fix: remove storageContext

2026-07-01 22:14:03 -04:00 · 2024-02-26 12:02:19 -03:00
3170 changed files with 127888 additions and 201058 deletions
@@ -1,7 +1,7 @@
 {
  "$schema": "https://unpkg.com/@changesets/config@2.3.1/schema.json",
  "changelog": "@changesets/cli/changelog",
-  "commit": false,
+  "commit": true,
  "fixed": [],
  "linked": [],
  "access": "public",
@@ -0,0 +1,5 @@
+---
+"llamaindex": patch
+---
+
+feat: add base evaluator and correctness evaluator
@@ -0,0 +1,5 @@
+---
+"llamaindex": patch
+---
+
+feat: add base evaluator and correctness evaluator
@@ -0,0 +1,6 @@
+---
+"llamaindex": patch
+"docs": patch
+---
+
+Add Groq LLM to LlamaIndex
@@ -1,16 +0,0 @@
-{
-  "jsc": {
-    "parser": {
-      "syntax": "typescript",
-      "decorators": true
-    },
-    "target": "esnext",
-    "transform": {
-      "decoratorVersion": "2022-03"
-    }
-  },
-  "module": {
-    "type": "commonjs",
-    "ignoreDynamic": true
-  }
-}
@@ -0,0 +1,15 @@
+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/", "lib/"],
+};
@@ -1,46 +0,0 @@
---
-name: Bug report
-about: Create a report to help us improve
-title: ""
-labels: bug
-assignees: ""
---
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-Code to reproduce the behavior:
-
-```ts
-// paste the code here
-```
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**Desktop (please complete the following information):**
-
- OS: [e.g. macOS, Linux]
- JS Runtime / Framework / Bundler (select all applicable)
- [ ] Node.js
- [ ] Deno
- [ ] Bun
- [ ] Next.js
- [ ] ESBuild
- [ ] Rollup
- [ ] Webpack
- [ ] Turbopack
- [ ] Vite
- [ ] Waku
- [ ] Edge Runtime
- [ ] AWS Lambda
- [ ] Cloudflare Worker
- [ ] Others (please elaborate on this)
- Version [e.g. 22]
-
-**Additional context**
-Add any other context about the problem here.
@@ -1,13 +0,0 @@
-name: Trigger Vercel Deploy
-
-on:
-  push:
-    branches: [main]
-
-jobs:
-  deploy:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Trigger Vercel deployment
-        run: |
-          curl -X POST "${{ secrets.DEVELOPER_HUB_DEPLOY_HOOK }}"
@@ -0,0 +1,68 @@
+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
@@ -8,17 +8,14 @@ on:
    branches:
      - main

-env:
-  TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
-  TURBO_TEAM: ${{ vars.TURBO_TEAM }}
-  TURBO_REMOTE_ONLY: true
-
 jobs:
  lint:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v2
+        with:
+          version: latest
      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
@@ -1,33 +0,0 @@
-name: Publish Preview
-on: [pull_request]
-
-env:
-  TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
-  TURBO_TEAM: ${{ vars.TURBO_TEAM }}
-  TURBO_REMOTE_ONLY: true
-
-jobs:
-  pre_release:
-    name: Pre Release
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout Repo
-        uses: actions/checkout@v4
-
-      - uses: pnpm/action-setup@v4
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version-file: ".nvmrc"
-          cache: "pnpm"
-
-      - name: Install dependencies
-        run: pnpm install
-
-      - name: Build
-        run: pnpm run build
-
-      - name: Pre Release
-        run: pnpx pkg-pr-new publish --pnpm ./packages/* ./packages/providers/* ./packages/providers/storage/*
@@ -1,37 +0,0 @@
-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@v4
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version-file: ".nvmrc"
-          cache: "pnpm"
-
-      - name: Install dependencies
-        run: pnpm install
-
-      - name: Build 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 }}
@@ -1,70 +0,0 @@
-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@v4
-
-      - 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 }}
-
-      # Refs: https://github.com/changesets/changesets/issues/421
-      - name: Update lock file
-        continue-on-error: true
-        run: pnpm install --lockfile-only
-
-      - name: Commit lock file
-        continue-on-error: true
-        uses: stefanzweifel/git-auto-commit-action@v5
-        with:
-          commit_message: "chore: update lock file"
-          branch: changeset-release/main
-          file_pattern: "pnpm-lock.yaml"
@@ -1,68 +1,18 @@
 name: Run Tests

-on:
-  push:
-    branches:
-      - main
-  pull_request:
-    branches:
-      - main
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-env:
-  POSTGRES_HOST_AUTH_METHOD: trust
-  TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
-  TURBO_TEAM: ${{ vars.TURBO_TEAM }}
-  TURBO_REMOTE_ONLY: true
+on: [push, pull_request]

 jobs:
-  e2e:
-    strategy:
-      fail-fast: false
-      matrix:
-        node-version: [20.x, 22.x, 23.x]
-    name: E2E on Node.js ${{ matrix.node-version }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ankane/setup-postgres@v1
-        with:
-          database: llamaindex_node_test
-          dev-files: true
-      - run: |
-          cd /tmp
-          git clone --branch v0.7.0 https://github.com/pgvector/pgvector.git
-          cd pgvector
-          make
-          sudo make install
-      - uses: pnpm/action-setup@v4
-      - 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: [20.x, 22.x, 23.x]
-    name: Test on Node.js ${{ matrix.node-version }}
    runs-on: ubuntu-latest
+
    steps:
      - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v2
      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
-          node-version: ${{ matrix.node-version }}
+          node-version-file: ".nvmrc"
          cache: "pnpm"
      - name: Install dependencies
        run: pnpm install
@@ -73,7 +23,7 @@ jobs:

    steps:
      - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v2
      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
@@ -82,95 +32,24 @@ jobs:
      - name: Install dependencies
        run: pnpm install
      - name: Build
-        run: pnpm run build
+        run: pnpm run build --filter llamaindex
      - name: Run Type Check
        run: pnpm run type-check
      - name: Run Circular Dependency Check
        run: pnpm run circular-check
-  e2e-npm:
-    runs-on: ubuntu-latest
-    name: Test using packages with npm
-    steps:
-      - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
+        working-directory: ./packages/core
+      - uses: actions/upload-artifact@v3
+        if: failure()
        with:
-          node-version-file: ".nvmrc"
-      - name: Install dependencies
-        run: pnpm install
-      - name: Build packages
-        run: pnpm run build
-      - name: Pack packages
-        run: |
-          pnpm pack --pack-destination ${{ runner.temp }} -C packages/llamaindex
-          pnpm pack --pack-destination ${{ runner.temp }} -C packages/workflow
-          pnpm pack --pack-destination ${{ runner.temp }} -C packages/core
-      - name: Install packed packages
-        run: npm add ${{ runner.temp }}/*.tgz
-        working-directory: e2e/npm
-      - name: Run tests
-        run: npm test
-        working-directory: e2e/npm
-  e2e-llamaindex-examples:
-    strategy:
-      fail-fast: false
-      matrix:
-        packages:
-          - cloudflare-worker-agent
-          - nextjs-agent
-          - nextjs-edge-runtime
-          - nextjs-node-runtime
-          - waku-query-engine
-          - vite-import-llamaindex
-    runs-on: ubuntu-latest
-    name: Build LlamaIndex Example (${{ matrix.packages }})
-    steps:
-      - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version-file: ".nvmrc"
-          cache: "pnpm"
-      - name: Install dependencies
-        run: pnpm install
-      - name: Build llamaindex
-        run: pnpm run build
-      - name: Build ${{ matrix.packages }}
-        run: pnpm run build
-        working-directory: e2e/examples/${{ matrix.packages }}
-
-  size-limit:
-    runs-on: ubuntu-latest
-    if: github.event_name == 'pull_request'
-    name: Size Limit
-    steps:
-      - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version-file: ".nvmrc"
-          cache: "pnpm"
-      - name: Install dependencies
-        run: pnpm install
-      - name: Build llamaindex
-        run: pnpm run build
-      - uses: andresz1/size-limit-action@94bc357df29c36c8f8d50ea497c3e225c3c95d1d
-        with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          directory: e2e/examples/vite-import-llamaindex
-          skip_step: "install"
-          build_script: ci-build
-          package_manager: pnpm
-
+          name: typecheck-build-dist
+          path: ./packages/core/dist
+          if-no-files-found: error
  typecheck-examples:
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v4
+      - uses: pnpm/action-setup@v2
      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
@@ -179,39 +58,18 @@ jobs:
      - name: Install dependencies
        run: pnpm install
      - name: Build
-        run: pnpm run build
+        run: pnpm run build --filter llamaindex
      - name: Copy examples
        run: rsync -rv --exclude=node_modules ./examples ${{ runner.temp }}
-      - name: Pack packages
-        run: |
-          for dir in packages/*; do
-            if [ -d "$dir" ] && [ -f "$dir/package.json" ] && [[ ! "$dir" =~ autotool ]]; then
-              echo "Packing $dir"
-              pnpm pack --pack-destination ${{ runner.temp }} -C $dir
-            else
-              echo "Skipping $dir, no package.json found"
-            fi
-          done
-      - name: Pack provider packages
-        run: |
-          for dir in packages/providers/* packages/providers/storage/*; do
-            if [ -d "$dir" ] && [ -f "$dir/package.json" ]; then
-              echo "Packing $dir"
-              pnpm pack --pack-destination ${{ runner.temp }} -C $dir
-            else
-              echo "Skipping $dir, no package.json found"
-            fi
-          done
+      - name: Pack @llamaindex/env
+        run: pnpm pack --pack-destination ${{ runner.temp }}
+        working-directory: packages/env
+      - name: Pack llamaindex
+        run: pnpm pack --pack-destination ${{ runner.temp }}
+        working-directory: packages/core
      - name: Install
-        run: npm add ${{ runner.temp }}/*.tgz --legacy-peer-deps
+        run: npm add ${{ runner.temp }}/*.tgz
        working-directory: ${{ runner.temp }}/examples
      - name: Run Type Check
        run: npx tsc --project ./tsconfig.json
        working-directory: ${{ runner.temp }}/examples
-      - uses: actions/upload-artifact@v4
-        if: failure()
-        with:
-          name: build-dist
-          path: |
-            ${{ runner.temp }}/*.tgz
-          if-no-files-found: error
@@ -44,10 +44,6 @@ test-results/
 playwright-report/
 blob-report/
 playwright/.cache/
-.tsbuildinfo

 # intellij
 **/.idea
-
-# generated API
-packages/cloud/src/client
@@ -1 +1,3 @@
-pnpm run lint-staged
+pnpm format
+pnpm lint
+npx lint-staged
@@ -0,0 +1 @@
+pnpm test
@@ -1,5 +1,2 @@
 auto-install-peers = true
 enable-pre-post-scripts = true
-prefer-workspace-packages = true
-save-workspace-protocol = true
-link-workspace-packages = true
@@ -1 +1 @@
-22
+18
@@ -3,9 +3,4 @@ apps/docs/docs/api
 pnpm-lock.yaml
 lib/
 dist/
-docs/
 .docusaurus/
-.source/
-# prttier doesn't support mdx3 we are using
-*.mdx
-packages/server/server/
@@ -1,12 +0,0 @@
-{
-  "jsc": {
-    "parser": {
-      "syntax": "typescript",
-      "decorators": true
-    },
-    "target": "esnext",
-    "transform": {
-      "decoratorVersion": "2022-03"
-    }
-  }
-}
@@ -10,9 +10,8 @@
      "name": "Debug Example",
      "skipFiles": ["<node_internals>/**"],
      "runtimeExecutable": "pnpm",
-      "console": "integratedTerminal",
      "cwd": "${workspaceFolder}/examples",
-      "runtimeArgs": ["npx", "tsx", "${file}"]
+      "runtimeArgs": ["ts-node", "${fileBasename}"]
    }
  ]
 }
@@ -1 +0,0 @@
-LlamaIndexTS
@@ -13,7 +13,5 @@
  },
  "[json]": {
    "editor.defaultFormatter": "esbenp.prettier-vscode"
-  },
-  "prettier.prettierPath": "./node_modules/prettier",
-  "prettier.configPath": "prettier.config.mjs"
+  }
 }
@@ -1,92 +0,0 @@
-# CLAUDE.md
-
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
-## Development Commands
-
-This project uses pnpm as the package manager and Turbo for build orchestration:
-
- `pnpm install` - Install all dependencies
- `pnpm build` - Build all packages using Turbo
- `pnpm dev` - Start development mode for all packages
- `pnpm test` - Run all unit tests
- `pnpm e2e` - Run end-to-end tests
- `pnpm lint` - Run ESLint across all packages
- `pnpm type-check` - Run TypeScript type checking across workspace
- `pnpm format` - Check code formatting with Prettier
- `pnpm format:write` - Auto-fix formatting issues
- `pnpm circular-check` - Check for circular dependencies using madge
-
-For individual package development:
-
- `turbo run build --filter="@llamaindex/core"` - Build specific package
- `turbo run test --filter="@llamaindex/core"` - Test specific package
- Navigate to specific package directory and run `pnpm test` for focused testing
- `pnpm clean` - Remove all build artifacts and node_modules across workspace
-
-## Architecture Overview
-
-LlamaIndex.TS is a TypeScript data framework for LLM applications organized as a pnpm monorepo with multiple runtime environment support (Node.js, Deno, Bun, Vercel Edge, Cloudflare Workers).
-
-### Package Structure
-
-**Core Packages:**
-
- `packages/core/` - Abstract base classes and interfaces for all runtime environments
- `packages/llamaindex/` - Main package that aggregates core functionality
- `packages/env/` - Environment-specific compatibility layers for different JS runtimes
-
-**Provider Packages (`packages/providers/`):**
-
- LLM providers: `openai/`, `anthropic/`, `ollama/`, `google/`, `groq/`, etc.
- Vector stores: `storage/pinecone/`, `storage/chroma/`, `storage/qdrant/`, etc.
- Embeddings: Various embedding providers integrated within LLM packages
- Readers: `assemblyai/`, `discord/`, `notion/` for data ingestion
-
-**Specialized Packages:**
-
- `packages/cloud/` - LlamaCloud integration for managed services
- `packages/tools/` - Function calling tools and utilities
- `packages/workflow/` - Agent workflow orchestration
- `packages/readers/` - File format readers (PDF, DOCX, etc.)
-
-### Key Architectural Patterns
-
-**Runtime Abstraction:** Core functionality is runtime-agnostic, with environment-specific implementations in separate entry points (`index.ts`, `index.edge.ts`, `index.workerd.ts`).
-
-**Provider Pattern:** LLMs, embeddings, and vector stores implement common interfaces from `@llamaindex/core`, allowing easy swapping between providers.
-
-**Modular Design:** Each provider is a separate package to minimize bundle size - users install only what they need.
-
-**Data Flow:** Document → NodeParser → Embedding → VectorStore → Retriever → QueryEngine → Response
-
-### Core Components
-
- **Agents and Workflows:** Abstractions for building agentic workflows and agents in `packages/workflow`
- **Chat Engines:** Conversational interfaces in `core/chat-engine/`
- **Query Engines:** Document querying with retrieval in `core/query-engine/`
- **Indices:** VectorStoreIndex, SummaryIndex, KeywordTable in `llamaindex/indices/`
- **Node Parsers:** Text splitting and chunking in `core/node-parser/`
- **Ingestion Pipeline:** Document processing workflows in `llamaindex/ingestion/`
- **Storage:** Chat stores, document stores, index stores, and KV stores in `core/storage/`
-
-### Deprecated Components
-
- **Agents:** ReAct and function calling agents in `core/agent/` and `llamaindex/agent/`
-
-### Testing Structure
-
- Unit tests in each package's `tests/` directory
- E2E tests in `e2e/` directory with runtime-specific examples
- Tests depend on build artifacts, so always run `pnpm build` before testing
-
-### Multi-Runtime Support
-
-The codebase supports multiple JavaScript runtimes through conditional exports and separate entry points. When making changes, consider compatibility across Node.js, Deno, Bun, and edge runtimes.
-
-### Development Notes
-
- The project uses Husky for git hooks with lint-staged for pre-commit formatting and linting
- All packages use bunchee for building with dual CJS/ESM support
- Core package exports are organized as sub-modules (e.g., `@llamaindex/core/llms`, `@llamaindex/core/embeddings`)
- Always run `pnpm build` before running tests, as tests depend on build artifacts
@@ -2,164 +2,91 @@

 ## Structure

-LlamaIndex.TS uses pnpm monorepo.
+This is a monorepo built with Turborepo

-We recommend you to understand the basics of Node.js, TypeScript, pnpm, and of course, LLM before contributing.
+Right now there are two packages of importance:

-There are some important folders in the repository:
+packages/core which is the main NPM library llamaindex

- `packages/*`: Contains the source code of the packages. Each package is a separate npm package.
-  - `llamaindex`: The starter package for LlamaIndex.TS, which contains the all sub-packages.
-  - `core`: The core package of LlamaIndex.TS, which contains the abstract classes and interfaces. It is designed for
-    all JS runtime environments.
-  - `env`: The environment package of LlamaIndex.TS, which contains the environment-specific classes and interfaces. It
-    includes compatibility layers for Node.js, Deno, Vercel Edge Runtime, Cloudflare Workers...
-  - `providers/*`: The providers package of LlamaIndex.TS, which contains the providers for LLM and other services.
- `apps/*`: The applications based on LlamaIndex.TS.
-  - `next`: Our documentation website based on Next.js.
- `examples`: The code examples of LlamaIndex.TS using Node.js.
+examples is where the demo code lives
+
+### Turborepo docs
+
+You can checkout how Turborepo works using the default [README-turborepo.md](/README-turborepo.md)

 ## Getting Started

-Make sure you have Node.js LTS (Long-term Support) installed. You can check your Node.js version by running:
+Install NodeJS. Preferably v18 using nvm or n.
+
+Inside the LlamaIndexTS directory:

-```shell
-node -v
-# v22.x.x
 ```
-
-### Use pnpm
-
-```shell
-npm install -g pnpm
-```
-
-### Install dependencies
-
-```shell
+npm i -g pnpm ts-node
 pnpm install
-pnpm install -g tsx
 ```

-### Build the packages
+Note: we use pnpm in this repo, which has a lot of the same functionality and CLI options as npm but it does do some things better in a monorepo, like centralizing dependencies and caching.

-To build all packages, run:
+PNPM's has documentation on its [workspace feature](https://pnpm.io/workspaces) and Turborepo had some [useful documentation also](https://turbo.build/repo/docs/core-concepts/monorepos/running-tasks).

-```shell
-pnpm build
+### Running Typescript
+
+When we publish to NPM we will have a tsc compiled version of the library in JS. For now, the easiest thing to do is use ts-node.
+
+### Test cases
+
+To run them, run
+
+```
+pnpm run test
 ```

-### Start Developing
+To write new test cases write them in [packages/core/src/tests](/packages/core/src/tests)

-You can launch the package in dev-mode by running:
+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

-```shell
-pnpm dev
+### Demo applications
+
+There is an existing ["example"](/examples/README.md) demos folder with mainly NodeJS scripts. Feel free to add additional demos to that folder. If you would like to try out your changes in the core package with a new demo, you need to run the build command in the README.
+
+You can create new demo applications in the apps folder. Just run pnpm init in the folder after you create it to create its own package.json
+
+### Installing packages
+
+To install packages for a specific package or demo application, run
+
+```
+pnpm add [NPM Package] --filter [package or application i.e. core or docs]
 ```

-This will use turbo to run all packages in watch-mode. This means you can make changes and have them automatically built.
+To install packages for every package or application run

-If you want to customize what packages are built/watched, you can run turbo directly and adjust the filter:
-
-```shell
-pnpm turbo run dev --filter="./packages/core" --concurrency=100
 ```
-
-In another terminal, you can write and run any script needed to quickly test your changes. For example:
-
-```typescript
-import { createMemory, staticBlock } from "@llamaindex/core/memory";
-
-// Create memory with predefined context
-const memory = createMemory({
-  memoryBlocks: [
-    staticBlock({
-      content:
-        "The user is a software engineer who loves TypeScript and LlamaIndex.",
-      messageRole: "system",
-    }),
-  ],
-});
-
-async function main() {
-  const result = await memory.getLLM();
-  console.log(result);
-}
-
-void main().catch(console.error);
+pnpm add -w [NPM Package]
 ```

-And run it with:
-
-```shell
-pnpm exec tsx my_script.ts
-```
-
-This flow allows you to easily test your changes without having to build the entire project.
-
-Once you are happy with your changes, be sure to add tests (and confirm existing tests are passing!).
-
-### Run tests
-
-#### Unit tests
-
-After build, to run all unit tests, call:
-
-```shell
-pnpm test
-```
-
-Unit tests are located in the `tests` folder of each package. They are using their own package (e.g. `@llamaindex/core-tests` for `@llamaindex/core`). The tests are importing the package under test and the test package is not published.
-
-#### E2E tests
-
-To run all E2E tests, call:
-
-```shell
-pnpm e2e
-```
-
-All E2E tests are in the `e2e` folder.
-
 ### Docs

-See the [docs](./apps/next/README.md) for more information.
+To contribute to the docs, go to the docs website folder and run the Docusaurus instance.

-## Adding a new package
-
-Please follow these steps to add a new package:
-
-1. Only add new packages to the `packages/providers` folder.
-2. Use the `package.json` and `tsconfig.json` of an existing packages as template.
-3. Reference your new package in the root `tsconfig.json` file
-4. Add your package to the `examples/package.json` file if you add a new example.
-
-## Before sending a PR
-
-Before sending a PR, make sure of the following:
-
-1. Tests are all running and you added meaningful tests for your change.
-2. If you have a new feature, document it in the `apps/next` docs folder.
-3. If you have a new feature, add a new example in the `examples` folder.
-4. You have a descriptive changeset for each PR:
-
-### Bumping the versions of packages you've modified
-
-We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new
-changeset, run in the root folder:
-
-```shell
-pnpm changeset
+```bash
+cd apps/docs
+pnpm install
+pnpm start
 ```

-You will be prompted to choose what packages need their versions bumped, and what kind of bump (major, minor or patch) is needed. Once you carry out this operation, the bumping will be automatic after the PR is merged.
+That should start a webserver which will serve the docs on https://localhost:3000

-## Publishing (maintainers only)
+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.

-The [Release Github Action](.github/workflows/release.yml) is automatically generating and updating a
-PR called "Release {version}".
+## Publishing

-This PR will update the `package.json` and `CHANGELOG.md` files of each package according to
-the current changesets in the [.changeset](.changeset) folder.
+To publish a new version of the library, run

-If this PR is merged it will automatically add version tags to the repository and publish the updated packages to NPM.
+```shell
+pnpm new-llamaindex
+pnpm new-create-llama
+pnpm release
+git push # push to the main branch
+git push --tags
+```
@@ -0,0 +1,81 @@
+# 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)
@@ -1,18 +1,13 @@
-<p align="center">
-  <img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" />
-</p>
-<h1 align="center">LlamaIndex.TS</h1>
-<h3 align="center">
-  Data framework for your LLM application.
-</h3>
+# LlamaIndex.TS

 [![NPM Version](https://img.shields.io/npm/v/llamaindex)](https://www.npmjs.com/package/llamaindex)
-[![NPM License](https://img.shields.io/npm/l/llamaindex)](https://github.com/run-llama/LlamaIndexTS/blob/main/LICENSE)
+[![NPM License](https://img.shields.io/npm/l/llamaindex)](https://www.npmjs.com/package/llamaindex)
 [![NPM Downloads](https://img.shields.io/npm/dm/llamaindex)](https://www.npmjs.com/package/llamaindex)
 [![Discord](https://img.shields.io/discord/1059199217496772688)](https://discord.com/invite/eN6D2HQ4aX)
-[![Twitter](https://img.shields.io/twitter/follow/llama_index)](https://x.com/llama_index)

-Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in JS runtime environments with TypeScript support.
+LlamaIndex is a data framework for your LLM application.
+
+Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in Typescript and Javascript.

 Documentation: https://ts.llamaindex.ai/

@@ -24,58 +19,58 @@ Try examples online:

 LlamaIndex.TS aims to be a lightweight, easy to use set of libraries to help you integrate large language models into your applications with your own data.

-## Compatibility
+## 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 >= 20 ✅
- Deno ✅
- Bun ✅
- Nitro ✅
- Vercel Edge Runtime ✅ (with some limitations)
- Cloudflare Workers ✅ (with some limitations)
-
-For now, browser support is limited due to the lack of support for [AsyncLocalStorage-like APIs](https://github.com/tc39/proposal-async-context)
-
-### Supported LLMs:
-
- OpenAI LLms
- Anthropic LLms
- Groq LLMs
- Llama2, Llama3, Llama3.1 LLMs
- MistralAI LLMs
- Fireworks LLMs
- DeepSeek LLMs
- ReplicateAI LLMs
- TogetherAI LLMs
- HuggingFace LLms
- DeepInfra LLMs
- Gemini LLMs
-
-## Getting started
-
-```shell
-npm install llamaindex
+```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
 pnpm install llamaindex
-yarn add llamaindex
+pnpm install @types/node
 ```

-### Setup in Node.js, Deno, Bun, TypeScript...?
+Create the file example.ts

-See our official document: https://ts.llamaindex.ai/docs/llamaindex/getting_started
+```ts
+// example.ts
+import fs from "fs/promises";
+import { Document, VectorStoreIndex } from "llamaindex";

-### Adding provider packages
+async function main() {
+  // Load essay from abramov.txt in Node
+  const essay = await fs.readFile(
+    "node_modules/llamaindex/examples/abramov.txt",
+    "utf-8",
+  );

-In most cases, you'll also need to install provider packages to use LlamaIndexTS. These are for adding AI models, file readers for ingestion or storing documents, e.g. in vector databases.
+  // Create Document object with essay
+  const document = new Document({ text: essay });

-For example, to use the OpenAI LLM, you would install the following package:
+  // Split text and create embeddings. Store them in a VectorStoreIndex
+  const index = await VectorStoreIndex.fromDocuments([document]);

-```shell
-npm install @llamaindex/openai
-pnpm install @llamaindex/openai
-yarn add @llamaindex/openai
+  // 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
+pnpm dlx ts-node example.ts
 ```

 ## Playground
@@ -84,13 +79,61 @@ Check out our NextJS playground at https://llama-playground.vercel.app/. The sou

 ## Core concepts for getting started:

-See our documentation: https://ts.llamaindex.ai/docs/llamaindex/getting_started/concepts
+- [Document](/packages/core/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.
+
+- [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.
+
+- [Indices](/packages/core/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.
+
+- [ChatEngine](/packages/core/src/ChatEngine.ts): A ChatEngine helps you build a chatbot that will interact with your Indices.
+
+- [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.
+
+## Note: NextJS:
+
+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.
+
+```js
+export const runtime = "nodejs"; // default
+```
+
+```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;
+  },
+};
+
+module.exports = nextConfig;
+```
+
+## Supported LLMs:
+
+- OpenAI GPT-3.5-turbo and GPT-4
+- Anthropic Claude Instant and Claude 2
+- Groq LLMs
+- Llama2 Chat LLMs (70B, 13B, and 7B parameters)
+- MistralAI Chat LLMs
+- Fireworks Chat LLMs

 ## Contributing:

-Please see our [contributing guide](CONTRIBUTING.md) for more information.
-You are highly encouraged to contribute to LlamaIndex.TS!
+We are in the very early days of LlamaIndex.TS. If you’re interested in hacking on it with us check out our [contributing guide](/CONTRIBUTING.md)

-## Community
+## Bugs? Questions?

 Please join our Discord! https://discord.com/invite/eN6D2HQ4aX
@@ -0,0 +1,21 @@
+# Dependencies
+/node_modules
+
+# Production
+/build
+
+# Generated files
+.docusaurus
+.cache-loader
+lib
+
+# Misc
+.DS_Store
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
@@ -0,0 +1,13 @@
+# docs
+
+## 0.0.2
+
+### Patch Changes
+
+- 0f64084: docs: update API references
+
+## 0.0.1
+
+### Patch Changes
+
+- 3154f52: chore: add qdrant readme
@@ -0,0 +1,47 @@
+# Website
+
+This website is built using [Docusaurus 2](https://docusaurus.io/), a modern static website generator.
+
+### Installation
+
+```
+$ pnpm
+```
+
+### Local Development
+
+```
+$ pnpm start
+```
+
+This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
+
+However, the searchbar may not function with `yarn start`. Instead, run `yarn build` and launch a server:
+
+```
+$ npx http-server ./build
+```
+
+### Build
+
+```
+$ pnpm build
+```
+
+This command generates static content into the `build` directory and can be served using any static contents hosting service.
+
+### Deployment
+
+Using SSH:
+
+```
+$ USE_SSH=true pnpm deploy
+```
+
+Not using SSH:
+
+```
+$ GIT_USER=<Your GitHub username> pnpm deploy
+```
+
+If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.
@@ -0,0 +1,3 @@
+module.exports = {
+  presets: [require.resolve("@docusaurus/core/lib/babel/preset")],
+};
@@ -0,0 +1 @@
+api/
@@ -0,0 +1,2 @@
+label: Examples
+position: 2
@@ -0,0 +1,85 @@
+# Agents
+
+A built-in agent that can take decisions and reasoning based on the tools provided to it.
+
+## OpenAI Agent
+
+```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 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");
+});
+```
@@ -0,0 +1,12 @@
+---
+sidebar_position: 1
+---
+
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../examples/chatEngine";
+
+# Chat Engine
+
+Chat Engine is a class that allows you to create a chatbot from a retriever. It is a wrapper around a retriever that allows you to chat with it in a conversational manner.
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
@@ -0,0 +1,7 @@
+---
+sidebar_position: 5
+---
+
+# More examples
+
+You can check out more examples in the [examples](https://github.com/run-llama/LlamaIndexTS/tree/main/examples) folder of the repository.
@@ -0,0 +1,10 @@
+---
+sidebar_position: 4
+---
+
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../examples/storageContext";
+
+# Save/Load an Index
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
@@ -0,0 +1,10 @@
+---
+sidebar_position: 3
+---
+
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../examples/summaryIndex";
+
+# Summary Index
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
@@ -0,0 +1,10 @@
+---
+sidebar_position: 2
+---
+
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../examples/vectorIndex";
+
+# Vector Index
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
@@ -0,0 +1,2 @@
+label: Getting Started
+position: 1
@@ -0,0 +1,78 @@
+---
+sidebar_position: 3
+---
+
+# Concepts
+
+LlamaIndex.TS helps you build LLM-powered applications (e.g. Q&A, chatbot) over custom data.
+
+In this high-level concepts guide, you will learn:
+
+- how an LLM can answer questions using your own data.
+- key concepts and modules in LlamaIndex.TS for composing your own query pipeline.
+
+## Answering Questions Across Your Data
+
+LlamaIndex uses a two stage method when using an LLM with your data:
+
+1. **indexing stage**: preparing a knowledge base, and
+2. **querying stage**: retrieving relevant context from the knowledge to assist the LLM in responding to a question
+
+![](../_static/concepts/rag.jpg)
+
+This process is also known as Retrieval Augmented Generation (RAG).
+
+LlamaIndex.TS provides the essential toolkit for making both steps super easy.
+
+Let's explore each stage in detail.
+
+### Indexing Stage
+
+LlamaIndex.TS help you prepare the knowledge base with a suite of data connectors and indexes.
+
+![](../_static/concepts/indexing.jpg)
+
+[**Data Loaders**](../modules/data_loader.md):
+A data connector (i.e. `Reader`) ingest data from different data sources and data formats into a simple `Document` representation (text and simple metadata).
+
+[**Documents / Nodes**](../modules/documents_and_nodes/index.md): A `Document` is a generic container around any data source - for instance, a PDF, an API output, or retrieved data from a database. A `Node` is the atomic unit of data in LlamaIndex and represents a "chunk" of a source `Document`. It's a rich representation that includes metadata and relationships (to other nodes) to enable accurate and expressive retrieval operations.
+
+[**Data Indexes**](../modules/data_index.md):
+Once you've ingested your data, LlamaIndex helps you index data into a format that's easy to retrieve.
+
+Under the hood, LlamaIndex parses the raw documents into intermediate representations, calculates vector embeddings, and stores your data in-memory or to disk.
+
+### Querying Stage
+
+In the querying stage, the query pipeline retrieves the most relevant context given a user query,
+and pass that to the LLM (along with the query) to synthesize a response.
+
+This gives the LLM up-to-date knowledge that is not in its original training data,
+(also reducing hallucination).
+
+The key challenge in the querying stage is retrieval, orchestration, and reasoning over (potentially many) knowledge bases.
+
+LlamaIndex provides composable modules that help you build and integrate RAG pipelines for Q&A (query engine), chatbot (chat engine), or as part of an agent.
+
+These building blocks can be customized to reflect ranking preferences, as well as composed to reason over multiple knowledge bases in a structured way.
+
+![](../_static/concepts/querying.jpg)
+
+#### Building Blocks
+
+[**Retrievers**](../modules/retriever.md):
+A retriever defines how to efficiently retrieve relevant context from a knowledge base (i.e. index) when given a query.
+The specific retrieval logic differs for difference indices, the most popular being dense retrieval against a vector index.
+
+[**Response Synthesizers**](../modules/response_synthesizer.md):
+A response synthesizer generates a response from an LLM, using a user query and a given set of retrieved text chunks.
+
+#### Pipelines
+
+[**Query Engines**](../modules/query_engines):
+A query engine is an end-to-end pipeline that allow you to ask question over your data.
+It takes in a natural language query, and returns a response, along with reference context retrieved and passed to the LLM.
+
+[**Chat Engines**](../modules/chat_engine.md):
+A chat engine is an end-to-end pipeline for having a conversation with your data
+(multiple back-and-forth instead of a single question & answer).
@@ -0,0 +1,15 @@
+---
+sidebar_position: 2
+---
+
+# Environments
+
+LlamaIndex currently officially supports NodeJS 18 and NodeJS 20.
+
+## NextJS App Router
+
+If you're using NextJS App Router route handlers/serverless functions, you'll need to use the NodeJS mode:
+
+```js
+export const runtime = "nodejs"; // default
+```
@@ -0,0 +1,63 @@
+---
+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
+
+## Installation from NPM
+
+```bash npm2yarn
+npm install llamaindex
+```
+
+### Environment variables
+
+Our examples use OpenAI by default. You'll need to set up your Open AI key like so:
+
+```bash
+export OPENAI_API_KEY="sk-......" # Replace with your key from https://platform.openai.com/account/api-keys
+```
+
+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.
@@ -0,0 +1,56 @@
+---
+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
@@ -0,0 +1,56 @@
+---
+sidebar_position: 0
+slug: /
+---
+
+# What is LlamaIndex.TS?
+
+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.
+
+## 🚀 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.
+
+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.
+
+That's where **LlamaIndex.TS** comes in.
+
+## 🦙 How can LlamaIndex.TS help?
+
+LlamaIndex.TS provides the following tools:
+
+- **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.
+
+## 👨‍👩‍👧‍👦 Who is LlamaIndex for?
+
+LlamaIndex.TS provides a core set of tools, essential for anyone building LLM apps with JavaScript and TypeScript.
+
+Our high-level API allows beginner users to use LlamaIndex.TS to ingest and query their data.
+
+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.
+
+## Getting Started
+
+`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.
+
+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.
+
+## 🗺️ Ecosystem
+
+To download or contribute, find LlamaIndex on:
+
+- Github: https://github.com/run-llama/LlamaIndexTS
+- NPM: https://www.npmjs.com/package/llamaindex
+
+## Community
+
+Need help? Have a feature suggestion? Join the LlamaIndex community:
+
+- Twitter: https://twitter.com/llama_index
+- Discord https://discord.gg/dGcwcsnxhU
@@ -0,0 +1,3 @@
+label: "Modules"
+collapsed: false
+position: 5
@@ -0,0 +1,2 @@
+label: "Agents"
+position: 3
@@ -0,0 +1,14 @@
+# Agents
+
+An “agent” is an automated reasoning and decision engine. It takes in a user input/query and can make internal decisions for executing that query in order to return the correct result. The key agent components can include, but are not limited to:
+
+- Breaking down a complex question into smaller ones
+- Choosing an external Tool to use + coming up with parameters for calling the Tool
+- Planning out a set of tasks
+- Storing previously completed tasks in a memory module
+
+## Getting Started
+
+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)
@@ -0,0 +1,314 @@
+# 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)
@@ -0,0 +1,187 @@
+---
+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");
+});
+```
@@ -0,0 +1,132 @@
+---
+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");
+});
+```
@@ -0,0 +1,203 @@
+# 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");
+});
+```
@@ -0,0 +1,29 @@
+---
+sidebar_position: 4
+---
+
+# ChatEngine
+
+The chat engine is a quick and simple way to chat with the data in your index.
+
+```typescript
+const retriever = index.asRetriever();
+const chatEngine = new ContextChatEngine({ retriever });
+
+// start chatting
+const response = await chatEngine.chat({ message: query });
+```
+
+The `chat` function also supports streaming, just add `stream: true` as an option:
+
+```typescript
+const stream = await chatEngine.chat({ message: query, stream: true });
+for await (const chunk of stream) {
+  process.stdout.write(chunk.response);
+}
+```
+
+## Api References
+
+- [ContextChatEngine](../api/classes/ContextChatEngine.md)
+- [CondenseQuestionChatEngine](../api/classes/ContextChatEngine.md)
@@ -0,0 +1,23 @@
+---
+sidebar_position: 4
+---
+
+# Index
+
+An index is the basic container and organization for your data. LlamaIndex.TS supports two indexes:
+
+- `VectorStoreIndex` - will send the top-k `Node`s to the LLM when generating a response. The default top-k is 2.
+- `SummaryIndex` - will send every `Node` in the index to the LLM in order to generate a response
+
+```typescript
+import { Document, VectorStoreIndex } from "llamaindex";
+
+const document = new Document({ text: "test" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## API Reference
+
+- [SummaryIndex](../api/classes/SummaryIndex.md)
+- [VectorStoreIndex](../api/classes/VectorStoreIndex.md)
@@ -0,0 +1,48 @@
+---
+sidebar_position: 4
+---
+
+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";
+
+# Loader
+
+Before you can start indexing your documents, you need to load them into memory.
+
+### SimpleDirectoryReader
+
+[![Open in StackBlitz](https://developer.stackblitz.com/img/open_in_stackblitz.svg)](https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples/readers?file=src/simple-directory-reader.ts&title=Simple%20Directory%20Reader)
+
+LlamaIndex.TS supports easy loading of files from folders using the `SimpleDirectoryReader` class.
+
+It is a simple reader that reads all files from a directory and its subdirectories.
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
+
+Currently, it supports reading `.csv`, `.docx`, `.html`, `.md` and `.pdf` 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.
+
+<CodeBlock language="ts" showLineNumbers metastring="{8-12,17-21}">
+  {CodeSource2}
+</CodeBlock>
+
+### LlamaParse
+
+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`.
+
+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:
+
+<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.
+
+## API Reference
+
+- [SimpleDirectoryReader](../api/classes/SimpleDirectoryReader.md)
@@ -0,0 +1,2 @@
+label: "Document / Nodes"
+position: 0
@@ -0,0 +1,18 @@
+---
+sidebar_position: 1
+---
+
+# Documents and Nodes
+
+`Document`s and `Node`s are the basic building blocks of any index. While the API for these objects is similar, `Document` objects represent entire files, while `Node`s are smaller pieces of that original document, that are suitable for an LLM and Q&A.
+
+```typescript
+import { Document } from "llamaindex";
+
+document = new Document({ text: "text", metadata: { key: "val" } });
+```
+
+## API Reference
+
+- [Document](../api/classes/Document.md)
+- [TextNode](../api/classes/TextNode.md)
@@ -0,0 +1,45 @@
+# Metadata Extraction Usage Pattern
+
+You can use LLMs to automate metadata extraction with our `Metadata Extractor` modules.
+
+Our metadata extractor modules include the following "feature extractors":
+
+- `SummaryExtractor` - automatically extracts a summary over a set of Nodes
+- `QuestionsAnsweredExtractor` - extracts a set of questions that each Node can answer
+- `TitleExtractor` - extracts a title over the context of each Node by document and combine them
+- `KeywordExtractor` - extracts keywords over the context of each Node
+
+Then you can chain the `Metadata Extractors` with the `IngestionPipeline` to extract metadata from a set of documents.
+
+```ts
+import {
+  IngestionPipeline,
+  TitleExtractor,
+  QuestionsAnsweredExtractor,
+  Document,
+  OpenAI,
+} from "llamaindex";
+
+async function main() {
+  const pipeline = new IngestionPipeline({
+    transformations: [
+      new TitleExtractor(),
+      new QuestionsAnsweredExtractor({
+        questions: 5,
+      }),
+    ],
+  });
+
+  const nodes = await pipeline.run({
+    documents: [
+      new Document({ text: "I am 10 years old. John is 20 years old." }),
+    ],
+  });
+
+  for (const node of nodes) {
+    console.log(node.metadata);
+  }
+}
+
+main().then(() => console.log("done"));
+```
@@ -0,0 +1,2 @@
+label: "Embeddings"
+position: 3
@@ -0,0 +1 @@
+label: "Available Embeddings"
@@ -0,0 +1,25 @@
+# HuggingFace
+
+To use HuggingFace embeddings, you need to import `HuggingFaceEmbedding` from `llamaindex`.
+
+```ts
+import { HuggingFaceEmbedding, serviceContextFromDefaults } from "llamaindex";
+
+const huggingFaceEmbeds = new HuggingFaceEmbedding();
+
+const serviceContext = serviceContextFromDefaults({ embedModel: openaiEmbeds });
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document], {
+  serviceContext,
+});
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
@@ -0,0 +1,29 @@
+# MistralAI
+
+To use MistralAI embeddings, you need to import `MistralAIEmbedding` from `llamaindex`.
+
+```ts
+import { MistralAIEmbedding, serviceContextFromDefaults } from "llamaindex";
+
+const mistralEmbedModel = 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 queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
@@ -0,0 +1,27 @@
+# Ollama
+
+To use Ollama embeddings, you need to import `Ollama` from `llamaindex`.
+
+```ts
+import { Ollama, serviceContextFromDefaults } from "llamaindex";
+
+const ollamaEmbedModel = new Ollama();
+
+const serviceContext = serviceContextFromDefaults({
+  embedModel: ollamaEmbedModel,
+});
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document], {
+  serviceContext,
+});
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
@@ -0,0 +1,27 @@
+# OpenAI
+
+To use OpenAI embeddings, you need to import `OpenAIEmbedding` from `llamaindex`.
+
+```ts
+import { OpenAIEmbedding, serviceContextFromDefaults } from "llamaindex";
+
+const openaiEmbedModel = new OpenAIEmbedding();
+
+const serviceContext = serviceContextFromDefaults({
+  embedModel: openaiEmbedModel,
+});
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document], {
+  serviceContext,
+});
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
@@ -0,0 +1,29 @@
+# Together
+
+To use together embeddings, you need to import `TogetherEmbedding` from `llamaindex`.
+
+```ts
+import { TogetherEmbedding, serviceContextFromDefaults } from "llamaindex";
+
+const togetherEmbedModel = 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 queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
@@ -0,0 +1,22 @@
+# Embedding
+
+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.
+
+```typescript
+import { OpenAIEmbedding, serviceContextFromDefaults } from "llamaindex";
+
+const openaiEmbeds = new OpenAIEmbedding();
+
+const serviceContext = serviceContextFromDefaults({ embedModel: openaiEmbeds });
+```
+
+## Local Embedding
+
+For local embeddings, you can use the [HuggingFace](./available_embeddings/huggingface.md) embedding model.
+
+## API Reference
+
+- [OpenAIEmbedding](../../api/classes/OpenAIEmbedding.md)
+- [ServiceContext](../../api/interfaces//ServiceContext.md)
@@ -0,0 +1,2 @@
+label: "Evaluating"
+position: 3
@@ -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)
@@ -0,0 +1 @@
+label: "Modules"
@@ -0,0 +1,72 @@
+# 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,
+  serviceContextFromDefaults,
+} from "llamaindex";
+```
+
+Let's setup gpt-4 for better results:
+
+```ts
+const llm = new OpenAI({
+  model: "gpt-4",
+});
+
+const ctx = serviceContextFromDefaults({
+  llm,
+});
+```
+
+```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({
+  serviceContext: ctx,
+});
+
+const response = await queryEngine.query({
+  query,
+});
+
+const result = await evaluator.evaluateResponse({
+  query,
+  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
+```
@@ -0,0 +1,84 @@
+# 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,
+  serviceContextFromDefaults,
+} from "llamaindex";
+```
+
+Let's setup gpt-4 for better results:
+
+```ts
+const llm = new OpenAI({
+  model: "gpt-4",
+});
+
+const ctx = serviceContextFromDefaults({
+  llm,
+});
+```
+
+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({
+  serviceContext: ctx,
+});
+
+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
+```
@@ -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,
+  serviceContextFromDefaults,
+} from "llamaindex";
+```
+
+Let's setup gpt-4 for better results:
+
+```ts
+const llm = new OpenAI({
+  model: "gpt-4",
+});
+
+const ctx = serviceContextFromDefaults({
+  llm,
+});
+```
+
+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 result = await evaluator.evaluateResponse({
+  query,
+  response: response,
+});
+
+console.log(`the response is ${result.passing ? "relevant" : "not relevant"}`);
+```
+
+```bash
+the response is relevant
+```
@@ -0,0 +1,2 @@
+label: "Ingestion Pipeline"
+position: 2
@@ -0,0 +1,99 @@
+# Ingestion Pipeline
+
+An `IngestionPipeline` uses a concept of `Transformations` that are applied to input data.
+These `Transformations` are applied to your input data, and the resulting nodes are either returned or inserted into a vector database (if given).
+
+## Usage Pattern
+
+The simplest usage is to instantiate an IngestionPipeline like so:
+
+```ts
+import fs from "node:fs/promises";
+
+import {
+  Document,
+  IngestionPipeline,
+  MetadataMode,
+  OpenAIEmbedding,
+  TitleExtractor,
+  SimpleNodeParser,
+} from "llamaindex";
+
+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 });
+  const pipeline = new IngestionPipeline({
+    transformations: [
+      new SimpleNodeParser({ chunkSize: 1024, chunkOverlap: 20 }),
+      new TitleExtractor(),
+      new OpenAIEmbedding(),
+    ],
+  });
+
+  // run the pipeline
+  const nodes = await pipeline.run({ documents: [document] });
+
+  // print out the result of the pipeline run
+  for (const node of nodes) {
+    console.log(node.getContent(MetadataMode.NONE));
+  }
+}
+
+main().catch(console.error);
+```
+
+## Connecting to Vector Databases
+
+When running an ingestion pipeline, you can also chose to automatically insert the resulting nodes into a remote vector store.
+
+Then, you can construct an index from that vector store later on.
+
+```ts
+import fs from "node:fs/promises";
+
+import {
+  Document,
+  IngestionPipeline,
+  MetadataMode,
+  OpenAIEmbedding,
+  TitleExtractor,
+  SimpleNodeParser,
+  QdrantVectorStore,
+  VectorStoreIndex,
+} from "llamaindex";
+
+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");
+
+  const vectorStore = new QdrantVectorStore({
+    host: "http://localhost:6333",
+  });
+
+  // Create Document object with essay
+  const document = new Document({ text: essay, id_: path });
+  const pipeline = new IngestionPipeline({
+    transformations: [
+      new SimpleNodeParser({ chunkSize: 1024, chunkOverlap: 20 }),
+      new TitleExtractor(),
+      new OpenAIEmbedding(),
+    ],
+    vectorStore,
+  });
+
+  // run the pipeline
+  const nodes = await pipeline.run({ documents: [document] });
+
+  // create an index
+  const index = VectorStoreIndex.fromVectorStore(vectorStore);
+}
+
+main().catch(console.error);
+```
@@ -0,0 +1,77 @@
+# 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
+
+Currently, the following components are Transformation objects:
+
+- [SimpleNodeParser](../api/classes/SimpleNodeParser.md)
+- [MetadataExtractor](../documents_and_nodes/metadata_extraction.md)
+- Embeddings
+
+## Usage Pattern
+
+While transformations are best used with with an IngestionPipeline, they can also be used directly.
+
+```ts
+import { SimpleNodeParser, TitleExtractor, Document } from "llamaindex";
+
+async function main() {
+  let nodes = new SimpleNodeParser().getNodesFromDocuments([
+    new Document({ text: "I am 10 years old. John is 20 years old." }),
+  ]);
+
+  const titleExtractor = new TitleExtractor();
+
+  nodes = await titleExtractor.transform(nodes);
+
+  for (const node of nodes) {
+    console.log(node.getContent(MetadataMode.NONE));
+  }
+}
+
+main().catch(console.error);
+```
+
+## Custom Transformations
+
+You can implement any transformation yourself by implementing the `TransformerComponent`.
+
+The following custom transformation will remove any special characters or punctutaion in text.
+
+```ts
+import { TransformerComponent, Node } from "llamaindex";
+
+class RemoveSpecialCharacters extends TransformerComponent {
+  async transform(nodes: Node[]): Promise<Node[]> {
+    for (const node of nodes) {
+      node.text = node.text.replace(/[^\w\s]/gi, "");
+    }
+
+    return nodes;
+  }
+}
+```
+
+These can then be used directly or in any IngestionPipeline.
+
+```ts
+import { IngestionPipeline, Document } from "llamaindex";
+
+async function main() {
+  const pipeline = new IngestionPipeline({
+    transformations: [new RemoveSpecialCharacters()],
+  });
+
+  const nodes = await pipeline.run({
+    documents: [
+      new Document({ text: "I am 10 years old. John is 20 years old." }),
+    ],
+  });
+
+  for (const node of nodes) {
+    console.log(node.getContent(MetadataMode.NONE));
+  }
+}
+
+main().catch(console.error);
+```
@@ -0,0 +1,32 @@
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../examples/cloud/chat.ts";
+
+# LlamaCloud
+
+LlamaCloud is a new generation of managed parsing, ingestion, and retrieval services, designed to bring production-grade context-augmentation to your LLM and RAG applications.
+
+Currently, LlamaCloud supports
+
+- Managed Ingestion API, handling parsing and document management
+- Managed Retrieval API, configuring optimal retrieval for your RAG system
+
+## Access
+
+We are opening up a private beta to a limited set of enterprise partners for the managed ingestion and retrieval API. If you’re interested in centralizing your data pipelines and spending more time working on your actual RAG use cases, come [talk to us.](https://www.llamaindex.ai/contact)
+
+If you have access to LlamaCloud, you can visit [LlamaCloud](https://cloud.llamaindex.ai) to sign in and get an API key.
+
+## Create a Managed Index
+
+Currently, you can't create a managed index on LlamaCloud using LlamaIndexTS, but you can use an existing managed index for retrieval that was created by the Python version of LlamaIndex. See [the LlamaCloudIndex documentation](https://docs.llamaindex.ai/en/stable/module_guides/indexing/llama_cloud_index.html#usage) for more information on how to create a managed index.
+
+## Use a Managed Index
+
+Here's an example of how to use a managed index together with a chat engine:
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
+
+## API Reference
+
+- [LlamaCloudIndex](../api/classes/LlamaCloudIndex.md)
+- [LlamaCloudRetriever](../api/classes/LlamaCloudRetriever.md)
@@ -0,0 +1,2 @@
+label: "LLMs"
+position: 3
@@ -0,0 +1 @@
+label: "Available LLMs"
@@ -0,0 +1,80 @@
+# Anthropic
+
+## Usage
+
+```ts
+import { Anthropic, serviceContextFromDefaults } from "llamaindex";
+
+const anthropicLLM = new Anthropic({
+  apiKey: "<YOUR_API_KEY>",
+});
+
+const serviceContext = serviceContextFromDefaults({ llm: anthropicLLM });
+```
+
+## 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], {
+  serviceContext,
+});
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import {
+  Anthropic,
+  Document,
+  VectorStoreIndex,
+  serviceContextFromDefaults,
+} from "llamaindex";
+
+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,
+  });
+
+  // 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);
+}
+```
@@ -0,0 +1,91 @@
+# Azure OpenAI
+
+To use Azure OpenAI, you only need to set a few environment variables together with the `OpenAI` class.
+
+For example:
+
+## Environment Variables
+
+```
+export AZURE_OPENAI_KEY="<YOUR KEY HERE>"
+export AZURE_OPENAI_ENDPOINT="<YOUR ENDPOINT, see https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart?tabs=command-line%2Cpython&pivots=rest-api>"
+export AZURE_OPENAI_DEPLOYMENT="gpt-4" # or some other deployment name
+```
+
+## Usage
+
+```ts
+import { OpenAI, serviceContextFromDefaults } from "llamaindex";
+
+const azureOpenaiLLM = new OpenAI({ model: "gpt-4", temperature: 0 });
+
+const serviceContext = serviceContextFromDefaults({ llm: azureOpenaiLLM });
+```
+
+## 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], {
+  serviceContext,
+});
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import {
+  OpenAI,
+  Document,
+  VectorStoreIndex,
+  serviceContextFromDefaults,
+} from "llamaindex";
+
+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,
+  });
+
+  // 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);
+}
+```
@@ -0,0 +1,65 @@
+# Fireworks LLM
+
+Fireworks.ai focus on production use cases for open source LLMs, offering speed and quality.
+
+## Usage
+
+```ts
+import { FireworksLLM, serviceContextFromDefaults } from "llamaindex";
+
+const fireworksLLM = new FireworksLLM({
+  apiKey: "<YOUR_API_KEY>",
+});
+
+const serviceContext = serviceContextFromDefaults({ llm: fireworksLLM });
+```
+
+## Load and index documents
+
+For this example, we will load the Berkshire Hathaway 2022 annual report pdf
+
+```ts
+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,
+});
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+const response = await queryEngine.query({
+  query: "What mistakes did Warren E. Buffett make?",
+});
+```
+
+## Full Example
+
+```ts
+import { VectorStoreIndex } from "llamaindex";
+import { PDFReader } from "llamaindex/readers/PDFReader";
+
+async function main() {
+  // Load PDF
+  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);
+
+  // Query the index
+  const queryEngine = index.asQueryEngine();
+  const response = await queryEngine.query({
+    query: "What mistakes did Warren E. Buffett make?",
+  });
+
+  // Output response
+  console.log(response.toString());
+}
+
+main().catch(console.error);
+```
@@ -0,0 +1,56 @@
+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, serviceContextFromDefaults } from "llamaindex";
+
+const groq = 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>",
+});
+
+const serviceContext = serviceContextFromDefaults({ llm: groq });
+```
+
+## 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], {
+  serviceContext,
+});
+```
+
+## 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>
@@ -0,0 +1,100 @@
+# LLama2
+
+## Usage
+
+```ts
+import { Ollama, serviceContextFromDefaults } from "llamaindex";
+
+const llama2LLM = new LlamaDeuce({ chatStrategy: DeuceChatStrategy.META });
+
+const serviceContext = serviceContextFromDefaults({ llm: llama2LLM });
+```
+
+## Usage with Replication
+
+```ts
+import {
+  Ollama,
+  ReplicateSession,
+  serviceContextFromDefaults,
+} from "llamaindex";
+
+const replicateSession = new ReplicateSession({
+  replicateKey,
+});
+
+const llama2LLM = new LlamaDeuce({
+  chatStrategy: DeuceChatStrategy.META,
+  replicateSession,
+});
+
+const serviceContext = serviceContextFromDefaults({ llm: llama2LLM });
+```
+
+## 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], {
+  serviceContext,
+});
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import {
+  LlamaDeuce,
+  Document,
+  VectorStoreIndex,
+  serviceContextFromDefaults,
+} from "llamaindex";
+
+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,
+  });
+
+  // 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);
+}
+```
@@ -0,0 +1,82 @@
+# Mistral
+
+## Usage
+
+```ts
+import { Ollama, serviceContextFromDefaults } from "llamaindex";
+
+const mistralLLM = new MistralAI({
+  model: "mistral-tiny",
+  apiKey: "<YOUR_API_KEY>",
+});
+
+const serviceContext = serviceContextFromDefaults({ llm: mistralLLM });
+```
+
+## 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], {
+  serviceContext,
+});
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import {
+  MistralAI,
+  Document,
+  VectorStoreIndex,
+  serviceContextFromDefaults,
+} from "llamaindex";
+
+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,
+  });
+
+  // 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);
+}
+```
@@ -0,0 +1,89 @@
+# Ollama
+
+## Usage
+
+```ts
+import { Ollama, serviceContextFromDefaults } from "llamaindex";
+
+const ollamaLLM = new Ollama({ model: "llama2", temperature: 0.75 });
+
+const serviceContext = serviceContextFromDefaults({
+  llm: ollamaLLM,
+  embedModel: ollamaLLM,
+});
+```
+
+## 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], {
+  serviceContext,
+});
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import {
+  Ollama,
+  Document,
+  VectorStoreIndex,
+  serviceContextFromDefaults,
+} from "llamaindex";
+
+import fs from "fs/promises";
+
+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,
+  });
+
+  // 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);
+}
+```
@@ -0,0 +1,83 @@
+# OpenAI
+
+```ts
+import { OpenAI, serviceContextFromDefaults } from "llamaindex";
+
+const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0, apiKey: <YOUR_API_KEY> });
+
+const serviceContext = serviceContextFromDefaults({ llm: openaiLLM });
+```
+
+You can setup the apiKey on the environment variables, like:
+
+```bash
+export OPENAI_API_KEY="<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], {
+  serviceContext,
+});
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import {
+  OpenAI,
+  Document,
+  VectorStoreIndex,
+  serviceContextFromDefaults,
+} from "llamaindex";
+
+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,
+  });
+
+  // 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);
+}
+```
@@ -0,0 +1,83 @@
+# Portkey LLM
+
+## Usage
+
+```ts
+import { Portkey, serviceContextFromDefaults } from "llamaindex";
+
+const portkeyLLM = new Portkey({
+  apiKey: "<YOUR_API_KEY>",
+});
+
+const serviceContext = serviceContextFromDefaults({ llm: portkeyLLM });
+```
+
+## 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], {
+  serviceContext,
+});
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import {
+  Portkey,
+  Document,
+  VectorStoreIndex,
+  serviceContextFromDefaults,
+} from "llamaindex";
+
+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 });
+
+  const document = new Document({ text: essay, id_: "essay" });
+
+  // Load and index documents
+  const index = await VectorStoreIndex.fromDocuments([document], {
+    serviceContext,
+  });
+
+  // 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);
+}
+```
@@ -0,0 +1,83 @@
+# Together LLM
+
+## Usage
+
+```ts
+import { TogetherLLM, serviceContextFromDefaults } from "llamaindex";
+
+const togetherLLM = new TogetherLLM({
+  apiKey: "<YOUR_API_KEY>",
+});
+
+const serviceContext = serviceContextFromDefaults({ llm: togetherLLM });
+```
+
+## 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], {
+  serviceContext,
+});
+```
+
+## Query
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## Full Example
+
+```ts
+import {
+  TogetherLLM,
+  Document,
+  VectorStoreIndex,
+  serviceContextFromDefaults,
+} from "llamaindex";
+
+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,
+  });
+
+  // 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);
+}
+```
@@ -0,0 +1,38 @@
+---
+sidebar_position: 3
+---
+
+# Large Language Models (LLMs)
+
+The LLM is responsible for reading text and generating natural language responses to queries. By default, LlamaIndex.TS uses `gpt-3.5-turbo`.
+
+The LLM can be explicitly set in the `ServiceContext` object.
+
+```typescript
+import { OpenAI, serviceContextFromDefaults } from "llamaindex";
+
+const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
+
+const serviceContext = serviceContextFromDefaults({ llm: openaiLLM });
+```
+
+## Azure OpenAI
+
+To use Azure OpenAI, you only need to set a few environment variables.
+
+For example:
+
+```
+export AZURE_OPENAI_KEY="<YOUR KEY HERE>"
+export AZURE_OPENAI_ENDPOINT="<YOUR ENDPOINT, see https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart?tabs=command-line%2Cpython&pivots=rest-api>"
+export AZURE_OPENAI_DEPLOYMENT="gpt-4" # or some other deployment name
+```
+
+## Local LLM
+
+For local LLMs, currently we recommend the use of [Ollama](./available_llms/ollama.md) LLM.
+
+## API Reference
+
+- [OpenAI](../api/classes/OpenAI.md)
+- [ServiceContext](../api/interfaces//ServiceContext.md)
@@ -0,0 +1,98 @@
+---
+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.
+
+```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." }),
+]);
+```
+
+## TextSplitter
+
+The underlying text splitter will split text by sentences. It can also be used as a standalone module for splitting raw text.
+
+```typescript
+import { SentenceSplitter } from "llamaindex";
+
+const splitter = new SentenceSplitter({ chunkSize: 1 });
+
+const textSplits = splitter.splitText("Hello World");
+```
+
+## MarkdownNodeParser
+
+The `MarkdownNodeParser` is a more advanced `NodeParser` that can handle markdown documents. It will split the markdown into nodes and then parse the nodes into a `Document` object.
+
+```typescript
+import { MarkdownNodeParser } from "llamaindex";
+
+const nodeParser = new MarkdownNodeParser();
+
+const nodes = nodeParser.getNodesFromDocuments([
+  new Document({
+    text: `# Main Header
+Main content
+
+# Header 2
+Header 2 content
+
+## Sub-header
+Sub-header content
+
+  `,
+  }),
+]);
+```
+
+The output metadata will be something like:
+
+```bash
+[
+  TextNode {
+    id_: '008e41a8-b097-487c-bee8-bd88b9455844',
+    metadata: { 'Header 1': 'Main Header' },
+    excludedEmbedMetadataKeys: [],
+    excludedLlmMetadataKeys: [],
+    relationships: { PARENT: [Array] },
+    hash: 'KJ5e/um/RkHaNR6bonj9ormtZY7I8i4XBPVYHXv1A5M=',
+    text: 'Main Header\nMain content',
+    textTemplate: '',
+    metadataSeparator: '\n'
+  },
+  TextNode {
+    id_: '0f5679b3-ba63-4aff-aedc-830c4208d0b5',
+    metadata: { 'Header 1': 'Header 2' },
+    excludedEmbedMetadataKeys: [],
+    excludedLlmMetadataKeys: [],
+    relationships: { PARENT: [Array] },
+    hash: 'IP/g/dIld3DcbK+uHzDpyeZ9IdOXY4brxhOIe7wc488=',
+    text: 'Header 2\nHeader 2 content',
+    textTemplate: '',
+    metadataSeparator: '\n'
+  },
+  TextNode {
+    id_: 'e81e9bd0-121c-4ead-8ca7-1639d65fdf90',
+    metadata: { 'Header 1': 'Header 2', 'Header 2': 'Sub-header' },
+    excludedEmbedMetadataKeys: [],
+    excludedLlmMetadataKeys: [],
+    relationships: { PARENT: [Array] },
+    hash: 'B3kYNnxaYi9ghtAgwza0ZEVKF4MozobkNUlcekDL7JQ=',
+    text: 'Sub-header\nSub-header content',
+    textTemplate: '',
+    metadataSeparator: '\n'
+  }
+]
+```
+
+## API Reference
+
+- [SimpleNodeParser](../api/classes/SimpleNodeParser.md)
+- [SentenceSplitter](../api/classes/SentenceSplitter.md)
@@ -0,0 +1,2 @@
+label: "Node Postprocessors"
+position: 3
@@ -0,0 +1,71 @@
+# Cohere Reranker
+
+The Cohere Reranker is a postprocessor that uses the Cohere 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 [Cohere](https://cohere.ai/). Once you have your API key you can import the necessary modules and create a new instance of the `CohereRerank` class.
+
+```ts
+import {
+  CohereRerank,
+  Document,
+  OpenAI,
+  VectorStoreIndex,
+  serviceContextFromDefaults,
+} 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" });
+
+const serviceContext = serviceContextFromDefaults({
+  llm: new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.1 }),
+});
+
+const index = await VectorStoreIndex.fromDocuments([document], {
+  serviceContext,
+});
+```
+
+## 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 CohereRerank class
+
+Then you can create a new instance of the `CohereRerank` class and pass in your API key and the number of results you want to return.
+
+```ts
+const nodePostprocessor = new CohereRerank({
+  apiKey: "<COHERE_API_KEY>",
+  topN: 4,
+});
+```
+
+## 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?");
+```
@@ -0,0 +1,110 @@
+# Node Postprocessors
+
+## Concept
+
+Node postprocessors are a set of modules that take a set of nodes, and apply some kind of transformation or filtering before returning them.
+
+In LlamaIndex, node postprocessors are most commonly applied within a query engine, after the node retrieval step and before the response synthesis step.
+
+LlamaIndex offers several node postprocessors for immediate use, while also providing a simple API for adding your own custom postprocessors.
+
+## Usage Pattern
+
+An example of using a node postprocessors is below:
+
+```ts
+import {
+  Node,
+  NodeWithScore,
+  SimilarityPostprocessor,
+  CohereRerank,
+} from "llamaindex";
+
+const nodes: NodeWithScore[] = [
+  {
+    node: new TextNode({ text: "hello world" }),
+    score: 0.8,
+  },
+  {
+    node: new TextNode({ text: "LlamaIndex is the best" }),
+    score: 0.6,
+  },
+];
+
+// similarity postprocessor: filter nodes below 0.75 similarity score
+const processor = new SimilarityPostprocessor({
+  similarityCutoff: 0.7,
+});
+
+const filteredNodes = processor.postprocessNodes(nodes);
+
+// cohere rerank: rerank nodes given query using trained model
+const reranker = new CohereRerank({
+  apiKey: "<COHERE_API_KEY>",
+  topN: 2,
+});
+
+const rerankedNodes = await reranker.postprocessNodes(nodes, "<user_query>");
+
+console.log(filteredNodes, rerankedNodes);
+```
+
+Now you can use the `filteredNodes` and `rerankedNodes` in your application.
+
+## Using Node Postprocessors in LlamaIndex
+
+Most commonly, node-postprocessors will be used in a query engine, where they are applied to the nodes returned from a retriever, and before the response synthesis step.
+
+### Using Node Postprocessors in a Query Engine
+
+```ts
+import { Node, NodeWithScore, SimilarityPostprocessor, CohereRerank } from "llamaindex";
+
+const nodes: NodeWithScore[] = [
+  {
+    node: new TextNode({ text: "hello world" }),
+    score: 0.8,
+  },
+  {
+    node: new TextNode({ text: "LlamaIndex is the best" }),
+    score: 0.6,
+  }
+];
+
+// cohere rerank: rerank nodes given query using trained model
+const reranker = new CohereRerank({
+  apiKey: "<COHERE_API_KEY>,
+  topN: 2,
+})
+
+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],
+});
+
+// all node post-processors will be applied during each query
+const response = await queryEngine.query("<user_query>");
+```
+
+### Using with retrieved nodes
+
+```ts
+import { SimilarityPostprocessor } from "llamaindex";
+
+nodes = await index.asRetriever().retrieve("test query str");
+
+const processor = new SimilarityPostprocessor({
+  similarityCutoff: 0.7,
+});
+
+const filteredNodes = processor.postprocessNodes(nodes);
+```
@@ -0,0 +1,2 @@
+label: "Prompts"
+position: 0
@@ -0,0 +1,76 @@
+# Prompts
+
+Prompting is the fundamental input that gives LLMs their expressive power. LlamaIndex uses prompts to build the index, do insertion, perform traversal during querying, and to synthesize the final answer.
+
+Users may also provide their own prompt templates to further customize the behavior of the framework. The best method for customizing is copying the default prompt from the link above, and using that as the base for any modifications.
+
+## Usage Pattern
+
+Currently, there are two ways to customize prompts in LlamaIndex:
+
+For both methods, you will need to create an function that overrides the default prompt.
+
+```ts
+// Define a custom prompt
+const newTextQaPrompt: TextQaPrompt = ({ context, query }) => {
+  return `Context information is below.
+---------------------
+${context}
+---------------------
+Given the context information and not prior knowledge, answer the query.
+Answer the query in the style of a Sherlock Holmes detective novel.
+Query: ${query}
+Answer:`;
+};
+```
+
+### 1. Customizing the default prompt on initialization
+
+The first method is to create a new instance of `ResponseSynthesizer` (or the module you would like to update the prompt) and pass the custom prompt to the `responseBuilder` parameter. Then, pass the instance to the `asQueryEngine` method of the index.
+
+```ts
+// Create an instance of response synthesizer
+const responseSynthesizer = new ResponseSynthesizer({
+  responseBuilder: new CompactAndRefine(serviceContext, newTextQaPrompt),
+});
+
+// Create index
+const index = await VectorStoreIndex.fromDocuments([document], {
+  serviceContext,
+});
+
+// Query the index
+const queryEngine = index.asQueryEngine({ responseSynthesizer });
+
+const response = await queryEngine.query({
+  query: "What did the author do in college?",
+});
+```
+
+### 2. Customizing submodules prompt
+
+The second method is that most of the modules in LlamaIndex have a `getPrompts` and a `updatePrompt` method that allows you to override the default prompt. This method is useful when you want to change the prompt on the fly or in submodules on a more granular level.
+
+```ts
+// Create index
+const index = await VectorStoreIndex.fromDocuments([document], {
+  serviceContext,
+});
+
+// Query the index
+const queryEngine = index.asQueryEngine();
+
+// Get a list of prompts for the query engine
+const prompts = queryEngine.getPrompts();
+
+// output: { "responseSynthesizer:textQATemplate": defaultTextQaPrompt, "responseSynthesizer:refineTemplate": defaultRefineTemplatePrompt }
+
+// Now, we can override the default prompt
+queryEngine.updatePrompt({
+  "responseSynthesizer:textQATemplate": newTextQaPrompt,
+});
+
+const response = await queryEngine.query({
+  query: "What did the author do in college?",
+});
+```
@@ -0,0 +1,2 @@
+label: "Query Engines"
+position: 2
--- a/Show More
+++ b/Show More