Release 0.2.11 (#765)

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

.changeset/config.json

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

.changeset/fuzzy-snails-applaud.md

@@ -1,5 +0,0 @@
----
-"llamaindex": patch
----
-
-feat: add filtering of metadata to PGVectorStore

.changeset/olive-wolves-own.md

@@ -1,5 +0,0 @@
----
-"llamaindex": patch
----
-
-feat(reranker): cohere reranker

.changeset/tame-ways-applaud.md

@@ -1,5 +0,0 @@
----
-"llamaindex": patch
----
-
-feat: use batching in vector store index

.changeset/violet-cows-fix.md

@@ -1,5 +0,0 @@
----
-"llamaindex": patch
----
-
-Add reader for LlamaParse

.cjs.swcrc

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

.eslintrc.cjs

@@ -0,0 +1,76 @@
+module.exports = {
+  root: true,
+  extends: [
+    "turbo",
+    "prettier",
+    "plugin:@typescript-eslint/recommended-type-checked-only",
+  ],
+  parserOptions: {
+    project: true,
+    __tsconfigRootDir: __dirname,
+  },
+  settings: {
+    react: {
+      version: "999.999.999",
+    },
+  },
+  rules: {
+    "max-params": ["error", 4],
+    "prefer-const": "error",
+    "@typescript-eslint/no-floating-promises": [
+      "error",
+      {
+        ignoreIIFE: true,
+      },
+    ],
+    "@typescript-eslint/await-thenable": "off",
+    "@typescript-eslint/ban-ts-comment": "off",
+    "@typescript-eslint/ban-types": "off",
+    "no-array-constructor": "off",
+    "@typescript-eslint/no-array-constructor": "off",
+    "@typescript-eslint/no-base-to-string": "off",
+    "@typescript-eslint/no-duplicate-enum-values": "off",
+    "@typescript-eslint/no-duplicate-type-constituents": "off",
+    "@typescript-eslint/no-explicit-any": "off",
+    "@typescript-eslint/no-extra-non-null-assertion": "off",
+    "@typescript-eslint/no-for-in-array": "off",
+    "no-implied-eval": "off",
+    "@typescript-eslint/no-implied-eval": "off",
+    "no-loss-of-precision": "off",
+    "@typescript-eslint/no-loss-of-precision": "off",
+    "@typescript-eslint/no-misused-new": "off",
+    "@typescript-eslint/no-misused-promises": "off",
+    "@typescript-eslint/no-namespace": "off",
+    "@typescript-eslint/no-non-null-asserted-optional-chain": "off",
+    "@typescript-eslint/no-redundant-type-constituents": "off",
+    "@typescript-eslint/no-this-alias": "off",
+    "@typescript-eslint/no-unnecessary-type-assertion": "off",
+    "@typescript-eslint/no-unnecessary-type-constraint": "off",
+    "@typescript-eslint/no-unsafe-argument": "off",
+    "@typescript-eslint/no-unsafe-assignment": "off",
+    "@typescript-eslint/no-unsafe-call": "off",
+    "@typescript-eslint/no-unsafe-declaration-merging": "off",
+    "@typescript-eslint/no-unsafe-enum-comparison": "off",
+    "@typescript-eslint/no-unsafe-member-access": "off",
+    "@typescript-eslint/no-unsafe-return": "off",
+    "no-unused-vars": "off",
+    "@typescript-eslint/no-unused-vars": "off",
+    "@typescript-eslint/no-var-requires": "off",
+    "@typescript-eslint/prefer-as-const": "off",
+    "require-await": "off",
+    "@typescript-eslint/require-await": "off",
+    "@typescript-eslint/restrict-plus-operands": "off",
+    "@typescript-eslint/restrict-template-expressions": "off",
+    "@typescript-eslint/triple-slash-reference": "off",
+    "@typescript-eslint/unbound-method": "off",
+  },
+  overrides: [
+    {
+      files: ["examples/**/*.ts"],
+      rules: {
+        "turbo/no-undeclared-env-vars": "off",
+      },
+    },
+  ],
+  ignorePatterns: ["dist/", "lib/", "deps/"],
+};

.eslintrc.js

@@ -1,14 +0,0 @@
-module.exports = {
-  root: true,
-  // This tells ESLint to load the config from the package `eslint-config-custom`
-  extends: ["custom"],
-  settings: {
-    next: {
-      rootDir: ["apps/*/"],
-    },
-  },
-  rules: {
-    "max-params": ["error", 4],
-  },
-  ignorePatterns: ["dist/"],
-};

.github/workflows/e2e.yml

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

.github/workflows/lint_on_push_or_pull.yml

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

.github/workflows/publish.yml

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

.github/workflows/release.yml

@@ -0,0 +1,57 @@
+name: Release
+
+on:
+  push:
+    branches:
+      - main
+
+concurrency: ${{ github.workflow }}-${{ github.ref }}
+
+jobs:
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v3
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "pnpm"
+
+      - name: Install dependencies
+        run: pnpm install
+
+      - name: Add auth token to .npmrc file
+        run: |
+          cat << EOF >> ".npmrc"
+            //registry.npmjs.org/:_authToken=$NPM_TOKEN
+          EOF
+        env:
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
+
+      - name: Get changeset status
+        id: get-changeset-status
+        run: |
+          pnpm changeset status --output .changeset/status.json
+          new_version=$(jq -r '.releases[] | select(.name == "llamaindex") | .newVersion' < .changeset/status.json)
+          rm -v .changeset/status.json
+          echo "new-version=${new_version}" >> "$GITHUB_OUTPUT"
+
+      - name: Create Release Pull Request or Publish to npm
+        id: changesets
+        uses: changesets/action@v1
+        with:
+          commit: Release ${{ steps.get-changeset-status.outputs.new-version }}
+          title: Release ${{ steps.get-changeset-status.outputs.new-version }}
+          # update version PR with the latest changesets
+          version: pnpm new-version
+          # build package and call changeset publish
+          publish: pnpm release
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}

.github/workflows/test.yml

@@ -1,18 +1,55 @@
 name: Run Tests
 
-on: [push, pull_request]
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
 
 jobs:
+  e2e:
+    strategy:
+      fail-fast: false
+      matrix:
+        node-version: [18.x, 20.x, 22.x]
+    name: E2E on Node.js ${{ matrix.node-version }}
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v3
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+          cache: "pnpm"
+      - name: Install dependencies
+        run: pnpm install
+      - name: Run E2E Tests
+        run: pnpm run e2e
+
   test:
+    strategy:
+      fail-fast: false
+      matrix:
+        node-version: [18.x, 20.x, 22.x]
+    name: Test on Node.js ${{ matrix.node-version }}
     runs-on: ubuntu-latest
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version-file: ".nvmrc"
+          node-version: ${{ matrix.node-version }}
           cache: "pnpm"
       - name: Install dependencies
         run: pnpm install
@@ -23,7 +60,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -33,6 +70,9 @@ jobs:
         run: pnpm install
       - name: Build
         run: pnpm run build --filter llamaindex
+      - name: Use Build For Examples
+        run: pnpm link ../packages/core/
+        working-directory: ./examples
       - name: Run Type Check
         run: pnpm run type-check
       - name: Run Circular Dependency Check
@@ -44,12 +84,30 @@ jobs:
           name: typecheck-build-dist
           path: ./packages/core/dist
           if-no-files-found: error
+  core-edge-runtime:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: pnpm/action-setup@v3
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "pnpm"
+      - name: Install dependencies
+        run: pnpm install
+      - name: Build
+        run: pnpm run build --filter @llamaindex/edge
+      - name: Build Edge Runtime
+        run: pnpm run build
+        working-directory: ./packages/edge/e2e/test-edge-runtime
   typecheck-examples:
     runs-on: ubuntu-latest
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -61,10 +119,13 @@ jobs:
         run: pnpm run build --filter llamaindex
       - name: Copy examples
         run: rsync -rv --exclude=node_modules ./examples ${{ runner.temp }}
-      - name: Pack
+      - 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 llamaindex
+      - name: Install
         run: npm add ${{ runner.temp }}/*.tgz
         working-directory: ${{ runner.temp }}/examples
       - name: Run Type Check

.gitignore

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

.npmrc

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

.swcrc

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

.vscode/launch.json

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

.vscode/settings.json

@@ -5,7 +5,6 @@
   "[xml]": {
     "editor.defaultFormatter": "redhat.vscode-xml"
   },
-  "jest.rootPath": "./packages/core",
   "[python]": {
     "editor.defaultFormatter": "ms-python.black-formatter"
   },

CONTRIBUTING.md

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

README-turborepo.md

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

README.md

@@ -83,37 +83,52 @@ Check out our NextJS playground at https://llama-playground.vercel.app/. The sou
 
 - [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.
+- [Embedding](/packages/core/src/embeddings/OpenAIEmbedding.ts): Embeddings are sets of floating point numbers which represent the data in a Node. By comparing the similarity of embeddings, we can derive an understanding of the similarity of two pieces of data. One use case is to compare the embedding of a question with the embeddings of our Nodes to see which Nodes may contain the data needed to answer that quesiton. Because the default service context is OpenAI, the default embedding is `OpenAIEmbedding`. If using different models, say through Ollama, use this [Embedding](/packages/core/src/embeddings/OllamaEmbedding.ts) (see all [here](/packages/core/src/embeddings)).
 
 - [Indices](/packages/core/src/indices/): Indices store the Nodes and the embeddings of those nodes. QueryEngines retrieve Nodes from these Indices using embedding similarity.
 
-- [QueryEngine](/packages/core/src/QueryEngine.ts): Query engines are what generate the query you put in and give you back the result. Query engines generally combine a pre-built prompt with selected Nodes from your Index to give the LLM the context it needs to answer your query.
+- [QueryEngine](/packages/core/src/engines/query/RetrieverQueryEngine.ts): Query engines are what generate the query you put in and give you back the result. Query engines generally combine a pre-built prompt with selected Nodes from your Index to give the LLM the context it needs to answer your query. To build a query engine from your Index (recommended), use the [`asQueryEngine`](/packages/core/src/indices/BaseIndex.ts) method on your Index. See all query engines [here](/packages/core/src/engines/query).
 
-- [ChatEngine](/packages/core/src/ChatEngine.ts): A ChatEngine helps you build a chatbot that will interact with your Indices.
+- [ChatEngine](/packages/core/src/engines/chat/SimpleChatEngine.ts): A ChatEngine helps you build a chatbot that will interact with your Indices. See all chat engines [here](/packages/core/src/engines/chat).
 
 - [SimplePrompt](/packages/core/src/Prompt.ts): A simple standardized function call definition that takes in inputs and formats them in a template literal. SimplePrompts can be specialized using currying and combined using other SimplePrompt functions.
 
-## Note: NextJS:
+## Using 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.
+If you're using the NextJS App Router, you can choose between the Node.js and the [Edge runtime](https://nextjs.org/docs/app/building-your-application/rendering/edge-and-nodejs-runtimes#edge-runtime).
 
-```js
-export const runtime = "nodejs"; // default
+With NextJS 13 and 14, using the Node.js runtime is the default. You can explicitly set the Edge runtime in your [router handler](https://nextjs.org/docs/app/building-your-application/routing/route-handlers) by adding this line:
+
+```typescript
+export const runtime = "edge";
 ```
 
+The following sections explain further differences in using the Node.js or Edge runtime.
+
+### Using the Node.js runtime
+
+Add the following config to your `next.config.js` to ignore specific packages in the server-side bundling:
+
 ```js
 // next.config.js
 /** @type {import('next').NextConfig} */
 const nextConfig = {
   experimental: {
-    serverComponentsExternalPackages: ["pdf2json"],
+    serverComponentsExternalPackages: [
+      "pdf2json",
+      "@zilliz/milvus2-sdk-node",
+      "sharp",
+      "onnxruntime-node",
+    ],
   },
   webpack: (config) => {
-    config.resolve.alias = {
-      ...config.resolve.alias,
-      sharp$: false,
-      "onnxruntime-node$": false,
-    };
+    config.externals.push({
+      pdf2json: "commonjs pdf2json",
+      "@zilliz/milvus2-sdk-node": "commonjs @zilliz/milvus2-sdk-node",
+      sharp: "commonjs sharp",
+      "onnxruntime-node": "commonjs onnxruntime-node",
+    });
+
     return config;
   },
 };
@@ -121,12 +136,63 @@ const nextConfig = {
 module.exports = nextConfig;
 ```
 
+### Using the Edge runtime
+
+We publish a dedicated package (`@llamaindex/edge` instead of `llamaindex`) for using the Edge runtime. To use it, first install the package:
+
+```shell
+pnpm install @llamaindex/edge
+```
+
+> _Note_: Ensure that your `package.json` doesn't include the `llamaindex` package if you're using `@llamaindex/edge`.
+
+Then make sure to use the correct import statement in your code:
+
+```typescript
+// replace 'llamaindex' with '@llamaindex/edge'
+import {} from "@llamaindex/edge";
+```
+
+A further difference is that the `@llamaindex/edge` package doesn't export classes from the `readers` or `storage` folders. The reason is that most of these classes are not compatible with the Edge runtime.
+
+If you need any of those classes, you have to import them instead directly. Here's an example for importing the `PineconeVectorStore` class:
+
+```typescript
+import { PineconeVectorStore } from "@llamaindex/edge/storage/vectorStore/PineconeVectorStore";
+```
+
+As the `PDFReader` is not working with the Edge runtime, here's how to use the `SimpleDirectoryReader` with the `LlamaParseReader` to load PDFs:
+
+```typescript
+import { SimpleDirectoryReader } from "@llamaindex/edge/readers/SimpleDirectoryReader";
+import { LlamaParseReader } from "@llamaindex/edge/readers/LlamaParseReader";
+
+export const DATA_DIR = "./data";
+
+export async function getDocuments() {
+  const reader = new SimpleDirectoryReader();
+  // Load PDFs using LlamaParseReader
+  return await reader.loadData({
+    directoryPath: DATA_DIR,
+    fileExtToReader: {
+      pdf: new LlamaParseReader({ resultType: "markdown" }),
+    },
+  });
+}
+```
+
+> _Note_: Reader classes have to be added explictly to the `fileExtToReader` map in the Edge version of the `SimpleDirectoryReader`.
+
+You'll find a complete example of using the Edge runtime with LlamaIndexTS here: https://github.com/run-llama/create_llama_projects/tree/main/nextjs-edge-llamaparse
+
 ## Supported LLMs:
 
 - OpenAI GPT-3.5-turbo and GPT-4
-- Anthropic Claude Instant and Claude 2
-- Llama2 Chat LLMs (70B, 13B, and 7B parameters)
+- Anthropic Claude 3 (Opus, Sonnet, and Haiku) and the legacy models (Claude 2 and Instant)
+- Groq LLMs
+- Llama2/3 Chat LLMs (70B, 13B, and 7B parameters)
 - MistralAI Chat LLMs
+- Fireworks Chat LLMs
 
 ## Contributing:
 

apps/docs/CHANGELOG.md

@@ -1,5 +1,29 @@
 # docs
 
+## 0.0.5
+
+### Patch Changes
+
+- Updated dependencies [87142b2]
+- Updated dependencies [5a6cc0e]
+- Updated dependencies [87142b2]
+  - llamaindex@0.2.11
+
+## 0.0.4
+
+### Patch Changes
+
+- Updated dependencies [5116ad8]
+  - @llamaindex/env@0.0.5
+
+## 0.0.3
+
+### Patch Changes
+
+- 09bf27a: Add Groq LLM to LlamaIndex
+- Updated dependencies [cf87f84]
+  - @llamaindex/env@0.0.4
+
 ## 0.0.2
 
 ### Patch Changes

apps/docs/docs/examples/agent.mdx

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

apps/docs/docs/getting_started/starter.md

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

apps/docs/docs/getting_started/starter.mdx

@@ -0,0 +1,51 @@
+---
+sidebar_position: 1
+---
+
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../examples/vectorIndex";
+import TSConfigSource from "!!raw-loader!../../../../examples/tsconfig.json";
+
+# Starter Tutorial
+
+Make sure you have installed LlamaIndex.TS and have an OpenAI key. If you haven't, check out the [installation](installation) guide.
+
+## From scratch(node.js + TypeScript):
+
+In a new folder:
+
+```bash npm2yarn
+npm init
+npm install -D typescript @types/node
+```
+
+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.
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
+
+Create a `tsconfig.json` file in the same folder:
+
+<CodeBlock language="json">{TSConfigSource}</CodeBlock>
+
+Now you can run the code with
+
+```bash
+npx tsx example.ts
+```
+
+Also, you can clone our examples and try them out:
+
+```bash npm2yarn
+npx degit run-llama/LlamaIndexTS/examples my-new-project
+cd my-new-project
+npm install
+npx tsx ./vectorIndex.ts
+```
+
+## From scratch (Next.js + TypeScript):
+
+You just need one command to create a new Next.js project:
+
+```bash npm2yarn
+npx create-llama@latest
+```

apps/docs/docs/introduction.md

@@ -37,7 +37,7 @@ For more complex applications, our lower-level APIs allow advanced users to cust
 
 `npm install llamaindex`
 
-Our documentation includes [Installation Instructions](./getting_started/installation.mdx) and a [Starter Tutorial](./getting_started/starter.md) to build your first application.
+Our documentation includes [Installation Instructions](./getting_started/installation.mdx) and a [Starter Tutorial](./getting_started/starter.mdx) to build your first application.
 
 Once you're up and running, [High-Level Concepts](./getting_started/concepts.md) has an overview of LlamaIndex's modular architecture. For more hands-on practical examples, look through our Examples section on the sidebar.
 

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

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

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

@@ -11,4 +11,10 @@ An “agent” is an automated reasoning and decision engine. It takes in a user
 
 LlamaIndex.TS comes with a few built-in agents, but you can also create your own. The built-in agents include:
 
-- [OpenAI Agent](./openai.mdx)
+- OpenAI Agent
+- Anthropic Agent
+- ReACT Agent
+
+## Examples
+
+- [OpenAI Agent](../../examples/agent.mdx)

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

@@ -1,183 +0,0 @@
-# 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 worker = new OpenAIAgent({
-  tools: [sumFunctionTool, divideFunctionTool],
-  verbose: true,
-});
-```
-
-## Chat with the agent
-
-Now we can chat with the agent.
-
-```ts
-const response = await worker.chat({
-  message: "How much is 5 + 5? then divide by 2",
-});
-
-console.log(String(response));
-```
-
-## Full code
-
-```ts
-import { FunctionTool, OpenAIAgent } from "llamaindex";
-
-// Define a function to sum two numbers
-function sumNumbers({ a, b }: { a: number; b: number }): number {
-  return a + b;
-}
-
-// Define a function to divide two numbers
-function divideNumbers({ a, b }: { a: number; b: number }): number {
-  return a / b;
-}
-
-// Define the parameters of the sum function as a JSON schema
-const sumJSON = {
-  type: "object",
-  properties: {
-    a: {
-      type: "number",
-      description: "The first number",
-    },
-    b: {
-      type: "number",
-      description: "The second number",
-    },
-  },
-  required: ["a", "b"],
-};
-
-// Define the parameters of the divide function as a JSON schema
-const divideJSON = {
-  type: "object",
-  properties: {
-    a: {
-      type: "number",
-      description: "The argument a to divide",
-    },
-    b: {
-      type: "number",
-      description: "The argument b to divide",
-    },
-  },
-  required: ["a", "b"],
-};
-
-async function main() {
-  // Create a function tool from the sum function
-  const sumFunctionTool = new FunctionTool(sumNumbers, {
-    name: "sumNumbers",
-    description: "Use this function to sum two numbers",
-    parameters: sumJSON,
-  });
-
-  // Create a function tool from the divide function
-  const divideFunctionTool = new FunctionTool(divideNumbers, {
-    name: "divideNumbers",
-    description: "Use this function to divide two numbers",
-    parameters: divideJSON,
-  });
-
-  // Create an OpenAIAgent with the function tools
-  const agent = new OpenAIAgent({
-    tools: [sumFunctionTool, divideFunctionTool],
-    verbose: true,
-  });
-
-  // Chat with the agent
-  const response = await agent.chat({
-    message: "How much is 5 + 5? then divide by 2",
-  });
-
-  // Print the response
-  console.log(String(response));
-}
-
-main().then(() => {
-  console.log("Done");
-});
-```

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

@@ -1,128 +0,0 @@
-# OpenAI Agent + QueryEngineTool
-
-QueryEngineTool is a tool that allows you to query a vector index. In this example, we will create a vector index from a set of documents and then create a QueryEngineTool from the vector index. We will then create an OpenAIAgent with the QueryEngineTool and chat with the agent.
-
-## Setup
-
-First, you need to install the `llamaindex` package. You can do this by running the following command in your terminal:
-
-```bash
-pnpm i llamaindex
-```
-
-Then you can import the necessary classes and functions.
-
-```ts
-import {
-  OpenAIAgent,
-  SimpleDirectoryReader,
-  VectorStoreIndex,
-  QueryEngineTool,
-} from "llamaindex";
-```
-
-## Create a vector index
-
-Now we can create a vector index from a set of documents.
-
-```ts
-// Load the documents
-const documents = await new SimpleDirectoryReader().loadData({
-  directoryPath: "node_modules/llamaindex/examples/",
-});
-
-// Create a vector index from the documents
-const vectorIndex = await VectorStoreIndex.fromDocuments(documents);
-```
-
-## Create a QueryEngineTool
-
-Now we can create a QueryEngineTool from the vector index.
-
-```ts
-// Create a query engine from the vector index
-const abramovQueryEngine = vectorIndex.asQueryEngine();
-
-// Create a QueryEngineTool with the query engine
-const queryEngineTool = new QueryEngineTool({
-  queryEngine: abramovQueryEngine,
-  metadata: {
-    name: "abramov_query_engine",
-    description: "A query engine for the Abramov documents",
-  },
-});
-```
-
-## Create an OpenAIAgent
-
-```ts
-// Create an OpenAIAgent with the query engine tool tools
-
-const agent = new OpenAIAgent({
-  tools: [queryEngineTool],
-  verbose: true,
-});
-```
-
-## Chat with the agent
-
-Now we can chat with the agent.
-
-```ts
-const response = await agent.chat({
-  message: "What was his salary?",
-});
-
-console.log(String(response));
-```
-
-## Full code
-
-```ts
-import {
-  OpenAIAgent,
-  SimpleDirectoryReader,
-  VectorStoreIndex,
-  QueryEngineTool,
-} from "llamaindex";
-
-async function main() {
-  // Load the documents
-  const documents = await new SimpleDirectoryReader().loadData({
-    directoryPath: "node_modules/llamaindex/examples/",
-  });
-
-  // Create a vector index from the documents
-  const vectorIndex = await VectorStoreIndex.fromDocuments(documents);
-
-  // Create a query engine from the vector index
-  const abramovQueryEngine = vectorIndex.asQueryEngine();
-
-  // Create a QueryEngineTool with the query engine
-  const queryEngineTool = new QueryEngineTool({
-    queryEngine: abramovQueryEngine,
-    metadata: {
-      name: "abramov_query_engine",
-      description: "A query engine for the Abramov documents",
-    },
-  });
-
-  // Create an OpenAIAgent with the function tools
-  const agent = new OpenAIAgent({
-    tools: [queryEngineTool],
-    verbose: true,
-  });
-
-  // Chat with the agent
-  const response = await agent.chat({
-    message: "What was his salary?",
-  });
-
-  // Print the response
-  console.log(String(response));
-}
-
-main().then(() => {
-  console.log("Done");
-});
-```

apps/docs/docs/modules/data_loader.mdx

@@ -5,6 +5,7 @@ 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
 
@@ -30,6 +31,18 @@ Or pass new readers for `fileExtToReader` to support more file types.
   {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)

apps/docs/docs/modules/embedding.md

@@ -1,22 +0,0 @@
----
-sidebar_position: 4
----
-
-# 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 });
-```
-
-## API Reference
-
-- [OpenAIEmbedding](../api/classes/OpenAIEmbedding.md)
-- [ServiceContext](../api/interfaces//ServiceContext.md)

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

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

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

@@ -0,0 +1 @@
+label: "Available Embeddings"

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

@@ -0,0 +1,34 @@
+# HuggingFace
+
+To use HuggingFace embeddings, you need to import `HuggingFaceEmbedding` from `llamaindex`.
+
+```ts
+import { HuggingFaceEmbedding, Settings } from "llamaindex";
+
+// Update Embed Model
+Settings.embedModel = new HuggingFaceEmbedding();
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+Per default, `HuggingFaceEmbedding` is using the `Xenova/all-MiniLM-L6-v2` model. You can change the model by passing the `modelType` parameter to the constructor.
+If you're not using a quantized model, set the `quantized` parameter to `false`.
+
+For example, to use the not quantized `BAAI/bge-small-en-v1.5` model, you can use the following code:
+
+```ts
+Settings.embedModel = new HuggingFaceEmbedding({
+  modelType: "BAAI/bge-small-en-v1.5",
+  quantized: false,
+});
+```

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

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

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

@@ -0,0 +1,24 @@
+# MistralAI
+
+To use MistralAI embeddings, you need to import `MistralAIEmbedding` from `llamaindex`.
+
+```ts
+import { MistralAIEmbedding, Settings } from "llamaindex";
+
+// Update Embed Model
+Settings.embedModel = new MistralAIEmbedding({
+  apiKey: "<YOUR_API_KEY>",
+});
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```

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

@@ -0,0 +1,29 @@
+# Ollama
+
+To use Ollama embeddings, you need to import `OllamaEmbedding` from `llamaindex`.
+
+Note that you need to pull the embedding model first before using it.
+
+In the example below, we're using the [`nomic-embed-text`](https://ollama.com/library/nomic-embed-text) model, so you have to call:
+
+```shell
+ollama pull nomic-embed-text
+```
+
+```ts
+import { OllamaEmbedding, Settings } from "llamaindex";
+
+Settings.embedModel = new OllamaEmbedding({ model: "nomic-embed-text" });
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```

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

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

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

@@ -0,0 +1,23 @@
+# Together
+
+To use together embeddings, you need to import `TogetherEmbedding` from `llamaindex`.
+
+```ts
+import { TogetherEmbedding, Settings } from "llamaindex";
+
+Settings.embedModel = new TogetherEmbedding({
+  apiKey: "<YOUR_API_KEY>",
+});
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```

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

@@ -0,0 +1,21 @@
+# 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 updated through `Settings`
+
+```typescript
+import { OpenAIEmbedding, Settings } from "llamaindex";
+
+Settings.embedModel = new OpenAIEmbedding({
+  model: "text-embedding-ada-002",
+});
+```
+
+## Local Embedding
+
+For local embeddings, you can use the [HuggingFace](./available_embeddings/huggingface.md) embedding model.
+
+## API Reference
+
+- [OpenAIEmbedding](../../api/classes/OpenAIEmbedding.md)

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

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

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,66 @@
+# Relevancy Evaluator
+
+Relevancy measure if the response from a query engine matches any source nodes.
+
+It is useful for measuring if the response was relevant to the query. The evaluator returns a score between 0 and 1, where 1 means the response is relevant to the query.
+
+## Usage
+
+Firstly, you need to install the package:
+
+```bash
+pnpm i llamaindex
+```
+
+Set the OpenAI API key:
+
+```bash
+export OPENAI_API_KEY=your-api-key
+```
+
+Import the required modules:
+
+```ts
+import { RelevancyEvaluator, OpenAI, Settings } from "llamaindex";
+```
+
+Let's setup gpt-4 for better results:
+
+```ts
+Settings.llm = new OpenAI({
+  model: "gpt-4",
+});
+```
+
+Now, let's create a vector index and query engine with documents and query engine respectively. Then, we can evaluate the response with the query and response from the query engine.:
+
+```ts
+const documents = [
+  new Document({
+    text: `The city came under British control in 1664 and was renamed New York after King Charles II of England granted the lands to his brother, the Duke of York. The city was regained by the Dutch in July 1673 and was renamed New Orange for one year and three months; the city has been continuously named New York since November 1674. New York City was the capital of the United States from 1785 until 1790, and has been the largest U.S. city since 1790. The Statue of Liberty greeted millions of immigrants as they came to the U.S. by ship in the late 19th and early 20th centuries, and is a symbol of the U.S. and its ideals of liberty and peace. In the 21st century, New York City has emerged as a global node of creativity, entrepreneurship, and as a symbol of freedom and cultural diversity. The New York Times has won the most Pulitzer Prizes for journalism and remains the U.S. media's "newspaper of record". In 2019, New York City was voted the greatest city in the world in a survey of over 30,000 p...	Pass`,
+  }),
+];
+
+const vectorIndex = await VectorStoreIndex.fromDocuments(documents);
+
+const queryEngine = vectorIndex.asQueryEngine();
+
+const query = "How did New York City get its name?";
+
+const response = await queryEngine.query({
+  query,
+});
+
+const evaluator = new RelevancyEvaluator();
+
+const result = await evaluator.evaluateResponse({
+  query,
+  response: response,
+});
+
+console.log(`the response is ${result.passing ? "relevant" : "not relevant"}`);
+```
+
+```bash
+the response is relevant
+```

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

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

apps/docs/docs/modules/llamacloud.mdx

@@ -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)

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

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

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

@@ -15,11 +15,9 @@ export AZURE_OPENAI_DEPLOYMENT="gpt-4" # or some other deployment name
 ## Usage
 
 ```ts
-import { OpenAI, serviceContextFromDefaults } from "llamaindex";
+import { OpenAI, Settings } from "llamaindex";
 
-const azureOpenaiLLM = new OpenAI({ model: "gpt-4", temperature: 0 });
-
-const serviceContext = serviceContextFromDefaults({ llm: azureOpenaiLLM });
+Settings.llm = new OpenAI({ model: "gpt-4", temperature: 0 });
 ```
 
 ## Load and index documents
@@ -29,9 +27,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -49,26 +45,18 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  Anthropic,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { OpenAI, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+Settings.llm = new OpenAI({ model: "gpt-4", temperature: 0 });
 
 async function main() {
-  // Create an instance of the LLM
-  const azureOpenaiLLM = new OpenAI({ model: "gpt-4", temperature: 0 });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: azureOpenaiLLM });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // get retriever
+  const retriever = index.asRetriever();
 
   // Create a query engine
   const queryEngine = index.asQueryEngine({

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

@@ -0,0 +1,61 @@
+# Fireworks LLM
+
+Fireworks.ai focus on production use cases for open source LLMs, offering speed and quality.
+
+## Usage
+
+```ts
+import { FireworksLLM, Settings } from "llamaindex";
+
+Settings.llm = new FireworksLLM({
+  apiKey: "<YOUR_API_KEY>",
+});
+```
+
+## 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);
+```
+
+## 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);
+```

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

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

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

@@ -3,11 +3,9 @@
 ## Usage
 
 ```ts
-import { Ollama, serviceContextFromDefaults } from "llamaindex";
+import { Ollama, Settings, DeuceChatStrategy } from "llamaindex";
 
-const llama2LLM = new LlamaDeuce({ chatStrategy: DeuceChatStrategy.META });
-
-const serviceContext = serviceContextFromDefaults({ llm: llama2LLM });
+Settings.llm = new LlamaDeuce({ chatStrategy: DeuceChatStrategy.META });
 ```
 
 ## Usage with Replication
@@ -16,19 +14,18 @@ const serviceContext = serviceContextFromDefaults({ llm: llama2LLM });
 import {
   Ollama,
   ReplicateSession,
-  serviceContextFromDefaults,
+  Settings,
+  DeuceChatStrategy,
 } from "llamaindex";
 
 const replicateSession = new ReplicateSession({
   replicateKey,
 });
 
-const llama2LLM = new LlamaDeuce({
+Settings.llm = new LlamaDeuce({
   chatStrategy: DeuceChatStrategy.META,
   replicateSession,
 });
-
-const serviceContext = serviceContextFromDefaults({ llm: llama2LLM });
 ```
 
 ## Load and index documents
@@ -38,9 +35,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -59,25 +54,24 @@ const results = await queryEngine.query({
 
 ```ts
 import {
-  Anthropic,
+  LlamaDeuce,
   Document,
   VectorStoreIndex,
-  serviceContextFromDefaults,
+  Settings,
+  DeuceChatStrategy,
 } from "llamaindex";
 
+// Use the LlamaDeuce LLM
+Settings.llm = new LlamaDeuce({ chatStrategy: DeuceChatStrategy.META });
+
 async function main() {
-  // Create an instance of the LLM
-  const llama2LLM = new LlamaDeuce({ chatStrategy: DeuceChatStrategy.META });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: mistralLLM });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // get retriever
+  const retriever = index.asRetriever();
 
   // Create a query engine
   const queryEngine = index.asQueryEngine({

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

@@ -3,14 +3,12 @@
 ## Usage
 
 ```ts
-import { Ollama, serviceContextFromDefaults } from "llamaindex";
+import { Ollama, Settings } from "llamaindex";
 
-const mistralLLM = new MistralAI({
+Settings.llm = new MistralAI({
   model: "mistral-tiny",
   apiKey: "<YOUR_API_KEY>",
 });
-
-const serviceContext = serviceContextFromDefaults({ llm: mistralLLM });
 ```
 
 ## Load and index documents
@@ -20,9 +18,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -40,26 +36,19 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  Anthropic,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { MistralAI, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+// Use the MistralAI LLM
+Settings.llm = new MistralAI({ model: "mistral-tiny" });
 
 async function main() {
-  // Create an instance of the LLM
-  const mistralLLM = new MistralAI({ model: "mistral-tiny" });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: mistralLLM });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // get retriever
+  const retriever = index.asRetriever();
 
   // Create a query engine
   const queryEngine = index.asQueryEngine({

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

@@ -3,11 +3,10 @@
 ## Usage
 
 ```ts
-import { Ollama, serviceContextFromDefaults } from "llamaindex";
+import { Ollama, Settings } from "llamaindex";
 
-const ollamaLLM = new Ollama({ model: "llama2", temperature: 0.75 });
-
-const serviceContext = serviceContextFromDefaults({ llm: ollamaLLM });
+Settings.llm = ollamaLLM;
+Settings.embedModel = ollamaLLM;
 ```
 
 ## Load and index documents
@@ -17,9 +16,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -37,26 +34,26 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  Anthropic,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { Ollama, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+import fs from "fs/promises";
+
+const ollama = new Ollama({ model: "llama2", temperature: 0.75 });
+
+// Use Ollama LLM and Embed Model
+Settings.llm = ollama;
+Settings.embedModel = ollama;
 
 async function main() {
-  // Create an instance of the LLM
-  const ollamaLLM = new Ollama({ model: "llama2", temperature: 0.75 });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: ollamaLLM });
+  const essay = await fs.readFile("./paul_graham_essay.txt", "utf-8");
 
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // get retriever
+  const retriever = index.asRetriever();
 
   // Create a query engine
   const queryEngine = index.asQueryEngine({

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

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

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

@@ -3,13 +3,11 @@
 ## Usage
 
 ```ts
-import { Portkey, serviceContextFromDefaults } from "llamaindex";
+import { Portkey, Settings } from "llamaindex";
 
-const portkeyLLM = new Portkey({
+Settings.llm = new Portkey({
   apiKey: "<YOUR_API_KEY>",
 });
-
-const serviceContext = serviceContextFromDefaults({ llm: portkeyLLM });
 ```
 
 ## Load and index documents
@@ -19,9 +17,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -39,28 +35,22 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  Anthropic,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { Portkey, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+// Use the Portkey LLM
+Settings.llm = new Portkey({
+  apiKey: "<YOUR_API_KEY>",
+});
 
 async function main() {
-  // Create an instance of the LLM
-  const portkeyLLM = new Portkey({
-    apiKey: "<YOUR_API_KEY>",
-  });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: portkeyLLM });
-
+  // Create a document
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // get retriever
+  const retriever = index.asRetriever();
 
   // Create a query engine
   const queryEngine = index.asQueryEngine({

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

@@ -3,13 +3,11 @@
 ## Usage
 
 ```ts
-import { TogetherLLM, serviceContextFromDefaults } from "llamaindex";
+import { TogetherLLM, Settings } from "llamaindex";
 
-const togetherLLM = new TogetherLLM({
+Settings.llm = new TogetherLLM({
   apiKey: "<YOUR_API_KEY>",
 });
-
-const serviceContext = serviceContextFromDefaults({ llm: togetherLLM });
 ```
 
 ## Load and index documents
@@ -19,9 +17,7 @@ For this example, we will use a single document. In a real-world scenario, you w
 ```ts
 const document = new Document({ text: essay, id_: "essay" });
 
-const index = await VectorStoreIndex.fromDocuments([document], {
-  serviceContext,
-});
+const index = await VectorStoreIndex.fromDocuments([document]);
 ```
 
 ## Query
@@ -39,28 +35,20 @@ const results = await queryEngine.query({
 ## Full Example
 
 ```ts
-import {
-  Anthropic,
-  Document,
-  VectorStoreIndex,
-  serviceContextFromDefaults,
-} from "llamaindex";
+import { TogetherLLM, Document, VectorStoreIndex, Settings } from "llamaindex";
+
+Settings.llm = new TogetherLLM({
+  apiKey: "<YOUR_API_KEY>",
+});
 
 async function main() {
-  // Create an instance of the LLM
-  const togetherLLM = new TogetherLLM({
-    apiKey: "<YOUR_API_KEY>",
-  });
-
-  // Create a service context
-  const serviceContext = serviceContextFromDefaults({ llm: togetherLLM });
-
   const document = new Document({ text: essay, id_: "essay" });
 
   // Load and index documents
-  const index = await VectorStoreIndex.fromDocuments([document], {
-    serviceContext,
-  });
+  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  // get retriever
+  const retriever = index.asRetriever();
 
   // Create a query engine
   const queryEngine = index.asQueryEngine({

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

@@ -6,14 +6,12 @@ sidebar_position: 3
 
 The LLM is responsible for reading text and generating natural language responses to queries. By default, LlamaIndex.TS uses `gpt-3.5-turbo`.
 
-The LLM can be explicitly set in the `ServiceContext` object.
+The LLM can be explicitly updated through `Settings`.
 
 ```typescript
-import { OpenAI, serviceContextFromDefaults } from "llamaindex";
+import { OpenAI, Settings } from "llamaindex";
 
-const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
-
-const serviceContext = serviceContextFromDefaults({ llm: openaiLLM });
+Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
 ```
 
 ## Azure OpenAI
@@ -28,7 +26,10 @@ export AZURE_OPENAI_ENDPOINT="<YOUR ENDPOINT, see https://learn.microsoft.com/en
 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)

apps/docs/docs/modules/node_parser.md

@@ -4,15 +4,14 @@ sidebar_position: 4
 
 # NodeParser
 
-The `NodeParser` in LlamaIndex is responsible for splitting `Document` objects into more manageable `Node` objects. When you call `.fromDocuments()`, the `NodeParser` from the `ServiceContext` is used to do this automatically for you. Alternatively, you can use it to split documents ahead of time.
+The `NodeParser` in LlamaIndex is responsible for splitting `Document` objects into more manageable `Node` objects. When you call `.fromDocuments()`, the `NodeParser` from the `Settings` is used to do this automatically for you. Alternatively, you can use it to split documents ahead of time.
 
 ```typescript
 import { Document, SimpleNodeParser } from "llamaindex";
 
 const nodeParser = new SimpleNodeParser();
-const nodes = nodeParser.getNodesFromDocuments([
-  new Document({ text: "I am 10 years old. John is 20 years old." }),
-]);
+
+Settings.nodeParser = nodeParser;
 ```
 
 ## TextSplitter
@@ -27,6 +26,71 @@ 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)

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

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

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

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

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

@@ -0,0 +1,71 @@
+# Jina AI Reranker
+
+The Jina AI Reranker is a postprocessor that uses the Jina AI Reranker API to rerank the results of a search query.
+
+## Setup
+
+Firstly, you will need to install the `llamaindex` package.
+
+```bash
+pnpm install llamaindex
+```
+
+Now, you will need to sign up for an API key at [Jina AI](https://jina.ai/reranker). Once you have your API key you can import the necessary modules and create a new instance of the `JinaAIReranker` class.
+
+```ts
+import {
+  JinaAIReranker,
+  Document,
+  OpenAI,
+  VectorStoreIndex,
+  Settings,
+} from "llamaindex";
+```
+
+## Load and index documents
+
+For this example, we will use a single document. In a real-world scenario, you would have multiple documents to index.
+
+```ts
+const document = new Document({ text: essay, id_: "essay" });
+
+Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.1 });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## Increase similarity topK to retrieve more results
+
+The default value for `similarityTopK` is 2. This means that only the most similar document will be returned. To retrieve more results, you can increase the value of `similarityTopK`.
+
+```ts
+const retriever = index.asRetriever();
+retriever.similarityTopK = 5;
+```
+
+## Create a new instance of the JinaAIReranker class
+
+Then you can create a new instance of the `JinaAIReranker` class and pass in the number of results you want to return.
+The Jina AI Reranker API key is set in the `JINAAI_API_KEY` environment variable.
+
+```bash
+export JINAAI_API_KEY=<YOUR API KEY>
+```
+
+```ts
+const nodePostprocessor = new JinaAIReranker({
+  topN: 5,
+});
+```
+
+## Create a query engine with the retriever and node postprocessor
+
+```ts
+const queryEngine = index.asQueryEngine({
+  retriever,
+  nodePostprocessors: [nodePostprocessor],
+});
+
+// log the response
+const response = await queryEngine.query("Where did the author grown up?");
+```

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

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

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

@@ -0,0 +1,72 @@
+# 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(undefined, newTextQaPrompt),
+});
+
+// Create index
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+// 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]);
+
+// 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?",
+});
+```

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

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

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

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

apps/docs/docs/modules/retriever.md

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

apps/docs/docs/observability/index.md

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

apps/docs/docs/recipes/_category_.yml

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

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

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

apps/docs/docusaurus.config.js

@@ -163,7 +163,7 @@ const config = {
       "docusaurus-plugin-typedoc",
       {
         entryPoints: ["../../packages/core/src/index.ts"],
-        tsconfig: "../../packages/core/tsconfig.json",
+        tsconfig: "../../tsconfig.json",
         readme: "none",
         sourceLinkTemplate:
           "https://github.com/run-llama/LlamaIndexTS/blob/{gitRevision}/{path}#L{line}",

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

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

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

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

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

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

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

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

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Hent noder!
-const nodesWithScore = await retriever.retrieve("forespørgselsstreng");
+const nodesWithScore = await retriever.retrieve({ query: "forespørgselsstreng" });
 ```
 
 ## API Reference

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Knoten abrufen!
-const nodesWithScore = await retriever.retrieve("Abfragezeichenfolge");
+const nodesWithScore = await retriever.retrieve({ query: "Abfragezeichenfolge" });
 ```
 
 ## API-Referenz

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Ανάκτηση κόμβων!
-const nodesWithScore = await retriever.retrieve("συμβολοσειρά ερωτήματος");
+const nodesWithScore = await retriever.retrieve({ query: "συμβολοσειρά ερωτήματος" });
 ```
 
 ## Αναφορά API

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

@@ -13,7 +13,7 @@ const recuperador = vector_index.asRetriever();
 recuperador.similarityTopK = 3;
 
 // ¡Obtener nodos!
-const nodosConPuntuación = await recuperador.retrieve("cadena de consulta");
+const nodosConPuntuación = await recuperador.retrieve({ query: "cadena de consulta" });
 ```
 
 ## Referencia de la API

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Too sõlmed!
-const nodesWithScore = await retriever.retrieve("päringu string");
+const nodesWithScore = await retriever.retrieve({ query: "päringu string" });
 ```
 
 ## API viide

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // بازیابی گره ها!
-const nodesWithScore = await retriever.retrieve("رشته پرس و جو");
+const nodesWithScore = await retriever.retrieve({ query: "رشته پرس و جو" });
 ```
 
 ## مرجع API

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Hae solmut!
-const nodesWithScore = await retriever.retrieve("kyselymerkkijono");
+const nodesWithScore = await retriever.retrieve({ query: "kyselymerkkijono" });
 ```
 
 ## API-viite

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

@@ -11,7 +11,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Récupérer les nœuds !
-const nodesWithScore = await retriever.retrieve("chaîne de requête");
+const nodesWithScore = await retriever.retrieve({ query: "chaîne de requête" });
 ```
 
 ## Référence de l'API

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // אחזור צמתים!
-const nodesWithScore = await retriever.retrieve("מחרוזת שאילתה");
+const nodesWithScore = await retriever.retrieve({ query: "מחרוזת שאילתה" });
 ```
 
 ## מדריך לממשק API

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // नोड्स प्राप्त करें!
-const nodesWithScore = await retriever.retrieve("क्वेरी स्ट्रिंग");
+const nodesWithScore = await retriever.retrieve({ query: "क्वेरी स्ट्रिंग" });
 ```
 
 ## एपीआई संदर्भ (API Reference)

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

@@ -13,7 +13,7 @@ const dohvatnik = vector_index.asRetriever();
 dohvatnik.similarityTopK = 3;
 
 // Dohvati čvorove!
-const čvoroviSaRezultatom = await dohvatnik.retrieve("upitni niz");
+const čvoroviSaRezultatom = await dohvatnik.retrieve({ query: "upitni niz" });
 ```
 
 ## API Referenca

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Node-ok lekérése!
-const nodesWithScore = await retriever.retrieve("lekérdezési karakterlánc");
+const nodesWithScore = await retriever.retrieve({ query: "lekérdezési karakterlánc" });
 ```
 
 ## API Referencia

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Mengambil node!
-const nodesWithScore = await retriever.retrieve("string query");
+const nodesWithScore = await retriever.retrieve({ query: "string query" });
 ```
 
 ## Referensi API

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Recupera i nodi!
-const nodesWithScore = await retriever.retrieve("stringa di query");
+const nodesWithScore = await retriever.retrieve({ query: "stringa di query" });
 ```
 
 ## Riferimento API

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // ノードを取得します！
-const nodesWithScore = await retriever.retrieve("クエリ文字列");
+const nodesWithScore = await retriever.retrieve({ query: "クエリ文字列" });
 ```
 
 ## API リファレンス

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // 노드를 가져옵니다!
-const nodesWithScore = await retriever.retrieve("쿼리 문자열");
+const nodesWithScore = await retriever.retrieve({ query: "쿼리 문자열" });
 ```
 
 ## API 참조

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

@@ -13,7 +13,7 @@ const gavėjas = vector_index.asRetriever();
 gavėjas.similarityTopK = 3;
 
 // Išgaunami mazgai!
-const mazgaiSuRezultatu = await gavėjas.retrieve("užklausos eilutė");
+const mazgaiSuRezultatu = await gavėjas.retrieve({ query: "užklausos eilutė" });
 ```
 
 ## API nuorodos (API Reference)

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Haal knooppunten op!
-const nodesWithScore = await retriever.retrieve("zoekopdracht");
+const nodesWithScore = await retriever.retrieve({ query: "zoekopdracht" });
 ```
 
 ## API Referentie

apps/docs/i18n/no/docusaurus-plugin-content-docs/current/modules/low_level/retriever.md

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Hent noder!
-const nodesWithScore = await retriever.retrieve("spørringsstreng");
+const nodesWithScore = await retriever.retrieve({ query: "spørringsstreng" });
 ```
 
 ## API-referanse

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Pobierz węzły!
-const nodesWithScore = await retriever.retrieve("ciąg zapytania");
+const nodesWithScore = await retriever.retrieve({ query: "ciąg zapytania" });
 ```
 
 ## Dokumentacja interfejsu API

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

@@ -13,7 +13,7 @@ const recuperador = vector_index.asRetriever();
 recuperador.similarityTopK = 3;
 
 // Buscar nós!
-const nósComPontuação = await recuperador.retrieve("string de consulta");
+const nósComPontuação = await recuperador.retrieve({ query: "string de consulta" });
 ```
 
 ## Referência da API

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

@@ -13,7 +13,7 @@ const recuperator = vector_index.asRetriever();
 recuperator.similarityTopK = 3;
 
 // Preia nodurile!
-const noduriCuScor = await recuperator.retrieve("șir de interogare");
+const noduriCuScor = await recuperator.retrieve({ query: "șir de interogare" });
 ```
 
 ## Referință API

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

@@ -13,7 +13,7 @@ const retriever = vector_index.asRetriever();
 retriever.similarityTopK = 3;
 
 // Получение узлов!
-const nodesWithScore = await retriever.retrieve("строка запроса");
+const nodesWithScore = await retriever.retrieve({ query: "строка запроса" });
 ```
 
 ## Справочник по API