Release 0.8.19 (#1507)

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

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 +1,65 @@
 # docs
 
+## 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/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": "0.0.124",
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",
@@ -15,23 +15,23 @@
     "typecheck": "tsc"
   },
   "dependencies": {
-    "@docusaurus/core": "3.6.0",
+    "@docusaurus/core": "3.6.1",
-    "@docusaurus/remark-plugin-npm2yarn": "3.6.0",
+    "@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/module-type-aliases": "3.6.1",
-    "@docusaurus/preset-classic": "3.6.0",
+    "@docusaurus/preset-classic": "3.6.1",
-    "@docusaurus/theme-classic": "3.6.0",
+    "@docusaurus/theme-classic": "3.6.1",
-    "@docusaurus/types": "3.6.0",
+    "@docusaurus/types": "3.6.1",
     "@tsconfig/docusaurus": "2.0.3",
     "@types/node": "^22.9.0",
     "docusaurus-plugin-typedoc": "1.0.5",

apps/next/CHANGELOG.md

@@ -1,5 +1,100 @@
 # @llamaindex/doc
 
+## 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": "0.0.22",
   "private": true,
   "scripts": {
     "build": "pnpm run build:docs && next build",
@@ -12,7 +12,7 @@
   },
   "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",
+    "foxact": "^0.2.41",
-    "framer-motion": "^11.11.11",
+    "framer-motion": "^11.11.17",
-    "fumadocs-core": "14.2.0",
+    "fumadocs-core": "14.4.2",
-    "fumadocs-docgen": "^1.3.1",
+    "fumadocs-docgen": "^1.3.2",
     "fumadocs-mdx": "^11.1.1",
-    "fumadocs-openapi": "^5.5.6",
+    "fumadocs-openapi": "^5.7.0",
     "fumadocs-twoslash": "^2.0.1",
-    "fumadocs-typescript": "^3.0.1",
+    "fumadocs-typescript": "^3.0.2",
-    "fumadocs-ui": "14.2.0",
+    "fumadocs-ui": "14.4.2",
     "hast-util-to-jsx-runtime": "^2.3.2",
     "llamaindex": "workspace:*",
-    "lucide-react": "^0.454.0",
+    "lucide-react": "^0.460.0",
-    "next": "15.0.2",
+    "next": "15.0.3",
-    "next-themes": "^0.3.0",
+    "next-themes": "^0.4.3",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-icons": "^5.3.0",
@@ -54,19 +54,19 @@
     "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": "^0.22.1",
-    "tree-sitter-typescript": "^0.23.0",
+    "tree-sitter-typescript": "^0.23.2",
-    "use-stick-to-bottom": "^1.0.41",
+    "use-stick-to-bottom": "^1.0.42",
-    "web-tree-sitter": "^0.24.3",
+    "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",
@@ -75,12 +75,12 @@
     "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"
   }

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/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 
+title: Using API Route
-description: Use chat-ui to add a chat interface to your LlamaIndexTS application.
+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.
+

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

@@ -1,5 +1,58 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 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": "0.0.115",
   "type": "module",
   "private": true,
   "scripts": {
@@ -12,13 +12,13 @@
     "cf-typegen": "wrangler types"
   },
   "devDependencies": {
-    "@cloudflare/vitest-pool-workers": "^0.5.8",
+    "@cloudflare/vitest-pool-workers": "^0.5.28",
-    "@cloudflare/workers-types": "^4.20240924.0",
+    "@cloudflare/workers-types": "^4.20241112.0",
-    "@vitest/runner": "2.1.4",
+    "@vitest/runner": "2.1.5",
-    "@vitest/snapshot": "2.1.4",
+    "@vitest/snapshot": "2.1.5",
     "typescript": "^5.6.3",
-    "vitest": "2.1.4",
+    "vitest": "2.1.5",
-    "wrangler": "^3.78.8"
+    "wrangler": "^3.87.0"
   },
   "dependencies": {
     "llamaindex": "workspace:*"

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

@@ -1,5 +1,36 @@
 # @llamaindex/llama-parse-browser-test
 
+## 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": "0.0.33",
   "type": "module",
   "scripts": {
     "dev": "vite",
@@ -10,7 +10,7 @@
   },
   "devDependencies": {
     "typescript": "^5.6.3",
-    "vite": "^5.4.1",
+    "vite": "^5.4.11",
     "vite-plugin-wasm": "^3.3.0"
   },
   "dependencies": {

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,58 @@
 # @llamaindex/next-agent-test
 
+## 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": "0.1.115",
   "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": "9.15.0",
-    "eslint-config-next": "15.0.2",
+    "eslint-config-next": "15.0.3",
-    "postcss": "^8.4.41",
+    "postcss": "^8.4.49",
-    "tailwindcss": "^3.4.10",
+    "tailwindcss": "^3.4.15",
     "typescript": "^5.6.3"
   }
 }

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

@@ -1,5 +1,58 @@
 # test-edge-runtime
 
+## 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": "0.1.114",
   "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"
   },

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

@@ -1,5 +1,58 @@
 # @llamaindex/next-node-runtime
 
+## 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": "0.0.96",
   "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": "9.15.0",
-    "eslint-config-next": "15.0.2",
+    "eslint-config-next": "15.0.3",
-    "postcss": "^8.4.41",
+    "postcss": "^8.4.49",
-    "tailwindcss": "^3.4.10",
+    "tailwindcss": "^3.4.15",
     "typescript": "^5.6.3"
   }
 }

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

@@ -1,5 +1,58 @@
 # @llamaindex/waku-query-engine-test
 
+## 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": "0.0.115",
   "type": "module",
   "private": true,
   "scripts": {
@@ -10,16 +10,16 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "react": "19.0.0-rc-bf7e210c-20241017",
+    "react": "19.0.0-rc-5c56b873-20241107",
-    "react-dom": "19.0.0-rc-bf7e210c-20241017",
+    "react-dom": "19.0.0-rc-5c56b873-20241107",
-    "react-server-dom-webpack": "19.0.0-rc-bf7e210c-20241017",
+    "react-server-dom-webpack": "19.0.0-rc-5c56b873-20241107",
-    "waku": "0.21.4"
+    "waku": "0.21.6"
   },
   "devDependencies": {
     "@types/react": "18.3.12",
     "@types/react-dom": "18.3.1",
     "autoprefixer": "^10.4.20",
-    "tailwindcss": "^3.4.14",
+    "tailwindcss": "^3.4.15",
     "typescript": "5.6.3"
   }
 }

examples/CHANGELOG.md

@@ -1,5 +1,25 @@
 # examples
 
+## 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/package.json

@@ -1,24 +1,24 @@
 {
   "name": "@llamaindex/examples",
   "private": true,
-  "version": "0.0.14",
+  "version": "0.0.16",
   "dependencies": {
     "@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/core": "^0.4.10",
-    "@llamaindex/readers": "^1.0.8",
+    "@llamaindex/readers": "^1.0.11",
-    "@llamaindex/workflow": "^0.0.4",
+    "@llamaindex/workflow": "^0.0.6",
     "@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",
     "chromadb": "^1.8.1",
     "commander": "^12.1.0",
     "dotenv": "^16.4.5",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.8.10",
+    "llamaindex": "^0.8.13",
     "mongodb": "^6.7.0",
     "pathe": "^1.1.2",
     "postgres": "^3.4.4"

package.json

@@ -19,20 +19,20 @@
   },
   "devDependencies": {
     "@changesets/cli": "^2.27.5",
-    "eslint": "9.14.0",
+    "eslint": "9.15.0",
-    "eslint-config-next": "^15.0.2",
+    "eslint-config-next": "^15.0.3",
     "eslint-config-prettier": "^9.1.0",
-    "eslint-config-turbo": "^2.2.3",
+    "eslint-config-turbo": "^2.3.0",
     "eslint-plugin-react": "7.37.2",
     "globals": "^15.12.0",
-    "husky": "^9.1.6",
+    "husky": "^9.1.7",
     "lint-staged": "^15.2.10",
     "madge": "^8.0.0",
     "prettier": "^3.3.3",
     "prettier-plugin-organize-imports": "^4.1.0",
-    "turbo": "^2.2.3",
+    "turbo": "^2.3.0",
     "typescript": "^5.6.3",
-    "typescript-eslint": "^8.13.0"
+    "typescript-eslint": "^8.15.0"
   },
   "packageManager": "pnpm@9.12.3",
   "lint-staged": {

packages/autotool/CHANGELOG.md

@@ -1,5 +1,59 @@
 # @llamaindex/autotool
 
+## 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 +1,66 @@
 # @llamaindex/autotool-01-node-example
 
+## 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": "^4.72.0"
   },
   "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": "0.0.62"
 }

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

@@ -1,5 +1,66 @@
 # @llamaindex/autotool-02-next-example
 
+## 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": "0.1.106",
   "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",
+    "lucide-react": "^0.460.0",
-    "next": "15.0.2",
+    "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",
+    "postcss": "^8.4.49",
-    "tailwindcss": "^3.4.10",
+    "tailwindcss": "^3.4.15",
     "typescript": "^5.6.3"
   }
 }

packages/autotool/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool",
   "type": "module",
-  "version": "5.0.11",
+  "version": "5.0.19",
   "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",
+    "@swc/core": "^1.9.2",
-    "jotai": "2.8.4",
+    "jotai": "2.10.2",
     "typedoc": "^0.26.11",
-    "unplugin": "^1.12.2"
+    "unplugin": "^1.16.0"
   },
   "peerDependencies": {
     "llamaindex": "workspace:*",
@@ -72,11 +72,11 @@
     "@types/node": "^22.9.0",
     "bunchee": "5.6.1",
     "llamaindex": "workspace:*",
-    "next": "15.0.2",
+    "next": "15.0.3",
-    "rollup": "^4.24.4",
+    "rollup": "^4.27.3",
     "tsx": "^4.19.0",
     "typescript": "^5.6.3",
-    "vitest": "^2.1.4",
+    "vitest": "^2.1.5",
     "webpack": "^5.94.0"
   }
 }

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 +1,43 @@
 # @llamaindex/cloud
 
+## 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": "2.0.13",
   "type": "module",
   "license": "MIT",
   "scripts": {
@@ -50,8 +50,8 @@
     "directory": "packages/cloud"
   },
   "devDependencies": {
-    "@hey-api/client-fetch": "^0.4.2",
+    "@hey-api/client-fetch": "^0.4.4",
-    "@hey-api/openapi-ts": "^0.54.3",
+    "@hey-api/openapi-ts": "^0.56.0",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
     "bunchee": "5.6.1"

packages/community/CHANGELOG.md

@@ -1,5 +1,43 @@
 # @llamaindex/community
 
+## 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/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.66",
+  "version": "0.0.71",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",
@@ -46,8 +46,8 @@
     "bunchee": "5.6.1"
   },
   "dependencies": {
-    "@aws-sdk/client-bedrock-agent-runtime": "^3.642.0",
+    "@aws-sdk/client-bedrock-agent-runtime": "^3.693.0",
-    "@aws-sdk/client-bedrock-runtime": "^3.642.0",
+    "@aws-sdk/client-bedrock-runtime": "^3.693.0",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*"
   }

packages/core/CHANGELOG.md

@@ -1,5 +1,38 @@
 # @llamaindex/core
 
+## 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": "0.4.13",
   "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",
+    "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>>();
+  #taskSet = new Set<
-  abstract taskHandler: TaskHandler<AI, Store, AdditionalMessageOptions>;
+    TaskStep<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
+  >();
+  abstract taskHandler: TaskHandler<
+    AI,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
 
   public createTask(
     query: MessageContent,
-    context: AgentTaskContext<AI, Store, AdditionalMessageOptions>,
+    context: AgentTaskContext<
-  ): ReadableStream<TaskStepOutput<AI, Store, AdditionalMessageOptions>> {
+      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;
@@ -330,6 +368,7 @@ export abstract class AgentRunner<
     stream: boolean = false,
     verbose: boolean | undefined = undefined,
     chatHistory?: ChatMessage<AdditionalMessageOptions>[],
+    additionalChatOptions?: AdditionalChatOptions,
   ) {
     const initialMessages = [...(chatHistory ?? this.#chatHistory)];
     if (this.#systemPrompt !== null) {
@@ -348,6 +387,7 @@ export abstract class AgentRunner<
       stream,
       toolCallCount: 0,
       llm: this.#llm,
+      additionalChatOptions: additionalChatOptions ?? {},
       getTools: (message) => this.getTools(message),
       store: {
         ...this.createStore(),
@@ -365,13 +405,29 @@ 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 +444,7 @@ export abstract class AgentRunner<
       !!params.stream,
       false,
       chatHistory,
+      params.chatOptions,
     );
     for await (const stepOutput of task) {
       // update chat history for each round

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;
+  prevStep: TaskStep<
-  nextSteps: Set<TaskStep<Model, Store, AdditionalMessageOptions>>;
+    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/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/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/env/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/env
 
+## 0.1.21
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+
 ## 0.1.20
 
 ### Patch Changes

packages/env/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/env",
   "description": "environment wrapper, supports all JS environment including node, deno, bun, edge runtime, and cloudflare worker",
-  "version": "0.1.20",
+  "version": "0.1.21",
   "type": "module",
   "types": "dist/index.d.ts",
   "module": "dist/index.js",
@@ -122,13 +122,13 @@
     "test": "vitest"
   },
   "devDependencies": {
+    "@huggingface/transformers": "^3.0.2",
     "@types/node": "^22.9.0",
     "@types/readable-stream": "^4.0.15",
-    "@huggingface/transformers": "^3.0.2",
     "bunchee": "5.6.1",
-    "gpt-tokenizer": "^2.6.0",
+    "gpt-tokenizer": "^2.6.2",
     "pathe": "^1.1.2",
-    "vitest": "^2.1.4"
+    "vitest": "^2.1.5"
   },
   "peerDependencies": {
     "@aws-crypto/sha256-js": "^5.2.0",

packages/experimental/CHANGELOG.md

@@ -1,5 +1,59 @@
 # @llamaindex/experimental
 
+## 0.0.131
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - llamaindex@0.8.19
+
+## 0.0.130
+
+### Patch Changes
+
+- Updated dependencies [d17450f]
+  - llamaindex@0.8.18
+
+## 0.0.129
+
+### Patch Changes
+
+- llamaindex@0.8.17
+
+## 0.0.128
+
+### Patch Changes
+
+- llamaindex@0.8.16
+
+## 0.0.127
+
+### Patch Changes
+
+- Updated dependencies [3d503cb]
+- Updated dependencies [5dae534]
+  - llamaindex@0.8.15
+
+## 0.0.126
+
+### Patch Changes
+
+- Updated dependencies [630b425]
+  - llamaindex@0.8.14
+
+## 0.0.125
+
+### Patch Changes
+
+- llamaindex@0.8.13
+
+## 0.0.124
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
 ## 0.0.123
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.123",
+  "version": "0.0.131",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",
@@ -57,7 +57,7 @@
   "devDependencies": {
     "@aws-crypto/sha256-js": "^5.2.0",
     "@swc/cli": "^0.5.0",
-    "@swc/core": "^1.7.22",
+    "@swc/core": "^1.9.2",
     "@types/jsonpath": "^0.2.4",
     "concurrently": "^9.1.0",
     "pathe": "^1.1.2"

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,130 @@
 # llamaindex
 
+## 0.8.19
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/cloud@2.0.13
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+  - @llamaindex/node-parser@0.0.14
+  - @llamaindex/readers@1.0.15
+  - @llamaindex/anthropic@0.0.22
+  - @llamaindex/groq@0.0.37
+  - @llamaindex/ollama@0.0.29
+  - @llamaindex/openai@0.1.38
+  - @llamaindex/portkey-ai@0.0.22
+  - @llamaindex/clip@0.0.22
+  - @llamaindex/deepinfra@0.0.22
+  - @llamaindex/huggingface@0.0.22
+  - @llamaindex/replicate@0.0.22
+  - @llamaindex/vllm@0.0.8
+
+## 0.8.18
+
+### Patch Changes
+
+- d17450f: fix: rename from serverComponentsExternalPackages to serverExternalPackages
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+  - @llamaindex/cloud@2.0.12
+  - @llamaindex/node-parser@0.0.13
+  - @llamaindex/anthropic@0.0.21
+  - @llamaindex/clip@0.0.21
+  - @llamaindex/deepinfra@0.0.21
+  - @llamaindex/huggingface@0.0.21
+  - @llamaindex/ollama@0.0.28
+  - @llamaindex/openai@0.1.37
+  - @llamaindex/portkey-ai@0.0.21
+  - @llamaindex/replicate@0.0.21
+  - @llamaindex/readers@1.0.14
+  - @llamaindex/groq@0.0.36
+  - @llamaindex/vllm@0.0.7
+
+## 0.8.17
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+  - @llamaindex/cloud@2.0.11
+  - @llamaindex/node-parser@0.0.12
+  - @llamaindex/anthropic@0.0.20
+  - @llamaindex/clip@0.0.20
+  - @llamaindex/deepinfra@0.0.20
+  - @llamaindex/huggingface@0.0.20
+  - @llamaindex/ollama@0.0.27
+  - @llamaindex/openai@0.1.36
+  - @llamaindex/portkey-ai@0.0.20
+  - @llamaindex/replicate@0.0.20
+  - @llamaindex/readers@1.0.13
+  - @llamaindex/groq@0.0.35
+  - @llamaindex/vllm@0.0.6
+
+## 0.8.16
+
+### Patch Changes
+
+- Updated dependencies [e60328b]
+  - @llamaindex/readers@1.0.12
+
+## 0.8.15
+
+### Patch Changes
+
+- 3d503cb: Update azure cosmos db
+- 5dae534: fix: propagate queryStr to concrete vectorStore
+
+## 0.8.14
+
+### Patch Changes
+
+- 630b425: feat: add Azure CosmosDB NoSql Chat store
+
+## 0.8.13
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/anthropic@0.0.19
+  - @llamaindex/core@0.4.10
+  - @llamaindex/cloud@2.0.10
+  - @llamaindex/node-parser@0.0.11
+  - @llamaindex/clip@0.0.19
+  - @llamaindex/deepinfra@0.0.19
+  - @llamaindex/huggingface@0.0.19
+  - @llamaindex/ollama@0.0.26
+  - @llamaindex/openai@0.1.35
+  - @llamaindex/portkey-ai@0.0.19
+  - @llamaindex/replicate@0.0.19
+  - @llamaindex/readers@1.0.11
+  - @llamaindex/groq@0.0.34
+  - @llamaindex/vllm@0.0.5
+
+## 0.8.12
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+  - @llamaindex/openai@0.1.34
+  - @llamaindex/cloud@2.0.9
+  - @llamaindex/node-parser@0.0.10
+  - @llamaindex/anthropic@0.0.18
+  - @llamaindex/clip@0.0.18
+  - @llamaindex/deepinfra@0.0.18
+  - @llamaindex/huggingface@0.0.18
+  - @llamaindex/ollama@0.0.25
+  - @llamaindex/portkey-ai@0.0.18
+  - @llamaindex/replicate@0.0.18
+  - @llamaindex/readers@1.0.10
+  - @llamaindex/groq@0.0.33
+  - @llamaindex/vllm@0.0.4
+
 ## 0.8.11
 
 ### Patch Changes

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.8.11",
+  "version": "0.8.19",
   "license": "MIT",
   "type": "module",
   "keywords": [
@@ -20,15 +20,15 @@
     "llamaindex"
   ],
   "dependencies": {
-    "@anthropic-ai/sdk": "0.27.1",
+    "@anthropic-ai/sdk": "0.32.1",
     "@aws-crypto/sha256-js": "^5.2.0",
-    "@aws-sdk/client-sso-oidc": "^3.679.0",
+    "@aws-sdk/client-sso-oidc": "^3.693.0",
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@datastax/astra-db-ts": "^1.4.1",
     "@discoveryjs/json-ext": "^0.6.1",
-    "@google-cloud/vertexai": "1.2.0",
+    "@google-cloud/vertexai": "1.9.0",
-    "@google/generative-ai": "0.12.0",
+    "@google/generative-ai": "0.21.0",
     "@grpc/grpc-js": "^1.12.2",
     "@llamaindex/anthropic": "workspace:*",
     "@llamaindex/clip": "workspace:*",
@@ -45,9 +45,9 @@
     "@llamaindex/readers": "workspace:*",
     "@llamaindex/replicate": "workspace:*",
     "@llamaindex/vllm": "workspace:*",
-    "@mistralai/mistralai": "^1.0.4",
+    "@mistralai/mistralai": "^1.3.4",
     "@mixedbread-ai/sdk": "^2.2.11",
-    "@pinecone-database/pinecone": "^3.0.2",
+    "@pinecone-database/pinecone": "^4.0.0",
     "@qdrant/js-client-rest": "^1.11.0",
     "@types/lodash": "^4.17.7",
     "@types/node": "^22.9.0",
@@ -55,20 +55,20 @@
     "@upstash/vector": "^1.1.5",
     "@zilliz/milvus2-sdk-node": "^2.4.6",
     "ajv": "^8.17.1",
-    "assemblyai": "^4.7.0",
+    "assemblyai": "^4.8.0",
     "chromadb": "1.9.2",
     "chromadb-default-embed": "^2.13.2",
-    "cohere-ai": "7.13.0",
+    "cohere-ai": "7.14.0",
-    "gpt-tokenizer": "^2.6.0",
+    "gpt-tokenizer": "^2.6.2",
-    "groq-sdk": "^0.6.1",
+    "groq-sdk": "^0.8.0",
     "js-tiktoken": "^1.0.14",
     "lodash": "^4.17.21",
     "magic-bytes.js": "^1.10.0",
     "mongodb": "^6.7.0",
-    "openai": "^4.60.0",
+    "openai": "^4.72.0",
     "pathe": "^1.1.2",
     "rake-modified": "^1.0.8",
-    "weaviate-client": "^3.1.4",
+    "weaviate-client": "^3.2.3",
     "wikipedia": "^2.1.2",
     "wink-nlp": "^2.3.0",
     "zod": "^3.23.8"
@@ -88,7 +88,7 @@
   "devDependencies": {
     "@huggingface/transformers": "^3.0.2",
     "@swc/cli": "^0.5.0",
-    "@swc/core": "^1.7.22",
+    "@swc/core": "^1.9.2",
     "@vercel/postgres": "^0.10.0",
     "concurrently": "^9.1.0",
     "glob": "^11.0.0",
@@ -125,6 +125,16 @@
         "default": "./dist/cjs/index.js"
       }
     },
+    "./next": {
+      "import": {
+        "types": "./dist/type/next.d.ts",
+        "default": "./dist/next.js"
+      },
+      "require": {
+        "types": "./dist/type/next.d.ts",
+        "default": "./dist/cjs/next.js"
+      }
+    },
     "./register": "./register.js",
     "./internal/*": {
       "import": "./dist/not-allow.js",

packages/llamaindex/src/indices/vectorStore/index.ts

@@ -18,6 +18,7 @@ import {
   type NodeWithScore,
 } from "@llamaindex/core/schema";
 import type { BaseIndexStore } from "@llamaindex/core/storage/index-store";
+import { extractText } from "@llamaindex/core/utils";
 import type { ServiceContext } from "../../ServiceContext.js";
 import { nodeParserFromSettingsOrContext } from "../../Settings.js";
 import { RetrieverQueryEngine } from "../../engines/query/RetrieverQueryEngine.js";
@@ -449,8 +450,13 @@ export class VectorIndexRetriever extends BaseRetriever {
     filters?: MetadataFilters,
   ): Promise<NodeWithScore[]> {
     // convert string message to multi-modal format
+
+    let queryStr = query;
     if (typeof query === "string") {
-      query = [{ type: "text", text: query }];
+      queryStr = query;
+      query = [{ type: "text", text: queryStr }];
+    } else {
+      queryStr = extractText(query);
     }
     // overwrite embed model if specified, otherwise use the one from the vector store
     const embedModel = this.index.embedModel ?? vectorStore.embedModel;
@@ -460,6 +466,7 @@ export class VectorIndexRetriever extends BaseRetriever {
       const queryEmbedding = await embedModel.getQueryEmbedding(item);
       if (queryEmbedding) {
         const result = await vectorStore.query({
+          queryStr,
           queryEmbedding,
           mode: VectorStoreQueryMode.DEFAULT,
           similarityTopK: this.topK[type]!,

packages/llamaindex/src/llm/gemini/utils.ts

@@ -4,6 +4,7 @@ import {
   HarmBlockThreshold,
   HarmCategory,
   type SafetySetting,
+  SchemaType,
 } from "@google/generative-ai";
 
 import { type GenerateContentResponse } from "@google-cloud/vertexai";
@@ -161,7 +162,7 @@ export const mapBaseToolToGeminiFunctionDeclaration = (
   tool: BaseTool,
 ): FunctionDeclaration => {
   const parameters: FunctionDeclarationSchema = {
-    type: tool.metadata.parameters?.type.toUpperCase(),
+    type: tool.metadata.parameters?.type.toLowerCase() as SchemaType,
     properties: tool.metadata.parameters?.properties,
     description: tool.metadata.parameters?.description,
     required: tool.metadata.parameters?.required,

packages/llamaindex/src/next.ts

@@ -15,15 +15,28 @@
  *
  * @module
  */
+import { createRequire } from "node:module";
+
+const require = createRequire(import.meta.url);
+
+const nextJsVersion: string = require("next/package.json").version;
+const is14OrLower =
+  nextJsVersion.startsWith("14.") || nextJsVersion.startsWith("13.");
+
 // eslint-disable-next-line @typescript-eslint/no-explicit-any
 export default function withLlamaIndex(config: any) {
-  config.experimental = config.experimental ?? {};
   // needed for transformers, see https://huggingface.co/docs/transformers.js/en/tutorials/next#step-2-install-and-configure-transformersjs
-  config.experimental.serverComponentsExternalPackages =
+  if (is14OrLower) {
-    config.experimental.serverComponentsExternalPackages ?? [];
+    config.experimental.serverComponentsExternalPackages =
-  config.experimental.serverComponentsExternalPackages.push(
+      config.experimental.serverComponentsExternalPackages ?? [];
-    "@huggingface/transformers",
+    config.experimental.serverComponentsExternalPackages.push(
-  );
+      "@huggingface/transformers",
+    );
+  } else {
+    config.serverExternalPackages = config.serverExternalPackages ?? [];
+    config.serverExternalPackages.push("@huggingface/transformers");
+  }
+
   const userWebpack = config.webpack;
   // eslint-disable-next-line @typescript-eslint/no-explicit-any
   config.webpack = function (webpackConfig: any, options: any) {

packages/llamaindex/src/storage/chatStore/AzureCosmosNoSqlChatStore.ts

@@ -0,0 +1,345 @@
+import { CosmosClient, type Container, type Database } from "@azure/cosmos";
+import { DefaultAzureCredential, type TokenCredential } from "@azure/identity";
+import type {
+  ChatMessage,
+  MessageContent,
+  MessageType,
+} from "@llamaindex/core/llms";
+import { BaseChatStore } from "@llamaindex/core/storage/chat-store";
+import { getEnv } from "@llamaindex/env";
+
+const USER_AGENT_SUFFIX = "llamaindex-cdbnosql-chatstore-javascript";
+const DEFAULT_CHAT_DATABASE = "ChatMessagesDB";
+const DEFAULT_CHAT_CONTAINER = "ChatMessagesContainer";
+const DEFAULT_OFFER_THROUGHPUT = 400;
+
+function parseConnectionString(connectionString: string): {
+  endpoint: string;
+  key: string;
+} {
+  const parts = connectionString.split(";");
+  let endpoint = "";
+  let accountKey = "";
+
+  parts.forEach((part) => {
+    const [key, value] = part.split("=");
+    if (key && key.trim() === "AccountEndpoint") {
+      endpoint = value?.trim() ?? "";
+    } else if ((key ?? "").trim() === "AccountKey") {
+      accountKey = value?.trim() ?? "";
+    }
+  });
+
+  if (!endpoint || !accountKey) {
+    throw new Error(
+      "Invalid connection string: missing AccountEndpoint or AccountKey.",
+    );
+  }
+  return { endpoint, key: accountKey };
+}
+
+export interface AzureCosmosChatDatabaseProperties {
+  throughput?: number;
+}
+
+export interface AzureCosmosChatContainerProperties {
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  [key: string]: any;
+}
+
+export interface AzureCosmosNoSqlChatStoreConfig {
+  cosmosClient?: CosmosClient;
+  dbName?: string;
+  containerName?: string;
+  userId?: string;
+  sessionId?: string;
+  cosmosContainerProperties?: AzureCosmosChatContainerProperties;
+  cosmosDatabaseProperties?: AzureCosmosChatDatabaseProperties;
+  ttlInSeconds?: number;
+}
+
+export class AzureCosmosNoSqlChatStore<
+  AdditionalMessageOptions extends object = object,
+> extends BaseChatStore<AdditionalMessageOptions> {
+  private userId: string;
+  private ttl: number;
+  private cosmosClient: CosmosClient;
+  private database!: Database;
+  private container!: Container;
+  private initPromise?: Promise<void>;
+
+  private dbName: string;
+  private containerName: string;
+  private cosmosContainerProperties: AzureCosmosChatContainerProperties;
+  private cosmosDatabaseProperties: AzureCosmosChatDatabaseProperties;
+  private initialize: () => Promise<void>;
+
+  constructor({
+    cosmosClient,
+    dbName = DEFAULT_CHAT_DATABASE,
+    containerName = DEFAULT_CHAT_CONTAINER,
+    cosmosContainerProperties = { partitionKey: "/userId" },
+    cosmosDatabaseProperties = {},
+    ttlInSeconds = -1,
+  }: AzureCosmosNoSqlChatStoreConfig) {
+    super();
+    if (!cosmosClient) {
+      throw new Error(
+        "CosmosClient is required for AzureCosmosDBNoSQLChatStore initialization",
+      );
+    }
+    this.ttl = ttlInSeconds;
+    this.userId = cosmosContainerProperties.userId || "anonymous";
+    this.cosmosClient = cosmosClient;
+    this.dbName = dbName;
+    this.containerName = containerName;
+    this.cosmosContainerProperties = cosmosContainerProperties;
+    this.cosmosDatabaseProperties = cosmosDatabaseProperties;
+
+    this.initialize = () => {
+      if (this.initPromise === undefined) {
+        this.initPromise = this.init().catch((error) => {
+          console.error(
+            "Error during AzureCosmosDBNoSQLChatStore initialization",
+            error,
+          );
+        });
+      }
+      return this.initPromise;
+    };
+  }
+
+  client(): CosmosClient {
+    return this.cosmosClient;
+  }
+
+  // Asynchronous initialization method to create database and container
+  private async init(): Promise<void> {
+    // Set default throughput if not provided
+    const throughput =
+      this.cosmosDatabaseProperties?.throughput || DEFAULT_OFFER_THROUGHPUT;
+
+    // Create the database if it doesn't exist
+    const { database } = await this.cosmosClient.databases.createIfNotExists({
+      id: this.dbName,
+      throughput,
+    });
+    this.database = database;
+
+    // Create the container if it doesn't exist
+    const { container } = await this.database.containers.createIfNotExists({
+      id: this.containerName,
+      throughput: this.cosmosContainerProperties?.throughput,
+      partitionKey: "/userId",
+      indexingPolicy: this.cosmosContainerProperties?.indexingPolicy,
+      defaultTtl: this.ttl,
+      uniqueKeyPolicy: this.cosmosContainerProperties?.uniqueKeyPolicy,
+      conflictResolutionPolicy:
+        this.cosmosContainerProperties?.conflictResolutionPolicy,
+      computedProperties: this.cosmosContainerProperties?.computedProperties,
+    });
+    this.container = container;
+  }
+  /**
+   * Static method for creating an instance using a connection string.
+   * If no connection string is provided, it will attempt to use the env variable `AZURE_COSMOSDB_NOSQL_CONNECTION_STRING` as connection string.
+   * @returns Instance of AzureCosmosNoSqlKVStore
+   */
+  static fromConnectionString(
+    config: {
+      connectionString?: string;
+    } & AzureCosmosNoSqlChatStoreConfig = {},
+  ): AzureCosmosNoSqlChatStore {
+    const cosmosConnectionString =
+      config.connectionString ||
+      (getEnv("AZURE_COSMOSDB_NOSQL_CONNECTION_STRING") as string);
+    if (!cosmosConnectionString) {
+      throw new Error("Azure CosmosDB connection string must be provided");
+    }
+    const { endpoint, key } = parseConnectionString(cosmosConnectionString);
+    const cosmosClient = new CosmosClient({
+      endpoint,
+      key,
+      userAgentSuffix: USER_AGENT_SUFFIX,
+    });
+    return new AzureCosmosNoSqlChatStore({
+      ...config,
+      cosmosClient,
+    });
+  }
+
+  /**
+   * Static method for creating an instance using a account endpoint and key.
+   * If no endpoint and key  is provided, it will attempt to use the env variable `AZURE_COSMOSDB_NOSQL_ACCOUNT_ENDPOINT` as enpoint and `AZURE_COSMOSDB_NOSQL_ACCOUNT_KEY` as key.
+   * @returns Instance of AzureCosmosNoSqlKVStore
+   */
+  static fromAccountAndKey(
+    config: {
+      endpoint?: string;
+      key?: string;
+    } & AzureCosmosNoSqlChatStoreConfig = {},
+  ): AzureCosmosNoSqlChatStore {
+    const cosmosEndpoint =
+      config.endpoint ||
+      (getEnv("AZURE_COSMOSDB_NOSQL_ACCOUNT_ENDPOINT") as string);
+    const cosmosKey =
+      config.key || (getEnv("AZURE_COSMOSDB_NOSQL_ACCOUNT_KEY") as string);
+
+    if (!cosmosEndpoint || !cosmosKey) {
+      throw new Error(
+        "Azure CosmosDB account endpoint and key must be provided",
+      );
+    }
+    const cosmosClient = new CosmosClient({
+      endpoint: cosmosEndpoint,
+      key: cosmosKey,
+      userAgentSuffix: USER_AGENT_SUFFIX,
+    });
+    return new AzureCosmosNoSqlChatStore({
+      ...config,
+      cosmosClient,
+    });
+  }
+
+  /**
+   * Static method for creating an instance using AAD token.
+   * If no endpoint and credentials are provided, it will attempt to use the env variable `AZURE_COSMOSDB_NOSQL_ACCOUNT_ENDPOINT` as endpoint and use DefaultAzureCredential() as credentials.
+   * @returns Instance of AzureCosmosNoSqlKVStore
+   */
+  static fromAadToken(
+    config: {
+      endpoint?: string;
+      credential?: TokenCredential;
+    } & AzureCosmosNoSqlChatStoreConfig = {},
+  ): AzureCosmosNoSqlChatStore {
+    const cosmosEndpoint =
+      config.endpoint ||
+      (getEnv("AZURE_COSMOSDB_NOSQL_CONNECTION_STRING") as string);
+
+    if (!cosmosEndpoint) {
+      throw new Error("Azure CosmosDB account endpoint must be provided");
+    }
+    const credentials = config.credential ?? new DefaultAzureCredential();
+    const cosmosClient = new CosmosClient({
+      endpoint: cosmosEndpoint,
+      aadCredentials: credentials,
+      userAgentSuffix: USER_AGENT_SUFFIX,
+    });
+    return new AzureCosmosNoSqlChatStore({
+      ...config,
+      cosmosClient,
+    });
+  }
+
+  private convertToChatMessage(
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    message: any,
+  ): ChatMessage<AdditionalMessageOptions> {
+    return {
+      content: message.content as MessageContent,
+      role: message.role as MessageType,
+      options: message.options as AdditionalMessageOptions,
+    } as ChatMessage<AdditionalMessageOptions>;
+  }
+
+  private convertToCosmosMessage(
+    message: ChatMessage<AdditionalMessageOptions>,
+  ): // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  any {
+    return {
+      content: message.content,
+      role: message.role,
+      options: message.options,
+    };
+  }
+
+  /**
+   * Set messages for a given key.
+   */
+  async setMessages(
+    key: string,
+    messages: ChatMessage<AdditionalMessageOptions>[],
+  ): Promise<void> {
+    await this.initialize();
+    const inputMessages = messages.map(this.convertToCosmosMessage);
+    await this.container.items.upsert({
+      id: key,
+      messages: inputMessages,
+      userId: this.userId,
+    });
+  }
+
+  /**
+   * Get messages for a given key.
+   */
+  async getMessages(
+    key: string,
+  ): Promise<ChatMessage<AdditionalMessageOptions>[]> {
+    await this.initialize();
+    const res = await this.container.item(key, this.userId).read();
+    const messageHistory = res?.resource?.messages ?? [];
+    const result = messageHistory.map(this.convertToChatMessage);
+    return result;
+  }
+
+  /**
+   * Add a message for a given key.
+   */
+  async addMessage(
+    key: string,
+    message: ChatMessage<AdditionalMessageOptions>,
+    idx?: number,
+  ): Promise<void> {
+    await this.initialize();
+    const res = await this.container.item(key, this.userId).read();
+    const messageHistory = res?.resource?.messages ?? [];
+    if (idx === undefined) {
+      messageHistory.push(this.convertToCosmosMessage(message));
+    } else {
+      messageHistory.splice(idx, 0, this.convertToCosmosMessage(message));
+    }
+    await this.setMessages(key, messageHistory);
+  }
+
+  /**
+   * Deletes all messages for a given key.
+   */
+  async deleteMessages(key: string): Promise<void> {
+    await this.initialize();
+    try {
+      await this.container.item(key, this.userId).delete();
+      // eslint-disable-next-line no-empty
+    } catch (e) {}
+  }
+
+  /**
+   * Deletes one message at idx index for a given key.
+   */
+  async deleteMessage(key: string, idx: number): Promise<void> {
+    await this.initialize();
+    const res = await this.container.item(key, this.userId).read();
+    const messageHistory = res?.resource?.messages ?? [];
+    if (idx >= 0 && idx < messageHistory.length) {
+      messageHistory.splice(idx, 1);
+      await this.setMessages(key, messageHistory);
+    }
+  }
+
+  /**
+   * Get all keys.
+   */
+  async getKeys(): Promise<IterableIterator<string>> {
+    await this.initialize();
+    const result = await this.container.items
+      .query("Select c.id from c")
+      .fetchAll();
+    const keys = result.resources.map((res: { id: string }) => res.id);
+
+    function* keyGenerator(): IterableIterator<string> {
+      for (const key of keys) {
+        yield key;
+      }
+    }
+    return keyGenerator();
+  }
+}

packages/llamaindex/src/storage/index.ts

@@ -2,6 +2,7 @@ export * from "@llamaindex/core/storage/chat-store";
 export * from "@llamaindex/core/storage/doc-store";
 export * from "@llamaindex/core/storage/index-store";
 export * from "@llamaindex/core/storage/kv-store";
+export * from "./chatStore/AzureCosmosNoSqlChatStore.js";
 export * from "./docStore/AzureCosmosNoSqlDocumentStore.js";
 export { PostgresDocumentStore } from "./docStore/PostgresDocumentStore.js";
 export { SimpleDocumentStore } from "./docStore/SimpleDocumentStore.js";

packages/llamaindex/src/storage/kvStore/AzureCosmosNoSqlKVStore.ts

@@ -3,7 +3,7 @@ import { Container, CosmosClient, Database } from "@azure/cosmos";
 import { DefaultAzureCredential, type TokenCredential } from "@azure/identity";
 import { BaseKVStore } from "@llamaindex/core/storage/kv-store";
 import { getEnv } from "@llamaindex/env";
-const USER_AGENT_SUFFIX = "LlamaIndex-CDBNoSQL-KVStore-JavaScript";
+const USER_AGENT_SUFFIX = "llamaindex-cdbnosql-kvstore-javascript";
 const DEFAULT_CHAT_DATABASE = "KVStoreDB";
 const DEFAULT_CHAT_CONTAINER = "KVStoreContainer";
 const DEFAULT_OFFER_THROUGHPUT = 400;
@@ -82,7 +82,7 @@ export class AzureCosmosNoSqlKVStore extends BaseKVStore {
     super();
     if (!cosmosClient) {
       throw new Error(
-        "CosmosClient is required for AzureCosmosDBNoSQLVectorStore initialization",
+        "CosmosClient is required for AzureCosmosDBNoSQLKVStore initialization",
       );
     }
     this.cosmosClient = cosmosClient;

packages/llamaindex/src/vector-store/AzureCosmosDBNoSqlVectorStore.ts

@@ -55,8 +55,18 @@ export interface AzureCosmosDBNoSQLConfig
   readonly flatMetadata?: boolean;
   readonly idKey?: string;
 }
+/**
+ * Query options for the `AzureCosmosDBNoSQLVectorStore.query` method.
+ * @property includeEmbeddings - Whether to include the embeddings in the result. Default false
+ * @property includeVectorDistance - Whether to include the vector distance in the result. Default true
+ * @property whereClause - The where clause to use in the query. While writing this clause, use `c` as the alias for the container and do not include the `WHERE` keyword.
+ */
+export interface AzureCosmosQueryOptions {
+  includeVectorDistance?: boolean;
+  whereClause?: string;
+}
 
-const USER_AGENT_SUFFIX = "LlamaIndex-CDBNoSQL-VectorStore-JavaScript";
+const USER_AGENT_SUFFIX = "llamaindex-cdbnosql-vectorstore-javascript";
 
 const DEFAULT_VECTOR_EMBEDDING_POLICY = {
   vectorEmbeddings: [
@@ -98,6 +108,22 @@ function parseConnectionString(connectionString: string): {
 
   return { endpoint, key: accountKey };
 }
+/**
+ * utility function to build the query string for the CosmosDB query
+ */
+function queryBuilder(options: AzureCosmosQueryOptions): string {
+  let initialQuery =
+    "SELECT TOP @k c[@id] as id, c[@text] as text, c[@metadata] as metadata";
+  if (options.includeVectorDistance !== false) {
+    initialQuery += `, VectorDistance(c[@embeddingKey],@embedding) AS SimilarityScore`;
+  }
+  initialQuery += ` FROM c`;
+  if (options.whereClause) {
+    initialQuery += ` WHERE ${options.whereClause}`;
+  }
+  initialQuery += ` ORDER BY VectorDistance(c[@embeddingKey],@embedding)`;
+  return initialQuery;
+}
 
 export class AzureCosmosDBNoSqlVectorStore extends BaseVectorStore {
   storesText: boolean = true;
@@ -334,21 +360,25 @@ export class AzureCosmosDBNoSqlVectorStore extends BaseVectorStore {
    */
   async query(
     query: VectorStoreQuery,
-    options?: object,
+    options: AzureCosmosQueryOptions = {},
   ): Promise<VectorStoreQueryResult> {
     await this.initialize();
+    if (!query.queryEmbedding || query.queryEmbedding.length === 0) {
+      throw new Error(
+        "queryEmbedding is required for AzureCosmosDBNoSqlVectorStore query",
+      );
+    }
     const params = {
       vector: query.queryEmbedding!,
       k: query.similarityTopK,
     };
-
+    const builtQuery = queryBuilder(options);
     const nodes: BaseNode[] = [];
     const ids: string[] = [];
     const similarities: number[] = [];
     const queryResults = await this.container.items
       .query({
-        query:
+        query: builtQuery,
-          "SELECT TOP @k c[@id] as id, c[@text] as text, c[@metadata] as metadata, VectorDistance(c[@embeddingKey],@embedding) AS SimilarityScore FROM c ORDER BY VectorDistance(c[@embeddingKey],@embedding)",
         parameters: [
           { name: "@k", value: params.k },
           { name: "@id", value: this.idKey },

packages/llamaindex/tests/package.json

@@ -10,7 +10,7 @@
     "@faker-js/faker": "^9.2.0",
     "dotenv": "^16.4.5",
     "llamaindex": "workspace:*",
-    "msw": "^2.6.0",
+    "msw": "^2.6.5",
-    "vitest": "^2.1.4"
+    "vitest": "^2.1.5"
   }
 }

packages/llamaindex/tests/vector-stores/AzureCosmosDBNoSqlVectorStore.int.test.ts

@@ -14,9 +14,10 @@ import {
   Settings,
   VectorStoreQueryMode,
   type AzureCosmosDBNoSQLConfig,
+  type AzureCosmosQueryOptions,
   type VectorStoreQueryResult,
 } from "llamaindex";
-import { beforeEach, describe, expect, it } from "vitest";
+import { beforeAll, describe, expect, it } from "vitest";
 dotenv.config();
 /*
  * To run this test, you need have an Azure Cosmos DB for NoSQL instance
@@ -64,7 +65,10 @@ Settings.llm = new OpenAI(llmInit);
 Settings.embedModel = new OpenAIEmbedding(embedModelInit);
 // This test is skipped because it requires an Azure Cosmos DB instance and OpenAI API keys
 describe.skip("AzureCosmosDBNoSQLVectorStore", () => {
-  beforeEach(async () => {
+  let vectorStore: AzureCosmosDBNoSqlVectorStore;
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  let embeddings: any = [];
+  beforeAll(async () => {
     if (process.env.AZURE_COSMOSDB_NOSQL_CONNECTION_STRING) {
       client = new CosmosClient(
         process.env.AZURE_COSMOSDB_NOSQL_CONNECTION_STRING,
@@ -79,15 +83,12 @@ describe.skip("AzureCosmosDBNoSQLVectorStore", () => {
         "Please set the environment variable AZURE_COSMOSDB_NOSQL_CONNECTION_STRING or AZURE_COSMOSDB_NOSQL_ENDPOINT",
       );
     }
-
     // Make sure the database does not exists
     try {
       await client.database(DATABASE_NAME).delete();
     } catch {
       // Ignore error if the database does not exist
     }
-  });
-  it("perform query", async () => {
     const config: AzureCosmosDBNoSQLConfig = {
       idKey: "name",
       textKey: "customText",
@@ -134,9 +135,9 @@ describe.skip("AzureCosmosDBNoSQLVectorStore", () => {
       },
     };
 
-    const vectorStore = new AzureCosmosDBNoSqlVectorStore(config);
+    vectorStore = new AzureCosmosDBNoSqlVectorStore(config);
 
-    const embeddings = await Settings.embedModel.getTextEmbeddings([
+    embeddings = await Settings.embedModel.getTextEmbeddings([
       "This book is about politics",
       "Cats sleeps a lot.",
       "Sandwiches taste good.",
@@ -150,28 +151,29 @@ describe.skip("AzureCosmosDBNoSQLVectorStore", () => {
         id_: "1",
         text: "This book is about politics",
         embedding: embeddings[0],
-        metadata: { key: "politics" },
+        metadata: { key: "politics", number: 1 },
       }),
       new Document({
         id_: "2",
         text: "Cats sleeps a lot.",
         embedding: embeddings[1],
-        metadata: { key: "cats" },
+        metadata: { key: "cats", number: 2 },
       }),
       new Document({
         id_: "3",
         text: "Sandwiches taste good.",
         embedding: embeddings[2],
-        metadata: { key: "sandwiches" },
+        metadata: { key: "sandwiches", number: 3 },
       }),
       new Document({
         id_: "4",
         text: "The house is open",
         embedding: embeddings[3],
-        metadata: { key: "house" },
+        metadata: { key: "house", number: 4 },
       }),
     ]);
-
+  });
+  it("perform query", async () => {
     const results: VectorStoreQueryResult = await vectorStore.query({
       queryEmbedding: embeddings[4] || [],
       similarityTopK: 1,
@@ -179,5 +181,62 @@ describe.skip("AzureCosmosDBNoSQLVectorStore", () => {
     });
     expect(results.ids.length).toEqual(1);
     expect(results.ids[0]).toEqual("3");
+    expect(results.similarities).toBeDefined();
+    expect(results.similarities[0]).toBeDefined();
+  }, 1000000);
+
+  it("perform query with where clause", async () => {
+    const options: AzureCosmosQueryOptions = {
+      whereClause: "c.customMetadata.number > 3",
+    };
+    const results: VectorStoreQueryResult = await vectorStore.query(
+      {
+        queryEmbedding: embeddings[4] || [],
+        similarityTopK: 1,
+        mode: VectorStoreQueryMode.DEFAULT,
+      },
+      options,
+    );
+    expect(results.ids.length).toEqual(1);
+    expect(results.ids[0]).toEqual("4");
+    expect(results.similarities).toBeDefined();
+    expect(results.similarities[0]).toBeDefined();
+  }, 1000000);
+
+  it("perform query with includeVectorDistance false", async () => {
+    const options: AzureCosmosQueryOptions = {
+      includeVectorDistance: false,
+    };
+    const results: VectorStoreQueryResult = await vectorStore.query(
+      {
+        queryEmbedding: embeddings[4] || [],
+        similarityTopK: 1,
+        mode: VectorStoreQueryMode.DEFAULT,
+      },
+      options,
+    );
+    expect(results.ids.length).toEqual(1);
+    expect(results.ids[0]).toEqual("3");
+    expect(results.similarities).toBeDefined();
+    expect(results.similarities[0]).toBeUndefined();
+  }, 1000000);
+
+  it("perform query with includeVectorDistance false and whereClause", async () => {
+    const options: AzureCosmosQueryOptions = {
+      includeVectorDistance: false,
+      whereClause: "c.customMetadata.number > 3",
+    };
+    const results: VectorStoreQueryResult = await vectorStore.query(
+      {
+        queryEmbedding: embeddings[4] || [],
+        similarityTopK: 1,
+        mode: VectorStoreQueryMode.DEFAULT,
+      },
+      options,
+    );
+    expect(results.ids.length).toEqual(1);
+    expect(results.ids[0]).toEqual("4");
+    expect(results.similarities).toBeDefined();
+    expect(results.similarities[0]).toBeUndefined();
   }, 1000000);
 });

packages/llamaindex/tests/vector-stores/AzureCosmosDBNoSqlVectorStore.test.ts

@@ -1,6 +1,7 @@
 /* eslint-disable @typescript-eslint/no-explicit-any */
 import type { BaseNode } from "@llamaindex/core/schema";
 import { beforeEach, describe, expect, it, vi } from "vitest";
+import { VectorStoreQueryMode } from "../../src/vector-store.js";
 import { TestableAzureCosmosDBNoSqlVectorStore } from "../mocks/TestableAzureCosmosDBNoSqlVectorStore.js";
 import { createMockClient } from "../utility/mockCosmosClient.js"; // Import the mock client
 
@@ -95,4 +96,27 @@ describe("AzureCosmosDBNoSqlVectorStore Tests", () => {
     expect(client.databases.containers.items.create).toHaveBeenCalledTimes(2);
     expect(result).toEqual(["node-0", "node-1"]);
   });
+
+  it("should throw error if no query embedding is provided", async () => {
+    const client = createMockClient();
+    const store = new TestableAzureCosmosDBNoSqlVectorStore({
+      client: client as any,
+      endpoint: "https://example.com",
+      idKey: "id",
+      textKey: "text",
+      metadataKey: "metadata",
+    });
+
+    expect(store).toBeDefined();
+
+    await expect(
+      store.query({
+        queryEmbedding: [],
+        similarityTopK: 4,
+        mode: VectorStoreQueryMode.DEFAULT,
+      }),
+    ).rejects.toThrowError(
+      "queryEmbedding is required for AzureCosmosDBNoSqlVectorStore query",
+    );
+  });
 });

packages/node-parser/CHANGELOG.md

@@ -1,5 +1,43 @@
 # @llamaindex/node-parser
 
+## 0.0.14
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+
+## 0.0.13
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+
+## 0.0.12
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+
+## 0.0.11
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+
+## 0.0.10
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
 ## 0.0.9
 
 ### Patch Changes

packages/node-parser/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/node-parser",
-  "version": "0.0.9",
+  "version": "0.0.14",
   "description": "Node parser for LlamaIndex",
   "type": "module",
   "exports": {
@@ -44,8 +44,8 @@
     "@types/html-to-text": "^9.0.4",
     "@types/node": "^22.9.0",
     "bunchee": "5.6.1",
-    "tree-sitter": "^0.22.0",
+    "tree-sitter": "^0.22.1",
-    "web-tree-sitter": "^0.24.3"
+    "web-tree-sitter": "^0.24.4"
   },
   "peerDependencies": {
     "@llamaindex/core": "workspace:*",

packages/providers/anthropic/CHANGELOG.md

@@ -1,5 +1,44 @@
 # @llamaindex/anthropic
 
+## 0.0.22
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+
+## 0.0.20
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+
+## 0.0.19
+
+### Patch Changes
+
+- a7b0ac3: feat(anthropic): support prompt caching
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
 ## 0.0.17
 
 ### Patch Changes

packages/providers/anthropic/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/anthropic",
   "description": "Anthropic Adapter for LlamaIndex",
-  "version": "0.0.17",
+  "version": "0.0.22",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -33,9 +33,9 @@
     "bunchee": "5.6.1"
   },
   "dependencies": {
-    "@anthropic-ai/sdk": "0.27.1",
+    "@anthropic-ai/sdk": "0.32.1",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
-    "remeda": "^2.12.0"
+    "remeda": "^2.17.3"
   }
 }

packages/providers/anthropic/src/agent.ts

@@ -11,7 +11,7 @@ import { Settings } from "@llamaindex/core/global";
 import type { EngineResponse } from "@llamaindex/core/schema";
 import { Anthropic } from "./llm.js";
 
-export type AnthropicAgentParams = LLMAgentParams;
+export type AnthropicAgentParams = LLMAgentParams<Anthropic>;
 
 export class AnthropicAgentWorker extends LLMAgentWorker {}
 

packages/providers/anthropic/src/llm.ts

@@ -1,5 +1,9 @@
 import type { ClientOptions } from "@anthropic-ai/sdk";
 import { Anthropic as SDKAnthropic } from "@anthropic-ai/sdk";
+import type {
+  BetaCacheControlEphemeral,
+  BetaTextBlockParam,
+} from "@anthropic-ai/sdk/resources/beta/index";
 import type {
   TextBlock,
   TextBlockParam,
@@ -8,6 +12,7 @@ import type {
   ImageBlockParam,
   MessageCreateParamsNonStreaming,
   MessageParam,
+  Model,
   Tool,
   ToolResultBlockParam,
   ToolUseBlock,
@@ -75,6 +80,9 @@ export const ALL_AVAILABLE_ANTHROPIC_LEGACY_MODELS = {
   "claude-2.1": {
     contextWindow: 200000,
   },
+  "claude-2.0": {
+    contextWindow: 100000,
+  },
   "claude-instant-1.2": {
     contextWindow: 100000,
   },
@@ -82,18 +90,30 @@ export const ALL_AVAILABLE_ANTHROPIC_LEGACY_MODELS = {
 
 export const ALL_AVAILABLE_V3_MODELS = {
   "claude-3-opus": { contextWindow: 200000 },
+  "claude-3-opus-latest": { contextWindow: 200000 },
+  "claude-3-opus-20240229": { contextWindow: 200000 },
   "claude-3-sonnet": { contextWindow: 200000 },
+  "claude-3-sonnet-20240229": { contextWindow: 200000 },
   "claude-3-haiku": { contextWindow: 200000 },
+  "claude-3-haiku-20240307": { contextWindow: 200000 },
 };
 
 export const ALL_AVAILABLE_V3_5_MODELS = {
   "claude-3-5-sonnet": { contextWindow: 200000 },
+  "claude-3-5-sonnet-20241022": { contextWindow: 200000 },
+  "claude-3-5-sonnet-20240620": { contextWindow: 200000 },
+  "claude-3-5-sonnet-latest": { contextWindow: 200000 },
+  "claude-3-5-haiku": { contextWindow: 200000 },
+  "claude-3-5-haiku-latest": { contextWindow: 200000 },
+  "claude-3-5-haiku-20241022": { contextWindow: 200000 },
 };
 
 export const ALL_AVAILABLE_ANTHROPIC_MODELS = {
   ...ALL_AVAILABLE_ANTHROPIC_LEGACY_MODELS,
   ...ALL_AVAILABLE_V3_MODELS,
   ...ALL_AVAILABLE_V3_5_MODELS,
+} satisfies {
+  [key in Model]: { contextWindow: number };
 };
 
 const AVAILABLE_ANTHROPIC_MODELS_WITHOUT_DATE: { [key: string]: string } = {
@@ -104,10 +124,16 @@ const AVAILABLE_ANTHROPIC_MODELS_WITHOUT_DATE: { [key: string]: string } = {
 } as { [key in keyof typeof ALL_AVAILABLE_ANTHROPIC_MODELS]: string };
 
 export type AnthropicAdditionalChatOptions = object;
+export type AnthropicToolCallLLMMessageOptions = ToolCallLLMMessageOptions & {
+  cache_control?: BetaCacheControlEphemeral | null;
+};
 
-export class Anthropic extends ToolCallLLM<AnthropicAdditionalChatOptions> {
+export class Anthropic extends ToolCallLLM<
+  AnthropicAdditionalChatOptions,
+  AnthropicToolCallLLMMessageOptions
+> {
   // Per completion Anthropic params
-  model: keyof typeof ALL_AVAILABLE_ANTHROPIC_MODELS;
+  model: keyof typeof ALL_AVAILABLE_ANTHROPIC_MODELS | ({} & string);
   temperature: number;
   topP: number;
   maxTokens?: number | undefined;
@@ -147,7 +173,12 @@ export class Anthropic extends ToolCallLLM<AnthropicAdditionalChatOptions> {
       temperature: this.temperature,
       topP: this.topP,
       maxTokens: this.maxTokens,
-      contextWindow: ALL_AVAILABLE_ANTHROPIC_MODELS[this.model].contextWindow,
+      contextWindow:
+        this.model in ALL_AVAILABLE_ANTHROPIC_MODELS
+          ? ALL_AVAILABLE_ANTHROPIC_MODELS[
+              this.model as keyof typeof ALL_AVAILABLE_ANTHROPIC_MODELS
+            ].contextWindow
+          : 200000,
       tokenizer: undefined,
     };
   }
@@ -291,56 +322,74 @@ export class Anthropic extends ToolCallLLM<AnthropicAdditionalChatOptions> {
   chat(
     params: LLMChatParamsStreaming<
       AnthropicAdditionalChatOptions,
-      ToolCallLLMMessageOptions
+      AnthropicToolCallLLMMessageOptions
     >,
-  ): Promise<AsyncIterable<ChatResponseChunk<ToolCallLLMMessageOptions>>>;
+  ): Promise<
+    AsyncIterable<ChatResponseChunk<AnthropicToolCallLLMMessageOptions>>
+  >;
   chat(
     params: LLMChatParamsNonStreaming<
       AnthropicAdditionalChatOptions,
-      ToolCallLLMMessageOptions
+      AnthropicToolCallLLMMessageOptions
     >,
-  ): Promise<ChatResponse<ToolCallLLMMessageOptions>>;
+  ): Promise<ChatResponse<AnthropicToolCallLLMMessageOptions>>;
   @wrapLLMEvent
   async chat(
     params:
       | LLMChatParamsNonStreaming<
           AnthropicAdditionalChatOptions,
-          ToolCallLLMMessageOptions
+          AnthropicToolCallLLMMessageOptions
         >
       | LLMChatParamsStreaming<
           AnthropicAdditionalChatOptions,
-          ToolCallLLMMessageOptions
+          AnthropicToolCallLLMMessageOptions
         >,
   ): Promise<
-    | ChatResponse<ToolCallLLMMessageOptions>
+    | ChatResponse<AnthropicToolCallLLMMessageOptions>
-    | AsyncIterable<ChatResponseChunk<ToolCallLLMMessageOptions>>
+    | AsyncIterable<ChatResponseChunk<AnthropicToolCallLLMMessageOptions>>
   > {
     let { messages } = params;
 
     const { stream, tools } = params;
 
-    let systemPrompt: string | null = null;
+    let systemPrompt: string | Array<BetaTextBlockParam> | null = null;
 
     const systemMessages = messages.filter(
       (message) => message.role === "system",
     );
 
     if (systemMessages.length > 0) {
-      systemPrompt = systemMessages
+      systemPrompt = systemMessages.map((message) =>
-        .map((message) => message.content)
+        message.options && "cache_control" in message.options
-        .join("\n");
+          ? {
+              type: "text",
+              text: extractText(message.content),
+              cache_control: message.options.cache_control,
+            }
+          : {
+              type: "text",
+              text: extractText(message.content),
+            },
+      );
       messages = messages.filter((message) => message.role !== "system");
     }
+    const beta =
+      systemPrompt?.find((message) => "cache_control" in message) !== undefined;
+
+    // case: Non-streaming
+    let anthropic = this.session.anthropic;
+    if (beta) {
+      // @ts-expect-error type casting
+      anthropic = anthropic.beta.promptCaching;
+    }
 
     // case: Streaming
     if (stream) {
       if (tools) {
         console.error("Tools are not supported in streaming mode");
       }
-      return this.streamChat(messages, systemPrompt);
+      return this.streamChat(messages, systemPrompt, anthropic);
     }
-    // case: Non-streaming
-    const anthropic = this.session.anthropic;
 
     if (tools) {
       const params: MessageCreateParamsNonStreaming = {
@@ -378,7 +427,10 @@ export class Anthropic extends ToolCallLLM<AnthropicAdditionalChatOptions> {
                   toolCall: toolUseBlock.map((block) => ({
                     id: block.id,
                     name: block.name,
-                    input: block.input,
+                    input:
+                      typeof block.input === "object"
+                        ? JSON.stringify(block.input)
+                        : `${block.input}`,
                   })),
                 }
               : {},
@@ -411,10 +463,11 @@ export class Anthropic extends ToolCallLLM<AnthropicAdditionalChatOptions> {
   }
 
   protected async *streamChat(
-    messages: ChatMessage<ToolCallLLMMessageOptions>[],
+    messages: ChatMessage<AnthropicToolCallLLMMessageOptions>[],
-    systemPrompt?: string | null,
+    systemPrompt: string | Array<BetaTextBlockParam> | null,
-  ): AsyncIterable<ChatResponseChunk<ToolCallLLMMessageOptions>> {
+    anthropic: SDKAnthropic,
-    const stream = await this.session.anthropic.messages.create({
+  ): AsyncIterable<ChatResponseChunk<AnthropicToolCallLLMMessageOptions>> {
+    const stream = await anthropic.messages.create({
       model: this.getModelName(this.model),
       messages: this.formatMessages(messages),
       max_tokens: this.maxTokens ?? 4096,

packages/providers/clip/CHANGELOG.md

@@ -1,5 +1,47 @@
 # @llamaindex/clip
 
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+  - @llamaindex/openai@0.1.38
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+  - @llamaindex/openai@0.1.37
+
+## 0.0.20
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+  - @llamaindex/openai@0.1.36
+
+## 0.0.19
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+  - @llamaindex/openai@0.1.35
+
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+  - @llamaindex/openai@0.1.34
+
 ## 0.0.17
 
 ### Patch Changes

packages/providers/clip/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/clip",
   "description": "Clip Embedding Adapter for LlamaIndex",
-  "version": "0.0.17",
+  "version": "0.0.22",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/deepinfra/CHANGELOG.md

@@ -1,5 +1,47 @@
 # @llamaindex/deepinfra
 
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+  - @llamaindex/openai@0.1.38
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+  - @llamaindex/openai@0.1.37
+
+## 0.0.20
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+  - @llamaindex/openai@0.1.36
+
+## 0.0.19
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+  - @llamaindex/openai@0.1.35
+
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+  - @llamaindex/openai@0.1.34
+
 ## 0.0.17
 
 ### Patch Changes

packages/providers/deepinfra/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepinfra",
   "description": "Deepinfra Adapter for LlamaIndex",
-  "version": "0.0.17",
+  "version": "0.0.22",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/groq/CHANGELOG.md

@@ -1,5 +1,39 @@
 # @llamaindex/groq
 
+## 0.0.37
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/env@0.1.21
+  - @llamaindex/openai@0.1.38
+
+## 0.0.36
+
+### Patch Changes
+
+- @llamaindex/openai@0.1.37
+
+## 0.0.35
+
+### Patch Changes
+
+- @llamaindex/openai@0.1.36
+
+## 0.0.34
+
+### Patch Changes
+
+- @llamaindex/openai@0.1.35
+
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/openai@0.1.34
+
 ## 0.0.32
 
 ### Patch Changes

packages/providers/groq/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/groq",
   "description": "Groq Adapter for LlamaIndex",
-  "version": "0.0.32",
+  "version": "0.0.37",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -35,6 +35,6 @@
   "dependencies": {
     "@llamaindex/env": "workspace:*",
     "@llamaindex/openai": "workspace:*",
-    "groq-sdk": "0.6.1"
+    "groq-sdk": "0.8.0"
   }
 }

packages/providers/huggingface/CHANGELOG.md

@@ -1,5 +1,47 @@
 # @llamaindex/huggingface
 
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+  - @llamaindex/openai@0.1.38
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+  - @llamaindex/openai@0.1.37
+
+## 0.0.20
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+  - @llamaindex/openai@0.1.36
+
+## 0.0.19
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+  - @llamaindex/openai@0.1.35
+
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+  - @llamaindex/openai@0.1.34
+
 ## 0.0.17
 
 ### Patch Changes

packages/providers/huggingface/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/huggingface",
   "description": "Huggingface Adapter for LlamaIndex",
-  "version": "0.0.17",
+  "version": "0.0.22",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/ollama/CHANGELOG.md

@@ -1,5 +1,43 @@
 # @llamaindex/ollama
 
+## 0.0.29
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+
+## 0.0.28
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+
+## 0.0.27
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+
+## 0.0.26
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+
+## 0.0.25
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
 ## 0.0.24
 
 ### Patch Changes

packages/providers/ollama/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/ollama",
   "description": "Ollama Adapter for LlamaIndex",
-  "version": "0.0.24",
+  "version": "0.0.29",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -35,7 +35,7 @@
   "dependencies": {
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
-    "ollama": "^0.5.9",
+    "ollama": "^0.5.10",
-    "remeda": "^2.12.0"
+    "remeda": "^2.17.3"
   }
 }

packages/providers/ollama/src/agent.ts

@@ -8,7 +8,7 @@ import { Ollama } from "./llm";
 
 // This is likely not necessary anymore but leaving it here just incase it's in use elsewhere
 
-export type OllamaAgentParams = LLMAgentParams & {
+export type OllamaAgentParams = LLMAgentParams<Ollama> & {
   model?: string;
 };
 

packages/providers/openai/CHANGELOG.md

@@ -1,5 +1,44 @@
 # @llamaindex/openai
 
+## 0.1.38
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+
+## 0.1.37
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+
+## 0.1.36
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+
+## 0.1.35
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+
+## 0.1.34
+
+### Patch Changes
+
+- 7ae6eaa: feat: allow pass `additionalChatOptions` to agent
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
 ## 0.1.33
 
 ### Patch Changes

packages/providers/openai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/openai",
   "description": "OpenAI Adapter for LlamaIndex",
-  "version": "0.1.33",
+  "version": "0.1.38",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -35,7 +35,6 @@
   "dependencies": {
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
-    "openai": "^4.68.1",
+    "openai": "^4.72.0"
-    "remeda": "^2.12.0"
   }
 }

packages/providers/openai/src/agent.ts

@@ -4,11 +4,16 @@ import {
   type LLMAgentParams,
 } from "@llamaindex/core/agent";
 import { Settings } from "@llamaindex/core/global";
-import { OpenAI } from "./llm";
+import type { ToolCallLLMMessageOptions } from "@llamaindex/core/llms";
+import { OpenAI, type OpenAIAdditionalChatOptions } from "./llm";
 
-// This is likely not necessary anymore but leaving it here just incase it's in use elsewhere
+// This is likely not necessary anymore but leaving it here just in case it's in use elsewhere
 
-export type OpenAIAgentParams = LLMAgentParams;
+export type OpenAIAgentParams = LLMAgentParams<
+  OpenAI,
+  ToolCallLLMMessageOptions,
+  OpenAIAdditionalChatOptions
+>;
 
 export class OpenAIAgentWorker extends LLMAgentWorker {}
 

packages/providers/portkey-ai/CHANGELOG.md

@@ -1,5 +1,43 @@
 # @llamaindex/portkey-ai
 
+## 0.0.22
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+
+## 0.0.20
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+
+## 0.0.19
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
 ## 0.0.17
 
 ### Patch Changes

packages/providers/portkey-ai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/portkey-ai",
   "description": "Portkey Adapter for LlamaIndex",
-  "version": "0.0.17",
+  "version": "0.0.22",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -36,6 +36,6 @@
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
     "portkey-ai": "0.1.16",
-    "remeda": "^2.12.0"
+    "remeda": "^2.17.3"
   }
 }

packages/providers/replicate/CHANGELOG.md

@@ -1,5 +1,42 @@
 # @llamaindex/replicate
 
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+
+## 0.0.20
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+
+## 0.0.19
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
 ## 0.0.17
 
 ### Patch Changes