Release 0.8.29 (#1566)

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

.github/workflows/test.yml

@@ -23,7 +23,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        node-version: [20.x, 22.x, 23.x]
+        node-version: [18.x, 20.x, 22.x, 23.x]
     name: E2E on Node.js ${{ matrix.node-version }}
     runs-on: ubuntu-latest
     steps:
@@ -53,7 +53,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        node-version: [20.x, 22.x, 23.x]
+        node-version: [18.x, 20.x, 22.x, 23.x]
     name: Test on Node.js ${{ matrix.node-version }}
     runs-on: ubuntu-latest
     steps:

README.md

@@ -1,12 +1,16 @@
-# LlamaIndex.TS
+<p align="center">
+  <img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" />
+</p>
+<h1 align="center">LlamaIndex.TS</h1>
+<h3 align="center">
+  Data framework for your LLM application.
+</h3>
 
 [![NPM Version](https://img.shields.io/npm/v/llamaindex)](https://www.npmjs.com/package/llamaindex)
 [![NPM License](https://img.shields.io/npm/l/llamaindex)](https://www.npmjs.com/package/llamaindex)
 [![NPM Downloads](https://img.shields.io/npm/dm/llamaindex)](https://www.npmjs.com/package/llamaindex)
 [![Discord](https://img.shields.io/discord/1059199217496772688)](https://discord.com/invite/eN6D2HQ4aX)
 
-LlamaIndex is a data framework for your LLM application.
-
 Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in JS runtime environments with TypeScript support.
 
 Documentation: https://ts.llamaindex.ai/

apps/docs/CHANGELOG.md

@@ -1,5 +1,146 @@
 # docs
 
+## 0.0.135
+
+### Patch Changes
+
+- Updated dependencies [dd596a0]
+  - llamaindex@0.8.29
+
+## 0.0.134
+
+### Patch Changes
+
+- llamaindex@0.8.28
+- @llamaindex/examples@0.0.21
+
+## 0.0.133
+
+### Patch Changes
+
+- c1850ee: feat: Amazon Nova support via Bedrock
+- Updated dependencies [b504303]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+  - @llamaindex/examples@0.0.20
+
+## 0.0.132
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - llamaindex@0.8.26
+  - @llamaindex/examples@0.0.19
+
+## 0.0.131
+
+### Patch Changes
+
+- llamaindex@0.8.25
+- @llamaindex/examples@0.0.18
+
+## 0.0.130
+
+### Patch Changes
+
+- Updated dependencies [fd38a25]
+  - @llamaindex/examples@0.0.17
+
+## 0.0.129
+
+### Patch Changes
+
+- Updated dependencies [515f2c1]
+  - llamaindex@0.8.24
+
+## 0.0.128
+
+### Patch Changes
+
+- llamaindex@0.8.23
+
+## 0.0.127
+
+### Patch Changes
+
+- Updated dependencies [819af45]
+  - llamaindex@0.8.22
+
+## 0.0.126
+
+### Patch Changes
+
+- Updated dependencies [83c3897]
+- Updated dependencies [efa2211]
+  - llamaindex@0.8.21
+
+## 0.0.125
+
+### Patch Changes
+
+- Updated dependencies [02b22da]
+  - llamaindex@0.8.20
+
+## 0.0.124
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - llamaindex@0.8.19
+
+## 0.0.123
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+  - llamaindex@0.8.18
+
+## 0.0.122
+
+### Patch Changes
+
+- llamaindex@0.8.17
+
+## 0.0.121
+
+### Patch Changes
+
+- llamaindex@0.8.16
+
+## 0.0.120
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+
+## 0.0.119
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+
+## 0.0.118
+
+### Patch Changes
+
+- llamaindex@0.8.13
+- @llamaindex/examples@0.0.16
+
+## 0.0.117
+
+### Patch Changes
+
+- @llamaindex/examples@0.0.15
+
+## 0.0.116
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
 ## 0.0.115
 
 ### Patch Changes

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

@@ -37,6 +37,9 @@ META_LLAMA3_2_1B_INSTRUCT = "meta.llama3-2-1b-instruct-v1:0"; // only available
 META_LLAMA3_2_3B_INSTRUCT = "meta.llama3-2-3b-instruct-v1:0"; // only available via inference endpoints (see below)
 META_LLAMA3_2_11B_INSTRUCT = "meta.llama3-2-11b-instruct-v1:0"; // only available via inference endpoints (see below), multimodal and function call supported
 META_LLAMA3_2_90B_INSTRUCT = "meta.llama3-2-90b-instruct-v1:0"; // only available via inference endpoints (see below), multimodal and function call supported
+AMAZON_NOVA_PRO_1 = "amazon.nova-pro-v1:0";
+AMAZON_NOVA_LITE_1 = "amazon.nova-lite-v1:0";
+AMAZON_NOVA_MICRO_1 = "amazon.nova-micro-v1:0";
 ```
 
 You can also use Bedrock's Inference endpoints by using the model names:
@@ -53,6 +56,9 @@ US_META_LLAMA_3_2_1B_INSTRUCT = "us.meta.llama3-2-1b-instruct-v1:0";
 US_META_LLAMA_3_2_3B_INSTRUCT = "us.meta.llama3-2-3b-instruct-v1:0";
 US_META_LLAMA_3_2_11B_INSTRUCT = "us.meta.llama3-2-11b-instruct-v1:0";
 US_META_LLAMA_3_2_90B_INSTRUCT = "us.meta.llama3-2-90b-instruct-v1:0";
+US_AMAZON_NOVA_PRO_1 = "us.amazon.nova-pro-v1:0";
+US_AMAZON_NOVA_LITE_1 = "us.amazon.nova-lite-v1:0";
+US_AMAZON_NOVA_MICRO_1 = "us.amazon.nova-micro-v1:0";
 
 // EU
 EU_ANTHROPIC_CLAUDE_3_HAIKU = "eu.anthropic.claude-3-haiku-20240307-v1:0";

apps/docs/docusaurus.config.js

@@ -62,6 +62,12 @@ const config = {
     ({
       // Replace with your project's social card
       image: "img/favicon.png", // TODO change this
+      announcementBar: {
+        id: "migrate_to_next",
+        content:
+          'We are migrating to Next.js based documentation. Check it out <a href="https://ts.llamaindex.ai/docs/llamaindex">here</a>!',
+        isCloseable: false,
+      },
       navbar: {
         title: "LlamaIndex.TS",
         logo: {

apps/docs/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docs",
-  "version": "0.0.115",
+  "version": "0.0.135",
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",
@@ -15,29 +15,29 @@
     "typecheck": "tsc"
   },
   "dependencies": {
-    "@docusaurus/core": "3.6.0",
-    "@docusaurus/remark-plugin-npm2yarn": "3.6.0",
+    "@docusaurus/core": "3.6.1",
+    "@docusaurus/remark-plugin-npm2yarn": "3.6.1",
     "@llamaindex/examples": "workspace:*",
     "@mdx-js/react": "^3.1.0",
     "clsx": "^2.1.1",
     "llamaindex": "workspace:*",
-    "postcss": "^8.4.47",
+    "postcss": "^8.4.49",
     "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": "3.6.0",
-    "@docusaurus/preset-classic": "3.6.0",
-    "@docusaurus/theme-classic": "3.6.0",
-    "@docusaurus/types": "3.6.0",
+    "@docusaurus/module-type-aliases": "3.6.1",
+    "@docusaurus/preset-classic": "3.6.1",
+    "@docusaurus/theme-classic": "3.6.1",
+    "@docusaurus/types": "3.6.1",
     "@tsconfig/docusaurus": "2.0.3",
     "@types/node": "^22.9.0",
     "docusaurus-plugin-typedoc": "1.0.5",
     "typedoc": "0.26.11",
     "typedoc-plugin-markdown": "4.2.10",
-    "typescript": "^5.6.3"
+    "typescript": "^5.7.2"
   },
   "browserslist": {
     "production": [

apps/next/.gitignore

@@ -29,4 +29,5 @@ next-env.d.ts
 
 # build
 /src/content/docs/cloud/api
+/src/content/docs/api
 ./types

apps/next/CHANGELOG.md

@@ -1,5 +1,212 @@
 # @llamaindex/doc
 
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [dd596a0]
+  - llamaindex@0.8.29
+
+## 0.0.32
+
+### Patch Changes
+
+- a9b5b99: feat: build api reference pages for new documentation site
+- Updated dependencies [a9b5b99]
+  - @llamaindex/core@0.4.19
+  - @llamaindex/readers@1.0.21
+  - @llamaindex/cloud@2.0.19
+  - llamaindex@0.8.28
+  - @llamaindex/node-parser@0.0.20
+  - @llamaindex/openai@0.1.44
+
+## 0.0.31
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [e0f6cc3]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+  - @llamaindex/core@0.4.18
+  - @llamaindex/cloud@2.0.18
+  - @llamaindex/node-parser@0.0.19
+  - @llamaindex/openai@0.1.43
+  - @llamaindex/readers@1.0.20
+  - @llamaindex/workflow@0.0.8
+
+## 0.0.30
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - @llamaindex/core@0.4.17
+  - llamaindex@0.8.26
+  - @llamaindex/openai@0.1.42
+  - @llamaindex/cloud@2.0.17
+  - @llamaindex/node-parser@0.0.18
+  - @llamaindex/readers@1.0.19
+
+## 0.0.29
+
+### Patch Changes
+
+- Updated dependencies [7e8230b]
+- Updated dependencies [8be4589]
+  - @llamaindex/readers@1.0.18
+  - @llamaindex/cloud@2.0.16
+  - @llamaindex/core@0.4.16
+  - @llamaindex/node-parser@0.0.17
+  - @llamaindex/openai@0.1.41
+  - @llamaindex/workflow@0.0.7
+  - llamaindex@0.8.25
+
+## 0.0.28
+
+### Patch Changes
+
+- fd38a25: Add vercel tool adapter to use query engine tool
+
+## 0.0.27
+
+### Patch Changes
+
+- Updated dependencies [515f2c1]
+  - llamaindex@0.8.24
+
+## 0.0.26
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.15
+- @llamaindex/core@0.4.15
+- llamaindex@0.8.23
+- @llamaindex/node-parser@0.0.16
+- @llamaindex/openai@0.1.40
+- @llamaindex/readers@1.0.17
+
+## 0.0.25
+
+### Patch Changes
+
+- Updated dependencies [819af45]
+  - llamaindex@0.8.22
+  - @llamaindex/cloud@2.0.14
+  - @llamaindex/core@0.4.14
+  - @llamaindex/node-parser@0.0.15
+  - @llamaindex/openai@0.1.39
+  - @llamaindex/readers@1.0.16
+
+## 0.0.24
+
+### Patch Changes
+
+- Updated dependencies [83c3897]
+- Updated dependencies [efa2211]
+  - llamaindex@0.8.21
+
+## 0.0.23
+
+### Patch Changes
+
+- Updated dependencies [02b22da]
+  - llamaindex@0.8.20
+
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - @llamaindex/cloud@2.0.13
+  - @llamaindex/core@0.4.13
+  - llamaindex@0.8.19
+  - @llamaindex/node-parser@0.0.14
+  - @llamaindex/readers@1.0.15
+  - @llamaindex/openai@0.1.38
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+- Updated dependencies [ef4f63d]
+  - llamaindex@0.8.18
+  - @llamaindex/core@0.4.12
+  - @llamaindex/cloud@2.0.12
+  - @llamaindex/node-parser@0.0.13
+  - @llamaindex/openai@0.1.37
+  - @llamaindex/readers@1.0.14
+
+## 0.0.20
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+  - @llamaindex/cloud@2.0.11
+  - llamaindex@0.8.17
+  - @llamaindex/node-parser@0.0.12
+  - @llamaindex/openai@0.1.36
+  - @llamaindex/readers@1.0.13
+
+## 0.0.19
+
+### Patch Changes
+
+- Updated dependencies [e60328b]
+  - @llamaindex/readers@1.0.12
+  - llamaindex@0.8.16
+
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+
+## 0.0.17
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+
+## 0.0.16
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [ee20c44]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+  - @llamaindex/workflow@0.0.6
+  - llamaindex@0.8.13
+  - @llamaindex/cloud@2.0.10
+  - @llamaindex/node-parser@0.0.11
+  - @llamaindex/openai@0.1.35
+  - @llamaindex/readers@1.0.11
+
+## 0.0.15
+
+### Patch Changes
+
+- Updated dependencies [ea92b69]
+- Updated dependencies [fadc8b8]
+  - @llamaindex/workflow@0.0.5
+
+## 0.0.14
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+  - @llamaindex/openai@0.1.34
+  - @llamaindex/cloud@2.0.9
+  - llamaindex@0.8.12
+  - @llamaindex/node-parser@0.0.10
+  - @llamaindex/readers@1.0.10
+
 ## 0.0.13
 
 ### Patch Changes

apps/next/next.config.mjs

@@ -6,6 +6,7 @@ const withMDX = createMDX();
 const config = {
   reactStrictMode: true,
   transpilePackages: ["monaco-editor"],
+  serverExternalPackages: ["@huggingface/transformers"],
   webpack: (config, { isServer }) => {
     if (Array.isArray(config.target) && config.target.includes("web")) {
       config.target = ["web", "es2020"];
@@ -26,6 +27,7 @@ const config = {
         }),
       );
     }
+    config.resolve.alias["replicate"] = false;
     return config;
   },
 };

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.0.13",
+  "version": "0.0.33",
   "private": true,
   "scripts": {
     "build": "pnpm run build:docs && next build",
@@ -8,11 +8,11 @@
     "start": "next start",
     "postdev": "fumadocs-mdx",
     "postbuild": "fumadocs-mdx && tsx scripts/post-build.mts",
-    "build:docs": "node ./scripts/generate-docs.mjs"
+    "build:docs": "cross-env NODE_OPTIONS=\"--max-old-space-size=8192\" typedoc && node ./scripts/generate-docs.mjs"
   },
   "dependencies": {
     "@icons-pack/react-simple-icons": "^10.1.0",
-    "@llamaindex/chat-ui": "0.0.5",
+    "@llamaindex/chat-ui": "0.0.9",
     "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/node-parser": "workspace:*",
@@ -20,31 +20,31 @@
     "@llamaindex/readers": "workspace:*",
     "@llamaindex/workflow": "workspace:*",
     "@mdx-js/mdx": "^3.1.0",
-    "@number-flow/react": "^0.3.0",
+    "@number-flow/react": "^0.3.4",
     "@radix-ui/react-dialog": "^1.1.2",
-    "@radix-ui/react-icons": "^1.3.1",
+    "@radix-ui/react-icons": "^1.3.2",
     "@radix-ui/react-label": "^2.1.0",
     "@radix-ui/react-slider": "^1.2.1",
     "@radix-ui/react-slot": "^1.1.0",
-    "@radix-ui/react-tooltip": "^1.1.3",
+    "@radix-ui/react-tooltip": "^1.1.4",
     "@vercel/functions": "^1.5.0",
-    "ai": "^3.4.31",
+    "ai": "^3.4.33",
     "class-variance-authority": "^0.7.0",
     "clsx": "2.1.1",
-    "foxact": "^0.2.40",
-    "framer-motion": "^11.11.11",
-    "fumadocs-core": "14.2.0",
-    "fumadocs-docgen": "^1.3.1",
-    "fumadocs-mdx": "^11.1.1",
-    "fumadocs-openapi": "^5.5.6",
-    "fumadocs-twoslash": "^2.0.1",
-    "fumadocs-typescript": "^3.0.1",
-    "fumadocs-ui": "14.2.0",
+    "foxact": "^0.2.41",
+    "framer-motion": "^11.11.17",
+    "fumadocs-core": "^14.6.0",
+    "fumadocs-docgen": "^1.3.2",
+    "fumadocs-mdx": "^11.1.2",
+    "fumadocs-openapi": "^5.8.2",
+    "fumadocs-twoslash": "^2.0.2",
+    "fumadocs-typescript": "^3.0.2",
+    "fumadocs-ui": "^14.6.0",
     "hast-util-to-jsx-runtime": "^2.3.2",
     "llamaindex": "workspace:*",
-    "lucide-react": "^0.454.0",
-    "next": "15.0.2",
-    "next-themes": "^0.3.0",
+    "lucide-react": "^0.460.0",
+    "next": "15.0.3",
+    "next-themes": "^0.4.3",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-icons": "^5.3.0",
@@ -54,34 +54,38 @@
     "rehype-katex": "^7.0.1",
     "remark-math": "^6.0.0",
     "rimraf": "^6.0.1",
-    "shiki": "^1.22.2",
+    "shiki": "^1.23.1",
     "shiki-magic-move": "^0.5.0",
     "swr": "^2.2.5",
     "tailwind-merge": "^2.5.2",
     "tailwindcss-animate": "^1.0.7",
-    "tree-sitter": "^0.22.0",
-    "tree-sitter-typescript": "^0.23.0",
-    "use-stick-to-bottom": "^1.0.41",
-    "web-tree-sitter": "^0.24.3",
+    "tree-sitter": "^0.22.1",
+    "tree-sitter-typescript": "^0.23.2",
+    "use-stick-to-bottom": "^1.0.42",
+    "web-tree-sitter": "^0.24.4",
     "zod": "^3.23.8"
   },
   "devDependencies": {
-    "@next/env": "^15.0.2",
+    "@next/env": "^15.0.3",
     "@types/mdx": "^2.0.13",
     "@types/node": "22.9.0",
     "@types/react": "^18.3.12",
     "@types/react-dom": "^18.3.1",
     "autoprefixer": "^10.4.20",
+    "cross-env": "^7.0.3",
     "fast-glob": "^3.3.2",
     "gray-matter": "^4.0.3",
     "monaco-editor-webpack-plugin": "^7.1.0",
-    "postcss": "^8.4.47",
+    "postcss": "^8.4.49",
     "remark": "^15.0.1",
     "remark-gfm": "^4.0.0",
     "remark-mdx": "^3.1.0",
     "remark-stringify": "^11.0.0",
-    "tailwindcss": "^3.4.14",
+    "tailwindcss": "^3.4.15",
     "tsx": "^4.19.2",
-    "typescript": "^5.6.3"
+    "typedoc": "^0.26.11",
+    "typedoc-plugin-markdown": "^4.3.1",
+    "typedoc-plugin-merge-modules": "^6.1.0",
+    "typescript": "^5.7.2"
   }
 }

apps/next/scripts/generate-docs.mjs

@@ -1,8 +1,12 @@
 import * as OpenAPI from "fumadocs-openapi";
+import { generateFiles } from "fumadocs-typescript";
+import fs from "node:fs";
+import * as path from "node:path";
 import { fileURLToPath } from "node:url";
 import { rimrafSync } from "rimraf";
 
 const out = "./src/content/docs/cloud/api";
+const apiRefOut = "./src/content/docs/api";
 
 // clean generated files
 rimrafSync(out, {
@@ -20,3 +24,63 @@ void OpenAPI.generateFiles({
   output: out,
   groupBy: "tag",
 });
+
+void generateFiles({
+  input: ["./src/content/docs/api/**/*.mdx"],
+  output: (file) => path.resolve(path.dirname(file), path.basename(file)),
+  transformOutput,
+});
+
+function transformOutput(filePath, content) {
+  const fileName = path.basename(filePath);
+  let title = fileName.split(".")[0];
+  let pageContent = content;
+  if (title === "index") title = "LlamaIndex API Reference";
+  return `---\ntitle: ${title}\n---\n\n${transformAbsoluteUrl(pageContent, filePath)}`;
+}
+
+/**
+ * Transforms the content by converting relative MDX links to absolute docs API links
+ * Example: [text](../type-aliases/TaskHandler.mdx) -> [text](/docs/api/type-aliases/TaskHandler)
+ * [text](BaseChatEngine.mdx) -> [text](/docs/api/classes/BaseChatEngine)
+ * [text](BaseVectorStore.mdx#constructors) -> [text](/docs/api/classes/BaseVectorStore#constructors)
+ * [text](TaskStep.mdx) -> [text](/docs/api/type-aliases/TaskStep)
+ */
+function transformAbsoluteUrl(content, filePath) {
+  const group = path.dirname(filePath).split(path.sep).pop();
+  return content.replace(
+    /\]\(([^)]+)\.mdx([^)]*)\)/g,
+    (match, slug, anchor) => {
+      const slugParts = slug.split("/");
+      const fileName = slugParts[slugParts.length - 1];
+      const fileGroup = slugParts[slugParts.length - 2] ?? group;
+      const result = ["/docs/api", fileGroup, fileName, anchor]
+        .filter(Boolean)
+        .join("/");
+      return `](${result})`;
+    },
+  );
+}
+
+// append meta.json for API page
+fs.writeFileSync(
+  path.resolve(apiRefOut, "meta.json"),
+  JSON.stringify(
+    {
+      title: "API Reference",
+      description: "LlamaIndex API Reference",
+      root: true,
+      pages: [
+        "index",
+        "classes",
+        "enumerations",
+        "functions",
+        "interfaces",
+        "type-aliases",
+        "variables",
+      ],
+    },
+    null,
+    2,
+  ),
+);

apps/next/src/app/api/chat/route.ts

@@ -1,7 +1,10 @@
+import { MockLLM } from "@llamaindex/core/utils";
 import { LlamaIndexAdapter, type Message } from "ai";
-import { SimpleChatEngine, type ChatMessage } from "llamaindex";
+import { Settings, SimpleChatEngine, type ChatMessage } from "llamaindex";
 import { NextResponse, type NextRequest } from "next/server";
 
+Settings.llm = new MockLLM(); // config your LLM here
+
 export async function POST(request: NextRequest) {
   try {
     const { messages } = (await request.json()) as { messages: Message[] };

apps/next/src/app/global.css

@@ -94,4 +94,33 @@
   body {
     @apply bg-background text-foreground;
   }
+
+  /*
+  * Override default styles for Markdown
+  */
+  .prose
+    :where(blockquote):not(
+      :where([class~="not-prose"], [class~="not-prose"] *)
+    ) {
+    font-style: normal !important;
+  }
+
+  .prose
+    :where(blockquote p:first-of-type):not(
+      :where([class~="not-prose"], [class~="not-prose"] *)
+    ):before {
+    content: none !important;
+  }
+
+  .prose
+    :where(blockquote p:first-of-type):not(
+      :where([class~="not-prose"], [class~="not-prose"] *)
+    ):after {
+    content: none !important;
+  }
+
+  .prose
+    :where(code):not(:where([class~="not-prose"], [class~="not-prose"] *)) {
+    @apply text-blue-600 !important;
+  }
 }

apps/next/src/components/demo/chat.tsx

@@ -1,8 +0,0 @@
-"use client";
-import { ChatSection } from "@llamaindex/chat-ui";
-import { useChat } from "ai/react";
-
-export const ChatDemo = () => {
-  const handler = useChat();
-  return <ChatSection handler={handler} />;
-};

apps/next/src/components/demo/chat/api/demo.tsx

@@ -0,0 +1,16 @@
+"use client";
+import { ChatInput, ChatMessages, ChatSection } from "@llamaindex/chat-ui";
+import { useChat } from "ai/react";
+
+export const ChatDemo = () => {
+  const handler = useChat();
+  return (
+    <ChatSection handler={handler}>
+      <ChatMessages>
+        <ChatMessages.List className="h-auto max-h-[400px]" />
+        <ChatMessages.Actions />
+      </ChatMessages>
+      <ChatInput />
+    </ChatSection>
+  );
+};

apps/next/src/components/demo/chat/rsc/ai-action.tsx

@@ -0,0 +1,57 @@
+import { Markdown } from "@llamaindex/chat-ui/widgets";
+import { MockLLM } from "@llamaindex/core/utils";
+import { generateId, Message } from "ai";
+import { createAI, createStreamableUI, getMutableAIState } from "ai/rsc";
+import { type ChatMessage, Settings, SimpleChatEngine } from "llamaindex";
+import { ReactNode } from "react";
+
+type ServerState = Message[];
+type FrontendState = Array<Message & { display: ReactNode }>;
+type Actions = {
+  chat: (message: Message) => Promise<Message & { display: ReactNode }>;
+};
+
+Settings.llm = new MockLLM(); // config your LLM here
+
+export const AI = createAI<ServerState, FrontendState, Actions>({
+  initialAIState: [],
+  initialUIState: [],
+  actions: {
+    chat: async (message: Message) => {
+      "use server";
+
+      const aiState = getMutableAIState<typeof AI>();
+      aiState.update((prev) => [...prev, message]);
+
+      const uiStream = createStreamableUI();
+      const chatEngine = new SimpleChatEngine();
+      const assistantMessage: Message = {
+        id: generateId(),
+        role: "assistant",
+        content: "",
+      };
+
+      // run the async function without blocking
+      (async () => {
+        const chatResponse = await chatEngine.chat({
+          stream: true,
+          message: message.content,
+          chatHistory: aiState.get() as ChatMessage[],
+        });
+
+        for await (const chunk of chatResponse) {
+          assistantMessage.content += chunk.delta;
+          uiStream.update(<Markdown content={assistantMessage.content} />);
+        }
+
+        aiState.done([...aiState.get(), assistantMessage]);
+        uiStream.done();
+      })();
+
+      return {
+        ...assistantMessage,
+        display: uiStream.value,
+      };
+    },
+  },
+});

apps/next/src/components/demo/chat/rsc/chat-section.tsx

@@ -0,0 +1,33 @@
+"use client";
+
+import {
+  ChatInput,
+  ChatMessage,
+  ChatMessages,
+  ChatSection as ChatSectionUI,
+} from "@llamaindex/chat-ui";
+import { useChatRSC } from "./use-chat-rsc";
+
+export const ChatSectionRSC = () => {
+  const handler = useChatRSC();
+  return (
+    <ChatSectionUI handler={handler}>
+      <ChatMessages>
+        <ChatMessages.List className="h-auto max-h-[400px]">
+          {handler.messages.map((message, index) => (
+            <ChatMessage
+              key={index}
+              message={message}
+              isLast={index === handler.messages.length - 1}
+            >
+              <ChatMessage.Avatar />
+              <ChatMessage.Content>{message.display}</ChatMessage.Content>
+            </ChatMessage>
+          ))}
+          <ChatMessages.Loading />
+        </ChatMessages.List>
+      </ChatMessages>
+      <ChatInput />
+    </ChatSectionUI>
+  );
+};

apps/next/src/components/demo/chat/rsc/demo.tsx

@@ -0,0 +1,8 @@
+import { AI } from "./ai-action";
+import { ChatSectionRSC } from "./chat-section";
+
+export const ChatDemoRSC = () => (
+  <AI>
+    <ChatSectionRSC />
+  </AI>
+);

apps/next/src/components/demo/chat/rsc/use-chat-rsc.tsx

@@ -0,0 +1,41 @@
+"use client";
+
+import { useActions } from "ai/rsc";
+
+import { generateId, Message } from "ai";
+import { useUIState } from "ai/rsc";
+import { useState } from "react";
+import { AI } from "./ai-action";
+
+export function useChatRSC() {
+  const [input, setInput] = useState<string>("");
+  const [isLoading, setIsLoading] = useState<boolean>(false);
+  const [messages, setMessages] = useUIState<typeof AI>();
+  const { chat } = useActions<typeof AI>();
+
+  const append = async (message: Omit<Message, "id">) => {
+    const newMsg: Message = { ...message, id: generateId() };
+
+    setIsLoading(true);
+    try {
+      setMessages((prev) => [...prev, { ...newMsg, display: message.content }]);
+      const assistantMsg = await chat(newMsg);
+      setMessages((prev) => [...prev, assistantMsg]);
+    } catch (error) {
+      console.error(error);
+    }
+    setIsLoading(false);
+    setInput("");
+
+    return message.content;
+  };
+
+  return {
+    input,
+    setInput,
+    isLoading,
+    messages,
+    setMessages,
+    append,
+  };
+}

apps/next/src/components/website/Footer.tsx

@@ -85,6 +85,33 @@ const Footer = () => {
                   <Text as="span">SharePoint</Text>
                 </a>
               </li>
+              <li>
+                <a
+                  href="https://llamaindex.ai/llamacloud-aws-s3-data-loading-for-generative-ai"
+                  data-tracking-variant="link"
+                  data-tracking-section="footer"
+                >
+                  <Text as="span">AWS S3</Text>
+                </a>
+              </li>
+              <li>
+                <a
+                  href="https://llamaindex.ai/llamacloud-azure-blob-storage-data-loading-for-generative-ai"
+                  data-tracking-variant="link"
+                  data-tracking-section="footer"
+                >
+                  <Text as="span">Azure Blob Storage</Text>
+                </a>
+              </li>
+              <li>
+                <a
+                  href="https://llamaindex.ai/llamacloud-google-drive-data-loading-for-generative-ai"
+                  data-tracking-variant="link"
+                  data-tracking-section="footer"
+                >
+                  <Text as="span">Google Drive</Text>
+                </a>
+              </li>
             </ul>
           </div>
           <div>
@@ -171,11 +198,6 @@ const Footer = () => {
                   <Text as="span">SEC Insights</Text>
                 </a>
               </li>
-              <li>
-                <a href="https://chat.llamaindex.ai/">
-                  <Text as="span">Chat LlamaIndex</Text>
-                </a>
-              </li>
               <li>
                 <a href="https://github.com/run-llama/llamabot">
                   <Text as="span">LlamaBot</Text>

apps/next/src/content/docs/llamaindex/guide/chat/chat.mdx

@@ -1,8 +1,8 @@
 ---
-title: Chat-UI 
-description: Use chat-ui to add a chat interface to your LlamaIndexTS application.
+title: Using API Route
+description: Chat interface for your LlamaIndexTS application using API Route
 ---
-import { ChatDemo } from '../../../../components/demo/chat';
+import { ChatDemo } from '../../../../../components/demo/chat/api/demo';
 import "@llamaindex/chat-ui/styles/code.css";
 import "@llamaindex/chat-ui/styles/katex.css";
 
@@ -26,7 +26,7 @@ This is the simplest way to add a chat interface to your application. Copy the f
 
 ```json doc-gen:file
 {
-  "file": "./src/components/demo/chat.tsx",
+  "file": "./src/components/demo/chat/api/demo.tsx",
 	"codeblock": true
 }
 ```
@@ -37,6 +37,7 @@ Combining both, you're getting a fully functional chat interface:
 
 <ChatDemo />
 
+
 ## Next Steps
 
 The steps above are the bare minimum to get a chat interface working. From here, you can go two ways:

apps/next/src/content/docs/llamaindex/guide/chat/meta.json

@@ -0,0 +1,6 @@
+{
+  "title": "Chat-UI",
+  "description": "Use chat-ui to add a chat interface to your LlamaIndexTS application.",
+  "defaultOpen": false,
+  "pages": ["chat", "rsc"]
+}

apps/next/src/content/docs/llamaindex/guide/chat/rsc.mdx

@@ -0,0 +1,68 @@
+---
+title: Using Next.js RSC
+description: Chat interface for your LlamaIndexTS application using Next.js RSC
+---
+import { ChatDemoRSC } from '../../../../../components/demo/chat/rsc/demo';
+import "@llamaindex/chat-ui/styles/code.css";
+import "@llamaindex/chat-ui/styles/katex.css";
+
+Using [chat-ui](https://github.com/run-llama/chat-ui), it's easy to add a chat interface to your LlamaIndexTS application using [Next.js RSC](https://nextjs.org/docs/app/building-your-application/rendering/server-components) and [Vercel AI RSC](https://sdk.vercel.ai/docs/ai-sdk-rsc/overview).
+
+With RSC, the chat messages are not returned as JSON from the server (like when using an [API route](./chat)), instead the chat message components are rendered on the server side.
+This is for example useful for rendering a whole chat history on the server before sending it to the client. [Check here](https://sdk.vercel.ai/docs/getting-started/navigating-the-library#when-to-use-ai-sdk-rsc), for a discussion of when to use use RSC.
+
+For implementing a chat interface with RSC, you need to create an AI action and then connect the chat interface to use it.
+
+## Create an AI action
+
+First, define an [AI context provider](https://sdk.vercel.ai/examples/rsc/state-management/ai-ui-states) with a chat server action:
+
+```json doc-gen:file
+{
+  "file": "./src/components/demo/chat/rsc/ai-action.tsx",
+	"codeblock": true
+}
+```
+
+The chat server action is using LlamaIndexTS to generate a response based on the chat history and the user input.
+
+## Create the chat UI
+
+The entrypoint of our application initializes the AI provider for the application and adds a `ChatSection` component:
+
+```json doc-gen:file
+{
+  "file": "./src/components/demo/chat/rsc/demo.tsx",
+	"codeblock": true
+}
+```
+
+The `ChatSection` component is created by using chat components from @llamaindex/chat-ui:
+
+```json doc-gen:file
+{
+  "file": "./src/components/demo/chat/rsc/chat-section.tsx",
+	"codeblock": true
+}
+```
+
+It is using a `useChatRSC` hook to conntect the chat interface to the `chat` AI action that we defined earlier:
+
+```json doc-gen:file
+{
+  "file": "./src/components/demo/chat/rsc/use-chat-rsc.tsx",
+	"codeblock": true
+}
+```
+
+## Try RSC Chat ⬇️
+
+<ChatDemoRSC />
+
+## Next Steps
+
+The steps above are the bare minimum to get a chat interface working with RSC. From here, you can go two ways:
+
+1. Use our [full-stack RSC example](https://github.com/run-llama/nextjs-rsc) based on [create-llama](https://github.com/run-llama/create-llama) to get started quickly with a fully working chat interface or
+2. Learn more about [AI RSC](https://sdk.vercel.ai/examples/rsc), [chat-ui](https://github.com/run-llama/chat-ui) and [LlamaIndexTS](https://github.com/run-llama/llamaindex-ts) to customize the chat interface and AI actions to your needs.
+

apps/next/src/content/docs/llamaindex/integration/meta.json

@@ -1,5 +1,5 @@
 {
   "title": "Integration",
   "description": "See our integrations",
-  "pages": ["open-llm-metry", "lang-trace"]
+  "pages": ["open-llm-metry", "lang-trace", "vercel"]
 }

apps/next/src/content/docs/llamaindex/integration/vercel.mdx

@@ -0,0 +1,101 @@
+---
+title: Vercel
+description: Integrate LlamaIndex with Vercel's AI SDK
+---
+
+LlamaIndex provides integration with Vercel's AI SDK, allowing you to create powerful search and retrieval applications. You can:
+- Use any of Vercel AI's [model providers](https://sdk.vercel.ai/docs/foundations/providers-and-models) as LLMs in LlamaIndex
+- Use indexes (e.g. VectorStoreIndex, LlamaCloudIndex) from LlamaIndexTS in your Vercel AI applications
+
+## Setup
+
+First, install the required dependencies:
+
+```bash
+npm install @llamaindex/vercel ai
+```
+
+## Using Vercel AI's Model Providers 
+
+Using the `VercelLLM` adapter, it's easy to use any of Vercel AI's [model providers](https://sdk.vercel.ai/docs/foundations/providers-and-models) as LLMs in LlamaIndex. Here's an example of how to use OpenAI's GPT-4o model:
+
+```typescript
+const llm = new VercelLLM({ model: openai("gpt-4o") });
+const result = await llm.complete({
+  prompt: "What is the capital of France?",
+  stream: false, // Set to true if you want streaming responses
+});
+console.log(result.text);
+```
+
+## Use Indexes
+
+### Using VectorStoreIndex
+
+Here's how to create a simple vector store index and query it using Vercel's AI SDK:
+
+```typescript
+import { openai } from "@ai-sdk/openai";
+import { llamaindex } from "@llamaindex/vercel";
+import { streamText } from "ai";
+import { Document, VectorStoreIndex } from "llamaindex";
+
+// Create an index from your documents
+const document = new Document({ text: yourText, id_: "unique-id" });
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+// Create a query tool
+const queryTool = llamaindex({
+  model: openai("gpt-4"),
+  index,
+  description: "Search through the documents", // optional
+});
+
+// Use the tool with Vercel's AI SDK
+streamText({
+  model: openai("gpt-4"),
+  prompt: "Your question here",
+  tools: { queryTool },
+  onFinish({ response }) {
+    console.log("Response:", response.messages); // log the response
+  },
+}).toDataStream();
+```
+
+> Note: the Vercel AI model referenced in the `llamaindex` function is used by the response synthesizer to generate a response for the tool call.
+
+### Using LlamaCloud
+
+For production deployments, you can use LlamaCloud to store and manage your documents:
+
+```typescript
+import { LlamaCloudIndex } from "llamaindex";
+
+// Create a LlamaCloud index
+const index = await LlamaCloudIndex.fromDocuments({
+  documents: [document],
+  name: "your-index-name",
+  projectName: "your-project",
+  apiKey: process.env.LLAMA_CLOUD_API_KEY,
+});
+
+// Use it the same way as VectorStoreIndex
+const queryTool = llamaindex({
+  model: openai("gpt-4"),
+  index,
+  description: "Search through the documents",
+});
+
+// Use the tool with Vercel's AI SDK
+streamText({
+  model: openai("gpt-4"),
+  prompt: "Your question here",
+  tools: { queryTool },
+}).toDataStream();
+```
+
+## Next Steps
+
+1. Explore [LlamaCloud](https://cloud.llamaindex.ai/) for managed document storage and retrieval
+2. Join our [Discord community](https://discord.gg/dGcwcsnxhU) for support and discussions
+

apps/next/src/content/docs/llamaindex/setup/cloudflare.mdx

@@ -37,6 +37,33 @@ Then, you need create `.dev.vars` and add LLM api keys for the local development
 
 <Callout type="warn">Do not commit the api key to git repository.</Callout>
 
+## Integrating with Hono
+
+```ts
+import { Hono } from "hono";
+
+type Bindings = {
+  OPENAI_API_KEY: string;
+};
+
+const app = new Hono<{
+  Bindings: Bindings;
+}>();
+
+app.post("/llm", async (c) => {
+  const { setEnvs } = await import("@llamaindex/env");
+  setEnvs(c.env);
+
+  // ...
+
+  return new Response('Hello, world!');
+})
+
+export default {
+  fetch: app.fetch,
+};
+```
+
 ## Difference between Node.js and Cloudflare Worker
 
 In Cloudflare Worker and similar serverless JS environment, you need to be aware of the following differences:
@@ -46,3 +73,7 @@ In Cloudflare Worker and similar serverless JS environment, you need to be aware
 - Some of LlamaIndex.TS modules are not available in Cloudflare Worker, for example `SimpleDirectoryReader` (requires `node:fs`), Some multimodal API that relies on [`onnxruntime-node`](https://www.npmjs.com/package/onnxruntime-node)(we might port to HTTP based module in the future).
 - `@llamaindex/core` is designed to work in all JavaScript environment, including Cloudflare Worker. If you find any issue, please report to us.
 - `@llamaindex/env` is a JS environment binding module, which polyfill some Node.js/Modern Web API (for example, we have a memory based `fs` module, and Crypto API polyfill). It is designed to work in all JavaScript environment, including Cloudflare Worker.
+
+## Known issues
+
+- `llamaindex` not work perfectly in Cloudflare Worker, bundle size will be larger than 1MB, which is the limit of Cloudflare Worker. You will need import submodule instead of the whole `llamaindex` module.

apps/next/src/content/docs/llamaindex/setup/typescript.mdx

@@ -84,7 +84,7 @@ Imaging you put output file into `/dist/openai.js` but you are importing `llamai
 }
 ```
 
-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)
+In old module resolution, TypeScript will not be able to find the module because it is not following 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).

apps/next/src/content/docs/meta.json

@@ -1,3 +1,3 @@
 {
-  "pages": ["llamaindex", "cloud"]
+  "pages": ["llamaindex", "cloud", "api"]
 }

apps/next/typedoc.json

@@ -0,0 +1,18 @@
+{
+  "plugin": ["typedoc-plugin-markdown", "typedoc-plugin-merge-modules"],
+  "entryPoints": ["../../packages/llamaindex/src/index.ts"],
+  "tsconfig": "../../tsconfig.json",
+  "readme": "none",
+  "sourceLinkTemplate": "https://github.com/run-llama/LlamaIndexTS/blob/{gitRevision}/{path}#L{line}",
+  "out": "./src/content/docs/api",
+  "outputFileStrategy": "members",
+  "categorizeByGroup": true,
+  "categoryOrder": ["Classes", "Enums", "Functions", "Interfaces", "Types"],
+  "sort": ["source-order"],
+  "entryFileName": "index.md",
+  "fileExtension": ".mdx",
+  "hidePageTitle": true,
+  "hidePageHeader": true,
+  "hideGroupHeadings": true,
+  "hideBreadcrumbs": true
+}

e2e/.env.ci

@@ -1 +1,4 @@
 POSTGRES_USER=runner
+PINECONE_API_KEY=
+PINECONE_INDEX_NAME=
+PINECONE_NAMESPACE=

e2e/examples/cloudflare-hono/.gitignore

@@ -0,0 +1,172 @@
+# Logs
+
+logs
+_.log
+npm-debug.log_
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+
+report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
+
+# Runtime data
+
+pids
+_.pid
+_.seed
+\*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+
+lib-cov
+
+# Coverage directory used by tools like istanbul
+
+coverage
+\*.lcov
+
+# nyc test coverage
+
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+
+bower_components
+
+# node-waf configuration
+
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+
+build/Release
+
+# Dependency directories
+
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+
+web_modules/
+
+# TypeScript cache
+
+\*.tsbuildinfo
+
+# Optional npm cache directory
+
+.npm
+
+# Optional eslint cache
+
+.eslintcache
+
+# Optional stylelint cache
+
+.stylelintcache
+
+# Microbundle cache
+
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+
+.node_repl_history
+
+# Output of 'npm pack'
+
+\*.tgz
+
+# Yarn Integrity file
+
+.yarn-integrity
+
+# dotenv environment variable files
+
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+
+.cache
+.parcel-cache
+
+# Next.js build output
+
+.next
+out
+
+# Nuxt.js build / generate output
+
+.nuxt
+dist
+
+# Gatsby files
+
+.cache/
+
+# Comment in the public line in if your project uses Gatsby and not Next.js
+
+# https://nextjs.org/blog/next-9-1#public-directory-support
+
+# public
+
+# vuepress build output
+
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+
+.temp
+.cache
+
+# Docusaurus cache and generated files
+
+.docusaurus
+
+# Serverless directories
+
+.serverless/
+
+# FuseBox cache
+
+.fusebox/
+
+# DynamoDB Local files
+
+.dynamodb/
+
+# TernJS port file
+
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+
+.vscode-test
+
+# yarn v2
+
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.\*
+
+# wrangler project
+
+.dev.vars
+.wrangler/

e2e/examples/cloudflare-hono/package.json

@@ -0,0 +1,20 @@
+{
+  "name": "@llamaindex/cloudflare-hono",
+  "version": "0.0.0",
+  "private": true,
+  "scripts": {
+    "deploy": "wrangler deploy",
+    "build": "wrangler deploy --dry-run --outdir dist",
+    "dev": "wrangler dev",
+    "start": "wrangler dev",
+    "cf-typegen": "wrangler types"
+  },
+  "devDependencies": {
+    "@cloudflare/workers-types": "^4.20241112.0",
+    "typescript": "^5.7.2",
+    "wrangler": "^3.89.0"
+  },
+  "dependencies": {
+    "hono": "^4.6.11"
+  }
+}

e2e/examples/cloudflare-hono/src/index.ts

@@ -0,0 +1,91 @@
+import { Hono } from "hono";
+
+type Bindings = {
+  OPENAI_API_KEY: string;
+  PINECONE_API_KEY: string;
+};
+
+const app = new Hono<{
+  Bindings: Bindings;
+}>();
+
+app.post("/llm", async (c) => {
+  //#region init envs
+  const { setEnvs } = await import("@llamaindex/env");
+  setEnvs(c.env);
+  //#endregion
+
+  const { message } = await c.req.json();
+
+  const { extractText } = await import("@llamaindex/core/utils");
+
+  const {
+    QueryEngineTool,
+    serviceContextFromDefaults,
+    VectorStoreIndex,
+    OpenAIAgent,
+    Settings,
+    OpenAI,
+    OpenAIEmbedding,
+  } = await import("llamaindex");
+
+  const { PineconeVectorStore } = await import(
+    "llamaindex/vector-store/PineconeVectorStore"
+  );
+
+  const llm = new OpenAI({
+    model: "gpt-4o-mini",
+    apiKey: c.env.OPENAI_API_KEY,
+  });
+
+  Settings.embedModel = new OpenAIEmbedding({
+    model: "text-embedding-3-small",
+    apiKey: c.env.OPENAI_API_KEY,
+  });
+
+  const serviceContext = serviceContextFromDefaults({
+    llm,
+    chunkSize: 8191,
+    chunkOverlap: 0,
+  });
+
+  const store = new PineconeVectorStore({
+    namespace: "8xolsn4ulEQGdhnhP76yCzfLHdOZ",
+  });
+
+  const index = await VectorStoreIndex.fromVectorStore(store, serviceContext);
+
+  const retriever = index.asRetriever({
+    similarityTopK: 3,
+  });
+
+  // Create a query engine
+  const queryEngine = index.asQueryEngine({
+    retriever,
+  });
+
+  const tools = [
+    new QueryEngineTool({
+      queryEngine: queryEngine,
+      metadata: {
+        name: "business_info_tool",
+        description:
+          "This tool can answer questions based " +
+          "on business information. Return not found if you" +
+          " can't find the answer in the documents.",
+      },
+    }),
+  ];
+
+  const agent = new OpenAIAgent({ tools });
+
+  const response = await agent.chat({
+    message: message,
+  });
+
+  return new Response(extractText(response.message.content));
+});
+
+export default {
+  fetch: app.fetch,
+};

e2e/examples/cloudflare-hono/tsconfig.json

@@ -0,0 +1,39 @@
+{
+  "extends": "../../tsconfig.json",
+  "compilerOptions": {
+    /* Visit https://aka.ms/tsconfig.json to read more about this file */
+
+    /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */
+    "target": "es2021",
+    /* Specify a set of bundled library declaration files that describe the target runtime environment. */
+    "lib": ["es2021", "DOM.AsyncIterable"],
+    /* Specify what JSX code is generated. */
+    "jsx": "react-jsx",
+    /* Specify what module code is generated. */
+    "module": "es2022",
+    /* Specify how TypeScript looks up a file from a given module specifier. */
+    "moduleResolution": "Bundler",
+    /* Specify type package names to be included without being referenced in a source file. */
+    "types": ["@cloudflare/workers-types/2023-07-01"],
+    /* Enable importing .json files */
+    "resolveJsonModule": true,
+    /* Allow JavaScript files to be a part of your program. Use the `checkJS` option to get errors from these files. */
+    "allowJs": true,
+    /* Enable error reporting in type-checked JavaScript files. */
+    "checkJs": false,
+    /* Disable emitting files from a compilation. */
+    "noEmit": true,
+    /* Ensure that each file can be safely transpiled without relying on other imports. */
+    "isolatedModules": true,
+    /* Allow 'import x from y' when a module doesn't have a default export. */
+    "allowSyntheticDefaultImports": true,
+    /* Ensure that casing is correct in imports. */
+    "forceConsistentCasingInFileNames": true,
+    /* Enable all strict type-checking options. */
+    "strict": true,
+    /* Skip type checking all .d.ts files. */
+    "skipLibCheck": true
+  },
+  "exclude": ["test"],
+  "include": ["vitest.config.mts", "worker-configuration.d.ts", "src/**/*.ts"]
+}

e2e/examples/cloudflare-hono/worker-configuration.d.ts

@@ -0,0 +1,4 @@
+// Generated by Wrangler by running `wrangler types`
+
+// eslint-disable-next-line @typescript-eslint/no-empty-object-type
+interface Env {}

e2e/examples/cloudflare-hono/wrangler.toml

@@ -0,0 +1,7 @@
+name = "llamaindex-cloudflare-hono-example"
+main = "src/index.ts"
+compatibility_date = "2024-11-12"
+compatibility_flags = ["nodejs_als"]
+
+[observability]
+enabled = true

e2e/examples/cloudflare-worker-agent/CHANGELOG.md

@@ -1,5 +1,127 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.125
+
+### Patch Changes
+
+- Updated dependencies [dd596a0]
+  - llamaindex@0.8.29
+
+## 0.0.124
+
+### Patch Changes
+
+- llamaindex@0.8.28
+
+## 0.0.123
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+
+## 0.0.122
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - llamaindex@0.8.26
+
+## 0.0.121
+
+### Patch Changes
+
+- llamaindex@0.8.25
+
+## 0.0.120
+
+### Patch Changes
+
+- Updated dependencies [515f2c1]
+  - llamaindex@0.8.24
+
+## 0.0.119
+
+### Patch Changes
+
+- llamaindex@0.8.23
+
+## 0.0.118
+
+### Patch Changes
+
+- Updated dependencies [819af45]
+  - llamaindex@0.8.22
+
+## 0.0.117
+
+### Patch Changes
+
+- Updated dependencies [83c3897]
+- Updated dependencies [efa2211]
+  - llamaindex@0.8.21
+
+## 0.0.116
+
+### Patch Changes
+
+- Updated dependencies [02b22da]
+  - llamaindex@0.8.20
+
+## 0.0.115
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - llamaindex@0.8.19
+
+## 0.0.114
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+  - llamaindex@0.8.18
+
+## 0.0.113
+
+### Patch Changes
+
+- llamaindex@0.8.17
+
+## 0.0.112
+
+### Patch Changes
+
+- llamaindex@0.8.16
+
+## 0.0.111
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+
+## 0.0.110
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+
+## 0.0.109
+
+### Patch Changes
+
+- llamaindex@0.8.13
+
+## 0.0.108
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
 ## 0.0.107
 
 ### Patch Changes

e2e/examples/cloudflare-worker-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.107",
+  "version": "0.0.125",
   "type": "module",
   "private": true,
   "scripts": {
@@ -12,13 +12,13 @@
     "cf-typegen": "wrangler types"
   },
   "devDependencies": {
-    "@cloudflare/vitest-pool-workers": "^0.5.8",
-    "@cloudflare/workers-types": "^4.20240924.0",
-    "@vitest/runner": "2.1.4",
-    "@vitest/snapshot": "2.1.4",
-    "typescript": "^5.6.3",
-    "vitest": "2.1.4",
-    "wrangler": "^3.78.8"
+    "@cloudflare/vitest-pool-workers": "^0.5.28",
+    "@cloudflare/workers-types": "^4.20241112.0",
+    "@vitest/runner": "2.1.5",
+    "@vitest/snapshot": "2.1.5",
+    "typescript": "^5.7.2",
+    "vitest": "2.1.5",
+    "wrangler": "^3.87.0"
   },
   "dependencies": {
     "llamaindex": "workspace:*"

e2e/examples/llama-parse-browser/CHANGELOG.md

@@ -1,5 +1,73 @@
 # @llamaindex/llama-parse-browser-test
 
+## 0.0.39
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.19
+
+## 0.0.38
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.18
+
+## 0.0.37
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.17
+
+## 0.0.36
+
+### Patch Changes
+
+- Updated dependencies [8be4589]
+  - @llamaindex/cloud@2.0.16
+
+## 0.0.35
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.15
+
+## 0.0.34
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.14
+
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - @llamaindex/cloud@2.0.13
+
+## 0.0.32
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.12
+
+## 0.0.31
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.11
+
+## 0.0.30
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.10
+
+## 0.0.29
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.9
+
 ## 0.0.28
 
 ### Patch Changes

e2e/examples/llama-parse-browser/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.28",
+  "version": "0.0.39",
   "type": "module",
   "scripts": {
     "dev": "vite",
@@ -9,8 +9,8 @@
     "preview": "vite preview"
   },
   "devDependencies": {
-    "typescript": "^5.6.3",
-    "vite": "^5.4.1",
+    "typescript": "^5.7.2",
+    "vite": "^5.4.11",
     "vite-plugin-wasm": "^3.3.0"
   },
   "dependencies": {

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,127 @@
 # @llamaindex/next-agent-test
 
+## 0.1.125
+
+### Patch Changes
+
+- Updated dependencies [dd596a0]
+  - llamaindex@0.8.29
+
+## 0.1.124
+
+### Patch Changes
+
+- llamaindex@0.8.28
+
+## 0.1.123
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+
+## 0.1.122
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - llamaindex@0.8.26
+
+## 0.1.121
+
+### Patch Changes
+
+- llamaindex@0.8.25
+
+## 0.1.120
+
+### Patch Changes
+
+- Updated dependencies [515f2c1]
+  - llamaindex@0.8.24
+
+## 0.1.119
+
+### Patch Changes
+
+- llamaindex@0.8.23
+
+## 0.1.118
+
+### Patch Changes
+
+- Updated dependencies [819af45]
+  - llamaindex@0.8.22
+
+## 0.1.117
+
+### Patch Changes
+
+- Updated dependencies [83c3897]
+- Updated dependencies [efa2211]
+  - llamaindex@0.8.21
+
+## 0.1.116
+
+### Patch Changes
+
+- Updated dependencies [02b22da]
+  - llamaindex@0.8.20
+
+## 0.1.115
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - llamaindex@0.8.19
+
+## 0.1.114
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+  - llamaindex@0.8.18
+
+## 0.1.113
+
+### Patch Changes
+
+- llamaindex@0.8.17
+
+## 0.1.112
+
+### Patch Changes
+
+- llamaindex@0.8.16
+
+## 0.1.111
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+
+## 0.1.110
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+
+## 0.1.109
+
+### Patch Changes
+
+- llamaindex@0.8.13
+
+## 0.1.108
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
 ## 0.1.107
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.107",
+  "version": "0.1.125",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -8,9 +8,9 @@
     "start": "next start"
   },
   "dependencies": {
-    "ai": "^3.3.21",
+    "ai": "^4.0.0",
     "llamaindex": "workspace:*",
-    "next": "15.0.2",
+    "next": "15.0.3",
     "react": "18.3.1",
     "react-dom": "18.3.1"
   },
@@ -18,10 +18,10 @@
     "@types/node": "^22.9.0",
     "@types/react": "^18.3.12",
     "@types/react-dom": "^18.3.1",
-    "eslint": "9.14.0",
-    "eslint-config-next": "15.0.2",
-    "postcss": "^8.4.41",
-    "tailwindcss": "^3.4.10",
-    "typescript": "^5.6.3"
+    "eslint": "9.16.0",
+    "eslint-config-next": "15.1.0",
+    "postcss": "^8.4.49",
+    "tailwindcss": "^3.4.15",
+    "typescript": "^5.7.2"
   }
 }

e2e/examples/nextjs-edge-runtime/CHANGELOG.md

@@ -1,5 +1,127 @@
 # test-edge-runtime
 
+## 0.1.124
+
+### Patch Changes
+
+- Updated dependencies [dd596a0]
+  - llamaindex@0.8.29
+
+## 0.1.123
+
+### Patch Changes
+
+- llamaindex@0.8.28
+
+## 0.1.122
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+
+## 0.1.121
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - llamaindex@0.8.26
+
+## 0.1.120
+
+### Patch Changes
+
+- llamaindex@0.8.25
+
+## 0.1.119
+
+### Patch Changes
+
+- Updated dependencies [515f2c1]
+  - llamaindex@0.8.24
+
+## 0.1.118
+
+### Patch Changes
+
+- llamaindex@0.8.23
+
+## 0.1.117
+
+### Patch Changes
+
+- Updated dependencies [819af45]
+  - llamaindex@0.8.22
+
+## 0.1.116
+
+### Patch Changes
+
+- Updated dependencies [83c3897]
+- Updated dependencies [efa2211]
+  - llamaindex@0.8.21
+
+## 0.1.115
+
+### Patch Changes
+
+- Updated dependencies [02b22da]
+  - llamaindex@0.8.20
+
+## 0.1.114
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - llamaindex@0.8.19
+
+## 0.1.113
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+  - llamaindex@0.8.18
+
+## 0.1.112
+
+### Patch Changes
+
+- llamaindex@0.8.17
+
+## 0.1.111
+
+### Patch Changes
+
+- llamaindex@0.8.16
+
+## 0.1.110
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+
+## 0.1.109
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+
+## 0.1.108
+
+### Patch Changes
+
+- llamaindex@0.8.13
+
+## 0.1.107
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
 ## 0.1.106
 
 ### Patch Changes

e2e/examples/nextjs-edge-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.106",
+  "version": "0.1.124",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -9,7 +9,7 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "next": "15.0.2",
+    "next": "15.0.3",
     "react": "^18.3.1",
     "react-dom": "^18.3.1"
   },
@@ -17,6 +17,6 @@
     "@types/node": "^22.9.0",
     "@types/react": "^18.3.12",
     "@types/react-dom": "^18.3.1",
-    "typescript": "^5.6.3"
+    "typescript": "^5.7.2"
   }
 }

e2e/examples/nextjs-node-runtime/CHANGELOG.md

@@ -1,5 +1,127 @@
 # @llamaindex/next-node-runtime
 
+## 0.0.106
+
+### Patch Changes
+
+- Updated dependencies [dd596a0]
+  - llamaindex@0.8.29
+
+## 0.0.105
+
+### Patch Changes
+
+- llamaindex@0.8.28
+
+## 0.0.104
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+
+## 0.0.103
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - llamaindex@0.8.26
+
+## 0.0.102
+
+### Patch Changes
+
+- llamaindex@0.8.25
+
+## 0.0.101
+
+### Patch Changes
+
+- Updated dependencies [515f2c1]
+  - llamaindex@0.8.24
+
+## 0.0.100
+
+### Patch Changes
+
+- llamaindex@0.8.23
+
+## 0.0.99
+
+### Patch Changes
+
+- Updated dependencies [819af45]
+  - llamaindex@0.8.22
+
+## 0.0.98
+
+### Patch Changes
+
+- Updated dependencies [83c3897]
+- Updated dependencies [efa2211]
+  - llamaindex@0.8.21
+
+## 0.0.97
+
+### Patch Changes
+
+- Updated dependencies [02b22da]
+  - llamaindex@0.8.20
+
+## 0.0.96
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - llamaindex@0.8.19
+
+## 0.0.95
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+  - llamaindex@0.8.18
+
+## 0.0.94
+
+### Patch Changes
+
+- llamaindex@0.8.17
+
+## 0.0.93
+
+### Patch Changes
+
+- llamaindex@0.8.16
+
+## 0.0.92
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+
+## 0.0.91
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+
+## 0.0.90
+
+### Patch Changes
+
+- llamaindex@0.8.13
+
+## 0.0.89
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
 ## 0.0.88
 
 ### Patch Changes

e2e/examples/nextjs-node-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.0.88",
+  "version": "0.0.106",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -9,7 +9,7 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "next": "15.0.2",
+    "next": "15.0.3",
     "react": "18.3.1",
     "react-dom": "18.3.1"
   },
@@ -17,10 +17,10 @@
     "@types/node": "^22.9.0",
     "@types/react": "^18.3.12",
     "@types/react-dom": "^18.3.1",
-    "eslint": "9.14.0",
-    "eslint-config-next": "15.0.2",
-    "postcss": "^8.4.41",
-    "tailwindcss": "^3.4.10",
-    "typescript": "^5.6.3"
+    "eslint": "9.16.0",
+    "eslint-config-next": "15.1.0",
+    "postcss": "^8.4.49",
+    "tailwindcss": "^3.4.15",
+    "typescript": "^5.7.2"
   }
 }

e2e/examples/waku-query-engine/CHANGELOG.md

@@ -1,5 +1,127 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.125
+
+### Patch Changes
+
+- Updated dependencies [dd596a0]
+  - llamaindex@0.8.29
+
+## 0.0.124
+
+### Patch Changes
+
+- llamaindex@0.8.28
+
+## 0.0.123
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+
+## 0.0.122
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - llamaindex@0.8.26
+
+## 0.0.121
+
+### Patch Changes
+
+- llamaindex@0.8.25
+
+## 0.0.120
+
+### Patch Changes
+
+- Updated dependencies [515f2c1]
+  - llamaindex@0.8.24
+
+## 0.0.119
+
+### Patch Changes
+
+- llamaindex@0.8.23
+
+## 0.0.118
+
+### Patch Changes
+
+- Updated dependencies [819af45]
+  - llamaindex@0.8.22
+
+## 0.0.117
+
+### Patch Changes
+
+- Updated dependencies [83c3897]
+- Updated dependencies [efa2211]
+  - llamaindex@0.8.21
+
+## 0.0.116
+
+### Patch Changes
+
+- Updated dependencies [02b22da]
+  - llamaindex@0.8.20
+
+## 0.0.115
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - llamaindex@0.8.19
+
+## 0.0.114
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+  - llamaindex@0.8.18
+
+## 0.0.113
+
+### Patch Changes
+
+- llamaindex@0.8.17
+
+## 0.0.112
+
+### Patch Changes
+
+- llamaindex@0.8.16
+
+## 0.0.111
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+
+## 0.0.110
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+
+## 0.0.109
+
+### Patch Changes
+
+- llamaindex@0.8.13
+
+## 0.0.108
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
 ## 0.0.107
 
 ### Patch Changes

e2e/examples/waku-query-engine/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.107",
+  "version": "0.0.125",
   "type": "module",
   "private": true,
   "scripts": {
@@ -10,16 +10,16 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "react": "19.0.0-rc-bf7e210c-20241017",
-    "react-dom": "19.0.0-rc-bf7e210c-20241017",
-    "react-server-dom-webpack": "19.0.0-rc-bf7e210c-20241017",
-    "waku": "0.21.4"
+    "react": "19.0.0-rc-5c56b873-20241107",
+    "react-dom": "19.0.0-rc-5c56b873-20241107",
+    "react-server-dom-webpack": "19.0.0-rc-5c56b873-20241107",
+    "waku": "0.21.6"
   },
   "devDependencies": {
     "@types/react": "18.3.12",
     "@types/react-dom": "18.3.1",
     "autoprefixer": "^10.4.20",
-    "tailwindcss": "^3.4.14",
-    "typescript": "5.6.3"
+    "tailwindcss": "^3.4.15",
+    "typescript": "5.7.2"
   }
 }

e2e/node/embedding/clip.e2e.ts

@@ -21,6 +21,11 @@ test.beforeEach(() => {
 });
 
 await test("clip embedding", async (t) => {
+  const major = parseInt(process.versions.node.split(".")[0] ?? "0", 10);
+  if (major < 20) {
+    t.skip("Skip CLIP tests on Node.js < 20");
+    return;
+  }
   await t.test("should trigger load transformer event", async () => {
     const nodes = [
       new ImageNode({

e2e/node/vector-store/pinecone.e2e.ts

@@ -0,0 +1,66 @@
+import { Document, MetadataMode } from "@llamaindex/core/schema";
+import { config } from "dotenv";
+import {
+  OpenAIEmbedding,
+  PineconeVectorStore,
+  VectorStoreIndex,
+} from "llamaindex";
+import assert from "node:assert";
+import { test } from "node:test";
+
+config({ path: [".env.local", ".env", ".env.ci"] });
+
+await test("pinecone", async (t) => {
+  if (
+    !process.env.PINECONE_API_KEY ||
+    !process.env.PINECONE_NAMESPACE ||
+    !process.env.PINECONE_INDEX_NAME
+  ) {
+    return t.skip(
+      "PINECONE_API_KEY, PINECONE_NAMESPACE, and PINECONE_INDEX_NAME must be set to run this test",
+    );
+  }
+  const openaiEmbedding = new OpenAIEmbedding({
+    model: "text-embedding-3-large",
+  });
+
+  const vectorStore = new PineconeVectorStore({
+    embeddingModel: openaiEmbedding,
+  });
+
+  t.after(async () => {
+    await vectorStore.clearIndex();
+  });
+
+  const index = await VectorStoreIndex.fromVectorStore(vectorStore);
+
+  const retriever = index.asRetriever({
+    similarityTopK: 3,
+  });
+  const text = "We are open from 9am to 5pm";
+
+  await vectorStore.add([
+    new Document({
+      text,
+      embedding: await openaiEmbedding.getTextEmbedding(text),
+    }),
+  ]);
+
+  const results = await retriever.retrieve({
+    query: "When are you open?",
+  });
+  results.every((result) => {
+    assert.ok(result.node.embedding instanceof Array);
+    result.node.embedding.every((embedding, idx) =>
+      assert.ok(
+        typeof embedding === "number",
+        `Embedding at index ${idx} should be a number`,
+      ),
+    );
+    assert.ok(typeof result.score === "number", "Score should be a number");
+    assert.ok(
+      result.node.getContent(MetadataMode.NONE).length > 0,
+      "Content should not be empty",
+    );
+  });
+});

examples/CHANGELOG.md

@@ -1,5 +1,79 @@
 # examples
 
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [a9b5b99]
+  - @llamaindex/core@0.4.19
+  - @llamaindex/readers@1.0.21
+  - llamaindex@0.8.28
+  - @llamaindex/vercel@0.0.6
+
+## 0.0.20
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [086a651]
+- Updated dependencies [e0f6cc3]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+  - @llamaindex/vercel@0.0.5
+  - @llamaindex/core@0.4.18
+  - @llamaindex/readers@1.0.20
+  - @llamaindex/workflow@0.0.8
+
+## 0.0.19
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - @llamaindex/core@0.4.17
+  - llamaindex@0.8.26
+  - @llamaindex/vercel@0.0.4
+  - @llamaindex/readers@1.0.19
+
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7e8230b]
+- Updated dependencies [8be4589]
+  - @llamaindex/readers@1.0.18
+  - @llamaindex/core@0.4.16
+  - @llamaindex/vercel@0.0.3
+  - @llamaindex/workflow@0.0.7
+  - llamaindex@0.8.25
+
+## 0.0.17
+
+### Patch Changes
+
+- fd38a25: Add vercel tool adapter to use query engine tool
+- Updated dependencies [fd38a25]
+  - @llamaindex/vercel@0.0.2
+
+## 0.0.16
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [ee20c44]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+  - @llamaindex/workflow@0.0.6
+  - llamaindex@0.8.13
+  - @llamaindex/readers@1.0.11
+
+## 0.0.15
+
+### Patch Changes
+
+- Updated dependencies [ea92b69]
+- Updated dependencies [fadc8b8]
+  - @llamaindex/workflow@0.0.5
+
 ## 0.0.14
 
 ### Patch Changes

examples/anthropic/prompt-caching.ts

@@ -0,0 +1,38 @@
+import { Anthropic } from "llamaindex";
+
+async function main() {
+  const anthropic = new Anthropic({
+    model: "claude-3-5-sonnet-20241022",
+  });
+
+  const entireBook = await fetch(
+    "https://www.gutenberg.org/files/1342/1342-0.txt",
+  ).then((response) => response.text());
+
+  const response = await anthropic.chat({
+    messages: [
+      {
+        content:
+          "You are an AI assistant tasked with analyzing literary works. Your goal is to provide insightful commentary on themes, characters, and writing style.\n",
+        role: "system",
+      },
+      {
+        content: entireBook,
+        role: "system",
+        options: {
+          cache_control: {
+            type: "ephemeral",
+          },
+        },
+      },
+      {
+        content: "analyze the major themes in Pride and Prejudice.",
+        role: "user",
+      },
+    ],
+  });
+
+  console.log(response.message.content);
+}
+
+main().catch(console.error);

examples/cosmosdb/queryVectorData.ts

@@ -83,14 +83,6 @@ async function query() {
     });
   }
 
-  // configure the Azure CosmosDB NoSQL Vector Store
-  const dbConfig: AzureCosmosDBNoSQLConfig = {
-    client: cosmosClient,
-    databaseName,
-    containerName,
-    flatMetadata: false,
-  };
-
   // use Azure CosmosDB as a vectorStore, docStore, and indexStore
   const { vectorStore, docStore, indexStore } = await initializeStores();
 

examples/ingestion/basicIngestion.ts

@@ -1,16 +1,15 @@
-import fs from "node:fs/promises";
-
 import {
   Document,
   IngestionPipeline,
-  MetadataMode,
   OpenAIEmbedding,
   SentenceSplitter,
+  VectorStoreIndex,
 } from "llamaindex";
+import fs from "node:fs/promises";
 
 async function main() {
   // Load essay from abramov.txt in Node
-  const path = "node_modules/llamaindex/examples/abramov.txt";
+  const path = "../node_modules/llamaindex/examples/abramov.txt";
 
   const essay = await fs.readFile(path, "utf-8");
 
@@ -22,14 +21,23 @@ async function main() {
       new OpenAIEmbedding(),
     ],
   });
+  console.time("Pipeline Run Time");
 
-  // run the pipeline
   const nodes = await pipeline.run({ documents: [document] });
 
-  // print out the result of the pipeline run
-  for (const node of nodes) {
-    console.log(node.getContent(MetadataMode.NONE));
-  }
+  console.timeEnd("Pipeline Run Time");
+
+  // initialize the VectorStoreIndex from nodes
+  const index = await VectorStoreIndex.init({ nodes });
+
+  // Query the index
+  const queryEngine = index.asQueryEngine();
+
+  const { message } = await queryEngine.query({
+    query: "summarize the article in three sentence",
+  });
+
+  console.log(message);
 }
 
 main().catch(console.error);

examples/package.json

@@ -1,24 +1,27 @@
 {
   "name": "@llamaindex/examples",
   "private": true,
-  "version": "0.0.14",
+  "version": "0.0.21",
   "dependencies": {
+    "@ai-sdk/openai": "^1.0.5",
     "@aws-crypto/sha256-js": "^5.2.0",
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@datastax/astra-db-ts": "^1.4.1",
-    "@llamaindex/core": "^0.4.7",
-    "@llamaindex/readers": "^1.0.8",
-    "@llamaindex/workflow": "^0.0.4",
+    "@llamaindex/core": "^0.4.19",
+    "@llamaindex/readers": "^1.0.21",
+    "@llamaindex/vercel": "^0.0.6",
+    "@llamaindex/workflow": "^0.0.8",
     "@notionhq/client": "^2.2.15",
-    "@pinecone-database/pinecone": "^3.0.2",
+    "@pinecone-database/pinecone": "^4.0.0",
     "@vercel/postgres": "^0.10.0",
     "@zilliz/milvus2-sdk-node": "^2.4.6",
+    "ai": "^4.0.0",
     "chromadb": "^1.8.1",
     "commander": "^12.1.0",
     "dotenv": "^16.4.5",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.8.10",
+    "llamaindex": "^0.8.28",
     "mongodb": "^6.7.0",
     "pathe": "^1.1.2",
     "postgres": "^3.4.4"
@@ -26,7 +29,7 @@
   "devDependencies": {
     "@types/node": "^22.9.0",
     "tsx": "^4.19.0",
-    "typescript": "^5.6.3"
+    "typescript": "^5.7.2"
   },
   "scripts": {
     "lint": "eslint ."

examples/readers/package.json

@@ -15,7 +15,8 @@
     "start:llamaparse-dir": "node --import tsx ./src/simple-directory-reader-with-llamaparse.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"
+    "start:json": "node --import tsx ./src/json.ts",
+    "start:obsidian": "node --import tsx ./src/obsidian.ts"
   },
   "dependencies": {
     "@llamaindex/readers": "*",
@@ -24,6 +25,6 @@
   "devDependencies": {
     "@types/node": "^22.9.0",
     "tsx": "^4.19.0",
-    "typescript": "^5.6.3"
+    "typescript": "^5.7.2"
   }
 }

examples/readers/src/obsidian.ts

@@ -0,0 +1,12 @@
+import { ObsidianReader } from "@llamaindex/readers/obsidian";
+
+const obsidianReader = new ObsidianReader(
+  "/Users/jingyi/Documents/jingyi-vault",
+);
+
+obsidianReader.loadData().then((documents) => {
+  console.log("documents:", documents.length);
+  documents.forEach((doc) => {
+    console.log(`document (${doc.id_}):`, doc.getText());
+  });
+});

examples/vercel/README.md

@@ -0,0 +1,60 @@
+# Vercel Examples
+
+These examples demonstrate how to integrate LlamaIndexTS with Vercel's AI SDK. The examples show how to use LlamaIndex for search and retrieval in both local vector store and LlamaCloud environments.
+
+## Setup
+
+To run these examples, first install the required dependencies from the parent folder `examples`:
+
+```bash
+npm i
+```
+
+## Running the Examples
+
+Make sure to run the examples from the parent folder called `examples`. The following examples are available:
+
+### Vercel LLM Example
+
+Run the Vercel LLM example with:
+
+```bash
+npx tsx vercel/llm.ts
+```
+
+This example demonstrates using the `VercelLLM` adapter with Vercel's OpenAI model provider
+
+### Vector Store Example
+
+Run the local vector store example with:
+
+```bash
+npx tsx vercel/vector-store.ts
+```
+
+This example demonstrates:
+
+- Creating a vector store index from one document
+- Using Vercel's AI SDK with LlamaIndex for streaming responses
+
+### LlamaCloud Example
+
+To run the LlamaCloud example:
+
+```bash
+npx tsx vercel/llamacloud.ts
+```
+
+This example requires a LlamaCloud API key set in your environment and an embedding model set in the `EMBEDDING_MODEL` environment variable:
+
+```bash
+export LLAMA_CLOUD_API_KEY=your_api_key_here
+export EMBEDDING_MODEL="text-embedding-3-small"
+```
+
+The example demonstrates:
+
+- Creating a LlamaCloud index from one document
+- Streaming responses using Vercel's AI SDK
+
+For more detailed information about the Vercel integration, check out [the documentation](https://ts.llamaindex.ai/docs/llamaindex/integration/vercel).

examples/vercel/llamacloud.ts

@@ -0,0 +1,39 @@
+import { openai } from "@ai-sdk/openai";
+import { llamaindex } from "@llamaindex/vercel";
+import { streamText } from "ai";
+import { Document, LlamaCloudIndex } from "llamaindex";
+import fs from "node:fs/promises";
+
+async function main() {
+  const path = "node_modules/llamaindex/examples/abramov.txt";
+  const essay = await fs.readFile(path, "utf-8");
+  const document = new Document({ text: essay, id_: path });
+
+  const index = await LlamaCloudIndex.fromDocuments({
+    documents: [document],
+    name: "test-pipeline",
+    projectName: "Default",
+    apiKey: process.env.LLAMA_CLOUD_API_KEY,
+  });
+  console.log("Successfully created index");
+
+  const result = streamText({
+    model: openai("gpt-4o"),
+    prompt: "Cost of moving cat from Russia to UK?",
+    tools: {
+      queryTool: llamaindex({
+        model: openai("gpt-4o"),
+        index,
+        description:
+          "get information from your knowledge base to answer questions.", // optional description
+      }),
+    },
+    maxSteps: 5,
+  });
+
+  for await (const textPart of result.textStream) {
+    process.stdout.write(textPart);
+  }
+}
+
+main().catch(console.error);

examples/vercel/llm.ts

@@ -0,0 +1,45 @@
+import { openai } from "@ai-sdk/openai";
+import { VercelLLM } from "@llamaindex/vercel";
+import { LLMAgent, WikipediaTool } from "llamaindex";
+
+async function main() {
+  // Create an instance of VercelLLM with the OpenAI model
+  const vercelLLM = new VercelLLM({ model: openai("gpt-4o") });
+
+  console.log("\n=== Test 1: Using complete() for single response ===");
+  const result = await vercelLLM.complete({
+    prompt: "What is the capital of France?",
+    stream: false, // Set to true if you want streaming responses
+  });
+  console.log(result.text);
+
+  console.log("\n=== Test 2: Using chat() for streaming response ===");
+  const stream = await vercelLLM.chat({
+    messages: [
+      { content: "You want to talk in rhymes.", role: "system" },
+      {
+        content:
+          "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
+        role: "user",
+      },
+    ],
+    stream: true,
+  });
+  for await (const chunk of stream) {
+    process.stdout.write(chunk.delta);
+  }
+
+  console.log("\n=== Test 3: Using LLMAgent with WikipediaTool ===");
+  const agent = new LLMAgent({
+    llm: vercelLLM,
+    tools: [new WikipediaTool()],
+  });
+
+  const { message } = await agent.chat({
+    message: "What's the history of New York from Wikipedia in 3 sentences?",
+  });
+
+  console.log(message);
+}
+
+main().catch(console.error);

examples/vercel/vector-store.ts

@@ -0,0 +1,35 @@
+import { openai } from "@ai-sdk/openai";
+import { llamaindex } from "@llamaindex/vercel";
+import { streamText } from "ai";
+import { Document, VectorStoreIndex } from "llamaindex";
+
+import fs from "node:fs/promises";
+
+async function main() {
+  const path = "node_modules/llamaindex/examples/abramov.txt";
+  const essay = await fs.readFile(path, "utf-8");
+  const document = new Document({ text: essay, id_: path });
+
+  const index = await VectorStoreIndex.fromDocuments([document]);
+  console.log("Successfully created index");
+
+  const result = streamText({
+    model: openai("gpt-4o"),
+    prompt: "Cost of moving cat from Russia to UK?",
+    tools: {
+      queryTool: llamaindex({
+        model: openai("gpt-4o"),
+        index,
+        description:
+          "get information from your knowledge base to answer questions.", // optional description
+      }),
+    },
+    maxSteps: 5,
+  });
+
+  for await (const textPart of result.textStream) {
+    process.stdout.write(textPart);
+  }
+}
+
+main().catch(console.error);

package.json

@@ -2,8 +2,8 @@
   "name": "@llamaindex/monorepo",
   "private": true,
   "scripts": {
-    "build": "turbo run build --filter=\"./packages/*\"",
-    "dev": "turbo run dev --filter=\"./packages/*\"",
+    "build": "turbo run build --filter=\"./packages/*\" --filter=\"./packages/providers/*\"",
+    "dev": "turbo run dev --filter=\"./packages/*\" --filter=\"./packages/providers/*\"",
     "format": "prettier --ignore-unknown --cache --check .",
     "format:write": "prettier --ignore-unknown --write .",
     "lint": "turbo run lint",
@@ -19,20 +19,20 @@
   },
   "devDependencies": {
     "@changesets/cli": "^2.27.5",
-    "eslint": "9.14.0",
-    "eslint-config-next": "^15.0.2",
+    "eslint": "9.16.0",
+    "eslint-config-next": "^15.1.0",
     "eslint-config-prettier": "^9.1.0",
-    "eslint-config-turbo": "^2.2.3",
+    "eslint-config-turbo": "^2.3.3",
     "eslint-plugin-react": "7.37.2",
     "globals": "^15.12.0",
-    "husky": "^9.1.6",
-    "lint-staged": "^15.2.10",
+    "husky": "^9.1.7",
+    "lint-staged": "^15.2.11",
     "madge": "^8.0.0",
-    "prettier": "^3.3.3",
+    "prettier": "^3.4.2",
     "prettier-plugin-organize-imports": "^4.1.0",
-    "turbo": "^2.2.3",
-    "typescript": "^5.6.3",
-    "typescript-eslint": "^8.13.0"
+    "turbo": "^2.3.3",
+    "typescript": "^5.7.2",
+    "typescript-eslint": "^8.18.0"
   },
   "packageManager": "pnpm@9.12.3",
   "lint-staged": {

packages/autotool/CHANGELOG.md

@@ -1,5 +1,130 @@
 # @llamaindex/autotool
 
+## 5.0.29
+
+### Patch Changes
+
+- Updated dependencies [dd596a0]
+  - llamaindex@0.8.29
+
+## 5.0.28
+
+### Patch Changes
+
+- llamaindex@0.8.28
+
+## 5.0.27
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+
+## 5.0.26
+
+### Patch Changes
+
+- 3d1808b: chore: bump version
+- Updated dependencies [3d1808b]
+  - llamaindex@0.8.26
+
+## 5.0.25
+
+### Patch Changes
+
+- 8be4589: chore: bump version
+  - llamaindex@0.8.25
+
+## 5.0.24
+
+### Patch Changes
+
+- Updated dependencies [515f2c1]
+  - llamaindex@0.8.24
+
+## 5.0.23
+
+### Patch Changes
+
+- llamaindex@0.8.23
+
+## 5.0.22
+
+### Patch Changes
+
+- Updated dependencies [819af45]
+  - llamaindex@0.8.22
+
+## 5.0.21
+
+### Patch Changes
+
+- Updated dependencies [83c3897]
+- Updated dependencies [efa2211]
+  - llamaindex@0.8.21
+
+## 5.0.20
+
+### Patch Changes
+
+- Updated dependencies [02b22da]
+  - llamaindex@0.8.20
+
+## 5.0.19
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - llamaindex@0.8.19
+
+## 5.0.18
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+  - llamaindex@0.8.18
+
+## 5.0.17
+
+### Patch Changes
+
+- llamaindex@0.8.17
+
+## 5.0.16
+
+### Patch Changes
+
+- llamaindex@0.8.16
+
+## 5.0.15
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+
+## 5.0.14
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+
+## 5.0.13
+
+### Patch Changes
+
+- llamaindex@0.8.13
+
+## 5.0.12
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
 ## 5.0.11
 
 ### Patch Changes

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

@@ -1,5 +1,146 @@
 # @llamaindex/autotool-01-node-example
 
+## 0.0.72
+
+### Patch Changes
+
+- Updated dependencies [dd596a0]
+  - llamaindex@0.8.29
+  - @llamaindex/autotool@5.0.29
+
+## 0.0.71
+
+### Patch Changes
+
+- llamaindex@0.8.28
+- @llamaindex/autotool@5.0.28
+
+## 0.0.70
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+  - @llamaindex/autotool@5.0.27
+
+## 0.0.69
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - @llamaindex/autotool@5.0.26
+  - llamaindex@0.8.26
+
+## 0.0.68
+
+### Patch Changes
+
+- Updated dependencies [8be4589]
+  - @llamaindex/autotool@5.0.25
+  - llamaindex@0.8.25
+
+## 0.0.67
+
+### Patch Changes
+
+- Updated dependencies [515f2c1]
+  - llamaindex@0.8.24
+  - @llamaindex/autotool@5.0.24
+
+## 0.0.66
+
+### Patch Changes
+
+- llamaindex@0.8.23
+- @llamaindex/autotool@5.0.23
+
+## 0.0.65
+
+### Patch Changes
+
+- Updated dependencies [819af45]
+  - llamaindex@0.8.22
+  - @llamaindex/autotool@5.0.22
+
+## 0.0.64
+
+### Patch Changes
+
+- Updated dependencies [83c3897]
+- Updated dependencies [efa2211]
+  - llamaindex@0.8.21
+  - @llamaindex/autotool@5.0.21
+
+## 0.0.63
+
+### Patch Changes
+
+- Updated dependencies [02b22da]
+  - llamaindex@0.8.20
+  - @llamaindex/autotool@5.0.20
+
+## 0.0.62
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - @llamaindex/autotool@5.0.19
+  - llamaindex@0.8.19
+
+## 0.0.61
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+  - llamaindex@0.8.18
+  - @llamaindex/autotool@5.0.18
+
+## 0.0.60
+
+### Patch Changes
+
+- llamaindex@0.8.17
+- @llamaindex/autotool@5.0.17
+
+## 0.0.59
+
+### Patch Changes
+
+- llamaindex@0.8.16
+- @llamaindex/autotool@5.0.16
+
+## 0.0.58
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+  - @llamaindex/autotool@5.0.15
+
+## 0.0.57
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+  - @llamaindex/autotool@5.0.14
+
+## 0.0.56
+
+### Patch Changes
+
+- llamaindex@0.8.13
+- @llamaindex/autotool@5.0.13
+
+## 0.0.55
+
+### Patch Changes
+
+- llamaindex@0.8.12
+- @llamaindex/autotool@5.0.12
+
 ## 0.0.54
 
 ### Patch Changes

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

@@ -5,7 +5,7 @@
   "dependencies": {
     "@llamaindex/autotool": "workspace:*",
     "llamaindex": "workspace:*",
-    "openai": "^4.57.0"
+    "openai": "^4.73.1"
   },
   "devDependencies": {
     "tsx": "^4.19.0"
@@ -13,5 +13,5 @@
   "scripts": {
     "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
   },
-  "version": "0.0.54"
+  "version": "0.0.72"
 }

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

@@ -1,5 +1,146 @@
 # @llamaindex/autotool-02-next-example
 
+## 0.1.116
+
+### Patch Changes
+
+- Updated dependencies [dd596a0]
+  - llamaindex@0.8.29
+  - @llamaindex/autotool@5.0.29
+
+## 0.1.115
+
+### Patch Changes
+
+- llamaindex@0.8.28
+- @llamaindex/autotool@5.0.28
+
+## 0.1.114
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [a0e6f57]
+  - llamaindex@0.8.27
+  - @llamaindex/autotool@5.0.27
+
+## 0.1.113
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - @llamaindex/autotool@5.0.26
+  - llamaindex@0.8.26
+
+## 0.1.112
+
+### Patch Changes
+
+- Updated dependencies [8be4589]
+  - @llamaindex/autotool@5.0.25
+  - llamaindex@0.8.25
+
+## 0.1.111
+
+### Patch Changes
+
+- Updated dependencies [515f2c1]
+  - llamaindex@0.8.24
+  - @llamaindex/autotool@5.0.24
+
+## 0.1.110
+
+### Patch Changes
+
+- llamaindex@0.8.23
+- @llamaindex/autotool@5.0.23
+
+## 0.1.109
+
+### Patch Changes
+
+- Updated dependencies [819af45]
+  - llamaindex@0.8.22
+  - @llamaindex/autotool@5.0.22
+
+## 0.1.108
+
+### Patch Changes
+
+- Updated dependencies [83c3897]
+- Updated dependencies [efa2211]
+  - llamaindex@0.8.21
+  - @llamaindex/autotool@5.0.21
+
+## 0.1.107
+
+### Patch Changes
+
+- Updated dependencies [02b22da]
+  - llamaindex@0.8.20
+  - @llamaindex/autotool@5.0.20
+
+## 0.1.106
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - @llamaindex/autotool@5.0.19
+  - llamaindex@0.8.19
+
+## 0.1.105
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+  - llamaindex@0.8.18
+  - @llamaindex/autotool@5.0.18
+
+## 0.1.104
+
+### Patch Changes
+
+- llamaindex@0.8.17
+- @llamaindex/autotool@5.0.17
+
+## 0.1.103
+
+### Patch Changes
+
+- llamaindex@0.8.16
+- @llamaindex/autotool@5.0.16
+
+## 0.1.102
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+  - @llamaindex/autotool@5.0.15
+
+## 0.1.101
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+  - @llamaindex/autotool@5.0.14
+
+## 0.1.100
+
+### Patch Changes
+
+- llamaindex@0.8.13
+- @llamaindex/autotool@5.0.13
+
+## 0.1.99
+
+### Patch Changes
+
+- llamaindex@0.8.12
+- @llamaindex/autotool@5.0.12
+
 ## 0.1.98
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool-02-next-example",
   "private": true,
-  "version": "0.1.98",
+  "version": "0.1.116",
   "scripts": {
     "dev": "next dev",
     "build": "next build",
@@ -10,17 +10,17 @@
   "dependencies": {
     "@llamaindex/autotool": "workspace:*",
     "@radix-ui/react-slot": "^1.1.0",
-    "ai": "^3.3.21",
+    "ai": "^4.0.0",
     "class-variance-authority": "^0.7.0",
     "dotenv": "^16.3.1",
     "llamaindex": "workspace:*",
-    "lucide-react": "^0.436.0",
-    "next": "15.0.2",
+    "lucide-react": "^0.460.0",
+    "next": "15.0.3",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-markdown": "^9.0.1",
     "react-syntax-highlighter": "^15.5.0",
-    "sonner": "^1.5.0",
+    "sonner": "^1.7.0",
     "tailwind-merge": "^2.5.2"
   },
   "devDependencies": {
@@ -30,8 +30,8 @@
     "@types/react-syntax-highlighter": "^15.5.11",
     "autoprefixer": "^10.4.20",
     "cross-env": "^7.0.3",
-    "postcss": "^8.4.41",
-    "tailwindcss": "^3.4.10",
-    "typescript": "^5.6.3"
+    "postcss": "^8.4.49",
+    "tailwindcss": "^3.4.15",
+    "typescript": "^5.7.2"
   }
 }

packages/autotool/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool",
   "type": "module",
-  "version": "5.0.11",
+  "version": "5.0.29",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",
@@ -45,10 +45,10 @@
     "dev": "bunchee --watch"
   },
   "dependencies": {
-    "@swc/core": "^1.7.22",
-    "jotai": "2.8.4",
+    "@swc/core": "^1.9.2",
+    "jotai": "2.10.2",
     "typedoc": "^0.26.11",
-    "unplugin": "^1.12.2"
+    "unplugin": "^1.16.0"
   },
   "peerDependencies": {
     "llamaindex": "workspace:*",
@@ -70,13 +70,13 @@
     "@swc/types": "^0.1.12",
     "@types/json-schema": "^7.0.15",
     "@types/node": "^22.9.0",
-    "bunchee": "5.6.1",
+    "bunchee": "6.0.3",
     "llamaindex": "workspace:*",
-    "next": "15.0.2",
-    "rollup": "^4.24.4",
+    "next": "15.0.3",
+    "rollup": "^4.28.1",
     "tsx": "^4.19.0",
-    "typescript": "^5.6.3",
-    "vitest": "^2.1.4",
-    "webpack": "^5.94.0"
+    "typescript": "^5.7.2",
+    "vitest": "^2.1.5",
+    "webpack": "^5.97.1"
   }
 }

packages/autotool/src/internal/index.ts

@@ -22,7 +22,7 @@ export type InfoString = {
   parameterMapping: Record<string, number>;
 };
 
-export const store = createStore();
+export const store: ReturnType<typeof createStore> = createStore();
 export const toolMetadataAtom = atom<[ToolMetadata, Info][]>([]);
 // eslint-disable-next-line @typescript-eslint/no-explicit-any
 export const toolsAtom = atom<Record<string, (...args: any[]) => any>>({});

packages/cloud/CHANGELOG.md

@@ -1,5 +1,91 @@
 # @llamaindex/cloud
 
+## 2.0.19
+
+### Patch Changes
+
+- Updated dependencies [a9b5b99]
+  - @llamaindex/core@0.4.19
+
+## 2.0.18
+
+### Patch Changes
+
+- Updated dependencies [b504303]
+- Updated dependencies [e0f6cc3]
+  - @llamaindex/env@0.1.25
+  - @llamaindex/core@0.4.18
+
+## 2.0.17
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - @llamaindex/core@0.4.17
+
+## 2.0.16
+
+### Patch Changes
+
+- 8be4589: chore: bump version
+- Updated dependencies [8be4589]
+  - @llamaindex/core@0.4.16
+  - @llamaindex/env@0.1.24
+
+## 2.0.15
+
+### Patch Changes
+
+- Updated dependencies [d2b2722]
+  - @llamaindex/env@0.1.23
+  - @llamaindex/core@0.4.15
+
+## 2.0.14
+
+### Patch Changes
+
+- Updated dependencies [969365c]
+  - @llamaindex/env@0.1.22
+  - @llamaindex/core@0.4.14
+
+## 2.0.13
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+
+## 2.0.12
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+
+## 2.0.11
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+
+## 2.0.10
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+
+## 2.0.9
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
 ## 2.0.8
 
 ### Patch Changes

packages/cloud/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloud",
-  "version": "2.0.8",
+  "version": "2.0.19",
   "type": "module",
   "license": "MIT",
   "scripts": {
@@ -50,11 +50,11 @@
     "directory": "packages/cloud"
   },
   "devDependencies": {
-    "@hey-api/client-fetch": "^0.4.2",
-    "@hey-api/openapi-ts": "^0.54.3",
+    "@hey-api/client-fetch": "^0.4.4",
+    "@hey-api/openapi-ts": "^0.56.0",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
-    "bunchee": "5.6.1"
+    "bunchee": "6.0.3"
   },
   "peerDependencies": {
     "@llamaindex/core": "workspace:*",

packages/community/CHANGELOG.md

@@ -1,5 +1,93 @@
 # @llamaindex/community
 
+## 0.0.77
+
+### Patch Changes
+
+- 24caf93: fix: added inference profile mapping for nova models"
+- Updated dependencies [a9b5b99]
+  - @llamaindex/core@0.4.19
+
+## 0.0.76
+
+### Patch Changes
+
+- c1850ee: feat: Amazon Nova support via Bedrock
+- Updated dependencies [b504303]
+- Updated dependencies [e0f6cc3]
+  - @llamaindex/env@0.1.25
+  - @llamaindex/core@0.4.18
+
+## 0.0.75
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - @llamaindex/core@0.4.17
+
+## 0.0.74
+
+### Patch Changes
+
+- 8be4589: chore: bump version
+- Updated dependencies [8be4589]
+  - @llamaindex/core@0.4.16
+  - @llamaindex/env@0.1.24
+
+## 0.0.73
+
+### Patch Changes
+
+- Updated dependencies [d2b2722]
+  - @llamaindex/env@0.1.23
+  - @llamaindex/core@0.4.15
+
+## 0.0.72
+
+### Patch Changes
+
+- Updated dependencies [969365c]
+  - @llamaindex/env@0.1.22
+  - @llamaindex/core@0.4.14
+
+## 0.0.71
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+
+## 0.0.70
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+
+## 0.0.69
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+
+## 0.0.68
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+
+## 0.0.67
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
 ## 0.0.66
 
 ### Patch Changes

packages/community/README.md

@@ -4,6 +4,7 @@
 
 ## Current Features:
 
+- Bedrock support for Amazon Nova models Pro, Lite and Micro
 - Bedrock support for the Anthropic Claude Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock) including the latest Sonnet 3.5 v2 and Haiku 3.5
 - Bedrock support for the Meta LLama 2, 3, 3.1 and 3.2 Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock)
 - Meta LLama3.1 405b and Llama3.2 tool call support

packages/community/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.66",
+  "version": "0.0.77",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",
@@ -43,11 +43,11 @@
   },
   "devDependencies": {
     "@types/node": "^22.9.0",
-    "bunchee": "5.6.1"
+    "bunchee": "6.0.3"
   },
   "dependencies": {
-    "@aws-sdk/client-bedrock-agent-runtime": "^3.642.0",
-    "@aws-sdk/client-bedrock-runtime": "^3.642.0",
+    "@aws-sdk/client-bedrock-agent-runtime": "^3.706.0",
+    "@aws-sdk/client-bedrock-runtime": "^3.706.0",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*"
   }

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

@@ -0,0 +1,133 @@
+import type {
+  ContentBlockDelta,
+  ConverseOutput,
+  ConverseRequest,
+  ConverseResponse,
+  ConverseStreamOutput,
+  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 { Provider, type BedrockChatStreamResponse } from "../provider";
+import {
+  mapBaseToolsToAmazonTools,
+  mapChatMessagesToAmazonMessages,
+} from "./utils";
+
+export class AmazonProvider extends Provider<ConverseStreamOutput> {
+  getResultFromResponse(response: Record<string, any>): ConverseResponse {
+    return JSON.parse(toUtf8(response.body));
+  }
+
+  getToolsFromResponse<ToolContent>(response: ConverseOutput): ToolContent[] {
+    return (
+      response.message?.content
+        ?.filter((item) => item.toolUse)
+        .map(
+          (item) =>
+            ({
+              id: item.toolUse!.toolUseId,
+              name: item.toolUse!.name,
+              input: item.toolUse!.input
+                ? JSON.parse(item.toolUse!.input as string)
+                : "",
+            }) as ToolContent,
+        ) ?? []
+    );
+  }
+
+  getTextFromResponse(response: ConverseResponse): string {
+    const result = this.getResultFromResponse(response);
+    const content = result.output?.message?.content ?? [];
+    return content.map((item) => item.text).join(" ");
+  }
+
+  getTextFromStreamResponse(response: ResponseStream): string {
+    let event: ConverseStreamOutput | undefined =
+      this.getStreamingEventResponse(response);
+    if (!event || !event.contentBlockDelta) return "";
+    const delta: ContentBlockDelta | undefined = event.contentBlockDelta.delta;
+    return delta?.text || "";
+  }
+
+  async *reduceStream(
+    stream: AsyncIterable<ResponseStream>,
+  ): BedrockChatStreamResponse {
+    let toolId: string | undefined = undefined;
+    let toolName: string | undefined = undefined;
+    for await (const response of stream) {
+      const event = this.getStreamingEventResponse(response);
+      const delta = this.getTextFromStreamResponse(response);
+
+      let options: undefined | ToolCallLLMMessageOptions = undefined;
+      if (event?.contentBlockStart && event.contentBlockStart.start?.toolUse) {
+        toolId = event.contentBlockStart.start?.toolUse.toolUseId;
+        toolName = event.contentBlockStart.start?.toolUse.name;
+        continue;
+      }
+      if (
+        toolId &&
+        toolName &&
+        event?.contentBlockDelta?.delta?.toolUse?.input
+      ) {
+        options = {
+          toolCall: [
+            {
+              id: toolId,
+              name: toolName,
+              input: JSON.parse(event?.contentBlockDelta?.delta?.toolUse.input),
+            } as ToolCall,
+          ],
+        };
+        toolId = undefined;
+        toolName = undefined;
+      }
+
+      if (!delta && !options) continue;
+
+      yield {
+        delta: options ? "" : delta,
+        options,
+        raw: response,
+      };
+    }
+  }
+
+  getRequestBody<T extends ChatMessage>(
+    metadata: LLMMetadata,
+    messages: T[],
+    tools: BaseTool[] = [],
+    options: Omit<ConverseRequest, "modelId" | "messages" | "inferenceConfig">,
+  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
+    const request: Omit<ConverseRequest, "modelId"> = {
+      ...options,
+      messages: mapChatMessagesToAmazonMessages(messages),
+      inferenceConfig: {
+        maxTokens: metadata.maxTokens,
+        temperature: metadata.temperature,
+        topP: metadata.topP,
+      },
+    };
+    if (tools.length) {
+      request.toolConfig = {
+        tools: mapBaseToolsToAmazonTools(tools),
+      };
+    }
+
+    return {
+      modelId: metadata.model,
+      contentType: "application/json",
+      accept: "application/json",
+      body: JSON.stringify(request),
+    };
+  }
+}

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

@@ -0,0 +1,5 @@
+import type { ConverseRequest, Message } from "@aws-sdk/client-bedrock-runtime";
+
+export type AmazonMessages = ConverseRequest["messages"];
+
+export type AmazonMessage = Message;

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

@@ -0,0 +1,141 @@
+import type {
+  ImageBlock,
+  ImageFormat,
+  Message,
+  Tool,
+} from "@aws-sdk/client-bedrock-runtime";
+import type {
+  BaseTool,
+  ChatMessage,
+  MessageContentDetail,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import {
+  extractDataUrlComponents,
+  mapMessageContentToMessageContentDetails,
+} from "../utils";
+
+import type { JSONObject } from "@llamaindex/core/global";
+import type { AmazonMessage, AmazonMessages } from "./types";
+
+const ACCEPTED_IMAGE_MIME_TYPES = [
+  "image/jpeg",
+  "image/png",
+  "image/webp",
+  "image/gif",
+] as const;
+
+const ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP: Record<
+  (typeof ACCEPTED_IMAGE_MIME_TYPES)[number],
+  ImageFormat
+> = {
+  "image/jpeg": "jpeg",
+  "image/png": "png",
+  "image/webp": "webp",
+  "image/gif": "gif",
+};
+
+export const mapImageContent = (imageUrl: string): ImageBlock => {
+  if (!imageUrl.startsWith("data:"))
+    throw new Error(
+      "For Amazon 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 as keyof typeof ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP,
+    )
+  )
+    throw new Error(
+      `Amazon only accepts the following mimeTypes: ${ACCEPTED_IMAGE_MIME_TYPES.join("\n")}`,
+    );
+
+  return {
+    format:
+      ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP[
+        mimeType as keyof typeof ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP
+      ],
+
+    // @ts-ignore: there's a mistake in the "@aws-sdk/client-bedrock-runtime" compared to the actual api
+    source: { bytes: data },
+  };
+};
+
+export const mapMessageContentDetailToAmazonContent = <
+  T extends MessageContentDetail,
+>(
+  detail: T,
+): Message["content"] => {
+  let content: Message["content"] = [];
+
+  if (detail.type === "text") {
+    content = [{ text: detail.text }];
+  } else if (detail.type === "image_url") {
+    content = [{ image: mapImageContent(detail.image_url.url) }];
+  } else {
+    throw new Error("Unsupported content detail type");
+  }
+  return content;
+};
+
+export const mapChatMessagesToAmazonMessages = <
+  T extends ChatMessage<ToolCallLLMMessageOptions>,
+>(
+  messages: T[],
+): AmazonMessages => {
+  return messages.flatMap((msg: T): AmazonMessage[] => {
+    return mapMessageContentToMessageContentDetails(msg.content).map(
+      (detail: MessageContentDetail): AmazonMessage => {
+        if (msg.options && "toolCall" in msg.options) {
+          return {
+            role: "assistant",
+            content: msg.options.toolCall.map((call) => ({
+              toolUse: {
+                toolUseId: call.id,
+                name: call.name,
+                input: call.input as JSONObject,
+              },
+            })),
+          };
+        }
+        if (msg.options && "toolResult" in msg.options) {
+          return {
+            role: "user",
+            content: [
+              {
+                toolResult: {
+                  toolUseId: msg.options.toolResult.id,
+                  content: [
+                    {
+                      text: msg.options.toolResult.result,
+                    },
+                  ],
+                },
+              },
+            ],
+          };
+        }
+
+        return {
+          role: msg.role === "assistant" ? "assistant" : "user",
+          content: mapMessageContentDetailToAmazonContent(detail),
+        };
+      },
+    );
+  });
+};
+
+export const mapBaseToolsToAmazonTools = (tools?: BaseTool[]): Tool[] => {
+  if (!tools) return [];
+  return tools.map((tool: BaseTool) => {
+    const {
+      metadata: { parameters, ...options },
+    } = tool;
+    return {
+      toolSpec: {
+        ...options,
+        inputSchema: parameters,
+      },
+    } as Tool;
+  });
+};

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

@@ -11,13 +11,10 @@ import type {
   ToolCall,
   ToolCallLLMMessageOptions,
 } from "@llamaindex/core/llms";
-import {
-  type BedrockAdditionalChatOptions,
-  type BedrockChatStreamResponse,
-  Provider,
-} from "../provider";
+import { type BedrockChatStreamResponse, Provider } from "../provider";
 import { toUtf8 } from "../utils";
 import type {
+  AnthropicAdditionalChatOptions,
   AnthropicNoneStreamingResponse,
   AnthropicStreamEvent,
   AnthropicTextContent,
@@ -134,7 +131,7 @@ export class AnthropicProvider extends Provider<AnthropicStreamEvent> {
     metadata: LLMMetadata,
     messages: T[],
     tools?: BaseTool[],
-    options?: BedrockAdditionalChatOptions,
+    options?: AnthropicAdditionalChatOptions,
   ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
     const extra: Record<string, unknown> = {};
     if (options?.toolChoice) {

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

@@ -1,6 +1,13 @@
 import type { ToolMetadata } from "@llamaindex/core/llms";
 import type { InvocationMetrics } from "../types";
 
+export type ToolChoice =
+  | { type: "any" }
+  | { type: "auto" }
+  | { type: "tool"; name: string };
+
+export type AnthropicAdditionalChatOptions = { toolChoice: ToolChoice };
+
 type Usage = {
   input_tokens: number;
   output_tokens: number;

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

@@ -25,6 +25,7 @@ import {
 import { mapMessageContentToMessageContentDetails } from "./utils";
 
 import { wrapLLMEvent } from "@llamaindex/core/decorator";
+import { AmazonProvider } from "./amazon/provider";
 import { AnthropicProvider } from "./anthropic/provider";
 import { MetaProvider } from "./meta/provider";
 
@@ -32,6 +33,7 @@ import { MetaProvider } from "./meta/provider";
 export const PROVIDERS: { [key: string]: Provider } = {
   anthropic: new AnthropicProvider(),
   meta: new MetaProvider(),
+  amazon: new AmazonProvider(),
 };
 
 export type BedrockChatParamsStreaming = LLMChatParamsStreaming<
@@ -81,7 +83,11 @@ export const BEDROCK_MODELS = {
   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",
+  AMAZON_NOVA_PRO_1: "amazon.nova-pro-v1:0",
+  AMAZON_NOVA_LITE_1: "amazon.nova-lite-v1:0",
+  AMAZON_NOVA_MICRO_1: "amazon.nova-micro-v1:0",
 };
+
 export type BEDROCK_MODELS =
   (typeof BEDROCK_MODELS)[keyof typeof BEDROCK_MODELS];
 
@@ -98,6 +104,9 @@ export const INFERENCE_BEDROCK_MODELS = {
   US_META_LLAMA_3_2_3B_INSTRUCT: "us.meta.llama3-2-3b-instruct-v1:0",
   US_META_LLAMA_3_2_11B_INSTRUCT: "us.meta.llama3-2-11b-instruct-v1:0",
   US_META_LLAMA_3_2_90B_INSTRUCT: "us.meta.llama3-2-90b-instruct-v1:0",
+  US_AMAZON_NOVA_PRO_1: "us.amazon.nova-pro-v1:0",
+  US_AMAZON_NOVA_LITE_1: "us.amazon.nova-lite-v1:0",
+  US_AMAZON_NOVA_MICRO_1: "us.amazon.nova-micro-v1:0",
 
   EU_ANTHROPIC_CLAUDE_3_HAIKU: "eu.anthropic.claude-3-haiku-20240307-v1:0",
   EU_ANTHROPIC_CLAUDE_3_5_HAIKU: "eu.anthropic.claude-3-5-haiku-20240307-v1:0",
@@ -136,6 +145,13 @@ export const INFERENCE_TO_BEDROCK_MAP: Record<
   [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_90B_INSTRUCT]:
     BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT,
 
+  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_PRO_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
+  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_LITE_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
+  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_MICRO_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
+
   [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_HAIKU]:
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
   [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_SONNET]:
@@ -189,6 +205,9 @@ const CHAT_ONLY_MODELS = {
   [BEDROCK_MODELS.MISTRAL_7B_INSTRUCT]: 32000,
   [BEDROCK_MODELS.MISTRAL_MIXTRAL_7B_INSTRUCT]: 32000,
   [BEDROCK_MODELS.MISTRAL_MIXTRAL_LARGE_2402]: 32000,
+  [BEDROCK_MODELS.AMAZON_NOVA_PRO_1]: 300000,
+  [BEDROCK_MODELS.AMAZON_NOVA_LITE_1]: 300000,
+  [BEDROCK_MODELS.AMAZON_NOVA_MICRO_1]: 130000,
 };
 
 const BEDROCK_FOUNDATION_LLMS = { ...COMPLETION_MODELS, ...CHAT_ONLY_MODELS };
@@ -225,6 +244,9 @@ export const STREAMING_MODELS = new Set([
   BEDROCK_MODELS.MISTRAL_7B_INSTRUCT,
   BEDROCK_MODELS.MISTRAL_MIXTRAL_7B_INSTRUCT,
   BEDROCK_MODELS.MISTRAL_MIXTRAL_LARGE_2402,
+  BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
+  BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
+  BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
 ]);
 
 export const TOOL_CALL_MODELS: BEDROCK_MODELS[] = [
@@ -239,6 +261,9 @@ export const TOOL_CALL_MODELS: BEDROCK_MODELS[] = [
   BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
   BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT,
   BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT,
+  BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
+  BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
+  BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
 ];
 
 const getProvider = (model: string): Provider => {
@@ -320,10 +345,6 @@ export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
     this.temperature = temperature ?? DEFAULT_BEDROCK_PARAMS.temperature;
     this.topP = topP ?? DEFAULT_BEDROCK_PARAMS.topP;
     this.client = new BedrockRuntimeClient(params);
-
-    if (!this.supportToolCall) {
-      console.warn(`The model "${this.model}" doesn't support ToolCall`);
-    }
   }
 
   get supportToolCall(): boolean {
@@ -345,6 +366,9 @@ export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
   protected async nonStreamChat(
     params: BedrockChatParamsNonStreaming,
   ): Promise<BedrockChatNonStreamResponse> {
+    if (!this.supportToolCall && params.tools?.length) {
+      console.warn(`The model "${this.model}" doesn't support ToolCall`);
+    }
     const input = this.provider.getRequestBody(
       this.metadata,
       params.messages,
@@ -378,6 +402,10 @@ export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
     if (!STREAMING_MODELS.has(this.model))
       throw new Error(`The model: ${this.model} does not support streaming`);
 
+    if (!this.supportToolCall && params.tools?.length) {
+      console.warn(`The model "${this.model}" doesn't support ToolCall`);
+    }
+
     const input = this.provider.getRequestBody(
       this.metadata,
       params.messages,
@@ -388,7 +416,6 @@ export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
     command.input.modelId = this.actualModel;
 
     const response = await this.client.send(command);
-
     if (response.body) yield* this.provider.reduceStream(response.body);
   }
 

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

@@ -11,10 +11,9 @@ import {
   type ToolCallLLMMessageOptions,
 } from "@llamaindex/core/llms";
 import { streamConverter } from "@llamaindex/core/utils";
-import type { ToolChoice } from "./types";
 import { toUtf8 } from "./utils";
 
-export type BedrockAdditionalChatOptions = { toolChoice: ToolChoice };
+export type BedrockAdditionalChatOptions = Record<string, unknown>;
 
 export type BedrockChatStreamResponse = AsyncIterable<
   ChatResponseChunk<ToolCallLLMMessageOptions>

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

@@ -4,8 +4,3 @@ export type InvocationMetrics = {
   invocationLatency: number;
   firstByteLatency: number;
 };
-
-export type ToolChoice =
-  | { type: "any" }
-  | { type: "auto" }
-  | { type: "tool"; name: string };

packages/core/CHANGELOG.md

@@ -1,5 +1,80 @@
 # @llamaindex/core
 
+## 0.4.19
+
+### Patch Changes
+
+- a9b5b99: feat: build api reference pages for new documentation site
+
+## 0.4.18
+
+### Patch Changes
+
+- e0f6cc3: The compact and refine response synthesizer (retrieved by using `getResponseSynthesizer('compact')`) has been fixed to return the original source nodes that were provided to it in its response. Previous to this it was returning the compacted text chunk documents.
+- Updated dependencies [b504303]
+  - @llamaindex/env@0.1.25
+
+## 0.4.17
+
+### Patch Changes
+
+- 3d1808b: chore: bump version
+
+## 0.4.16
+
+### Patch Changes
+
+- 8be4589: chore: bump version
+- Updated dependencies [8be4589]
+  - @llamaindex/env@0.1.24
+
+## 0.4.15
+
+### Patch Changes
+
+- Updated dependencies [d2b2722]
+  - @llamaindex/env@0.1.23
+
+## 0.4.14
+
+### Patch Changes
+
+- Updated dependencies [969365c]
+  - @llamaindex/env@0.1.22
+
+## 0.4.13
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/env@0.1.21
+
+## 0.4.12
+
+### Patch Changes
+
+- ef4f63d: refactor: move mockLLM to core
+
+## 0.4.11
+
+### Patch Changes
+
+- 6d22fa2: Get PromptTemplate template variables at run-time
+
+## 0.4.10
+
+### Patch Changes
+
+- a7b0ac3: fix: update tool call llm type
+- c69605f: feat: add async support to BaseChatStore and BaseChatStoreMemory
+
+## 0.4.9
+
+### Patch Changes
+
+- 7ae6eaa: feat: allow pass `additionalChatOptions` to agent
+
 ## 0.4.8
 
 ### Patch Changes

packages/core/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.4.8",
+  "version": "0.4.19",
   "description": "LlamaIndex Core Module",
   "exports": {
     "./agent": {
@@ -389,10 +389,10 @@
     "url": "https://github.com/run-llama/LlamaIndexTS.git"
   },
   "devDependencies": {
-    "@edge-runtime/vm": "^4.0.3",
+    "@edge-runtime/vm": "^4.0.4",
     "ajv": "^8.17.1",
-    "bunchee": "5.6.1",
-    "happy-dom": "^15.11.0",
+    "bunchee": "6.0.3",
+    "happy-dom": "^15.11.6",
     "natural": "^8.0.1"
   },
   "dependencies": {

packages/core/src/agent/base.ts

@@ -106,11 +106,17 @@ export type AgentRunnerParams<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > = {
   llm: AI;
   chatHistory: ChatMessage<AdditionalMessageOptions>[];
   systemPrompt: MessageContent | null;
-  runner: AgentWorker<AI, Store, AdditionalMessageOptions>;
+  runner: AgentWorker<
+    AI,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
   tools:
     | BaseToolWithCall[]
     | ((query: MessageContent) => Promise<BaseToolWithCall[]>);
@@ -125,6 +131,7 @@ export type AgentParamsBase<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > =
   | {
       llm?: AI;
@@ -132,6 +139,7 @@ export type AgentParamsBase<
       systemPrompt?: MessageContent;
       verbose?: boolean;
       tools: BaseToolWithCall[];
+      additionalChatOptions?: AdditionalChatOptions;
     }
   | {
       llm?: AI;
@@ -139,6 +147,7 @@ export type AgentParamsBase<
       systemPrompt?: MessageContent;
       verbose?: boolean;
       toolRetriever: ObjectRetriever<BaseToolWithCall>;
+      additionalChatOptions?: AdditionalChatOptions;
     };
 
 /**
@@ -153,21 +162,36 @@ export abstract class AgentWorker<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > {
-  #taskSet = new Set<TaskStep<AI, Store, AdditionalMessageOptions>>();
-  abstract taskHandler: TaskHandler<AI, Store, AdditionalMessageOptions>;
+  #taskSet = new Set<
+    TaskStep<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
+  >();
+  abstract taskHandler: TaskHandler<
+    AI,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
 
   public createTask(
     query: MessageContent,
-    context: AgentTaskContext<AI, Store, AdditionalMessageOptions>,
-  ): ReadableStream<TaskStepOutput<AI, Store, AdditionalMessageOptions>> {
+    context: AgentTaskContext<
+      AI,
+      Store,
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >,
+  ): ReadableStream<
+    TaskStepOutput<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
+  > {
     context.store.messages.push({
       role: "user",
       content: query,
     });
     const taskOutputStream = createTaskOutputStream(this.taskHandler, context);
     return new ReadableStream<
-      TaskStepOutput<AI, Store, AdditionalMessageOptions>
+      TaskStepOutput<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
     >({
       start: async (controller) => {
         for await (const stepOutput of taskOutputStream) {
@@ -176,7 +200,8 @@ export abstract class AgentWorker<
             let currentStep: TaskStep<
               AI,
               Store,
-              AdditionalMessageOptions
+              AdditionalMessageOptions,
+              AdditionalChatOptions
             > | null = stepOutput.taskStep;
             while (currentStep) {
               this.#taskSet.delete(currentStep);
@@ -227,6 +252,7 @@ export abstract class AgentRunner<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > extends BaseChatEngine {
   readonly #llm: AI;
   readonly #tools:
@@ -234,7 +260,12 @@ export abstract class AgentRunner<
     | ((query: MessageContent) => Promise<BaseToolWithCall[]>);
   readonly #systemPrompt: MessageContent | null = null;
   #chatHistory: ChatMessage<AdditionalMessageOptions>[];
-  readonly #runner: AgentWorker<AI, Store, AdditionalMessageOptions>;
+  readonly #runner: AgentWorker<
+    AI,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
   readonly #verbose: boolean;
 
   // create extra store
@@ -245,7 +276,7 @@ export abstract class AgentRunner<
   }
 
   static defaultTaskHandler: TaskHandler<LLM> = async (step, enqueueOutput) => {
-    const { llm, getTools, stream } = step.context;
+    const { llm, getTools, stream, additionalChatOptions } = step.context;
     const lastMessage = step.context.store.messages.at(-1)!.content;
     const tools = await getTools(lastMessage);
     if (!stream) {
@@ -253,8 +284,9 @@ export abstract class AgentRunner<
         stream,
         tools,
         messages: [...step.context.store.messages],
+        additionalChatOptions,
       });
-      await stepTools<LLM>({
+      await stepTools({
         response,
         tools,
         step,
@@ -265,6 +297,7 @@ export abstract class AgentRunner<
         stream,
         tools,
         messages: [...step.context.store.messages],
+        additionalChatOptions,
       });
       await stepToolsStreaming<LLM>({
         response,
@@ -276,7 +309,12 @@ export abstract class AgentRunner<
   };
 
   protected constructor(
-    params: AgentRunnerParams<AI, Store, AdditionalMessageOptions>,
+    params: AgentRunnerParams<
+      AI,
+      Store,
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >,
   ) {
     super();
     const { llm, chatHistory, systemPrompt, runner, tools, verbose } = params;
@@ -330,7 +368,10 @@ export abstract class AgentRunner<
     stream: boolean = false,
     verbose: boolean | undefined = undefined,
     chatHistory?: ChatMessage<AdditionalMessageOptions>[],
-  ) {
+    additionalChatOptions?: AdditionalChatOptions,
+  ): ReadableStream<
+    TaskStepOutput<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
+  > {
     const initialMessages = [...(chatHistory ?? this.#chatHistory)];
     if (this.#systemPrompt !== null) {
       const systemPrompt = this.#systemPrompt;
@@ -348,6 +389,7 @@ export abstract class AgentRunner<
       stream,
       toolCallCount: 0,
       llm: this.#llm,
+      additionalChatOptions: additionalChatOptions ?? {},
       getTools: (message) => this.getTools(message),
       store: {
         ...this.createStore(),
@@ -365,13 +407,29 @@ export abstract class AgentRunner<
     });
   }
 
-  async chat(params: NonStreamingChatEngineParams): Promise<EngineResponse>;
   async chat(
-    params: StreamingChatEngineParams,
+    params: NonStreamingChatEngineParams<
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >,
+  ): Promise<EngineResponse>;
+  async chat(
+    params: StreamingChatEngineParams<
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >,
   ): Promise<ReadableStream<EngineResponse>>;
   @wrapEventCaller
   async chat(
-    params: NonStreamingChatEngineParams | StreamingChatEngineParams,
+    params:
+      | NonStreamingChatEngineParams<
+          AdditionalMessageOptions,
+          AdditionalChatOptions
+        >
+      | StreamingChatEngineParams<
+          AdditionalMessageOptions,
+          AdditionalChatOptions
+        >,
   ): Promise<EngineResponse | ReadableStream<EngineResponse>> {
     let chatHistory: ChatMessage<AdditionalMessageOptions>[] = [];
 
@@ -388,6 +446,7 @@ export abstract class AgentRunner<
       !!params.stream,
       false,
       chatHistory,
+      params.chatOptions,
     );
     for await (const stepOutput of task) {
       // update chat history for each round
@@ -396,14 +455,9 @@ export abstract class AgentRunner<
         const { output } = stepOutput;
         if (output instanceof ReadableStream) {
           return output.pipeThrough(
-            new TransformStream<EngineResponse>({
+            new TransformStream({
               transform(chunk, controller) {
-                controller.enqueue(
-                  EngineResponse.fromChatResponseChunk(
-                    chunk,
-                    chunk.sourceNodes,
-                  ),
-                );
+                controller.enqueue(EngineResponse.fromChatResponseChunk(chunk));
               },
             }),
           );

packages/core/src/agent/llm.ts

@@ -4,24 +4,66 @@ import { ObjectRetriever } from "../objects";
 import { AgentRunner, AgentWorker, type AgentParamsBase } from "./base.js";
 import { validateAgentParams } from "./utils.js";
 
-type LLMParamsBase = AgentParamsBase<LLM>;
+type LLMParamsBase<
+  AI extends LLM,
+  AdditionalMessageOptions extends object = AI extends LLM<
+    object,
+    infer AdditionalMessageOptions
+  >
+    ? AdditionalMessageOptions
+    : never,
+  AdditionalChatOptions extends object = object,
+> = AgentParamsBase<AI, AdditionalMessageOptions, AdditionalChatOptions>;
 
-type LLMParamsWithTools = LLMParamsBase & {
+type LLMParamsWithTools<
+  AI extends LLM,
+  AdditionalMessageOptions extends object = AI extends LLM<
+    object,
+    infer AdditionalMessageOptions
+  >
+    ? AdditionalMessageOptions
+    : never,
+  AdditionalChatOptions extends object = object,
+> = LLMParamsBase<AI, AdditionalMessageOptions, AdditionalChatOptions> & {
   tools: BaseToolWithCall[];
 };
 
-type LLMParamsWithToolRetriever = LLMParamsBase & {
+type LLMParamsWithToolRetriever<
+  AI extends LLM,
+  AdditionalMessageOptions extends object = AI extends LLM<
+    object,
+    infer AdditionalMessageOptions
+  >
+    ? AdditionalMessageOptions
+    : never,
+  AdditionalChatOptions extends object = object,
+> = LLMParamsBase<AI, AdditionalMessageOptions, AdditionalChatOptions> & {
   toolRetriever: ObjectRetriever<BaseToolWithCall>;
 };
 
-export type LLMAgentParams = LLMParamsWithTools | LLMParamsWithToolRetriever;
+export type LLMAgentParams<
+  AI extends LLM,
+  AdditionalMessageOptions extends object = AI extends LLM<
+    object,
+    infer AdditionalMessageOptions
+  >
+    ? AdditionalMessageOptions
+    : never,
+  AdditionalChatOptions extends object = object,
+> =
+  | LLMParamsWithTools<AI, AdditionalMessageOptions, AdditionalChatOptions>
+  | LLMParamsWithToolRetriever<
+      AI,
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >;
 
 export class LLMAgentWorker extends AgentWorker<LLM> {
   taskHandler = AgentRunner.defaultTaskHandler;
 }
 
 export class LLMAgent extends AgentRunner<LLM> {
-  constructor(params: LLMAgentParams) {
+  constructor(params: LLMAgentParams<LLM>) {
     validateAgentParams(params);
     const llm = params.llm ?? (Settings.llm ? (Settings.llm as LLM) : null);
     if (!llm)

packages/core/src/agent/types.ts

@@ -19,6 +19,7 @@ export type AgentTaskContext<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > = {
   readonly stream: boolean;
   readonly toolCallCount: number;
@@ -26,6 +27,7 @@ export type AgentTaskContext<
   readonly getTools: (
     input: MessageContent,
   ) => BaseToolWithCall[] | Promise<BaseToolWithCall[]>;
+  readonly additionalChatOptions: Partial<AdditionalChatOptions>;
   shouldContinue: (
     taskStep: Readonly<TaskStep<Model, Store, AdditionalMessageOptions>>,
   ) => boolean;
@@ -45,13 +47,26 @@ export type TaskStep<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > = {
   id: UUID;
-  context: AgentTaskContext<Model, Store, AdditionalMessageOptions>;
+  context: AgentTaskContext<
+    Model,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
 
   // linked list
-  prevStep: TaskStep<Model, Store, AdditionalMessageOptions> | null;
-  nextSteps: Set<TaskStep<Model, Store, AdditionalMessageOptions>>;
+  prevStep: TaskStep<
+    Model,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  > | null;
+  nextSteps: Set<
+    TaskStep<Model, Store, AdditionalMessageOptions, AdditionalChatOptions>
+  >;
 };
 
 export type TaskStepOutput<
@@ -63,8 +78,14 @@ export type TaskStepOutput<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > = {
-  taskStep: TaskStep<Model, Store, AdditionalMessageOptions>;
+  taskStep: TaskStep<
+    Model,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
   // output shows the response to the user
   output:
     | ChatResponse<AdditionalMessageOptions>
@@ -81,10 +102,16 @@ export type TaskHandler<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > = (
-  step: TaskStep<Model, Store, AdditionalMessageOptions>,
+  step: TaskStep<Model, Store, AdditionalMessageOptions, AdditionalChatOptions>,
   enqueueOutput: (
-    taskOutput: TaskStepOutput<Model, Store, AdditionalMessageOptions>,
+    taskOutput: TaskStepOutput<
+      Model,
+      Store,
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >,
   ) => void,
 ) => Promise<void>;
 

packages/core/src/chat-engine/base.ts

@@ -16,14 +16,18 @@ export interface BaseChatEngineParams<
 
 export interface StreamingChatEngineParams<
   AdditionalMessageOptions extends object = object,
+  AdditionalChatOptions extends object = object,
 > extends BaseChatEngineParams<AdditionalMessageOptions> {
   stream: true;
+  chatOptions?: AdditionalChatOptions;
 }
 
 export interface NonStreamingChatEngineParams<
   AdditionalMessageOptions extends object = object,
+  AdditionalChatOptions extends object = object,
 > extends BaseChatEngineParams<AdditionalMessageOptions> {
   stream?: false;
+  chatOptions?: AdditionalChatOptions;
 }
 
 export abstract class BaseChatEngine {

packages/core/src/chat-engine/context-chat-engine.ts

@@ -22,7 +22,8 @@ import type { ContextGenerator } from "./type";
 
 /**
  * ContextChatEngine uses the Index to get the appropriate context for each query.
- * The context is stored in the system prompt, and the chat history is chunk: ChatResponseChunk, nodes?: NodeWithScore<import("/Users/marcus/code/llamaindex/LlamaIndexTS/packages/core/src/Node").Metadata>[], nodes?: NodeWithScore<import("/Users/marcus/code/llamaindex/LlamaIndexTS/packages/core/src/Node").Metadata>[]lowing the appropriate context to be surfaced for each query.
+ * The context is stored in the system prompt, and the chat history is chunk,
+ * allowing the appropriate context to be surfaced for each query.
  */
 export class ContextChatEngine extends PromptMixin implements BaseChatEngine {
   chatModel: LLM;

packages/core/src/llms/base.ts

@@ -66,6 +66,8 @@ export abstract class BaseLLM<
 
 export abstract class ToolCallLLM<
   AdditionalChatOptions extends object = object,
-> extends BaseLLM<AdditionalChatOptions, ToolCallLLMMessageOptions> {
+  AdditionalMessageOptions extends
+    ToolCallLLMMessageOptions = ToolCallLLMMessageOptions,
+> extends BaseLLM<AdditionalChatOptions, AdditionalMessageOptions> {
   abstract supportToolCall: boolean;
 }

packages/core/src/memory/base.ts

@@ -71,15 +71,15 @@ export abstract class BaseChatStoreMemory<
     return this.chatStore.getMessages(this.chatStoreKey);
   }
 
-  put(messages: ChatMessage<AdditionalMessageOptions>) {
+  put(messages: ChatMessage<AdditionalMessageOptions>): void | Promise<void> {
     this.chatStore.addMessage(this.chatStoreKey, messages);
   }
 
-  set(messages: ChatMessage<AdditionalMessageOptions>[]) {
+  set(messages: ChatMessage<AdditionalMessageOptions>[]): void | Promise<void> {
     this.chatStore.setMessages(this.chatStoreKey, messages);
   }
 
-  reset() {
+  reset(): void | Promise<void> {
     this.chatStore.deleteMessages(this.chatStoreKey);
   }
 }

packages/core/src/prompts/base.ts

@@ -32,6 +32,10 @@ export abstract class BasePromptTemplate<
   const Vars extends readonly string[] = string[],
 > {
   metadata: Metadata = {};
+  /**
+   * Set of template variables used in the prompt template. Used for type hints only.
+   * To get the list of template variables used in the prompt at run-time, use the `vars` method.
+   */
   templateVars: Set<string> = new Set();
   options: Partial<Record<TemplatesVar[number] | (string & {}), string>> = {};
   outputParser: BaseOutputParser | undefined;
@@ -223,4 +227,13 @@ export class PromptTemplate<
   get template(): Template {
     return this.#template;
   }
+
+  /**
+   * Returns all the template variables used in the prompt template.
+   */
+  vars(): string[] {
+    const template = this.template;
+    const matches = template.match(/\{([^}]+)\}/g) || [];
+    return [...new Set(matches.map((match) => match.slice(1, -1)))];
+  }
 }

packages/core/src/response-synthesizers/factory.ts

@@ -77,6 +77,16 @@ class Refine extends BaseSynthesizer {
     }
   }
 
+  async getResponse(
+    query: MessageContent,
+    nodes: NodeWithScore[],
+    stream: true,
+  ): Promise<AsyncIterable<EngineResponse>>;
+  async getResponse(
+    query: MessageContent,
+    nodes: NodeWithScore[],
+    stream: false,
+  ): Promise<EngineResponse>;
   async getResponse(
     query: MessageContent,
     nodes: NodeWithScore[],
@@ -197,6 +207,16 @@ class Refine extends BaseSynthesizer {
  * CompactAndRefine is a slight variation of Refine that first compacts the text chunks into the smallest possible number of chunks.
  */
 class CompactAndRefine extends Refine {
+  async getResponse(
+    query: MessageContent,
+    nodes: NodeWithScore[],
+    stream: true,
+  ): Promise<AsyncIterable<EngineResponse>>;
+  async getResponse(
+    query: MessageContent,
+    nodes: NodeWithScore[],
+    stream: false,
+  ): Promise<EngineResponse>;
   async getResponse(
     query: MessageContent,
     nodes: NodeWithScore[],
@@ -216,17 +236,24 @@ class CompactAndRefine extends Refine {
     const newTexts = this.promptHelper.repack(maxPrompt, textChunks);
     const newNodes = newTexts.map((text) => new TextNode({ text }));
     if (stream) {
-      return super.getResponse(
+      const streamResponse = await super.getResponse(
         query,
         newNodes.map((node) => ({ node })),
         true,
       );
+      return streamConverter(streamResponse, (chunk) => {
+        chunk.sourceNodes = nodes;
+        return chunk;
+      });
     }
-    return super.getResponse(
+
+    const originalResponse = await super.getResponse(
       query,
       newNodes.map((node) => ({ node })),
       false,
     );
+    originalResponse.sourceNodes = nodes;
+    return originalResponse;
   }
 }
 

packages/core/src/storage/chat-store/base-chat-store.ts

@@ -19,5 +19,7 @@ export abstract class BaseChatStore<
   ): void;
   abstract deleteMessages(key: string): void;
   abstract deleteMessage(key: string, idx: number): void;
-  abstract getKeys(): IterableIterator<string>;
+  abstract getKeys():
+    | IterableIterator<string>
+    | Promise<IterableIterator<string>>;
 }

packages/core/src/utils/index.ts

@@ -76,6 +76,7 @@ export {
   extractText,
   imageToDataUrl,
   messagesToHistory,
+  MockLLM,
   toToolDescriptions,
 } from "./llms";
 

packages/core/src/utils/llms.ts

@@ -2,6 +2,15 @@ import { fs } from "@llamaindex/env";
 import { filetypemime } from "magic-bytes.js";
 import type {
   ChatMessage,
+  ChatResponse,
+  ChatResponseChunk,
+  CompletionResponse,
+  LLM,
+  LLMChatParamsNonStreaming,
+  LLMChatParamsStreaming,
+  LLMCompletionParamsNonStreaming,
+  LLMCompletionParamsStreaming,
+  LLMMetadata,
   MessageContent,
   MessageContentDetail,
   MessageContentTextDetail,
@@ -143,3 +152,82 @@ export async function imageToDataUrl(
   }
   return await blobToDataUrl(input);
 }
+
+export class MockLLM implements LLM {
+  metadata: LLMMetadata;
+  options: {
+    timeBetweenToken: number;
+    responseMessage: string;
+  };
+
+  constructor(options?: {
+    timeBetweenToken?: number;
+    responseMessage?: string;
+    metadata?: LLMMetadata;
+  }) {
+    this.options = {
+      timeBetweenToken: options?.timeBetweenToken ?? 20,
+      responseMessage: options?.responseMessage ?? "This is a mock response",
+    };
+    this.metadata = options?.metadata ?? {
+      model: "MockLLM",
+      temperature: 0.5,
+      topP: 0.5,
+      contextWindow: 1024,
+      tokenizer: undefined,
+    };
+  }
+
+  chat(
+    params: LLMChatParamsStreaming<object, object>,
+  ): Promise<AsyncIterable<ChatResponseChunk>>;
+  chat(
+    params: LLMChatParamsNonStreaming<object, object>,
+  ): Promise<ChatResponse<object>>;
+  async chat(
+    params:
+      | LLMChatParamsStreaming<object, object>
+      | LLMChatParamsNonStreaming<object, object>,
+  ): Promise<AsyncIterable<ChatResponseChunk> | ChatResponse<object>> {
+    const responseMessage = this.options.responseMessage;
+    const timeBetweenToken = this.options.timeBetweenToken;
+
+    if (params.stream) {
+      return (async function* () {
+        for (const char of responseMessage) {
+          yield { delta: char, raw: {} };
+          await new Promise((resolve) => setTimeout(resolve, timeBetweenToken));
+        }
+      })();
+    }
+
+    return {
+      message: { content: responseMessage, role: "assistant" },
+      raw: {},
+    };
+  }
+
+  async complete(
+    params: LLMCompletionParamsStreaming,
+  ): Promise<AsyncIterable<CompletionResponse>>;
+  async complete(
+    params: LLMCompletionParamsNonStreaming,
+  ): Promise<CompletionResponse>;
+  async complete(
+    params: LLMCompletionParamsStreaming | LLMCompletionParamsNonStreaming,
+  ): Promise<AsyncIterable<CompletionResponse> | CompletionResponse> {
+    const responseMessage = this.options.responseMessage;
+    const timeBetweenToken = this.options.timeBetweenToken;
+
+    if (params.stream) {
+      return (async function* () {
+        for (const char of responseMessage) {
+          yield { delta: char, text: char, raw: {} };
+          await new Promise((resolve) => setTimeout(resolve, timeBetweenToken));
+        }
+      })();
+    }
+
+    return { text: responseMessage, raw: {} };
+  }
+}

packages/core/tests/package.json

@@ -7,6 +7,6 @@
   },
   "devDependencies": {
     "@llamaindex/core": "workspace:*",
-    "vitest": "^2.1.4"
+    "vitest": "^2.1.5"
   }
 }

packages/core/tests/prompts.test.ts

@@ -158,4 +158,15 @@ describe("PromptTemplate", () => {
     const formatted = prompt.format({ text: "world", foo: "bar" });
     expect(formatted).toBe("hello world bar\noutput_instruction");
   });
+
+  test("should return all unique template vars of a prompt", () => {
+    const prompt = new PromptTemplate({
+      template: "Hello {name}! Your age is {age}. Nice to meet you {name}!",
+    });
+
+    const vars = prompt.vars();
+    expect(vars).toHaveLength(2);
+    expect(vars).toContain("name");
+    expect(vars).toContain("age");
+  });
 });

packages/core/tests/response-synthesizers/compact-and-refine.test.ts

@@ -0,0 +1,66 @@
+import { describe, expect, test, vi } from "vitest";
+import type { LLMMetadata } from "../../llms/dist/index.js";
+import { getResponseSynthesizer } from "../../response-synthesizers/dist/index.js";
+import { Document } from "../../schema/dist/index.js";
+
+const mockLllm = () => ({
+  complete: vi.fn().mockImplementation(({ stream }) => {
+    const response = { text: "unimportant" };
+    if (!stream) {
+      return response;
+    }
+
+    function* gen() {
+      // yield a few times to make sure each chunk has the sourceNodes
+      yield response;
+      yield response;
+      yield response;
+    }
+
+    return gen();
+  }),
+  chat: vi.fn(),
+  metadata: {} as unknown as LLMMetadata,
+});
+
+describe("compact and refine response synthesizer", () => {
+  describe("synthesize", () => {
+    test("should return original sourceNodes with response when stream = false", async () => {
+      const synthesizer = getResponseSynthesizer("compact", {
+        llm: mockLllm(),
+      });
+
+      const sourceNode = { node: new Document({}), score: 1 };
+
+      const response = await synthesizer.synthesize(
+        {
+          query: "test",
+          nodes: [sourceNode],
+        },
+        false,
+      );
+
+      expect(response.sourceNodes).toEqual([sourceNode]);
+    });
+
+    test("should return original sourceNodes with response when stream = true", async () => {
+      const synthesizer = getResponseSynthesizer("compact", {
+        llm: mockLllm(),
+      });
+
+      const sourceNode = { node: new Document({}), score: 1 };
+
+      const response = await synthesizer.synthesize(
+        {
+          query: "test",
+          nodes: [sourceNode],
+        },
+        true,
+      );
+
+      for await (const chunk of response) {
+        expect(chunk.sourceNodes).toEqual([sourceNode]);
+      }
+    });
+  });
+});