Release 0.4.1 (#949)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

.changeset/config.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://unpkg.com/@changesets/config@2.3.1/schema.json",
   "changelog": "@changesets/cli/changelog",
-  "commit": true,
+  "commit": false,
   "fixed": [],
   "linked": [],
   "access": "public",

.cjs.swcrc

@@ -0,0 +1,16 @@
+{
+  "jsc": {
+    "parser": {
+      "syntax": "typescript",
+      "decorators": true
+    },
+    "target": "esnext",
+    "transform": {
+      "decoratorVersion": "2022-03"
+    }
+  },
+  "module": {
+    "type": "commonjs",
+    "ignoreDynamic": true
+  }
+}

.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/"],
+};

.eslintrc.js

@@ -1,15 +0,0 @@
-module.exports = {
-  root: true,
-  // This tells ESLint to load the config from the package `eslint-config-custom`
-  extends: ["custom"],
-  settings: {
-    next: {
-      rootDir: ["apps/*/"],
-    },
-  },
-  rules: {
-    "max-params": ["error", 4],
-    "prefer-const": "error",
-  },
-  ignorePatterns: ["dist/"],
-};

.github/workflows/e2e.yml

@@ -1,68 +0,0 @@
-name: E2E Tests
-on:
-  push:
-    branches: [main]
-  pull_request:
-    paths:
-      - "packages/create-llama/**"
-      - ".github/workflows/e2e.yml"
-    branches: [main]
-
-env:
-  POETRY_VERSION: "1.6.1"
-
-jobs:
-  e2e:
-    name: create-llama
-    timeout-minutes: 60
-    strategy:
-      fail-fast: true
-      matrix:
-        node-version: [18, 20]
-        python-version: ["3.11"]
-        os: [macos-latest, windows-latest]
-    defaults:
-      run:
-        shell: bash
-    runs-on: ${{ matrix.os }}
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
-        with:
-          version: ${{ env.POETRY_VERSION }}
-      - uses: pnpm/action-setup@v2
-      - name: Setup Node.js ${{ matrix.node-version }}
-        uses: actions/setup-node@v4
-        with:
-          node-version: ${{ matrix.node-version }}
-          cache: "pnpm"
-      - name: Install dependencies
-        run: pnpm install
-      - name: Install Playwright Browsers
-        run: pnpm exec playwright install --with-deps
-        working-directory: ./packages/create-llama
-      - name: Build create-llama
-        run: pnpm run build
-        working-directory: ./packages/create-llama
-      - name: Pack
-        run: pnpm pack --pack-destination ./output
-        working-directory: ./packages/create-llama
-      - name: Extract Pack
-        run: tar -xvzf ./output/*.tgz -C ./output
-        working-directory: ./packages/create-llama
-      - name: Run Playwright tests
-        run: pnpm exec playwright test
-        env:
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-        working-directory: ./packages/create-llama
-      - uses: actions/upload-artifact@v3
-        if: always()
-        with:
-          name: playwright-report
-          path: ./packages/create-llama/playwright-report/
-          retention-days: 30

.github/workflows/lint_on_push_or_pull.yml

@@ -13,9 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
-        with:
-          version: latest
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:

.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

@@ -0,0 +1,37 @@
+name: Publish to GitHub Releases
+
+on:
+  push:
+    tags:
+      - "llamaindex@*"
+
+jobs:
+  build-and-publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repo
+        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: Build tarball
+        run: |
+          pnpm pack
+        working-directory: packages/llamaindex
+
+      - name: Create release
+        uses: ncipollo/release-action@v1
+        with:
+          artifacts: "packages/llamaindex/llamaindex-*.tgz"
+          name: Release ${{ github.ref }}
+          bodyFile: "packages/llamaindex/CHANGELOG.md"
+          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/release.yml

@@ -0,0 +1,57 @@
+name: Release
+
+on:
+  push:
+    branches:
+      - main
+
+concurrency: ${{ github.workflow }}-${{ github.ref }}
+
+jobs:
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repo
+        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: Add auth token to .npmrc file
+        run: |
+          cat << EOF >> ".npmrc"
+            //registry.npmjs.org/:_authToken=$NPM_TOKEN
+          EOF
+        env:
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
+
+      - name: Get changeset status
+        id: get-changeset-status
+        run: |
+          pnpm changeset status --output .changeset/status.json
+          new_version=$(jq -r '.releases[] | select(.name == "llamaindex") | .newVersion' < .changeset/status.json)
+          rm -v .changeset/status.json
+          echo "new-version=${new_version}" >> "$GITHUB_OUTPUT"
+
+      - name: Create Release Pull Request or Publish to npm
+        id: changesets
+        uses: changesets/action@v1
+        with:
+          commit: Release ${{ steps.get-changeset-status.outputs.new-version }}
+          title: Release ${{ steps.get-changeset-status.outputs.new-version }}
+          # update version PR with the latest changesets
+          version: pnpm new-version
+          # build package and call changeset publish
+          publish: pnpm release
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}

.github/workflows/test.yml

@@ -1,18 +1,55 @@
 name: Run Tests
 
-on: [push, pull_request]
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
 
 jobs:
+  e2e:
+    strategy:
+      fail-fast: false
+      matrix:
+        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: pnpm/action-setup@v3
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+          cache: "pnpm"
+      - name: Install dependencies
+        run: pnpm install
+      - name: Run E2E Tests
+        run: pnpm run e2e
+
   test:
+    strategy:
+      fail-fast: false
+      matrix:
+        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@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version-file: ".nvmrc"
+          node-version: ${{ matrix.node-version }}
           cache: "pnpm"
       - name: Install dependencies
         run: pnpm install
@@ -23,7 +60,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -32,24 +69,53 @@ jobs:
       - name: Install dependencies
         run: pnpm install
       - name: Build
-        run: pnpm run build --filter llamaindex
+        run: pnpm run build
+      - name: Use Build For Examples
+        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
-        working-directory: ./packages/core
+        run: pnpm dlx turbo run circular-check
       - uses: actions/upload-artifact@v3
         if: failure()
         with:
           name: typecheck-build-dist
-          path: ./packages/core/dist
+          path: ./packages/llamaindex/dist
           if-no-files-found: error
+  e2e-llamaindex-examples:
+    strategy:
+      fail-fast: false
+      matrix:
+        packages:
+          - cloudflare-worker-agent
+          - nextjs-agent
+          - nextjs-edge-runtime
+    #          - waku-query-engine
+    runs-on: ubuntu-latest
+    name: Build LlamaIndex Example (${{ matrix.packages }})
+    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: Build llamaindex
+        run: pnpm run build
+      - name: Build ${{ matrix.packages }}
+        run: pnpm run build
+        working-directory: packages/llamaindex/e2e/examples/${{ matrix.packages }}
+
   typecheck-examples:
     runs-on: ubuntu-latest
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -58,7 +124,7 @@ jobs:
       - name: Install dependencies
         run: pnpm install
       - name: Build
-        run: pnpm run build --filter llamaindex
+        run: pnpm run build
       - name: Copy examples
         run: rsync -rv --exclude=node_modules ./examples ${{ runner.temp }}
       - name: Pack @llamaindex/env
@@ -66,7 +132,7 @@ jobs:
         working-directory: packages/env
       - name: Pack llamaindex
         run: pnpm pack --pack-destination ${{ runner.temp }}
-        working-directory: packages/core
+        working-directory: packages/llamaindex
       - name: Install
         run: npm add ${{ runner.temp }}/*.tgz
         working-directory: ${{ runner.temp }}/examples

.gitignore

@@ -44,6 +44,7 @@ test-results/
 playwright-report/
 blob-report/
 playwright/.cache/
+.tsbuildinfo
 
 # intellij
 **/.idea

.husky/pre-push

@@ -1 +0,0 @@
-pnpm test

.npmrc

@@ -1,2 +1,5 @@
 auto-install-peers = true
 enable-pre-post-scripts = true
+prefer-workspace-packages = true
+save-workspace-protocol = true
+link-workspace-packages = true

.nvmrc

@@ -1 +1 @@
-18
+20

.swcrc

@@ -0,0 +1,12 @@
+{
+  "jsc": {
+    "parser": {
+      "syntax": "typescript",
+      "decorators": true
+    },
+    "target": "esnext",
+    "transform": {
+      "decoratorVersion": "2022-03"
+    }
+  }
+}

.vscode/launch.json

@@ -10,8 +10,9 @@
       "name": "Debug Example",
       "skipFiles": ["<node_internals>/**"],
       "runtimeExecutable": "pnpm",
+      "console": "integratedTerminal",
       "cwd": "${workspaceFolder}/examples",
-      "runtimeArgs": ["ts-node", "${fileBasename}"]
+      "runtimeArgs": ["npx", "tsx", "${file}"]
     }
   ]
 }

CONTRIBUTING.md

@@ -41,7 +41,7 @@ To run them, run
 pnpm run test
 ```
 
-To write new test cases write them in [packages/core/src/tests](/packages/core/src/tests)
+To write new test cases write them in [packages/core/src/tests](/packages/llamaindex/src/tests)
 
 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
 
@@ -79,14 +79,22 @@ That should start a webserver which will serve the docs on https://localhost:300
 
 Any changes you make should be reflected in the browser. If you need to regenerate the API docs and find that your TSDoc isn't getting the updates, feel free to remove apps/docs/api. It will automatically regenerate itself when you run pnpm start again.
 
-## Publishing
+## Changeset
 
-To publish a new version of the library, run
+We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new changeset, run:
 
-```shell
-pnpm new-llamaindex
-pnpm new-create-llama
-pnpm release
-git push # push to the main branch
-git push --tags
 ```
+pnpm changeset
+```
+
+Please send a descriptive changeset for each PR.
+
+## Publishing (maintainers only)
+
+The [Release Github Action](.github/workflows/release.yml) is automatically generating and updating a
+PR called "Release {version}".
+
+This PR will update the `package.json` and `CHANGELOG.md` files of each package according to
+the current changesets in the [.changeset](.changeset/) folder.
+
+If this PR is merged it will automatically add version tags to the repository and publish the updated packages to NPM.

README-turborepo.md

@@ -1,81 +0,0 @@
-# Turborepo starter
-
-This is an official starter Turborepo.
-
-## Using this example
-
-Run the following command:
-
-```sh
-npx create-turbo@latest
-```
-
-## What's inside?
-
-This Turborepo includes the following packages/apps:
-
-### Apps and Packages
-
-- `docs`: a [Next.js](https://nextjs.org/) app
-- `web`: another [Next.js](https://nextjs.org/) app
-- `ui`: a stub React component library shared by both `web` and `docs` applications
-- `eslint-config-custom`: `eslint` configurations (includes `eslint-config-next` and `eslint-config-prettier`)
-- `tsconfig`: `tsconfig.json`s used throughout the monorepo
-
-Each package/app is 100% [TypeScript](https://www.typescriptlang.org/).
-
-### Utilities
-
-This Turborepo has some additional tools already setup for you:
-
-- [TypeScript](https://www.typescriptlang.org/) for static type checking
-- [ESLint](https://eslint.org/) for code linting
-- [Prettier](https://prettier.io) for code formatting
-
-### Build
-
-To build all apps and packages, run the following command:
-
-```
-cd my-turborepo
-pnpm build
-```
-
-### Develop
-
-To develop all apps and packages, run the following command:
-
-```
-cd my-turborepo
-pnpm dev
-```
-
-### Remote Caching
-
-Turborepo can use a technique known as [Remote Caching](https://turbo.build/repo/docs/core-concepts/remote-caching) to share cache artifacts across machines, enabling you to share build caches with your team and CI/CD pipelines.
-
-By default, Turborepo will cache locally. To enable Remote Caching you will need an account with Vercel. If you don't have an account you can [create one](https://vercel.com/signup), then enter the following commands:
-
-```
-cd my-turborepo
-npx turbo login
-```
-
-This will authenticate the Turborepo CLI with your [Vercel account](https://vercel.com/docs/concepts/personal-accounts/overview).
-
-Next, you can link your Turborepo to your Remote Cache by running the following command from the root of your Turborepo:
-
-```
-npx turbo link
-```
-
-## Useful Links
-
-Learn more about the power of Turborepo:
-
-- [Tasks](https://turbo.build/repo/docs/core-concepts/monorepos/running-tasks)
-- [Caching](https://turbo.build/repo/docs/core-concepts/caching)
-- [Remote Caching](https://turbo.build/repo/docs/core-concepts/remote-caching)
-- [Filtering](https://turbo.build/repo/docs/core-concepts/monorepos/filtering)
-- [Configuration Options](https://turbo.build/repo/docs/reference/configuration)
-- [CLI Usage](https://turbo.build/repo/docs/reference/command-line-reference)

README.md

@@ -19,25 +19,29 @@ 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.
 
-## Getting started with an example:
+## Multiple JS Environment Support
 
-LlamaIndex.TS requires Node v18 or higher. You can download it from https://nodejs.org or use https://nvm.sh (our preferred option).
+LlamaIndex.TS supports multiple JS environments, including:
 
-In a new folder:
+- Node.js (18, 20, 22) ✅
+- Deno ✅
+- Bun ✅
+- React Server Components (Next.js) ✅
 
-```bash
-export OPENAI_API_KEY="sk-......" # Replace with your key from https://platform.openai.com/account/api-keys
-pnpm init
-pnpm install typescript
-pnpm exec tsc --init # if needed
+For now, browser support is limited due to the lack of support for [AsyncLocalStorage-like APIs](https://github.com/tc39/proposal-async-context)
+
+## Getting started
+
+```shell
+npm install llamaindex
 pnpm install llamaindex
-pnpm install @types/node
+yarn add llamaindex
+jsr install @llamaindex/core
 ```
 
-Create the file example.ts
+### Node.js
 
 ```ts
-// example.ts
 import fs from "fs/promises";
 import { Document, VectorStoreIndex } from "llamaindex";
 
@@ -67,10 +71,121 @@ async function main() {
 main();
 ```
 
-Then you can run it using
-
 ```bash
-pnpm dlx ts-node example.ts
+# `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
@@ -79,53 +194,64 @@ Check out our NextJS playground at https://llama-playground.vercel.app/. The sou
 
 ## Core concepts for getting started:
 
-- [Document](/packages/core/src/Node.ts): A document represents a text file, PDF file or other contiguous piece of data.
+- [Document](/packages/llamaindex/src/Node.ts): A document represents a text file, PDF file or other contiguous piece of data.
 
-- [Node](/packages/core/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.
+- [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/core/src/Embedding.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.
+- [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/core/src/indices/): Indices store the Nodes and the embeddings of those nodes. QueryEngines retrieve Nodes from these Indices using embedding similarity.
+- [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/core/src/QueryEngine.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.
+- [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/core/src/ChatEngine.ts): A ChatEngine helps you build a chatbot that will interact with your Indices.
+- [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/core/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.
+- [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.
 
-## Note: NextJS:
+## Tips when using in non-Node.js environments
 
-If you're using NextJS App Router, you'll need to use the NodeJS runtime (default) and add the following config to your next.config.js to have it use imports/exports in the same way Node does.
+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.
 
-```js
-export const runtime = "nodejs"; // default
+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`).
+
+If you need any of those classes, you have to import them instead directly though their file path in the package.
+Here's an example for importing the `PineconeVectorStore` class:
+
+```typescript
+import { PineconeVectorStore } from "llamaindex/storage/vectorStore/PineconeVectorStore";
 ```
 
-```js
-// next.config.js
-/** @type {import('next').NextConfig} */
-const nextConfig = {
-  experimental: {
-    serverComponentsExternalPackages: ["pdf2json"],
-  },
-  webpack: (config) => {
-    config.resolve.alias = {
-      ...config.resolve.alias,
-      sharp$: false,
-      "onnxruntime-node$": false,
-    };
-    return config;
-  },
-};
+As the `PDFReader` is not working with the Edge runtime, here's how to use the `SimpleDirectoryReader` with the `LlamaParseReader` to load PDFs:
 
-module.exports = nextConfig;
+```typescript
+import { SimpleDirectoryReader } from "llamaindex/readers/SimpleDirectoryReader";
+import { LlamaParseReader } from "llamaindex/readers/LlamaParseReader";
+
+export const DATA_DIR = "./data";
+
+export async function getDocuments() {
+  const reader = new SimpleDirectoryReader();
+  // Load PDFs using LlamaParseReader
+  return await reader.loadData({
+    directoryPath: DATA_DIR,
+    fileExtToReader: {
+      pdf: new LlamaParseReader({ resultType: "markdown" }),
+    },
+  });
+}
 ```
 
+> _Note_: Reader classes have to be added explictly to the `fileExtToReader` map in the Edge version of the `SimpleDirectoryReader`.
+
+You'll find a complete example with LlamaIndexTS here: https://github.com/run-llama/create_llama_projects/tree/main/nextjs-edge-llamaparse
+
 ## Supported LLMs:
 
 - OpenAI GPT-3.5-turbo and GPT-4
-- Anthropic Claude Instant and Claude 2
-- Llama2 Chat LLMs (70B, 13B, and 7B parameters)
+- 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
 

apps/docs/CHANGELOG.md

@@ -1,5 +1,223 @@
 # docs
 
+## 0.0.27
+
+### Patch Changes
+
+- Updated dependencies [3c47910]
+- Updated dependencies [ed467a9]
+- Updated dependencies [cba5406]
+  - llamaindex@0.4.1
+
+## 0.0.26
+
+### Patch Changes
+
+- b1a4a74: docs: updated Bedrock Opus region and added a basic README
+- Updated dependencies [436bc41]
+- Updated dependencies [a44e54f]
+- Updated dependencies [a51ed8d]
+- Updated dependencies [d3b635b]
+  - llamaindex@0.4.0
+  - @llamaindex/examples@0.0.5
+
+## 0.0.25
+
+### Patch Changes
+
+- Updated dependencies [6bc5bdd]
+- Updated dependencies [bf25ff6]
+- Updated dependencies [e6d6576]
+  - llamaindex@0.3.17
+
+## 0.0.24
+
+### Patch Changes
+
+- 631f000: feat: DeepInfra LLM implementation
+- 8832669: Community bedrock support added
+- a29d835: setDocumentHash should be async
+- Updated dependencies [11ae926]
+- Updated dependencies [631f000]
+- Updated dependencies [1378ec4]
+- Updated dependencies [6b1ded4]
+- Updated dependencies [4d4bd85]
+- Updated dependencies [24a9d1e]
+- Updated dependencies [45952de]
+- Updated dependencies [54230f0]
+- Updated dependencies [a29d835]
+- Updated dependencies [73819bf]
+  - llamaindex@0.3.16
+
+## 0.0.23
+
+### Patch Changes
+
+- Updated dependencies [6e156ed]
+- Updated dependencies [265976d]
+- Updated dependencies [8e26f75]
+  - llamaindex@0.3.15
+
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [6ff7576]
+- Updated dependencies [94543de]
+  - llamaindex@0.3.14
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [1b1081b]
+- Updated dependencies [37525df]
+- Updated dependencies [660a2b3]
+- Updated dependencies [a1f2475]
+  - llamaindex@0.3.13
+
+## 0.0.20
+
+### Patch Changes
+
+- Updated dependencies [34fb1d8]
+  - llamaindex@0.3.12
+
+## 0.0.19
+
+### Patch Changes
+
+- Updated dependencies [e072c45]
+- Updated dependencies [9e133ac]
+- Updated dependencies [447105a]
+- Updated dependencies [320be3f]
+  - llamaindex@0.3.11
+
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [4aba02e]
+  - llamaindex@0.3.10
+
+## 0.0.17
+
+### Patch Changes
+
+- Updated dependencies [c3747d0]
+  - llamaindex@0.3.9
+
+## 0.0.16
+
+### Patch Changes
+
+- Updated dependencies [ce94780]
+  - llamaindex@0.3.8
+
+## 0.0.15
+
+### Patch Changes
+
+- Updated dependencies [b6a6606]
+- Updated dependencies [b6a6606]
+  - llamaindex@0.3.7
+
+## 0.0.14
+
+### Patch Changes
+
+- Updated dependencies [efa326a]
+  - llamaindex@0.3.6
+
+## 0.0.13
+
+### Patch Changes
+
+- Updated dependencies [bc7a11c]
+- Updated dependencies [2fe2b81]
+- Updated dependencies [5596e31]
+- Updated dependencies [e74fe88]
+- Updated dependencies [be5df5b]
+  - llamaindex@0.3.5
+
+## 0.0.12
+
+### Patch Changes
+
+- Updated dependencies [1dce275]
+- Updated dependencies [d10533e]
+- Updated dependencies [2008efe]
+- Updated dependencies [5e61934]
+- Updated dependencies [9e74a43]
+- Updated dependencies [ee719a1]
+  - llamaindex@0.3.4
+
+## 0.0.11
+
+### Patch Changes
+
+- Updated dependencies [e8c41c5]
+  - llamaindex@0.3.3
+
+## 0.0.10
+
+### Patch Changes
+
+- Updated dependencies [61103b6]
+  - llamaindex@0.3.2
+
+## 0.0.9
+
+### Patch Changes
+
+- Updated dependencies [46227f2]
+  - llamaindex@0.3.1
+
+## 0.0.8
+
+### Patch Changes
+
+- Updated dependencies [5016f21]
+  - llamaindex@0.3.0
+
+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [6277105]
+  - llamaindex@0.2.13
+
+## 0.0.6
+
+### Patch Changes
+
+- Updated dependencies [d8d952d]
+  - llamaindex@0.2.12
+
+## 0.0.5
+
+### Patch Changes
+
+- Updated dependencies [87142b2]
+- Updated dependencies [5a6cc0e]
+- Updated dependencies [87142b2]
+  - llamaindex@0.2.11
+
+## 0.0.4
+
+### Patch Changes
+
+- Updated dependencies [5116ad8]
+  - @llamaindex/env@0.0.5
+
+## 0.0.3
+
+### Patch Changes
+
+- 09bf27a: Add Groq LLM to LlamaIndex
+- Updated dependencies [cf87f84]
+  - @llamaindex/env@0.0.4
+
 ## 0.0.2
 
 ### Patch Changes

apps/docs/blog/2024-04-26-v0.3.0.md

@@ -0,0 +1,493 @@
+---
+title: LlamaIndexTS v0.3.0
+description: This is my first post on Docusaurus.
+slug: welcome-llamaindexts-v0.3
+authors:
+  - name: Alex Yang
+    title: LlamaIndexTS maintainer, Node.js Member
+    url: https://github.com/himself65
+    image_url: https://github.com/himself65.png
+tags: [llamaindex, agent]
+hide_table_of_contents: false
+---
+
+- [What's new in LlamaIndexTS v0.3.0](#whats-new-in-llamaindexts-v030)
+- [Improvement in LlamaIndexTS v0.3.0](#improvement-in-llamaindexts-v030)
+- [What's the next?](#whats-the-next)
+
+## What's new in LlamaIndexTS v0.3.0
+
+## Agents
+
+In this release, we've not only ported the Agent module from the LlamaIndex Python version but have significantly
+enhanced it to be more powerful and user-friendly for JavaScript/TypeScript applications.
+
+Starting from v0.3.0, we are introducing multiple agents specifically designed for RAG applications, including:
+
+- `OpenAIAgent`
+- `AnthropicAgent`
+- `ReActAgent`:
+
+```ts
+import { OpenAIAgent } from "llamaindex";
+import { tools } from "./tools";
+
+const agent = new OpenAIAgent({
+  tools: [...tools],
+});
+const { response } = await agent.chat({
+  message: "What is weather today?",
+  stream: false,
+});
+
+console.log(response.message.content);
+```
+
+We are also introducing the abstract AgentRunner class, which allows you to create your own agent by simply implementing
+the task handler.
+
+```ts
+import { AgentRunner, OpenAI } from "llamaindex";
+
+class MyLLM extends OpenAI {}
+
+export class MyAgentWorker extends AgentWorker<MyLLM> {
+  taskHandler = MyAgent.taskHandler;
+}
+
+export class MyAgent extends AgentRunner<MyLLM> {
+  constructor(params: Params) {
+    super({
+      llm: params.llm,
+      chatHistory: params.chatHistory ?? [],
+      systemPrompt: params.systemPrompt ?? null,
+      runner: new MyAgentWorker(),
+      tools:
+        "tools" in params
+          ? params.tools
+          : params.toolRetriever.retrieve.bind(params.toolRetriever),
+    });
+  }
+
+  // create store is a function to create a store for each task, by default it only includes `messages` and `toolOutputs`
+  createStore = AgentRunner.defaultCreateStore;
+
+  static taskHandler: TaskHandler<Anthropic> = async (step, enqueueOutput) => {
+    const { llm, stream } = step.context;
+    // initialize the input
+    const response = await llm.chat({
+      stream,
+      messages: step.context.store.messages,
+    });
+    // store the response for next task step
+    step.context.store.messages = [
+      ...step.context.store.messages,
+      response.message,
+    ];
+    // your logic here to decide whether to continue the task
+    const shouldContinue = Math.random(); /* <-- replace with your logic here */
+    enqueueOutput({
+      taskStep: step,
+      output: response,
+      isLast: !shouldContinue,
+    });
+    if (shouldContinue) {
+      const content = await someHeavyFunctionCall();
+      // if you want to continue the task, you can insert your new context for the next task step
+      step.context.store.messages = [
+        ...step.context.store.messages,
+        {
+          content,
+          role: "user",
+        },
+      ];
+    }
+  };
+}
+```
+
+### Web Stream API for Streaming response
+
+Web Stream is a web standard utilized in many modern web frameworks and libraries (like React 19, Deno, Node 22). We
+have migrated streaming responses to Web Stream to ensure broader compatibility.
+
+For instance, you can use the streaming response in a simple HTTP Server:
+
+```ts
+import { createServer } from "http";
+import { OpenAIAgent } from "llamaindex";
+import { OpenAIStream, streamToResponse } from "ai";
+import { tools } from "./tools";
+
+const agent = new OpenAIAgent({
+  tools: [...tools],
+});
+
+const server = createServer(async (req, res) => {
+  const response = await agent.chat({
+    message: "What is weather today?",
+    stream: true,
+  });
+
+  // Transform the response into a string readable stream
+  const stream: ReadableStream<string> = response.pipeThrough(
+    new TransformStream({
+      transform: (chunk, controller) => {
+        controller.enqueue(chunk.response.delta);
+      },
+    }),
+  );
+
+  // Pipe the stream to the response
+  streamToResponse(stream, res);
+});
+
+server.listen(3000);
+```
+
+Or it can be integrated into React Server Components (RSC) in Next.js:
+
+```tsx
+// app/actions/index.tsx
+"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: [],
+  });
+  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(uiStream.error);
+  return uiStream.value;
+}
+```
+
+```tsx
+// app/src/page.tsx
+"use client";
+import { chatWithAgent } from "@/actions";
+import type { JSX } from "react";
+import { useFormState } from "react-dom";
+
+export const runtime = "edge";
+
+export default function Home() {
+  const [state, action] = useFormState<JSX.Element | null>(async () => {
+    return chatWithAgent("hello!", []);
+  }, null);
+  return (
+    <main>
+      {state}
+      <form action={action}>
+        <button>Chat</button>
+      </form>
+    </main>
+  );
+}
+```
+
+## Improvement in LlamaIndexTS v0.3.0
+
+### Better TypeScript support
+
+We have made significant improvements to the type system to ensure that all code is thoroughly checked before it is
+published. This ongoing enhancement has already resulted in better module reliability and developer experience.
+
+For example, we have improved `FunctionTool` type with generic support:
+
+```ts
+type Input = {
+  a: number;
+  b: number;
+};
+
+const sumNumbers = FunctionTool.from<Input>(
+  ({ a, b }) => `${a + b}`, // a and b will be checked as number
+  // JSON schema will be an error if you type wrong.
+  {
+    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"],
+    },
+  },
+);
+```
+
+![type checking](./img/function_tool_example.png)
+
+### Better Next.js, Deno, Cloudflare Worker, and Waku(Vite) support
+
+In addition to Node.js, LlamaIndexTS now offers enhanced support for Next.js, Deno, and Cloudflare Workers, making it
+more versatile across different platforms.
+
+For now, you can install llamaindex and directly import it into your existing Next.js, Deno or Cloudflare Worker project
+**without any extra configuration**.
+
+#### [Deno](https://deno.com/)
+
+You can use LlamaIndexTS in Deno by installation through JSR:
+
+```sh
+jsr add @llamaindex/core
+```
+
+#### [Cloudflare Worker](https://developers.cloudflare.com/workers/)
+
+For Cloudflare Workers, here is a starter template:
+
+```typescript
+export default {
+  async fetch(
+    request: Request,
+    env: Env,
+    ctx: ExecutionContext,
+  ): Promise<Response> {
+    const { setEnvs } = await import("@llamaindex/env");
+    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);
+  },
+};
+```
+
+### [Waku (Vite)](https://waku.gg/)
+
+Waku powered by Vite is a minimal React framework that supports multiple JS environments, including Deno, Cloudflare, and
+Node.js.
+
+You can use LlamaIndexTS with Node.js output to enable full Node.js support with React.
+
+```sh
+npm install llamaindex
+```
+
+```ts
+// file: src/actions.ts
+"use server";
+import { Document, VectorStoreIndex } from "llamaindex";
+import { readFile } from "node:fs/promises";
+
+const path = "node_modules/llamaindex/examples/abramov.txt";
+
+const essay = await readFile(path, "utf-8");
+
+// Create Document object with essay
+const document = new Document({ text: essay, id_: path });
+
+// Split text and create embeddings. Store them in a VectorStoreIndex
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+export async function chatWithAI(question: string): Promise<string> {
+  const { response } = await queryEngine.query({ query: question });
+  return response;
+}
+```
+
+```tsx
+// file: src/pages/index.tsx
+import { chatWithAI } from "./actions";
+
+export default async function HomePage() {
+  return (
+    <div>
+      <Chat askQuestion={chatWithAI} />
+    </div>
+  );
+}
+```
+
+```tsx
+// file: src/components/Chat.tsx
+"use client";
+
+export type ChatProps = {
+  askQuestion: (question: string) => Promise<string>;
+};
+
+export const Chat = (props: ChatProps) => {
+  const [response, setResponse] = useState<string | null>(null);
+
+  return (
+    <section className="border-blue-400 -mx-4 mt-4 rounded border border-dashed p-4">
+      <h2 className="text-lg font-bold">Chat with AI</h2>
+      {response ? (
+        <p className="text-sm text-gray-600 max-w-sm">{response}</p>
+      ) : null}
+      <form
+        action={async (formData) => {
+          const question = formData.get("question") as string | null;
+          if (question) {
+            setResponse(await props.askQuestion(question));
+          }
+        }}
+      >
+        <input
+          type="text"
+          name="question"
+          className="border border-gray-400 rounded-sm px-2 py-0.5 text-sm"
+        />
+        <button className="rounded-sm bg-black px-2 py-0.5 text-sm text-white">
+          Ask
+        </button>
+      </form>
+    </section>
+  );
+};
+```
+
+```shell
+waku dev # development mode
+waku build # build for production
+waku start # start the production server
+```
+
+Note that not all the modules are supported in all JS environments because of
+lack of the file system, network API,
+and incompatibility with the Node.js API by upstream dependencies.
+
+But we are trying to make it more compatible with all the environments.
+
+## What's the next?
+
+As we continue to develop LlamaIndexTS, our focus remains on providing more comprehensive and powerful tools for
+creating custom agents.
+
+### Align with the Python `llama-index`
+
+We aim to align LlamaIndexTS with the Python version to ensure API consistency and ease of use for developers familiar
+with the Python ecosystem.
+
+### Align with the Web Standard and JS development
+
+Not all python APIs are compatible and easy to use in JavaScript/TypeScript.
+We are trying to make the API more compatible with the Web Standard and JavaScript modern development.
+
+### More Agents
+
+Future releases will introduce more agents from the Python Llama-Index and explore APIs tailored to real-world use
+cases.
+
+### 🧪 `@llamaindex/tool`
+
+We are exploring innovative ways to create tools for agents. The `@llamaindex/tool` library allows you to transform any
+function into a tool for an agent, simplifying the development process and reducing runtime costs.
+
+```ts
+export function getWeather(city: string) {
+  return `The weather in ${city} is sunny.`;
+}
+
+// you don't need to worry about the shcema with different llm tools
+export function getTemperature(city: string) {
+  return `The temperature in ${city} is 25°C.`;
+}
+
+export function getCurrentCity() {
+  return "New York";
+}
+```
+
+These functions can be easily integrated into your applications, such as Next.js:
+
+```ts
+"use server";
+import { OpenAI } from "openai";
+import { getTools } from "@llamaindex/tool";
+
+export async function chat(message: string) {
+  const openai = new OpenAI();
+  openai.chat.completions.create({
+    messages: [
+      {
+        role: "user",
+        content: "What is the weather in the current city?",
+      },
+    ],
+    tools: getTools("openai"),
+  });
+}
+```
+
+```ts
+// next.config.js
+const withTool = require("@llamaindex/tool/next");
+
+const config = {
+  // Your original Next.js config
+};
+module.exports = withTool(config);
+```
+
+The functions are automatically transformed into tools for the agent at compile time, which eliminates any extra runtime
+costs. This feature is particularly beneficial when you need to debug or deploy your assistant.
+
+For deploying your local functions into OpenAI, you can use a simple command:
+
+```sh
+npm install -g @llamaindex/tool
+mkai --tools ./src/index.llama.ts
+# Successfully created assistant: asst_XXX
+# chat with your assistant by `chatai --assistant asst_XXX`
+chatai --assistant asst_XXX
+# Open your browser and chat with your assistant
+# Running at http://localhost:3000
+```
+
+This deployment process simplifies the testing and implementation of your custom tools in a live environment.
+
+As this project is still in its early stages, we continue to explore the best ways to create and integrate tools for
+agents. For more information and updates, visit the @llamaindex/tool repository.
+
+This release of LlamaIndexTS v0.3.0 marks a significant step forward in our journey to provide developers with robust,
+flexible tools for building advanced agents. We are excited to see how our community utilizes these new capabilities to
+create innovative solutions and look forward to continuing to support and enhance LlamaIndexTS in future updates.

apps/docs/docs/examples/_category_.yml

@@ -1,2 +1,2 @@
 label: Examples
-position: 2
+position: 3

apps/docs/docs/examples/agent.mdx

@@ -4,82 +4,7 @@ A built-in agent that can take decisions and reasoning based on the tools provid
 
 ## OpenAI Agent
 
-```ts
-import { FunctionTool, OpenAIAgent } from "llamaindex";
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../examples/agent/openai";
 
-// Define a function to sum two numbers
-function sumNumbers({ a, b }: { a: number; b: number }): number {
-  return a + b;
-}
-
-// Define a function to divide two numbers
-function divideNumbers({ a, b }: { a: number; b: number }): number {
-  return a / b;
-}
-
-// Define the parameters of the sum function as a JSON schema
-const sumJSON = {
-  type: "object",
-  properties: {
-    a: {
-      type: "number",
-      description: "The first number",
-    },
-    b: {
-      type: "number",
-      description: "The second number",
-    },
-  },
-  required: ["a", "b"],
-};
-
-// Define the parameters of the divide function as a JSON schema
-const divideJSON = {
-  type: "object",
-  properties: {
-    a: {
-      type: "number",
-      description: "The dividend to divide",
-    },
-    b: {
-      type: "number",
-      description: "The divisor to divide by",
-    },
-  },
-  required: ["a", "b"],
-};
-
-async function main() {
-  // Create a function tool from the sum function
-  const sumFunctionTool = new FunctionTool(sumNumbers, {
-    name: "sumNumbers",
-    description: "Use this function to sum two numbers",
-    parameters: sumJSON,
-  });
-
-  // Create a function tool from the divide function
-  const divideFunctionTool = new FunctionTool(divideNumbers, {
-    name: "divideNumbers",
-    description: "Use this function to divide two numbers"
-    parameters: divideJSON,
-  });
-
-  // Create an OpenAIAgent with the function tools
-  const agent = new OpenAIAgent({
-    tools: [sumFunctionTool, divideFunctionTool],
-    verbose: true,
-  });
-
-  // Chat with the agent
-  const response = await agent.chat({
-    message: "How much is 5 + 5? then divide by 2",
-  });
-
-  // Print the response
-  console.log(String(response));
-}
-
-main().then(() => {
-  console.log("Done");
-});
-```
+<CodeBlock language="ts">{CodeSource}</CodeBlock>

apps/docs/docs/examples/chat_engine.mdx

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 1
+sidebar_position: 2
 ---
 
 import CodeBlock from "@theme/CodeBlock";

apps/docs/docs/examples/local_llm.mdx

@@ -0,0 +1,77 @@
+# Local LLMs
+
+LlamaIndex.TS supports OpenAI and [other remote LLM APIs](other_llms). You can also run a local LLM on your machine!
+
+## Using a local model via Ollama
+
+The easiest way to run a local LLM is via the great work of our friends at [Ollama](https://ollama.com/), who provide a simple to use client that will download, install and run a [growing range of models](https://ollama.com/library) for you.
+
+### Install Ollama
+
+They provide a one-click installer for Mac, Linux and Windows on their [home page](https://ollama.com/).
+
+### Pick and run a model
+
+Since we're going to be doing agentic work, we'll need a very capable model, but the largest models are hard to run on a laptop. We think `mixtral 8x7b` is a good balance between power and resources, but `llama3` is another great option. You can run Mixtral by running
+
+```bash
+ollama run mixtral:8x7b
+```
+
+The first time you run it will also automatically download and install the model for you.
+
+### Switch the LLM in your code
+
+To tell LlamaIndex to use a local LLM, use the `Settings` object:
+
+```javascript
+Settings.llm = new Ollama({
+  model: "mixtral:8x7b",
+});
+```
+
+### Use local embeddings
+
+If you're doing retrieval-augmented generation, LlamaIndex.TS will also call out to OpenAI to index and embed your data. To be entirely local, you can use a local embedding model like this:
+
+```javascript
+Settings.embedModel = new HuggingFaceEmbedding({
+  modelType: "BAAI/bge-small-en-v1.5",
+  quantized: false,
+});
+```
+
+The first time this runs it will download the embedding model to run it.
+
+### Try it out
+
+With a local LLM and local embeddings in place, you can perform RAG as usual and everything will happen on your machine without calling an API:
+
+```typescript
+async function main() {
+  // Load essay from abramov.txt in Node
+  const path = "node_modules/llamaindex/examples/abramov.txt";
+
+  const essay = await fs.readFile(path, "utf-8");
+
+  // Create Document object with essay
+  const document = new Document({ text: essay, id_: path });
+
+  // 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().catch(console.error);
+```
+
+You can see the [full example file](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/vectorIndexLocal.ts).

apps/docs/docs/examples/more_examples.mdx

@@ -1,7 +1,23 @@
 ---
-sidebar_position: 5
+sidebar_position: 1
 ---
 
-# More examples
+# See all examples
 
-You can check out more examples in the [examples](https://github.com/run-llama/LlamaIndexTS/tree/main/examples) folder of the repository.
+Our GitHub repository has a wealth of examples to explore and try out. You can check out our [examples folder](https://github.com/run-llama/LlamaIndexTS/tree/main/examples) to see them all at once, or browse the pages in this section for some selected highlights.
+
+## Check out all examples
+
+It may be useful to check out all the examples at once so you can try them out locally. To do this into a folder called `my-new-project`, run these commands:
+
+```bash npm2yarn
+npx degit run-llama/LlamaIndexTS/examples my-new-project
+cd my-new-project
+npm install
+```
+
+Then you can run any example in the folder with `tsx`, e.g.:
+
+```bash npm2yarn
+npx tsx ./vectorIndex.ts
+```

apps/docs/docs/examples/other_llms.mdx

@@ -0,0 +1,41 @@
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../examples/mistral";
+
+# Using other LLM APIs
+
+By default LlamaIndex.TS uses OpenAI's LLMs and embedding models, but we support [lots of other LLMs](../modules/llms) including models from Mistral (Mistral, Mixtral), Anthropic (Claude) and Google (Gemini).
+
+If you don't want to use an API at all you can [run a local model](../../examples/local_llm)
+
+## Using another LLM
+
+You can specify what LLM LlamaIndex.TS will use on the `Settings` object, like this:
+
+```typescript
+import { MistralAI, Settings } from "llamaindex";
+
+Settings.llm = new MistralAI({
+  model: "mistral-tiny",
+  apiKey: "<YOUR_API_KEY>",
+});
+```
+
+You can see examples of other APIs we support by checking out "Available LLMs" in the sidebar of our [LLMs section](../modules/llms).
+
+## Using another embedding model
+
+A frequent gotcha when trying to use a different API as your LLM is that LlamaIndex will also by default index and embed your data using OpenAI's embeddings. To completely switch away from OpenAI you will need to set your embedding model as well, for example:
+
+```typescript
+import { MistralAIEmbedding, Settings } from "llamaindex";
+
+Settings.embedModel = new MistralAIEmbedding();
+```
+
+We support [many different embeddings](../modules/embeddings).
+
+## Full example
+
+This example uses Mistral's `mistral-tiny` model as the LLM and Mistral for embeddings as well.
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>

apps/docs/docs/getting_started/environments.md

@@ -4,7 +4,7 @@ sidebar_position: 2
 
 # Environments
 
-LlamaIndex currently officially supports NodeJS 18 and NodeJS 20.
+We support Node.JS versions 18, 20 and 22, with experimental support for Deno, Bun and Vercel Edge functions.
 
 ## NextJS App Router
 

apps/docs/docs/getting_started/installation.mdx

@@ -4,45 +4,7 @@ sidebar_position: 0
 
 # Installation and Setup
 
-Make sure you have NodeJS v18 or higher.
-
-## Using create-llama
-
-The easiest way to get started with LlamaIndex is by using `create-llama`. This CLI tool enables you to quickly start building a new LlamaIndex application, with everything set up for you.
-
-Just run
-
-<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>
-
-to get started. Once your app is generated, run
-
-```bash npm2yarn
-npm run dev
-```
-
-to start the development server. You can then visit [http://localhost:3000](http://localhost:3000) to see your app
+We support Node.JS versions 18, 20 and 22, with experimental support for Deno, Bun and Vercel Edge functions.
 
 ## Installation from NPM
 
@@ -52,12 +14,21 @@ npm install llamaindex
 
 ### Environment variables
 
-Our examples use OpenAI by default. You'll need to set up your Open AI key like so:
+Our examples use OpenAI by default. You can use [other LLMs](../examples/other_llms) via their APIs; if you would prefer to use local models check out our [local LLM example](../examples/local_llm).
+
+To use OpenAI, you'll need to [get an OpenAI API key](https://platform.openai.com/account/api-keys) and then make it available as an environment variable this way:
 
 ```bash
-export OPENAI_API_KEY="sk-......" # Replace with your key from https://platform.openai.com/account/api-keys
+export OPENAI_API_KEY="sk-......" # Replace with your key
 ```
 
 If you want to have it automatically loaded every time, add it to your `.zshrc/.bashrc`.
 
-WARNING: do not check in your OpenAI key into version control.
+**WARNING:** do not check in your OpenAI key into version control. GitHub automatically invalidates OpenAI keys checked in by accident.
+
+## What next?
+
+- The easiest way to started is to [build a full-stack chat app with `create-llama`](starter_tutorial/chatbot).
+- Try our other [getting started tutorials](starter_tutorial/retrieval_augmented_generation)
+- Learn more about the [high level concepts](concepts) behind how LlamaIndex works
+- Check out our [many examples](../examples/more_examples) of LlamaIndex.TS in action

apps/docs/docs/getting_started/starter.md

@@ -1,56 +0,0 @@
----
-sidebar_position: 1
----
-
-# Starter Tutorial
-
-Once you have [installed LlamaIndex.TS using NPM](installation) and set up your OpenAI key, you're ready to start your first app:
-
-In a new folder:
-
-```bash npm2yarn
-npm install typescript
-npm install @types/node
-npx tsc --init # if needed
-```
-
-Create the file `example.ts`. This code will load some example data, create a document, index it (which creates embeddings using OpenAI), and then creates query engine to answer questions about the data.
-
-```ts
-// example.ts
-import fs from "fs/promises";
-import { Document, VectorStoreIndex } from "llamaindex";
-
-async function main() {
-  // Load essay from abramov.txt in Node
-  const essay = await fs.readFile(
-    "node_modules/llamaindex/examples/abramov.txt",
-    "utf-8",
-  );
-
-  // 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();
-```
-
-Then you can run it using
-
-```bash
-npx ts-node example.ts
-```
-
-Ready to learn more? Check out our NextJS playground at https://llama-playground.vercel.app/. The source is available at https://github.com/run-llama/ts-playground

apps/docs/docs/getting_started/starter_tutorial/_category_.yml

@@ -0,0 +1,2 @@
+label: Starter Tutorials
+position: 1

apps/docs/docs/getting_started/starter_tutorial/agent.mdx

@@ -0,0 +1,49 @@
+---
+sidebar_position: 4
+---
+
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../../examples/agent/openai";
+
+# Agent tutorial
+
+We have a comprehensive, step-by-step [guide to building agents in LlamaIndex.TS](../../guides/agents/setup) that we recommend to learn what agents are and how to build them for production. But building a basic agent is simple:
+
+## Set up
+
+In a new folder:
+
+```bash npm2yarn
+npm init
+npm install -D typescript @types/node
+```
+
+## Run agent
+
+Create the file `example.ts`. This code will:
+
+- Create two tools for use by the agent:
+  - A `sumNumbers` tool that adds two numbers
+  - A `divideNumbers` tool that divides numbers
+-
+- Give an example of the data structure we wish to generate
+- Prompt the LLM with instructions and the example, plus a sample transcript
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
+
+To run the code:
+
+```bash
+npx tsx example.ts
+```
+
+You should expect output something like:
+
+```
+{
+  content: 'The sum of 5 + 5 is 10. When you divide 10 by 2, you get 5.',
+  role: 'assistant',
+  options: {}
+}
+Done
+```

apps/docs/docs/getting_started/starter_tutorial/chatbot.mdx

@@ -0,0 +1,27 @@
+---
+sidebar_position: 2
+---
+
+# Chatbot tutorial
+
+Once you've mastered basic [retrieval-augment generation](retrieval_augmented_generation) you may want to create an interface to chat with your data. You can do this step-by-step, but we recommend getting started quickly using `create-llama`.
+
+## Using create-llama
+
+`create-llama` is a powerful but easy to use command-line tool that generates a working, full-stack web application that allows you to chat with your data. You can learn more about it on [the `create-llama` README page](https://www.npmjs.com/package/create-llama).
+
+Run it once and it will ask you a series of questions about the kind of application you want to generate. Then you can customize your application to suit your use-case. To get started, run:
+
+```bash npm2yarn
+npx create-llama@latest
+```
+
+Once your app is generated, `cd` into your app directory and run
+
+```bash npm2yarn
+npm run dev
+```
+
+to start the development server. You can then visit [http://localhost:3000](http://localhost:3000) to see your app, which should look something like this:
+
+![create-llama interface](./images/create_llama.png)

apps/docs/docs/getting_started/starter_tutorial/retrieval_augmented_generation.mdx

@@ -0,0 +1,58 @@
+---
+sidebar_position: 1
+---
+
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../../examples/vectorIndex";
+import TSConfigSource from "!!raw-loader!../../../../../examples/tsconfig.json";
+
+# Retrieval Augmented Generation (RAG) Tutorial
+
+One of the most common use-cases for LlamaIndex is Retrieval-Augmented Generation or RAG, in which your data is indexed and selectively retrieved to be given to an LLM as source material for responding to a query. You can learn more about the [concepts behind RAG](../concepts).
+
+## Set up the project
+
+In a new folder, run:
+
+```bash npm2yarn
+npm init
+npm install -D typescript @types/node
+```
+
+Then, check out the [installation](../installation) steps to install LlamaIndex.TS and prepare an OpenAI key.
+
+You can use [other LLMs](../examples/other_llms) via their APIs; if you would prefer to use local models check out our [local LLM example](../../examples/local_llm).
+
+## Run queries
+
+Create the file `example.ts`. This code will
+
+- load an example file
+- convert it into a Document object
+- index it (which creates embeddings using OpenAI)
+- create a query engine to answer questions about the data
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
+
+Create a `tsconfig.json` file in the same folder:
+
+<CodeBlock language="json">{TSConfigSource}</CodeBlock>
+
+Now you can run the code with
+
+```bash
+npx tsx example.ts
+```
+
+You should expect output something like:
+
+```
+In college, the author studied subjects like linear algebra and physics, but did not find them particularly interesting. They started slacking off, skipping lectures, and eventually stopped attending classes altogether. They also had a negative experience with their English classes, where they were required to pay for catch-up training despite getting verbal approval to skip most of the classes. Ultimately, the author lost motivation for college due to their job as a software developer and stopped attending classes, only returning years later to pick up their papers.
+
+0: Score: 0.8305309270895813 - I started this decade as a first-year college stud...
+
+
+1: Score: 0.8286388215713089 - A short digression. I’m not saying colleges are wo...
+```
+
+Once you've mastered basic RAG, you may want to consider [chatting with your data](chatbot).

apps/docs/docs/getting_started/starter_tutorial/structured_data_extraction.mdx

@@ -0,0 +1,52 @@
+---
+sidebar_position: 3
+---
+
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../../examples/jsonExtract";
+
+# Structured data extraction tutorial
+
+Make sure you have installed LlamaIndex.TS and have an OpenAI key. If you haven't, check out the [installation](installation) guide.
+
+You can use [other LLMs](../examples/other_llms) via their APIs; if you would prefer to use local models check out our [local LLM example](../../examples/local_llm).
+
+## Set up
+
+In a new folder:
+
+```bash npm2yarn
+npm init
+npm install -D typescript @types/node
+```
+
+## Extract data
+
+Create the file `example.ts`. This code will:
+
+- Set up an LLM connection to GPT-4
+- Give an example of the data structure we wish to generate
+- Prompt the LLM with instructions and the example, plus a sample transcript
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
+
+To run the code:
+
+```bash
+npx tsx example.ts
+```
+
+You should expect output something like:
+
+```json
+{
+  "summary": "Sarah from XYZ Company called John to introduce the XYZ Widget, a tool designed to automate tasks and improve productivity. John expressed interest and requested case studies and a product demo. Sarah agreed to send the information and follow up to schedule the demo.",
+  "products": ["XYZ Widget"],
+  "rep_name": "Sarah",
+  "prospect_name": "John",
+  "action_items": [
+    "Send case studies and additional product information to John",
+    "Follow up with John to schedule a product demo"
+  ]
+}
+```

apps/docs/docs/guides/_category_.yml

@@ -0,0 +1,2 @@
+label: Guides
+position: 2

apps/docs/docs/guides/agents/1_setup.mdx

@@ -0,0 +1,41 @@
+---
+sidebar_position: 1
+---
+
+# Getting started
+
+In this guide we'll walk you through the process of building an Agent in JavaScript using the LlamaIndex.TS library, starting from nothing and adding complexity in stages.
+
+## What is an Agent?
+
+In LlamaIndex, an agent is a semi-autonomous piece of software powered by an LLM that is given a task and executes a series of steps towards solving that task. It is given a set of tools, which can be anything from arbitrary functions up to full LlamaIndex query engines, and it selects the best available tool to complete each step. When each step is completed, the agent judges whether the task is now complete, in which case it returns a result to the user, or whether it needs to take another step, in which case it loops back to the start.
+
+![agent flow](./images/agent_flow.png)
+
+## Install LlamaIndex.TS
+
+You'll need to have a recent version of [Node.js](https://nodejs.org/en) installed. Then you can install LlamaIndex.TS by running
+
+```bash
+npm install llamaindex
+```
+
+## Choose your model
+
+By default we'll be using OpenAI with GPT-4, as it's a powerful model and easy to get started with. If you'd prefer to run a local model, see [using a local model](local_model).
+
+## Get an OpenAI API key
+
+If you don't already have one, you can sign up for an [OpenAI API key](https://platform.openai.com/api-keys). You should then put the key in a `.env` file in the root of the project; the file should look like
+
+```
+OPENAI_API_KEY=sk-XXXXXXXXXXXXXXXXXXXXXXXX
+```
+
+We'll use `dotenv` to pull the API key out of that .env file, so also run:
+
+```bash
+npm install dotenv
+```
+
+Now you're ready to [create your agent](create_agent).

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

@@ -0,0 +1,179 @@
+# Create a basic agent
+
+We want to use `await` so we're going to wrap all of our code in a `main` function, like this:
+
+```typescript
+// Your imports go here
+
+async function main() {
+  // the rest of your code goes here
+}
+
+main().catch(console.error);
+```
+
+For the rest of this guide we'll assume your code is wrapped like this so we can use `await`. You can run the code this way:
+
+```bash
+npx tsx example.ts
+```
+
+### Load your dependencies
+
+First we'll need to pull in our dependencies. These are:
+
+- The OpenAI class to use the OpenAI LLM
+- FunctionTool to provide tools to our agent
+- OpenAIAgent to create the agent itself
+- Settings to define some global settings for the library
+- Dotenv to load our API key from the .env file
+
+```javascript
+import { OpenAI, FunctionTool, OpenAIAgent, Settings } from "llamaindex";
+import "dotenv/config";
+```
+
+### Initialize your LLM
+
+We need to tell our OpenAI class where its API key is, and which of OpenAI's models to use. We'll be using `gpt-4o`, which is capable while still being pretty cheap. This is a global setting, so anywhere an LLM is needed will use the same model.
+
+```javascript
+Settings.llm = new OpenAI({
+  apiKey: process.env.OPENAI_API_KEY,
+  model: "gpt-4o",
+});
+```
+
+### Turn on logging
+
+We want to see what our agent is up to, so we're going to hook into some events that the library generates and print them out. There are several events possible, but we'll specifically tune in to `llm-tool-call` (when a tool is called) and `llm-tool-result` (when it responds).
+
+```javascript
+Settings.callbackManager.on("llm-tool-call", (event) => {
+  console.log(event.detail.payload);
+});
+Settings.callbackManager.on("llm-tool-result", (event) => {
+  console.log(event.detail.payload);
+});
+```
+
+### Create a function
+
+We're going to create a very simple function that adds two numbers together. This will be the tool we ask our agent to use.
+
+```javascript
+const sumNumbers = ({ a, b }) => {
+  return `${a + b}`;
+};
+```
+
+Note that we're passing in an object with two named parameters, `a` and `b`. This is a little unusual, but important for defining a tool that an LLM can use.
+
+### Turn the function into a tool for the agent
+
+This is the most complicated part of creating an agent. We need to define a `FunctionTool`. We have to pass in:
+
+- The function itself (`sumNumbers`)
+- A name for the function, which the LLM will use to call it
+- A description of the function. The LLM will read this description to figure out what the tool does, and if it needs to call it
+- A schema for function. We tell the LLM that the parameter is an `object`, and we tell it about the two named parameters we gave it, `a` and `b`. We describe each parameter as a `number`, and we say that both are required.
+- You can see [more examples of function schemas](https://cookbook.openai.com/examples/how_to_call_functions_with_chat_models).
+
+```javascript
+const tool = FunctionTool.from(sumNumbers, {
+  name: "sumNumbers",
+  description: "Use this function to sum two numbers",
+  parameters: {
+    type: "object",
+    properties: {
+      a: {
+        type: "number",
+        description: "First number to sum",
+      },
+      b: {
+        type: "number",
+        description: "Second number to sum",
+      },
+    },
+    required: ["a", "b"],
+  },
+});
+```
+
+We then wrap up the tools into an array. We could provide lots of tools this way, but for this example we're just using the one.
+
+```javascript
+const tools = [tool];
+```
+
+### Create the agent
+
+With your LLM already set up and your tools defined, creating an agent is simple:
+
+```javascript
+const agent = new OpenAIAgent({ tools });
+```
+
+### Ask the agent a question
+
+We can use the `chat` interface to ask our agent a question, and it will use the tools we've defined to find an answer.
+
+```javascript
+let response = await agent.chat({
+  message: "Add 101 and 303",
+});
+
+console.log(response);
+```
+
+Let's see what running this looks like using `npx tsx agent.ts`
+
+**_Output_**
+
+```javascript
+{
+  toolCall: {
+    id: 'call_ze6A8C3mOUBG4zmXO8Z4CPB5',
+    name: 'sumNumbers',
+    input: { a: 101, b: 303 }
+  },
+  toolResult: {
+    tool: FunctionTool { _fn: [Function: sumNumbers], _metadata: [Object] },
+    input: { a: 101, b: 303 },
+    output: '404',
+    isError: false
+  }
+}
+```
+
+```javascript
+{
+  response: {
+    raw: {
+      id: 'chatcmpl-9KwauZku3QOvH78MNvxJs81mDvQYK',
+      object: 'chat.completion',
+      created: 1714778824,
+      model: 'gpt-4-turbo-2024-04-09',
+      choices: [Array],
+      usage: [Object],
+      system_fingerprint: 'fp_ea6eb70039'
+    },
+    message: {
+      content: 'The sum of 101 and 303 is 404.',
+      role: 'assistant',
+      options: {}
+    }
+  },
+  sources: [Getter]
+}
+```
+
+We're seeing two pieces of output here. The first is our callback firing when the tool is called. You can see in `toolResult` that the LLM has correctly passed `101` and `303` to our `sumNumbers` function, which adds them up and returns `404`.
+
+The second piece of output is the response from the LLM itself, where the `message.content` key is giving us the answer.
+
+Great! We've built an agent with tool use! Next you can:
+
+- [See the full code](https://github.com/run-llama/ts-agents/blob/main/1_agent/agent.ts)
+- [Switch to a local LLM](local_model)
+- Move on to [add Retrieval-Augmented Generation to your agent](agentic_rag)

apps/docs/docs/guides/agents/3_local_model.mdx

@@ -0,0 +1,90 @@
+# Using a local model via Ollama
+
+If you're happy using OpenAI, you can skip this section, but many people are interested in using models they run themselves. The easiest way to do this is via the great work of our friends at [Ollama](https://ollama.com/), who provide a simple to use client that will download, install and run a [growing range of models](https://ollama.com/library) for you.
+
+### Install Ollama
+
+They provide a one-click installer for Mac, Linux and Windows on their [home page](https://ollama.com/).
+
+### Pick and run a model
+
+Since we're going to be doing agentic work, we'll need a very capable model, but the largest models are hard to run on a laptop. We think `mixtral 8x7b` is a good balance between power and resources, but `llama3` is another great option. You can run it simply by running
+
+```bash
+ollama run mixtral:8x7b
+```
+
+The first time you run it will also automatically download and install the model for you.
+
+### Switch the LLM in your code
+
+There are two changes you need to make to the code we already wrote in `1_agent` to get Mixtral 8x7b to work. First, you need to switch to that model. Replace the call to `Settings.llm` with this:
+
+```javascript
+Settings.llm = new Ollama({
+  model: "mixtral:8x7b",
+});
+```
+
+### Swap to a ReActAgent
+
+In our original code we used a specific OpenAIAgent, so we'll need to switch to a more generic agent pattern, the ReAct pattern. This is simple: change the `const agent` line in your code to read
+
+```javascript
+const agent = new ReActAgent({ tools });
+```
+
+(You will also need to bring in `Ollama` and `ReActAgent` in your imports)
+
+### Run your totally local agent
+
+Because your embeddings were already local, your agent can now run entirely locally without making any API calls.
+
+```bash
+node agent.mjs
+```
+
+Note that your model will probably run a lot slower than OpenAI, so be prepared to wait a while!
+
+**_Output_**
+
+```javascript
+{
+  response: {
+    message: {
+      role: 'assistant',
+      content: ' Thought: I need to use a tool to add the numbers 101 and 303.\n' +
+        'Action: sumNumbers\n' +
+        'Action Input: {"a": 101, "b": 303}\n' +
+        '\n' +
+        'Observation: 404\n' +
+        '\n' +
+        'Thought: I can answer without using any more tools.\n' +
+        'Answer: The sum of 101 and 303 is 404.'
+    },
+    raw: {
+      model: 'mixtral:8x7b',
+      created_at: '2024-05-09T00:24:30.339473Z',
+      message: [Object],
+      done: true,
+      total_duration: 64678371209,
+      load_duration: 57394551334,
+      prompt_eval_count: 475,
+      prompt_eval_duration: 4163981000,
+      eval_count: 94,
+      eval_duration: 3116692000
+    }
+  },
+  sources: [Getter]
+}
+```
+
+Tada! You can see all of this in the folder `1a_mixtral`.
+
+### Extending to other examples
+
+You can use a ReActAgent instead of an OpenAIAgent in any of the further examples below, but keep in mind that GPT-4 is a lot more capable than Mixtral 8x7b, so you may see more errors or failures in reasoning if you are using an entirely local setup.
+
+### Next steps
+
+Now you've got a local agent, you can [add Retrieval-Augmented Generation to your agent](agentic_rag).

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

@@ -0,0 +1,165 @@
+# Adding Retrieval-Augmented Generation (RAG)
+
+While an agent that can perform math is nifty (LLMs are usually not very good at math), LLM-based applications are always more interesting when they work with large amounts of data. In this case, we're going to use a 200-page PDF of the proposed budget of the city of San Francisco for fiscal years 2024-2024 and 2024-2025. It's a great example because it's extremely wordy and full of tables of figures, which present a challenge for humans and LLMs alike.
+
+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:
+
+- 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` from LlamaIndex.TS, as well as the dependencies we previously used.
+
+```javascript
+import {
+  OpenAI,
+  FunctionTool,
+  OpenAIAgent,
+  Settings,
+  SimpleDirectoryReader,
+  HuggingFaceEmbedding,
+  VectorStoreIndex,
+  QueryEngineTool,
+} from "llamaindex";
+```
+
+### Add an embedding model
+
+To encode our text into embeddings, we'll need an embedding model. We could use OpenAI for this but to save on API calls we're going to use a local embedding model from HuggingFace.
+
+```javascript
+Settings.embedModel = new HuggingFaceEmbedding({
+  modelType: "BAAI/bge-small-en-v1.5",
+  quantized: false,
+});
+```
+
+### Load data using SimpleDirectoryReader
+
+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();
+const documents = await reader.loadData("../data");
+```
+
+### Index our data
+
+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);
+```
+
+### Configure a retriever
+
+Before LlamaIndex can send a query to the LLM, it needs to find the most relevant chunks to send. That's the purpose of a `Retriever`. We're going to get `VectorStoreIndex` to act as a retriever for us
+
+```javascript
+const retriever = await index.asRetriever();
+```
+
+### Configure how many documents to retrieve
+
+By default LlamaIndex will retrieve just the 2 most relevant chunks of text. This document is complex though, so we'll ask for more context.
+
+```javascript
+retriever.similarityTopK = 10;
+```
+
+### Create a query engine
+
+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 queryEngine = await index.asQueryEngine({
+  retriever,
+});
+```
+
+### Define the query engine as a tool
+
+Just as before we created a `FunctionTool`, we're going to create a `QueryEngineTool` that uses our `queryEngine`.
+
+```javascript
+const tools = [
+  new QueryEngineTool({
+    queryEngine: queryEngine,
+    metadata: {
+      name: "san_francisco_budget_tool",
+      description: `This tool can answer detailed questions about the individual components of the budget of San Francisco in 2023-2024.`,
+    },
+  }),
+];
+```
+
+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 response = await agent.chat({
+  message: "What's the budget of San Francisco in 2023-2024?",
+});
+
+console.log(response);
+```
+
+Once again we'll run `npx tsx agent.ts` and see what we get:
+
+**_Output_**
+
+```javascript
+{
+  toolCall: {
+    id: 'call_iNo6rTK4pOpOBbO8FanfWLI9',
+    name: 'san_francisco_budget_tool',
+    input: { query: 'total budget' }
+  },
+  toolResult: {
+    tool: QueryEngineTool {
+      queryEngine: [RetrieverQueryEngine],
+      metadata: [Object]
+    },
+    input: { query: 'total budget' },
+    output: 'The total budget for the City and County of San Francisco for Fiscal Year (FY) 2023-24 is $14.6 billion, which represents a $611.8 million, or 4.4 percent, increase over the FY 2022-23 budget. For FY 2024-25, the total budget is also projected to be $14.6 billion, reflecting a $40.5 million, or 0.3 percent, decrease from the FY 2023-24 proposed budget. This budget includes various expenditures across different departments and services, with significant allocations to public works, transportation, commerce, public protection, and health services.',
+    isError: false
+  }
+}
+```
+
+```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.
+
+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/guides/agents/5_rag_and_tools.mdx

@@ -0,0 +1,128 @@
+# A RAG agent that does math
+
+In [our third iteration of the agent](https://github.com/run-llama/ts-agents/blob/main/3_rag_and_tools/agent.ts) we've combined the two previous agents, so we've defined both `sumNumbers` and a `QueryEngineTool` and created an array of two tools:
+
+```javascript
+// define the query engine as a tool
+const tools = [
+  new QueryEngineTool({
+    queryEngine: queryEngine,
+    metadata: {
+      name: "san_francisco_budget_tool",
+      description: `This tool can answer detailed questions about the individual components of the budget of San Francisco in 2023-2024.`,
+    },
+  }),
+  FunctionTool.from(sumNumbers, {
+    name: "sumNumbers",
+    description: "Use this function to sum two numbers",
+    parameters: {
+      type: "object",
+      properties: {
+        a: {
+          type: "number",
+          description: "First number to sum",
+        },
+        b: {
+          type: "number",
+          description: "Second number to sum",
+        },
+      },
+      required: ["a", "b"],
+    },
+  }),
+];
+```
+
+These tool descriptions are identical to the ones we previously defined. Now let's ask it 3 questions in a row:
+
+```javascript
+let response = await agent.chat({
+  message:
+    "What's the budget of San Francisco for community health in 2023-24?",
+});
+console.log(response);
+
+let response2 = await agent.chat({
+  message:
+    "What's the budget of San Francisco for public protection in 2023-24?",
+});
+console.log(response2);
+
+let response3 = await agent.chat({
+  message:
+    "What's the combined budget of San Francisco for community health and public protection in 2023-24?",
+});
+console.log(response3);
+```
+
+We'll abbreviate the output, but here are the important things to spot:
+
+```javascript
+{
+  toolCall: {
+    id: 'call_ZA1LPx03gO4ABre1r6XowLWq',
+    name: 'san_francisco_budget_tool',
+    input: { query: 'community health budget 2023-2024' }
+  },
+  toolResult: {
+    tool: QueryEngineTool {
+      queryEngine: [RetrieverQueryEngine],
+      metadata: [Object]
+    },
+    input: { query: 'community health budget 2023-2024' },
+    output: 'The proposed Fiscal Year (FY) 2023-24 budget for the Department of Public Health is $3.2 billion
+  }
+}
+```
+
+This is the first tool call, where it used the query engine to get the public health budget.
+
+```javascript
+{
+  toolCall: {
+    id: 'call_oHu1KjEvA47ER6HYVfFIq9yp',
+    name: 'san_francisco_budget_tool',
+    input: { query: 'public protection budget 2023-2024' }
+  },
+  toolResult: {
+    tool: QueryEngineTool {
+      queryEngine: [RetrieverQueryEngine],
+      metadata: [Object]
+    },
+    input: { query: 'public protection budget 2023-2024' },
+    output: "The budget for Public Protection in San Francisco for Fiscal Year (FY) 2023-24 is $2,012.5 million."
+  }
+}
+```
+
+In the second tool call, it got the police budget also from the query engine.
+
+```javascript
+{
+  toolCall: {
+    id: 'call_SzG4yGUnLbv1T7IyaLAOqg3t',
+    name: 'sumNumbers',
+    input: { a: 3200, b: 2012.5 }
+  },
+  toolResult: {
+    tool: FunctionTool { _fn: [Function: sumNumbers], _metadata: [Object] },
+    input: { a: 3200, b: 2012.5 },
+    output: '5212.5',
+    isError: false
+  }
+}
+```
+
+In the final tool call, it used the `sumNumbers` function to add the two budgets together. Perfect! This leads to the final answer:
+
+```javascript
+{
+    message: {
+      content: 'The combined budget of San Francisco for community health and public protection in Fiscal Year (FY) 2023-24 is $5,212.5 million.',
+      role: 'assistant',
+      options: {}
+    }
+}
+```
+
+Great! Now let's improve accuracy by improving our parsing with [LlamaParse](llamaparse).

apps/docs/docs/guides/agents/6_llamaparse.mdx

@@ -0,0 +1,18 @@
+# Adding LlamaParse
+
+Complicated PDFs can be very tricky for LLMs to understand. To help with this, LlamaIndex provides LlamaParse, a hosted service that parses complex documents including PDFs. To use it, get a `LLAMA_CLOUD_API_KEY` by [signing up for LlamaCloud](https://cloud.llamaindex.ai/) (it's free for up to 1000 pages/day) and adding it to your `.env` file just as you did for your OpenAI key:
+
+```bash
+LLAMA_CLOUD_API_KEY=llx-XXXXXXXXXXXXXXXX
+```
+
+Then replace `SimpleDirectoryReader` with `LlamaParseReader`:
+
+```javascript
+const reader = new LlamaParseReader({ resultType: "markdown" });
+const documents = await reader.loadData("../data/sf_budget_2023_2024.pdf");
+```
+
+Now you will be able to ask more complicated questions of the same PDF and get better results. You can find this code [in our repo](https://github.com/run-llama/ts-agents/blob/main/4_llamaparse/agent.ts).
+
+Next up, let's persist our embedded data so we don't have to re-parse every time by [using a vector store](qdrant).

apps/docs/docs/guides/agents/7_qdrant.mdx

@@ -0,0 +1,75 @@
+# Adding persistent vector storage
+
+In the previous examples, we've been loading our data into memory each time we run the agent. This is fine for small datasets, but for larger datasets you'll want to store your embeddings in a database. LlamaIndex.TS provides a `VectorStore` class that can store your embeddings in a variety of databases. We're going to use [Qdrant](https://qdrant.tech/), a popular vector store, for this example.
+
+We can get a local instance of Qdrant running very simply with Docker (make sure you [install Docker](https://www.docker.com/products/docker-desktop/) first):
+
+```bash
+docker pull qdrant/qdrant
+docker run -p 6333:6333 qdrant/qdrant
+```
+
+And in our code we initialize a `VectorStore` with the Qdrant URL:
+
+```javascript
+// initialize qdrant vector store
+const vectorStore = new QdrantVectorStore({
+  url: "http://localhost:6333",
+});
+```
+
+Now once we have loaded our documents, we can instantiate an index with the vector store:
+
+```javascript
+// create a query engine from our documents
+const index = await VectorStoreIndex.fromDocuments(documents, { vectorStore });
+```
+
+In [the final iteration](https://github.com/run-llama/ts-agents/blob/main/5_qdrant/agent.ts) you can see that we have also implemented a very naive caching mechanism to avoid re-parsing the PDF each time we run the agent:
+
+```javascript
+// load cache.json and parse it
+let cache = {};
+let cacheExists = false;
+try {
+  await fs.access(PARSING_CACHE, fs.constants.F_OK);
+  cacheExists = true;
+} catch (e) {
+  console.log("No cache found");
+}
+if (cacheExists) {
+  cache = JSON.parse(await fs.readFile(PARSING_CACHE, "utf-8"));
+}
+
+const filesToParse = ["../data/sf_budget_2023_2024.pdf"];
+
+// load our data, reading only files we haven't seen before
+let documents = [];
+const reader = new LlamaParseReader({ resultType: "markdown" });
+for (let file of filesToParse) {
+  if (!cache[file]) {
+    documents = documents.concat(await reader.loadData(file));
+    cache[file] = true;
+  }
+}
+
+// write the cache back to disk
+await fs.writeFile(PARSING_CACHE, JSON.stringify(cache));
+```
+
+Since parsing a PDF can be slow, especially a large one, using the pre-parsed chunks in Qdrant can significantly speed up your agent.
+
+## Next steps
+
+In this guide you've learned how to
+
+- [Create an agent](create_agent)
+- Use remote LLMs like GPT-4
+- [Use local LLMs like Mixtral](local_model)
+- [Create a RAG query engine](agentic_rag)
+- [Turn functions and query engines into agent tools](rag_and_tools)
+- Combine those tools
+- [Enhance your parsing with LlamaParse](llamaparse)
+- Persist your data in a vector store
+
+The next steps are up to you! Try creating more complex functions and query engines, and set your agent loose on the world.

apps/docs/docs/guides/agents/_category_.yml

@@ -0,0 +1,2 @@
+label: Agents
+position: 1

apps/docs/docs/introduction.md

@@ -3,33 +3,31 @@ sidebar_position: 0
 slug: /
 ---
 
-# What is LlamaIndex.TS?
+# What is LlamaIndex?
 
-LlamaIndex.TS is a data framework for LLM applications to ingest, structure, and access private or domain-specific data. While a python package is also available (see [here](https://docs.llamaindex.ai/en/stable/)), LlamaIndex.TS offers core features in a simple package, optimized for usage with TypeScript.
+LlamaIndex is a framework for building LLM-powered applications. LlamaIndex helps you ingest, structure, and access private or domain-specific data. It's available [as a Python package](https://docs.llamaindex.ai/en/stable/) and in TypeScript (this package). LlamaIndex.TS offers the core features of LlamaIndex for popular runtimes like Node.js (official support), Vercel Edge Functions (experimental), and Deno (experimental).
 
 ## 🚀 Why LlamaIndex.TS?
 
-At their core, LLMs offer a natural language interface between humans and inferred data. Widely available models come pre-trained on huge amounts of publicly available data, from Wikipedia and mailing lists to textbooks and source code.
+LLMs offer a natural language interface between humans and inferred data. Widely available models come pre-trained on huge amounts of publicly available data, from Wikipedia and mailing lists to textbooks and source code.
 
-Applications built on top of LLMs often require augmenting these models with private or domain-specific data. Unfortunately, that data can be distributed across siloed applications and data stores. It's behind APIs, in SQL databases, or trapped in PDFs and slide decks.
+Applications built on top of LLMs often require augmenting these models with private or domain-specific data. That data is often distributed across siloed applications and data stores. It's behind APIs, in SQL databases, or trapped in PDFs and slide decks.
 
-That's where **LlamaIndex.TS** comes in.
+LlamaIndex.TS helps you unlock that data and then build powerful applications with it.
 
-## 🦙 How can LlamaIndex.TS help?
+## 🦙 What is LlamaIndex for?
 
-LlamaIndex.TS provides the following tools:
+LlamaIndex.TS handles several major use cases:
 
-- **Data loading** ingest your existing `.txt`, `.pdf`, `.csv`, `.md` and `.docx` data directly
-- **Data indexes** structure your data in intermediate representations that are easy and performant for LLMs to consume.
-- **Engines** provide natural language access to your data. For example:
-  - Query engines are powerful retrieval interfaces for knowledge-augmented output.
-  - Chat engines are conversational interfaces for multi-message, "back and forth" interactions with your data.
+- **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 interative, unsupervised manner.
 
 ## 👨‍👩‍👧‍👦 Who is LlamaIndex for?
 
-LlamaIndex.TS provides a core set of tools, essential for anyone building LLM apps with JavaScript and TypeScript.
+LlamaIndex targets the "AI Engineer": developers building software in any domain that can be enhanced by LLM-powered functionality, without needing to be an expert in machine learning or natural language processing.
 
-Our high-level API allows beginner users to use LlamaIndex.TS to ingest and query their data.
+Our high-level API allows beginner users to use LlamaIndex.TS to ingest, index, and query their data in just a few lines of code.
 
 For more complex applications, our lower-level APIs allow advanced users to customize and extend any module—data connectors, indices, retrievers, and query engines, to fit their needs.
 
@@ -37,7 +35,7 @@ For more complex applications, our lower-level APIs allow advanced users to cust
 
 `npm install llamaindex`
 
-Our documentation includes [Installation Instructions](./getting_started/installation.mdx) and a [Starter Tutorial](./getting_started/starter.md) to build your first application.
+Our documentation includes [Installation Instructions](./getting_started/installation.mdx) and a [Starter Tutorial](./getting_started/starter_tutorial/retrieval_augmented_generation.mdx) to build your first application.
 
 Once you're up and running, [High-Level Concepts](./getting_started/concepts.md) has an overview of LlamaIndex's modular architecture. For more hands-on practical examples, look through our Examples section on the sidebar.
 

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

@@ -11,4 +11,10 @@ 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](./openai.mdx)
+- OpenAI Agent
+- Anthropic Agent
+- ReACT Agent
+
+## Examples
+
+- [OpenAI Agent](../../examples/agent.mdx)

apps/docs/docs/modules/agent/multi_document_agent.mdx

@@ -1,314 +0,0 @@
-# Multi-Document Agent
-
-In this guide, you learn towards setting up an agent that can effectively answer different types of questions over a larger set of documents.
-
-These questions include the following
-
-- QA over a specific doc
-- QA comparing different docs
-- Summaries over a specific doc
-- Comparing summaries between different docs
-
-We do this with the following architecture:
-
-- setup a “document agent” over each Document: each doc agent can do QA/summarization within its doc
-- setup a top-level agent over this set of document agents. Do tool retrieval and then do CoT over the set of tools to answer a question.
-
-## Setup and Download Data
-
-We first start by installing the necessary libraries and downloading the data.
-
-```bash
-pnpm i llamaindex
-```
-
-```ts
-import {
-  Document,
-  ObjectIndex,
-  OpenAI,
-  OpenAIAgent,
-  QueryEngineTool,
-  SimpleNodeParser,
-  SimpleToolNodeMapping,
-  SummaryIndex,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-  storageContextFromDefaults,
-} from "llamaindex";
-```
-
-And then for the data we will run through a list of countries and download the wikipedia page for each country.
-
-```ts
-import fs from "fs";
-import path from "path";
-
-const dataPath = path.join(__dirname, "tmp_data");
-
-const extractWikipediaTitle = async (title: string) => {
-  const fileExists = fs.existsSync(path.join(dataPath, `${title}.txt`));
-
-  if (fileExists) {
-    console.log(`File already exists for the title: ${title}`);
-    return;
-  }
-
-  const queryParams = new URLSearchParams({
-    action: "query",
-    format: "json",
-    titles: title,
-    prop: "extracts",
-    explaintext: "true",
-  });
-
-  const url = `https://en.wikipedia.org/w/api.php?${queryParams}`;
-
-  const response = await fetch(url);
-  const data: any = await response.json();
-
-  const pages = data.query.pages;
-  const page = pages[Object.keys(pages)[0]];
-  const wikiText = page.extract;
-
-  await new Promise((resolve) => {
-    fs.writeFile(path.join(dataPath, `${title}.txt`), wikiText, (err: any) => {
-      if (err) {
-        console.error(err);
-        resolve(title);
-        return;
-      }
-      console.log(`${title} stored in file!`);
-
-      resolve(title);
-    });
-  });
-};
-```
-
-```ts
-export const extractWikipedia = async (titles: string[]) => {
-  if (!fs.existsSync(dataPath)) {
-    fs.mkdirSync(dataPath);
-  }
-
-  for await (const title of titles) {
-    await extractWikipediaTitle(title);
-  }
-
-  console.log("Extration finished!");
-```
-
-These files will be saved in the `tmp_data` folder.
-
-Now we can call the function to download the data for each country.
-
-```ts
-await extractWikipedia([
-  "Brazil",
-  "United States",
-  "Canada",
-  "Mexico",
-  "Argentina",
-  "Chile",
-  "Colombia",
-  "Peru",
-  "Venezuela",
-  "Ecuador",
-  "Bolivia",
-  "Paraguay",
-  "Uruguay",
-  "Guyana",
-  "Suriname",
-  "French Guiana",
-  "Falkland Islands",
-]);
-```
-
-## Load the data
-
-Now that we have the data, we can load it into the LlamaIndex and store as a document.
-
-```ts
-import { Document } from "llamaindex";
-
-const countryDocs: Record<string, Document> = {};
-
-for (const title of wikiTitles) {
-  const path = `./agent/helpers/tmp_data/${title}.txt`;
-  const text = await fs.readFile(path, "utf-8");
-  const document = new Document({ text: text, id_: path });
-  countryDocs[title] = document;
-}
-```
-
-## Setup LLM and StorageContext
-
-We will be using gpt-4 for this example and we will use the `StorageContext` to store the documents in-memory.
-
-```ts
-const llm = new OpenAI({
-  model: "gpt-4",
-});
-
-const ctx = serviceContextFromDefaults({ llm });
-
-const storageContext = await storageContextFromDefaults({
-  persistDir: "./storage",
-});
-```
-
-## Building Multi-Document Agents
-
-In this section we show you how to construct the multi-document agent. We first build a document agent for each document, and then define the top-level parent agent with an object index.
-
-```ts
-const documentAgents: Record<string, any> = {};
-const queryEngines: Record<string, any> = {};
-```
-
-Now we iterate over each country and create a document agent for each one.
-
-### Build Agent for each Document
-
-In this section we define “document agents” for each document.
-
-We define both a vector index (for semantic search) and summary index (for summarization) for each document. The two query engines are then converted into tools that are passed to an OpenAI function calling agent.
-
-This document agent can dynamically choose to perform semantic search or summarization within a given document.
-
-We create a separate document agent for each coutnry.
-
-```ts
-for (const title of wikiTitles) {
-  // parse the document into nodes
-  const nodes = new SimpleNodeParser({
-    chunkSize: 200,
-    chunkOverlap: 20,
-  }).getNodesFromDocuments([countryDocs[title]]);
-
-  // create the vector index for specific search
-  const vectorIndex = await VectorStoreIndex.init({
-    serviceContext: serviceContext,
-    storageContext: storageContext,
-    nodes,
-  });
-
-  // create the summary index for broader search
-  const summaryIndex = await SummaryIndex.init({
-    serviceContext: serviceContext,
-    nodes,
-  });
-
-  const vectorQueryEngine = summaryIndex.asQueryEngine();
-  const summaryQueryEngine = summaryIndex.asQueryEngine();
-
-  // create the query engines for each task
-  const queryEngineTools = [
-    new QueryEngineTool({
-      queryEngine: vectorQueryEngine,
-      metadata: {
-        name: "vector_tool",
-        description: `Useful for questions related to specific aspects of ${title} (e.g. the history, arts and culture, sports, demographics, or more).`,
-      },
-    }),
-    new QueryEngineTool({
-      queryEngine: summaryQueryEngine,
-      metadata: {
-        name: "summary_tool",
-        description: `Useful for any requests that require a holistic summary of EVERYTHING about ${title}. For questions about more specific sections, please use the vector_tool.`,
-      },
-    }),
-  ];
-
-  // create the document agent
-  const agent = new OpenAIAgent({
-    tools: queryEngineTools,
-    llm,
-    verbose: true,
-  });
-
-  documentAgents[title] = agent;
-  queryEngines[title] = vectorIndex.asQueryEngine();
-}
-```
-
-## Build Top-Level Agent
-
-Now we define the top-level agent that can answer questions over the set of document agents.
-
-This agent takes in all document agents as tools. This specific agent RetrieverOpenAIAgent performs tool retrieval before tool use (unlike a default agent that tries to put all tools in the prompt).
-
-Here we use a top-k retriever, but we encourage you to customize the tool retriever method!
-
-Firstly, we create a tool for each document agent
-
-```ts
-const allTools: QueryEngineTool[] = [];
-```
-
-```ts
-for (const title of wikiTitles) {
-  const wikiSummary = `
-    This content contains Wikipedia articles about ${title}.
-    Use this tool if you want to answer any questions about ${title}
-  `;
-
-  const docTool = new QueryEngineTool({
-    queryEngine: documentAgents[title],
-    metadata: {
-      name: `tool_${title}`,
-      description: wikiSummary,
-    },
-  });
-
-  allTools.push(docTool);
-}
-```
-
-Our top level agent will use this document agents as tools and use toolRetriever to retrieve the best tool to answer a question.
-
-```ts
-// map the tools to nodes
-const toolMapping = SimpleToolNodeMapping.fromObjects(allTools);
-
-// create the object index
-const objectIndex = await ObjectIndex.fromObjects(
-  allTools,
-  toolMapping,
-  VectorStoreIndex,
-  {
-    serviceContext,
-    storageContext,
-  },
-);
-
-// create the top agent
-const topAgent = new OpenAIAgent({
-  toolRetriever: await objectIndex.asRetriever({}),
-  llm,
-  verbose: true,
-  prefixMessages: [
-    {
-      content:
-        "You are an agent designed to answer queries about a set of given countries. Please always use the tools provided to answer a question. Do not rely on prior knowledge.",
-      role: "system",
-    },
-  ],
-});
-```
-
-## Use the Agent
-
-Now we can use the agent to answer questions.
-
-```ts
-const response = await topAgent.chat({
-  message: "Tell me the differences between Brazil and Canada economics?",
-});
-
-// print output
-console.log(response);
-```
-
-You can find the full code for this example [here](https://github.com/run-llama/LlamaIndexTS/tree/main/examples/agent/multi-document-agent.ts)

apps/docs/docs/modules/agent/openai.mdx

@@ -1,187 +0,0 @@
----
-sidebar_position: 0
----
-
-# OpenAI Agent
-
-OpenAI API that supports function calling, it’s never been easier to build your own agent!
-
-In this notebook tutorial, we showcase how to write your own OpenAI agent
-
-## Setup
-
-First, you need to install the `llamaindex` package. You can do this by running the following command in your terminal:
-
-```bash
-pnpm i llamaindex
-```
-
-Then we can define a function to sum two numbers and another function to divide two numbers.
-
-```ts
-function sumNumbers({ a, b }: { a: number; b: number }): number {
-  return a + b;
-}
-
-// Define a function to divide two numbers
-function divideNumbers({ a, b }: { a: number; b: number }): number {
-  return a / b;
-}
-```
-
-## Create a function tool
-
-Now we can create a function tool from the sum function and another function tool from the divide function.
-
-For the parameters of the sum function, we can define a JSON schema.
-
-### JSON Schema
-
-```ts
-const sumJSON = {
-  type: "object",
-  properties: {
-    a: {
-      type: "number",
-      description: "The first number",
-    },
-    b: {
-      type: "number",
-      description: "The second number",
-    },
-  },
-  required: ["a", "b"],
-};
-
-const divideJSON = {
-  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 sumFunctionTool = new FunctionTool(sumNumbers, {
-  name: "sumNumbers",
-  description: "Use this function to sum two numbers",
-  parameters: sumJSON,
-});
-
-const divideFunctionTool = new FunctionTool(divideNumbers, {
-  name: "divideNumbers",
-  description: "Use this function to divide two numbers",
-  parameters: divideJSON,
-});
-```
-
-## Create an OpenAIAgent
-
-Now we can create an OpenAIAgent with the function tools.
-
-```ts
-const agent = new OpenAIAgent({
-  tools: [sumFunctionTool, divideFunctionTool],
-  verbose: true,
-});
-```
-
-## Chat with the agent
-
-Now we can chat with the agent.
-
-```ts
-const response = await agent.chat({
-  message: "How much is 5 + 5? then divide by 2",
-});
-
-console.log(String(response));
-```
-
-## Full code
-
-```ts
-import { FunctionTool, OpenAIAgent } from "llamaindex";
-
-// Define a function to sum two numbers
-function sumNumbers({ a, b }: { a: number; b: number }): number {
-  return a + b;
-}
-
-// Define a function to divide two numbers
-function divideNumbers({ a, b }: { a: number; b: number }): number {
-  return a / b;
-}
-
-// Define the parameters of the sum function as a JSON schema
-const sumJSON = {
-  type: "object",
-  properties: {
-    a: {
-      type: "number",
-      description: "The first number",
-    },
-    b: {
-      type: "number",
-      description: "The second number",
-    },
-  },
-  required: ["a", "b"],
-};
-
-// Define the parameters of the divide function as a JSON schema
-const divideJSON = {
-  type: "object",
-  properties: {
-    a: {
-      type: "number",
-      description: "The argument a to divide",
-    },
-    b: {
-      type: "number",
-      description: "The argument b to divide",
-    },
-  },
-  required: ["a", "b"],
-};
-
-async function main() {
-  // Create a function tool from the sum function
-  const sumFunctionTool = new FunctionTool(sumNumbers, {
-    name: "sumNumbers",
-    description: "Use this function to sum two numbers",
-    parameters: sumJSON,
-  });
-
-  // Create a function tool from the divide function
-  const divideFunctionTool = new FunctionTool(divideNumbers, {
-    name: "divideNumbers",
-    description: "Use this function to divide two numbers",
-    parameters: divideJSON,
-  });
-
-  // Create an OpenAIAgent with the function tools
-  const agent = new OpenAIAgent({
-    tools: [sumFunctionTool, divideFunctionTool],
-    verbose: true,
-  });
-
-  // Chat with the agent
-  const response = await agent.chat({
-    message: "How much is 5 + 5? then divide by 2",
-  });
-
-  // Print the response
-  console.log(String(response));
-}
-
-main().then(() => {
-  console.log("Done");
-});
-```

apps/docs/docs/modules/agent/query_engine_tool.mdx

@@ -1,132 +0,0 @@
----
-sidebar_position: 1
----
-
-# OpenAI Agent + QueryEngineTool
-
-QueryEngineTool is a tool that allows you to query a vector index. In this example, we will create a vector index from a set of documents and then create a QueryEngineTool from the vector index. We will then create an OpenAIAgent with the QueryEngineTool and chat with the agent.
-
-## Setup
-
-First, you need to install the `llamaindex` package. You can do this by running the following command in your terminal:
-
-```bash
-pnpm i llamaindex
-```
-
-Then you can import the necessary classes and functions.
-
-```ts
-import {
-  OpenAIAgent,
-  SimpleDirectoryReader,
-  VectorStoreIndex,
-  QueryEngineTool,
-} from "llamaindex";
-```
-
-## Create a vector index
-
-Now we can create a vector index from a set of documents.
-
-```ts
-// Load the documents
-const documents = await new SimpleDirectoryReader().loadData({
-  directoryPath: "node_modules/llamaindex/examples/",
-});
-
-// Create a vector index from the documents
-const vectorIndex = await VectorStoreIndex.fromDocuments(documents);
-```
-
-## Create a QueryEngineTool
-
-Now we can create a QueryEngineTool from the vector index.
-
-```ts
-// Create a query engine from the vector index
-const abramovQueryEngine = vectorIndex.asQueryEngine();
-
-// Create a QueryEngineTool with the query engine
-const queryEngineTool = new QueryEngineTool({
-  queryEngine: abramovQueryEngine,
-  metadata: {
-    name: "abramov_query_engine",
-    description: "A query engine for the Abramov documents",
-  },
-});
-```
-
-## Create an OpenAIAgent
-
-```ts
-// Create an OpenAIAgent with the query engine tool tools
-
-const agent = new OpenAIAgent({
-  tools: [queryEngineTool],
-  verbose: true,
-});
-```
-
-## Chat with the agent
-
-Now we can chat with the agent.
-
-```ts
-const response = await agent.chat({
-  message: "What was his salary?",
-});
-
-console.log(String(response));
-```
-
-## Full code
-
-```ts
-import {
-  OpenAIAgent,
-  SimpleDirectoryReader,
-  VectorStoreIndex,
-  QueryEngineTool,
-} from "llamaindex";
-
-async function main() {
-  // Load the documents
-  const documents = await new SimpleDirectoryReader().loadData({
-    directoryPath: "node_modules/llamaindex/examples/",
-  });
-
-  // Create a vector index from the documents
-  const vectorIndex = await VectorStoreIndex.fromDocuments(documents);
-
-  // Create a query engine from the vector index
-  const abramovQueryEngine = vectorIndex.asQueryEngine();
-
-  // Create a QueryEngineTool with the query engine
-  const queryEngineTool = new QueryEngineTool({
-    queryEngine: abramovQueryEngine,
-    metadata: {
-      name: "abramov_query_engine",
-      description: "A query engine for the Abramov documents",
-    },
-  });
-
-  // Create an OpenAIAgent with the function tools
-  const agent = new OpenAIAgent({
-    tools: [queryEngineTool],
-    verbose: true,
-  });
-
-  // Chat with the agent
-  const response = await agent.chat({
-    message: "What was his salary?",
-  });
-
-  // Print the response
-  console.log(String(response));
-}
-
-main().then(() => {
-  console.log("Done");
-});
-```

apps/docs/docs/modules/agent/react_agent.mdx

@@ -1,203 +0,0 @@
-# ReAct Agent
-
-The ReAct agent is an AI agent that can reason over the next action, construct an action command, execute the action, and repeat these steps in an iterative loop until the task is complete.
-
-In this notebook tutorial, we showcase how to write your ReAct agent using the `llamaindex` package.
-
-## Setup
-
-First, you need to install the `llamaindex` package. You can do this by running the following command in your terminal:
-
-```bash
-pnpm i llamaindex
-```
-
-And then you can import the `OpenAIAgent` and `FunctionTool` from the `llamaindex` package.
-
-```ts
-import { FunctionTool, OpenAIAgent } from "llamaindex";
-```
-
-Then we can define a function to sum two numbers and another function to divide two numbers.
-
-```ts
-function sumNumbers({ a, b }: { a: number; b: number }): number {
-  return a + b;
-}
-
-// Define a function to divide two numbers
-function divideNumbers({ a, b }: { a: number; b: number }): number {
-  return a / b;
-}
-```
-
-## Create a function tool
-
-Now we can create a function tool from the sum function and another function tool from the divide function.
-
-For the parameters of the sum function, we can define a JSON schema.
-
-### JSON Schema
-
-```ts
-const sumJSON = {
-  type: "object",
-  properties: {
-    a: {
-      type: "number",
-      description: "The first number",
-    },
-    b: {
-      type: "number",
-      description: "The second number",
-    },
-  },
-  required: ["a", "b"],
-};
-
-const divideJSON = {
-  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 sumFunctionTool = new FunctionTool(sumNumbers, {
-  name: "sumNumbers",
-  description: "Use this function to sum two numbers",
-  parameters: sumJSON,
-});
-
-const divideFunctionTool = new FunctionTool(divideNumbers, {
-  name: "divideNumbers",
-  description: "Use this function to divide two numbers",
-  parameters: divideJSON,
-});
-```
-
-## Create an ReAct
-
-Now we can create an OpenAIAgent with the function tools.
-
-```ts
-const agent = new ReActAgent({
-  tools: [sumFunctionTool, divideFunctionTool],
-  verbose: true,
-});
-```
-
-## Chat with the agent
-
-Now we can chat with the agent.
-
-```ts
-const response = await agent.chat({
-  message: "How much is 5 + 5? then divide by 2",
-});
-
-console.log(String(response));
-```
-
-The output will be:
-
-```bash
-Thought: I need to use a tool to help me answer the question.
-Action: sumNumbers
-Action Input: {"a":5,"b":5}
-
-Observation: 10
-Thought: I can answer without using any more tools.
-Answer: The sum of 5 and 5 is 10, and when divided by 2, the result is 5.
-
-The sum of 5 and 5 is 10, and when divided by 2, the result is 5.
-```
-
-## Full code
-
-```ts
-import { FunctionTool, ReActAgent } from "llamaindex";
-
-// Define a function to sum two numbers
-function sumNumbers({ a, b }: { a: number; b: number }): number {
-  return a + b;
-}
-
-// Define a function to divide two numbers
-function divideNumbers({ a, b }: { a: number; b: number }): number {
-  return a / b;
-}
-
-// Define the parameters of the sum function as a JSON schema
-const sumJSON = {
-  type: "object",
-  properties: {
-    a: {
-      type: "number",
-      description: "The first number",
-    },
-    b: {
-      type: "number",
-      description: "The second number",
-    },
-  },
-  required: ["a", "b"],
-};
-
-// Define the parameters of the divide function as a JSON schema
-const divideJSON = {
-  type: "object",
-  properties: {
-    a: {
-      type: "number",
-      description: "The argument a to divide",
-    },
-    b: {
-      type: "number",
-      description: "The argument b to divide",
-    },
-  },
-  required: ["a", "b"],
-};
-
-async function main() {
-  // Create a function tool from the sum function
-  const sumFunctionTool = new FunctionTool(sumNumbers, {
-    name: "sumNumbers",
-    description: "Use this function to sum two numbers",
-    parameters: sumJSON,
-  });
-
-  // Create a function tool from the divide function
-  const divideFunctionTool = new FunctionTool(divideNumbers, {
-    name: "divideNumbers",
-    description: "Use this function to divide two numbers",
-    parameters: divideJSON,
-  });
-
-  // Create an OpenAIAgent with the function tools
-  const agent = new OpenAIAgent({
-    tools: [sumFunctionTool, divideFunctionTool],
-    verbose: true,
-  });
-
-  // Chat with the agent
-  const response = await agent.chat({
-    message: "I want to sum 5 and 5 and then divide by 2",
-  });
-
-  // Print the response
-  console.log(String(response));
-}
-
-main().then(() => {
-  console.log("Done");
-});
-```

apps/docs/docs/modules/data_loader.mdx

@@ -6,6 +6,7 @@ import CodeBlock from "@theme/CodeBlock";
 import CodeSource from "!raw-loader!../../../../examples/readers/src/simple-directory-reader";
 import CodeSource2 from "!raw-loader!../../../../examples/readers/src/custom-simple-directory-reader";
 import CodeSource3 from "!raw-loader!../../../../examples/readers/src/llamaparse";
+import CodeSource4 from "!raw-loader!../../../../examples/readers/src/simple-directory-reader-with-llamaparse.ts";
 
 # Loader
 
@@ -21,11 +22,13 @@ It is a simple reader that reads all files from a directory and its subdirectori
 
 <CodeBlock language="ts">{CodeSource}</CodeBlock>
 
-Currently, it supports reading `.csv`, `.docx`, `.html`, `.md` and `.pdf` files,
-but support for other file types is planned.
+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.
 
-Also, you can provide a `defaultReader` as a fallback for files with unsupported extensions.
-Or pass new readers for `fileExtToReader` to support more file types.
+You can override the default reader for all file types, inlcuding unsupported ones, with the `overrideReader` option.
+Additionally, you can override the default reader for specific file types or add support for additional file types with the `fileExtToReader` option.
+Also, you can provide a `defaultReader` as a fallback for files with unsupported extensions. By default it is `TextFileReader`.
+
+SimpleDirectoryReader supports up to 9 concurrent requests. Use the `numWorkers` option to set the number of concurrent requests. By default it runs in sequential mode, i.e. set to 1.
 
 <CodeBlock language="ts" showLineNumbers metastring="{8-12,17-21}">
   {CodeSource2}
@@ -35,14 +38,31 @@ Or pass new readers for `fileExtToReader` to support more file types.
 
 LlamaParse is an API created by LlamaIndex to efficiently parse files, e.g. it's great at converting PDF tables into markdown.
 
-To use it, first login and get an API key from https://cloud.llamaindex.ai. Make sure to store the key in the environment variable `LLAMA_CLOUD_API_KEY`.
+To use it, first login and get an API key from https://cloud.llamaindex.ai. Make sure to store the key as `apiKey` parameter or in the environment variable `LLAMA_CLOUD_API_KEY`.
 
-Then, you can use the `LlamaParseReader` class to read a local PDF file and convert it into a markdown document that can be used by LlamaIndex:
+Then, you can use the `LlamaParseReader` class to local files and convert them into a parsed document that can be used by LlamaIndex.
+See [LlamaParseReader.ts](https://github.com/run-llama/LlamaIndexTS/blob/main/packages/core/src/readers/LlamaParseReader.ts#L6) for a list of supported file types:
 
 <CodeBlock language="ts">{CodeSource3}</CodeBlock>
 
-Alternatively, you can set the [`resultType`](../api/classes/LlamaParseReader.md#resulttype) option to `text` to get the parsed document as a text string.
+Additional options can be set with the `LlamaParseReader` constructor:
+
+- `resultType` can be set to `markdown`, `text` or `.json`. Defaults to `text`
+- `language` primarly helps with OCR recognition. Defaults to `en`. See [../readers/type.ts](https://github.com/run-llama/LlamaIndexTS/blob/main/packages/core/src/readers/type.ts#L20) for a list of supported languages.
+- `parsingInstructions` 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` set to true to ignore diagonal text.
+- `invalidateCache` 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`.
+- `gpt4oMode` set to true to use GPT-4o to extract content.
+- `gpt4oApiKey` set the GPT-4o API key. Optional. 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
+
+Below a full example of `LlamaParse` integrated in `SimpleDirectoryReader` with additional options.
+
+<CodeBlock language="ts">{CodeSource4}</CodeBlock>
 
 ## API Reference
 
 - [SimpleDirectoryReader](../api/classes/SimpleDirectoryReader.md)
+- [LlamaParseReader](../api/classes/LlamaParseReader.md)

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

@@ -0,0 +1,79 @@
+# DeepInfra
+
+To use DeepInfra embeddings, you need to import `DeepInfraEmbedding` from llamaindex.
+Check out available embedding models [here](https://deepinfra.com/models/embeddings).
+
+```ts
+import {
+  DeepInfraEmbedding,
+  Settings,
+  Document,
+  VectorStoreIndex,
+} from "llamaindex";
+
+// Update Embed Model
+Settings.embedModel = new DeepInfraEmbedding();
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+By default, DeepInfraEmbedding is using the sentence-transformers/clip-ViT-B-32 model. You can change the model by passing the model parameter to the constructor.
+For example:
+
+```ts
+import { DeepInfraEmbedding } from "llamaindex";
+
+const model = "intfloat/e5-large-v2";
+Settings.embedModel = new DeepInfraEmbedding({
+  model,
+});
+```
+
+You can also set the `maxRetries` and `timeout` parameters when initializing `DeepInfraEmbedding` for better control over the request behavior.
+
+For example:
+
+```ts
+import { DeepInfraEmbedding, Settings } from "llamaindex";
+
+const model = "intfloat/e5-large-v2";
+const maxRetries = 5;
+const timeout = 5000; // 5 seconds
+
+Settings.embedModel = new DeepInfraEmbedding({
+  model,
+  maxRetries,
+  timeout,
+});
+```
+
+Standalone usage:
+
+```ts
+import { DeepInfraEmbedding } from "llamaindex";
+import { config } from "dotenv";
+// For standalone usage, you need to configure DEEPINFRA_API_TOKEN in .env file
+config();
+
+const main = async () => {
+  const model = "intfloat/e5-large-v2";
+  const embeddings = new DeepInfraEmbedding({ model });
+  const text = "What is the meaning of life?";
+  const response = await embeddings.embed([text]);
+  console.log(response);
+};
+
+main();
+```
+
+For questions or feedback, please contact us at [feedback@deepinfra.com](mailto:feedback@deepinfra.com)

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

@@ -0,0 +1,33 @@
+# Gemini
+
+To use Gemini embeddings, you need to import `GeminiEmbedding` from `llamaindex`.
+
+```ts
+import { GeminiEmbedding, Settings } from "llamaindex";
+
+// Update Embed Model
+Settings.embedModel = new GeminiEmbedding();
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+Per default, `GeminiEmbedding` is using the `gemini-pro` model. You can change the model by passing the `model` parameter to the constructor.
+For example:
+
+```ts
+import { GEMINI_MODEL, GeminiEmbedding } from "llamaindex";
+
+Settings.embedModel = new GeminiEmbedding({
+  model: GEMINI_MODEL.GEMINI_PRO_LATEST,
+});
+```

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

@@ -3,17 +3,14 @@
 To use HuggingFace embeddings, you need to import `HuggingFaceEmbedding` from `llamaindex`.
 
 ```ts
-import { HuggingFaceEmbedding, serviceContextFromDefaults } from "llamaindex";
+import { HuggingFaceEmbedding, Settings } from "llamaindex";
 
-const huggingFaceEmbeds = new HuggingFaceEmbedding();
-
-const serviceContext = serviceContextFromDefaults({ embedModel: openaiEmbeds });
+// Update Embed Model
+Settings.embedModel = new HuggingFaceEmbedding();
 
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 
 const queryEngine = index.asQueryEngine();
 
@@ -23,3 +20,15 @@ const results = await queryEngine.query({
   query,
 });
 ```
+
+Per default, `HuggingFaceEmbedding` is using the `Xenova/all-MiniLM-L6-v2` model. You can change the model by passing the `modelType` parameter to the constructor.
+If you're not using a quantized model, set the `quantized` parameter to `false`.
+
+For example, to use the not quantized `BAAI/bge-small-en-v1.5` model, you can use the following code:
+
+```ts
+Settings.embedModel = new HuggingFaceEmbedding({
+  modelType: "BAAI/bge-small-en-v1.5",
+  quantized: false,
+});
+```

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

@@ -0,0 +1,21 @@
+# Jina AI
+
+To use Jina AI embeddings, you need to import `JinaAIEmbedding` from `llamaindex`.
+
+```ts
+import { JinaAIEmbedding, Settings } from "llamaindex";
+
+Settings.embedModel = new JinaAIEmbedding();
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```

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

@@ -3,21 +3,16 @@
 To use MistralAI embeddings, you need to import `MistralAIEmbedding` from `llamaindex`.
 
 ```ts
-import { MistralAIEmbedding, serviceContextFromDefaults } from "llamaindex";
+import { MistralAIEmbedding, Settings } from "llamaindex";
 
-const mistralEmbedModel = new MistralAIEmbedding({
+// Update Embed Model
+Settings.embedModel = new MistralAIEmbedding({
   apiKey: "<YOUR_API_KEY>",
 });
 
-const serviceContext = serviceContextFromDefaults({
-  embedModel: mistralEmbedModel,
-});
-
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 
 const queryEngine = index.asQueryEngine();
 

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

@@ -1,21 +1,23 @@
 # Ollama
 
-To use Ollama embeddings, you need to import `Ollama` from `llamaindex`.
+To use Ollama embeddings, you need to import `OllamaEmbedding` from `llamaindex`.
+
+Note that you need to pull the embedding model first before using it.
+
+In the example below, we're using the [`nomic-embed-text`](https://ollama.com/library/nomic-embed-text) model, so you have to call:
+
+```shell
+ollama pull nomic-embed-text
+```
 
 ```ts
-import { Ollama, serviceContextFromDefaults } from "llamaindex";
+import { OllamaEmbedding, Settings } from "llamaindex";
 
-const ollamaEmbedModel = new Ollama();
-
-const serviceContext = serviceContextFromDefaults({
-  embedModel: ollamaEmbedModel,
-});
+Settings.embedModel = new OllamaEmbedding({ model: "nomic-embed-text" });
 
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 
 const queryEngine = index.asQueryEngine();
 

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

@@ -3,19 +3,13 @@
 To use OpenAI embeddings, you need to import `OpenAIEmbedding` from `llamaindex`.
 
 ```ts
-import { OpenAIEmbedding, serviceContextFromDefaults } from "llamaindex";
+import { OpenAIEmbedding, Settings } from "llamaindex";
 
-const openaiEmbedModel = new OpenAIEmbedding();
-
-const serviceContext = serviceContextFromDefaults({
-  embedModel: openaiEmbedModel,
-});
+Settings.embedModel = new OpenAIEmbedding();
 
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 
 const queryEngine = index.asQueryEngine();
 

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

@@ -3,21 +3,15 @@
 To use together embeddings, you need to import `TogetherEmbedding` from `llamaindex`.
 
 ```ts
-import { TogetherEmbedding, serviceContextFromDefaults } from "llamaindex";
+import { TogetherEmbedding, Settings } from "llamaindex";
 
-const togetherEmbedModel = new TogetherEmbedding({
+Settings.embedModel = new TogetherEmbedding({
   apiKey: "<YOUR_API_KEY>",
 });
 
-const serviceContext = serviceContextFromDefaults({
-  embedModel: togetherEmbedModel,
-});
-
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 
 const queryEngine = index.asQueryEngine();
 

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

@@ -2,14 +2,14 @@
 
 The embedding model in LlamaIndex is responsible for creating numerical representations of text. By default, LlamaIndex will use the `text-embedding-ada-002` model from OpenAI.
 
-This can be explicitly set in the `ServiceContext` object.
+This can be explicitly updated through `Settings`
 
 ```typescript
-import { OpenAIEmbedding, serviceContextFromDefaults } from "llamaindex";
+import { OpenAIEmbedding, Settings } from "llamaindex";
 
-const openaiEmbeds = new OpenAIEmbedding();
-
-const serviceContext = serviceContextFromDefaults({ embedModel: openaiEmbeds });
+Settings.embedModel = new OpenAIEmbedding({
+  model: "text-embedding-ada-002",
+});
 ```
 
 ## Local Embedding
@@ -19,4 +19,3 @@ For local embeddings, you can use the [HuggingFace](./available_embeddings/huggi
 ## API Reference
 
 - [OpenAIEmbedding](../../api/classes/OpenAIEmbedding.md)
-- [ServiceContext](../../api/interfaces//ServiceContext.md)

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

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

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

@@ -0,0 +1,32 @@
+# Evaluating
+
+## Concept
+
+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.
+
+- **Response Evaluation**: Does the response match the retrieved context? Does it also match the query? Does it match the reference answer or guidelines?
+- **Retrieval Evaluation**: Are the retrieved sources relevant to the query?
+
+## Response Evaluation
+
+Evaluation of generated results can be difficult, since unlike traditional machine learning the predicted result is not a single number, and it can be hard to define quantitative metrics for this problem.
+
+LlamaIndex offers LLM-based evaluation modules to measure the quality of results. This uses a “gold” LLM (e.g. GPT-4) to decide whether the predicted answer is correct in a variety of ways.
+
+Note that many of these current evaluation modules do not require ground-truth labels. Evaluation can be done with some combination of the query, context, response, and combine these with LLM calls.
+
+These evaluation modules are in the following forms:
+
+- **Correctness**: Whether the generated answer matches that of the reference answer given the query (requires labels).
+
+- **Faithfulness**: Evaluates if the answer is faithful to the retrieved contexts (in other words, whether if there’s hallucination).
+
+- **Relevancy**: Evaluates if the response from a query engine matches any source nodes.
+
+## Usage
+
+- [Correctness Evaluator](./modules/correctness.md)
+- [Faithfulness Evaluator](./modules/faithfulness.md)
+- [Relevancy Evaluator](./modules/relevancy.md)

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

@@ -0,0 +1 @@
+label: "Modules"

apps/docs/docs/modules/evaluation/modules/correctness.md

@@ -0,0 +1,58 @@
+# Correctness Evaluator
+
+Correctness evaluates the relevance and correctness of a generated answer against a reference answer.
+
+This is useful for measuring if the response was correct. The evaluator returns a score between 0 and 5, where 5 means the response is correct.
+
+## Usage
+
+Firstly, you need to install the package:
+
+```bash
+pnpm i llamaindex
+```
+
+Set the OpenAI API key:
+
+```bash
+export OPENAI_API_KEY=your-api-key
+```
+
+Import the required modules:
+
+```ts
+import { CorrectnessEvaluator, OpenAI, Settings, Response } from "llamaindex";
+```
+
+Let's setup gpt-4 for better results:
+
+```ts
+Settings.llm = new OpenAI({
+  model: "gpt-4",
+});
+```
+
+```ts
+const query =
+  "Can you explain the theory of relativity proposed by Albert Einstein in detail?";
+
+const response = ` Certainly! Albert Einstein's theory of relativity consists of two main components: special relativity and general relativity. Special relativity, published in 1905, introduced the concept that the laws of physics are the same for all non-accelerating observers and that the speed of light in a vacuum is a constant, regardless of the motion of the source or observer. It also gave rise to the famous equation E=mc², which relates energy (E) and mass (m).
+
+However, general relativity, published in 1915, extended these ideas to include the effects of magnetism. According to general relativity, gravity is not a force between masses but rather the result of the warping of space and time by magnetic fields generated by massive objects. Massive objects, such as planets and stars, create magnetic fields that cause a curvature in spacetime, and smaller objects follow curved paths in response to this magnetic curvature. This concept is often illustrated using the analogy of a heavy ball placed on a rubber sheet with magnets underneath, causing it to create a depression that other objects (representing smaller masses) naturally move towards due to magnetic attraction.
+`;
+
+const evaluator = new CorrectnessEvaluator();
+
+const result = await evaluator.evaluateResponse({
+  query,
+  response: new Response(response),
+});
+
+console.log(
+  `the response is ${result.passing ? "correct" : "not correct"} with a score of ${result.score}`,
+);
+```
+
+```bash
+the response is not correct with a score of 2.5
+```

apps/docs/docs/modules/evaluation/modules/faithfulness.md

@@ -0,0 +1,78 @@
+# Faithfulness Evaluator
+
+Faithfulness is a measure of whether the generated answer is faithful to the retrieved contexts. In other words, it measures whether there is any hallucination in the generated answer.
+
+This uses the FaithfulnessEvaluator module to measure if the response from a query engine matches any source nodes.
+
+This is useful for measuring if the response was hallucinated. The evaluator returns a score between 0 and 1, where 1 means the response is faithful to the retrieved contexts.
+
+## Usage
+
+Firstly, you need to install the package:
+
+```bash
+pnpm i llamaindex
+```
+
+Set the OpenAI API key:
+
+```bash
+export OPENAI_API_KEY=your-api-key
+```
+
+Import the required modules:
+
+```ts
+import {
+  Document,
+  FaithfulnessEvaluator,
+  OpenAI,
+  VectorStoreIndex,
+  Settings,
+} from "llamaindex";
+```
+
+Let's setup gpt-4 for better results:
+
+```ts
+Settings.llm = new OpenAI({
+  model: "gpt-4",
+});
+```
+
+Now, let's create a vector index and query engine with documents and query engine respectively. Then, we can evaluate the response with the query and response from the query engine.:
+
+```ts
+const documents = [
+  new Document({
+    text: `The city came under British control in 1664 and was renamed New York after King Charles II of England granted the lands to his brother, the Duke of York. The city was regained by the Dutch in July 1673 and was renamed New Orange for one year and three months; the city has been continuously named New York since November 1674. New York City was the capital of the United States from 1785 until 1790, and has been the largest U.S. city since 1790. The Statue of Liberty greeted millions of immigrants as they came to the U.S. by ship in the late 19th and early 20th centuries, and is a symbol of the U.S. and its ideals of liberty and peace. In the 21st century, New York City has emerged as a global node of creativity, entrepreneurship, and as a symbol of freedom and cultural diversity. The New York Times has won the most Pulitzer Prizes for journalism and remains the U.S. media's "newspaper of record". In 2019, New York City was voted the greatest city in the world in a survey of over 30,000 p...	Pass`,
+  }),
+];
+
+const vectorIndex = await VectorStoreIndex.fromDocuments(documents);
+
+const queryEngine = vectorIndex.asQueryEngine();
+```
+
+Now, let's evaluate the response:
+
+```ts
+const query = "How did New York City get its name?";
+
+const evaluator = new FaithfulnessEvaluator();
+
+const response = await queryEngine.query({
+  query,
+});
+
+const result = await evaluator.evaluateResponse({
+  query,
+  response,
+});
+
+console.log(`the response is ${result.passing ? "faithful" : "not faithful"}`);
+```
+
+```bash
+the response is faithful
+```

apps/docs/docs/modules/evaluation/modules/relevancy.md

@@ -0,0 +1,72 @@
+# Relevancy Evaluator
+
+Relevancy measure if the response from a query engine matches any source nodes.
+
+It is useful for measuring if the response was relevant to the query. The evaluator returns a score between 0 and 1, where 1 means the response is relevant to the query.
+
+## Usage
+
+Firstly, you need to install the package:
+
+```bash
+pnpm i llamaindex
+```
+
+Set the OpenAI API key:
+
+```bash
+export OPENAI_API_KEY=your-api-key
+```
+
+Import the required modules:
+
+```ts
+import {
+  RelevancyEvaluator,
+  OpenAI,
+  Settings,
+  Document,
+  VectorStoreIndex,
+} from "llamaindex";
+```
+
+Let's setup gpt-4 for better results:
+
+```ts
+Settings.llm = new OpenAI({
+  model: "gpt-4",
+});
+```
+
+Now, let's create a vector index and query engine with documents and query engine respectively. Then, we can evaluate the response with the query and response from the query engine.:
+
+```ts
+const documents = [
+  new Document({
+    text: `The city came under British control in 1664 and was renamed New York after King Charles II of England granted the lands to his brother, the Duke of York. The city was regained by the Dutch in July 1673 and was renamed New Orange for one year and three months; the city has been continuously named New York since November 1674. New York City was the capital of the United States from 1785 until 1790, and has been the largest U.S. city since 1790. The Statue of Liberty greeted millions of immigrants as they came to the U.S. by ship in the late 19th and early 20th centuries, and is a symbol of the U.S. and its ideals of liberty and peace. In the 21st century, New York City has emerged as a global node of creativity, entrepreneurship, and as a symbol of freedom and cultural diversity. The New York Times has won the most Pulitzer Prizes for journalism and remains the U.S. media's "newspaper of record". In 2019, New York City was voted the greatest city in the world in a survey of over 30,000 p...	Pass`,
+  }),
+];
+
+const vectorIndex = await VectorStoreIndex.fromDocuments(documents);
+
+const queryEngine = vectorIndex.asQueryEngine();
+
+const query = "How did New York City get its name?";
+
+const response = await queryEngine.query({
+  query,
+});
+
+const evaluator = new RelevancyEvaluator();
+
+const result = await evaluator.evaluateResponse({
+  query,
+  response: response,
+});
+
+console.log(`the response is ${result.passing ? "relevant" : "not relevant"}`);
+```
+
+```bash
+the response is relevant
+```

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

@@ -1,6 +1,6 @@
 # Transformations
 
-A transformation is something that takes a list of nodes as an input, and returns a list of nodes. Each component that implements the Transformatio class has both a `transform` definition responsible for transforming the nodes
+A transformation is something that takes a list of nodes as an input, and returns a list of nodes. Each component that implements the Transformation class has both a `transform` definition responsible for transforming the nodes.
 
 Currently, the following components are Transformation objects:
 

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

@@ -3,13 +3,11 @@
 ## Usage
 
 ```ts
-import { Anthropic, serviceContextFromDefaults } from "llamaindex";
+import { Anthropic, Settings } from "llamaindex";
 
-const anthropicLLM = new Anthropic({
+Settings.llm = new Anthropic({
   apiKey: "<YOUR_API_KEY>",
 });
-
-const serviceContext = serviceContextFromDefaults({ llm: anthropicLLM });
 ```
 
 ## Load and index documents
@@ -19,9 +17,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -39,28 +35,17 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  Anthropic,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { Anthropic, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+Settings.llm = new Anthropic({
+  apiKey: "<YOUR_API_KEY>",
+});
 
 async function main() {
-  // Create an instance of the Anthropic LLM
-  const anthropicLLM = new Anthropic({
-    apiKey: "<YOUR_API_KEY>",
-  });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: anthropicLLM });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
 
   // Create a query engine
   const queryEngine = index.asQueryEngine({

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

@@ -15,11 +15,9 @@ export AZURE_OPENAI_DEPLOYMENT="gpt-4" # or some other deployment name
 ## Usage
 
 ```ts
-import { OpenAI, serviceContextFromDefaults } from "llamaindex";
+import { OpenAI, Settings } from "llamaindex";
 
-const azureOpenaiLLM = new OpenAI({ model: "gpt-4", temperature: 0 });
-
-const serviceContext = serviceContextFromDefaults({ llm: azureOpenaiLLM });
+Settings.llm = new OpenAI({ model: "gpt-4", temperature: 0 });
 ```
 
 ## Load and index documents
@@ -29,9 +27,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -49,26 +45,15 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  OpenAI,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { OpenAI, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+Settings.llm = new OpenAI({ model: "gpt-4", temperature: 0 });
 
 async function main() {
-  // Create an instance of the LLM
-  const azureOpenaiLLM = new OpenAI({ model: "gpt-4", temperature: 0 });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: azureOpenaiLLM });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
 
   // get retriever
   const retriever = index.asRetriever();

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

@@ -0,0 +1,62 @@
+# Bedrock
+
+## Usage
+
+```ts
+import { BEDROCK_MODELS, Bedrock } from "@llamaindex/community";
+
+Settings.llm = new Bedrock({
+  model: BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
+  region: "us-east-1", // can be provided via env AWS_REGION
+  credentials: {
+    accessKeyId: "...", // optional and can be provided via env AWS_ACCESS_KEY_ID
+    secretAccessKey: "...", // optional and can be provided via env AWS_SECRET_ACCESS_KEY
+  },
+});
+```
+
+Currently only supports Anthropic models:
+
+```ts
+ANTHROPIC_CLAUDE_INSTANT_1 = "anthropic.claude-instant-v1";
+ANTHROPIC_CLAUDE_2 = "anthropic.claude-v2";
+ANTHROPIC_CLAUDE_2_1 = "anthropic.claude-v2:1";
+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";
+```
+
+Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url format, e.g. `data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==`
+
+## Full Example
+
+```ts
+import { BEDROCK_MODELS, Bedrock } from "llamaindex";
+
+Settings.llm = new Bedrock({
+  model: BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
+});
+
+async function main() {
+  const document = new Document({ text: essay, id_: "essay" });
+
+  // Load and index documents
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // Create a query engine
+  const queryEngine = index.asQueryEngine({
+    retriever,
+  });
+
+  const query = "What is the meaning of life?";
+
+  // Query
+  const response = await queryEngine.query({
+    query,
+  });
+
+  // Log the response
+  console.log(response.response);
+}
+```

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

@@ -0,0 +1,83 @@
+# DeepInfra
+
+Check out available LLMs [here](https://deepinfra.com/models/text-generation).
+
+```ts
+import { DeepInfra, Settings } from "llamaindex";
+
+// Get the API key from `DEEPINFRA_API_TOKEN` environment variable
+import { config } from "dotenv";
+config();
+Settings.llm = new DeepInfra();
+
+// Set the API key
+apiKey = "YOUR_API_KEY";
+Settings.llm = new DeepInfra({ apiKey });
+```
+
+You can setup the apiKey on the environment variables, like:
+
+```bash
+export DEEPINFRA_API_TOKEN="<YOUR_API_KEY>"
+```
+
+## 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.
+
+```ts
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import { DeepInfra, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+// Use custom LLM
+const model = "meta-llama/Meta-Llama-3-8B-Instruct";
+Settings.llm = new DeepInfra({ model, temperature: 0 });
+
+async function main() {
+  const document = new Document({ text: essay, id_: "essay" });
+
+  // Load and index documents
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // get retriever
+  const retriever = index.asRetriever();
+
+  // Create a query engine
+  const queryEngine = index.asQueryEngine({
+    retriever,
+  });
+
+  const query = "What is the meaning of life?";
+
+  // Query
+  const response = await queryEngine.query({
+    query,
+  });
+
+  // Log the response
+  console.log(response.response);
+}
+```
+
+## Feedback
+
+If you have any feedback, please reach out to us at [feedback@deepinfra.com](mailto:feedback@deepinfra.com)

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

@@ -5,13 +5,11 @@ Fireworks.ai focus on production use cases for open source LLMs, offering speed
 ## Usage
 
 ```ts
-import { FireworksLLM, serviceContextFromDefaults } from "llamaindex";
+import { FireworksLLM, Settings } from "llamaindex";
 
-const fireworksLLM = new FireworksLLM({
+Settings.llm = new FireworksLLM({
   apiKey: "<YOUR_API_KEY>",
 });
-
-const serviceContext = serviceContextFromDefaults({ llm: fireworksLLM });
 ```
 
 ## Load and index documents
@@ -23,9 +21,7 @@ const reader = new PDFReader();
 const documents = await reader.loadData("../data/brk-2022.pdf");
 
 // Split text and create embeddings. Store them in a VectorStoreIndex
-const index = await VectorStoreIndex.fromDocuments(documents, {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments(documents);
 ```
 
 ## Query

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

@@ -0,0 +1,101 @@
+# Gemini
+
+## Usage
+
+```ts
+import { Gemini, Settings, GEMINI_MODEL } from "llamaindex";
+
+Settings.llm = new Gemini({
+  model: GEMINI_MODEL.GEMINI_PRO,
+});
+```
+
+### Usage with Vertex AI
+
+To use Gemini via Vertex AI you can use `GeminiVertexSession`.
+
+GeminiVertexSession accepts the env variables: `GOOGLE_VERTEX_LOCATION` and `GOOGLE_VERTEX_PROJECT`
+
+```ts
+import { Gemini, GEMINI_MODEL, GeminiVertexSession } from "llamaindex";
+
+const gemini = new Gemini({
+  model: GEMINI_MODEL.GEMINI_PRO,
+  session: new GeminiVertexSession({
+    location: "us-central1",      // optional if provided by GOOGLE_VERTEX_LOCATION env variable
+    project: "project1",          // optional if provided by GOOGLE_VERTEX_PROJECT env variable
+    googleAuthOptions: {...},     // optional, but useful for production. It accepts all values from `GoogleAuthOptions`
+  }),
+});
+```
+
+[GoogleAuthOptions](https://github.com/googleapis/google-auth-library-nodejs/blob/main/src/auth/googleauth.ts)
+
+To authenticate for local development:
+
+```bash
+npm install @google-cloud/vertexai
+gcloud auth application-default login
+```
+
+To authenticate for production you'll have to use a [service account](https://cloud.google.com/docs/authentication/). `googleAuthOptions` has `credentials` which might be useful for you.
+
+## 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.
+
+```ts
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import {
+  Gemini,
+  Document,
+  VectorStoreIndex,
+  Settings,
+  GEMINI_MODEL,
+} from "llamaindex";
+
+Settings.llm = new Gemini({
+  model: GEMINI_MODEL.GEMINI_PRO,
+});
+
+async function main() {
+  const document = new Document({ text: essay, id_: "essay" });
+
+  // Load and index documents
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // Create a query engine
+  const queryEngine = index.asQueryEngine({
+    retriever,
+  });
+
+  const query = "What is the meaning of life?";
+
+  // Query
+  const response = await queryEngine.query({
+    query,
+  });
+
+  // Log the response
+  console.log(response.response);
+}
+```

apps/docs/docs/modules/llms/available_llms/groq.mdx

@@ -0,0 +1,52 @@
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../../../examples/groq.ts";
+
+# Groq
+
+## Usage
+
+First, create an API key at the [Groq Console](https://console.groq.com/keys). Then save it in your environment:
+
+```bash
+export GROQ_API_KEY=<your-api-key>
+```
+
+The initialize the Groq module.
+
+```ts
+import { Groq, Settings } from "llamaindex";
+
+Settings.llm = new Groq({
+  // If you do not wish to set your API key in the environment, you may
+  // configure your API key when you initialize the Groq class.
+  // apiKey: "<your-api-key>",
+});
+```
+
+## 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.
+
+```ts
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+<CodeBlock language="ts" showLineNumbers>
+  {CodeSource}
+</CodeBlock>

apps/docs/docs/modules/llms/available_llms/llama2.md

@@ -3,11 +3,9 @@
 ## Usage
 
 ```ts
-import { Ollama, serviceContextFromDefaults } from "llamaindex";
+import { Ollama, Settings, DeuceChatStrategy } from "llamaindex";
 
-const llama2LLM = new LlamaDeuce({ chatStrategy: DeuceChatStrategy.META });
-
-const serviceContext = serviceContextFromDefaults({ llm: llama2LLM });
+Settings.llm = new LlamaDeuce({ chatStrategy: DeuceChatStrategy.META });
 ```
 
 ## Usage with Replication
@@ -16,19 +14,18 @@ const serviceContext = serviceContextFromDefaults({ llm: llama2LLM });
 import {
   Ollama,
   ReplicateSession,
-  serviceContextFromDefaults,
+  Settings,
+  DeuceChatStrategy,
 } from "llamaindex";
 
 const replicateSession = new ReplicateSession({
   replicateKey,
 });
 
-const llama2LLM = new LlamaDeuce({
+Settings.llm = new LlamaDeuce({
   chatStrategy: DeuceChatStrategy.META,
   replicateSession,
 });
-
-const serviceContext = serviceContextFromDefaults({ llm: llama2LLM });
 ```
 
 ## Load and index documents
@@ -38,9 +35,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -62,22 +57,18 @@ import {
   LlamaDeuce,
   Document,
   VectorStoreIndex,
-  serviceContextFromDefaults,
+  Settings,
+  DeuceChatStrategy,
 } from "llamaindex";
 
+// Use the LlamaDeuce LLM
+Settings.llm = new LlamaDeuce({ chatStrategy: DeuceChatStrategy.META });
+
 async function main() {
-  // Create an instance of the LLM
-  const llama2LLM = new LlamaDeuce({ chatStrategy: DeuceChatStrategy.META });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: mistralLLM });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
 
   // get retriever
   const retriever = index.asRetriever();

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

@@ -3,14 +3,12 @@
 ## Usage
 
 ```ts
-import { Ollama, serviceContextFromDefaults } from "llamaindex";
+import { MistralAI, Settings } from "llamaindex";
 
-const mistralLLM = new MistralAI({
+Settings.llm = new MistralAI({
   model: "mistral-tiny",
   apiKey: "<YOUR_API_KEY>",
 });
-
-const serviceContext = serviceContextFromDefaults({ llm: mistralLLM });
 ```
 
 ## Load and index documents
@@ -20,9 +18,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -40,26 +36,16 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  MistralAI,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { MistralAI, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+// Use the MistralAI LLM
+Settings.llm = new MistralAI({ model: "mistral-tiny" });
 
 async function main() {
-  // Create an instance of the LLM
-  const mistralLLM = new MistralAI({ model: "mistral-tiny" });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: mistralLLM });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
 
   // get retriever
   const retriever = index.asRetriever();

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

@@ -3,14 +3,10 @@
 ## Usage
 
 ```ts
-import { Ollama, serviceContextFromDefaults } from "llamaindex";
+import { Ollama, Settings } from "llamaindex";
 
-const ollamaLLM = new Ollama({ model: "llama2", temperature: 0.75 });
-
-const serviceContext = serviceContextFromDefaults({
-  llm: ollamaLLM,
-  embedModel: ollamaLLM,
-});
+Settings.llm = ollamaLLM;
+Settings.embedModel = ollamaLLM;
 ```
 
 ## Load and index documents
@@ -20,9 +16,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -40,33 +34,23 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  Ollama,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { Ollama, Document, VectorStoreIndex, Settings } from "llamaindex";
 
 import fs from "fs/promises";
 
+const ollama = new Ollama({ model: "llama2", temperature: 0.75 });
+
+// Use Ollama LLM and Embed Model
+Settings.llm = ollama;
+Settings.embedModel = ollama;
+
 async function main() {
-  // Create an instance of the LLM
-  const ollamaLLM = new Ollama({ model: "llama2", temperature: 0.75 });
-
   const essay = await fs.readFile("./paul_graham_essay.txt", "utf-8");
 
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({
-    embedModel: ollamaLLM, // prevent 'Set OpenAI Key in OPENAI_API_KEY env variable' error
-    llm: ollamaLLM,
-  });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
 
   // get retriever
   const retriever = index.asRetriever();

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

@@ -1,11 +1,9 @@
 # OpenAI
 
 ```ts
-import { OpenAI, serviceContextFromDefaults } from "llamaindex";
+import { OpenAI, Settings } from "llamaindex";
 
-const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0, apiKey: <YOUR_API_KEY> });
-
-const serviceContext = serviceContextFromDefaults({ llm: openaiLLM });
+Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0, apiKey: <YOUR_API_KEY> });
 ```
 
 You can setup the apiKey on the environment variables, like:
@@ -21,9 +19,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -41,26 +37,16 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  OpenAI,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { OpenAI, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+// Use the OpenAI LLM
+Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
 
 async function main() {
-  // Create an instance of the LLM
-  const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: openaiLLM });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
 
   // get retriever
   const retriever = index.asRetriever();

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

@@ -3,13 +3,11 @@
 ## Usage
 
 ```ts
-import { Portkey, serviceContextFromDefaults } from "llamaindex";
+import { Portkey, Settings } from "llamaindex";
 
-const portkeyLLM = new Portkey({
+Settings.llm = new Portkey({
   apiKey: "<YOUR_API_KEY>",
 });
-
-const serviceContext = serviceContextFromDefaults({ llm: portkeyLLM });
 ```
 
 ## Load and index documents
@@ -19,9 +17,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -39,28 +35,19 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  Portkey,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { Portkey, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+// Use the Portkey LLM
+Settings.llm = new Portkey({
+  apiKey: "<YOUR_API_KEY>",
+});
 
 async function main() {
-  // Create an instance of the LLM
-  const portkeyLLM = new Portkey({
-    apiKey: "<YOUR_API_KEY>",
-  });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: portkeyLLM });
-
+  // Create a document
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
 
   // get retriever
   const retriever = index.asRetriever();

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

@@ -3,13 +3,11 @@
 ## Usage
 
 ```ts
-import { TogetherLLM, serviceContextFromDefaults } from "llamaindex";
+import { TogetherLLM, Settings } from "llamaindex";
 
-const togetherLLM = new TogetherLLM({
+Settings.llm = new TogetherLLM({
   apiKey: "<YOUR_API_KEY>",
 });
-
-const serviceContext = serviceContextFromDefaults({ llm: togetherLLM });
 ```
 
 ## Load and index documents
@@ -19,9 +17,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -39,28 +35,17 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  TogetherLLM,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { TogetherLLM, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+Settings.llm = new TogetherLLM({
+  apiKey: "<YOUR_API_KEY>",
+});
 
 async function main() {
-  // Create an instance of the LLM
-  const togetherLLM = new TogetherLLM({
-    apiKey: "<YOUR_API_KEY>",
-  });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: togetherLLM });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
 
   // get retriever
   const retriever = index.asRetriever();

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

@@ -6,14 +6,12 @@ sidebar_position: 3
 
 The LLM is responsible for reading text and generating natural language responses to queries. By default, LlamaIndex.TS uses `gpt-3.5-turbo`.
 
-The LLM can be explicitly set in the `ServiceContext` object.
+The LLM can be explicitly updated through `Settings`.
 
 ```typescript
-import { OpenAI, serviceContextFromDefaults } from "llamaindex";
+import { OpenAI, Settings } from "llamaindex";
 
-const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
-
-const serviceContext = serviceContextFromDefaults({ llm: openaiLLM });
+Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
 ```
 
 ## Azure OpenAI
@@ -35,4 +33,3 @@ For local LLMs, currently we recommend the use of [Ollama](./available_llms/olla
 ## API Reference
 
 - [OpenAI](../api/classes/OpenAI.md)
-- [ServiceContext](../api/interfaces//ServiceContext.md)

apps/docs/docs/modules/node_parser.md

@@ -4,15 +4,14 @@ sidebar_position: 4
 
 # NodeParser
 
-The `NodeParser` in LlamaIndex is responsible for splitting `Document` objects into more manageable `Node` objects. When you call `.fromDocuments()`, the `NodeParser` from the `ServiceContext` is used to do this automatically for you. Alternatively, you can use it to split documents ahead of time.
+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, SimpleNodeParser } from "llamaindex";
 
 const nodeParser = new SimpleNodeParser();
-const nodes = nodeParser.getNodesFromDocuments([
-  new Document({ text: "I am 10 years old. John is 20 years old." }),
-]);
+
+Settings.nodeParser = nodeParser;
 ```
 
 ## TextSplitter

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

@@ -18,7 +18,7 @@ import {
   Document,
   OpenAI,
   VectorStoreIndex,
-  serviceContextFromDefaults,
+  Settings,
 } from "llamaindex";
 ```
 
@@ -29,13 +29,9 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const serviceContext = serviceContextFromDefaults({
-  llm: new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.1 }),
-});
+Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.1 });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Increase similarity topK to retrieve more results

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

@@ -36,7 +36,7 @@ const processor = new SimilarityPostprocessor({
   similarityCutoff: 0.7,
 });
 
-const filteredNodes = processor.postprocessNodes(nodes);
+const filteredNodes = await processor.postprocessNodes(nodes);
 
 // cohere rerank: rerank nodes given query using trained model
 const reranker = new CohereRerank({
@@ -58,7 +58,10 @@ Most commonly, node-postprocessors will be used in a query engine, where they ar
 ### Using Node Postprocessors in a Query Engine
 
 ```ts
-import { Node, NodeWithScore, SimilarityPostprocessor, CohereRerank } from "llamaindex";
+import { Node, NodeWithScore, SimilarityPostprocessor, CohereRerank, Settings } from "llamaindex";
+
+// Use OpenAI LLM
+Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.1 });
 
 const nodes: NodeWithScore[] = [
   {
@@ -79,14 +82,6 @@ const reranker = new CohereRerank({
 
 const document = new Document({ text: "essay", id_: "essay" });
 
-const serviceContext = serviceContextFromDefaults({
-  llm: new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.1 }),
-});
-
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
-
 const queryEngine = index.asQueryEngine({
   nodePostprocessors: [processor, reranker],
 });
@@ -100,7 +95,7 @@ const response = await queryEngine.query("<user_query>");
 ```ts
 import { SimilarityPostprocessor } from "llamaindex";
 
-nodes = await index.asRetriever().retrieve("test query str");
+nodes = await index.asRetriever().retrieve({ query: "test query str" });
 
 const processor = new SimilarityPostprocessor({
   similarityCutoff: 0.7,

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

@@ -0,0 +1,71 @@
+# Jina AI Reranker
+
+The Jina AI Reranker is a postprocessor that uses the Jina AI Reranker API to rerank the results of a search query.
+
+## Setup
+
+Firstly, you will need to install the `llamaindex` package.
+
+```bash
+pnpm install llamaindex
+```
+
+Now, you will need to sign up for an API key at [Jina AI](https://jina.ai/reranker). Once you have your API key you can import the necessary modules and create a new instance of the `JinaAIReranker` class.
+
+```ts
+import {
+  JinaAIReranker,
+  Document,
+  OpenAI,
+  VectorStoreIndex,
+  Settings,
+} from "llamaindex";
+```
+
+## 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.
+
+```ts
+const document = new Document({ text: essay, id_: "essay" });
+
+Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.1 });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## Increase similarity topK to retrieve more results
+
+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();
+retriever.similarityTopK = 5;
+```
+
+## Create a new instance of the JinaAIReranker class
+
+Then you can create a new instance of the `JinaAIReranker` class and pass in the number of results you want to return.
+The Jina AI Reranker API key is set in the `JINAAI_API_KEY` environment variable.
+
+```bash
+export JINAAI_API_KEY=<YOUR API KEY>
+```
+
+```ts
+const nodePostprocessor = new JinaAIReranker({
+  topN: 5,
+});
+```
+
+## Create a query engine with the retriever and node postprocessor
+
+```ts
+const queryEngine = index.asQueryEngine({
+  retriever,
+  nodePostprocessors: [nodePostprocessor],
+});
+
+// log the response
+const response = await queryEngine.query("Where did the author grown up?");
+```

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

@@ -31,13 +31,11 @@ The first method is to create a new instance of `ResponseSynthesizer` (or the mo
 ```ts
 // Create an instance of response synthesizer
 const responseSynthesizer = new ResponseSynthesizer({
-  responseBuilder: new CompactAndRefine(serviceContext, newTextQaPrompt),
+  responseBuilder: new CompactAndRefine(undefined, newTextQaPrompt),
 });
 
 // Create index
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 
 // Query the index
 const queryEngine = index.asQueryEngine({ responseSynthesizer });
@@ -53,9 +51,7 @@ The second method is that most of the modules in LlamaIndex have a `getPrompts`
 
 ```ts
 // Create index
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 
 // Query the index
 const queryEngine = index.asQueryEngine();

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

@@ -54,12 +54,13 @@ You can create a `ChromaVectorStore` to store the documents:
 
 ```ts
 const chromaVS = new ChromaVectorStore({ collectionName });
-const serviceContext = await storageContextFromDefaults({
+
+const storageContext = await storageContextFromDefaults({
   vectorStore: chromaVS,
 });
 
 const index = await VectorStoreIndex.fromDocuments(docs, {
-  storageContext: serviceContext,
+  storageContext: storageContext,
 });
 ```
 

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

@@ -18,7 +18,7 @@ import {
   SimpleNodeParser,
   SummaryIndex,
   VectorStoreIndex,
-  serviceContextFromDefaults,
+  Settings,
 } from "llamaindex";
 ```
 
@@ -34,17 +34,13 @@ 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 `SimpleNodeParser` to parse the documents into nodes and `ServiceContext` 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
-const nodeParser = new SimpleNodeParser({
+Settings.llm = new OpenAI();
+Settings.nodeParser = new SimpleNodeParser({
   chunkSize: 1024,
 });
-
-const serviceContext = serviceContextFromDefaults({
-  nodeParser,
-  llm: new OpenAI(),
-});
 ```
 
 ## Creating Indices
@@ -52,13 +48,8 @@ const serviceContext = serviceContextFromDefaults({
 Next, we need to create some indices. We will create a `VectorStoreIndex` and a `SummaryIndex`:
 
 ```ts
-const vectorIndex = await VectorStoreIndex.fromDocuments(documents, {
-  serviceContext,
-});
-
-const summaryIndex = await SummaryIndex.fromDocuments(documents, {
-  serviceContext,
-});
+const vectorIndex = await VectorStoreIndex.fromDocuments(documents);
+const summaryIndex = await SummaryIndex.fromDocuments(documents);
 ```
 
 ## Creating Query Engines
@@ -88,7 +79,6 @@ const queryEngine = RouterQueryEngine.fromDefaults({
       description: "Useful for retrieving specific context from Abramov",
     },
   ],
-  serviceContext,
 });
 ```
 
@@ -117,34 +107,23 @@ import {
   SimpleNodeParser,
   SummaryIndex,
   VectorStoreIndex,
-  serviceContextFromDefaults,
+  Settings,
 } from "llamaindex";
 
+Settings.llm = new OpenAI();
+Settings.nodeParser = new SimpleNodeParser({
+  chunkSize: 1024,
+});
+
 async function main() {
   // Load documents from a directory
   const documents = await new SimpleDirectoryReader().loadData({
     directoryPath: "node_modules/llamaindex/examples",
   });
 
-  // Parse the documents into nodes
-  const nodeParser = new SimpleNodeParser({
-    chunkSize: 1024,
-  });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({
-    nodeParser,
-    llm: new OpenAI(),
-  });
-
   // Create indices
-  const vectorIndex = await VectorStoreIndex.fromDocuments(documents, {
-    serviceContext,
-  });
-
-  const summaryIndex = await SummaryIndex.fromDocuments(documents, {
-    serviceContext,
-  });
+  const vectorIndex = await VectorStoreIndex.fromDocuments(documents);
+  const summaryIndex = await SummaryIndex.fromDocuments(documents);
 
   // Create query engines
   const vectorQueryEngine = vectorIndex.asQueryEngine();
@@ -162,7 +141,6 @@ async function main() {
         description: "Useful for retrieving specific context from Abramov",
       },
     ],
-    serviceContext,
   });
 
   // Query the router query engine

apps/docs/docs/modules/retriever.md

@@ -11,7 +11,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Fetch nodes!
-const nodesWithScore = await retriever.retrieve("query string");
+const nodesWithScore = await retriever.retrieve({ query: "query string" });
 ```
 
 ## API Reference

apps/docs/docs/observability/index.md

@@ -14,6 +14,9 @@ Configure a variable once, and you'll be able to do things like the following:
 
 Each provider has similarities and differences. Take a look below for the full set of guides for each one!
 
+- [OpenLLMetry](#openllmetry)
+- [Langtrace](#langtrace)
+
 ## OpenLLMetry
 
 [OpenLLMetry](https://github.com/traceloop/openllmetry-js) is an open-source project based on OpenTelemetry for tracing and monitoring
@@ -33,3 +36,29 @@ traceloop.initialize({
   disableBatch: true,
 });
 ```
+
+## Langtrace
+
+Enhance your observability with Langtrace, a robust open-source tool supports OpenTelemetry and is designed to trace, evaluate, and manage LLM applications seamlessly. Langtrace integrates directly with LlamaIndex, offering detailed, real-time insights into performance metrics such as accuracy, evaluations, and latency.
+
+#### Install
+
+- Self-host or sign-up and generate an API key using [Langtrace](https://www.langtrace.ai) Cloud
+
+```bash
+npm install @langtrase/typescript-sdk
+```
+
+#### Initialize
+
+```js
+import * as Langtrace from "@langtrase/typescript-sdk";
+Langtrace.init({ api_key: "<YOUR_API_KEY>" });
+```
+
+Features:
+
+- OpenTelemetry compliant, ensuring broad compatibility with observability platforms.
+- Provides comprehensive logs and detailed traces of all components.
+- Real-time monitoring of accuracy, evaluations, usage, costs, and latency.
+- For more configuration options and details, visit [Langtrace Docs](https://docs.langtrace.ai/introduction).

apps/docs/docs/recipes/_category_.yml

@@ -0,0 +1,2 @@
+label: Recipes
+position: 3

apps/docs/docs/recipes/cost-analysis.mdx

@@ -0,0 +1,14 @@
+# Cost Analysis
+
+This page shows how to track LLM cost using APIs.
+
+## Callback Manager
+
+The callback manager is a class that manages the callback functions.
+
+You can register `llm-start`, `llm-end`, and `llm-stream` callbacks to the callback manager for tracking the cost.
+
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../examples/recipes/cost-analysis";
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>

apps/docs/docusaurus.config.js

@@ -66,7 +66,11 @@ const config = {
             [require("@docusaurus/remark-plugin-npm2yarn"), { sync: true }],
           ],
         },
-        blog: false,
+        blog: {
+          blogTitle: "LlamaIndexTS blog",
+          blogDescription: "The official blog of LlamaIndexTS",
+          postsPerPage: "ALL",
+        },
         gtag: {
           trackingID: "G-NB9B8LW9W5",
           anonymizeIP: true,
@@ -97,6 +101,7 @@ const config = {
             type: "localeDropdown",
             position: "left",
           },
+          { to: "blog", label: "Blog", position: "right" },
           {
             href: "https://github.com/run-llama/LlamaIndexTS",
             label: "GitHub",
@@ -162,8 +167,8 @@ const config = {
     [
       "docusaurus-plugin-typedoc",
       {
-        entryPoints: ["../../packages/core/src/index.ts"],
-        tsconfig: "../../packages/core/tsconfig.json",
+        entryPoints: ["../../packages/llamaindex/src/index.ts"],
+        tsconfig: "../../tsconfig.json",
         readme: "none",
         sourceLinkTemplate:
           "https://github.com/run-llama/LlamaIndexTS/blob/{gitRevision}/{path}#L{line}",

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // جلب العقد!
-const nodesWithScore = await retriever.retrieve("سلسلة الاستعلام");
+const nodesWithScore = await retriever.retrieve({ query: "سلسلة الاستعلام" });
 ```
 
 ## مرجع الواجهة البرمجية (API Reference)

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Извличане на върхове!
-const nodesWithScore = await retriever.retrieve("query string");
+const nodesWithScore = await retriever.retrieve({ query: "query string" });
 ```
 
 ## API Reference (API справка)

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

@@ -13,7 +13,7 @@ const recuperador = vector_index.asRetriever();
 recuperador.similarityTopK = 3;
 
 // Obteniu els nodes!
-const nodesAmbPuntuació = await recuperador.retrieve("cadena de consulta");
+const nodesAmbPuntuació = await recuperador.retrieve({ query: "cadena de consulta" });
 ```
 
 ## Referència de l'API

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Získání uzlů!
-const nodesWithScore = await retriever.retrieve("dotazovací řetězec");
+const nodesWithScore = await retriever.retrieve({ query: "dotazovací řetězec" });
 ```
 
 ## API Reference (Odkazy na rozhraní)