Release 0.6.2 (#1217)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>

.eslintrc.cjs

@@ -31,7 +31,12 @@ module.exports = {
     "@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-base-to-string": [
+      "error",
+      {
+        ignoredTypeNames: ["Error", "RegExp", "URL", "URLSearchParams"],
+      },
+    ],
     "@typescript-eslint/no-duplicate-enum-values": "off",
     "@typescript-eslint/no-duplicate-type-constituents": "off",
     "@typescript-eslint/no-explicit-any": "off",

.github/workflows/lint_on_push_or_pull.yml

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

.github/workflows/preview.yml

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

.github/workflows/publish_github.yml

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

.github/workflows/release.yml

@@ -15,7 +15,7 @@ jobs:
       - name: Checkout Repo
         uses: actions/checkout@v4
 
-      - uses: pnpm/action-setup@v3
+      - uses: pnpm/action-setup@v4
 
       - name: Setup Node.js
         uses: actions/setup-node@v4
@@ -67,3 +67,4 @@ jobs:
         with:
           commit_message: "chore: update lock file"
           branch: changeset-release/main
+          file_pattern: "pnpm-lock.yaml"

.github/workflows/test.yml

@@ -12,6 +12,10 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+env:
+  POSTGRES_USER: runneradmin
+  POSTGRES_HOST_AUTH_METHOD: trust
+
 jobs:
   e2e:
     strategy:
@@ -22,9 +26,17 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-
-      - uses: pnpm/action-setup@v3
-
+      - uses: ankane/setup-postgres@v1
+        with:
+          database: llamaindex_node_test
+          dev-files: true
+      - run: |
+          cd /tmp
+          git clone --branch v0.7.0 https://github.com/pgvector/pgvector.git
+          cd pgvector
+          make
+          sudo make install
+      - uses: pnpm/action-setup@v4
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -42,10 +54,9 @@ jobs:
         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@v3
+      - uses: pnpm/action-setup@v4
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -60,7 +71,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v3
+      - uses: pnpm/action-setup@v4
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -92,12 +103,13 @@ jobs:
           - nextjs-agent
           - nextjs-edge-runtime
           - nextjs-node-runtime
-    #          - waku-query-engine
+          - waku-query-engine
+          - llama-parse-browser
     runs-on: ubuntu-latest
     name: Build LlamaIndex Example (${{ matrix.packages }})
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v3
+      - uses: pnpm/action-setup@v4
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -116,7 +128,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v3
+      - uses: pnpm/action-setup@v4
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -131,6 +143,12 @@ jobs:
       - name: Pack @llamaindex/cloud
         run: pnpm pack --pack-destination ${{ runner.temp }}
         working-directory: packages/cloud
+      - name: Pack @llamaindex/openai
+        run: pnpm pack --pack-destination ${{ runner.temp }}
+        working-directory: packages/llm/openai
+      - name: Pack @llamaindex/groq
+        run: pnpm pack --pack-destination ${{ runner.temp }}
+        working-directory: packages/llm/groq
       - name: Pack @llamaindex/core
         run: pnpm pack --pack-destination ${{ runner.temp }}
         working-directory: packages/core

CONTRIBUTING.md

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

README.md

@@ -36,9 +36,44 @@ For now, browser support is limited due to the lack of support for [AsyncLocalSt
 npm install llamaindex
 pnpm install llamaindex
 yarn add llamaindex
-jsr install @llamaindex/core
 ```
 
+### Setup TypeScript
+
+```json5
+{
+  compilerOptions: {
+    // ⬇️ add this line to your tsconfig.json
+    moduleResolution: "bundler", // or "node16"
+  },
+}
+```
+
+<details>
+   <summary>Why?</summary>
+  We are shipping both ESM and CJS module, and compatible with Vercel Edge, Cloudflare Workers, and other serverless platforms.
+
+So we are using [conditional exports](https://nodejs.org/api/packages.html#conditional-exports) to support all environments.
+
+This is a kind of modern way of shipping packages, but might cause TypeScript type check to fail because of legacy module resolution.
+
+Imaging you put output file into `/dist/openai.js` but you are importing `llamaindex/openai` in your code, and set `package.json` like this:
+
+```json
+{
+  "exports": {
+    "./openai": "./dist/openai.js"
+  }
+}
+```
+
+In old module resolution, TypeScript will not be able to find the module because it is not follow the file structure, even you run `node index.js` successfully. (on Node.js >=16)
+
+See more about [moduleResolution](https://www.typescriptlang.org/docs/handbook/modules/theory.html#module-resolution) or
+[TypeScript 5.0 blog](https://devblogs.microsoft.com/typescript/announcing-typescript-5-0/#--moduleresolution-bundler7).
+
+</details>
+
 ### Node.js
 
 ```ts
@@ -154,6 +189,21 @@ export async function chatWithAgent(
 }
 ```
 
+### Vite
+
+We have some wasm dependencies for better performance. You can use `vite-plugin-wasm` to load them.
+
+```ts
+import wasm from "vite-plugin-wasm";
+
+export default {
+  plugins: [wasm()],
+  ssr: {
+    external: ["tiktoken"],
+  },
+};
+```
+
 ## Playground
 
 Check out our NextJS playground at https://llama-playground.vercel.app/. The source is available at https://github.com/run-llama/ts-playground
@@ -164,7 +214,7 @@ Check out our NextJS playground at https://llama-playground.vercel.app/. The sou
 
 - [Node](/packages/llamaindex/src/Node.ts): The basic data building block. Most commonly, these are parts of the document split into manageable pieces that are small enough to be fed into an embedding model and LLM.
 
-- [Embedding](/packages/llamaindex/src/embeddings/OpenAIEmbedding.ts): Embeddings are sets of floating point numbers which represent the data in a Node. By comparing the similarity of embeddings, we can derive an understanding of the similarity of two pieces of data. One use case is to compare the embedding of a question with the embeddings of our Nodes to see which Nodes may contain the data needed to answer that quesiton. Because the default service context is OpenAI, the default embedding is `OpenAIEmbedding`. If using different models, say through Ollama, use this [Embedding](/packages/llamaindex/src/embeddings/OllamaEmbedding.ts) (see all [here](/packages/llamaindex/src/embeddings)).
+- [Embedding](/packages/llamaindex/src/embeddings/OpenAIEmbedding.ts): Embeddings are sets of floating point numbers which represent the data in a Node. By comparing the similarity of embeddings, we can derive an understanding of the similarity of two pieces of data. One use case is to compare the embedding of a question with the embeddings of our Nodes to see which Nodes may contain the data needed to answer that question. Because the default service context is OpenAI, the default embedding is `OpenAIEmbedding`. If using different models, say through Ollama, use this [Embedding](/packages/llamaindex/src/embeddings/OllamaEmbedding.ts) (see all [here](/packages/llamaindex/src/embeddings)).
 
 - [Indices](/packages/llamaindex/src/indices/): Indices store the Nodes and the embeddings of those nodes. QueryEngines retrieve Nodes from these Indices using embedding similarity.
 

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

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

apps/docs/CHANGELOG.md

@@ -1,5 +1,281 @@
 # docs
 
+## 0.0.71
+
+### Patch Changes
+
+- Updated dependencies [749b43a]
+  - llamaindex@0.6.2
+
+## 0.0.70
+
+### Patch Changes
+
+- Updated dependencies [fbd5e01]
+- Updated dependencies [6b70c54]
+- Updated dependencies [1a6137b]
+- Updated dependencies [85c2e19]
+  - llamaindex@0.6.1
+
+## 0.0.69
+
+### Patch Changes
+
+- Updated dependencies [11feef8]
+  - llamaindex@0.6.0
+  - @llamaindex/examples@0.0.8
+
+## 0.0.68
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+
+## 0.0.67
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+
+## 0.0.66
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+
+## 0.0.65
+
+### Patch Changes
+
+- llamaindex@0.5.24
+
+## 0.0.64
+
+### Patch Changes
+
+- llamaindex@0.5.23
+
+## 0.0.63
+
+### Patch Changes
+
+- Updated dependencies [4648da6]
+  - llamaindex@0.5.22
+
+## 0.0.62
+
+### Patch Changes
+
+- Updated dependencies [ae1149f]
+- Updated dependencies [2411c9f]
+- Updated dependencies [e8f229c]
+- Updated dependencies [11b3856]
+- Updated dependencies [83d7f41]
+- Updated dependencies [0148354]
+- Updated dependencies [1711f6d]
+  - llamaindex@0.5.21
+
+## 0.0.61
+
+### Patch Changes
+
+- Updated dependencies [d9d6c56]
+- Updated dependencies [22ff486]
+- Updated dependencies [eed0b04]
+  - llamaindex@0.5.20
+
+## 0.0.60
+
+### Patch Changes
+
+- Updated dependencies [fcbf183]
+  - llamaindex@0.5.19
+
+## 0.0.59
+
+### Patch Changes
+
+- Updated dependencies [8b66cf4]
+  - llamaindex@0.5.18
+
+## 0.0.58
+
+### Patch Changes
+
+- Updated dependencies [c654398]
+  - llamaindex@0.5.17
+
+## 0.0.57
+
+### Patch Changes
+
+- Updated dependencies [58abc57]
+  - llamaindex@0.5.16
+
+## 0.0.56
+
+### Patch Changes
+
+- Updated dependencies [01c184c]
+- Updated dependencies [07a275f]
+  - llamaindex@0.5.15
+
+## 0.0.55
+
+### Patch Changes
+
+- Updated dependencies [c825a2f]
+  - llamaindex@0.5.14
+
+## 0.0.54
+
+### Patch Changes
+
+- llamaindex@0.5.13
+
+## 0.0.53
+
+### Patch Changes
+
+- Updated dependencies [345300f]
+- Updated dependencies [da5cfc4]
+- Updated dependencies [da5cfc4]
+  - llamaindex@0.5.12
+
+## 0.0.52
+
+### Patch Changes
+
+- 376d29a: feat: added tool calling and agent support for llama3.1 504B
+  - llamaindex@0.5.11
+
+## 0.0.51
+
+### Patch Changes
+
+- 086b940: feat: add DeepSeek LLM
+- 5d5716b: feat: add a reader for JSON data
+- Updated dependencies [086b940]
+- Updated dependencies [5d5716b]
+- Updated dependencies [91d02a4]
+- Updated dependencies [fb6db45]
+  - llamaindex@0.5.10
+
+## 0.0.50
+
+### Patch Changes
+
+- Updated dependencies [15962b3]
+  - llamaindex@0.5.9
+
+## 0.0.49
+
+### Patch Changes
+
+- Updated dependencies [3d5ba08]
+- Updated dependencies [d917cdc]
+  - llamaindex@0.5.8
+
+## 0.0.48
+
+### Patch Changes
+
+- Updated dependencies [ec59acd]
+  - llamaindex@0.5.7
+
+## 0.0.47
+
+### Patch Changes
+
+- Updated dependencies [2562244]
+- Updated dependencies [325aa51]
+- Updated dependencies [ab700ea]
+- Updated dependencies [92f0782]
+- Updated dependencies [6cf6ae6]
+- Updated dependencies [b7cfe5b]
+  - llamaindex@0.5.6
+
+## 0.0.46
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - llamaindex@0.5.5
+
+## 0.0.45
+
+### Patch Changes
+
+- Updated dependencies [1a65ead]
+  - llamaindex@0.5.4
+
+## 0.0.44
+
+### Patch Changes
+
+- Updated dependencies [9bbbc67]
+- Updated dependencies [b3681bf]
+  - llamaindex@0.5.3
+
+## 0.0.43
+
+### Patch Changes
+
+- llamaindex@0.5.2
+
+## 0.0.42
+
+### Patch Changes
+
+- 2774681: Add mixedbread's embeddings and reranking API
+- Updated dependencies [2774681]
+- Updated dependencies [a0f424e]
+  - llamaindex@0.5.1
+
+## 0.0.41
+
+### Patch Changes
+
+- 36ddec4: fix: typo in custom page separator parameter for LlamaParse
+- Updated dependencies [16ef5dd]
+- Updated dependencies [16ef5dd]
+- Updated dependencies [36ddec4]
+  - llamaindex@0.5.0
+  - @llamaindex/examples@0.0.7
+
+## 0.0.40
+
+### Patch Changes
+
+- llamaindex@0.4.14
+
+## 0.0.39
+
+### Patch Changes
+
+- Updated dependencies [e8f8bea]
+- Updated dependencies [304484b]
+  - llamaindex@0.4.13
+
+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+
+## 0.0.37
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
 ## 0.0.36
 
 ### Patch Changes

apps/docs/docs/getting_started/concepts.md

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

apps/docs/docs/getting_started/environments.md

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

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

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

apps/docs/docs/introduction.md

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

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

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

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

@@ -15,6 +15,7 @@ LlamaIndex.TS comes with a few built-in agents, but you can also create your own
 - Anthropic Agent both via Anthropic and Bedrock (in `@llamaIndex/community`)
 - Gemini Agent
 - ReACT Agent
+- Meta3.1 504B via Bedrock (in `@llamaIndex/community`)
 
 ## Examples
 

apps/docs/docs/modules/chat_engine.md

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

apps/docs/docs/modules/data_index.md

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

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

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

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

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

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

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

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

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

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

@@ -8,7 +8,7 @@ In JSON mode, LlamaParse will return a data structure representing the parsed ob
 
 ## Usage
 
-For Json mode, you need to use `loadJson`. The `resultType` is automatically set with this method. Currently it can't be used with `SimpleDirectoryReader`.
+For Json mode, you need to use `loadJson`. The `resultType` is automatically set with this method.
 More information about indexing the results on the next page.
 
 ```ts

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

@@ -15,7 +15,7 @@ Settings.llm = new Bedrock({
 });
 ```
 
-Currently only supports Anthropic models:
+Currently only supports Anthropic and Meta models:
 
 ```ts
 ANTHROPIC_CLAUDE_INSTANT_1 = "anthropic.claude-instant-v1";
@@ -25,6 +25,13 @@ ANTHROPIC_CLAUDE_3_SONNET = "anthropic.claude-3-sonnet-20240229-v1:0";
 ANTHROPIC_CLAUDE_3_HAIKU = "anthropic.claude-3-haiku-20240307-v1:0";
 ANTHROPIC_CLAUDE_3_OPUS = "anthropic.claude-3-opus-20240229-v1:0"; // available on us-west-2
 ANTHROPIC_CLAUDE_3_5_SONNET = "anthropic.claude-3-5-sonnet-20240620-v1:0";
+META_LLAMA2_13B_CHAT = "meta.llama2-13b-chat-v1";
+META_LLAMA2_70B_CHAT = "meta.llama2-70b-chat-v1";
+META_LLAMA3_8B_INSTRUCT = "meta.llama3-8b-instruct-v1:0";
+META_LLAMA3_70B_INSTRUCT = "meta.llama3-70b-instruct-v1:0";
+META_LLAMA3_1_8B_INSTRUCT = "meta.llama3-1-8b-instruct-v1:0"; // available on us-west-2
+META_LLAMA3_1_70B_INSTRUCT = "meta.llama3-1-70b-instruct-v1:0"; // available on us-west-2
+META_LLAMA3_1_405B_INSTRUCT = "meta.llama3-1-405b-instruct-v1:0"; // preview only, available on us-west-2, tool calling supported
 ```
 
 Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url format, e.g. `data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==`
@@ -60,3 +67,72 @@ async function main() {
   console.log(response.response);
 }
 ```
+
+## Agent Example
+
+```ts
+import { BEDROCK_MODELS, Bedrock } from "@llamaindex/community";
+import { FunctionTool, LLMAgent } from "llamaindex";
+
+const sumNumbers = FunctionTool.from(
+  ({ a, b }: { a: number; b: number }) => `${a + b}`,
+  {
+    name: "sumNumbers",
+    description: "Use this function to sum two numbers",
+    parameters: {
+      type: "object",
+      properties: {
+        a: {
+          type: "number",
+          description: "The first number",
+        },
+        b: {
+          type: "number",
+          description: "The second number",
+        },
+      },
+      required: ["a", "b"],
+    },
+  },
+);
+
+const divideNumbers = FunctionTool.from(
+  ({ a, b }: { a: number; b: number }) => `${a / b}`,
+  {
+    name: "divideNumbers",
+    description: "Use this function to divide two numbers",
+    parameters: {
+      type: "object",
+      properties: {
+        a: {
+          type: "number",
+          description: "The dividend a to divide",
+        },
+        b: {
+          type: "number",
+          description: "The divisor b to divide by",
+        },
+      },
+      required: ["a", "b"],
+    },
+  },
+);
+
+const bedrock = new Bedrock({
+  model: BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
+  ...
+});
+
+async function main() {
+  const agent = new LLMAgent({
+    llm: bedrock,
+    tools: [sumNumbers, divideNumbers],
+  });
+
+  const response = await agent.chat({
+    message: "How much is 5 + 5? then divide by 2",
+  });
+
+  console.log(response.message);
+}
+```

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

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

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

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

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

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

apps/docs/docs/modules/node_parser.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 4
+sidebar_position: 11
 ---
 
 # NodeParser
@@ -7,9 +7,9 @@ sidebar_position: 4
 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";
+import { Document, SentenceSplitter } from "llamaindex";
 
-const nodeParser = new SimpleNodeParser();
+const nodeParser = new SentenceSplitter();
 
 Settings.nodeParser = nodeParser;
 ```
@@ -93,6 +93,5 @@ The output metadata will be something like:
 
 ## API Reference
 
-- [SimpleNodeParser](../api/classes/SimpleNodeParser.md)
 - [SentenceSplitter](../api/classes/SentenceSplitter.md)
 - [MarkdownNodeParser](../api/classes/MarkdownNodeParser.md)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

apps/docs/docs/modules/response_synthesizer.md

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

apps/docs/docs/modules/retriever.md

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

apps/docs/docs/modules/storage.md

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

apps/docs/docs/modules/workflows.mdx

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

apps/docs/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docs",
-  "version": "0.0.36",
+  "version": "0.0.71",
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",
@@ -15,29 +15,29 @@
     "typecheck": "tsc"
   },
   "dependencies": {
-    "@docusaurus/core": "^3.3.2",
-    "@docusaurus/remark-plugin-npm2yarn": "^3.3.2",
+    "@docusaurus/core": "3.5.2",
+    "@docusaurus/remark-plugin-npm2yarn": "3.5.2",
     "@llamaindex/examples": "workspace:*",
-    "@mdx-js/react": "^3.0.1",
-    "clsx": "^2.1.1",
+    "@mdx-js/react": "3.0.1",
+    "clsx": "2.1.1",
     "llamaindex": "workspace:*",
-    "postcss": "^8.4.38",
-    "prism-react-renderer": "^2.3.1",
-    "raw-loader": "^4.0.2",
-    "react": "^18.3.1",
-    "react-dom": "^18.3.1"
+    "postcss": "8.4.41",
+    "prism-react-renderer": "2.4.0",
+    "raw-loader": "4.0.2",
+    "react": "18.3.1",
+    "react-dom": "18.3.1"
   },
   "devDependencies": {
-    "@docusaurus/module-type-aliases": "3.3.2",
-    "@docusaurus/preset-classic": "^3.3.2",
-    "@docusaurus/theme-classic": "^3.3.2",
-    "@docusaurus/types": "^3.3.2",
-    "@tsconfig/docusaurus": "^2.0.3",
-    "@types/node": "^20.12.11",
-    "docusaurus-plugin-typedoc": "^1.0.1",
-    "typedoc": "^0.25.13",
-    "typedoc-plugin-markdown": "^4.0.1",
-    "typescript": "^5.5.2"
+    "@docusaurus/module-type-aliases": "3.5.2",
+    "@docusaurus/preset-classic": "3.5.2",
+    "@docusaurus/theme-classic": "3.5.2",
+    "@docusaurus/types": "3.5.2",
+    "@tsconfig/docusaurus": "2.0.3",
+    "@types/node": "^22.5.1",
+    "docusaurus-plugin-typedoc": "1.0.5",
+    "typedoc": "0.26.6",
+    "typedoc-plugin-markdown": "4.2.6",
+    "typescript": "^5.6.2"
   },
   "browserslist": {
     "production": [

examples/CHANGELOG.md

@@ -1,5 +1,24 @@
 # examples
 
+## 0.0.8
+
+### Patch Changes
+
+- 11feef8: Add workflows
+- Updated dependencies [11feef8]
+  - @llamaindex/core@0.2.0
+  - llamaindex@0.6.0
+
+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [16ef5dd]
+- Updated dependencies [16ef5dd]
+- Updated dependencies [36ddec4]
+  - llamaindex@0.5.0
+  - @llamaindex/core@0.1.0
+
 ## 0.0.6
 
 ### Patch Changes

examples/agent/multi_document_agent.ts

@@ -6,8 +6,8 @@ import {
   OpenAI,
   OpenAIAgent,
   QueryEngineTool,
+  SentenceSplitter,
   Settings,
-  SimpleNodeParser,
   SimpleToolNodeMapping,
   SummaryIndex,
   VectorStoreIndex,
@@ -43,7 +43,7 @@ async function main() {
   for (const title of wikiTitles) {
     console.log(`Processing ${title}`);
 
-    const nodes = new SimpleNodeParser({
+    const nodes = new SentenceSplitter({
       chunkSize: 200,
       chunkOverlap: 20,
     }).getNodesFromDocuments([countryDocs[title]]);

examples/agent/openai-task.ts

@@ -1,5 +1,4 @@
 import { ChatResponseChunk, OpenAIAgent } from "llamaindex";
-import { ReadableStream } from "node:stream/web";
 import {
   getCurrentIDTool,
   getUserInfoTool,

examples/agent/react-task.ts

@@ -1,5 +1,4 @@
 import { ChatResponseChunk, ReActAgent } from "llamaindex";
-import { ReadableStream } from "node:stream/web";
 import {
   getCurrentIDTool,
   getUserInfoTool,

examples/anthropic/agent.ts

@@ -2,7 +2,7 @@ import { Anthropic, FunctionTool, Settings, WikipediaTool } from "llamaindex";
 import { AnthropicAgent } from "llamaindex/agent/anthropic";
 
 Settings.callbackManager.on("llm-tool-call", (event) => {
-  console.log("llm-tool-call", event.detail.payload.toolCall);
+  console.log("llm-tool-call", event.detail.toolCall);
 });
 
 const anthropic = new Anthropic({

examples/anthropic/chat_interactive.ts

@@ -1,4 +1,4 @@
-import { Anthropic, SimpleChatEngine, SimpleChatHistory } from "llamaindex";
+import { Anthropic, ChatMemoryBuffer, SimpleChatEngine } from "llamaindex";
 import { stdin as input, stdout as output } from "node:process";
 import readline from "node:readline/promises";
 
@@ -8,8 +8,8 @@ import readline from "node:readline/promises";
     model: "claude-3-opus",
   });
   // chatHistory will store all the messages in the conversation
-  const chatHistory = new SimpleChatHistory({
-    messages: [
+  const chatHistory = new ChatMemoryBuffer({
+    chatHistory: [
       {
         content: "You want to talk in rhymes.",
         role: "system",

examples/chatEngine.ts

@@ -16,8 +16,9 @@ Settings.chunkSize = 512;
 async function main() {
   const document = new Document({ text: essay });
   const index = await VectorStoreIndex.fromDocuments([document]);
-  const retriever = index.asRetriever();
-  retriever.similarityTopK = 5;
+  const retriever = index.asRetriever({
+    similarityTopK: 5,
+  });
   const chatEngine = new ContextChatEngine({ retriever });
   const rl = readline.createInterface({ input, output });
 

examples/chatHistory.ts

@@ -2,10 +2,10 @@ import { stdin as input, stdout as output } from "node:process";
 import readline from "node:readline/promises";
 
 import {
+  ChatSummaryMemoryBuffer,
   OpenAI,
   Settings,
   SimpleChatEngine,
-  SummaryChatHistory,
 } from "llamaindex";
 
 if (process.env.NODE_ENV === "development") {
@@ -18,7 +18,7 @@ async function main() {
   // Set maxTokens to 75% of the context window size of 4096
   // This will trigger the summarizer once the chat history reaches 25% of the context window size (1024 tokens)
   const llm = new OpenAI({ model: "gpt-3.5-turbo", maxTokens: 4096 * 0.75 });
-  const chatHistory = new SummaryChatHistory({ llm });
+  const chatHistory = new ChatSummaryMemoryBuffer({ llm });
   const chatEngine = new SimpleChatEngine({ llm });
   const rl = readline.createInterface({ input, output });
 

examples/chromadb/preFilters.ts

@@ -40,7 +40,7 @@ async function main() {
           {
             key: "dogId",
             value: "2",
-            filterType: "ExactMatch",
+            operator: "==",
           },
         ],
       },

examples/deepinfra/embedding.ts

@@ -3,7 +3,7 @@ import { DeepInfraEmbedding } from "llamaindex";
 async function main() {
   // API token can be provided as an environment variable too
   // using DEEPINFRA_API_TOKEN variable
-  const apiToken = "YOUR_API_TOKEN" ?? process.env.DEEPINFRA_API_TOKEN;
+  const apiToken = process.env.DEEPINFRA_API_TOKEN ?? "YOUR_API_TOKEN";
   const model = "BAAI/bge-large-en-v1.5";
   const embedModel = new DeepInfraEmbedding({
     model,

examples/extractors/keywordExtractor.ts

@@ -2,13 +2,13 @@ import {
   Document,
   KeywordExtractor,
   OpenAI,
-  SimpleNodeParser,
+  SentenceSplitter,
 } from "llamaindex";
 
 (async () => {
   const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
 
-  const nodeParser = new SimpleNodeParser();
+  const nodeParser = new SentenceSplitter();
 
   const nodes = nodeParser.getNodesFromDocuments([
     new Document({ text: "banana apple orange pear peach watermelon" }),

examples/extractors/questionsAnsweredExtractor.ts

@@ -2,13 +2,13 @@ import {
   Document,
   OpenAI,
   QuestionsAnsweredExtractor,
-  SimpleNodeParser,
+  SentenceSplitter,
 } from "llamaindex";
 
 (async () => {
   const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
 
-  const nodeParser = new SimpleNodeParser();
+  const nodeParser = new SentenceSplitter();
 
   const nodes = nodeParser.getNodesFromDocuments([
     new Document({

examples/extractors/summaryExtractor.ts

@@ -1,14 +1,14 @@
 import {
   Document,
   OpenAI,
-  SimpleNodeParser,
+  SentenceSplitter,
   SummaryExtractor,
 } from "llamaindex";
 
 (async () => {
   const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
 
-  const nodeParser = new SimpleNodeParser();
+  const nodeParser = new SentenceSplitter();
 
   const nodes = nodeParser.getNodesFromDocuments([
     new Document({

examples/extractors/titleExtractor.ts

@@ -1,11 +1,11 @@
-import { Document, OpenAI, SimpleNodeParser, TitleExtractor } from "llamaindex";
+import { Document, OpenAI, SentenceSplitter, TitleExtractor } from "llamaindex";
 
 import essay from "../essay";
 
 (async () => {
   const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo-0125", temperature: 0 });
 
-  const nodeParser = new SimpleNodeParser({});
+  const nodeParser = new SentenceSplitter({});
 
   const nodes = nodeParser.getNodesFromDocuments([
     new Document({

examples/groq.ts

@@ -1,12 +1,23 @@
 import fs from "node:fs/promises";
 
-import { Document, Groq, Settings, VectorStoreIndex } from "llamaindex";
+import {
+  Document,
+  Groq,
+  HuggingFaceEmbedding,
+  Settings,
+  VectorStoreIndex,
+} from "llamaindex";
 
 // Update llm to use Groq
 Settings.llm = new Groq({
   apiKey: process.env.GROQ_API_KEY,
 });
 
+// Use HuggingFace for embeddings
+Settings.embedModel = new HuggingFaceEmbedding({
+  modelType: "Xenova/all-mpnet-base-v2",
+});
+
 async function main() {
   // Load essay from abramov.txt in Node
   const path = "node_modules/llamaindex/examples/abramov.txt";

examples/jupyter/nodeparser.ipynb

@@ -7,10 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import {\n",
-    "  Document,\n",
-    "  SimpleNodeParser\n",
-    "} from \"npm:llamaindex\";"
+    "import { Document, SentenceSplitter } from \"npm:llamaindex\";"
    ]
   },
   {
@@ -45,7 +42,7 @@
     }
    ],
    "source": [
-    "const nodeParser = new SimpleNodeParser();\n",
+    "const nodeParser = new SentenceSplitter();\n",
     "const nodes = nodeParser.getNodesFromDocuments([\n",
     "    new Document({ text: \"I am 10 years old. John is 20 years old.\" }),\n",
     "]);\n",

examples/longText.ts

@@ -1,17 +1,16 @@
 import {
   Document,
+  SentenceSplitter,
   Settings,
-  SimpleNodeParser,
   VectorStoreIndex,
 } from "llamaindex";
 
 export const STORAGE_DIR = "./data";
 
 // Update node parser
-Settings.nodeParser = new SimpleNodeParser({
+Settings.nodeParser = new SentenceSplitter({
   chunkSize: 512,
   chunkOverlap: 20,
-  splitLongSentences: true,
 });
 (async () => {
   // generate a document with a very long sentence (9000 words long)

examples/lowlevel.ts

@@ -2,12 +2,12 @@ import {
   Document,
   NodeWithScore,
   ResponseSynthesizer,
-  SimpleNodeParser,
+  SentenceSplitter,
   TextNode,
 } from "llamaindex";
 
 (async () => {
-  const nodeParser = new SimpleNodeParser();
+  const nodeParser = new SentenceSplitter();
   const nodes = nodeParser.getNodesFromDocuments([
     new Document({ text: "I am 10 years old. John is 20 years old." }),
   ]);
@@ -27,11 +27,13 @@ import {
     },
   ];
 
-  const stream = await responseSynthesizer.synthesize({
-    query: "What age am I?",
-    nodesWithScore,
-    stream: true,
-  });
+  const stream = await responseSynthesizer.synthesize(
+    {
+      query: "What age am I?",
+      nodesWithScore,
+    },
+    true,
+  );
   for await (const chunk of stream) {
     process.stdout.write(chunk.response);
   }

examples/metadata-filter/milvus.ts

@@ -0,0 +1,40 @@
+import { MilvusVectorStore, VectorStoreIndex } from "llamaindex";
+
+const collectionName = "movie_reviews";
+
+async function main() {
+  try {
+    const milvus = new MilvusVectorStore({ collection: collectionName });
+    const index = await VectorStoreIndex.fromVectorStore(milvus);
+    const retriever = index.asRetriever({ similarityTopK: 20 });
+
+    console.log("\n=====\nQuerying the index with filters");
+    const queryEngineWithFilters = index.asQueryEngine({
+      retriever,
+      preFilters: {
+        filters: [
+          {
+            key: "document_id",
+            value: "./data/movie_reviews.csv_37",
+            operator: "==",
+          },
+          {
+            key: "document_id",
+            value: "./data/movie_reviews.csv_37",
+            operator: "!=",
+          },
+        ],
+        condition: "or",
+      },
+    });
+    const resultAfterFilter = await queryEngineWithFilters.query({
+      query: "Get all movie titles.",
+    });
+    console.log(`Query from ${resultAfterFilter.sourceNodes?.length} nodes`);
+    console.log(resultAfterFilter.response);
+  } catch (e) {
+    console.error(e);
+  }
+}
+
+void main();

examples/metadata-filter/simple.ts

@@ -0,0 +1,143 @@
+import {
+  Document,
+  Settings,
+  SimpleDocumentStore,
+  VectorStoreIndex,
+  storageContextFromDefaults,
+} from "llamaindex";
+
+Settings.callbackManager.on("retrieve-end", (event) => {
+  const { nodes } = event.detail;
+  console.log("Number of retrieved nodes:", nodes.length);
+});
+
+async function getDataSource() {
+  const docs = [
+    new Document({
+      text: "The dog is brown",
+      metadata: {
+        dogId: "1",
+        private: true,
+      },
+    }),
+    new Document({
+      text: "The dog is yellow",
+      metadata: {
+        dogId: "2",
+        private: false,
+      },
+    }),
+    new Document({
+      text: "The dog is red",
+      metadata: {
+        dogId: "3",
+        private: false,
+      },
+    }),
+  ];
+  const storageContext = await storageContextFromDefaults({
+    persistDir: "./cache",
+  });
+  const numberOfDocs = Object.keys(
+    (storageContext.docStore as SimpleDocumentStore).toDict(),
+  ).length;
+  if (numberOfDocs === 0) {
+    // Generate the data source if it's empty
+    return await VectorStoreIndex.fromDocuments(docs, {
+      storageContext,
+    });
+  }
+  return await VectorStoreIndex.init({
+    storageContext,
+  });
+}
+
+async function main() {
+  const index = await getDataSource();
+  console.log(
+    "=============\nQuerying index with no filters. The output should be any color.",
+  );
+  const queryEngineNoFilters = index.asQueryEngine({
+    similarityTopK: 3,
+  });
+  const noFilterResponse = await queryEngineNoFilters.query({
+    query: "What is the color of the dog?",
+  });
+  console.log("No filter response:", noFilterResponse.toString());
+
+  console.log(
+    "\n=============\nQuerying index with dogId 2 and private false. The output always should be red.",
+  );
+  const queryEngineEQ = index.asQueryEngine({
+    preFilters: {
+      filters: [
+        {
+          key: "private",
+          value: "false",
+          operator: "==",
+        },
+        {
+          key: "dogId",
+          value: "3",
+          operator: "==",
+        },
+      ],
+    },
+    similarityTopK: 3,
+  });
+  const responseEQ = await queryEngineEQ.query({
+    query: "What is the color of the dog?",
+  });
+  console.log("Filter with dogId 2 response:", responseEQ.toString());
+
+  console.log(
+    "\n=============\nQuerying index with dogId IN (1, 3). The output should be brown and red.",
+  );
+  const queryEngineIN = index.asQueryEngine({
+    preFilters: {
+      filters: [
+        {
+          key: "dogId",
+          value: ["1", "3"],
+          operator: "in",
+        },
+      ],
+    },
+    similarityTopK: 3,
+  });
+  const responseIN = await queryEngineIN.query({
+    query: "What is the color of the dog?",
+  });
+  console.log("Filter with dogId IN (1, 3) response:", responseIN.toString());
+
+  console.log(
+    "\n=============\nQuerying index with dogId IN (1, 3). The output should be any.",
+  );
+  const queryEngineOR = index.asQueryEngine({
+    preFilters: {
+      filters: [
+        {
+          key: "private",
+          value: "false",
+          operator: "==",
+        },
+        {
+          key: "dogId",
+          value: ["1", "3"],
+          operator: "in",
+        },
+      ],
+      condition: "or",
+    },
+    similarityTopK: 3,
+  });
+  const responseOR = await queryEngineOR.query({
+    query: "What is the color of the dog?",
+  });
+  console.log(
+    "Filter with dogId with OR operator response:",
+    responseOR.toString(),
+  );
+}
+
+void main();

examples/mongodb/2_load_and_index.ts

@@ -28,12 +28,23 @@ async function loadAndIndex() {
     "full_text",
   ]);
 
+  const FILTER_METADATA_FIELD = "content_type";
+
+  documents.forEach((document, index) => {
+    const contentType = ["tweet", "post", "story"][index % 3]; // assign a random content type to each document
+    document.metadata = {
+      ...document.metadata,
+      [FILTER_METADATA_FIELD]: contentType,
+    };
+  });
+
   // create Atlas as a vector store
   const vectorStore = new MongoDBAtlasVectorSearch({
     mongodbClient: client,
     dbName: databaseName,
     collectionName: vectorCollectionName, // this is where your embeddings will be stored
     indexName: indexName, // this is the name of the index you will need to create
+    indexedMetadataFields: [FILTER_METADATA_FIELD], // this is the field that will be used for the query
   });
 
   // now create an index from all the Documents and store them in Atlas
@@ -45,39 +56,4 @@ async function loadAndIndex() {
   await client.close();
 }
 
-/**
- * This method is document in https://www.mongodb.com/docs/atlas/atlas-search/create-index/#create-an-fts-index-programmatically
- * But, while testing a 'CommandNotFound' error occurred, so we're not using this here.
- */
-async function createSearchIndex() {
-  const client = new MongoClient(mongoUri);
-  const database = client.db(databaseName);
-  const collection = database.collection(vectorCollectionName);
-
-  // define your Atlas Search index
-  const index = {
-    name: indexName,
-    definition: {
-      /* search index definition fields */
-      mappings: {
-        dynamic: true,
-        fields: [
-          {
-            type: "vector",
-            path: "embedding",
-            numDimensions: 1536,
-            similarity: "cosine",
-          },
-        ],
-      },
-    },
-  };
-  // run the helper method
-  const result = await collection.createSearchIndex(index);
-  console.log("Successfully created search index:", result);
-  await client.close();
-}
-
 loadAndIndex().catch(console.error);
-
-// you can't query your index yet because you need to create a vector search index in mongodb's UI now

examples/mongodb/3_query.ts

@@ -14,14 +14,26 @@ async function query() {
     dbName: process.env.MONGODB_DATABASE!,
     collectionName: process.env.MONGODB_VECTORS!,
     indexName: process.env.MONGODB_VECTOR_INDEX!,
+    indexedMetadataFields: ["content_type"],
   });
 
   const index = await VectorStoreIndex.fromVectorStore(store);
 
   const retriever = index.asRetriever({ similarityTopK: 20 });
-  const queryEngine = index.asQueryEngine({ retriever });
+  const queryEngine = index.asQueryEngine({
+    retriever,
+    preFilters: {
+      filters: [
+        {
+          key: "content_type",
+          value: "story", // try "tweet" or "post" to see the difference
+          operator: "==",
+        },
+      ],
+    },
+  });
   const result = await queryEngine.query({
-    query: "What does the author think of web frameworks?",
+    query: "What does author receive when he was 11 years old?", // Isaac Asimov's "Foundation" for Christmas
   });
   console.log(result.response);
   await client.close();

examples/mongodb/README.md

@@ -68,45 +68,6 @@ What you're doing here is creating a Reader which loads the data out of Mongo in
 
 Now you're creating a vector search client for Mongo. In addition to a MongoDB client object, you again tell it what database everything is in. This time you give it the name of the collection where you'll store the vector embeddings, and the name of the vector search index you'll create in the next step.
 
-### Create a vector search index
-
-Now if all has gone well you should be able to log in to the Mongo Atlas UI and see two collections in your database: the original data in `tiny_tweets_collection`, and the vector embeddings in `tiny_tweets_vectors`.
-
-![MongoDB Atlas collections](./docs/3_vectors_in_db.png)
-
-Now it's time to create the vector search index so that you can query the data.
-It's not yet possible to programmatically create a vector search index using the [`createIndex`](https://www.mongodb.com/docs/manual/reference/method/db.collection.createIndex/) function, therefore we have to create one manually in the UI.
-To do so, first, click the 'Atlas Search' tab, and then click "Create Search Index":
-
-![MongoDB Atlas create search index](./docs/4_search_tab.png)
-
-We have to use the JSON editor, as the Visual Editor does not yet support to create a vector search index:
-
-![MongoDB Atlas JSON editor](./docs/5_json_editor.png)
-
-Now under "database and collection" select `tiny_tweets_db` and within that select `tiny_tweets_vectors`. Then under "Index name" enter `tiny_tweets_vector_index` (or whatever value you put for MONGODB_VECTOR_INDEX in `.env`). Under that, you'll want to enter this JSON object:
-
-```json
-{
-  "fields": [
-    {
-      "type": "vector",
-      "path": "embedding",
-      "numDimensions": 1536,
-      "similarity": "cosine"
-    }
-  ]
-}
-```
-
-This tells Mongo that the `embedding` field in each document (in the `tiny_tweets_vectors` collection) is a vector of 1536 dimensions (this is the size of embeddings used by OpenAI), and that we want to use cosine similarity to compare vectors. You don't need to worry too much about these values unless you want to use a different LLM to OpenAI entirely.
-
-The UI will ask you to review and confirm your choices, then you need to wait a minute or two while it generates the index. If all goes well, you should see something like this screen:
-
-![MongoDB Atlas index created](./docs/7_index_created.png)
-
-Now you're ready to query your data!
-
 ### Run a test query
 
 You can do this by running

examples/multimodal/chat.ts

@@ -0,0 +1,40 @@
+// call pnpm tsx multimodal/load.ts first to init the storage
+import { OpenAI, Settings, SimpleChatEngine, imageToDataUrl } from "llamaindex";
+import fs from "node:fs/promises";
+
+import path from "path";
+// Update llm
+Settings.llm = new OpenAI({ model: "gpt-4o-mini", maxTokens: 512 });
+
+async function main() {
+  const chatEngine = new SimpleChatEngine();
+
+  // Load the image and convert it to a data URL
+  const imagePath = path.join(__dirname, ".", "data", "60.jpg");
+
+  // 1. you can read the buffer from the file
+  const imageBuffer = await fs.readFile(imagePath);
+  const dataUrl = await imageToDataUrl(imageBuffer);
+  // or 2. you can just pass the file path to the imageToDataUrl function
+  // const dataUrl = await imageToDataUrl(imagePath);
+
+  // Update the image_url in the chat message
+  const response = await chatEngine.chat({
+    message: [
+      {
+        type: "text",
+        text: "What is in this image?",
+      },
+      {
+        type: "image_url",
+        image_url: {
+          url: dataUrl,
+        },
+      },
+    ],
+  });
+
+  console.log(response.message.content);
+}
+
+main().catch(console.error);

examples/multimodal/context.ts

@@ -4,7 +4,6 @@ import {
   NodeWithScore,
   ObjectType,
   OpenAI,
-  RetrievalEndEvent,
   Settings,
   VectorStoreIndex,
 } from "llamaindex";
@@ -18,8 +17,8 @@ Settings.chunkOverlap = 20;
 Settings.llm = new OpenAI({ model: "gpt-4-turbo", maxTokens: 512 });
 
 // Update callbackManager
-Settings.callbackManager.on("retrieve-end", (event: RetrievalEndEvent) => {
-  const { nodes, query } = event.detail.payload;
+Settings.callbackManager.on("retrieve-end", (event) => {
+  const { nodes, query } = event.detail;
   const imageNodes = nodes.filter(
     (node: NodeWithScore) => node.node.type === ObjectType.IMAGE_DOCUMENT,
   );

examples/multimodal/jina.ts

@@ -0,0 +1,83 @@
+import {
+  ImageDocument,
+  JinaAIEmbedding,
+  similarity,
+  SimilarityType,
+  SimpleDirectoryReader,
+} from "llamaindex";
+import path from "path";
+
+async function main() {
+  const jina = new JinaAIEmbedding({
+    model: "jina-clip-v1",
+  });
+
+  // Get text embeddings
+  const text1 = "a car";
+  const textEmbedding1 = await jina.getTextEmbedding(text1);
+  const text2 = "a football match";
+  const textEmbedding2 = await jina.getTextEmbedding(text2);
+
+  // Get image embedding
+  const image =
+    "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg";
+  const imageEmbedding = await jina.getImageEmbedding(image);
+
+  // Calc similarity between text and image
+  const sim1 = similarity(
+    textEmbedding1,
+    imageEmbedding,
+    SimilarityType.DEFAULT,
+  );
+  const sim2 = similarity(
+    textEmbedding2,
+    imageEmbedding,
+    SimilarityType.DEFAULT,
+  );
+
+  console.log(`Similarity between "${text1}" and the image is ${sim1}`);
+  console.log(`Similarity between "${text2}" and the image is ${sim2}`);
+
+  // Get multiple text embeddings
+  const textEmbeddings = await jina.getTextEmbeddings([text1, text2]);
+  const sim3 = similarity(
+    textEmbeddings[0],
+    textEmbeddings[1],
+    SimilarityType.DEFAULT,
+  );
+  console.log(
+    `Similarity between the two texts "${text1}" and "${text2}" is ${sim3}`,
+  );
+
+  // Get multiple image embeddings
+  const catImg1 =
+    "https://i.pinimg.com/600x315/21/48/7e/21487e8e0970dd366dafaed6ab25d8d8.jpg";
+  const catImg2 =
+    "https://i.pinimg.com/736x/c9/f2/3e/c9f23e212529f13f19bad5602d84b78b.jpg";
+  const imageEmbeddings = await jina.getImageEmbeddings([catImg1, catImg2]);
+  const sim4 = similarity(
+    imageEmbeddings[0],
+    imageEmbeddings[1],
+    SimilarityType.DEFAULT,
+  );
+  console.log(`Similarity between the two online cat images is ${sim4}`);
+
+  // Get image embeddings from multiple local files
+  const documents = await new SimpleDirectoryReader().loadData({
+    directoryPath: path.join("multimodal", "data"),
+  });
+  const localImages = documents
+    .filter((doc) => doc instanceof ImageDocument)
+    .slice(0, 2); // Get only the first two images
+  const localImageEmbeddings = await jina.getImageEmbeddings(
+    localImages.map((doc) => (doc as ImageDocument).image),
+  );
+  const sim5 = similarity(
+    localImageEmbeddings[0],
+    localImageEmbeddings[1],
+    SimilarityType.DEFAULT,
+  );
+  console.log(`Similarity between the two local images is ${sim5}`);
+}
+
+void main();

examples/multimodal/rag.ts

@@ -1,7 +1,6 @@
 import {
   MultiModalResponseSynthesizer,
   OpenAI,
-  RetrievalEndEvent,
   Settings,
   VectorStoreIndex,
 } from "llamaindex";
@@ -15,8 +14,8 @@ Settings.chunkOverlap = 20;
 Settings.llm = new OpenAI({ model: "gpt-4-turbo", maxTokens: 512 });
 
 // Update callbackManager
-Settings.callbackManager.on("retrieve-end", (event: RetrievalEndEvent) => {
-  const { nodes, query } = event.detail.payload;
+Settings.callbackManager.on("retrieve-end", (event) => {
+  const { nodes, query } = event.detail;
   console.log(`Retrieved ${nodes.length} nodes for query: ${query}`);
 });
 

examples/openai_o1.ts

@@ -0,0 +1,13 @@
+import { OpenAI } from "llamaindex";
+
+(async () => {
+  const llm = new OpenAI({ model: "o1-preview", temperature: 1 });
+
+  const prompt = `What are three compounds we should consider investigating to advance research 
+  into new antibiotics? Why should we consider them?
+  `;
+
+  // complete api
+  const response = await llm.complete({ prompt });
+  console.log(response.text);
+})();

examples/package.json

@@ -1,26 +1,27 @@
 {
   "name": "@llamaindex/examples",
   "private": true,
-  "version": "0.0.6",
+  "version": "0.0.8",
   "dependencies": {
     "@aws-crypto/sha256-js": "^5.2.0",
-    "@azure/identity": "^4.2.1",
-    "@datastax/astra-db-ts": "^1.2.1",
+    "@azure/identity": "^4.4.1",
+    "@datastax/astra-db-ts": "^1.4.1",
+    "@llamaindex/core": "^0.2.0",
     "@notionhq/client": "^2.2.15",
-    "@pinecone-database/pinecone": "^2.2.2",
-    "@zilliz/milvus2-sdk-node": "^2.4.2",
+    "@pinecone-database/pinecone": "^3.0.2",
+    "@zilliz/milvus2-sdk-node": "^2.4.6",
     "chromadb": "^1.8.1",
     "commander": "^12.1.0",
     "dotenv": "^16.4.5",
-    "js-tiktoken": "^1.0.12",
-    "llamaindex": "^0.4.3",
+    "js-tiktoken": "^1.0.14",
+    "llamaindex": "^0.6.0",
     "mongodb": "^6.7.0",
     "pathe": "^1.1.2"
   },
   "devDependencies": {
-    "@types/node": "^20.14.1",
-    "tsx": "^4.15.6",
-    "typescript": "^5.5.2"
+    "@types/node": "^22.5.1",
+    "tsx": "^4.19.0",
+    "typescript": "^5.6.2"
   },
   "scripts": {
     "lint": "eslint ."

examples/pipeline/ingestion.ts

@@ -5,7 +5,7 @@ import {
   IngestionPipeline,
   MetadataMode,
   OpenAIEmbedding,
-  SimpleNodeParser,
+  SentenceSplitter,
 } from "llamaindex";
 
 async function main() {
@@ -18,7 +18,7 @@ async function main() {
   const document = new Document({ text: essay, id_: path });
   const pipeline = new IngestionPipeline({
     transformations: [
-      new SimpleNodeParser({ chunkSize: 1024, chunkOverlap: 20 }),
+      new SentenceSplitter({ chunkSize: 1024, chunkOverlap: 20 }),
       new OpenAIEmbedding(),
     ],
   });

examples/prompts/promptMixin.ts

@@ -1,21 +1,22 @@
 import {
   Document,
+  PromptTemplate,
   ResponseSynthesizer,
   TreeSummarize,
   TreeSummarizePrompt,
   VectorStoreIndex,
 } from "llamaindex";
 
-const treeSummarizePrompt: TreeSummarizePrompt = ({ context, query }) => {
-  return `Context information from multiple sources is below.
+const treeSummarizePrompt: TreeSummarizePrompt = new PromptTemplate({
+  template: `Context information from multiple sources is below.
 ---------------------
-${context}
+{context}
 ---------------------
 Given the information from multiple sources and not prior knowledge.
 Answer the query in the style of a Shakespeare play"
-Query: ${query}
-Answer:`;
-};
+Query: {query}
+Answer:`,
+});
 
 async function main() {
   const documents = new Document({

examples/qdrantdb/preFilters.ts

@@ -1,8 +1,8 @@
 import * as dotenv from "dotenv";
 import {
-  CallbackManager,
   Document,
   MetadataMode,
+  NodeWithScore,
   QdrantVectorStore,
   Settings,
   VectorStoreIndex,
@@ -10,13 +10,12 @@ import {
 } from "llamaindex";
 
 // Update callback manager
-Settings.callbackManager = new CallbackManager({
-  onRetrieve: (data) => {
-    console.log(
-      "The retrieved nodes are:",
-      data.nodes.map((node) => node.node.getContent(MetadataMode.NONE)),
-    );
-  },
+Settings.callbackManager.on("retrieve-end", (event) => {
+  const { nodes } = event.detail;
+  console.log(
+    "The retrieved nodes are:",
+    nodes.map((node: NodeWithScore) => node.node.getContent(MetadataMode.NONE)),
+  );
 });
 
 // Load environment variables from local .env file
@@ -65,7 +64,7 @@ async function main() {
           {
             key: "dogId",
             value: "2",
-            filterType: "ExactMatch",
+            operator: "==",
           },
         ],
       },

examples/readers/package.json

@@ -11,15 +11,18 @@
     "start:pdf": "node --import tsx ./src/pdf.ts",
     "start:llamaparse": "node --import tsx ./src/llamaparse.ts",
     "start:notion": "node --import tsx ./src/notion.ts",
+    "start:assemblyai": "node --import tsx ./src/assemblyai.ts",
     "start:llamaparse-dir": "node --import tsx ./src/simple-directory-reader-with-llamaparse.ts",
-    "start:llamaparse-json": "node --import tsx ./src/llamaparse-json.ts"
+    "start:llamaparse-json": "node --import tsx ./src/llamaparse-json.ts",
+    "start:discord": "node --import tsx ./src/discord.ts",
+    "start:json": "node --import tsx ./src/json.ts"
   },
   "dependencies": {
     "llamaindex": "*"
   },
   "devDependencies": {
-    "@types/node": "^20.12.11",
-    "tsx": "^4.15.6",
-    "typescript": "^5.5.2"
+    "@types/node": "^22.5.1",
+    "tsx": "^4.19.0",
+    "typescript": "^5.6.2"
   }
 }

examples/readers/src/csv.ts

@@ -1,6 +1,7 @@
 import {
   CompactAndRefine,
   OpenAI,
+  PromptTemplate,
   ResponseSynthesizer,
   Settings,
   VectorStoreIndex,
@@ -18,14 +19,15 @@ async function main() {
   // Split text and create embeddings. Store them in a VectorStoreIndex
   const index = await VectorStoreIndex.fromDocuments(documents);
 
-  const csvPrompt = ({ context = "", query = "" }) => {
-    return `The following CSV file is loaded from ${path}
+  const csvPrompt = new PromptTemplate({
+    templateVars: ["query", "context"],
+    template: `The following CSV file is loaded from ${path}
 \`\`\`csv
-${context}
+{context}
 \`\`\`
-Given the CSV file, generate me Typescript code to answer the question: ${query}. You can use built in NodeJS functions but avoid using third party libraries.
-`;
-  };
+Given the CSV file, generate me Typescript code to answer the question: {query}. You can use built in NodeJS functions but avoid using third party libraries.
+`,
+  });
 
   const responseSynthesizer = new ResponseSynthesizer({
     responseBuilder: new CompactAndRefine(undefined, csvPrompt),