test: add e2e test for nextjs/node with tokenizer

.changeset/odd-insects-vanish.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/env": patch
+---
+
+Use tiktoken instead of tiktoken/lite and disable WASM tiktoken for non-Node environments

.changeset/pink-keys-kiss.md

@@ -0,0 +1,5 @@
+---
+"llamaindex": patch
+---
+
+include node relationships when converting jsonToDoc

.eslintrc.cjs

@@ -0,0 +1,79 @@
+const { join } = require("node:path");
+
+module.exports = {
+  root: true,
+  extends: [
+    "turbo",
+    "prettier",
+    "plugin:@typescript-eslint/recommended-type-checked-only",
+  ],
+  parserOptions: {
+    project: join(__dirname, "tsconfig.eslint.json"),
+    __tsconfigRootDir: __dirname,
+  },
+  settings: {
+    react: {
+      version: "999.999.999",
+    },
+  },
+  rules: {
+    "max-params": ["error", 4],
+    "prefer-const": "error",
+    "@typescript-eslint/no-floating-promises": [
+      "error",
+      {
+        ignoreIIFE: true,
+      },
+    ],
+    "no-debugger": "error",
+    "@typescript-eslint/await-thenable": "off",
+    "@typescript-eslint/ban-ts-comment": "off",
+    "@typescript-eslint/ban-types": "off",
+    "no-array-constructor": "off",
+    "@typescript-eslint/no-array-constructor": "off",
+    "@typescript-eslint/no-base-to-string": "off",
+    "@typescript-eslint/no-duplicate-enum-values": "off",
+    "@typescript-eslint/no-duplicate-type-constituents": "off",
+    "@typescript-eslint/no-explicit-any": "off",
+    "@typescript-eslint/no-extra-non-null-assertion": "off",
+    "@typescript-eslint/no-for-in-array": "off",
+    "no-implied-eval": "off",
+    "@typescript-eslint/no-implied-eval": "off",
+    "no-loss-of-precision": "off",
+    "@typescript-eslint/no-loss-of-precision": "off",
+    "@typescript-eslint/no-misused-new": "off",
+    "@typescript-eslint/no-misused-promises": "off",
+    "@typescript-eslint/no-namespace": "off",
+    "@typescript-eslint/no-non-null-asserted-optional-chain": "off",
+    "@typescript-eslint/no-redundant-type-constituents": "off",
+    "@typescript-eslint/no-this-alias": "off",
+    "@typescript-eslint/no-unnecessary-type-assertion": "off",
+    "@typescript-eslint/no-unnecessary-type-constraint": "off",
+    "@typescript-eslint/no-unsafe-argument": "off",
+    "@typescript-eslint/no-unsafe-assignment": "off",
+    "@typescript-eslint/no-unsafe-call": "off",
+    "@typescript-eslint/no-unsafe-declaration-merging": "off",
+    "@typescript-eslint/no-unsafe-enum-comparison": "off",
+    "@typescript-eslint/no-unsafe-member-access": "off",
+    "@typescript-eslint/no-unsafe-return": "off",
+    "no-unused-vars": "off",
+    "@typescript-eslint/no-unused-vars": "off",
+    "@typescript-eslint/no-var-requires": "off",
+    "@typescript-eslint/prefer-as-const": "off",
+    "require-await": "off",
+    "@typescript-eslint/require-await": "off",
+    "@typescript-eslint/restrict-plus-operands": "off",
+    "@typescript-eslint/restrict-template-expressions": "off",
+    "@typescript-eslint/triple-slash-reference": "off",
+    "@typescript-eslint/unbound-method": "off",
+  },
+  overrides: [
+    {
+      files: ["examples/**/*.ts"],
+      rules: {
+        "turbo/no-undeclared-env-vars": "off",
+      },
+    },
+  ],
+  ignorePatterns: ["dist/", "lib/", "deps/"],
+};

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,46 +0,0 @@
----
-name: Bug report
-about: Create a report to help us improve
-title: ""
-labels: bug
-assignees: ""
----
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-Code to reproduce the behavior:
-
-```ts
-// paste the code here
-```
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**Desktop (please complete the following information):**
-
-- OS: [e.g. macOS, Linux]
-- JS Runtime / Framework / Bundler (select all applicable)
-- [ ] Node.js
-- [ ] Deno
-- [ ] Bun
-- [ ] Next.js
-- [ ] ESBuild
-- [ ] Rollup
-- [ ] Webpack
-- [ ] Turbopack
-- [ ] Vite
-- [ ] Waku
-- [ ] Edge Runtime
-- [ ] AWS Lambda
-- [ ] Cloudflare Worker
-- [ ] Others (please elaborate on this)
-- Version [e.g. 22]
-
-**Additional context**
-Add any other context about the problem here.

.github/workflows/lint_on_push_or_pull.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:

.github/workflows/preview.yml

@@ -1,28 +0,0 @@
-name: Publish Preview
-on: [pull_request]
-
-jobs:
-  pre_release:
-    name: Pre Release
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout Repo
-        uses: actions/checkout@v4
-
-      - uses: pnpm/action-setup@v4
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version-file: ".nvmrc"
-          cache: "pnpm"
-
-      - name: Install dependencies
-        run: pnpm install
-
-      - name: Build
-        run: pnpm run build
-
-      - name: Pre Release
-        run: pnpx pkg-pr-new publish ./packages/* ./packages/providers/*

.github/workflows/publish.yml

@@ -0,0 +1,36 @@
+name: Publish
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+      id-token: write
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: pnpm/action-setup@v3
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "pnpm"
+      - name: Install dependencies
+        run: pnpm install
+
+      - name: Publish @llamaindex/env
+        run: npx jsr publish
+        working-directory: packages/env
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Publish @llamaindex/core
+        run: npx jsr publish --allow-slow-types
+        working-directory: packages/llamaindex
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/publish_github.yml

@@ -12,7 +12,7 @@ jobs:
       - name: Checkout Repo
         uses: actions/checkout@v4
 
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v3
 
       - name: Setup Node.js
         uses: actions/setup-node@v4

.github/workflows/release.yml

@@ -15,7 +15,7 @@ jobs:
       - name: Checkout Repo
         uses: actions/checkout@v4
 
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v3
 
       - name: Setup Node.js
         uses: actions/setup-node@v4
@@ -55,16 +55,3 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
-
-      # Refs: https://github.com/changesets/changesets/issues/421
-      - name: Update lock file
-        continue-on-error: true
-        run: pnpm install --lockfile-only
-
-      - name: Commit lock file
-        continue-on-error: true
-        uses: stefanzweifel/git-auto-commit-action@v5
-        with:
-          commit_message: "chore: update lock file"
-          branch: changeset-release/main
-          file_pattern: "pnpm-lock.yaml"

.github/workflows/test.yml

@@ -12,33 +12,19 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
-env:
-  POSTGRES_HOST_AUTH_METHOD: trust
-  TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
-  TURBO_TEAM: ${{ vars.TURBO_TEAM }}
-  TURBO_REMOTE_ONLY: true
-
 jobs:
   e2e:
     strategy:
       fail-fast: false
       matrix:
-        node-version: [20.x, 22.x, 23.x]
+        node-version: [18.x, 20.x, 22.x]
     name: E2E on Node.js ${{ matrix.node-version }}
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: ankane/setup-postgres@v1
-        with:
-          database: llamaindex_node_test
-          dev-files: true
-      - run: |
-          cd /tmp
-          git clone --branch v0.7.0 https://github.com/pgvector/pgvector.git
-          cd pgvector
-          make
-          sudo make install
-      - uses: pnpm/action-setup@v4
+
+      - uses: pnpm/action-setup@v3
+
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -53,12 +39,13 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        node-version: [20.x, 22.x, 23.x]
+        node-version: [18.x, 20.x, 22.x]
     name: Test on Node.js ${{ matrix.node-version }}
     runs-on: ubuntu-latest
+
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -73,7 +60,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -84,14 +71,18 @@ jobs:
       - name: Build
         run: pnpm run build
       - name: Use Build For Examples
-        run: |
-          pnpm link ../packages/llamaindex/
-          cd readers && pnpm link ../../packages/llamaindex/
+        run: pnpm link ../packages/llamaindex/
         working-directory: ./examples
       - name: Run Type Check
         run: pnpm run type-check
       - name: Run Circular Dependency Check
-        run: pnpm run circular-check
+        run: pnpm dlx turbo run circular-check
+      - uses: actions/upload-artifact@v3
+        if: failure()
+        with:
+          name: typecheck-build-dist
+          path: ./packages/llamaindex/dist
+          if-no-files-found: error
   e2e-llamaindex-examples:
     strategy:
       fail-fast: false
@@ -101,13 +92,12 @@ jobs:
           - nextjs-agent
           - nextjs-edge-runtime
           - nextjs-node-runtime
-          - waku-query-engine
-          - llama-parse-browser
+    #          - waku-query-engine
     runs-on: ubuntu-latest
     name: Build LlamaIndex Example (${{ matrix.packages }})
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -126,7 +116,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -138,36 +128,15 @@ jobs:
         run: pnpm run build
       - name: Copy examples
         run: rsync -rv --exclude=node_modules ./examples ${{ runner.temp }}
-      - name: Pack packages
-        run: |
-          for dir in packages/*; do
-            if [ -d "$dir" ] && [ -f "$dir/package.json" ] && [[ ! "$dir" =~ autotool ]]; then
-              echo "Packing $dir"
-              pnpm pack --pack-destination ${{ runner.temp }} -C $dir
-            else
-              echo "Skipping $dir, no package.json found"
-            fi
-          done
-      - name: Pack provider packages
-        run: |
-          for dir in packages/providers/*; do
-            if [ -d "$dir" ] && [ -f "$dir/package.json" ]; then
-              echo "Packing $dir"
-              pnpm pack --pack-destination ${{ runner.temp }} -C $dir
-            else
-              echo "Skipping $dir, no package.json found"
-            fi
-          done
+      - name: Pack @llamaindex/env
+        run: pnpm pack --pack-destination ${{ runner.temp }}
+        working-directory: packages/env
+      - name: Pack llamaindex
+        run: pnpm pack --pack-destination ${{ runner.temp }}
+        working-directory: packages/llamaindex
       - name: Install
         run: npm add ${{ runner.temp }}/*.tgz
         working-directory: ${{ runner.temp }}/examples
       - name: Run Type Check
         run: npx tsc --project ./tsconfig.json
         working-directory: ${{ runner.temp }}/examples
-      - uses: actions/upload-artifact@v4
-        if: failure()
-        with:
-          name: build-dist
-          path: |
-            ${{ runner.temp }}/*.tgz
-          if-no-files-found: error

.gitignore

@@ -48,6 +48,3 @@ playwright/.cache/
 
 # intellij
 **/.idea
-
-# generated API
-packages/cloud/src/client

.prettierignore

@@ -4,6 +4,3 @@ pnpm-lock.yaml
 lib/
 dist/
 .docusaurus/
-.source/
-# prttier doesn't support mdx3 we are using
-*.mdx

.vscode/settings.json

@@ -13,6 +13,5 @@
   },
   "[json]": {
     "editor.defaultFormatter": "esbenp.prettier-vscode"
-  },
-  "prettier.prettierPath": "./node_modules/prettier"
+  }
 }

CONTRIBUTING.md

@@ -4,11 +4,11 @@
 
 This is a monorepo built with Turborepo
 
-Right now, for first-time contributors, these three packages are of the highest importance:
+Right now there are two packages of importance:
 
-- `packages/llamaindex` which is the main NPM library `llamaindex`
-- `examples` is where the demo code lives
-- `apps/docs` is where the code for the documentation of https://ts.llamaindex.ai/ is located
+packages/llamaindex which is the main NPM library llamaindex
+
+examples is where the demo code lives
 
 ### Turborepo docs
 
@@ -43,11 +43,11 @@ pnpm run test
 
 To write new test cases write them in [packages/llamaindex/tests](/packages/llamaindex/tests)
 
-We use Vitest https://vitest.dev to write our test cases. Vitest comes with a bunch of built-in assertions using the expect function: https://vitest.dev/api/expect.html#expect
+We use Jest https://jestjs.io/ to write our test cases. Jest comes with a bunch of built in assertions using the expect function: https://jestjs.io/docs/expect
 
 ### Demo applications
 
-There is an existing ["example"](/examples/README.md) demos folder with mainly NodeJS scripts. Feel free to add additional demos to that folder. If you would like to try out your changes in the `llamaindex` package with a new demo, you need to run the build command in the README.
+There is an existing ["example"](/examples/README.md) demos folder with mainly NodeJS scripts. Feel free to add additional demos to that folder. If you would like to try out your changes in the core package with a new demo, you need to run the build command in the README.
 
 You can create new demo applications in the apps folder. Just run pnpm init in the folder after you create it to create its own package.json
 
@@ -81,7 +81,7 @@ Any changes you make should be reflected in the browser. If you need to regenera
 
 ## Changeset
 
-We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new changeset, run in the root folder:
+We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new changeset, run:
 
 ```
 pnpm changeset

README.md

@@ -7,7 +7,7 @@
 
 LlamaIndex is a data framework for your LLM application.
 
-Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in JS runtime environments with TypeScript support.
+Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in Typescript and Javascript.
 
 Documentation: https://ts.llamaindex.ai/
 
@@ -19,51 +19,198 @@ Try examples online:
 
 LlamaIndex.TS aims to be a lightweight, easy to use set of libraries to help you integrate large language models into your applications with your own data.
 
-## Compatibility
-
-### Multiple JS Environment Support
+## Multiple JS Environment Support
 
 LlamaIndex.TS supports multiple JS environments, including:
 
-- Node.js >= 20 ✅
+- Node.js (18, 20, 22) ✅
 - Deno ✅
 - Bun ✅
-- Nitro ✅
-- Vercel Edge Runtime ✅ (with some limitations)
-- Cloudflare Workers ✅ (with some limitations)
+- React Server Components (Next.js) ✅
 
 For now, browser support is limited due to the lack of support for [AsyncLocalStorage-like APIs](https://github.com/tc39/proposal-async-context)
 
-### Supported LLMs:
-
-- OpenAI LLms
-- Anthropic LLms
-- Groq LLMs
-- Llama2, Llama3, Llama3.1 LLMs
-- MistralAI LLMs
-- Fireworks LLMs
-- DeepSeek LLMs
-- ReplicateAI LLMs
-- TogetherAI LLMs
-- HuggingFace LLms
-- DeepInfra LLMs
-- Gemini LLMs
-
 ## Getting started
 
 ```shell
 npm install llamaindex
 pnpm install llamaindex
 yarn add llamaindex
+jsr install @llamaindex/core
 ```
 
-### Setup in Node.js, Deno, Bun, TypeScript...?
+### Node.js
 
-See our official document: <https://ts.llamaindex.ai/docs/llamaindex/setup/getting-started>
+```ts
+import fs from "fs/promises";
+import { Document, VectorStoreIndex } from "llamaindex";
 
-### Tips when using in non-Node.js environments
+async function main() {
+  // Load essay from abramov.txt in Node
+  const essay = await fs.readFile(
+    "node_modules/llamaindex/examples/abramov.txt",
+    "utf-8",
+  );
 
-When you are importing `llamaindex` in a non-Node.js environment(such as Vercel Edge, Cloudflare Workers, etc.)
+  // Create Document object with essay
+  const document = new Document({ text: essay });
+
+  // Split text and create embeddings. Store them in a VectorStoreIndex
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // Query the index
+  const queryEngine = index.asQueryEngine();
+  const response = await queryEngine.query({
+    query: "What did the author do in college?",
+  });
+
+  // Output response
+  console.log(response.toString());
+}
+
+main();
+```
+
+```bash
+# `pnpm install tsx` before running the script
+node --import tsx ./main.ts
+```
+
+### Next.js
+
+First, you will need to add a llamaindex plugin to your Next.js project.
+
+```js
+// next.config.js
+const withLlamaIndex = require("llamaindex/next");
+
+module.exports = withLlamaIndex({
+  // your next.js config
+});
+```
+
+You can combine `ai` with `llamaindex` in Next.js with RSC (React Server Components).
+
+```tsx
+// src/apps/page.tsx
+"use client";
+import { chatWithAgent } from "@/actions";
+import type { JSX } from "react";
+import { useFormState } from "react-dom";
+
+// You can use the Edge runtime in Next.js by adding this line:
+// export const runtime = "edge";
+
+export default function Home() {
+  const [ui, action] = useFormState<JSX.Element | null>(async () => {
+    return chatWithAgent("hello!", []);
+  }, null);
+  return (
+    <main>
+      {ui}
+      <form action={action}>
+        <button>Chat</button>
+      </form>
+    </main>
+  );
+}
+```
+
+```tsx
+// src/actions/index.ts
+"use server";
+import { createStreamableUI } from "ai/rsc";
+import { OpenAIAgent } from "llamaindex";
+import type { ChatMessage } from "llamaindex/llm/types";
+
+export async function chatWithAgent(
+  question: string,
+  prevMessages: ChatMessage[] = [],
+) {
+  const agent = new OpenAIAgent({
+    tools: [
+      // ... adding your tools here
+    ],
+  });
+  const responseStream = await agent.chat({
+    stream: true,
+    message: question,
+    chatHistory: prevMessages,
+  });
+  const uiStream = createStreamableUI(<div>loading...</div>);
+  responseStream
+    .pipeTo(
+      new WritableStream({
+        start: () => {
+          uiStream.update("response:");
+        },
+        write: async (message) => {
+          uiStream.append(message.response.delta);
+        },
+      }),
+    )
+    .catch(console.error);
+  return uiStream.value;
+}
+```
+
+### Cloudflare Workers
+
+```ts
+// src/index.ts
+export default {
+  async fetch(
+    request: Request,
+    env: Env,
+    ctx: ExecutionContext,
+  ): Promise<Response> {
+    const { setEnvs } = await import("@llamaindex/env");
+    // set environment variables so that the OpenAIAgent can use them
+    setEnvs(env);
+    const { OpenAIAgent } = await import("llamaindex");
+    const agent = new OpenAIAgent({
+      tools: [],
+    });
+    const responseStream = await agent.chat({
+      stream: true,
+      message: "Hello? What is the weather today?",
+    });
+    const textEncoder = new TextEncoder();
+    const response = responseStream.pipeThrough(
+      new TransformStream({
+        transform: (chunk, controller) => {
+          controller.enqueue(textEncoder.encode(chunk.response.delta));
+        },
+      }),
+    );
+    return new Response(response);
+  },
+};
+```
+
+## Playground
+
+Check out our NextJS playground at https://llama-playground.vercel.app/. The source is available at https://github.com/run-llama/ts-playground
+
+## Core concepts for getting started:
+
+- [Document](/packages/llamaindex/src/Node.ts): A document represents a text file, PDF file or other contiguous piece of data.
+
+- [Node](/packages/llamaindex/src/Node.ts): The basic data building block. Most commonly, these are parts of the document split into manageable pieces that are small enough to be fed into an embedding model and LLM.
+
+- [Embedding](/packages/llamaindex/src/embeddings/OpenAIEmbedding.ts): Embeddings are sets of floating point numbers which represent the data in a Node. By comparing the similarity of embeddings, we can derive an understanding of the similarity of two pieces of data. One use case is to compare the embedding of a question with the embeddings of our Nodes to see which Nodes may contain the data needed to answer that quesiton. Because the default service context is OpenAI, the default embedding is `OpenAIEmbedding`. If using different models, say through Ollama, use this [Embedding](/packages/llamaindex/src/embeddings/OllamaEmbedding.ts) (see all [here](/packages/llamaindex/src/embeddings)).
+
+- [Indices](/packages/llamaindex/src/indices/): Indices store the Nodes and the embeddings of those nodes. QueryEngines retrieve Nodes from these Indices using embedding similarity.
+
+- [QueryEngine](/packages/llamaindex/src/engines/query/RetrieverQueryEngine.ts): Query engines are what generate the query you put in and give you back the result. Query engines generally combine a pre-built prompt with selected Nodes from your Index to give the LLM the context it needs to answer your query. To build a query engine from your Index (recommended), use the [`asQueryEngine`](/packages/llamaindex/src/indices/BaseIndex.ts) method on your Index. See all query engines [here](/packages/llamaindex/src/engines/query).
+
+- [ChatEngine](/packages/llamaindex/src/engines/chat/SimpleChatEngine.ts): A ChatEngine helps you build a chatbot that will interact with your Indices. See all chat engines [here](/packages/llamaindex/src/engines/chat).
+
+- [SimplePrompt](/packages/llamaindex/src/Prompt.ts): A simple standardized function call definition that takes in inputs and formats them in a template literal. SimplePrompts can be specialized using currying and combined using other SimplePrompt functions.
+
+## Tips when using in non-Node.js environments
+
+When you are importing `llamaindex` in a non-Node.js environment(such as React Server Components, Cloudflare Workers, etc.)
 Some classes are not exported from top-level entry file.
 
 The reason is that some classes are only compatible with Node.js runtime,(e.g. `PDFReader`) which uses Node.js specific APIs(like `fs`, `child_process`, `crypto`).
@@ -99,31 +246,19 @@ export async function getDocuments() {
 
 You'll find a complete example with LlamaIndexTS here: https://github.com/run-llama/create_llama_projects/tree/main/nextjs-edge-llamaparse
 
-## Playground
+## Supported LLMs:
 
-Check out our NextJS playground at https://llama-playground.vercel.app/. The source is available at https://github.com/run-llama/ts-playground
-
-## Core concepts for getting started:
-
-- [Document](/packages/llamaindex/src/Node.ts): A document represents a text file, PDF file or other contiguous piece of data.
-
-- [Node](/packages/llamaindex/src/Node.ts): The basic data building block. Most commonly, these are parts of the document split into manageable pieces that are small enough to be fed into an embedding model and LLM.
-
-- [Embedding](/packages/llamaindex/src/embeddings/OpenAIEmbedding.ts): Embeddings are sets of floating point numbers which represent the data in a Node. By comparing the similarity of embeddings, we can derive an understanding of the similarity of two pieces of data. One use case is to compare the embedding of a question with the embeddings of our Nodes to see which Nodes may contain the data needed to answer that question. Because the default service context is OpenAI, the default embedding is `OpenAIEmbedding`. If using different models, say through Ollama, use this [Embedding](/packages/llamaindex/src/embeddings/OllamaEmbedding.ts) (see all [here](/packages/llamaindex/src/embeddings)).
-
-- [Indices](/packages/llamaindex/src/indices/): Indices store the Nodes and the embeddings of those nodes. QueryEngines retrieve Nodes from these Indices using embedding similarity.
-
-- [QueryEngine](/packages/llamaindex/src/engines/query/RetrieverQueryEngine.ts): Query engines are what generate the query you put in and give you back the result. Query engines generally combine a pre-built prompt with selected Nodes from your Index to give the LLM the context it needs to answer your query. To build a query engine from your Index (recommended), use the [`asQueryEngine`](/packages/llamaindex/src/indices/BaseIndex.ts) method on your Index. See all query engines [here](/packages/llamaindex/src/engines/query).
-
-- [ChatEngine](/packages/llamaindex/src/engines/chat/SimpleChatEngine.ts): A ChatEngine helps you build a chatbot that will interact with your Indices. See all chat engines [here](/packages/llamaindex/src/engines/chat).
-
-- [SimplePrompt](/packages/llamaindex/src/Prompt.ts): A simple standardized function call definition that takes in inputs and formats them in a template literal. SimplePrompts can be specialized using currying and combined using other SimplePrompt functions.
+- OpenAI GPT-3.5-turbo and GPT-4
+- Anthropic Claude 3 (Opus, Sonnet, and Haiku) and the legacy models (Claude 2 and Instant)
+- Groq LLMs
+- Llama2/3 Chat LLMs (70B, 13B, and 7B parameters)
+- MistralAI Chat LLMs
+- Fireworks Chat LLMs
 
 ## Contributing:
 
-Please see our [contributing guide](CONTRIBUTING.md) for more information.
-You are highly encouraged to contribute to LlamaIndex.TS!
+We are in the very early days of LlamaIndex.TS. If you’re interested in hacking on it with us check out our [contributing guide](/CONTRIBUTING.md)
 
-## Community
+## Bugs? Questions?
 
 Please join our Discord! https://discord.com/invite/eN6D2HQ4aX

apps/docs/.changeset/tall-parents-add.md

@@ -1,6 +0,0 @@
----
-"llamaindex": minor
-"docs": minor
----
-
-Add deepseek llm class

apps/docs/CHANGELOG.md

@@ -1,615 +1,5 @@
 # docs
 
-## 0.0.107
-
-### Patch Changes
-
-- llamaindex@0.8.3
-
-## 0.0.106
-
-### Patch Changes
-
-- @llamaindex/examples@0.0.12
-
-## 0.0.105
-
-### Patch Changes
-
-- Updated dependencies [c7a918c]
-  - llamaindex@0.8.2
-
-## 0.0.104
-
-### Patch Changes
-
-- llamaindex@0.8.1
-
-## 0.0.103
-
-### Patch Changes
-
-- Updated dependencies [359fd33]
-- Updated dependencies [efb7e1b]
-- Updated dependencies [98ba1e7]
-- Updated dependencies [620c63c]
-  - llamaindex@0.8.0
-  - @llamaindex/examples@0.0.11
-
-## 0.0.102
-
-### Patch Changes
-
-- Updated dependencies [9df9a8f]
-  - llamaindex@0.7.10
-
-## 0.0.101
-
-### Patch Changes
-
-- Updated dependencies [691c5bc]
-  - llamaindex@0.7.9
-
-## 0.0.100
-
-### Patch Changes
-
-- llamaindex@0.7.8
-
-## 0.0.99
-
-### Patch Changes
-
-- Updated dependencies [2486bd8]
-  - @llamaindex/examples@0.0.10
-  - llamaindex@0.7.7
-
-## 0.0.98
-
-### Patch Changes
-
-- Updated dependencies [534d550]
-  - llamaindex@0.7.6
-
-## 0.0.97
-
-### Patch Changes
-
-- Updated dependencies [e9a111d]
-- Updated dependencies [9f22aae]
-  - llamaindex@0.7.5
-
-## 0.0.96
-
-### Patch Changes
-
-- llamaindex@0.7.4
-
-## 0.0.95
-
-### Patch Changes
-
-- llamaindex@0.7.3
-
-## 0.0.94
-
-### Patch Changes
-
-- llamaindex@0.7.2
-
-## 0.0.93
-
-### Patch Changes
-
-- Updated dependencies [ae49ff4]
-- Updated dependencies [4c38c1b]
-- Updated dependencies [a75af83]
-- Updated dependencies [a75af83]
-  - llamaindex@0.7.1
-
-## 0.0.92
-
-### Patch Changes
-
-- Updated dependencies [1364e8e]
-- Updated dependencies [3b7736f]
-- Updated dependencies [96fc69c]
-  - llamaindex@0.7.0
-  - @llamaindex/examples@0.0.9
-
-## 0.0.91
-
-### Patch Changes
-
-- Updated dependencies [5729bd9]
-  - llamaindex@0.6.22
-
-## 0.0.90
-
-### Patch Changes
-
-- Updated dependencies [6f75306]
-- Updated dependencies [94cb4ad]
-  - llamaindex@0.6.21
-
-## 0.0.89
-
-### Patch Changes
-
-- Updated dependencies [6a9a7b1]
-  - llamaindex@0.6.20
-
-## 0.0.88
-
-### Patch Changes
-
-- Updated dependencies [62cba52]
-- Updated dependencies [d265e96]
-- Updated dependencies [d30bbf7]
-- Updated dependencies [53fd00a]
-  - llamaindex@0.6.19
-
-## 0.0.87
-
-### Patch Changes
-
-- Updated dependencies [5f67820]
-- Updated dependencies [fe08d04]
-  - llamaindex@0.6.18
-
-## 0.0.86
-
-### Patch Changes
-
-- Updated dependencies [ee697fb]
-  - llamaindex@0.6.17
-
-## 0.0.85
-
-### Patch Changes
-
-- Updated dependencies [63e9846]
-- Updated dependencies [6f3a31c]
-  - llamaindex@0.6.16
-
-## 0.0.84
-
-### Patch Changes
-
-- Updated dependencies [2a82413]
-  - llamaindex@0.6.15
-
-## 0.0.83
-
-### Patch Changes
-
-- llamaindex@0.6.14
-
-## 0.0.82
-
-### Patch Changes
-
-- llamaindex@0.6.13
-
-## 0.0.81
-
-### Patch Changes
-
-- Updated dependencies [f7b4e94]
-- Updated dependencies [78037a6]
-- Updated dependencies [1d9e3b1]
-  - llamaindex@0.6.12
-
-## 0.0.80
-
-### Patch Changes
-
-- Updated dependencies [df441e2]
-  - llamaindex@0.6.11
-
-## 0.0.79
-
-### Patch Changes
-
-- Updated dependencies [ebc5105]
-- Updated dependencies [6cce3b1]
-  - llamaindex@0.6.10
-
-## 0.0.78
-
-### Patch Changes
-
-- llamaindex@0.6.9
-
-## 0.0.77
-
-### Patch Changes
-
-- Updated dependencies [8b7fdba]
-  - llamaindex@0.6.8
-
-## 0.0.76
-
-### Patch Changes
-
-- Updated dependencies [23bcc37]
-  - llamaindex@0.6.7
-
-## 0.0.75
-
-### Patch Changes
-
-- Updated dependencies [d902cc3]
-- Updated dependencies [025ffe6]
-- Updated dependencies [a659574]
-  - llamaindex@0.6.6
-
-## 0.0.74
-
-### Patch Changes
-
-- Updated dependencies [e9714db]
-  - llamaindex@0.6.5
-
-## 0.0.73
-
-### Patch Changes
-
-- Updated dependencies [b48bcc3]
-  - llamaindex@0.6.4
-
-## 0.0.72
-
-### Patch Changes
-
-- Updated dependencies [2cd1383]
-- Updated dependencies [5c4badb]
-  - llamaindex@0.6.3
-
-## 0.0.71
-
-### Patch Changes
-
-- Updated dependencies [749b43a]
-  - llamaindex@0.6.2
-
-## 0.0.70
-
-### Patch Changes
-
-- Updated dependencies [fbd5e01]
-- Updated dependencies [6b70c54]
-- Updated dependencies [1a6137b]
-- Updated dependencies [85c2e19]
-  - llamaindex@0.6.1
-
-## 0.0.69
-
-### Patch Changes
-
-- Updated dependencies [11feef8]
-  - llamaindex@0.6.0
-  - @llamaindex/examples@0.0.8
-
-## 0.0.68
-
-### Patch Changes
-
-- Updated dependencies [7edeb1c]
-  - llamaindex@0.5.27
-
-## 0.0.67
-
-### Patch Changes
-
-- Updated dependencies [ffe0cd1]
-- Updated dependencies [ffe0cd1]
-  - llamaindex@0.5.26
-
-## 0.0.66
-
-### Patch Changes
-
-- Updated dependencies [4810364]
-- Updated dependencies [d3bc663]
-  - llamaindex@0.5.25
-
-## 0.0.65
-
-### Patch Changes
-
-- llamaindex@0.5.24
-
-## 0.0.64
-
-### Patch Changes
-
-- llamaindex@0.5.23
-
-## 0.0.63
-
-### Patch Changes
-
-- Updated dependencies [4648da6]
-  - llamaindex@0.5.22
-
-## 0.0.62
-
-### Patch Changes
-
-- Updated dependencies [ae1149f]
-- Updated dependencies [2411c9f]
-- Updated dependencies [e8f229c]
-- Updated dependencies [11b3856]
-- Updated dependencies [83d7f41]
-- Updated dependencies [0148354]
-- Updated dependencies [1711f6d]
-  - llamaindex@0.5.21
-
-## 0.0.61
-
-### Patch Changes
-
-- Updated dependencies [d9d6c56]
-- Updated dependencies [22ff486]
-- Updated dependencies [eed0b04]
-  - llamaindex@0.5.20
-
-## 0.0.60
-
-### Patch Changes
-
-- Updated dependencies [fcbf183]
-  - llamaindex@0.5.19
-
-## 0.0.59
-
-### Patch Changes
-
-- Updated dependencies [8b66cf4]
-  - llamaindex@0.5.18
-
-## 0.0.58
-
-### Patch Changes
-
-- Updated dependencies [c654398]
-  - llamaindex@0.5.17
-
-## 0.0.57
-
-### Patch Changes
-
-- Updated dependencies [58abc57]
-  - llamaindex@0.5.16
-
-## 0.0.56
-
-### Patch Changes
-
-- Updated dependencies [01c184c]
-- Updated dependencies [07a275f]
-  - llamaindex@0.5.15
-
-## 0.0.55
-
-### Patch Changes
-
-- Updated dependencies [c825a2f]
-  - llamaindex@0.5.14
-
-## 0.0.54
-
-### Patch Changes
-
-- llamaindex@0.5.13
-
-## 0.0.53
-
-### Patch Changes
-
-- Updated dependencies [345300f]
-- Updated dependencies [da5cfc4]
-- Updated dependencies [da5cfc4]
-  - llamaindex@0.5.12
-
-## 0.0.52
-
-### Patch Changes
-
-- 376d29a: feat: added tool calling and agent support for llama3.1 504B
-  - llamaindex@0.5.11
-
-## 0.0.51
-
-### Patch Changes
-
-- 086b940: feat: add DeepSeek LLM
-- 5d5716b: feat: add a reader for JSON data
-- Updated dependencies [086b940]
-- Updated dependencies [5d5716b]
-- Updated dependencies [91d02a4]
-- Updated dependencies [fb6db45]
-  - llamaindex@0.5.10
-
-## 0.0.50
-
-### Patch Changes
-
-- Updated dependencies [15962b3]
-  - llamaindex@0.5.9
-
-## 0.0.49
-
-### Patch Changes
-
-- Updated dependencies [3d5ba08]
-- Updated dependencies [d917cdc]
-  - llamaindex@0.5.8
-
-## 0.0.48
-
-### Patch Changes
-
-- Updated dependencies [ec59acd]
-  - llamaindex@0.5.7
-
-## 0.0.47
-
-### Patch Changes
-
-- Updated dependencies [2562244]
-- Updated dependencies [325aa51]
-- Updated dependencies [ab700ea]
-- Updated dependencies [92f0782]
-- Updated dependencies [6cf6ae6]
-- Updated dependencies [b7cfe5b]
-  - llamaindex@0.5.6
-
-## 0.0.46
-
-### Patch Changes
-
-- Updated dependencies [b974eea]
-  - llamaindex@0.5.5
-
-## 0.0.45
-
-### Patch Changes
-
-- Updated dependencies [1a65ead]
-  - llamaindex@0.5.4
-
-## 0.0.44
-
-### Patch Changes
-
-- Updated dependencies [9bbbc67]
-- Updated dependencies [b3681bf]
-  - llamaindex@0.5.3
-
-## 0.0.43
-
-### Patch Changes
-
-- llamaindex@0.5.2
-
-## 0.0.42
-
-### Patch Changes
-
-- 2774681: Add mixedbread's embeddings and reranking API
-- Updated dependencies [2774681]
-- Updated dependencies [a0f424e]
-  - llamaindex@0.5.1
-
-## 0.0.41
-
-### Patch Changes
-
-- 36ddec4: fix: typo in custom page separator parameter for LlamaParse
-- Updated dependencies [16ef5dd]
-- Updated dependencies [16ef5dd]
-- Updated dependencies [36ddec4]
-  - llamaindex@0.5.0
-  - @llamaindex/examples@0.0.7
-
-## 0.0.40
-
-### Patch Changes
-
-- llamaindex@0.4.14
-
-## 0.0.39
-
-### Patch Changes
-
-- Updated dependencies [e8f8bea]
-- Updated dependencies [304484b]
-  - llamaindex@0.4.13
-
-## 0.0.38
-
-### Patch Changes
-
-- Updated dependencies [f326ab8]
-  - llamaindex@0.4.12
-
-## 0.0.37
-
-### Patch Changes
-
-- Updated dependencies [8bf5b4a]
-  - llamaindex@0.4.11
-
-## 0.0.36
-
-### Patch Changes
-
-- Updated dependencies [7dce3d2]
-  - llamaindex@0.4.10
-
-## 0.0.35
-
-### Patch Changes
-
-- Updated dependencies [3a96a48]
-  - llamaindex@0.4.9
-
-## 0.0.34
-
-### Patch Changes
-
-- Updated dependencies [83ebdfb]
-  - llamaindex@0.4.8
-
-## 0.0.33
-
-### Patch Changes
-
-- Updated dependencies [41fe871]
-- Updated dependencies [321c39d]
-- Updated dependencies [f7f1af0]
-  - llamaindex@0.4.7
-
-## 0.0.32
-
-### Patch Changes
-
-- Updated dependencies [1feb23b]
-- Updated dependencies [08c55ec]
-  - llamaindex@0.4.6
-
-## 0.0.31
-
-### Patch Changes
-
-- Updated dependencies [6c3e5d0]
-  - llamaindex@0.4.5
-
-## 0.0.30
-
-### Patch Changes
-
-- Updated dependencies [42eb73a]
-  - llamaindex@0.4.4
-
-## 0.0.29
-
-### Patch Changes
-
-- Updated dependencies [2ef62a9]
-  - llamaindex@0.4.3
-  - @llamaindex/examples@0.0.6
-
-## 0.0.28
-
-### Patch Changes
-
-- Updated dependencies [a87a4d1]
-- Updated dependencies [0730140]
-  - llamaindex@0.4.2
-
 ## 0.0.27
 
 ### Patch Changes

apps/docs/docs/examples/agent_gemini.mdx

@@ -1,6 +0,0 @@
-# Gemini Agent
-
-import CodeBlock from "@theme/CodeBlock";
-import CodeSourceGemini from "!raw-loader!../../../../examples/gemini/agent.ts";
-
-<CodeBlock language="ts">{CodeSourceGemini}</CodeBlock>

apps/docs/docs/examples/context_aware_agent.mdx

@@ -1,63 +0,0 @@
----
-sidebar_position: 14
----
-
-# Context-Aware Agent
-
-The Context-Aware Agent enhances the capabilities of standard LLM agents by incorporating relevant context from a retriever for each query. This allows the agent to provide more informed and specific responses based on the available information.
-
-## Usage
-
-Here's a simple example of how to use the Context-Aware Agent:
-
-```typescript
-import {
-  Document,
-  VectorStoreIndex,
-  OpenAIContextAwareAgent,
-  OpenAI,
-} from "llamaindex";
-
-async function createContextAwareAgent() {
-  // Create and index some documents
-  const documents = [
-    new Document({
-      text: "LlamaIndex is a data framework for LLM applications.",
-      id_: "doc1",
-    }),
-    new Document({
-      text: "The Eiffel Tower is located in Paris, France.",
-      id_: "doc2",
-    }),
-  ];
-
-  const index = await VectorStoreIndex.fromDocuments(documents);
-  const retriever = index.asRetriever({ similarityTopK: 1 });
-
-  // Create the Context-Aware Agent
-  const agent = new OpenAIContextAwareAgent({
-    llm: new OpenAI({ model: "gpt-3.5-turbo" }),
-    contextRetriever: retriever,
-  });
-
-  // Use the agent to answer queries
-  const response = await agent.chat({
-    message: "What is LlamaIndex used for?",
-  });
-
-  console.log("Agent Response:", response.response);
-}
-
-createContextAwareAgent().catch(console.error);
-```
-
-In this example, the Context-Aware Agent uses the retriever to fetch relevant context for each query, allowing it to provide more accurate and informed responses based on the indexed documents.
-
-## Key Components
-
-- `contextRetriever`: A retriever (e.g., from a VectorStoreIndex) that fetches relevant documents or passages for each query.
-
-## Available Context-Aware Agents
-
-- `OpenAIContextAwareAgent`: A context-aware agent using OpenAI's models.
-- `AnthropicContextAwareAgent`: A context-aware agent using Anthropic's models.

apps/docs/docs/getting_started/concepts.md

@@ -62,7 +62,7 @@ These building blocks can be customized to reflect ranking preferences, as well
 
 [**Retrievers**](../modules/retriever.md):
 A retriever defines how to efficiently retrieve relevant context from a knowledge base (i.e. index) when given a query.
-The specific retrieval logic differs for different indices, the most popular being dense retrieval against a vector index.
+The specific retrieval logic differs for difference indices, the most popular being dense retrieval against a vector index.
 
 [**Response Synthesizers**](../modules/response_synthesizer.md):
 A response synthesizer generates a response from an LLM, using a user query and a given set of retrieved text chunks.

apps/docs/docs/getting_started/environments.md

@@ -6,17 +6,10 @@ sidebar_position: 2
 
 We support Node.JS versions 18, 20 and 22, with experimental support for Deno, Bun and Vercel Edge functions.
 
-## NextJS
+## NextJS App Router
 
-If you're using NextJS you'll need to add `withLlamaIndex` to your `next.config.js` file. This will add the necessary configuration for included 3rd-party libraries to your build:
+If you're using NextJS App Router route handlers/serverless functions, you'll need to use the NodeJS mode:
 
 ```js
-// next.config.js
-const withLlamaIndex = require("llamaindex/next");
-
-module.exports = withLlamaIndex({
-  // your next.js config
-});
+export const runtime = "nodejs"; // default
 ```
-
-For details, check the latest [withLlamaIndex](https://github.com/run-llama/LlamaIndexTS/blob/main/packages/llamaindex/src/next.ts) implementation.

apps/docs/docs/guides/agents/2_create_agent.mdx

@@ -50,10 +50,10 @@ We want to see what our agent is up to, so we're going to hook into some events
 
 ```javascript
 Settings.callbackManager.on("llm-tool-call", (event) => {
-  console.log(event.detail);
+  console.log(event.detail.payload);
 });
 Settings.callbackManager.on("llm-tool-result", (event) => {
-  console.log(event.detail);
+  console.log(event.detail.payload);
 });
 ```
 

apps/docs/docs/guides/agents/4_agentic_rag.mdx

@@ -4,23 +4,22 @@ While an agent that can perform math is nifty (LLMs are usually not very good at
 
 To learn more about RAG, we recommend this [introduction](https://docs.llamaindex.ai/en/stable/getting_started/concepts/) from our Python docs. We'll assume you know the basics:
 
-- Parse your source data into chunks of text.
-- Encode that text as numbers, called embeddings.
-- Search your embeddings for the most relevant chunks of text.
-- Use the relevant chunks along with a query to ask an LLM to generate an answer.
+- You need to parse your source data into chunks of text
+- You need to encode that text as numbers, called embeddings
+- You need to search your embeddings for the most relevant chunks of text
+- You feed your relevant chunks and a query to an LLM to answer a question
 
 We're going to start with the same agent we [built in step 1](https://github.com/run-llama/ts-agents/blob/main/1_agent/agent.ts), but make a few changes. You can find the finished version [in the repository](https://github.com/run-llama/ts-agents/blob/main/2_agentic_rag/agent.ts).
 
 ### New dependencies
 
-We'll be bringing in `SimpleDirectoryReader`, `HuggingFaceEmbedding`, `VectorStoreIndex`, and `QueryEngineTool`, `OpenAIContextAwareAgent` from LlamaIndex.TS, as well as the dependencies we previously used.
+We'll be bringing in `SimpleDirectoryReader`, `HuggingFaceEmbedding`, `VectorStoreIndex`, and `QueryEngineTool` from LlamaIndex.TS, as well as the dependencies we previously used.
 
 ```javascript
 import {
   OpenAI,
   FunctionTool,
   OpenAIAgent,
-  OpenAIContextAwareAgent,
   Settings,
   SimpleDirectoryReader,
   HuggingFaceEmbedding,
@@ -42,7 +41,7 @@ Settings.embedModel = new HuggingFaceEmbedding({
 
 ### Load data using SimpleDirectoryReader
 
-`SimpleDirectoryReader` is a flexible tool that can read various file formats. We will point it at our data directory, which contains a single PDF file, and retrieve a set of documents.
+SimpleDirectoryReader is a flexible tool that can read a variety of file formats. We're going to point it at our data directory, which contains just the single PDF file, and get it to return a set of documents.
 
 ```javascript
 const reader = new SimpleDirectoryReader();
@@ -51,7 +50,7 @@ const documents = await reader.loadData("../data");
 
 ### Index our data
 
-We will convert our text into embeddings using the `VectorStoreIndex` class through the `fromDocuments` method, which utilizes the embedding model defined earlier in `Settings`.
+Now we turn our text into embeddings. The `VectorStoreIndex` class takes care of this for us when we use the `fromDocuments` method (it uses the embedding model we defined in `Settings` earlier).
 
 ```javascript
 const index = await VectorStoreIndex.fromDocuments(documents);
@@ -73,35 +72,21 @@ By default LlamaIndex will retrieve just the 2 most relevant chunks of text. Thi
 retriever.similarityTopK = 10;
 ```
 
-### Approach 1: Create a Context-Aware Agent
+### Create a query engine
 
-With the retriever ready, you can create a **context-aware agent**.
+And our final step in creating a RAG pipeline is to create a query engine that will use the retriever to find the most relevant chunks of text, and then use the LLM to answer the question.
 
 ```javascript
-const agent = new OpenAIContextAwareAgent({
-  contextRetriever: retriever,
+const queryEngine = await index.asQueryEngine({
+  retriever,
 });
-
-// Example query to the context-aware agent
-let response = await agent.chat({
-  message: `What's the budget of San Francisco in 2023-2024?`,
-});
-
-console.log(response);
 ```
 
-**Expected Output:**
+### Define the query engine as a tool
 
-```md
-The total budget for the City and County of San Francisco for the fiscal year 2023-2024 is $14.6 billion. This represents a $611.8 million, or 4.4 percent, increase over the previous fiscal year's budget. The budget covers various expenditures across different departments and services, including significant allocations to public works, transportation, commerce, public protection, and health services.
-```
-
-### Approach 2: Using QueryEngineTool (Alternative Approach)
-
-If you prefer more flexibility and don't mind additional complexity, you can create a `QueryEngineTool`. This approach allows you to define the query logic, providing a more tailored way to interact with the data, but note that it introduces a delay due to the extra tool call.
+Just as before we created a `FunctionTool`, we're going to create a `QueryEngineTool` that uses our `queryEngine`.
 
 ```javascript
-const queryEngine = await index.asQueryEngine({ retriever });
 const tools = [
   new QueryEngineTool({
     queryEngine: queryEngine,
@@ -111,18 +96,28 @@ const tools = [
     },
   }),
 ];
+```
 
-// Create an agent using the tools array
+As before, we've created an array of tools with just one tool in it. The metadata is slightly different: we don't need to define our parameters, we just give the tool a name and a natural-language description.
+
+### Create the agent as before
+
+Creating the agent and asking a question is exactly the same as before, but we'll ask a different question.
+
+```javascript
+// create the agent
 const agent = new OpenAIAgent({ tools });
 
-let toolResponse = await agent.chat({
+let response = await agent.chat({
   message: "What's the budget of San Francisco in 2023-2024?",
 });
 
-console.log(toolResponse);
+console.log(response);
 ```
 
-**Expected Output:**
+Once again we'll run `npx tsx agent.ts` and see what we get:
+
+**_Output_**
 
 ```javascript
 {
@@ -143,12 +138,28 @@ console.log(toolResponse);
 }
 ```
 
+```javascript
+{
+  response: {
+    raw: {
+      id: 'chatcmpl-9KxUkwizVCYCmxwFQcZFSHrInzNFU',
+      object: 'chat.completion',
+      created: 1714782286,
+      model: 'gpt-4-turbo-2024-04-09',
+      choices: [Array],
+      usage: [Object],
+      system_fingerprint: 'fp_ea6eb70039'
+    },
+    message: {
+      content: "The total budget for the City and County of San Francisco for the fiscal year 2023-2024 is $14.6 billion. This represents a $611.8 million, or 4.4 percent, increase over the previous fiscal year's budget. The budget covers various expenditures across different departments and services, including significant allocations to public works, transportation, commerce, public protection, and health services.",
+      role: 'assistant',
+      options: {}
+    }
+  },
+  sources: [Getter]
+}
+```
+
 Once again we see a `toolResult`. You can see the query the LLM decided to send to the query engine ("total budget"), and the output the engine returned. In `response.message` you see that the LLM has returned the output from the tool almost verbatim, although it trimmed out the bit about 2024-2025 since we didn't ask about that year.
 
-### Comparison of Approaches
-
-The `OpenAIContextAwareAgent` approach simplifies the setup by allowing you to directly link the retriever to the agent, making it straightforward to access relevant context for your queries. This is ideal for situations where you want easy integration with existing data sources, like a context chat engine.
-
-On the other hand, using the `QueryEngineTool` offers more flexibility and power. This method allows for customization in how queries are constructed and executed, enabling you to query data from various storages and process them in different ways. However, this added flexibility comes with increased complexity and response time due to the separate tool call and queryEngine generating tool output by LLM that is then passed to the agent.
-
 So now we have an agent that can index complicated documents and answer questions about them. Let's [combine our math agent and our RAG agent](rag_and_tools)!

apps/docs/docs/introduction.md

@@ -21,7 +21,7 @@ LlamaIndex.TS handles several major use cases:
 
 - **Structured Data Extraction**: turning complex, unstructured and semi-structured data into uniform, programmatically accessible formats.
 - **Retrieval-Augmented Generation (RAG)**: answering queries across your internal data by providing LLMs with up-to-date, semantically relevant context including Question and Answer systems and chat bots.
-- **Autonomous Agents**: building software that is capable of intelligently selecting and using tools to accomplish tasks in an interactive, unsupervised manner.
+- **Autonomous Agents**: building software that is capable of intelligently selecting and using tools to accomplish tasks in an interative, unsupervised manner.
 
 ## 👨‍👩‍👧‍👦 Who is LlamaIndex for?
 

apps/docs/docs/modules/agent/_category_.yml

@@ -1,2 +1,2 @@
 label: "Agents"
-position: 10
+position: 3

apps/docs/docs/modules/agent/index.md

@@ -12,15 +12,12 @@ An “agent” is an automated reasoning and decision engine. It takes in a user
 LlamaIndex.TS comes with a few built-in agents, but you can also create your own. The built-in agents include:
 
 - OpenAI Agent
-- Anthropic Agent both via Anthropic and Bedrock (in `@llamaIndex/community`)
-- Gemini Agent
+- Anthropic Agent
 - ReACT Agent
-- Meta3.1 504B via Bedrock (in `@llamaIndex/community`)
 
 ## Examples
 
 - [OpenAI Agent](../../examples/agent.mdx)
-- [Gemini Agent](../../examples/agent_gemini.mdx)
 
 ## Api References
 

apps/docs/docs/modules/chat_engine.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 13
+sidebar_position: 4
 ---
 
 # ChatEngine
@@ -27,4 +27,3 @@ for await (const chunk of stream) {
 
 - [ContextChatEngine](../api/classes/ContextChatEngine.md)
 - [CondenseQuestionChatEngine](../api/classes/ContextChatEngine.md)
-- [SimpleChatEngine](../api/classes/SimpleChatEngine.md)

apps/docs/docs/modules/data_index.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 12
+sidebar_position: 4
 ---
 
 # Index
@@ -8,7 +8,6 @@ An index is the basic container and organization for your data. LlamaIndex.TS su
 
 - `VectorStoreIndex` - will send the top-k `Node`s to the LLM when generating a response. The default top-k is 2.
 - `SummaryIndex` - will send every `Node` in the index to the LLM in order to generate a response
-- `KeywordTableIndex` extracts and provides keywords from `Node`s to the LLM
 
 ```typescript
 import { Document, VectorStoreIndex } from "llamaindex";
@@ -22,4 +21,3 @@ const index = await VectorStoreIndex.fromDocuments([document]);
 
 - [SummaryIndex](../api/classes/SummaryIndex.md)
 - [VectorStoreIndex](../api/classes/VectorStoreIndex.md)
-- [KeywordTableIndex](../api/classes/KeywordTableIndex.md)

apps/docs/docs/modules/data_loaders/discord.mdx

@@ -1,34 +0,0 @@
-import CodeBlock from "@theme/CodeBlock";
-import CodeSource from "!raw-loader!../../../../../examples/readers/src/discord";
-
-# DiscordReader
-
-DiscordReader is a simple data loader that reads all messages in a given Discord channel and returns them as Document objects.
-It uses the [@discordjs/rest](https://github.com/discordjs/discord.js/tree/main/packages/rest) library to fetch the messages.
-
-## Usage
-
-First step is to create a Discord Application and generating a bot token [here](https://discord.com/developers/applications).
-In your Discord Application, go to the `OAuth2` tab and generate an invite URL by selecting `bot` and click `Read Messages/View Channels` as wells as `Read Message History`.
-This will invite the bot with the necessary permissions to read messages.
-Copy the URL in your browser and select the server you want your bot to join.
-
-<CodeBlock language="ts">{CodeSource}</CodeBlock>
-
-### Params
-
-#### DiscordReader()
-
-- `discordToken?`: The Discord bot token.
-- `requestHandler?`: Optionally provide a custom request function for edge environments, e.g. `fetch`. See discord.js for more info.
-
-#### DiscordReader.loadData
-
-- `channelIDs`: The ID(s) of discord channels as an array of strings.
-- `limit?`: Optionally limit the number of messages to read
-- `additionalInfo?`: An optional flag to include embedded messages and attachment urls in the document.
-- `oldestFirst?`: An optional flag to return the oldest messages first.
-
-## API Reference
-
-- [DiscordReader](../../api/classes/DiscordReader.md)

apps/docs/docs/modules/data_loaders/index.mdx

@@ -6,19 +6,6 @@ import CodeSource2 from "!raw-loader!../../../../../examples/readers/src/custom-
 
 Before you can start indexing your documents, you need to load them into memory.
 
-All "basic" data loaders can be seen below, mapped to their respective filetypes in `SimpleDirectoryReader`. More loaders are shown in the sidebar on the left.
-Additionally the following loaders exist without separate documentation:
-
-- `AssemblyAIReader` transcribes audio using [AssemblyAI](https://www.assemblyai.com/).
-  - [AudioTranscriptReader](../../api/classes/AudioTranscriptReader.md): loads entire transcript as a single document.
-  - [AudioTranscriptParagraphsReader](../../api/classes/AudioTranscriptParagraphsReader.md): creates a document per paragraph.
-  - [AudioTranscriptSentencesReader](../../api/classes/AudioTranscriptSentencesReader.md): creates a document per sentence.
-  - [AudioSubtitlesReader](../../api/classes/AudioTranscriptParagraphsReader.md): creates a document containing the subtitles of a transcript.
-- [NotionReader](../../api/classes/NotionReader.md) loads [Notion](https://www.notion.so/) pages.
-- [SimpleMongoReader](../../api/classes/SimpleMongoReader) loads data from a [MongoDB](https://www.mongodb.com/).
-
-Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
-
 ## SimpleDirectoryReader
 
 [![Open in StackBlitz](https://developer.stackblitz.com/img/open_in_stackblitz.svg)](https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples/readers?file=src/simple-directory-reader.ts&title=Simple%20Directory%20Reader)
@@ -29,15 +16,7 @@ It is a simple reader that reads all files from a directory and its subdirectori
 
 <CodeBlock language="ts">{CodeSource}</CodeBlock>
 
-Currently, the following readers are mapped to specific file types:
-
-- [TextFileReader](../../api/classes/TextFileReader.md): `.txt`
-- [PDFReader](../../api/classes/PDFReader.md): `.pdf`
-- [PapaCSVReader](../../api/classes/PapaCSVReader.md): `.csv`
-- [MarkdownReader](../../api/classes/MarkdownReader.md): `.md`
-- [DocxReader](../../api/classes/DocxReader.md): `.docx`
-- [HTMLReader](../../api/classes/HTMLReader.md): `.htm`, `.html`
-- [ImageReader](../../api/classes/ImageReader.md): `.jpg`, `.jpeg`, `.png`, `.gif`
+Currently, it supports reading `.txt`, `.pdf`, `.csv`, `.md`, `.docx`, `.htm`, `.html`, `.jpg`, `.jpeg`, `.png` and `.gif` files, but support for other file types is planned.
 
 You can modify the reader three different ways:
 

apps/docs/docs/modules/data_loaders/json.md

@@ -1,149 +0,0 @@
-# JSONReader
-
-A simple JSON data loader with various options.
-Either parses the entire string, cleaning it and treat each line as an embedding or performs a recursive depth-first traversal yielding JSON paths.
-Supports streaming of large JSON data using [@discoveryjs/json-ext](https://github.com/discoveryjs/json-ext)
-
-## Usage
-
-```ts
-import { JSONReader } from "llamaindex";
-
-const file = "../../PATH/TO/FILE";
-const content = new TextEncoder().encode("JSON_CONTENT");
-
-const reader = new JSONReader({ levelsBack: 0, collapseLength: 100 });
-const docsFromFile = reader.loadData(file);
-const docsFromContent = reader.loadDataAsContent(content);
-```
-
-### Options
-
-Basic:
-
-- `streamingThreshold?`: The threshold for using streaming mode in MB of the JSON Data. CEstimates characters by calculating bytes: `(streamingThreshold * 1024 * 1024) / 2` and comparing against `.length` of the JSON string. Set `undefined` to disable streaming or `0` to always use streaming. Default is `50` MB.
-
-- `ensureAscii?`: Wether to ensure only ASCII characters be present in the output by converting non-ASCII characters to their unicode escape sequence. Default is `false`.
-
-- `isJsonLines?`: Wether the JSON is in JSON Lines format. If true, will split into lines, remove empty one and parse each line as JSON. Note: Uses a custom streaming parser, most likely less robust than json-ext. Default is `false`
-
-- `cleanJson?`: Whether to clean the JSON by filtering out structural characters (`{}, [], and ,`). If set to false, it will just parse the JSON, not removing structural characters. Default is `true`.
-
-- `logger?`: A placeholder for a custom logger function.
-
-Depth-First-Traversal:
-
-- `levelsBack?`: Specifies how many levels up the JSON structure to include in the output. `cleanJson` will be ignored. If set to 0, all levels are included. If undefined, parses the entire JSON, treat each line as an embedding and create a document per top-level array. Default is `undefined`
-
-- `collapseLength?`: The maximum length of JSON string representation to be collapsed into a single line. Only applicable when `levelsBack` is set. Default is `undefined`
-
-#### Examples
-
-<!-- prettier-ignore-start -->
-Input:
-
-```json
-{"a": {"1": {"key1": "value1"}, "2": {"key2": "value2"}}, "b": {"3": {"k3": "v3"}, "4": {"k4": "v4"}}}
-```
-
-Default options:
-
-`LevelsBack` = `undefined` & `cleanJson` = `true`
-
-Output:
-
-```json
-"a": {
-"1": {
-"key1": "value1"
-"2": {
-"key2": "value2"
-"b": {
-"3": {
-"k3": "v3"
-"4": {
-"k4": "v4"
-```
-
-Depth-First Traversal all levels:
-
-`levelsBack` = `0`
-
-Output:
-
-```json
-a 1 key1 value1
-a 2 key2 value2
-b 3 k3 v3
-b 4 k4 v4
-```
-
-Depth-First Traversal and Collapse:
-
-`levelsBack` = `0` & `collapseLength` = `35`
-
-Output:
-
-```json
-a 1 {"key1":"value1"}
-a 2 {"key2":"value2"}
-b {"3":{"k3":"v3"},"4":{"k4":"v4"}}
-```
-
-Depth-First Traversal limited levels:
-
-`levelsBack` = `2`
-
-Output:
-
-```json
-1 key1 value1
-2 key2 value2
-3 k3 v3
-4 k4 v4
-```
-
-Uncleaned JSON:
-
-`levelsBack` = `undefined` & `cleanJson` = `false`
-
-Output:
-
-```json
-{"a":{"1":{"key1":"value1"},"2":{"key2":"value2"}},"b":{"3":{"k3":"v3"},"4":{"k4":"v4"}}}
-```
-
-ASCII-Conversion:
-
-Input:
-
-```json
-{ "message": "こんにちは世界" }
-```
-
-Output:
-
-```json
-"message": "\u3053\u3093\u306b\u3061\u306f\u4e16\u754c"
-```
-
-JSON Lines Format:
-
-Input:
-
-```json
-{"tweet": "Hello world"}\n{"tweet": "こんにちは世界"}
-```
-
-Output:
-
-```json
-"tweet": "Hello world"
-
-"tweet": "こんにちは世界"
-```
-<!-- prettier-ignore-end -->
-
-## API Reference
-
-- [JSONReader](../../api/classes/JSONReader.md)

apps/docs/docs/modules/data_loaders/llama_parse/index.mdx

@@ -13,7 +13,7 @@ Official documentation for LlamaParse can be found [here](https://docs.cloud.lla
 ## Usage
 
 You can then use the `LlamaParseReader` class to load local files and convert them into a parsed document that can be used by LlamaIndex.
-See [reader.ts](https://github.com/run-llama/LlamaIndexTS/blob/main/packages/cloud/src/reader.ts) for a list of supported file types:
+See [LlamaParseReader.ts](https://github.com/run-llama/LlamaIndexTS/blob/main/packages/llamaindex/src/readers/LlamaParseReader.ts) for a list of supported file types:
 
 <CodeBlock language="ts">{CodeSource}</CodeBlock>
 
@@ -27,31 +27,23 @@ They can be divided into two groups.
 
 - `apiKey` is required. Can be set as an environment variable `LLAMA_CLOUD_API_KEY`
 - `checkInterval` is the interval in seconds to check if the parsing is done. Default is `1`.
-- `maxTimeout` is the maximum timeout to wait for parsing to finish. Default is `2000`
+- `maxTimeout` is the maximum timout to wait for parsing to finish. Default is `2000`
 - `verbose` shows progress of the parsing. Default is `true`
 - `ignoreErrors` set to false to get errors while parsing. Default is `true` and returns an empty array on error.
 
 #### Advanced params:
 
 - `resultType` can be set to `markdown`, `text` or `json`. Defaults to `text`. More information about `json` mode on the next pages.
-- `language` primarily helps with OCR recognition. Defaults to `en`. Click [here](../../../api/type-aliases/Language.md) for a list of supported languages.
+- `language` primarly helps with OCR recognition. Defaults to `en`. Click [here](../../../api/type-aliases/Language.md) for a list of supported languages.
 - `parsingInstructions?` Optional. Can help with complicated document structures. See this [LlamaIndex Blog Post](https://www.llamaindex.ai/blog/launching-the-first-genai-native-document-parsing-platform) for an example.
 - `skipDiagonalText?` Optional. Set to true to ignore diagonal text. (Text that is not rotated 0, 90, 180 or 270 degrees)
 - `invalidateCache?` Optional. Set to true to ignore the LlamaCloud cache. All document are kept in cache for 48hours after the job was completed to avoid processing the same document twice. Can be useful for testing when trying to re-parse the same document with, e.g. different `parsingInstructions`.
 - `doNotCache?` Optional. Set to true to not cache the document.
 - `fastMode?` Optional. Set to true to use the fast mode. This mode will skip OCR of images, and table/heading reconstruction. Note: Non-compatible with `gpt4oMode`.
-- `doNotUnrollColumns?` Optional. Set to true to keep the text according to document layout. Reduce reconstruction accuracy, and LLMs/embeddings performances in most cases.
-- `pageSeparator?` Optional. A templated page separator to use to split the text. If the results contain `{page_number}` (e.g. JSON mode), it will be replaced by the next page number. If not set the default separator `\\n---\\n` will be used.
-- `pagePrefix?` Optional. A templated prefix to add to the beginning of each page. If the results contain `{page_number}`, it will be replaced by the page number.
-- `pageSuffix?` Optional. A templated suffix to add to the end of each page. If the results contain `{page_number}`, it will be replaced by the page number.
-- `gpt4oMode` Deprecated. Use vendorMultimodal params. Set to true to use GPT-4o to extract content. Default is `false`.
-- `gpt4oApiKey?` Deprecated. Use vendorMultimodal params. Optional. Set the GPT-4o API key. Lowers the cost of parsing by using your own API key. Your OpenAI account will be charged. Can also be set in the environment variable `LLAMA_CLOUD_GPT4O_API_KEY`.
-- `boundingBox?` Optional. Specify an area of the document to parse. Expects the bounding box margins as a string in clockwise order, e.g. `boundingBox = "0.1,0,0,0"` to not parse the top 10% of the document.
-- `targetPages?` Optional. Specify which pages to parse by specifying them as a comma-separated list. First page is `0`.
-- `splitByPage` Wether to split the results, creating one document per page. Uses the set `pageSeparator` or `\n---\n` as fallback. Default is true.
-- `useVendorMultimodalModel` set to true to use a multimodal model. Default is `false`.
-- `vendorMultimodalModel?` Optional. Specify which multimodal model to use. Default is GPT4o. See [here](https://docs.cloud.llamaindex.ai/llamaparse/features/multimodal) for a list of available models and cost.
-- `vendorMultimodalApiKey?` Optional. Set the multimodal model API key. Can also be set in the environment variable `LLAMA_CLOUD_VENDOR_MULTIMODAL_API_KEY`.
+- `doNotUnrollColumns?` Optional. Set to true to keep the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most cases.
+- `pageSeperator?` Optional. The page seperator to use. Defaults is `\\n---\\n`.
+- `gpt4oMode` set to true to use GPT-4o to extract content. Default is `false`.
+- `gpt4oApiKey?` Optional. Set the GPT-4o API key. Lowers the cost of parsing by using your own API key. Your OpenAI account will be charged. Can also be set in the environment variable `LLAMA_CLOUD_GPT4O_API_KEY`.
 - `numWorkers` as in the python version, is set in `SimpleDirectoryReader`. Default is 1.
 
 ### LlamaParse with SimpleDirectoryReader

apps/docs/docs/modules/data_loaders/llama_parse/json_mode.mdx

@@ -8,7 +8,7 @@ In JSON mode, LlamaParse will return a data structure representing the parsed ob
 
 ## Usage
 
-For Json mode, you need to use `loadJson`. The `resultType` is automatically set with this method.
+For Json mode, you need to use `loadJson`. The `resultType` is automatically set with this method. Currently it can't be used with `SimpleDirectoryReader`.
 More information about indexing the results on the next page.
 
 ```ts
@@ -54,42 +54,6 @@ Within page objects, the following keys may be present depending on your documen
 - `images`: Any images extracted from the page.
 - `items`: An array of heading, text and table objects in the order they appear on the page.
 
-### JSON Mode with SimpleDirectoryReader
-
-All Readers share a `loadData` method with `SimpleDirectoryReader` that promises to return a uniform Document with Metadata. This makes JSON mode incompatible with SimpleDirectoryReader.
-
-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";
-
-class LlamaParseReaderWithJson extends LlamaParseReader {
-  // Override the loadData method
-  override async loadData(filePath: string): Promise<Document[]> {
-    // Call loadJson method that was inherited by LlamaParseReader
-    const jsonObjs = await super.loadJson(filePath);
-    let documents: Document[] = [];
-
-    jsonObjs.forEach((jsonObj) => {
-      // Making sure it's an array before iterating over it
-      if (Array.isArray(jsonObj.pages)) {
-      }
-      const docs = jsonObj.pages.map(
-        (page: { text: string; page: number }) =>
-          new Document({ text: page.text, metadata: { page: page.page } }),
-      );
-      documents = documents.concat(docs);
-    });
-    return documents;
-  }
-}
-```
-
-Now we have documents with page number as metadata. This new reader can be used like any other and be integrated with SimpleDirectoryReader. Since it extends `LlamaParseReader`, you can use the same params.
-
-You can assign any other values of the JSON response to the Document as needed.
-
 ## API Reference
 
 - [LlamaParseReader](../../../api/classes/LlamaParseReader.md)
-- [SimpleDirectoryReader](../../../api/classes/SimpleDirectoryReader.md)

apps/docs/docs/modules/data_stores/_category_.yml

@@ -1,2 +0,0 @@
-label: "Data Stores"
-position: 2

apps/docs/docs/modules/data_stores/chat_stores/_category_.yml

@@ -1 +0,0 @@
-label: "Chat Stores"

apps/docs/docs/modules/data_stores/chat_stores/index.md

@@ -1,13 +0,0 @@
-# Chat Stores
-
-Chat stores manage chat history by storing sequences of messages in a structured way, ensuring the order of messages is maintained for accurate conversation flow.
-
-## Available Chat Stores
-
-- [SimpleChatStore](../../../api/classes/SimpleChatStore.md): A simple in-memory chat store with support for [persisting](../index.md#local-storage) data to disk.
-
-Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
-
-## API Reference
-
-- [BaseChatStore](../../../api/interfaces/BaseChatStore.md)

apps/docs/docs/modules/data_stores/doc_stores/_category_.yml

@@ -1,2 +0,0 @@
-label: "Document Stores"
-position: 2

apps/docs/docs/modules/data_stores/doc_stores/index.md

@@ -1,14 +0,0 @@
-# Document Stores
-
-Document stores contain ingested document chunks, i.e. [Node](../../documents_and_nodes/index.md)s.
-
-## Available Document Stores
-
-- [SimpleDocumentStore](../../../api/classes/SimpleDocumentStore.md): A simple in-memory document store with support for [persisting](../index.md#local-storage) data to disk.
-- [PostgresDocumentStore](../../../api/classes/PostgresDocumentStore.md): A PostgreSQL document store, see [PostgreSQL Storage](../index.md#postgresql-storage).
-
-Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
-
-## API Reference
-
-- [BaseDocumentStore](../../../api/classes/BaseDocumentStore.md)

apps/docs/docs/modules/data_stores/index.md

@@ -1,56 +0,0 @@
-# Storage
-
-Storage in LlamaIndex.TS works automatically once you've configured a
-`StorageContext` object.
-
-## Local Storage
-
-You can configure the `persistDir` and attach it to an index.
-
-```typescript
-import {
-  Document,
-  VectorStoreIndex,
-  storageContextFromDefaults,
-} from "llamaindex";
-
-const storageContext = await storageContextFromDefaults({
-  persistDir: "./storage",
-});
-
-const document = new Document({ text: "Test Text" });
-const index = await VectorStoreIndex.fromDocuments([document], {
-  storageContext,
-});
-```
-
-## PostgreSQL Storage
-
-You can configure the `schemaName`, `tableName`, `namespace`, and
-`connectionString`. If a `connectionString` is not
-provided, it will use the environment variables `PGHOST`, `PGUSER`,
-`PGPASSWORD`, `PGDATABASE` and `PGPORT`.
-
-```typescript
-import {
-  Document,
-  VectorStoreIndex,
-  PostgresDocumentStore,
-  PostgresIndexStore,
-  storageContextFromDefaults,
-} from "llamaindex";
-
-const storageContext = await storageContextFromDefaults({
-  docStore: new PostgresDocumentStore(),
-  indexStore: new PostgresIndexStore(),
-});
-
-const document = new Document({ text: "Test Text" });
-const index = await VectorStoreIndex.fromDocuments([document], {
-  storageContext,
-});
-```
-
-## API Reference
-
-- [StorageContext](../../api/interfaces/StorageContext.md)

apps/docs/docs/modules/data_stores/index_stores/_category_.yml

@@ -1,2 +0,0 @@
-label: "Index Stores"
-position: 3

apps/docs/docs/modules/data_stores/index_stores/index.md

@@ -1,14 +0,0 @@
-# Index Stores
-
-Index stores are underlying storage components that contain metadata(i.e. information created when indexing) about the [index](../../data_index.md) itself.
-
-## Available Index Stores
-
-- [SimpleIndexStore](../../../api/classes/SimpleIndexStore.md): A simple in-memory index store with support for [persisting](../index.md#local-storage) data to disk.
-- [PostgresIndexStore](../../../api/classes/PostgresIndexStore.md): A PostgreSQL index store, , see [PostgreSQL Storage](../index.md#postgresql-storage).
-
-Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
-
-## API Reference
-
-- [BaseIndexStore](../../../api/classes/BaseIndexStore.md)

apps/docs/docs/modules/data_stores/kv_stores/_category_.yml

@@ -1,2 +0,0 @@
-label: "Key-Value Stores"
-position: 4

apps/docs/docs/modules/data_stores/kv_stores/index.md

@@ -1,14 +0,0 @@
-# Key-Value Stores
-
-Key-Value Stores represent underlying storage components used in [Document Stores](../doc_stores/index.md) and [Index Stores](../index_stores/index.md)
-
-## Available Key-Value Stores
-
-- [SimpleKVStore](../../../api/classes/SimpleKVStore.md): A simple Key-Value store with support of [persisting](../index.md#local-storage) data to disk.
-- [PostgresKVStore](../../../api/classes/PostgresKVStore.md): A PostgreSQL Key-Value store, see [PostgreSQL Storage](../index.md#postgresql-storage).
-
-Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
-
-## API Reference
-
-- [BaseKVStore](../../../api/classes/BaseKVStore.md)

apps/docs/docs/modules/data_stores/vector_stores/index.md

@@ -1,22 +0,0 @@
-# Vector Stores
-
-Vector stores save embedding vectors of your ingested document chunks.
-
-## Available Vector Stores
-
-Available Vector Stores are shown on the sidebar to the left. Additionally the following integrations exist without separate documentation:
-
-- [SimpleVectorStore](../../../api/classes/SimpleVectorStore.md): A simple in-memory vector store with optional [persistance](../index.md#local-storage) to disk.
-- [AstraDBVectorStore](../../../api/classes/AstraDBVectorStore.md): A cloud-native, scalable Database-as-a-Service built on Apache Cassandra, see [datastax.com](https://www.datastax.com/products/datastax-astra)
-- [ChromaVectorStore](../../../api/classes/ChromaVectorStore.md): An open-source vector database, focused on ease of use and performance, see [trychroma.com](https://www.trychroma.com/)
-- [MilvusVectorStore](../../../api/classes/MilvusVectorStore.md): An open-source, high-performance, highly scalable vector database, see [milvus.io](https://milvus.io/)
-- [MongoDBAtlasVectorSearch](../../../api/classes/MongoDBAtlasVectorSearch.md): A cloud-based vector search solution for MongoDB, see [mongodb.com](https://www.mongodb.com/products/platform/atlas-vector-search)
-- [PGVectorStore](../../../api/classes/PGVectorStore.md): An open-source vector store built on PostgreSQL, see [pgvector Github](https://github.com/pgvector/pgvector)
-- [PineconeVectorStore](../../../api/classes/PineconeVectorStore.md): A managed, cloud-native vector database, see [pinecone.io](https://www.pinecone.io/)
-- [WeaviateVectorStore](../../../api/classes/WeaviateVectorStore.md): An open-source, ai-native vector database, see [weaviate.io](https://weaviate.io/)
-
-Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
-
-## API Reference
-
-- [VectorStoreBase](../../../api/classes/VectorStoreBase.md)

apps/docs/docs/modules/documents_and_nodes/index.md

@@ -1,3 +1,7 @@
+---
+sidebar_position: 1
+---
+
 # Documents and Nodes
 
 `Document`s and `Node`s are the basic building blocks of any index. While the API for these objects is similar, `Document` objects represent entire files, while `Node`s are smaller pieces of that original document, that are suitable for an LLM and Q&A.

apps/docs/docs/modules/embeddings/_category_.yml

@@ -1,2 +1,2 @@
 label: "Embeddings"
-position: 6
+position: 3

apps/docs/docs/modules/embeddings/available_embeddings/mixedbreadai.md

@@ -1,104 +0,0 @@
-# MixedbreadAI
-
-Welcome to the mixedbread embeddings guide! This guide will help you use the mixedbread ai's API to generate embeddings for your text documents, ensuring you get the most relevant information, just like picking the freshest bread from the bakery.
-
-To find out more about the latest features, updates, and available models, visit [mixedbread.ai](https://mixedbread-ai.com/).
-
-## Table of Contents
-
-1. [Setup](#setup)
-2. [Usage with LlamaIndex](#usage-with-llamaindex)
-3. [Embeddings with Custom Parameters](#embeddings-with-custom-parameters)
-
-## Setup
-
-First, you will need to install the `llamaindex` package.
-
-```bash
-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";
-```
-
-## Usage with LlamaIndex
-
-This section will guide you through integrating mixedbread embeddings with LlamaIndex for more advanced usage.
-
-### Step 1: Load and Index Documents
-
-For this example, we will use a single document. In a real-world scenario, you would have multiple documents to index, like a variety of breads in a bakery.
-
-```ts
-Settings.embedModel = new MixedbreadAIEmbeddings({
-  apiKey: "<MIXEDBREAD_API_KEY>",
-  model: "mixedbread-ai/mxbai-embed-large-v1",
-});
-
-const document = new Document({
-  text: "The true source of happiness.",
-  id_: "bread",
-});
-
-const index = await VectorStoreIndex.fromDocuments([document]);
-```
-
-### Step 2: Create a Query Engine
-
-Combine the retriever and the embed model to create a query engine. This setup ensures that your queries are processed to provide the best results, like arranging the bread in the order of freshness and quality.
-
-Models can require prompts to generate embeddings for queries, in the 'mixedbread-ai/mxbai-embed-large-v1' model's case, the prompt is `Represent this sentence for searching relevant passages:`.
-
-```ts
-const queryEngine = index.asQueryEngine();
-
-const query =
-  "Represent this sentence for searching relevant passages: What is bread?";
-
-// Log the response
-const results = await queryEngine.query(query);
-console.log(results); // Serving up the freshest, most relevant results.
-```
-
-## Embeddings with Custom Parameters
-
-This section will guide you through generating embeddings with custom parameters and usage with f.e. matryoshka and binary embeddings.
-
-### Step 1: Create an Instance of MixedbreadAIEmbeddings
-
-Create a new instance of the `MixedbreadAIEmbeddings` class with custom parameters. For example, to use the `mixedbread-ai/mxbai-embed-large-v1` model with a batch size of 64, normalized embeddings, and binary encoding format:
-
-```ts
-const embeddings = new MixedbreadAIEmbeddings({
-  apiKey: "<MIXEDBREAD_API_KEY>",
-  model: "mixedbread-ai/mxbai-embed-large-v1",
-  batchSize: 64,
-  normalized: true,
-  dimensions: 512,
-  encodingFormat: MixedbreadAI.EncodingFormat.Binary,
-});
-```
-
-### Step 2: Define Texts
-
-Define the texts you want to generate embeddings for.
-
-```ts
-const texts = ["Bread is life", "Bread is love"];
-```
-
-### Step 3: Generate Embeddings
-
-Use the `embedDocuments` method to generate embeddings for the texts.
-
-```ts
-const result = await embeddings.embedDocuments(texts);
-console.log(result); // Perfectly customized embeddings, ready to serve.
-```
-
-## API Reference
-
-- [MixedbreadAIEmbeddings](../../../api/classes/MixedbreadAIEmbeddings.md)

apps/docs/docs/modules/embeddings/index.md

@@ -16,16 +16,6 @@ Settings.embedModel = new OpenAIEmbedding({
 
 For local embeddings, you can use the [HuggingFace](./available_embeddings/huggingface.md) embedding model.
 
-## Available Embeddings
-
-Most available embeddings are listed in the sidebar on the left.
-Additionally the following integrations exist without separate documentation:
-
-- [ClipEmbedding](../../api/classes/ClipEmbedding.md) using `@xenova/transformers`
-- [FireworksEmbedding](../../api/classes/FireworksEmbedding.md) see [fireworks.ai](https://fireworks.ai/)
-
-Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
-
 ## API Reference
 
 - [OpenAIEmbedding](../../api/classes/OpenAIEmbedding.md)

apps/docs/docs/modules/evaluation/_category_.yml

@@ -1,2 +1,2 @@
 label: "Evaluating"
-position: 9
+position: 3

apps/docs/docs/modules/evaluation/index.md

@@ -2,7 +2,7 @@
 
 ## Concept
 
-Evaluation and benchmarking are crucial concepts in LLM development. To improve the performance of an LLM app (RAG, agents) you must have a way to measure it.
+Evaluation and benchmarking are crucial concepts in LLM development. To improve the perfomance of an LLM app (RAG, agents) you must have a way to measure it.
 
 LlamaIndex offers key modules to measure the quality of generated results. We also offer key modules to measure retrieval quality.
 

apps/docs/docs/modules/ingestion_pipeline/_category_.yml

@@ -1,2 +1,2 @@
 label: "Ingestion Pipeline"
-position: 4
+position: 2

apps/docs/docs/modules/ingestion_pipeline/index.md

@@ -16,7 +16,7 @@ import {
   MetadataMode,
   OpenAIEmbedding,
   TitleExtractor,
-  SentenceSplitter,
+  SimpleNodeParser,
 } from "llamaindex";
 
 async function main() {
@@ -29,7 +29,7 @@ async function main() {
   const document = new Document({ text: essay, id_: path });
   const pipeline = new IngestionPipeline({
     transformations: [
-      new SentenceSplitter({ chunkSize: 1024, chunkOverlap: 20 }),
+      new SimpleNodeParser({ chunkSize: 1024, chunkOverlap: 20 }),
       new TitleExtractor(),
       new OpenAIEmbedding(),
     ],
@@ -62,7 +62,7 @@ import {
   MetadataMode,
   OpenAIEmbedding,
   TitleExtractor,
-  SentenceSplitter,
+  SimpleNodeParser,
   QdrantVectorStore,
   VectorStoreIndex,
 } from "llamaindex";
@@ -81,7 +81,7 @@ async function main() {
   const document = new Document({ text: essay, id_: path });
   const pipeline = new IngestionPipeline({
     transformations: [
-      new SentenceSplitter({ chunkSize: 1024, chunkOverlap: 20 }),
+      new SimpleNodeParser({ chunkSize: 1024, chunkOverlap: 20 }),
       new TitleExtractor(),
       new OpenAIEmbedding(),
     ],

apps/docs/docs/modules/ingestion_pipeline/transformations.md

@@ -4,7 +4,7 @@ A transformation is something that takes a list of nodes as an input, and return
 
 Currently, the following components are Transformation objects:
 
-- [SentenceSplitter](../../api/classes/SentenceSplitter.md)
+- [SimpleNodeParser](../../api/classes/SimpleNodeParser.md)
 - [MetadataExtractor](../documents_and_nodes/metadata_extraction.md)
 - [Embeddings](../embeddings/index.md)
 
@@ -13,10 +13,10 @@ Currently, the following components are Transformation objects:
 While transformations are best used with with an IngestionPipeline, they can also be used directly.
 
 ```ts
-import { SentenceSplitter, TitleExtractor, Document } from "llamaindex";
+import { SimpleNodeParser, TitleExtractor, Document } from "llamaindex";
 
 async function main() {
-  let nodes = new SentenceSplitter().getNodesFromDocuments([
+  let nodes = new SimpleNodeParser().getNodesFromDocuments([
     new Document({ text: "I am 10 years old. John is 20 years old." }),
   ]);
 
@@ -34,15 +34,15 @@ main().catch(console.error);
 
 ## Custom Transformations
 
-You can implement any transformation yourself by implementing the `TransformComponent`.
+You can implement any transformation yourself by implementing the `TransformerComponent`.
 
-The following custom transformation will remove any special characters or punctuation in text.
+The following custom transformation will remove any special characters or punctutaion in text.
 
 ```ts
-import { TransformComponent, TextNode } from "llamaindex";
+import { TransformerComponent, Node } from "llamaindex";
 
-export class RemoveSpecialCharacters extends TransformComponent {
-  async transform(nodes: TextNode[]): Promise<TextNode[]> {
+class RemoveSpecialCharacters extends TransformerComponent {
+  async transform(nodes: Node[]): Promise<Node[]> {
     for (const node of nodes) {
       node.text = node.text.replace(/[^\w\s]/gi, "");
     }
@@ -75,7 +75,3 @@ async function main() {
 
 main().catch(console.error);
 ```
-
-## API Reference
-
-- [TransformComponent](../../api/classes/TransformComponent.md)

apps/docs/docs/modules/llms/_category_.yml

@@ -1,2 +1,2 @@
 label: "LLMs"
-position: 5
+position: 3

apps/docs/docs/modules/llms/available_llms/bedrock.md

@@ -15,7 +15,7 @@ Settings.llm = new Bedrock({
 });
 ```
 
-Currently only supports Anthropic and Meta models:
+Currently only supports Anthropic models:
 
 ```ts
 ANTHROPIC_CLAUDE_INSTANT_1 = "anthropic.claude-instant-v1";
@@ -25,40 +25,6 @@ ANTHROPIC_CLAUDE_3_SONNET = "anthropic.claude-3-sonnet-20240229-v1:0";
 ANTHROPIC_CLAUDE_3_HAIKU = "anthropic.claude-3-haiku-20240307-v1:0";
 ANTHROPIC_CLAUDE_3_OPUS = "anthropic.claude-3-opus-20240229-v1:0"; // available on us-west-2
 ANTHROPIC_CLAUDE_3_5_SONNET = "anthropic.claude-3-5-sonnet-20240620-v1:0";
-META_LLAMA2_13B_CHAT = "meta.llama2-13b-chat-v1";
-META_LLAMA2_70B_CHAT = "meta.llama2-70b-chat-v1";
-META_LLAMA3_8B_INSTRUCT = "meta.llama3-8b-instruct-v1:0";
-META_LLAMA3_70B_INSTRUCT = "meta.llama3-70b-instruct-v1:0";
-META_LLAMA3_1_8B_INSTRUCT = "meta.llama3-1-8b-instruct-v1:0"; // available on us-west-2
-META_LLAMA3_1_70B_INSTRUCT = "meta.llama3-1-70b-instruct-v1:0"; // available on us-west-2
-META_LLAMA3_1_405B_INSTRUCT = "meta.llama3-1-405b-instruct-v1:0"; // available on us-west-2, tool calling supported
-META_LLAMA3_2_1B_INSTRUCT = "meta.llama3-2-1b-instruct-v1:0"; // only available via inference endpoints (see below)
-META_LLAMA3_2_3B_INSTRUCT = "meta.llama3-2-3b-instruct-v1:0"; // only available via inference endpoints (see below)
-META_LLAMA3_2_11B_INSTRUCT = "meta.llama3-2-11b-instruct-v1:0"; // only available via inference endpoints (see below), multimodal and function call supported
-META_LLAMA3_2_90B_INSTRUCT = "meta.llama3-2-90b-instruct-v1:0"; // only available via inference endpoints (see below), multimodal and function call supported
-```
-
-You can also use Bedrock's Inference endpoints by using the model names:
-
-```ts
-// US
-US_ANTHROPIC_CLAUDE_3_HAIKU = "us.anthropic.claude-3-haiku-20240307-v1:0";
-US_ANTHROPIC_CLAUDE_3_OPUS = "us.anthropic.claude-3-opus-20240229-v1:0";
-US_ANTHROPIC_CLAUDE_3_SONNET = "us.anthropic.claude-3-sonnet-20240229-v1:0";
-US_ANTHROPIC_CLAUDE_3_5_SONNET = "us.anthropic.claude-3-5-sonnet-20240620-v1:0";
-US_ANTHROPIC_CLAUDE_3_5_SONNET_V2 =
-  "us.anthropic.claude-3-5-sonnet-20241022-v2:0";
-US_META_LLAMA_3_2_1B_INSTRUCT = "us.meta.llama3-2-1b-instruct-v1:0";
-US_META_LLAMA_3_2_3B_INSTRUCT = "us.meta.llama3-2-3b-instruct-v1:0";
-US_META_LLAMA_3_2_11B_INSTRUCT = "us.meta.llama3-2-11b-instruct-v1:0";
-US_META_LLAMA_3_2_90B_INSTRUCT = "us.meta.llama3-2-90b-instruct-v1:0";
-
-// EU
-EU_ANTHROPIC_CLAUDE_3_HAIKU = "eu.anthropic.claude-3-haiku-20240307-v1:0";
-EU_ANTHROPIC_CLAUDE_3_SONNET = "eu.anthropic.claude-3-sonnet-20240229-v1:0";
-EU_ANTHROPIC_CLAUDE_3_5_SONNET = "eu.anthropic.claude-3-5-sonnet-20240620-v1:0";
-EU_META_LLAMA_3_2_1B_INSTRUCT = "eu.meta.llama3-2-1b-instruct-v1:0";
-EU_META_LLAMA_3_2_3B_INSTRUCT = "eu.meta.llama3-2-3b-instruct-v1:0";
 ```
 
 Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url format, e.g. `data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==`
@@ -94,72 +60,3 @@ async function main() {
   console.log(response.response);
 }
 ```
-
-## Agent Example
-
-```ts
-import { BEDROCK_MODELS, Bedrock } from "@llamaindex/community";
-import { FunctionTool, LLMAgent } from "llamaindex";
-
-const sumNumbers = FunctionTool.from(
-  ({ a, b }: { a: number; b: number }) => `${a + b}`,
-  {
-    name: "sumNumbers",
-    description: "Use this function to sum two numbers",
-    parameters: {
-      type: "object",
-      properties: {
-        a: {
-          type: "number",
-          description: "The first number",
-        },
-        b: {
-          type: "number",
-          description: "The second number",
-        },
-      },
-      required: ["a", "b"],
-    },
-  },
-);
-
-const divideNumbers = FunctionTool.from(
-  ({ a, b }: { a: number; b: number }) => `${a / b}`,
-  {
-    name: "divideNumbers",
-    description: "Use this function to divide two numbers",
-    parameters: {
-      type: "object",
-      properties: {
-        a: {
-          type: "number",
-          description: "The dividend a to divide",
-        },
-        b: {
-          type: "number",
-          description: "The divisor b to divide by",
-        },
-      },
-      required: ["a", "b"],
-    },
-  },
-);
-
-const bedrock = new Bedrock({
-  model: BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
-  ...
-});
-
-async function main() {
-  const agent = new LLMAgent({
-    llm: bedrock,
-    tools: [sumNumbers, divideNumbers],
-  });
-
-  const response = await agent.chat({
-    message: "How much is 5 + 5? then divide by 2",
-  });
-
-  console.log(response.message);
-}
-```

apps/docs/docs/modules/llms/available_llms/deepseek.md

@@ -1,52 +0,0 @@
-# DeepSeek LLM
-
-[DeepSeek Platform](https://platform.deepseek.com/)
-
-## Usage
-
-```ts
-import { DeepSeekLLM, Settings } from "llamaindex";
-
-Settings.llm = new DeepSeekLLM({
-  apiKey: "<YOUR_API_KEY>",
-  model: "deepseek-coder", // or "deepseek-chat"
-});
-```
-
-## Example
-
-```ts
-import { DeepSeekLLM, Document, VectorStoreIndex, Settings } from "llamaindex";
-
-const deepseekLlm = new DeepSeekLLM({
-  apiKey: "<YOUR_API_KEY>",
-  model: "deepseek-coder", // or "deepseek-chat"
-});
-
-async function main() {
-  const response = await llm.deepseekLlm.chat({
-    messages: [
-      {
-        role: "system",
-        content: "You are an AI assistant",
-      },
-      {
-        role: "user",
-        content: "Tell me about San Francisco",
-      },
-    ],
-    stream: false,
-  });
-  console.log(response);
-}
-```
-
-# Limitations
-
-Currently does not support function calling.
-
-[Currently does not support json-output param while still is very good at json generating.](https://platform.deepseek.com/api-docs/faq#does-your-api-support-json-output)
-
-## API Reference
-
-- [DeepSeekLLM](../../../api/classes/DeepSeekLLM.md)

apps/docs/docs/modules/llms/available_llms/fireworks.md

@@ -1,6 +1,6 @@
 # Fireworks LLM
 
-[Fireworks.ai](https://fireworks.ai/) focus on production use cases for open source LLMs, offering speed and quality.
+Fireworks.ai focus on production use cases for open source LLMs, offering speed and quality.
 
 ## Usage
 

apps/docs/docs/modules/llms/index.md

@@ -1,3 +1,7 @@
+---
+sidebar_position: 3
+---
+
 # Large Language Models (LLMs)
 
 The LLM is responsible for reading text and generating natural language responses to queries. By default, LlamaIndex.TS uses `gpt-3.5-turbo`.
@@ -26,15 +30,6 @@ export AZURE_OPENAI_DEPLOYMENT="gpt-4" # or some other deployment name
 
 For local LLMs, currently we recommend the use of [Ollama](./available_llms/ollama.md) LLM.
 
-## Available LLMs
-
-Most available LLMs are listed in the sidebar on the left. Additionally the following integrations exist without separate documentation:
-
-- [HuggingFaceLLM](../../api/classes/HuggingFaceLLM.md) and [HuggingFaceInferenceAPI](../../api/classes/HuggingFaceInferenceAPI.md).
-- [ReplicateLLM](../../api/classes/ReplicateLLM.md) see [replicate.com](https://replicate.com/)
-
-Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
-
 ## API Reference
 
 - [OpenAI](../../api/classes/OpenAI.md)

apps/docs/docs/modules/node_parser.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 11
+sidebar_position: 4
 ---
 
 # NodeParser
@@ -7,9 +7,9 @@ sidebar_position: 11
 The `NodeParser` in LlamaIndex is responsible for splitting `Document` objects into more manageable `Node` objects. When you call `.fromDocuments()`, the `NodeParser` from the `Settings` is used to do this automatically for you. Alternatively, you can use it to split documents ahead of time.
 
 ```typescript
-import { Document, SentenceSplitter } from "llamaindex";
+import { Document, SimpleNodeParser } from "llamaindex";
 
-const nodeParser = new SentenceSplitter();
+const nodeParser = new SimpleNodeParser();
 
 Settings.nodeParser = nodeParser;
 ```
@@ -93,5 +93,6 @@ The output metadata will be something like:
 
 ## API Reference
 
+- [SimpleNodeParser](../api/classes/SimpleNodeParser.md)
 - [SentenceSplitter](../api/classes/SentenceSplitter.md)
 - [MarkdownNodeParser](../api/classes/MarkdownNodeParser.md)

apps/docs/docs/modules/node_postprocessors/cohere_reranker.md

@@ -39,9 +39,8 @@ const index = await VectorStoreIndex.fromDocuments([document]);
 The default value for `similarityTopK` is 2. This means that only the most similar document will be returned. To retrieve more results, you can increase the value of `similarityTopK`.
 
 ```ts
-const retriever = index.asRetriever({
-  similarityTopK: 5,
-});
+const retriever = index.asRetriever();
+retriever.similarityTopK = 5;
 ```
 
 ## Create a new instance of the CohereRerank class

apps/docs/docs/modules/node_postprocessors/index.md

@@ -107,4 +107,3 @@ const filteredNodes = processor.postprocessNodes(nodes);
 ## API Reference
 
 - [SimilarityPostprocessor](../../api/classes/SimilarityPostprocessor.md)
-- [MetadataReplacementPostProcessor](../../api/classes/MetadataReplacementPostProcessor.md)

apps/docs/docs/modules/node_postprocessors/jinaai_reranker.md

@@ -39,9 +39,8 @@ const index = await VectorStoreIndex.fromDocuments([document]);
 The default value for `similarityTopK` is 2. This means that only the most similar document will be returned. To retrieve more results, you can increase the value of `similarityTopK`.
 
 ```ts
-const retriever = index.asRetriever({
-  similarityTopK: 5,
-});
+const retriever = index.asRetriever();
+retriever.similarityTopK = 5;
 ```
 
 ## Create a new instance of the JinaAIReranker class

apps/docs/docs/modules/node_postprocessors/mixedbreadiai_reranker.md

@@ -1,169 +0,0 @@
-# MixedbreadAI
-
-Welcome to the mixedbread ai reranker guide! This guide will help you use mixedbread ai's API to rerank search query results, ensuring you get the most relevant information, just like picking the freshest bread from the bakery.
-
-To find out more about the latest features and updates, visit the [mixedbread.ai](https://mixedbread.ai/).
-
-## Table of Contents
-
-1. [Setup](#setup)
-2. [Usage with LlamaIndex](#usage-with-llamaindex)
-3. [Simple Reranking Guide](#simple-reranking-guide)
-4. [Reranking with Objects](#reranking-with-objects)
-
-## Setup
-
-First, you will need to install the `llamaindex` package.
-
-```bash
-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 `MixedbreadAIReranker` class.
-
-```ts
-import {
-  MixedbreadAIReranker,
-  Document,
-  OpenAI,
-  VectorStoreIndex,
-  Settings,
-} from "llamaindex";
-```
-
-## Usage with LlamaIndex
-
-This section will guide you through integrating mixedbread's reranker with LlamaIndex.
-
-### Step 1: Load and Index Documents
-
-For this example, we will use a single document. In a real-world scenario, you would have multiple documents to index, like a variety of breads in a bakery.
-
-```ts
-const document = new Document({
-  text: "This is a sample document.",
-  id_: "sampleDoc",
-});
-
-Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.1 });
-
-const index = await VectorStoreIndex.fromDocuments([document]);
-```
-
-### Step 2: Increase Similarity TopK
-
-The default value for `similarityTopK` is 2, which means only the most similar document will be returned. To get more results, like picking a variety of fresh breads, you can increase the value of `similarityTopK`.
-
-```ts
-const retriever = index.asRetriever({
-  similarityTopK: 5,
-});
-```
-
-### Step 3: Create a MixedbreadAIReranker Instance
-
-Create a new instance of the `MixedbreadAIReranker` class.
-
-```ts
-const nodePostprocessor = new MixedbreadAIReranker({
-  apiKey: "<MIXEDBREAD_API_KEY>",
-  topN: 4,
-});
-```
-
-### Step 4: Create a Query Engine
-
-Combine the retriever and node postprocessor to create a query engine. This setup ensures that your queries are processed and reranked to provide the best results, like arranging the bread in the order of freshness and quality.
-
-```ts
-const queryEngine = index.asQueryEngine({
-  retriever,
-  nodePostprocessors: [nodePostprocessor],
-});
-
-// Log the response
-const response = await queryEngine.query("Where did the author grow up?");
-console.log(response);
-```
-
-With mixedbread's Reranker, you're all set to serve up the most relevant and well-ordered results, just like a skilled baker arranging their best breads for eager customers. Enjoy the perfect blend of technology and culinary delight!
-
-## Simple Reranking Guide
-
-This section will guide you through a simple reranking process using mixedbread ai.
-
-### Step 1: Create an Instance of MixedbreadAIReranker
-
-Create a new instance of the `MixedbreadAIReranker` class, passing in your API key and the number of results you want to return. It's like setting up your bakery to offer a specific number of freshly baked items.
-
-```ts
-const reranker = new MixedbreadAIReranker({
-  apiKey: "<MIXEDBREAD_API_KEY>",
-  topN: 4,
-});
-```
-
-### Step 2: Define Nodes and Query
-
-Define the nodes (documents) you want to rerank and the query.
-
-```ts
-const nodes = [
-  { node: new BaseNode("To bake bread you need flour") },
-  { node: new BaseNode("To bake bread you need yeast") },
-];
-const query = "What do you need to bake bread?";
-```
-
-### Step 3: Perform Reranking
-
-Use the `postprocessNodes` method to rerank the nodes based on the query.
-
-```ts
-const result = await reranker.postprocessNodes(nodes, query);
-console.log(result); // Like pulling freshly baked nodes out of the oven.
-```
-
-## Reranking with Objects
-
-This section will guide you through reranking when working with objects.
-
-### Step 1: Create an Instance of MixedbreadAIReranker
-
-Create a new instance of the `MixedbreadAIReranker` class, just like before.
-
-```ts
-const reranker = new MixedbreadAIReranker({
-  apiKey: "<MIXEDBREAD_API_KEY>",
-  model: "mixedbread-ai/mxbai-rerank-large-v1",
-  topK: 5,
-  rankFields: ["title", "content"],
-  returnInput: true,
-  maxRetries: 5,
-});
-```
-
-### Step 2: Define Documents and Query
-
-Define the documents (objects) you want to rerank and the query.
-
-```ts
-const documents = [
-  { title: "Bread Recipe", content: "To bake bread you need flour" },
-  { title: "Bread Recipe", content: "To bake bread you need yeast" },
-];
-const query = "What do you need to bake bread?";
-```
-
-### Step 3: Perform Reranking
-
-Use the `rerank` method to reorder the documents based on the query.
-
-```ts
-const result = await reranker.rerank(documents, query);
-console.log(result); // Perfectly customized results, ready to serve.
-```
-
-## API Reference
-
-- [MixedbreadAIReranker](../../api/classes/MixedbreadAIReranker.md)

apps/docs/docs/modules/prompt/_category_.yml

@@ -1,2 +1,2 @@
 label: "Prompts"
-position: 7
+position: 0

apps/docs/docs/modules/prompt/index.md

@@ -73,5 +73,6 @@ const response = await queryEngine.query({
 
 ## API Reference
 
+- [TextQaPrompt](../../api/type-aliases/TextQaPrompt.md)
 - [ResponseSynthesizer](../../api/classes/ResponseSynthesizer.md)
 - [CompactAndRefine](../../api/classes/CompactAndRefine.md)

apps/docs/docs/modules/query_engines/_category_.yml

@@ -1,2 +1,2 @@
 label: "Query Engines"
-position: 8
+position: 2

apps/docs/docs/modules/query_engines/index.md

@@ -1,6 +1,6 @@
 # QueryEngine
 
-A query engine wraps a `Retriever` and a `ResponseSynthesizer` into a pipeline, that will use the query string to fetch nodes and then send them to the LLM to generate a response.
+A query engine wraps a `Retriever` and a `ResponseSynthesizer` into a pipeline, that will use the query string to fetech nodes and then send them to the LLM to generate a response.
 
 ```typescript
 const queryEngine = index.asQueryEngine();

apps/docs/docs/modules/query_engines/metadata_filtering.md

@@ -75,7 +75,7 @@ const queryEngine = index.asQueryEngine({
       {
         key: "dogId",
         value: "2",
-        operator: "==",
+        filterType: "ExactMatch",
       },
     ],
   },
@@ -88,8 +88,6 @@ const response = await queryEngine.query({
 console.log(response.toString());
 ```
 
-Besides using the equal operator (`==`), you can also use a whole set of different [operators](../../api/interfaces/MetadataFilter.md#operator) to filter your documents.
-
 ## Full Code
 
 ```ts
@@ -137,7 +135,7 @@ async function main() {
           {
             key: "dogId",
             value: "2",
-            operator: "==",
+            filterType: "ExactMatch",
           },
         ],
       },
@@ -158,4 +156,3 @@ main();
 
 - [VectorStoreIndex](../../api/classes/VectorStoreIndex.md)
 - [ChromaVectorStore](../../api/classes/ChromaVectorStore.md)
-- [MetadataFilter](../../api/interfaces/MetadataFilter.md)

apps/docs/docs/modules/query_engines/router_query_engine.md

@@ -15,7 +15,7 @@ import {
   OpenAI,
   RouterQueryEngine,
   SimpleDirectoryReader,
-  SentenceSplitter,
+  SimpleNodeParser,
   SummaryIndex,
   VectorStoreIndex,
   Settings,
@@ -34,11 +34,11 @@ const documents = await new SimpleDirectoryReader().loadData({
 
 ## Service Context
 
-Next, we need to define some basic rules and parse the documents into nodes. We will use the `SentenceSplitter` to parse the documents into nodes and `Settings` to define the rules (eg. LLM API key, chunk size, etc.):
+Next, we need to define some basic rules and parse the documents into nodes. We will use the `SimpleNodeParser` to parse the documents into nodes and `Settings` to define the rules (eg. LLM API key, chunk size, etc.):
 
 ```ts
 Settings.llm = new OpenAI();
-Settings.nodeParser = new SentenceSplitter({
+Settings.nodeParser = new SimpleNodeParser({
   chunkSize: 1024,
 });
 ```
@@ -104,14 +104,14 @@ import {
   OpenAI,
   RouterQueryEngine,
   SimpleDirectoryReader,
-  SentenceSplitter,
+  SimpleNodeParser,
   SummaryIndex,
   VectorStoreIndex,
   Settings,
 } from "llamaindex";
 
 Settings.llm = new OpenAI();
-Settings.nodeParser = new SentenceSplitter({
+Settings.nodeParser = new SimpleNodeParser({
   chunkSize: 1024,
 });
 

apps/docs/docs/modules/response_synthesizer.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 15
+sidebar_position: 6
 ---
 
 # ResponseSynthesizer

apps/docs/docs/modules/retriever.md

@@ -1,23 +1,21 @@
 ---
-sidebar_position: 14
+sidebar_position: 5
 ---
 
 # Retriever
 
-A retriever in LlamaIndex is what is used to fetch `Node`s from an index using a query string.
-
-- [VectorIndexRetriever](../api/classes/VectorIndexRetriever.md) will fetch the top-k most similar nodes. Ideal for dense retrieval to find most relevant nodes.
-- [SummaryIndexRetriever](../api/classes/SummaryIndexRetriever.md) will fetch all nodes no matter the query. Ideal when complete context is necessary, e.g. analyzing large datasets.
-- [SummaryIndexLLMRetriever](../api/classes/SummaryIndexLLMRetriever.md) utilizes an LLM to score and filter nodes based on relevancy to the query.
-- [KeywordTableLLMRetriever](../api/classes/KeywordTableLLMRetriever.md) uses an LLM to extract keywords from the query and retrieve relevant nodes based on keyword matches.
-- [KeywordTableSimpleRetriever](../api/classes/KeywordTableSimpleRetriever.md) uses a basic frequency-based approach to extract keywords and retrieve nodes.
-- [KeywordTableRAKERetriever](../api/classes/KeywordTableRAKERetriever.md) uses the RAKE (Rapid Automatic Keyword Extraction) algorithm to extract keywords from the query, focusing on co-occurrence and context for keyword-based retrieval.
+A retriever in LlamaIndex is what is used to fetch `Node`s from an index using a query string. Aa `VectorIndexRetriever` will fetch the top-k most similar nodes. Meanwhile, a `SummaryIndexRetriever` will fetch all nodes no matter the query.
 
 ```typescript
-const retriever = vectorIndex.asRetriever({
-  similarityTopK: 3,
-});
+const retriever = vector_index.asRetriever();
+retriever.similarityTopK = 3;
 
 // Fetch nodes!
 const nodesWithScore = await retriever.retrieve({ query: "query string" });
 ```
+
+## API Reference
+
+- [SummaryIndexRetriever](../api/classes/SummaryIndexRetriever.md)
+- [SummaryIndexLLMRetriever](../api/classes/SummaryIndexLLMRetriever.md)
+- [VectorIndexRetriever](../api/classes/VectorIndexRetriever.md)

apps/docs/docs/modules/storage.md

@@ -0,0 +1,26 @@
+---
+sidebar_position: 7
+---
+
+# Storage
+
+Storage in LlamaIndex.TS works automatically once you've configured a `StorageContext` object. Just configure the `persistDir` and attach it to an index.
+
+Right now, only saving and loading from disk is supported, with future integrations planned!
+
+```typescript
+import { Document, VectorStoreIndex, storageContextFromDefaults } from "./src";
+
+const storageContext = await storageContextFromDefaults({
+  persistDir: "./storage",
+});
+
+const document = new Document({ text: "Test Text" });
+const index = await VectorStoreIndex.fromDocuments([document], {
+  storageContext,
+});
+```
+
+## API Reference
+
+- [StorageContext](../api/interfaces/StorageContext.md)

apps/docs/docs/modules/vector_stores/qdrant.md

@@ -1,7 +1,5 @@
 # Qdrant Vector Store
 
-[qdrant.tech](https://qdrant.tech/)
-
 To run this example, you need to have a Qdrant instance running. You can run it with Docker:
 
 ```bash
@@ -89,4 +87,4 @@ main().catch(console.error);
 
 ## API Reference
 
-- [QdrantVectorStore](../../../api/classes/QdrantVectorStore.md)
+- [QdrantVectorStore](../../api/classes/QdrantVectorStore.md)

apps/docs/docs/modules/workflows.mdx

@@ -1,168 +0,0 @@
-import CodeBlock from "@theme/CodeBlock";
-import CodeSource from "!raw-loader!../../../../examples/workflow/joke.ts";
-
-# Workflows
-
-A `Workflow` in LlamaIndexTS is an event-driven abstraction used to chain together several events. Workflows are made up of `steps`, with each step responsible for handling certain event types and emitting new events.
-
-Workflows in LlamaIndexTS work by defining step functions that handle specific event types and emit new events.
-
-When a step function is added to a workflow, you need to specify the input and optionally the output event types (used for validation). The specification of the input events ensures each step only runs when an accepted event is ready.
-
-You can create a `Workflow` to do anything! Build an agent, a RAG flow, an extraction flow, or anything else you want.
-
-## Getting Started
-
-As an illustrative example, let's consider a naive workflow where a joke is generated and then critiqued.
-
-<CodeBlock language="ts">{CodeSource}</CodeBlock>
-
-There's a few moving pieces here, so let's go through this piece by piece.
-
-### Defining Workflow Events
-
-```typescript
-export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
-```
-
-Events are user-defined classes that extend `WorkflowEvent` and contain arbitrary data provided as template argument. In this case, our workflow relies on a single user-defined event, the `JokeEvent` with a `joke` attribute of type `string`.
-
-### Setting up the Workflow Class
-
-```typescript
-const llm = new OpenAI();
-...
-const jokeFlow = new Workflow({ verbose: true });
-```
-
-Our workflow is implemented by initiating the `Workflow` class. For simplicity, we created a `OpenAI` llm instance.
-
-### Workflow Entry Points
-
-```typescript
-const generateJoke = async (_context: Context, ev: StartEvent) => {
-  const prompt = `Write your best joke about ${ev.data.input}.`;
-  const response = await llm.complete({ prompt });
-  return new JokeEvent({ joke: response.text });
-};
-```
-
-Here, we come to the entry-point of our workflow. While events are user-defined, there are two special-case events, the `StartEvent` and the `StopEvent`. Here, the `StartEvent` signifies where to send the initial workflow input.
-
-The `StartEvent` is a bit of a special object since it can hold arbitrary attributes. Here, we accessed the topic with `ev.data.input`.
-
-At this point, you may have noticed that we haven't explicitly told the workflow what events are handled by which steps.
-
-To do so, we use the `addStep` method which adds a step to the workflow. The first argument is the event type that the step will handle, and the second argument is the previously defined step function:
-
-```typescript
-jokeFlow.addStep(StartEvent, generateJoke);
-```
-
-### Workflow Exit Points
-
-```typescript
-const critiqueJoke = async (_context: Context, ev: JokeEvent) => {
-  const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
-  const response = await llm.complete({ prompt });
-  return new StopEvent({ result: response.text });
-};
-```
-
-Here, we have our second, and last step, in the workflow. We know its the last step because the special `StopEvent` is returned. When the workflow encounters a returned `StopEvent`, it immediately stops the workflow and returns whatever the result was.
-
-In this case, the result is a string, but it could be a map, array, or any other object.
-
-Don't forget to add the step to the workflow:
-
-```typescript
-jokeFlow.addStep(JokeEvent, critiqueJoke);
-```
-
-### Running the Workflow
-
-```typescript
-const result = await jokeFlow.run("pirates");
-console.log(result.data.result);
-```
-
-Lastly, we run the workflow. The `.run()` method is async, so we use await here to wait for the result.
-
-### Validating Workflows
-
-To tell the workflow what events are produced by each step, you can optionally provide a third argument to `addStep` to specify the output event type:
-
-```typescript
-jokeFlow.addStep(StartEvent, generateJoke, { outputs: JokeEvent });
-jokeFlow.addStep(JokeEvent, critiqueJoke, { outputs: StopEvent });
-```
-
-To validate a workflow, you need to call the `validate` method:
-
-```typescript
-jokeFlow.validate();
-```
-
-To automatically validate a workflow when you run it, you can set the `validate` flag to `true` at initialization:
-
-```typescript
-const jokeFlow = new Workflow({ verbose: true, validate: true });
-```
-
-## Working with Global Context/State
-
-Optionally, you can choose to use global context between steps. For example, maybe multiple steps access the original `query` input from the user. You can store this in global context so that every step has access.
-
-```typescript
-import { Context } from "@llamaindex/core/workflow";
-
-const query = async (context: Context, ev: MyEvent) => {
-  // get the query from the context
-  const query = context.get("query");
-  // do something with context and event
-  const val = ...
-  const result = ...
-  // store in context
-  context.set("key", val);
-
-  return new StopEvent({ result });
-};
-```
-
-## Waiting for Multiple Events
-
-The context does more than just hold data, it also provides utilities to buffer and wait for multiple events.
-
-For example, you might have a step that waits for a query and retrieved nodes before synthesizing a response:
-
-```typescript
-const synthesize = async (context: Context, ev: QueryEvent | RetrieveEvent) => {
-  const events = context.collectEvents(ev, [QueryEvent | RetrieveEvent]);
-  if (!events) {
-    return;
-  }
-  const prompt = events
-    .map((event) => {
-      if (event instanceof QueryEvent) {
-        return `Answer this query using the context provided: ${event.data.query}`;
-      } else if (event instanceof RetrieveEvent) {
-        return `Context: ${event.data.context}`;
-      }
-      return "";
-    })
-    .join("\n");
-
-  const response = await llm.complete({ prompt });
-  return new StopEvent({ result: response.text });
-};
-```
-
-Using `ctx.collectEvents()` we can buffer and wait for ALL expected events to arrive. This function will only return events (in the requested order) once all events have arrived.
-
-## Manually Triggering Events
-
-Normally, events are triggered by returning another event during a step. However, events can also be manually dispatched using the `ctx.sendEvent(event)` method within a workflow.
-
-## Examples
-
-You can find many useful examples of using workflows in the [examples folder](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/workflow).

apps/docs/docusaurus.config.js

@@ -1,7 +1,6 @@
 // @ts-check
 // Note: type annotations allow type checking and IDEs autocompletion
 
-// eslint-disable-next-line @typescript-eslint/no-require-imports
 const renderer = require("prism-react-renderer");
 const lightCodeTheme = renderer.themes.github;
 const darkCodeTheme = renderer.themes.dracula;
@@ -26,6 +25,30 @@ const config = {
   onBrokenLinks: "warn",
   onBrokenMarkdownLinks: "warn",
 
+  // Even if you don't use internalization, you can use this field to set useful
+  // metadata like html lang. For example, if your site is Chinese, you may want
+  // to replace "en" with "zh-Hans".
+  i18n: {
+    defaultLocale: "en",
+    locales: [
+      "en",
+      "zh-Hans",
+      "es",
+      "fr",
+      "de",
+      "ja",
+      "ko",
+      "pt",
+      "ar",
+      "it",
+      "tr",
+      "pl",
+      "nl",
+      "vi",
+      "th",
+    ], // "fa", "ru", "ro", "sv", "hu", "cs", "el", "da", "fi", "he", "no", "hi", "in", "sl", "se", "sk", "uk", "bg", "hr", "lt", "lv", "et", "cat"
+  },
+
   presets: [
     [
       "@docusaurus/preset-classic",
@@ -40,7 +63,6 @@ const config = {
           // editUrl:
           //   "https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/",
           remarkPlugins: [
-            // eslint-disable-next-line @typescript-eslint/no-require-imports
             [require("@docusaurus/remark-plugin-npm2yarn"), { sync: true }],
           ],
         },

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/api

@@ -0,0 +1 @@
+../../../../docs/api

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/concepts.md

@@ -0,0 +1,86 @@
+---
+sidebar_position: 3
+---
+
+# المفاهيم على المستوى العالي
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+يساعدك LlamaIndex.TS في بناء تطبيقات قائمة على LLM (مثل Q&A و chatbot) على بيانات مخصصة.
+
+في هذا الدليل عن المفاهيم على المستوى العالي، ستتعلم:
+
+- كيف يمكن لـ LLM الإجابة على الأسئلة باستخدام بياناتك الخاصة.
+- المفاهيم الرئيسية والوحدات في LlamaIndex.TS لبناء خط أنابيب الاستعلام الخاص بك.
+
+## الإجابة على الأسئلة عبر بياناتك
+
+يستخدم LlamaIndex طريقة مكونة من مرحلتين عند استخدام LLM مع بياناتك:
+
+1. **مرحلة الفهرسة**: إعداد قاعدة المعرفة، و
+2. **مرحلة الاستعلام**: استرداد السياق ذي الصلة من المعرفة لمساعدة LLM في الاستجابة لسؤال
+
+![](./_static/concepts/rag.jpg)
+
+تُعرف هذه العملية أيضًا باسم "استرجاع معزز للتوليد" (RAG).
+
+يوفر LlamaIndex.TS أدوات أساسية لجعل كلا المرحلتين سهلتين للغاية.
+
+دعنا نستكشف كل مرحلة بالتفصيل.
+
+### مرحلة الفهرسة
+
+يساعدك LlamaIndex.TS في إعداد قاعدة المعرفة باستخدام مجموعة من موصلات البيانات والفهارس.
+
+![](./_static/concepts/indexing.jpg)
+
+[**محمّلات البيانات**](./modules/high_level/data_loader.md):
+موصل البيانات (أي `Reader`) يقوم بتجميع البيانات من مصادر بيانات مختلفة وتنسيقات بيانات مختلفة في تمثيل بسيط للـ `Document` (نص وبيانات تعريفية بسيطة).
+
+[**المستندات / العقد**](./modules/high_level/documents_and_nodes.md): المستند هو حاوية عامة حول أي مصدر بيانات - على سبيل المثال، ملف PDF، نتائج واجهة برمجة التطبيقات، أو بيانات استرداد من قاعدة بيانات. العقد هو الوحدة الذرية للبيانات في LlamaIndex ويمثل "قطعة" من المستند الأصلي. إنه تمثيل غني يتضمن بيانات تعريفية وعلاقات (مع عقد أخرى) لتمكين عمليات الاسترجاع الدقيقة والتعبيرية.
+
+[**فهارس البيانات**](./modules/high_level/data_index.md):
+بمجرد أن تقوم بتجميع بياناتك، يساعدك LlamaIndex في فهرسة البيانات في تنسيق سهل الاسترداد.
+
+تحت الغطاء، يقوم LlamaIndex بتحليل المستندات الخام إلى تمثيلات وسيطة، وحساب تضمينات الناقلات، وتخزين بياناتك في الذاكرة أو على القرص.
+
+"
+
+### مرحلة الاستعلام
+
+في مرحلة الاستعلام، يقوم خط الأنابيب للاستعلام بجلب السياق الأكثر صلة بناءً على استعلام المستخدم،
+ويمرر ذلك إلى LLM (جنبًا إلى جنب مع الاستعلام) لتوليد استجابة.
+
+يمنح ذلك LLM معرفة محدثة ليست موجودة في بيانات التدريب الأصلية لديه،
+(مما يقلل أيضًا من الهلوسة).
+
+التحدي الرئيسي في مرحلة الاستعلام هو الاسترجاع والتنسيق والاستدلال عبر قواعد المعرفة (المحتملة).
+
+يوفر LlamaIndex وحدات قابلة للتركيب تساعدك في بناء ودمج خطوط أنابيب RAG لـ Q&A (محرك الاستعلام)، chatbot (محرك الدردشة)، أو كجزء من وكيل.
+
+يمكن تخصيص هذه الكتل البنائية لتعكس تفضيلات التصنيف، وكذلك تركيبها للاستدلال عبر عدة قواعد معرفة بطريقة منظمة.
+
+![](./_static/concepts/querying.jpg)
+
+#### الكتل الأساسية
+
+[**مسترجعات**](./modules/low_level/retriever.md):
+يحدد المسترجع كيفية استرجاع السياق ذي الصلة بكفاءة من قاعدة المعرفة (أي الفهرس) عند إعطاء استعلام.
+تختلف منطق الاسترجاع المحددة حسب الفهارس المختلفة، والأكثر شيوعًا هو الاسترجاع الكثيف ضد فهرس الناقل.
+
+[**مركبات الاستجابة**](./modules/low_level/response_synthesizer.md):
+تقوم مركبة الاستجابة بتوليد استجابة من LLM باستخدام استعلام المستخدم ومجموعة معينة من أجزاء النص المسترجعة.
+
+"
+
+#### خطوط الأنابيب
+
+[**محركات الاستعلام**](./modules/high_level/query_engine.md):
+محرك الاستعلام هو خط أنابيب شامل يتيح لك طرح الأسئلة على بياناتك.
+يأخذ استعلامًا بلغة طبيعية ويعيد استجابة، جنبًا إلى جنب مع السياق المرجعي المسترجع والممرر إلى LLM.
+
+[**محركات الدردشة**](./modules/high_level/chat_engine.md):
+محرك الدردشة هو خط أنابيب شامل لإجراء محادثة مع بياناتك
+(عدة تفاعلات بدلاً من سؤال وجواب واحد).
+
+"

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/end_to_end.md

@@ -0,0 +1,61 @@
+---
+sidebar_position: 4
+---
+
+# أمثلة من البداية إلى النهاية
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+نقدم العديد من الأمثلة من البداية إلى النهاية باستخدام LlamaIndex.TS في المستودع
+
+تحقق من الأمثلة أدناه أو جربها وأكملها في دقائق مع دروس تفاعلية على Github Codespace المقدمة من Dev-Docs [هنا](https://codespaces.new/team-dev-docs/lits-dev-docs-playground?devcontainer_path=.devcontainer%2Fjavascript_ltsquickstart%2Fdevcontainer.json):
+
+## [محرك الدردشة](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/chatEngine.ts)
+
+اقرأ ملفًا وتحدث عنه مع LLM.
+
+## [فهرس الفيكتور](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/vectorIndex.ts)
+
+إنشاء فهرس فيكتور واستعلامه. سيستخدم فهرس الفيكتور التضمينات لاسترداد أعلى k عقد ذات صلة. بشكل افتراضي ، يكون k الأعلى هو 2.
+
+"
+
+## [مؤشر الملخص](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/summaryIndex.ts)
+
+إنشاء مؤشر قائمة واستعلامه. يستخدم هذا المثال أيضًا `LLMRetriever` ، الذي سيستخدم LLM لتحديد أفضل العقد لاستخدامها عند إنشاء الإجابة.
+
+"
+
+## [حفظ / تحميل فهرس](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/storageContext.ts)
+
+إنشاء وتحميل فهرس ناقل. يحدث التخزين المؤقت على القرص تلقائيًا في LlamaIndex.TS بمجرد إنشاء كائن سياق التخزين.
+
+"
+
+## [فهرس الناقل المخصص](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/vectorIndexCustomize.ts)
+
+إنشاء فهرس ناقل واستعلامه، مع تكوين `LLM` و `ServiceContext` و `similarity_top_k`.
+
+"
+
+## [OpenAI LLM](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/openai.ts)
+
+أنشئ OpenAI LLM واستخدمه مباشرة للدردشة.
+
+"
+
+## [Llama2 DeuceLLM](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/llamadeuce.ts)
+
+إنشاء Llama-2 LLM واستخدامه مباشرة للدردشة.
+
+"
+
+## [محرك استعلام الأسئلة الفرعية](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/subquestion.ts)
+
+يستخدم `محرك استعلام الأسئلة الفرعية` الذي يقسم الاستعلامات المعقدة إلى أسئلة فرعية متعددة، ثم يجمع الاستجابة عبر الإجابات على جميع الأسئلة الفرعية.
+
+"
+
+## [وحدات منخفضة المستوى](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/lowlevel.ts)
+
+يستخدم هذا المثال العديد من المكونات منخفضة المستوى، مما يزيل الحاجة إلى محرك استعلام فعلي. يمكن استخدام هذه المكونات في أي مكان، في أي تطبيق، أو تخصيصها وتصنيفها الفرعي لتلبية احتياجاتك الخاصة.

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/environments.md

@@ -0,0 +1,17 @@
+---
+sidebar_position: 5
+---
+
+# البيئات
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+يدعم LlamaIndex حاليًا رسميًا NodeJS 18 و NodeJS 20.
+
+## NextJS App Router
+
+إذا كنت تستخدم معالج الطرق / الوظائف الخادمة في NextJS App Router ، فستحتاج إلى استخدام وضع NodeJS:
+
+```js
+export const runtime = "nodejs"; // الافتراضي
+```

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/installation.mdx

@@ -0,0 +1,67 @@
+---
+sidebar_position: 1
+---
+
+# التثبيت والإعداد
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+تأكد من أن لديك NodeJS v18 أو أحدث.
+
+## باستخدام create-llama
+
+أسهل طريقة للبدء مع LlamaIndex هي باستخدام `create-llama`. هذه الأداة سطر الأوامر تمكنك من بدء بناء تطبيق LlamaIndex جديد بسرعة، مع كل شيء معد لك.
+
+ما عليك سوى تشغيل
+
+<Tabs>
+<TabItem value="1" label="npm" default>
+
+```bash
+npx create-llama@latest
+```
+
+</TabItem>
+<TabItem value="2" label="Yarn">
+
+```bash
+yarn create llama
+```
+
+</TabItem>
+<TabItem value="3" label="pnpm">
+
+```bash
+pnpm create llama@latest
+```
+
+</TabItem>
+</Tabs>
+
+للبدء. بمجرد إنشاء التطبيق الخاص بك، قم بتشغيل
+
+```bash npm2yarn
+npm run dev
+```
+
+لبدء خادم التطوير. يمكنك ثم زيارة [http://localhost:3000](http://localhost:3000) لرؤية تطبيقك.
+
+## التثبيت من NPM
+
+```bash npm2yarn
+npm install llamaindex
+```
+
+### المتغيرات البيئية
+
+تستخدم أمثلتنا OpenAI افتراضيًا. ستحتاج إلى إعداد مفتاح Open AI الخاص بك على النحو التالي:
+
+```bash
+export OPENAI_API_KEY="sk-......" # استبدله بالمفتاح الخاص بك من https://platform.openai.com/account/api-keys
+```
+
+إذا كنت ترغب في تحميله تلقائيًا في كل مرة، قم بإضافته إلى ملف .zshrc/.bashrc الخاص بك.
+
+تحذير: لا تقم بإضافة مفتاح OpenAI الخاص بك إلى نظام التحكم في الإصدارات.
+
+"

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/introduction.md

@@ -0,0 +1,60 @@
+---
+sidebar_position: 0
+slug: /
+---
+
+# ما هو LlamaIndex.TS؟
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+LlamaIndex.TS هو إطار بيانات لتطبيقات LLM لاستيعاب وتنظيم والوصول إلى البيانات الخاصة أو الخاصة بالمجال. في حين أن حزمة Python متاحة أيضًا (انظر [هنا](https://docs.llamaindex.ai/en/stable/)), يوفر LlamaIndex.TS ميزات أساسية في حزمة بسيطة ، محسنة للاستخدام مع TypeScript.
+
+## 🚀 لماذا LlamaIndex.TS؟
+
+في جوهرها ، توفر LLMs واجهة لغة طبيعية بين البشر والبيانات المستنتجة. تأتي النماذج المتاحة على نطاق واسع محملة مسبقًا بكميات هائلة من البيانات المتاحة للجمهور ، من ويكيبيديا وقوائم البريد الإلكتروني إلى الكتب المدرسية وشفرة المصدر.
+
+غالبًا ما تتطلب التطبيقات المبنية على LLMs تعزيز هذه النماذج بالبيانات الخاصة أو الخاصة بالمجال. للأسف ، يمكن توزيع هذه البيانات عبر تطبيقات ومخازن بيانات معزولة. إنها خلف واجهات برمجة التطبيقات ، في قواعد البيانات SQL ، أو محبوسة في ملفات PDF وعروض تقديمية.
+
+هنا يأتي دور **LlamaIndex.TS**.
+
+## 🦙 كيف يمكن أن يساعد LlamaIndex.TS؟
+
+يوفر LlamaIndex.TS الأدوات التالية:
+
+- **تحميل البيانات**: استيعاب البيانات الحالية الخاصة بك بتنسيقات `.txt`, `.pdf`, `.csv`, `.md` و `.docx` مباشرة.
+- **فهارس البيانات**: تنظيم البيانات الخاصة بك في تمثيلات وسيطة سهلة وفعالة للاستخدام من قبل LLMs.
+- **المحركات**: توفر واجهات الوصول إلى اللغة الطبيعية لبياناتك. على سبيل المثال:
+  - محركات الاستعلام هي واجهات استرجاع قوية للإخراج المعزز بالمعرفة.
+  - محركات الدردشة هي واجهات محادثة للتفاعلات "ذهابًا وإيابًا" متعددة الرسائل مع بياناتك.
+
+## 👨‍👩‍👧‍👦 من أجل من هو LlamaIndex؟
+
+يوفر LlamaIndex.TS مجموعة أدوات أساسية ، ضرورية لأي شخص يقوم ببناء تطبيقات LLM باستخدام JavaScript و TypeScript.
+
+يتيح لنا واجهة برمجة التطبيقات على مستوى عالي استخدام LlamaIndex.TS لاستيعاب واستعلام البيانات الخاصة بهم.
+
+بالنسبة للتطبيقات المعقدة أكثر ، تتيح لنا واجهات برمجة التطبيقات على مستوى أدنى للمستخدمين المتقدمين تخصيص وتوسيع أي وحدة - موصلات البيانات والفهارس وأجهزة الاسترجاع ومحركات الاستعلام - لتناسب احتياجاتهم.
+
+## البدء
+
+`npm install llamaindex`
+
+تتضمن وثائقنا [تعليمات التثبيت](./installation.mdx) و[دليل البداية](./starter.md) لبناء تطبيقك الأول.
+
+بمجرد أن تكون جاهزًا وتعمل ، يحتوي [مفاهيم عالية المستوى](./getting_started/concepts.md) على نظرة عامة على الهندسة المعمارية المتعددة المستويات لـ LlamaIndex. لمزيد من الأمثلة العملية التفصيلية ، يمكنك الاطلاع على [دروس النهاية إلى النهاية](./end_to_end.md).
+
+## 🗺️ النظام البيئي
+
+لتنزيل أو المساهمة ، ابحث عن LlamaIndex على:
+
+- Github: https://github.com/run-llama/LlamaIndexTS
+- NPM: https://www.npmjs.com/package/llamaindex
+
+"
+
+## المجتمع
+
+هل تحتاج إلى مساعدة؟ هل لديك اقتراح لميزة؟ انضم إلى مجتمع LlamaIndex:
+
+- تويتر: https://twitter.com/llama_index
+- ديسكورد: https://discord.gg/dGcwcsnxhU

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/high_level/chat_engine.md

@@ -0,0 +1,22 @@
+---
+sidebar_position: 4
+---
+
+# محرك الدردشة (ChatEngine)
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+محرك الدردشة هو طريقة سريعة وبسيطة للدردشة مع البيانات في الفهرس الخاص بك.
+
+```typescript
+const retriever = index.asRetriever();
+const chatEngine = new ContextChatEngine({ retriever });
+
+// بدء الدردشة
+const response = await chatEngine.chat(query);
+```
+
+## مراجع الواجهة البرمجية
+
+- [محرك الدردشة السياقي (ContextChatEngine)](../../api/classes/ContextChatEngine.md)
+- [محرك الدردشة المكثف للأسئلة (CondenseQuestionChatEngine)](../../api/classes/ContextChatEngine.md)

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/high_level/data_index.md

@@ -0,0 +1,27 @@
+---
+sidebar_position: 2
+---
+
+# الفهرس
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+الفهرس هو الحاوية الأساسية والتنظيم لبياناتك. يدعم LlamaIndex.TS نوعين من الفهارس:
+
+- `VectorStoreIndex` - سيقوم بإرسال أعلى `Node` الموجودة إلى LLM عند إنشاء استجابة. القيمة الافتراضية لأعلى `k` هي 2.
+- `SummaryIndex` - سيقوم بإرسال كل `Node` في الفهرس إلى LLM لإنشاء استجابة.
+
+```typescript
+import { Document, VectorStoreIndex } from "llamaindex";
+
+const document = new Document({ text: "اختبار" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## مرجع الواجهة البرمجية
+
+- [SummaryIndex](../../api/classes/SummaryIndex.md)
+- [VectorStoreIndex](../../api/classes/VectorStoreIndex.md)
+
+"

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/high_level/data_loader.md

@@ -0,0 +1,19 @@
+---
+sidebar_position: 1
+---
+
+# قارئ / محمل
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+يدعم LlamaIndex.TS تحميل الملفات بسهولة من المجلدات باستخدام فئة `SimpleDirectoryReader`. حاليًا ، يتم دعم الملفات `.txt` ، `.pdf` ، `.csv` ، `.md` و `.docx` ، مع المزيد المخطط له في المستقبل!
+
+```typescript
+import { SimpleDirectoryReader } from "llamaindex";
+
+documents = new SimpleDirectoryReader().loadData("./data");
+```
+
+## مرجع الواجهة البرمجية
+
+- [SimpleDirectoryReader](../../api/classes/SimpleDirectoryReader.md)

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/high_level/documents_and_nodes.md

@@ -0,0 +1,22 @@
+---
+sidebar_position: 0
+---
+
+# المستندات والعقد
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+`المستندات` و `العقد` هما العناصر الأساسية لأي فهرس. بينما يكون واجهة برمجة التطبيق (API) لهذه الكائنات مشابهة، يُمثل كائن `المستند` ملفات كاملة، بينما تكون `العقد` قطعًا أصغر من ذلك المستند الأصلي، والتي تكون مناسبة لـ LLM و Q&A.
+
+```typescript
+import { Document } from "llamaindex";
+
+document = new Document({ text: "نص", metadata: { key: "val" } });
+```
+
+## مرجع الواجهة البرمجية
+
+- [المستند (Document)](../../api/classes/Document.md)
+- [نص العقد (TextNode)](../../api/classes/TextNode.md)
+
+"

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/high_level/query_engine.md

@@ -0,0 +1,42 @@
+---
+sidebar_position: 3
+---
+
+# محرك الاستعلامات (QueryEngine)
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+يقوم محرك الاستعلامات بتجميع "Retriever" و "ResponseSynthesizer" في أنبوبة، والتي ستستخدم سلسلة الاستعلام لاسترداد العقد ومن ثم إرسالها إلى LLM لتوليد استجابة.
+
+```typescript
+const queryEngine = index.asQueryEngine();
+const response = await queryEngine.query("سلسلة الاستعلام");
+```
+
+## محرك الاستعلام للأسئلة الفرعية
+
+الفكرة الأساسية لمحرك الاستعلام للأسئلة الفرعية هي تقسيم استعلام واحد إلى استعلامات متعددة، والحصول على إجابة لكل من تلك الاستعلامات، ثم دمج تلك الإجابات المختلفة في استجابة واحدة متسقة للمستخدم. يمكنك أن تفكر فيها كتقنية "فكر في ذلك خطوة بخطوة" ولكن بتكرار مصادر البيانات الخاصة بك!
+
+### البدء
+
+أسهل طريقة لبدء تجربة محرك الاستعلام للأسئلة الفرعية هي تشغيل ملف subquestion.ts في [examples](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/subquestion.ts).
+
+```bash
+npx ts-node subquestion.ts
+```
+
+"
+
+### الأدوات
+
+يتم تنفيذ محرك الاستعلام للأسئلة الفرعية باستخدام الأدوات. الفكرة الأساسية للأدوات هي أنها خيارات قابلة للتنفيذ لنموذج اللغة الكبيرة. في هذه الحالة، يعتمد محرك الاستعلام للأسئلة الفرعية على أداة QueryEngineTool، والتي كما تخمن هي أداة لتشغيل استعلامات على محرك الاستعلام. يتيح لنا ذلك إعطاء النموذج خيارًا للاستعلام عن وثائق مختلفة لأسئلة مختلفة على سبيل المثال. يمكنك أيضًا أن تتخيل أن محرك الاستعلام للأسئلة الفرعية يمكنه استخدام أداة تبحث عن شيء ما على الويب أو تحصل على إجابة باستخدام Wolfram Alpha.
+
+يمكنك معرفة المزيد عن الأدوات من خلال الاطلاع على وثائق LlamaIndex Python https://gpt-index.readthedocs.io/en/latest/core_modules/agent_modules/tools/root.html
+
+"
+
+## مرجع واجهة برمجة التطبيق (API)
+
+- [محرك استعلام الاسترجاع (RetrieverQueryEngine)](../../api/classes/RetrieverQueryEngine.md)
+- [محرك استعلام السؤال الفرعي (SubQuestionQueryEngine)](../../api/classes/SubQuestionQueryEngine.md)
+- [أداة محرك الاستعلام (QueryEngineTool)](../../api/interfaces/QueryEngineTool.md)

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/index.md

@@ -0,0 +1,33 @@
+# الوحدات الأساسية
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+يوفر LlamaIndex.TS عدة وحدات أساسية، مقسمة إلى وحدات عالية المستوى للبدء السريع ووحدات منخفضة المستوى لتخصيص المكونات الرئيسية حسب الحاجة.
+
+## وحدات عالية المستوى
+
+- [**المستند**](./high_level/documents_and_nodes.md): يمثل المستند ملف نصي أو ملف PDF أو قطعة بيانات متتابعة أخرى.
+
+- [**العقدة**](./high_level/documents_and_nodes.md): هو البناء الأساسي للبيانات. في أغلب الأحيان، تكون هذه أجزاء من المستند المقسمة إلى قطع قابلة للإدارة وصغيرة بما يكفي ليتم تغذيتها إلى نموذج التضمين و LLM.
+
+- [**القارئ/المحمل**](./high_level/data_loader.md): القارئ أو المحمل هو شيء يأخذ المستند في العالم الحقيقي ويحوله إلى فئة المستند التي يمكن استخدامها في الفهرس الخاص بك والاستعلامات. ندعم حاليًا ملفات النص العادي وملفات PDF والمزيد الكثير.
+
+- [**الفهارس**](./high_level/data_index.md): تخزن الفهارس العقد وتضمينات تلك العقد.
+
+- [**محرك الاستعلامات**](./high_level/query_engine.md): محركات الاستعلامات هي التي تولد الاستعلام الذي تدخله وتعيد لك النتيجة. عمومًا، تجمع محركات الاستعلامات بين تعليمة مسبقة مبنية مع العقد المحددة من الفهرس الخاص بك لتعطي LLM السياق الذي يحتاجه للإجابة على استعلامك.
+
+- [**محرك الدردشة**](./high_level/chat_engine.md): يساعدك محرك الدردشة على بناء روبوت دردشة سيتفاعل مع فهرسك.
+
+## وحدة منخفضة المستوى
+
+- [**LLM**](./low_level/llm.md): فئة LLM هي واجهة موحدة فوق مزود نموذج لغة كبير مثل OpenAI GPT-4 أو Anthropic Claude أو Meta LLaMA. يمكنك توريثها لكتابة موصل إلى نموذج اللغة الخاص بك.
+
+- [**Embedding**](./low_level/embedding.md): يتم تمثيل التضمين كمتجه من الأرقام العائمة. نموذج التضمين الافتراضي لدينا هو text-embedding-ada-002 من OpenAI ويتكون كل تضمين يولده من 1,536 رقمًا عائمًا. نموذج التضمين الشائع الآخر هو BERT الذي يستخدم 768 رقمًا عائمًا لتمثيل كل عقدة. نوفر عددًا من الأدوات للعمل مع التضمين بما في ذلك 3 خيارات لحساب التشابه و Maximum Marginal Relevance.
+
+- [**TextSplitter/NodeParser**](./low_level/node_parser.md): تعتبر استراتيجيات تقسيم النصوص مهمة للغاية لفعالية البحث في التضمين. حاليًا، على الرغم من أن لدينا قيمة افتراضية، إلا أنه لا يوجد حلاً مناسبًا للجميع. اعتمادًا على وثائق المصدر، قد ترغب في استخدام أحجام واستراتيجيات تقسيم مختلفة. حاليًا، ندعم التقسيم حسب الحجم الثابت، التقسيم حسب الحجم الثابت مع أجزاء تتداخل، التقسيم حسب الجملة، والتقسيم حسب الفقرة. يتم استخدام مقسم النصوص بواسطة NodeParser عند تقسيم `Document` إلى `Node`.
+
+- [**Retriever**](./low_level/retriever.md): يقوم Retriever بتحديد العقد التي يتم استردادها من الفهرس. هنا، قد ترغب في محاولة استرداد عدد أكبر أو أقل من العقد لكل استعلام، تغيير وظيفة التشابه الخاصة بك، أو إنشاء استرداد خاص بك لكل حالة استخدام فردية في تطبيقك. على سبيل المثال، قد ترغب في وجود استرداد منفصل لمحتوى الشفرة مقابل محتوى النص.
+
+- [**ResponseSynthesizer**](./low_level/response_synthesizer.md): يتحمل ResponseSynthesizer مسؤولية أخذ سلسلة استعلام واستخدام قائمة من العقد لإنشاء استجابة. يمكن أن يأخذ هذا الشكل العديد من الأشكال، مثل التكرار عبر جميع السياق وتحسين الإجابة، أو بناء شجرة من الملخصات وإرجاع الملخص الجذري.
+
+- [**Storage**](./low_level/storage.md): في نقطة ما، سترغب في تخزين الفهارس والبيانات والمتجهات بدلاً من إعادة تشغيل نماذج التضمين في كل مرة. IndexStore و DocStore و VectorStore و KVStore هي تجريدات تتيح لك ذلك. مجتمعة، تشكل هذه التجريدات سياق التخزين. حاليًا، نسمح لك بالاحتفاظ بالتضمينات الخاصة بك في ملفات على نظام الملفات (أو نظام ملفات افتراضي في الذاكرة)، ولكننا نضيف أيضًا تكاملات مع قواعد بيانات المتجهات.

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/low_level/embedding.md

@@ -0,0 +1,26 @@
+---
+sidebar_position: 1
+---
+
+# تضمين
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+يتولى النموذج المضمن في LlamaIndex إنشاء تمثيلات رقمية للنص. بشكل افتراضي ، ستستخدم LlamaIndex نموذج `text-embedding-ada-002` من OpenAI.
+
+يمكن تعيين ذلك بشكل صريح في كائن `ServiceContext`.
+
+```typescript
+import { OpenAIEmbedding, serviceContextFromDefaults } from "llamaindex";
+
+const openaiEmbeds = new OpenAIEmbedding();
+
+const serviceContext = serviceContextFromDefaults({ embedModel: openaiEmbeds });
+```
+
+## مرجع الواجهة البرمجية
+
+- [OpenAIEmbedding](../../api/classes/OpenAIEmbedding.md)
+- [ServiceContext](../../api/interfaces/ServiceContext.md)
+
+"

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/low_level/llm.md

@@ -0,0 +1,26 @@
+---
+sidebar_position: 0
+---
+
+# LLM
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+يتولى LLM قراءة النص وتوليد استجابات لغوية طبيعية للاستفسارات. بشكل افتراضي ، يستخدم LlamaIndex.TS `gpt-3.5-turbo`.
+
+يمكن تعيين LLM بشكل صريح في كائن `ServiceContext`.
+
+```typescript
+import { OpenAI, serviceContextFromDefaults } from "llamaindex";
+
+const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
+
+const serviceContext = serviceContextFromDefaults({ llm: openaiLLM });
+```
+
+## مرجع الواجهة البرمجية
+
+- [OpenAI](../../api/classes/OpenAI.md)
+- [ServiceContext](../../api/interfaces/ServiceContext.md)
+
+"

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/low_level/node_parser.md

@@ -0,0 +1,37 @@
+---
+sidebar_position: 3
+---
+
+# NodeParser (محلل العقدة)
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+`NodeParser` في LlamaIndex مسؤول عن تقسيم كائنات `Document` إلى كائنات `Node` أكثر إدارة. عند استدعاء `.fromDocuments()`, يتم استخدام `NodeParser` من `ServiceContext` للقيام بذلك تلقائيًا بالنسبة لك. بدلاً من ذلك ، يمكنك استخدامه لتقسيم المستندات مسبقًا.
+
+```typescript
+import { Document, SimpleNodeParser } from "llamaindex";
+
+const nodeParser = new SimpleNodeParser();
+const nodes = nodeParser.getNodesFromDocuments([
+  new Document({ text: "أنا عمري 10 سنوات. جون عمره 20 سنة." }),
+]);
+```
+
+## TextSplitter (مقسم النص)
+
+سيقوم مقسم النص الأساسي بتقسيم النص إلى جمل. يمكن أيضًا استخدامه كوحدة مستقلة لتقسيم النص الخام.
+
+```typescript
+import { SentenceSplitter } from "llamaindex";
+
+const splitter = new SentenceSplitter({ chunkSize: 1 });
+
+const textSplits = splitter.splitText("مرحبًا بالعالم");
+```
+
+## مرجع الواجهة البرمجية
+
+- [SimpleNodeParser (محلل العقدة البسيط)](../../api/classes/SimpleNodeParser.md)
+- [SentenceSplitter (مقسم الجمل)](../../api/classes/SentenceSplitter.md)
+
+"

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/low_level/response_synthesizer.md

@@ -0,0 +1,45 @@
+---
+sidebar_position: 6
+---
+
+# مركب الاستجابة (ResponseSynthesizer)
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+مركب الاستجابة (ResponseSynthesizer) مسؤول عن إرسال الاستعلام والعقد وقوالب الاستفسار إلى LLM لتوليد استجابة. هناك بعض وسائط رئيسية لتوليد استجابة:
+
+- `تحسين`: "إنشاء وتحسين" إجابة عن طريق المرور تتاليًا عبر كل قطعة نص مُسترجعة. يتم إجراء استدعاء LLM منفصل لكل عقدة. جيد للإجابات المفصلة.
+- `مضغوط وتحسين` (الافتراضي): "ضغط" الاستفسار أثناء كل استدعاء LLM عن طريق حشو أكبر عدد ممكن من قطع النص التي يمكن أن تتناسب مع حجم الاستفسار الأقصى. إذا كان هناك الكثير من القطع لتعبئتها في استفسار واحد، "إنشاء وتحسين" إجابة عن طريق المرور بعدة استفسارات مضغوطة. نفس العملية كـ `تحسين`، ولكن يجب أن تؤدي إلى مزيد من استدعاءات LLM أقل.
+- `ملخص الشجرة`: بناء شجرة بشكل متكرر بناءً على مجموعة من قطع النص والاستعلام، وإرجاع العقدة الجذرية كاستجابة. جيد لأغراض التلخيص.
+- `منشئ الاستجابة البسيط`: تطبيق الاستعلام على كل قطعة نص وتجميع الاستجابات في مصفوفة. يعيد سلسلة متصلة من جميع الاستجابات. جيد عندما تحتاج إلى تشغيل نفس الاستعلام بشكل منفصل على كل قطعة نص.
+
+```typescript
+import { NodeWithScore, ResponseSynthesizer, TextNode } from "llamaindex";
+
+const responseSynthesizer = new ResponseSynthesizer();
+
+const nodesWithScore: NodeWithScore[] = [
+  {
+    node: new TextNode({ text: "أنا عمري 10 سنوات." }),
+    score: 1,
+  },
+  {
+    node: new TextNode({ text: "جون عمره 20 سنة." }),
+    score: 0.5,
+  },
+];
+
+const response = await responseSynthesizer.synthesize(
+  "ما هو عمري؟",
+  nodesWithScore,
+);
+console.log(response.response);
+```
+
+## مرجع الواجهة البرمجية
+
+- [مركب الاستجابة (ResponseSynthesizer)](../../api/classes/ResponseSynthesizer.md)
+- [تحسين (Refine)](../../api/classes/Refine.md)
+- [مضغوط وتحسين (CompactAndRefine)](../../api/classes/CompactAndRefine.md)
+- [ملخص الشجرة (TreeSummarize)](../../api/classes/TreeSummarize.md)
+- [منشئ الاستجابة البسيط (SimpleResponseBuilder)](../../api/classes/SimpleResponseBuilder.md)

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/low_level/retriever.md

@@ -0,0 +1,23 @@
+---
+sidebar_position: 5
+---
+
+# الباحث (Retriever)
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+الباحث في LlamaIndex هو ما يُستخدم لاسترداد العقد (`Node`) من فهرس باستخدام سلسلة الاستعلام. سيقوم الباحث `VectorIndexRetriever` بجلب أعلى k عقد مشابهة. بينما سيقوم الباحث `SummaryIndexRetriever` بجلب جميع العقد بغض النظر عن الاستعلام.
+
+```typescript
+const retriever = vector_index.asRetriever();
+retriever.similarityTopK = 3;
+
+// جلب العقد!
+const nodesWithScore = await retriever.retrieve({ query: "سلسلة الاستعلام" });
+```
+
+## مرجع الواجهة البرمجية (API Reference)
+
+- [SummaryIndexRetriever](../../api/classes/SummaryIndexRetriever.md)
+- [SummaryIndexLLMRetriever](../../api/classes/SummaryIndexLLMRetriever.md)
+- [VectorIndexRetriever](../../api/classes/VectorIndexRetriever.md)

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/modules/low_level/storage.md

@@ -0,0 +1,30 @@
+---
+sidebar_position: 7
+---
+
+# التخزين
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+يعمل التخزين في LlamaIndex.TS تلقائيًا بمجرد تكوين كائن `StorageContext`. قم بتكوين `persistDir` وربطه بفهرس.
+
+في الوقت الحالي ، يتم دعم حفظ وتحميل البيانات من القرص فقط ، مع وجود تكاملات مستقبلية مخططة!
+
+```typescript
+import { Document, VectorStoreIndex, storageContextFromDefaults } from "./src";
+
+const storageContext = await storageContextFromDefaults({
+  persistDir: "./storage",
+});
+
+const document = new Document({ text: "نص اختبار" });
+const index = await VectorStoreIndex.fromDocuments([document], {
+  storageContext,
+});
+```
+
+## مرجع الواجهة البرمجية
+
+- [StorageContext](../../api/interfaces/StorageContext.md)
+
+"

apps/docs/i18n/ar/docusaurus-plugin-content-docs/current/starter.md

@@ -0,0 +1,58 @@
+---
+sidebar_position: 2
+---
+
+# دليل البداية
+
+`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
+
+بمجرد [تثبيت LlamaIndex.TS باستخدام NPM](installation) وإعداد مفتاح OpenAI الخاص بك، أنت الآن جاهز لبدء تطبيقك الأول:
+
+في مجلد جديد:
+
+```bash npm2yarn
+npm install typescript
+npm install @types/node
+npx tsc --init # إذا لزم الأمر
+```
+
+أنشئ ملف `example.ts`. سيقوم هذا الكود بتحميل بعض البيانات المثالية، وإنشاء وثيقة، وفهرسة الوثيقة (مما ينشئ تضمينات باستخدام OpenAI)، ثم إنشاء محرك الاستعلام للإجابة على الأسئلة حول البيانات.
+
+```ts
+// example.ts
+import fs from "fs/promises";
+import { Document, VectorStoreIndex } from "llamaindex";
+
+async function main() {
+  // تحميل المقالة من abramov.txt في Node
+  const essay = await fs.readFile(
+    "node_modules/llamaindex/examples/abramov.txt",
+    "utf-8",
+  );
+
+  // إنشاء كائن Document بواسطة المقالة
+  const document = new Document({ text: essay });
+
+  // تقسيم النص وإنشاء التضمينات. تخزينها في VectorStoreIndex
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // استعلام الفهرس
+  const queryEngine = index.asQueryEngine();
+  const response = await queryEngine.query("ماذا فعل الكاتب في الكلية؟");
+
+  // إخراج الاستجابة
+  console.log(response.toString());
+}
+
+main();
+```
+
+ثم يمكنك تشغيله باستخدام
+
+```bash
+npx ts-node example.ts
+```
+
+هل أنت مستعد للمزيد من التعلم؟ تفضل بزيارة منصة NextJS الخاصة بنا على https://llama-playground.vercel.app/. يمكنك العثور على المصدر على https://github.com/run-llama/ts-playground
+
+"