Release 0.5.27 (#1195)

Co-authored-by: github-actions[bot] <github-actions[bot]@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/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: 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:
@@ -42,7 +54,6 @@ jobs:
         node-version: [18.x, 20.x, 22.x]
     name: Test on Node.js ${{ matrix.node-version }}
     runs-on: ubuntu-latest
-
     steps:
       - uses: actions/checkout@v4
       - uses: pnpm/action-setup@v4
@@ -92,7 +103,7 @@ jobs:
           - nextjs-agent
           - nextjs-edge-runtime
           - nextjs-node-runtime
-    #          - waku-query-engine
+          - waku-query-engine
     runs-on: ubuntu-latest
     name: Build LlamaIndex Example (${{ matrix.packages }})
     steps:
@@ -131,6 +142,9 @@ 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/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 +1,202 @@
 # docs
 
+## 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

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/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

@@ -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

@@ -21,3 +21,4 @@ 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

@@ -16,7 +16,15 @@ 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

@@ -41,11 +41,17 @@ They can be divided into two groups.
 - `doNotCache?` Optional. Set to true to not cache the document.
 - `fastMode?` Optional. Set to true to use the fast mode. This mode will skip OCR of images, and table/heading reconstruction. Note: Non-compatible with `gpt4oMode`.
 - `doNotUnrollColumns?` Optional. Set to true to keep the text according to document layout. Reduce reconstruction accuracy, and LLMs/embeddings performances in most cases.
-- `pageSeparator?` Optional. The page separator 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`.
+- `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/embeddings/available_embeddings/mixedbreadai.md

@@ -98,3 +98,7 @@ Use the `embedDocuments` method to generate embeddings for the texts.
 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/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/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/available_llms/bedrock.md

@@ -29,6 +29,9 @@ 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==`
@@ -64,3 +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/node_parser.md

@@ -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/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

@@ -55,8 +55,9 @@ const index = await VectorStoreIndex.fromDocuments([document]);
 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();
-retriever.similarityTopK = 5;
+const retriever = index.asRetriever({
+  similarityTopK: 5,
+});
 ```
 
 ### Step 3: Create a MixedbreadAIReranker Instance
@@ -162,3 +163,7 @@ Use the `rerank` method to reorder the documents based on the query.
 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/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/retriever.md

@@ -4,18 +4,20 @@ sidebar_position: 5
 
 # 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

@@ -4,12 +4,19 @@ 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.
+Storage in LlamaIndex.TS works automatically once you've configured a
+`StorageContext` object.
 
-Right now, only saving and loading from disk is supported, with future integrations planned!
+## Local Storage
+
+You can configure the `persistDir` and attach it to an index.
 
 ```typescript
-import { Document, VectorStoreIndex, storageContextFromDefaults } from "./src";
+import {
+  Document,
+  VectorStoreIndex,
+  storageContextFromDefaults,
+} from "llamaindex";
 
 const storageContext = await storageContextFromDefaults({
   persistDir: "./storage",
@@ -21,6 +28,33 @@ const index = await VectorStoreIndex.fromDocuments([document], {
 });
 ```
 
+## 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/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docs",
-  "version": "0.0.43",
+  "version": "0.0.68",
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",
@@ -15,29 +15,29 @@
     "typecheck": "tsc"
   },
   "dependencies": {
-    "@docusaurus/core": "3.4.0",
-    "@docusaurus/remark-plugin-npm2yarn": "3.4.0",
+    "@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",
     "llamaindex": "workspace:*",
-    "postcss": "8.4.39",
-    "prism-react-renderer": "2.3.1",
+    "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": "3.4.0",
-    "@docusaurus/preset-classic": "3.4.0",
-    "@docusaurus/theme-classic": "3.4.0",
-    "@docusaurus/types": "3.4.0",
+    "@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": "^20.12.11",
-    "docusaurus-plugin-typedoc": "1.0.2",
-    "typedoc": "0.26.3",
-    "typedoc-plugin-markdown": "4.1.2",
-    "typescript": "^5.5.2"
+    "@types/node": "^22.5.1",
+    "docusaurus-plugin-typedoc": "1.0.5",
+    "typedoc": "0.26.6",
+    "typedoc-plugin-markdown": "4.2.6",
+    "typescript": "^5.5.4"
   },
   "browserslist": {
     "production": [

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/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/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/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/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/package.json

@@ -4,24 +4,24 @@
   "version": "0.0.7",
   "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": "^0.1.0",
     "@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",
+    "js-tiktoken": "^1.0.14",
     "llamaindex": "^0.5.0",
     "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": "^5.5.4"
   },
   "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

@@ -64,7 +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": "^5.5.4"
   }
 }

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),

examples/readers/src/discord.ts

@@ -0,0 +1,20 @@
+import { DiscordReader } from "llamaindex";
+
+async function main() {
+  // Create an instance of the DiscordReader. Set token here or DISCORD_TOKEN environment variable
+  const discordReader = new DiscordReader();
+
+  // Specify the channel IDs you want to read messages from as an arry of strings
+  const channelIds = ["721374320794009630", "719596376261918720"];
+
+  // Specify the number of messages to fetch per channel
+  const limit = 10;
+
+  // Load messages from the specified channel
+  const messages = await discordReader.loadData(channelIds, limit, true);
+
+  // Print out the messages
+  console.log(messages);
+}
+
+main().catch(console.error);

examples/readers/src/json.ts

@@ -0,0 +1,49 @@
+import { JSONReader } from "llamaindex";
+
+async function main() {
+  // Data
+  const file = "../data/tinytweets.json";
+  const nonAsciiContent = '{"message": "こんにちは世界"}';
+  const jsonlContent = '{"tweet": "Hello world"}\n{"tweet": "こんにちは世界"}';
+
+  // Convert strings to Uint8Array for loadDataAsContent
+  const nonAsciiBuffer = new TextEncoder().encode(nonAsciiContent);
+  const jsonlBuffer = new TextEncoder().encode(jsonlContent);
+
+  // Default settings
+  const reader1 = new JSONReader();
+  const docs1 = await reader1.loadData(file);
+  console.log(docs1[0]);
+
+  // Unclean JSON
+  const reader2 = new JSONReader({ cleanJson: false });
+  const docs2 = await reader2.loadData(file);
+  console.log(docs2[0]);
+
+  // Depth first yield of JSON structural paths, going back 2 levels
+  const reader3 = new JSONReader({ levelsBack: 2 });
+  const docs3 = await reader3.loadData(file);
+  console.log(docs3[0]);
+
+  // Depth first yield of all levels
+  const reader4 = new JSONReader({ levelsBack: 0 });
+  const docs4 = await reader4.loadData(file);
+  console.log(docs4[0]);
+
+  // Depth first yield of all levels, collapse structural paths below length 100
+  const reader5 = new JSONReader({ levelsBack: 0, collapseLength: 100 });
+  const docs5 = await reader5.loadData(file);
+  console.log(docs5[0]);
+
+  // Convert ASCII to unichode escape sequences
+  const reader6 = new JSONReader({ ensureAscii: true });
+  const docs6 = await reader6.loadDataAsContent(nonAsciiBuffer);
+  console.log(docs6[0]);
+
+  // JSON Lines Format
+  const reader7 = new JSONReader({ isJsonLines: true });
+  const docs7 = await reader7.loadDataAsContent(jsonlBuffer);
+  console.log(docs7[0]);
+}
+
+main().catch(console.error);

examples/readers/src/llamaparse-json.ts

@@ -3,6 +3,7 @@ import {
   ImageNode,
   LlamaParseReader,
   OpenAI,
+  PromptTemplate,
   VectorStoreIndex,
 } from "llamaindex";
 import { createMessageContent } from "llamaindex/synthesizers/utils";
@@ -50,7 +51,9 @@ async function getImageTextDocs(
 
   for (const imageDict of imageDicts) {
     const imageDoc = new ImageNode({ image: imageDict.path });
-    const prompt = () => `Describe the image as alt text`;
+    const prompt = new PromptTemplate({
+      template: `Describe the image as alt text`,
+    });
     const message = await createMessageContent(prompt, [imageDoc]);
 
     const response = await llm.complete({

examples/rerankers/CohereReranker.ts

@@ -15,9 +15,9 @@ async function main() {
 
   const index = await VectorStoreIndex.fromDocuments([document]);
 
-  const retriever = index.asRetriever();
-
-  retriever.similarityTopK = 5;
+  const retriever = index.asRetriever({
+    similarityTopK: 5,
+  });
 
   const nodePostprocessor = new CohereRerank({
     apiKey: "<COHERE_API_KEY>",

examples/routerQueryEngine.ts

@@ -1,9 +1,9 @@
 import {
   OpenAI,
   RouterQueryEngine,
+  SentenceSplitter,
   Settings,
   SimpleDirectoryReader,
-  SimpleNodeParser,
   SummaryIndex,
   VectorStoreIndex,
 } from "llamaindex";
@@ -12,7 +12,7 @@ import {
 Settings.llm = new OpenAI();
 
 // Update node parser
-Settings.nodeParser = new SimpleNodeParser({
+Settings.nodeParser = new SentenceSplitter({
   chunkSize: 1024,
 });
 

examples/split.ts

@@ -8,7 +8,7 @@ async function main() {
 
   const textSplitter = new SentenceSplitter();
 
-  const chunks = textSplitter.splitTextWithOverlaps(essay);
+  const chunks = textSplitter.splitText(essay);
 
   console.log(chunks);
 }

examples/summaryIndex.ts

@@ -1,7 +1,7 @@
 import {
   Document,
+  SentenceSplitter,
   Settings,
-  SimpleNodeParser,
   SummaryIndex,
   SummaryRetrieverMode,
 } from "llamaindex";
@@ -9,7 +9,7 @@ import {
 import essay from "./essay";
 
 // Update node parser
-Settings.nodeParser = new SimpleNodeParser({
+Settings.nodeParser = new SentenceSplitter({
   chunkSize: 40,
 });
 

examples/tsconfig.json

@@ -7,8 +7,6 @@
     "forceConsistentCasingInFileNames": true,
     "strict": true,
     "skipLibCheck": true,
-    "lib": ["ES2022"],
-    "types": ["node"],
     "outDir": "./lib",
     "tsBuildInfoFile": "./lib/.tsbuildinfo",
     "incremental": true,

examples/vectorIndexCustomize.ts

@@ -18,8 +18,9 @@ async function main() {
 
   const index = await VectorStoreIndex.fromDocuments([document]);
 
-  const retriever = index.asRetriever();
-  retriever.similarityTopK = 5;
+  const retriever = index.asRetriever({
+    similarityTopK: 5,
+  });
   const nodePostprocessor = new SimilarityPostprocessor({
     similarityCutoff: 0.7,
   });

examples/weaviate/README.md

@@ -0,0 +1,31 @@
+# Weaviate Vector Store
+
+Here are two sample scripts which work with loading and querying data from a Weaviate Vector Store.
+
+## Prerequisites
+
+- An Weaviate Vector Database
+  - Hosted https://weaviate.io/
+  - Self Hosted https://weaviate.io/developers/weaviate/installation/docker-compose#starter-docker-compose-file
+- An OpenAI API Key
+
+## Setup
+
+1. Set your env variables:
+
+- `WEAVIATE_CLUSTER_URL`: Address of your Weaviate Vector Store (like localhost:8080)
+- `WEAVIATE_API_KEY`: Your Weaviate API key
+- `OPENAI_API_KEY`: Your OpenAI key
+
+2. `cd` Into the `examples` directory
+3. run `npm i`
+
+## Load the data
+
+This sample loads the same dataset of movie reviews as sample dataset
+
+run `npx tsx weaviate/load`
+
+## Use RAG to Query the data
+
+run `npx tsx weaviate/query`

examples/weaviate/load.ts

@@ -0,0 +1,23 @@
+import {
+  PapaCSVReader,
+  storageContextFromDefaults,
+  VectorStoreIndex,
+  WeaviateVectorStore,
+} from "llamaindex";
+
+const indexName = "MovieReviews";
+
+async function main() {
+  try {
+    const reader = new PapaCSVReader(false);
+    const docs = await reader.loadData("./data/movie_reviews.csv");
+    const vectorStore = new WeaviateVectorStore({ indexName });
+    const storageContext = await storageContextFromDefaults({ vectorStore });
+    await VectorStoreIndex.fromDocuments(docs, { storageContext });
+    console.log("Successfully loaded data into Weaviate");
+  } catch (e) {
+    console.error(e);
+  }
+}
+
+void main();

examples/weaviate/query.ts

@@ -0,0 +1,46 @@
+import { VectorStoreIndex, WeaviateVectorStore } from "llamaindex";
+
+const indexName = "MovieReviews";
+
+async function main() {
+  try {
+    const query = "Get all movie titles.";
+    const vectorStore = new WeaviateVectorStore({ indexName });
+    const index = await VectorStoreIndex.fromVectorStore(vectorStore);
+    const retriever = index.asRetriever({ similarityTopK: 20 });
+
+    const queryEngine = index.asQueryEngine({ retriever });
+    const results = await queryEngine.query({ query });
+    console.log(`Query from ${results.sourceNodes?.length} nodes`);
+    console.log(results.response);
+
+    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_21",
+            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();

package.json

@@ -19,26 +19,28 @@
   },
   "devDependencies": {
     "@changesets/cli": "^2.27.5",
-    "@typescript-eslint/eslint-plugin": "^7.13.1",
-    "eslint": "^8.57.0",
-    "eslint-config-next": "^14.2.4",
+    "@typescript-eslint/eslint-plugin": "^8.3.0",
+    "eslint": "8.57.0",
+    "eslint-config-next": "^14.2.7",
     "eslint-config-prettier": "^9.1.0",
-    "eslint-config-turbo": "^2.0.5",
-    "eslint-plugin-react": "7.34.1",
-    "husky": "^9.0.11",
-    "lint-staged": "^15.2.7",
-    "madge": "^7.0.0",
-    "prettier": "^3.3.2",
-    "prettier-plugin-organize-imports": "^3.2.4",
-    "turbo": "^2.0.5",
-    "typescript": "^5.5.2"
+    "eslint-config-turbo": "^2.1.0",
+    "eslint-plugin-react": "7.35.0",
+    "husky": "^9.1.5",
+    "lint-staged": "^15.2.9",
+    "madge": "^8.0.0",
+    "prettier": "^3.3.3",
+    "prettier-plugin-organize-imports": "^4.0.0",
+    "turbo": "^2.1.0",
+    "typescript": "^5.5.4"
   },
-  "packageManager": "pnpm@9.4.0",
+  "packageManager": "pnpm@9.5.0",
   "pnpm": {
     "overrides": {
       "trim": "1.0.1",
-      "@babel/traverse": "7.23.2",
       "protobufjs": "7.2.6"
+    },
+    "patchedDependencies": {
+      "python-format-js@1.4.3": "patches/python-format-js@1.4.3.patch"
     }
   },
   "lint-staged": {

packages/autotool/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/autotool
 
+## 2.0.1
+
+### Patch Changes
+
+- 58abc57: fix: align version
+- Updated dependencies [58abc57]
+  - llamaindex@0.5.16
+
 ## 2.0.0
 
 ### Patch Changes

packages/autotool/examples/01_node/CHANGELOG.md

@@ -1,5 +1,67 @@
 # @llamaindex/autotool-01-node-example
 
+## 0.0.8
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+  - @llamaindex/autotool@2.0.1
+
+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+  - @llamaindex/autotool@2.0.1
+
+## 0.0.6
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+  - @llamaindex/autotool@2.0.1
+
+## 0.0.5
+
+### Patch Changes
+
+- llamaindex@0.5.24
+- @llamaindex/autotool@2.0.1
+
+## 0.0.4
+
+### Patch Changes
+
+- llamaindex@0.5.23
+- @llamaindex/autotool@2.0.1
+
+## 0.0.3
+
+### Patch Changes
+
+- Updated dependencies [4648da6]
+  - llamaindex@0.5.22
+  - @llamaindex/autotool@2.0.1
+
+## 0.0.2
+
+### 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
+  - @llamaindex/autotool@2.0.1
+
 ## null
 
 ### Patch Changes

packages/autotool/examples/01_node/package.json

@@ -5,13 +5,13 @@
   "dependencies": {
     "@llamaindex/autotool": "workspace:*",
     "llamaindex": "workspace:*",
-    "openai": "^4.52.0"
+    "openai": "^4.57.0"
   },
   "devDependencies": {
-    "tsx": "^4.15.6"
+    "tsx": "^4.19.0"
   },
   "scripts": {
     "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
   },
-  "version": null
+  "version": "0.0.8"
 }

packages/autotool/examples/01_node/src/index.ts

@@ -16,7 +16,7 @@ const openai = new OpenAI();
     stream: false,
   });
 
-  const toolCalls = response.choices[0].message.tool_calls ?? [];
+  const toolCalls = response.choices[0]!.message.tool_calls ?? [];
   for (const toolCall of toolCalls) {
     toolCall.function.name;
   }

packages/autotool/examples/02_nextjs/CHANGELOG.md

@@ -1,5 +1,224 @@
 # @llamaindex/autotool-02-next-example
 
+## 0.1.52
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.51
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.50
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.49
+
+### Patch Changes
+
+- llamaindex@0.5.24
+- @llamaindex/autotool@2.0.1
+
+## 0.1.48
+
+### Patch Changes
+
+- llamaindex@0.5.23
+- @llamaindex/autotool@2.0.1
+
+## 0.1.47
+
+### Patch Changes
+
+- Updated dependencies [4648da6]
+  - llamaindex@0.5.22
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.46
+
+### 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
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.45
+
+### Patch Changes
+
+- Updated dependencies [d9d6c56]
+- Updated dependencies [22ff486]
+- Updated dependencies [eed0b04]
+  - llamaindex@0.5.20
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.44
+
+### Patch Changes
+
+- Updated dependencies [fcbf183]
+  - llamaindex@0.5.19
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.43
+
+### Patch Changes
+
+- Updated dependencies [8b66cf4]
+  - llamaindex@0.5.18
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.42
+
+### Patch Changes
+
+- Updated dependencies [c654398]
+  - llamaindex@0.5.17
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.41
+
+### Patch Changes
+
+- Updated dependencies [58abc57]
+  - @llamaindex/autotool@2.0.1
+  - llamaindex@0.5.16
+
+## 0.1.40
+
+### Patch Changes
+
+- Updated dependencies [01c184c]
+- Updated dependencies [07a275f]
+  - llamaindex@0.5.15
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.39
+
+### Patch Changes
+
+- Updated dependencies [c825a2f]
+  - llamaindex@0.5.14
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.38
+
+### Patch Changes
+
+- llamaindex@0.5.13
+- @llamaindex/autotool@2.0.0
+
+## 0.1.37
+
+### Patch Changes
+
+- Updated dependencies [345300f]
+- Updated dependencies [da5cfc4]
+- Updated dependencies [da5cfc4]
+  - llamaindex@0.5.12
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.36
+
+### Patch Changes
+
+- llamaindex@0.5.11
+- @llamaindex/autotool@2.0.0
+
+## 0.1.35
+
+### Patch Changes
+
+- Updated dependencies [086b940]
+- Updated dependencies [5d5716b]
+- Updated dependencies [91d02a4]
+- Updated dependencies [fb6db45]
+  - llamaindex@0.5.10
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.34
+
+### Patch Changes
+
+- Updated dependencies [15962b3]
+  - llamaindex@0.5.9
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.33
+
+### Patch Changes
+
+- Updated dependencies [3d5ba08]
+- Updated dependencies [d917cdc]
+  - llamaindex@0.5.8
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.32
+
+### Patch Changes
+
+- Updated dependencies [ec59acd]
+  - llamaindex@0.5.7
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.31
+
+### Patch Changes
+
+- Updated dependencies [2562244]
+- Updated dependencies [325aa51]
+- Updated dependencies [ab700ea]
+- Updated dependencies [92f0782]
+- Updated dependencies [6cf6ae6]
+- Updated dependencies [b7cfe5b]
+  - llamaindex@0.5.6
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.30
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - llamaindex@0.5.5
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.29
+
+### Patch Changes
+
+- Updated dependencies [1a65ead]
+  - llamaindex@0.5.4
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.28
+
+### Patch Changes
+
+- Updated dependencies [9bbbc67]
+- Updated dependencies [b3681bf]
+  - llamaindex@0.5.3
+  - @llamaindex/autotool@2.0.0
+
 ## 0.1.27
 
 ### Patch Changes

packages/autotool/examples/02_nextjs/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool-02-next-example",
   "private": true,
-  "version": "0.1.27",
+  "version": "0.1.52",
   "scripts": {
     "dev": "next dev",
     "build": "next build",
@@ -10,28 +10,28 @@
   "dependencies": {
     "@llamaindex/autotool": "workspace:*",
     "@radix-ui/react-slot": "^1.1.0",
-    "ai": "^3.2.1",
+    "ai": "^3.3.21",
     "class-variance-authority": "^0.7.0",
     "dotenv": "^16.3.1",
     "llamaindex": "workspace:*",
-    "lucide-react": "^0.378.0",
+    "lucide-react": "^0.436.0",
     "next": "14.3.0-canary.51",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-markdown": "^9.0.1",
     "react-syntax-highlighter": "^15.5.0",
     "sonner": "^1.5.0",
-    "tailwind-merge": "^2.1.0"
+    "tailwind-merge": "^2.5.2"
   },
   "devDependencies": {
-    "@types/node": "^20.12.11",
-    "@types/react": "^18.3.3",
+    "@types/node": "^22.5.1",
+    "@types/react": "^18.3.5",
     "@types/react-dom": "^18.3.0",
     "@types/react-syntax-highlighter": "^15.5.11",
-    "autoprefixer": "^10.4.16",
+    "autoprefixer": "^10.4.20",
     "cross-env": "^7.0.3",
-    "postcss": "^8.4.32",
-    "tailwindcss": "^3.4.4",
-    "typescript": "^5.5.2"
+    "postcss": "^8.4.41",
+    "tailwindcss": "^3.4.10",
+    "typescript": "^5.5.4"
   }
 }

packages/autotool/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool",
   "type": "module",
-  "version": "2.0.0",
+  "version": "2.0.1",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",
@@ -45,13 +45,13 @@
     "dev": "bunchee --watch"
   },
   "dependencies": {
-    "@swc/core": "^1.6.3",
-    "jotai": "^2.8.3",
-    "typedoc": "^0.25.13",
-    "unplugin": "^1.10.1"
+    "@swc/core": "^1.7.22",
+    "jotai": "2.8.4",
+    "typedoc": "^0.26.6",
+    "unplugin": "^1.12.2"
   },
   "peerDependencies": {
-    "llamaindex": "^0.5.2",
+    "llamaindex": "^0.5.27",
     "openai": "^4",
     "typescript": "^4"
   },
@@ -67,16 +67,16 @@
     }
   },
   "devDependencies": {
-    "@swc/types": "^0.1.8",
+    "@swc/types": "^0.1.12",
     "@types/json-schema": "^7.0.15",
-    "@types/node": "^20.12.11",
-    "bunchee": "5.3.0-beta.0",
+    "@types/node": "^22.5.1",
+    "bunchee": "5.3.2",
     "llamaindex": "workspace:*",
-    "next": "14.2.3",
-    "rollup": "^4.18.0",
-    "tsx": "^4.15.6",
-    "typescript": "^5.5.2",
-    "vitest": "^1.6.0",
-    "webpack": "^5.92.1"
+    "next": "14.2.7",
+    "rollup": "^4.21.2",
+    "tsx": "^4.19.0",
+    "typescript": "^5.5.4",
+    "vitest": "^2.0.5",
+    "webpack": "^5.94.0"
   }
 }

packages/autotool/src/index.ts

@@ -16,11 +16,16 @@ const openaiToolsAtom = atom<ChatCompletionTool[]>((get) => {
   const metadata = get(toolMetadataAtom);
   return metadata.map(([metadata]) => ({
     type: "function",
-    function: {
-      parameters: metadata.parameters,
-      name: metadata.name,
-      description: metadata.description,
-    },
+    function: metadata.parameters
+      ? {
+          parameters: metadata.parameters,
+          name: metadata.name,
+          description: metadata.description,
+        }
+      : {
+          name: metadata.name,
+          description: metadata.description,
+        },
   }));
 });
 

packages/autotool/src/internal/index.ts

@@ -17,7 +17,7 @@ export type Info = {
  * @internal
  */
 export type InfoString = {
-  originalFunction?: string;
+  originalFunction: string | undefined;
   parameterMapping: Record<string, number>;
 };
 

packages/cloud/CHANGELOG.md

@@ -1,5 +1,29 @@
 # @llamaindex/cloud
 
+## 0.2.4
+
+### Patch Changes
+
+- 4810364: fix: bump version
+
+## 0.2.3
+
+### Patch Changes
+
+- 0bf8d80: fix: bump version
+
+## 0.2.2
+
+### Patch Changes
+
+- 58abc57: fix: align version
+
+## 0.2.1
+
+### Patch Changes
+
+- 1f680d7: chore: bump llamacloud api
+
 ## 0.2.0
 
 ### Minor Changes

packages/cloud/openapi-ts.config.ts

@@ -4,6 +4,7 @@ export default defineConfig({
   // you can download this file to get the latest version of the OpenAPI document
   // @link https://api.cloud.llamaindex.ai/api/openapi.json
   input: "./openapi.json",
+  client: "@hey-api/client-fetch",
   output: {
     path: "./src/client",
     format: "prettier",

packages/cloud/package.json

@@ -1,10 +1,10 @@
 {
   "name": "@llamaindex/cloud",
-  "version": "0.2.0",
+  "version": "0.2.4",
   "type": "module",
   "license": "MIT",
   "scripts": {
-    "generate": "pnpm dlx @hey-api/openapi-ts",
+    "generate": "pnpx @hey-api/openapi-ts@0.53.0",
     "build": "pnpm run generate && bunchee"
   },
   "files": [
@@ -34,7 +34,8 @@
     "directory": "packages/cloud"
   },
   "devDependencies": {
-    "@hey-api/openapi-ts": "^0.48.0",
-    "bunchee": "5.3.0-beta.0"
+    "@hey-api/client-fetch": "^0.2.4",
+    "@hey-api/openapi-ts": "^0.53.0",
+    "bunchee": "5.3.2"
   }
 }

packages/community/CHANGELOG.md

@@ -1,5 +1,100 @@
 # @llamaindex/community
 
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [711c814]
+  - @llamaindex/core@0.1.12
+
+## 0.0.32
+
+### Patch Changes
+
+- Updated dependencies [4648da6]
+  - @llamaindex/env@0.1.10
+  - @llamaindex/core@0.1.11
+
+## 0.0.31
+
+### Patch Changes
+
+- Updated dependencies [0148354]
+  - @llamaindex/core@0.1.10
+
+## 0.0.30
+
+### Patch Changes
+
+- Updated dependencies [e27e7dd]
+  - @llamaindex/core@0.1.9
+
+## 0.0.29
+
+### Patch Changes
+
+- 58abc57: fix: align version
+- Updated dependencies [58abc57]
+  - @llamaindex/core@0.1.8
+  - @llamaindex/env@0.1.9
+
+## 0.0.28
+
+### Patch Changes
+
+- Updated dependencies [04b2f8e]
+  - @llamaindex/core@0.1.7
+
+## 0.0.27
+
+### Patch Changes
+
+- Updated dependencies [0452af9]
+  - @llamaindex/core@0.1.6
+
+## 0.0.26
+
+### Patch Changes
+
+- 224d507: fix: prevent tool calling getting mixed with conversation
+- 376d29a: feat: added tool calling and agent support for llama3.1 504B
+
+## 0.0.25
+
+### Patch Changes
+
+- Updated dependencies [91d02a4]
+  - @llamaindex/core@0.1.5
+
+## 0.0.24
+
+### Patch Changes
+
+- 3d9a802: feat: added llama 3.1
+- Updated dependencies [15962b3]
+  - @llamaindex/core@0.1.4
+
+## 0.0.23
+
+### Patch Changes
+
+- Updated dependencies [6cf6ae6]
+  - @llamaindex/core@0.1.3
+
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - @llamaindex/core@0.1.2
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [b3681bf]
+  - @llamaindex/core@0.1.1
+
 ## 0.0.20
 
 ### Patch Changes

packages/community/README.md

@@ -5,7 +5,8 @@
 ## Current Features:
 
 - Bedrock support for the Anthropic Claude Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock)
-- Bedrock support for the Meta LLama 2 and 3 Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock)
+- Bedrock support for the Meta LLama 2, 3 and 3.1 Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock)
+- Meta LLama3.1 405b tool call support
 
 ## LICENSE
 

packages/community/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.20",
+  "version": "0.0.33",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",
@@ -19,11 +19,11 @@
     "./llm/bedrock": {
       "import": {
         "types": "./dist/type/llm/bedrock.d.ts",
-        "default": "./dist/llm/bedrock/base.js"
+        "default": "./dist/llm/bedrock/index.js"
       },
       "require": {
         "types": "./dist/type/llm/bedrock.d.ts",
-        "default": "./dist/llm/bedrock/base.cjs"
+        "default": "./dist/llm/bedrock/index.cjs"
       }
     }
   },
@@ -42,11 +42,12 @@
     "dev": "bunchee --watch"
   },
   "devDependencies": {
-    "@types/node": "^20.14.2",
-    "bunchee": "5.3.0-beta.0"
+    "@types/node": "^22.5.1",
+    "bunchee": "5.3.2"
   },
   "dependencies": {
-    "@aws-sdk/client-bedrock-runtime": "^3.600.0",
-    "@llamaindex/core": "workspace:*"
+    "@aws-sdk/client-bedrock-runtime": "^3.642.0",
+    "@llamaindex/core": "workspace:*",
+    "@llamaindex/env": "workspace:*"
   }
 }

packages/community/src/index.ts

@@ -2,4 +2,4 @@ export {
   BEDROCK_MODELS,
   BEDROCK_MODEL_MAX_TOKENS,
   Bedrock,
-} from "./llm/bedrock/base.js";
+} from "./llm/bedrock/index.js";

packages/community/src/llm/bedrock/anthropic/provider.ts

@@ -16,17 +16,18 @@ import {
   type BedrockChatStreamResponse,
   Provider,
 } from "../provider";
+import { toUtf8 } from "../utils";
 import type {
   AnthropicNoneStreamingResponse,
   AnthropicStreamEvent,
   AnthropicTextContent,
   ToolBlock,
-} from "../types";
+} from "./types";
+
 import {
   mapBaseToolsToAnthropicTools,
   mapChatMessagesToAnthropicMessages,
-  toUtf8,
-} from "../utils";
+} from "./utils";
 
 export class AnthropicProvider extends Provider<AnthropicStreamEvent> {
   getResultFromResponse(
@@ -69,6 +70,7 @@ export class AnthropicProvider extends Provider<AnthropicStreamEvent> {
     let tool: ToolBlock | undefined = undefined;
     // #TODO this should be broken down into a separate consumer
     for await (const response of stream) {
+      const delta = this.getTextFromStreamResponse(response);
       const event = this.getStreamingEventResponse(response);
       if (
         event?.type === "content_block_start" &&
@@ -114,11 +116,10 @@ export class AnthropicProvider extends Provider<AnthropicStreamEvent> {
           };
         }
       }
-      const delta = this.getTextFromStreamResponse(response);
       if (!delta && !options) continue;
 
       yield {
-        delta,
+        delta: options ? "" : delta,
         options,
         raw: response,
       };

packages/community/src/llm/bedrock/anthropic/types.ts

@@ -0,0 +1,142 @@
+import type { ToolMetadata } from "@llamaindex/core/llms";
+import type { InvocationMetrics } from "../types";
+
+type Usage = {
+  input_tokens: number;
+  output_tokens: number;
+};
+
+type Message = {
+  id: string;
+  type: string;
+  role: string;
+  content: string[];
+  model: string;
+  stop_reason: string | null;
+  stop_sequence: string | null;
+  usage: Usage;
+};
+
+export type ToolBlock = {
+  id: string;
+  input: unknown;
+  name: string;
+  type: "tool_use";
+};
+
+export type TextBlock = {
+  type: "text";
+  text: string;
+};
+
+type ContentBlockStart = {
+  type: "content_block_start";
+  index: number;
+  content_block: ToolBlock | TextBlock;
+};
+
+type Delta =
+  | {
+      type: "text_delta";
+      text: string;
+    }
+  | {
+      type: "input_json_delta";
+      partial_json: string;
+    };
+
+type ContentBlockDelta = {
+  type: "content_block_delta";
+  index: number;
+  delta: Delta;
+};
+
+type ContentBlockStop = {
+  type: "content_block_stop";
+  index: number;
+};
+
+type MessageDelta = {
+  type: "message_delta";
+  delta: {
+    stop_reason: string;
+    stop_sequence: string | null;
+  };
+  usage: Usage;
+};
+
+export type MessageStop = {
+  type: "message_stop";
+  "amazon-bedrock-invocationMetrics": InvocationMetrics;
+};
+
+export type AnthropicStreamEvent =
+  | { type: "message_start"; message: Message }
+  | ContentBlockStart
+  | ContentBlockDelta
+  | ContentBlockStop
+  | MessageDelta
+  | MessageStop;
+
+export type AnthropicContent =
+  | AnthropicTextContent
+  | AnthropicImageContent
+  | AnthropicToolContent
+  | AnthropicToolResultContent;
+
+export type AnthropicTextContent = {
+  type: "text";
+  text: string;
+};
+
+export type AnthropicToolContent = {
+  type: "tool_use";
+  id: string;
+  name: string;
+  input: Record<string, unknown>;
+};
+
+export type AnthropicToolResultContent = {
+  type: "tool_result";
+  tool_use_id: string;
+  content: string;
+};
+
+export type AnthropicMediaTypes =
+  | "image/jpeg"
+  | "image/png"
+  | "image/webp"
+  | "image/gif";
+
+export type AnthropicImageSource = {
+  type: "base64";
+  media_type: AnthropicMediaTypes;
+  data: string; // base64 encoded image bytes
+};
+
+export type AnthropicImageContent = {
+  type: "image";
+  source: AnthropicImageSource;
+};
+
+export type AnthropicMessage = {
+  role: "user" | "assistant";
+  content: AnthropicContent[];
+};
+
+export type AnthropicNoneStreamingResponse = {
+  id: string;
+  type: "message";
+  role: "assistant";
+  content: AnthropicContent[];
+  model: string;
+  stop_reason: "end_turn" | "max_tokens" | "stop_sequence";
+  stop_sequence?: string;
+  usage: { input_tokens: number; output_tokens: number };
+};
+
+export type AnthropicTool = {
+  name: string;
+  description: string;
+  input_schema: ToolMetadata["parameters"];
+};

packages/community/src/llm/bedrock/anthropic/utils.ts

@@ -0,0 +1,186 @@
+import type { JSONObject } from "@llamaindex/core/global";
+import type {
+  BaseTool,
+  ChatMessage,
+  MessageContent,
+  MessageContentDetail,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import { mapMessageContentToMessageContentDetails } from "../utils";
+import type {
+  AnthropicContent,
+  AnthropicImageContent,
+  AnthropicMediaTypes,
+  AnthropicMessage,
+  AnthropicTextContent,
+  AnthropicTool,
+} from "./types.js";
+
+const ACCEPTED_IMAGE_MIME_TYPES = [
+  "image/jpeg",
+  "image/png",
+  "image/webp",
+  "image/gif",
+];
+
+export const mergeNeighboringSameRoleMessages = (
+  messages: AnthropicMessage[],
+): AnthropicMessage[] => {
+  return messages.reduce(
+    (result: AnthropicMessage[], current: AnthropicMessage, index: number) => {
+      if (index > 0 && messages[index - 1]!.role === current.role) {
+        result[result.length - 1]!.content = [
+          ...result[result.length - 1]!.content,
+          ...current.content,
+        ];
+      } else {
+        result.push(current);
+      }
+      return result;
+    },
+    [],
+  );
+};
+
+export const mapMessageContentDetailToAnthropicContent = <
+  T extends MessageContentDetail,
+>(
+  detail: T,
+): AnthropicContent => {
+  let content: AnthropicContent;
+
+  if (detail.type === "text") {
+    content = mapTextContent(detail.text);
+  } else if (detail.type === "image_url") {
+    content = mapImageContent(detail.image_url.url);
+  } else {
+    throw new Error("Unsupported content detail type");
+  }
+  return content;
+};
+
+export const mapMessageContentToAnthropicContent = <T extends MessageContent>(
+  content: T,
+): AnthropicContent[] => {
+  return mapMessageContentToMessageContentDetails(content).map(
+    mapMessageContentDetailToAnthropicContent,
+  );
+};
+
+export const mapBaseToolsToAnthropicTools = (
+  tools?: BaseTool[],
+): AnthropicTool[] => {
+  if (!tools) return [];
+  return tools.map((tool: BaseTool) => {
+    const {
+      metadata: { parameters, ...options },
+    } = tool;
+    return {
+      ...options,
+      input_schema: parameters,
+    };
+  });
+};
+
+export const mapChatMessagesToAnthropicMessages = <
+  T extends ChatMessage<ToolCallLLMMessageOptions>,
+>(
+  messages: T[],
+): AnthropicMessage[] => {
+  const mapped = messages
+    .flatMap((msg: T): AnthropicMessage[] => {
+      if (msg.options && "toolCall" in msg.options) {
+        return [
+          {
+            role: "assistant",
+            content: msg.options.toolCall.map((call) => ({
+              type: "tool_use",
+              id: call.id,
+              name: call.name,
+              input: call.input as JSONObject,
+            })),
+          },
+        ];
+      }
+      if (msg.options && "toolResult" in msg.options) {
+        return [
+          {
+            role: "user",
+            content: [
+              {
+                type: "tool_result",
+                tool_use_id: msg.options.toolResult.id,
+                content: msg.options.toolResult.result,
+              },
+            ],
+          },
+        ];
+      }
+      return mapMessageContentToMessageContentDetails(msg.content).map(
+        (detail: MessageContentDetail): AnthropicMessage => {
+          const content = mapMessageContentDetailToAnthropicContent(detail);
+
+          return {
+            role: msg.role === "assistant" ? "assistant" : "user",
+            content: [content],
+          };
+        },
+      );
+    })
+    .filter((message: AnthropicMessage) => {
+      const content = message.content[0]!;
+      if (content.type === "text" && !content.text) return false;
+      if (content.type === "image" && !content.source.data) return false;
+      if (content.type === "image" && message.role === "assistant")
+        return false;
+      return true;
+    });
+
+  return mergeNeighboringSameRoleMessages(mapped);
+};
+
+export const mapTextContent = (text: string): AnthropicTextContent => {
+  return { type: "text", text };
+};
+
+export const extractDataUrlComponents = (
+  dataUrl: string,
+): {
+  mimeType: string;
+  base64: string;
+} => {
+  const parts = dataUrl.split(";base64,");
+
+  if (parts.length !== 2 || !parts[0]!.startsWith("data:")) {
+    throw new Error("Invalid data URL");
+  }
+
+  const mimeType = parts[0]!.slice(5);
+  const base64 = parts[1]!;
+
+  return {
+    mimeType,
+    base64,
+  };
+};
+
+export const mapImageContent = (imageUrl: string): AnthropicImageContent => {
+  if (!imageUrl.startsWith("data:"))
+    throw new Error(
+      "For Anthropic please only use base64 data url, e.g.: data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==",
+    );
+  const { mimeType, base64: data } = extractDataUrlComponents(imageUrl);
+  if (!ACCEPTED_IMAGE_MIME_TYPES.includes(mimeType))
+    throw new Error(
+      `Anthropic only accepts the following mimeTypes: ${ACCEPTED_IMAGE_MIME_TYPES.join("\n")}`,
+    );
+
+  return {
+    type: "image",
+    source: {
+      type: "base64",
+      media_type: mimeType as AnthropicMediaTypes,
+      data,
+    },
+  };
+};

packages/community/src/llm/bedrock/index.ts

@@ -22,8 +22,16 @@ import {
   type BedrockChatStreamResponse,
   Provider,
 } from "./provider";
-import { PROVIDERS } from "./providers";
-import { mapMessageContentToMessageContentDetails } from "./utils.js";
+import { mapMessageContentToMessageContentDetails } from "./utils";
+
+import { AnthropicProvider } from "./anthropic/provider";
+import { MetaProvider } from "./meta/provider";
+
+// Other providers should go here
+export const PROVIDERS: { [key: string]: Provider } = {
+  anthropic: new AnthropicProvider(),
+  meta: new MetaProvider(),
+};
 
 export type BedrockChatParamsStreaming = LLMChatParamsStreaming<
   BedrockAdditionalChatOptions,
@@ -60,6 +68,9 @@ export enum BEDROCK_MODELS {
   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",
+  META_LLAMA3_1_70B_INSTRUCT = "meta.llama3-1-70b-instruct-v1:0",
+  META_LLAMA3_1_405B_INSTRUCT = "meta.llama3-1-405b-instruct-v1:0",
   MISTRAL_7B_INSTRUCT = "mistral.mistral-7b-instruct-v0:2",
   MISTRAL_MIXTRAL_7B_INSTRUCT = "mistral.mixtral-8x7b-instruct-v0:1",
   MISTRAL_MIXTRAL_LARGE_2402 = "mistral.mistral-large-2402-v1:0",
@@ -94,6 +105,9 @@ const CHAT_ONLY_MODELS = {
   [BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 4096,
   [BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 8192,
   [BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT]: 8192,
+  [BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT]: 128000,
+  [BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT]: 128000,
+  [BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT]: 128000,
   [BEDROCK_MODELS.MISTRAL_7B_INSTRUCT]: 32000,
   [BEDROCK_MODELS.MISTRAL_MIXTRAL_7B_INSTRUCT]: 32000,
   [BEDROCK_MODELS.MISTRAL_MIXTRAL_LARGE_2402]: 32000,
@@ -121,6 +135,9 @@ export const STREAMING_MODELS = new Set([
   BEDROCK_MODELS.META_LLAMA2_70B_CHAT,
   BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT,
   BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
   BEDROCK_MODELS.MISTRAL_7B_INSTRUCT,
   BEDROCK_MODELS.MISTRAL_MIXTRAL_7B_INSTRUCT,
   BEDROCK_MODELS.MISTRAL_MIXTRAL_LARGE_2402,
@@ -131,16 +148,20 @@ export const TOOL_CALL_MODELS = [
   BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
   BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS,
   BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
+  BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
 ];
 
 const getProvider = (model: string): Provider => {
   const providerName = model.split(".")[0];
+  if (!providerName) {
+    throw new Error(`Model ${model} is not supported`);
+  }
   if (!(providerName in PROVIDERS)) {
     throw new Error(
       `Provider ${providerName} for model ${model} is not supported`,
     );
   }
-  return PROVIDERS[providerName];
+  return PROVIDERS[providerName]!;
 };
 
 export type BedrockModelParams = {
@@ -160,6 +181,9 @@ export const BEDROCK_MODEL_MAX_TOKENS: Partial<Record<BEDROCK_MODELS, number>> =
     [BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 2048,
     [BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 2048,
     [BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT]: 2048,
   };
 
 const DEFAULT_BEDROCK_PARAMS = {

packages/community/src/llm/bedrock/meta/constants.ts

@@ -0,0 +1,3 @@
+export const TOKENS = {
+  TOOL_CALL: "<|python_tag|>",
+};

packages/community/src/llm/bedrock/meta/provider.ts

@@ -0,0 +1,136 @@
+import type {
+  InvokeModelCommandInput,
+  InvokeModelWithResponseStreamCommandInput,
+  ResponseStream,
+} from "@aws-sdk/client-bedrock-runtime";
+import type {
+  BaseTool,
+  ChatMessage,
+  LLMMetadata,
+  ToolCall,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import { toUtf8 } from "../utils";
+import type { MetaNoneStreamingResponse, MetaStreamEvent } from "./types";
+
+import { randomUUID } from "@llamaindex/env";
+import { Provider, type BedrockChatStreamResponse } from "../provider";
+import { TOKENS } from "./constants";
+import {
+  mapChatMessagesToMetaLlama2Messages,
+  mapChatMessagesToMetaLlama3Messages,
+} from "./utils";
+
+export class MetaProvider extends Provider<MetaStreamEvent> {
+  getResultFromResponse(
+    response: Record<string, any>,
+  ): MetaNoneStreamingResponse {
+    return JSON.parse(toUtf8(response.body));
+  }
+
+  getToolsFromResponse<ToolContent>(
+    response: Record<string, any>,
+  ): ToolContent[] {
+    const result = this.getResultFromResponse(response);
+    if (!result.generation.trim().startsWith(TOKENS.TOOL_CALL)) return [];
+    const tool = JSON.parse(
+      result.generation.trim().split(TOKENS.TOOL_CALL)[1]!,
+    );
+    return [
+      {
+        id: randomUUID(),
+        name: tool.name,
+        input: tool.parameters,
+      } as ToolContent,
+    ];
+  }
+
+  getTextFromResponse(response: Record<string, any>): string {
+    const result = this.getResultFromResponse(response);
+    if (result.generation.trim().startsWith(TOKENS.TOOL_CALL)) return "";
+    return result.generation;
+  }
+
+  getTextFromStreamResponse(response: Record<string, any>): string {
+    const event = this.getStreamingEventResponse(response);
+    if (event?.generation) {
+      return event.generation;
+    }
+    return "";
+  }
+
+  async *reduceStream(
+    stream: AsyncIterable<ResponseStream>,
+  ): BedrockChatStreamResponse {
+    const collecting: string[] = [];
+    let toolId: string | undefined = undefined;
+    for await (const response of stream) {
+      const event = this.getStreamingEventResponse(response);
+      const delta = this.getTextFromStreamResponse(response);
+      // odd quirk of llama3.1, start token is \n\n
+      if (
+        !event?.generation.trim() &&
+        event?.generation_token_count === 1 &&
+        event.prompt_token_count !== null
+      )
+        continue;
+
+      if (delta === TOKENS.TOOL_CALL) {
+        toolId = randomUUID();
+        continue;
+      }
+
+      let options: undefined | ToolCallLLMMessageOptions = undefined;
+      if (toolId && event?.stop_reason === "stop") {
+        const tool = JSON.parse(collecting.join(""));
+        options = {
+          toolCall: [
+            {
+              id: toolId,
+              name: tool.name,
+              input: tool.parameters,
+            } as ToolCall,
+          ],
+        };
+      } else if (toolId && !event?.stop_reason) {
+        collecting.push(delta);
+        continue;
+      }
+
+      if (!delta && !options) continue;
+
+      yield {
+        delta: options ? "" : delta,
+        options,
+        raw: response,
+      };
+    }
+  }
+
+  getRequestBody<T extends ChatMessage>(
+    metadata: LLMMetadata,
+    messages: T[],
+    tools?: BaseTool[],
+  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
+    let prompt: string = "";
+    if (metadata.model.startsWith("meta.llama3")) {
+      prompt = mapChatMessagesToMetaLlama3Messages(messages, tools);
+    } else if (metadata.model.startsWith("meta.llama2")) {
+      prompt = mapChatMessagesToMetaLlama2Messages(messages);
+    } else {
+      throw new Error(`Meta model ${metadata.model} is not supported`);
+    }
+
+    return {
+      modelId: metadata.model,
+      contentType: "application/json",
+      accept: "application/json",
+      body: JSON.stringify({
+        prompt,
+        max_gen_len: metadata.maxTokens,
+        temperature: metadata.temperature,
+        top_p: metadata.topP,
+      }),
+    };
+  }
+}

packages/community/src/llm/bedrock/meta/types.ts

@@ -0,0 +1,21 @@
+import type { InvocationMetrics } from "../types";
+
+export type MetaTextContent = string;
+
+export type MetaMessage = {
+  role: "user" | "assistant" | "system" | "ipython";
+  content: MetaTextContent;
+};
+
+type MetaResponse = {
+  generation: string;
+  prompt_token_count: number;
+  generation_token_count: number;
+  stop_reason: "stop" | "length";
+};
+
+export type MetaStreamEvent = MetaResponse & {
+  "amazon-bedrock-invocationMetrics": InvocationMetrics;
+};
+
+export type MetaNoneStreamingResponse = MetaResponse;

packages/community/src/llm/bedrock/meta/utils.ts

@@ -0,0 +1,198 @@
+import type {
+  BaseTool,
+  ChatMessage,
+  MessageContentTextDetail,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import type { MetaMessage } from "./types";
+
+const getToolCallInstructionString = (tool: BaseTool): string => {
+  return `Use the function '${tool.metadata.name}' to '${tool.metadata.description}'`;
+};
+
+const getToolCallParametersString = (tool: BaseTool): string => {
+  return JSON.stringify({
+    name: tool.metadata.name,
+    description: tool.metadata.description,
+    parameters: tool.metadata.parameters
+      ? Object.entries(tool.metadata.parameters.properties).map(
+          ([name, definition]) => ({ [name]: definition }),
+        )
+      : {},
+  });
+};
+
+// ported from https://github.com/meta-llama/llama-agentic-system/blob/main/llama_agentic_system/system_prompt.py
+// NOTE: using json instead of the above xml style tool calling works more reliability
+export const getToolsPrompt = (tools?: BaseTool[]) => {
+  if (!tools?.length) return "";
+
+  const customToolParams = tools.map((tool) => {
+    return [
+      getToolCallInstructionString(tool),
+      getToolCallParametersString(tool),
+    ].join("\n\n");
+  });
+
+  return `
+Environment: node
+
+# Tool Instructions
+- Never use ipython, always use javascript in node
+
+Cutting Knowledge Date: December 2023
+Today Date: ${new Date().toLocaleString("en-US", { year: "numeric", month: "long" })} 
+
+You have access to the following functions:
+
+${customToolParams}
+
+Think very carefully before calling functions.
+
+If a you choose to call a function ONLY reply in the following json format:
+{
+  "name": function_name,
+  "parameters": parameters,
+}
+where
+
+{
+  "name": function_name,
+  "parameters": parameters, => a JSON dict with the function argument name as key and function argument value as value.
+}
+
+Here is an example,
+
+{
+  "name": "example_function_name",
+  "parameters": {"example_name": "example_value"}
+}
+
+Reminder:
+- Function calls MUST follow the specified format
+- Required parameters MUST be specified
+- Only call one function at a time
+- Put the entire function call reply on one line
+- Always add your sources when using search results to answer the user query
+  `;
+};
+
+export const mapChatRoleToMetaRole = (
+  role: ChatMessage["role"],
+): MetaMessage["role"] => {
+  if (role === "assistant") return "assistant";
+  if (role === "user") return "user";
+  return "system";
+};
+
+export const mapChatMessagesToMetaMessages = <
+  T extends ChatMessage<ToolCallLLMMessageOptions>,
+>(
+  messages: T[],
+): MetaMessage[] => {
+  return messages.flatMap((msg) => {
+    if (msg.options && "toolCall" in msg.options) {
+      return msg.options.toolCall.map((call) => ({
+        role: "assistant",
+        content: JSON.stringify({
+          id: call.id,
+          name: call.name,
+          parameters: call.input,
+        }),
+      }));
+    }
+
+    if (msg.options && "toolResult" in msg.options) {
+      return {
+        role: "ipython",
+        content: JSON.stringify(msg.options.toolResult),
+      };
+    }
+
+    let content: string = "";
+    if (typeof msg.content === "string") {
+      content = msg.content;
+    } else if (msg.content.length) {
+      content = (msg.content[0] as MessageContentTextDetail).text;
+    }
+    return {
+      role: mapChatRoleToMetaRole(msg.role),
+      content,
+    };
+  });
+};
+
+/**
+ * Documentation at https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3
+ */
+export const mapChatMessagesToMetaLlama3Messages = <T extends ChatMessage>(
+  messages: T[],
+  tools?: BaseTool[],
+): string => {
+  const parts: string[] = [];
+  if (tools?.length) {
+    parts.push(
+      "<|begin_of_text|>",
+      "<|start_header_id|>system<|end_header_id|>",
+      getToolsPrompt(tools),
+      "<|eot_id|>",
+    );
+  }
+
+  const mapped = mapChatMessagesToMetaMessages(messages).map((message) => {
+    return [
+      "<|start_header_id|>",
+      message.role,
+      "<|end_header_id|>",
+      message.content,
+      "<|eot_id|>",
+    ].join("\n");
+  });
+
+  parts.push(
+    "<|begin_of_text|>",
+    ...mapped,
+    "<|start_header_id|>assistant<|end_header_id|>",
+  );
+  return parts.join("\n");
+};
+
+/**
+ * Documentation at https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-2
+ */
+export const mapChatMessagesToMetaLlama2Messages = <T extends ChatMessage>(
+  messages: T[],
+): string => {
+  const mapped = mapChatMessagesToMetaMessages(messages);
+  let output = "<s>";
+  let insideInst = false;
+  let needsStartAgain = false;
+  for (const message of mapped) {
+    if (needsStartAgain) {
+      output += "<s>";
+      needsStartAgain = false;
+    }
+    const text = message.content;
+    if (message.role === "system") {
+      if (!insideInst) {
+        output += "[INST] ";
+        insideInst = true;
+      }
+      output += `<<SYS>>\n${text}\n<</SYS>>\n`;
+    } else if (message.role === "user") {
+      output += text;
+      if (insideInst) {
+        output += " [/INST]";
+        insideInst = false;
+      }
+    } else if (message.role === "assistant") {
+      if (insideInst) {
+        output += " [/INST]";
+        insideInst = false;
+      }
+      output += ` ${text} </s>\n`;
+      needsStartAgain = true;
+    }
+  }
+  return output;
+};

packages/community/src/llm/bedrock/provider.ts

@@ -23,6 +23,7 @@ export type BedrockChatStreamResponse = AsyncIterable<
 export abstract class Provider<ProviderStreamEvent extends {} = {}> {
   abstract getTextFromResponse(response: Record<string, any>): string;
 
+  // Return tool calls from none streaming calls
   abstract getToolsFromResponse<T extends {} = {}>(
     response: Record<string, any>,
   ): T[];

packages/community/src/llm/bedrock/providers/index.ts

@@ -1,9 +0,0 @@
-import { Provider } from "../provider";
-import { AnthropicProvider } from "./anthropic";
-import { MetaProvider } from "./meta";
-
-// Other providers should go here
-export const PROVIDERS: { [key: string]: Provider } = {
-  anthropic: new AnthropicProvider(),
-  meta: new MetaProvider(),
-};

packages/community/src/llm/bedrock/providers/meta.ts

@@ -1,69 +0,0 @@
-import type {
-  InvokeModelCommandInput,
-  InvokeModelWithResponseStreamCommandInput,
-} from "@aws-sdk/client-bedrock-runtime";
-import type { ChatMessage, LLMMetadata } from "@llamaindex/core/llms";
-import type { MetaNoneStreamingResponse, MetaStreamEvent } from "../types";
-import {
-  mapChatMessagesToMetaLlama2Messages,
-  mapChatMessagesToMetaLlama3Messages,
-  toUtf8,
-} from "../utils";
-
-import { Provider } from "../provider";
-
-export class MetaProvider extends Provider<MetaStreamEvent> {
-  constructor() {
-    super();
-  }
-
-  getResultFromResponse(
-    response: Record<string, any>,
-  ): MetaNoneStreamingResponse {
-    return JSON.parse(toUtf8(response.body));
-  }
-
-  getToolsFromResponse(_response: Record<string, any>): never {
-    throw new Error("Not supported by this provider.");
-  }
-
-  getTextFromResponse(response: Record<string, any>): string {
-    const result = this.getResultFromResponse(response);
-    return result.generation;
-  }
-
-  getTextFromStreamResponse(response: Record<string, any>): string {
-    const event = this.getStreamingEventResponse(response);
-    if (event?.generation) {
-      return event.generation;
-    }
-    return "";
-  }
-
-  getRequestBody<T extends ChatMessage>(
-    metadata: LLMMetadata,
-    messages: T[],
-  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
-    let promptFunction: (messages: ChatMessage[]) => string;
-
-    if (metadata.model.startsWith("meta.llama3")) {
-      promptFunction = mapChatMessagesToMetaLlama3Messages;
-    } else if (metadata.model.startsWith("meta.llama2")) {
-      promptFunction = mapChatMessagesToMetaLlama2Messages;
-    } else {
-      throw new Error(`Meta model ${metadata.model} is not supported`);
-    }
-
-    return {
-      modelId: metadata.model,
-      contentType: "application/json",
-      accept: "application/json",
-      body: JSON.stringify({
-        prompt: promptFunction(messages),
-        max_gen_len: metadata.maxTokens,
-        temperature: metadata.temperature,
-        top_p: metadata.topP,
-      }),
-    };
-  }
-}

packages/community/src/llm/bedrock/types.ts

@@ -1,165 +1,11 @@
-type Usage = {
-  input_tokens: number;
-  output_tokens: number;
-};
-
-type Message = {
-  id: string;
-  type: string;
-  role: string;
-  content: string[];
-  model: string;
-  stop_reason: string | null;
-  stop_sequence: string | null;
-  usage: Usage;
-};
-
-export type ToolBlock = {
-  id: string;
-  input: unknown;
-  name: string;
-  type: "tool_use";
-};
-
-export type TextBlock = {
-  type: "text";
-  text: string;
-};
-
-type ContentBlockStart = {
-  type: "content_block_start";
-  index: number;
-  content_block: ToolBlock | TextBlock;
-};
-
-type Delta =
-  | {
-      type: "text_delta";
-      text: string;
-    }
-  | {
-      type: "input_json_delta";
-      partial_json: string;
-    };
-
-type ContentBlockDelta = {
-  type: "content_block_delta";
-  index: number;
-  delta: Delta;
-};
-
-type ContentBlockStop = {
-  type: "content_block_stop";
-  index: number;
-};
-
-type MessageDelta = {
-  type: "message_delta";
-  delta: {
-    stop_reason: string;
-    stop_sequence: string | null;
-  };
-  usage: Usage;
-};
-
-type InvocationMetrics = {
+export type InvocationMetrics = {
   inputTokenCount: number;
   outputTokenCount: number;
   invocationLatency: number;
   firstByteLatency: number;
 };
 
-type MessageStop = {
-  type: "message_stop";
-  "amazon-bedrock-invocationMetrics": InvocationMetrics;
-};
-
 export type ToolChoice =
   | { type: "any" }
   | { type: "auto" }
   | { type: "tool"; name: string };
-
-export type AnthropicStreamEvent =
-  | { type: "message_start"; message: Message }
-  | ContentBlockStart
-  | ContentBlockDelta
-  | ContentBlockStop
-  | MessageDelta
-  | MessageStop;
-
-export type AnthropicContent =
-  | AnthropicTextContent
-  | AnthropicImageContent
-  | AnthropicToolContent
-  | AnthropicToolResultContent;
-
-export type MetaTextContent = string;
-
-export type AnthropicTextContent = {
-  type: "text";
-  text: string;
-};
-
-export type AnthropicToolContent = {
-  type: "tool_use";
-  id: string;
-  name: string;
-  input: Record<string, unknown>;
-};
-
-export type AnthropicToolResultContent = {
-  type: "tool_result";
-  tool_use_id: string;
-  content: string;
-};
-
-export type AnthropicMediaTypes =
-  | "image/jpeg"
-  | "image/png"
-  | "image/webp"
-  | "image/gif";
-
-export type AnthropicImageSource = {
-  type: "base64";
-  media_type: AnthropicMediaTypes;
-  data: string; // base64 encoded image bytes
-};
-
-export type AnthropicImageContent = {
-  type: "image";
-  source: AnthropicImageSource;
-};
-
-export type AnthropicMessage = {
-  role: "user" | "assistant";
-  content: AnthropicContent[];
-};
-
-export type MetaMessage = {
-  role: "user" | "assistant" | "system";
-  content: MetaTextContent;
-};
-
-export type AnthropicNoneStreamingResponse = {
-  id: string;
-  type: "message";
-  role: "assistant";
-  content: AnthropicContent[];
-  model: string;
-  stop_reason: "end_turn" | "max_tokens" | "stop_sequence";
-  stop_sequence?: string;
-  usage: { input_tokens: number; output_tokens: number };
-};
-
-type MetaResponse = {
-  generation: string;
-  prompt_token_count: number;
-  generation_token_count: number;
-  stop_reason: "stop" | "length";
-};
-
-export type MetaStreamEvent = MetaResponse & {
-  "amazon-bedrock-invocationMetrics": InvocationMetrics;
-};
-
-export type MetaNoneStreamingResponse = MetaResponse;