mixedbread.ai](https://mixedbread.ai/). Once you have your API key, you can import the necessary modules and create a new instance of the `MixedbreadAIEmbeddings` class.
 
 ```ts
-import { MixedbreadAIEmbeddings, Document, Settings } from "llamaindex";
+import { MixedbreadAIEmbeddings } from "@llamaindex/mixedbread";
+import { Document, Settings } from "llamaindex";
 ```
 
 ## Usage with LlamaIndex

apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/ollama.mdx

@@ -2,7 +2,7 @@
 title: Ollama
 ---
 
-To use Ollama embeddings, you need to import `OllamaEmbedding` from `llamaindex`.
+To use Ollama embeddings, you need to import `OllamaEmbedding` from `@llamaindex/ollama`.
 
 Note that you need to pull the embedding model first before using it.
 
@@ -13,7 +13,8 @@ ollama pull nomic-embed-text
 ```
 
 ```ts
-import { OllamaEmbedding, Settings } from "llamaindex";
+import { OllamaEmbedding } from "@llamaindex/ollama";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
 
 Settings.embedModel = new OllamaEmbedding({ model: "nomic-embed-text" });
 

apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/openai.mdx

@@ -2,10 +2,11 @@
 title: OpenAI
 ---
 
-To use OpenAI embeddings, you need to import `OpenAIEmbedding` from `llamaindex`.
+To use OpenAI embeddings, you need to import `OpenAIEmbedding` from `@llamaindex/openai`.
 
 ```ts
-import { OpenAIEmbedding, Settings } from "llamaindex";
+import { OpenAIEmbedding } from "@llamaindex/openai";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
 
 Settings.embedModel = new OpenAIEmbedding();
 

apps/next/src/content/docs/llamaindex/modules/embeddings/index.mdx

@@ -7,7 +7,8 @@ The embedding model in LlamaIndex is responsible for creating numerical represen
 This can be explicitly updated through `Settings`
 
 ```typescript
-import { OpenAIEmbedding, Settings } from "llamaindex";
+import { OpenAIEmbedding } from "@llamaindex/openai";
+import { Settings } from "llamaindex";
 
 Settings.embedModel = new OpenAIEmbedding({
   model: "text-embedding-ada-002",

apps/next/src/content/docs/llamaindex/modules/evaluation/modules/correctness.mdx

@@ -23,7 +23,8 @@ export OPENAI_API_KEY=your-api-key
 Import the required modules:
 
 ```ts
-import { CorrectnessEvaluator, OpenAI, Settings, Response } from "llamaindex";
+import { OpenAI } from "@llamaindex/openai";
+import { CorrectnessEvaluator, Settings, Response } from "llamaindex";
 ```
 
 Let's setup gpt-4 for better results:

apps/next/src/content/docs/llamaindex/modules/evaluation/modules/faithfulness.mdx

@@ -25,12 +25,12 @@ export OPENAI_API_KEY=your-api-key
 Import the required modules:
 
 ```ts
+import { OpenAI } from "@llamaindex/openai";
 import {
   Document,
   FaithfulnessEvaluator,
-  OpenAI,
-  VectorStoreIndex,
   Settings,
+  VectorStoreIndex,
 } from "llamaindex";
 ```
 

apps/next/src/content/docs/llamaindex/modules/evaluation/modules/relevancy.mdx

@@ -23,11 +23,11 @@ export OPENAI_API_KEY=your-api-key
 Import the required modules:
 
 ```ts
+import { OpenAI } from "@llamaindex/openai";
 import {
+  Document,
   RelevancyEvaluator,
-  OpenAI,
   Settings,
-  Document,
   VectorStoreIndex,
 } from "llamaindex";
 ```