Release 0.9.6 (#1698)

Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>

.github/workflows/test.yml

@@ -119,6 +119,7 @@ jobs:
 
   size-limit:
     runs-on: ubuntu-latest
+    if: github.event_name == 'pull_request'
     name: Size Limit
     steps:
       - uses: actions/checkout@v4
@@ -132,12 +133,13 @@ jobs:
         run: pnpm install
       - name: Build llamaindex
         run: pnpm run build
-      - uses: andresz1/size-limit-action@v1
+      - uses: andresz1/size-limit-action@94bc357df29c36c8f8d50ea497c3e225c3c95d1d
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           directory: e2e/examples/vite-import-llamaindex
           skip_step: "install"
           build_script: build
+          package_manager: pnpm
 
   typecheck-examples:
     runs-on: ubuntu-latest

CONTRIBUTING.md

@@ -41,8 +41,15 @@ pnpm install
 
 ### Build the packages
 
+You'll need Turbo to build the packages. If you don't have it, you can run it with `pnpx`.
+
+To build all packages, run:
+
 ```shell
 # Build all packages
+pnpx turbo build --filter "./packages/*"
+
+# Or if you have turbo installed, you can run:
 turbo build --filter "./packages/*"
 ```
 

apps/next/CHANGELOG.md

@@ -1,5 +1,64 @@
 # @llamaindex/doc
 
+## 0.1.6
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+  - @llamaindex/workflow@0.0.12
+  - @llamaindex/cloud@3.0.6
+  - llamaindex@0.9.6
+  - @llamaindex/node-parser@1.0.5
+  - @llamaindex/openai@0.1.57
+  - @llamaindex/readers@2.0.5
+
+## 0.1.5
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+  - @llamaindex/cloud@3.0.5
+  - llamaindex@0.9.5
+  - @llamaindex/node-parser@1.0.4
+  - @llamaindex/openai@0.1.56
+  - @llamaindex/readers@2.0.4
+
+## 0.1.4
+
+### Patch Changes
+
+- Updated dependencies [cb256f2]
+- Updated dependencies [cb021e7]
+  - @llamaindex/openai@0.1.55
+  - @llamaindex/core@0.5.3
+  - llamaindex@0.9.4
+  - @llamaindex/cloud@3.0.4
+  - @llamaindex/node-parser@1.0.3
+  - @llamaindex/readers@2.0.3
+
+## 0.1.3
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+  - @llamaindex/cloud@3.0.3
+  - llamaindex@0.9.3
+  - @llamaindex/node-parser@1.0.2
+  - @llamaindex/openai@0.1.54
+  - @llamaindex/readers@2.0.2
+
+## 0.1.2
+
+### Patch Changes
+
+- Updated dependencies [c902fcb]
+- Updated dependencies [88d776f]
+  - @llamaindex/cloud@3.0.2
+  - llamaindex@0.9.2
+
 ## 0.1.1
 
 ### Patch Changes

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.1.1",
+  "version": "0.1.6",
   "private": true,
   "scripts": {
     "build": "pnpm run build:docs && next build",
@@ -44,10 +44,10 @@
     "hast-util-to-jsx-runtime": "^2.3.2",
     "llamaindex": "workspace:*",
     "lucide-react": "^0.460.0",
-    "next": "15.0.3",
+    "next": "15.1.7",
     "next-themes": "^0.4.3",
-    "react": "^18.3.1",
-    "react-dom": "^18.3.1",
+    "react": "^19.0.0",
+    "react-dom": "^19.0.0",
     "react-icons": "^5.3.0",
     "react-monaco-editor": "^0.56.2",
     "react-text-transition": "^3.1.0",

apps/next/src/content/docs/llamaindex/modules/agent_workflow.mdx

@@ -0,0 +1,139 @@
+---
+title: Agent Workflow
+---
+
+import { DynamicCodeBlock } from 'fumadocs-ui/components/dynamic-codeblock';
+import CodeSource from "!raw-loader!../../../../../../../examples/agentworkflow/blog_writer.ts";
+import { Tab, Tabs } from "fumadocs-ui/components/tabs";
+
+`AgentWorkflow` is a powerful system that enables you to create and orchestrate one or multiple agents with tools to perform specific tasks. It's built on top of the base `Workflow` system and provides a streamlined interface for agent interactions.
+
+## Installation
+
+You'll need to install the `@llamaindex/workflow` package:
+
+<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
+	```shell tab="npm"
+	npm install @llamaindex/workflow
+	```
+
+	```shell tab="yarn"
+	yarn add @llamaindex/workflow
+	```
+
+	```shell tab="pnpm"
+	pnpm add @llamaindex/workflow
+	```
+</Tabs>
+
+## Usage
+
+### Single Agent Workflow
+
+The simplest use case is creating a single agent with specific tools. Here's an example of creating an assistant that tells jokes:
+
+```typescript
+import { AgentWorkflow, FunctionTool } from "llamaindex";
+import { OpenAI } from "@llamaindex/openai";
+
+// Define a joke-telling tool
+const jokeTool = FunctionTool.from(
+  () => "Baby Llama is called cria",
+  {
+    name: "joke",
+    description: "Use this tool to get a joke",
+  }
+);
+
+// Create an agent workflow with the tool
+const workflow = AgentWorkflow.fromTools({
+  tools: [jokeTool],
+  llm: new OpenAI({
+    model: "gpt-4o-mini",
+  }),
+});
+
+// Run the workflow
+const result = await workflow.run("Tell me something funny");
+console.log(result); // Baby Llama is called cria
+```
+
+### Event Streaming
+
+`AgentWorkflow` provides a unified interface for event streaming, making it easy to track and respond to different events during execution:
+
+```typescript
+import { AgentToolCall, AgentStream } from "llamaindex";
+
+// Get the workflow execution context
+const context = workflow.run("Tell me something funny");
+
+// Stream and handle events
+for await (const event of context) {
+  if (event instanceof AgentToolCall) {
+    console.log(`Tool being called: ${event.data.toolName}`);
+  }
+  if (event instanceof AgentStream) {
+    process.stdout.write(event.data.delta);
+  }
+}
+```
+
+### Multi-Agent Workflow
+
+`AgentWorkflow` can orchestrate multiple agents, enabling complex interactions and task handoffs. Each agent in a multi-agent workflow requires:
+
+- `name`: Unique identifier for the agent
+- `description`: Purpose description used for task routing
+- `tools`: Array of tools the agent can use
+- `canHandoffTo` (optional): Array of agent names or agent instances that this agent can delegate tasks to
+
+Here's an example of a multi-agent system that combines joke-telling and weather information:
+
+```typescript
+import { AgentWorkflow, FunctionAgent, FunctionTool } from "llamaindex";
+import { OpenAI } from "@llamaindex/openai";
+import { z } from "zod";
+
+// Create a weather agent
+const weatherAgent = new FunctionAgent({
+  name: "WeatherAgent",
+  description: "Provides weather information for any city",
+  tools: [
+    FunctionTool.from(
+      ({ city }: { city: string }) => `The weather in ${city} is sunny`,
+      {
+        name: "fetchWeather",
+        description: "Get weather information for a city",
+        parameters: z.object({
+          city: z.string(),
+        }),
+      }
+    ),
+  ],
+  llm: new OpenAI({ model: "gpt-4o-mini" }),
+});
+
+// Create a joke-telling agent
+const jokeAgent = new FunctionAgent({
+  name: "JokeAgent",
+  description: "Tells jokes and funny stories",
+  tools: [jokeTool], // Using the joke tool defined earlier
+  llm: new OpenAI({ model: "gpt-4o-mini" }),
+  canHandoffTo: [weatherAgent], // Can hand off to the weather agent
+});
+
+// Create the multi-agent workflow
+const workflow = new AgentWorkflow({
+  agents: [jokeAgent, weatherAgent],
+  rootAgent: jokeAgent, // Start with the joke agent
+});
+
+// Run the workflow
+const result = await workflow.run(
+  "Give me a morning greeting with a joke and the weather in San Francisco"
+);
+```
+
+The workflow will coordinate between agents, allowing them to handle different aspects of the request and hand off tasks when appropriate.
+

apps/next/src/content/docs/llamaindex/modules/embeddings/available_embeddings/voyageai.mdx

@@ -0,0 +1,46 @@
+---
+title: VoyageAI
+---
+
+To use VoyageAI embeddings, you need to import `VoyageAIEmbedding` from `@llamaindex/voyage-ai`.
+
+## Installation
+
+import { Tab, Tabs } from "fumadocs-ui/components/tabs";
+
+<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
+	```shell tab="npm"
+	npm install llamaindex @llamaindex/voyage-ai
+	```
+
+	```shell tab="yarn"
+	yarn add llamaindex @llamaindex/voyage-ai
+	```
+
+	```shell tab="pnpm"
+	pnpm add llamaindex @llamaindex/voyage-ai
+	```
+</Tabs>
+
+```ts
+import { VoyageAIEmbedding } from "@llamaindex/voyage-ai";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
+
+Settings.embedModel = new VoyageAIEmbedding();
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```
+
+## API Reference
+
+- [VoyageAIEmbedding](/docs/api/classes/VoyageAIEmbedding)

apps/next/src/content/docs/llamaindex/modules/embeddings/index.mdx

@@ -37,6 +37,31 @@ Settings.embedModel = new OpenAIEmbedding({
 
 For local embeddings, you can use the [HuggingFace](/docs/llamaindex/modules/embeddings/available_embeddings/huggingface) embedding model.
 
+## Local Ollama Embeddings With Remote Host
+
+Ollama provides a way to run embedding models locally or connect to a remote Ollama instance. This is particularly useful when you need to:
+- Run embeddings without relying on external API services
+- Use custom embedding models
+- Connect to a shared Ollama instance in your network
+
+The ENV variable method you will find elsewhere sometimes may not work with the OllamaEmbedding class. Also note, you'll need to change the host
+in the Ollama server to `0.0.0.0` to allow connections from other machines.
+
+To use Ollama embeddings with a remote host, you need to specify the host URL in the configuration like this:
+
+```typescript
+import { OllamaEmbedding } from "@llamaindex/ollama";
+import { Settings } from "llamaindex";
+
+// Configure Ollama with a remote host
+Settings.embedModel = new OllamaEmbedding({
+  model: "nomic-embed-text",
+  config: {
+    host: "http://your-ollama-host:11434"
+  }
+});
+```
+
 ## Available Embeddings
 
 Most available embeddings are listed in the sidebar on the left.

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

@@ -1,5 +1,37 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.140
+
+### Patch Changes
+
+- llamaindex@0.9.6
+
+## 0.0.139
+
+### Patch Changes
+
+- llamaindex@0.9.5
+
+## 0.0.138
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - llamaindex@0.9.4
+
+## 0.0.137
+
+### Patch Changes
+
+- llamaindex@0.9.3
+
+## 0.0.136
+
+### Patch Changes
+
+- Updated dependencies [88d776f]
+  - llamaindex@0.9.2
+
 ## 0.0.135
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.135",
+  "version": "0.0.140",
   "type": "module",
   "private": true,
   "scripts": {

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

@@ -1,5 +1,36 @@
 # @llamaindex/llama-parse-browser-test
 
+## 0.0.51
+
+### Patch Changes
+
+- @llamaindex/cloud@3.0.6
+
+## 0.0.50
+
+### Patch Changes
+
+- @llamaindex/cloud@3.0.5
+
+## 0.0.49
+
+### Patch Changes
+
+- @llamaindex/cloud@3.0.4
+
+## 0.0.48
+
+### Patch Changes
+
+- @llamaindex/cloud@3.0.3
+
+## 0.0.47
+
+### Patch Changes
+
+- Updated dependencies [c902fcb]
+  - @llamaindex/cloud@3.0.2
+
 ## 0.0.46
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.46",
+  "version": "0.0.51",
   "type": "module",
   "scripts": {
     "dev": "vite",

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,37 @@
 # @llamaindex/next-agent-test
 
+## 0.1.140
+
+### Patch Changes
+
+- llamaindex@0.9.6
+
+## 0.1.139
+
+### Patch Changes
+
+- llamaindex@0.9.5
+
+## 0.1.138
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - llamaindex@0.9.4
+
+## 0.1.137
+
+### Patch Changes
+
+- llamaindex@0.9.3
+
+## 0.1.136
+
+### Patch Changes
+
+- Updated dependencies [88d776f]
+  - llamaindex@0.9.2
+
 ## 0.1.135
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.135",
+  "version": "0.1.140",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -10,9 +10,9 @@
   "dependencies": {
     "ai": "^4.0.0",
     "llamaindex": "workspace:*",
-    "next": "15.0.3",
-    "react": "18.3.1",
-    "react-dom": "18.3.1"
+    "next": "15.1.7",
+    "react": "19.0.0",
+    "react-dom": "19.0.0"
   },
   "devDependencies": {
     "@types/node": "^22.9.0",

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

@@ -1,5 +1,37 @@
 # test-edge-runtime
 
+## 0.1.139
+
+### Patch Changes
+
+- llamaindex@0.9.6
+
+## 0.1.138
+
+### Patch Changes
+
+- llamaindex@0.9.5
+
+## 0.1.137
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - llamaindex@0.9.4
+
+## 0.1.136
+
+### Patch Changes
+
+- llamaindex@0.9.3
+
+## 0.1.135
+
+### Patch Changes
+
+- Updated dependencies [88d776f]
+  - llamaindex@0.9.2
+
 ## 0.1.134
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.134",
+  "version": "0.1.139",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -9,7 +9,7 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "next": "15.0.3",
+    "next": "15.1.7",
     "react": "^18.3.1",
     "react-dom": "^18.3.1"
   },

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

@@ -1,5 +1,45 @@
 # @llamaindex/next-node-runtime
 
+## 0.1.6
+
+### Patch Changes
+
+- llamaindex@0.9.6
+- @llamaindex/huggingface@0.0.41
+- @llamaindex/readers@2.0.5
+
+## 0.1.5
+
+### Patch Changes
+
+- llamaindex@0.9.5
+- @llamaindex/huggingface@0.0.40
+- @llamaindex/readers@2.0.4
+
+## 0.1.4
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - llamaindex@0.9.4
+  - @llamaindex/huggingface@0.0.39
+  - @llamaindex/readers@2.0.3
+
+## 0.1.3
+
+### Patch Changes
+
+- llamaindex@0.9.3
+- @llamaindex/huggingface@0.0.38
+- @llamaindex/readers@2.0.2
+
+## 0.1.2
+
+### Patch Changes
+
+- Updated dependencies [88d776f]
+  - llamaindex@0.9.2
+
 ## 0.1.1
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.1",
+  "version": "0.1.6",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -11,9 +11,9 @@
     "llamaindex": "workspace:*",
     "@llamaindex/huggingface": "workspace:*",
     "@llamaindex/readers": "workspace:*",
-    "next": "15.0.3",
-    "react": "18.3.1",
-    "react-dom": "18.3.1"
+    "next": "15.1.7",
+    "react": "19.0.0",
+    "react-dom": "19.0.0"
   },
   "devDependencies": {
     "@types/node": "^22.9.0",

e2e/examples/vite-import-llamaindex/CHANGELOG.md

@@ -1,5 +1,37 @@
 # vite-import-llamaindex
 
+## 0.0.6
+
+### Patch Changes
+
+- llamaindex@0.9.6
+
+## 0.0.5
+
+### Patch Changes
+
+- llamaindex@0.9.5
+
+## 0.0.4
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - llamaindex@0.9.4
+
+## 0.0.3
+
+### Patch Changes
+
+- llamaindex@0.9.3
+
+## 0.0.2
+
+### Patch Changes
+
+- Updated dependencies [88d776f]
+  - llamaindex@0.9.2
+
 ## 0.0.1
 
 ### Patch Changes

e2e/examples/vite-import-llamaindex/package.json

@@ -1,7 +1,7 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.1",
+  "version": "0.0.6",
   "type": "module",
   "scripts": {
     "build": "vite build",

e2e/examples/waku-query-engine/.gitignore

@@ -5,3 +5,4 @@ dist
 .cache
 .DS_Store
 *.pem
+/src/pages.gen.ts

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

@@ -1,5 +1,37 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.140
+
+### Patch Changes
+
+- llamaindex@0.9.6
+
+## 0.0.139
+
+### Patch Changes
+
+- llamaindex@0.9.5
+
+## 0.0.138
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - llamaindex@0.9.4
+
+## 0.0.137
+
+### Patch Changes
+
+- llamaindex@0.9.3
+
+## 0.0.136
+
+### Patch Changes
+
+- Updated dependencies [88d776f]
+  - llamaindex@0.9.2
+
 ## 0.0.135
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.135",
+  "version": "0.0.140",
   "type": "module",
   "private": true,
   "scripts": {
@@ -11,10 +11,10 @@
   "dependencies": {
     "@llamaindex/env": "workspace:*",
     "llamaindex": "workspace:*",
-    "react": "19.0.0-rc-5c56b873-20241107",
-    "react-dom": "19.0.0-rc-5c56b873-20241107",
-    "react-server-dom-webpack": "19.0.0-rc-5c56b873-20241107",
-    "waku": "0.21.6"
+    "react": "19.0.0",
+    "react-dom": "19.0.0",
+    "react-server-dom-webpack": "19.0.0",
+    "waku": "0.21.20"
   },
   "devDependencies": {
     "@types/react": "18.3.12",

examples/CHANGELOG.md

@@ -1,5 +1,166 @@
 # examples
 
+## 0.2.5
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+- Updated dependencies [fd74ba4]
+  - @llamaindex/core@0.5.5
+  - @llamaindex/workflow@0.0.12
+  - @llamaindex/voyage-ai@1.0.2
+  - @llamaindex/cloud@3.0.6
+  - llamaindex@0.9.6
+  - @llamaindex/node-parser@1.0.5
+  - @llamaindex/anthropic@0.2.3
+  - @llamaindex/clip@0.0.41
+  - @llamaindex/cohere@0.0.10
+  - @llamaindex/deepinfra@0.0.41
+  - @llamaindex/google@0.0.12
+  - @llamaindex/huggingface@0.0.41
+  - @llamaindex/mistral@0.0.10
+  - @llamaindex/mixedbread@0.0.10
+  - @llamaindex/ollama@0.0.45
+  - @llamaindex/openai@0.1.57
+  - @llamaindex/portkey-ai@0.0.38
+  - @llamaindex/replicate@0.0.38
+  - @llamaindex/astra@0.0.10
+  - @llamaindex/azure@0.1.5
+  - @llamaindex/chroma@0.0.10
+  - @llamaindex/firestore@1.0.3
+  - @llamaindex/milvus@0.1.5
+  - @llamaindex/mongodb@0.0.10
+  - @llamaindex/pinecone@0.0.10
+  - @llamaindex/postgres@0.0.38
+  - @llamaindex/qdrant@0.1.5
+  - @llamaindex/upstash@0.0.10
+  - @llamaindex/weaviate@0.0.10
+  - @llamaindex/vercel@0.0.16
+  - @llamaindex/readers@2.0.5
+  - @llamaindex/groq@0.0.56
+  - @llamaindex/vllm@0.0.27
+
+## 0.2.4
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+  - @llamaindex/cloud@3.0.5
+  - llamaindex@0.9.5
+  - @llamaindex/node-parser@1.0.4
+  - @llamaindex/anthropic@0.2.2
+  - @llamaindex/clip@0.0.40
+  - @llamaindex/cohere@0.0.9
+  - @llamaindex/deepinfra@0.0.40
+  - @llamaindex/google@0.0.11
+  - @llamaindex/huggingface@0.0.40
+  - @llamaindex/mistral@0.0.9
+  - @llamaindex/mixedbread@0.0.9
+  - @llamaindex/ollama@0.0.44
+  - @llamaindex/openai@0.1.56
+  - @llamaindex/portkey-ai@0.0.37
+  - @llamaindex/replicate@0.0.37
+  - @llamaindex/astra@0.0.9
+  - @llamaindex/azure@0.1.4
+  - @llamaindex/chroma@0.0.9
+  - @llamaindex/firestore@1.0.2
+  - @llamaindex/milvus@0.1.4
+  - @llamaindex/mongodb@0.0.9
+  - @llamaindex/pinecone@0.0.9
+  - @llamaindex/postgres@0.0.37
+  - @llamaindex/qdrant@0.1.4
+  - @llamaindex/upstash@0.0.9
+  - @llamaindex/weaviate@0.0.9
+  - @llamaindex/vercel@0.0.15
+  - @llamaindex/voyage-ai@1.0.1
+  - @llamaindex/readers@2.0.4
+  - @llamaindex/groq@0.0.55
+  - @llamaindex/vllm@0.0.26
+
+## 0.2.3
+
+### Patch Changes
+
+- Updated dependencies [cb256f2]
+- Updated dependencies [cb021e7]
+- Updated dependencies [0346391]
+  - @llamaindex/openai@0.1.55
+  - @llamaindex/core@0.5.3
+  - llamaindex@0.9.4
+  - @llamaindex/voyage-ai@1.0.0
+  - @llamaindex/clip@0.0.39
+  - @llamaindex/deepinfra@0.0.39
+  - @llamaindex/groq@0.0.54
+  - @llamaindex/huggingface@0.0.39
+  - @llamaindex/azure@0.1.3
+  - @llamaindex/milvus@0.1.3
+  - @llamaindex/qdrant@0.1.3
+  - @llamaindex/vllm@0.0.25
+  - @llamaindex/cloud@3.0.4
+  - @llamaindex/node-parser@1.0.3
+  - @llamaindex/anthropic@0.2.1
+  - @llamaindex/cohere@0.0.8
+  - @llamaindex/google@0.0.10
+  - @llamaindex/mistral@0.0.8
+  - @llamaindex/mixedbread@0.0.8
+  - @llamaindex/ollama@0.0.43
+  - @llamaindex/portkey-ai@0.0.36
+  - @llamaindex/replicate@0.0.36
+  - @llamaindex/astra@0.0.8
+  - @llamaindex/chroma@0.0.8
+  - @llamaindex/firestore@1.0.1
+  - @llamaindex/mongodb@0.0.8
+  - @llamaindex/pinecone@0.0.8
+  - @llamaindex/postgres@0.0.36
+  - @llamaindex/upstash@0.0.8
+  - @llamaindex/weaviate@0.0.8
+  - @llamaindex/vercel@0.0.14
+  - @llamaindex/readers@2.0.3
+
+## 0.2.2
+
+### Patch Changes
+
+- 3564244: Add support for claude 3.7 thinking (and set default temperature to 1)
+- 3564244: add support for claude 3.7
+- Updated dependencies [d952e68]
+- Updated dependencies [a9c6144]
+- Updated dependencies [5c026e8]
+- Updated dependencies [3564244]
+- Updated dependencies [3564244]
+  - @llamaindex/core@0.5.2
+  - @llamaindex/anthropic@0.2.0
+  - @llamaindex/firestore@1.0.0
+  - @llamaindex/cloud@3.0.3
+  - llamaindex@0.9.3
+  - @llamaindex/node-parser@1.0.2
+  - @llamaindex/clip@0.0.38
+  - @llamaindex/cohere@0.0.7
+  - @llamaindex/deepinfra@0.0.38
+  - @llamaindex/google@0.0.9
+  - @llamaindex/huggingface@0.0.38
+  - @llamaindex/mistral@0.0.7
+  - @llamaindex/mixedbread@0.0.7
+  - @llamaindex/ollama@0.0.42
+  - @llamaindex/openai@0.1.54
+  - @llamaindex/portkey-ai@0.0.35
+  - @llamaindex/replicate@0.0.35
+  - @llamaindex/astra@0.0.7
+  - @llamaindex/azure@0.1.2
+  - @llamaindex/chroma@0.0.7
+  - @llamaindex/milvus@0.1.2
+  - @llamaindex/mongodb@0.0.7
+  - @llamaindex/pinecone@0.0.7
+  - @llamaindex/postgres@0.0.35
+  - @llamaindex/qdrant@0.1.2
+  - @llamaindex/upstash@0.0.7
+  - @llamaindex/weaviate@0.0.7
+  - @llamaindex/vercel@0.0.13
+  - @llamaindex/readers@2.0.2
+  - @llamaindex/groq@0.0.53
+  - @llamaindex/vllm@0.0.24
+
 ## 0.2.1
 
 ### Patch Changes

examples/agentworkflow/blog_writer.ts

@@ -0,0 +1,83 @@
+import { OpenAI } from "@llamaindex/openai";
+import fs from "fs";
+import {
+  AgentToolCall,
+  AgentToolCallResult,
+  AgentWorkflow,
+  FunctionAgent,
+  FunctionTool,
+} from "llamaindex";
+import os from "os";
+import { z } from "zod";
+
+import { WikipediaTool } from "../wiki";
+const llm = new OpenAI({
+  model: "gpt-4o-mini",
+});
+
+const saveFileTool = FunctionTool.from(
+  ({ content }: { content: string }) => {
+    const filePath = os.tmpdir() + "/report.md";
+    fs.writeFileSync(filePath, content);
+    return `File saved successfully at ${filePath}`;
+  },
+  {
+    name: "saveFile",
+    description:
+      "Save the written content into a file that can be downloaded by the user",
+    parameters: z.object({
+      content: z.string({
+        description: "The content to save into a file",
+      }),
+    }),
+  },
+);
+
+async function main() {
+  const reportAgent = new FunctionAgent({
+    name: "ReportAgent",
+    description:
+      "Responsible for crafting well-written blog posts based on research findings",
+    systemPrompt: `You are a professional writer. Your task is to create an engaging blog post using the research content provided. Once complete, save the post to a file using the saveFile tool.`,
+    tools: [saveFileTool],
+    llm,
+  });
+
+  const researchAgent = new FunctionAgent({
+    name: "ResearchAgent",
+    description:
+      "Responsible for gathering relevant information from the internet",
+    systemPrompt: `You are a research agent. Your role is to gather information from the internet using the provided tools and then transfer this information to the report agent for content creation.`,
+    tools: [new WikipediaTool()],
+    canHandoffTo: [reportAgent],
+    llm,
+  });
+
+  const workflow = new AgentWorkflow({
+    agents: [researchAgent, reportAgent],
+    rootAgent: researchAgent,
+  });
+
+  const context = workflow.run("Write a blog post about history of LLM");
+
+  let finalResult;
+  for await (const event of context) {
+    if (event instanceof AgentToolCall) {
+      console.log(
+        `[Agent ${event.displayName}] executing tool ${event.data.toolName} with parameters ${JSON.stringify(
+          event.data.toolKwargs,
+        )}`,
+      );
+    } else if (event instanceof AgentToolCallResult) {
+      console.log(
+        `[Agent ${event.displayName}] executed tool ${event.data.toolName} with result ${event.data.toolOutput.result}`,
+      );
+    }
+    finalResult = event;
+  }
+  console.log("Final result:", finalResult?.data);
+}
+
+main().catch((error) => {
+  console.error("Error:", error);
+});

examples/agentworkflow/multiple_agents.ts

@@ -0,0 +1,110 @@
+/**
+ * This example shows how to use AgentWorkflow with multiple agents
+ * 1. FetchWeatherAgent - Fetches the weather in a city
+ * 2. TemperatureConverterAgent - Converts the temperature from Fahrenheit to Celsius
+ */
+import { OpenAI } from "@llamaindex/openai";
+import { StopEvent } from "@llamaindex/workflow";
+import {
+  AgentInput,
+  AgentOutput,
+  AgentStream,
+  AgentToolCall,
+  AgentToolCallResult,
+  AgentWorkflow,
+  FunctionAgent,
+  FunctionTool,
+} from "llamaindex";
+import { z } from "zod";
+
+const llm = new OpenAI({
+  model: "gpt-4o-mini",
+});
+
+// Define tools for the agents
+const temperatureConverterTool = FunctionTool.from(
+  ({ temperature }: { temperature: number }) => {
+    return ((temperature - 32) * 5) / 9;
+  },
+  {
+    description: "Convert a temperature from Fahrenheit to Celsius",
+    name: "fahrenheitToCelsius",
+    parameters: z.object({
+      temperature: z.number({
+        description: "The temperature in Fahrenheit",
+      }),
+    }),
+  },
+);
+
+const temperatureFetcherTool = FunctionTool.from(
+  ({ city }: { city: string }) => {
+    const temperature = Math.floor(Math.random() * 58) + 32;
+    return `The current temperature in ${city} is ${temperature}°F`;
+  },
+  {
+    description: "Fetch the temperature (in Fahrenheit) for a city",
+    name: "fetchTemperature",
+    parameters: z.object({
+      city: z.string({
+        description: "The city to fetch the temperature for",
+      }),
+    }),
+  },
+);
+
+// Create agents
+async function multiWeatherAgent() {
+  const converterAgent = new FunctionAgent({
+    name: "TemperatureConverterAgent",
+    description:
+      "An agent that can convert temperatures from Fahrenheit to Celsius.",
+    tools: [temperatureConverterTool],
+    llm,
+  });
+
+  const weatherAgent = new FunctionAgent({
+    name: "FetchWeatherAgent",
+    description: "An agent that can get the weather in a city. ",
+    systemPrompt:
+      "If you can't answer the user question, hand off to other agents.",
+    tools: [temperatureFetcherTool],
+    llm,
+    // Define which next agents can be called next if this agent cannot complete the task
+    // Can be passed as agent name, e.g. "TemperatureConverterAgent"
+    canHandoffTo: [converterAgent],
+  });
+
+  // Create agent workflow with the agents
+  const workflow = new AgentWorkflow({
+    agents: [weatherAgent, converterAgent],
+    rootAgent: weatherAgent,
+    verbose: false,
+  });
+
+  // Ask the agent to get the weather in a city
+  const context = workflow.run(
+    "What is the weather in San Francisco in Celsius?",
+  );
+  // Stream the events
+  for await (const event of context) {
+    // These events might be useful for UI
+    if (
+      event instanceof AgentToolCall ||
+      event instanceof AgentToolCallResult ||
+      event instanceof AgentOutput ||
+      event instanceof AgentInput ||
+      event instanceof StopEvent
+    ) {
+      console.log(event);
+    } else if (event instanceof AgentStream) {
+      for (const chunk of event.data.delta) {
+        process.stdout.write(chunk);
+      }
+    }
+  }
+}
+
+multiWeatherAgent().catch((error) => {
+  console.error("Error:", error);
+});

examples/agentworkflow/single_agent.ts

@@ -0,0 +1,37 @@
+/**
+ * This example shows how to use AgentWorkflow as a single agent with tools
+ */
+import { OpenAI } from "@llamaindex/openai";
+import { AgentWorkflow } from "llamaindex";
+import { getWeatherTool } from "../agent/utils/tools";
+
+const llm = new OpenAI({
+  model: "gpt-4o",
+});
+
+async function singleWeatherAgent() {
+  const workflow = AgentWorkflow.fromTools({
+    tools: [getWeatherTool],
+    llm,
+    verbose: false,
+  });
+
+  const workflowContext = workflow.run(
+    "What's the weather like in San Francisco?",
+  );
+  const sfResult = await workflowContext;
+  // The weather in San Francisco, CA is currently sunny.
+  console.log(`${JSON.stringify(sfResult, null, 2)}`);
+
+  // Reuse the context from the previous run
+  const workflowContext2 = workflow.run("Compare it with California?", {
+    context: workflowContext.data,
+  });
+  const caResult = await workflowContext2;
+  // Both San Francisco and California are currently experiencing sunny weather.
+  console.log(`${JSON.stringify(caResult, null, 2)}`);
+}
+
+singleWeatherAgent().catch((error) => {
+  console.error("Error:", error);
+});

examples/anthropic/agent.ts

@@ -8,7 +8,7 @@ Settings.callbackManager.on("llm-tool-call", (event) => {
 
 const anthropic = new Anthropic({
   apiKey: process.env.ANTHROPIC_API_KEY,
-  model: "claude-3-5-sonnet",
+  model: "claude-3-7-sonnet",
 });
 
 const agent = new AnthropicAgent({

examples/anthropic/chat.ts

@@ -3,7 +3,7 @@ import { Anthropic } from "@llamaindex/anthropic";
 (async () => {
   const anthropic = new Anthropic({
     apiKey: process.env.ANTHROPIC_API_KEY,
-    model: "claude-3-opus",
+    model: "claude-3-7-sonnet",
   });
   const result = await anthropic.chat({
     messages: [
@@ -15,5 +15,5 @@ import { Anthropic } from "@llamaindex/anthropic";
       },
     ],
   });
-  console.log(result);
+  console.log(result.message.content);
 })();

examples/anthropic/chat_interactive.ts

@@ -6,7 +6,7 @@ import readline from "node:readline/promises";
 (async () => {
   const llm = new Anthropic({
     apiKey: process.env.ANTHROPIC_API_KEY,
-    model: "claude-3-opus",
+    model: "claude-3-7-sonnet",
   });
   // chatHistory will store all the messages in the conversation
   const chatHistory = new ChatMemoryBuffer({

examples/anthropic/prompt-caching.ts

@@ -2,7 +2,7 @@ import { Anthropic } from "@llamaindex/anthropic";
 
 async function main() {
   const anthropic = new Anthropic({
-    model: "claude-3-5-sonnet-20241022",
+    model: "claude-3-7-sonnet",
   });
 
   const entireBook = await fetch(

examples/anthropic/stream.ts

@@ -3,7 +3,7 @@ import { Anthropic } from "@llamaindex/anthropic";
 (async () => {
   const anthropic = new Anthropic({
     apiKey: process.env.ANTHROPIC_API_KEY,
-    model: "claude-3-5-sonnet",
+    model: "claude-3-7-sonnet",
   });
   const stream = await anthropic.chat({
     messages: [

examples/anthropic/thinking.ts

@@ -0,0 +1,32 @@
+import { Anthropic } from "@llamaindex/anthropic";
+
+(async () => {
+  const anthropic = new Anthropic({
+    model: "claude-3-7-sonnet",
+    maxTokens: 20000,
+    additionalChatOptions: {
+      thinking: {
+        type: "enabled",
+        budget_tokens: 16000,
+      },
+    },
+  });
+  const result = await anthropic.chat({
+    messages: [
+      {
+        role: "user",
+        content:
+          "Are there an infinite number of prime numbers such that n mod 4 == 3?",
+      },
+    ],
+    stream: true,
+  });
+  console.log("Thinking...");
+  for await (const chunk of result) {
+    if (chunk.delta) {
+      process.stdout.write(chunk.delta);
+    } else if (chunk.options?.thinking) {
+      process.stdout.write(chunk.options.thinking);
+    }
+  }
+})();

examples/chat-engine/streaming.ts

@@ -0,0 +1,25 @@
+import { LLMAgent } from "llamaindex";
+import { stdin as input, stdout as output } from "node:process";
+import readline from "node:readline/promises";
+
+const agent = new LLMAgent({ tools: [] });
+
+(async () => {
+  const rl = readline.createInterface({ input, output });
+
+  while (true) {
+    const query = await rl.question("User: ");
+
+    const startTime = Date.now();
+    const stream = await agent.chat({ message: query, stream: true });
+    const timeToGetFirstChunk = Date.now() - startTime;
+    process.stdout.write(
+      `Time to get first chunk from LLMAgent: ${timeToGetFirstChunk}ms\n`,
+    );
+    process.stdout.write("Assistant with LLMAgent: ");
+    for await (const chunk of stream) {
+      process.stdout.write(chunk.response);
+    }
+    process.stdout.write("\n");
+  }
+})();

examples/firestore/.env.template

@@ -0,0 +1,4 @@
+GCP_PROJECT_ID=
+GCP_CREDENTIALS=
+FIRESTORE_DB=
+OPENAI_API_KEY=

examples/firestore/README.md

@@ -0,0 +1,35 @@
+# Firestore Vector Store
+
+Here are some sample scripts which work with loading and querying data from a Firestore Vector Store.
+
+## Prerequisites
+
+- A Firestore Database
+  - Hosted https://console.firebase.google.com/
+- An OpenAI API Key
+
+## Setup
+
+1. Set your env variables:
+
+- `FIRESTORE_DB`: Name of your Firestore database
+- `GCP_PROJECT_ID`: Your GCP project ID
+- `GCP_CREDENTIALS`: Your GCP credentials JSON
+- `OPENAI_API_KEY`: Your OpenAI key
+
+2. `cd` Into the `examples` directory
+3. run `npm i`
+
+## Load the data
+
+This sample loads the same dataset of movie reviews as sample dataset
+
+run `npx tsx firestore/load.ts`
+
+## Use RAG to Query the data
+
+run `npx tsx firestore/query.ts`
+
+## Delete the data
+
+run `npx tsx firestore/delete.ts`

examples/firestore/delete.ts

@@ -0,0 +1,32 @@
+import { CollectionReference } from "@google-cloud/firestore";
+import "dotenv/config";
+
+import { FirestoreVectorStore } from "@llamaindex/firestore";
+import { OpenAIEmbedding, Settings } from "llamaindex";
+
+const indexName = "MovieReviews";
+
+Settings.embedModel = new OpenAIEmbedding();
+
+async function main() {
+  try {
+    const vectorStore = new FirestoreVectorStore({
+      clientOptions: {
+        credentials: JSON.parse(process.env.GCP_CREDENTIALS!),
+        projectId: process.env.GCP_PROJECT_ID!,
+        databaseId: process.env.FIRESTORE_DB!,
+        ignoreUndefinedProperties: true,
+      },
+      collectionName: indexName,
+      customCollectionReference: (rootCollection: CollectionReference) => {
+        return rootCollection.doc("accountId-123").collection("vectors");
+      },
+    });
+
+    vectorStore.delete("movie_reviews.csv");
+  } catch (e) {
+    console.error(e);
+  }
+}
+
+void main();

examples/firestore/load.ts

@@ -0,0 +1,44 @@
+import { CollectionReference } from "@google-cloud/firestore";
+import { CSVReader } from "@llamaindex/readers/csv";
+import "dotenv/config";
+
+import {
+  OpenAIEmbedding,
+  Settings,
+  storageContextFromDefaults,
+  VectorStoreIndex,
+} from "llamaindex";
+
+import { FirestoreVectorStore } from "@llamaindex/firestore";
+
+const indexName = "MovieReviews";
+
+Settings.embedModel = new OpenAIEmbedding();
+
+async function main() {
+  try {
+    const reader = new CSVReader(false);
+    const docs = await reader.loadData("./data/movie_reviews.csv");
+
+    const vectorStore = new FirestoreVectorStore({
+      clientOptions: {
+        credentials: JSON.parse(process.env.GCP_CREDENTIALS!),
+        projectId: process.env.GCP_PROJECT_ID!,
+        databaseId: process.env.FIRESTORE_DB!,
+        ignoreUndefinedProperties: true,
+      },
+      collectionName: indexName,
+      customCollectionReference: (rootCollection: CollectionReference) => {
+        return rootCollection.doc("accountId-123").collection("vectors");
+      },
+    });
+
+    const storageContext = await storageContextFromDefaults({ vectorStore });
+
+    await VectorStoreIndex.fromDocuments(docs, { storageContext });
+  } catch (e) {
+    console.error(e);
+  }
+}
+
+void main();

examples/firestore/query.ts

@@ -0,0 +1,58 @@
+import "dotenv/config";
+
+import { OpenAIEmbedding, Settings, VectorStoreIndex } from "llamaindex";
+
+import { CollectionReference } from "@google-cloud/firestore";
+import { FirestoreVectorStore } from "@llamaindex/firestore";
+
+const indexName = "MovieReviews";
+
+Settings.embedModel = new OpenAIEmbedding();
+
+async function main() {
+  try {
+    const vectorStore = new FirestoreVectorStore({
+      clientOptions: {
+        credentials: JSON.parse(process.env.GCP_CREDENTIALS!),
+        projectId: process.env.GCP_PROJECT_ID!,
+        databaseId: process.env.FIRESTORE_DB!,
+        ignoreUndefinedProperties: true,
+      },
+      collectionName: indexName,
+      customCollectionReference: (rootCollection: CollectionReference) => {
+        return rootCollection.doc("accountId-123").collection("vectors");
+      },
+    });
+    const index = await VectorStoreIndex.fromVectorStore(vectorStore);
+    const retriever = index.asRetriever({ similarityTopK: 20 });
+
+    const queryEngine = index.asQueryEngine({ retriever });
+    const query = "Get all movie titles.";
+    const results = await queryEngine.query({ query });
+    console.log(`Query from ${results.sourceNodes?.length} nodes`);
+    console.log(results.response);
+
+    console.log("\n=====\nQuerying the index with filters");
+    const queryEngineWithFilters = index.asQueryEngine({
+      retriever,
+      preFilters: {
+        filters: [
+          {
+            key: "file_name",
+            value: "movie_reviews.csv",
+            operator: "==",
+          },
+        ],
+      },
+    });
+    const resultAfterFilter = await queryEngineWithFilters.query({
+      query: "Get all movie titles.",
+    });
+    console.log(`Query from ${resultAfterFilter.sourceNodes?.length} nodes`);
+    console.log(resultAfterFilter.response);
+  } catch (e) {
+    console.error(e);
+  }
+}
+
+void main();

examples/openai.ts

@@ -1,7 +1,7 @@
 import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
 
 (async () => {
-  const llm = new OpenAI({ model: "gpt-4-1106-preview", temperature: 0.1 });
+  const llm = new OpenAI({ model: "gpt-4.5-preview", temperature: 0.1 });
 
   // complete api
   const response1 = await llm.complete({ prompt: "How are you?" });

examples/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/examples",
-  "version": "0.2.1",
+  "version": "0.2.5",
   "private": true,
   "scripts": {
     "lint": "eslint .",
@@ -11,37 +11,39 @@
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@azure/search-documents": "^12.1.0",
-    "@llamaindex/anthropic": "^0.1.1",
-    "@llamaindex/astra": "^0.0.6",
-    "@llamaindex/azure": "^0.1.1",
-    "@llamaindex/chroma": "^0.0.6",
-    "@llamaindex/clip": "^0.0.37",
-    "@llamaindex/cloud": "^3.0.1",
-    "@llamaindex/cohere": "^0.0.6",
-    "@llamaindex/core": "^0.5.1",
-    "@llamaindex/deepinfra": "^0.0.37",
+    "@llamaindex/anthropic": "^0.2.3",
+    "@llamaindex/astra": "^0.0.10",
+    "@llamaindex/azure": "^0.1.5",
+    "@llamaindex/chroma": "^0.0.10",
+    "@llamaindex/clip": "^0.0.41",
+    "@llamaindex/cloud": "^3.0.6",
+    "@llamaindex/cohere": "^0.0.10",
+    "@llamaindex/core": "^0.5.5",
+    "@llamaindex/deepinfra": "^0.0.41",
     "@llamaindex/env": "^0.1.28",
-    "@llamaindex/google": "^0.0.8",
-    "@llamaindex/groq": "^0.0.52",
-    "@llamaindex/huggingface": "^0.0.37",
-    "@llamaindex/milvus": "^0.1.1",
-    "@llamaindex/mistral": "^0.0.6",
-    "@llamaindex/mixedbread": "^0.0.6",
-    "@llamaindex/mongodb": "^0.0.6",
-    "@llamaindex/node-parser": "^1.0.1",
-    "@llamaindex/ollama": "^0.0.41",
-    "@llamaindex/openai": "^0.1.53",
-    "@llamaindex/pinecone": "^0.0.6",
-    "@llamaindex/portkey-ai": "^0.0.34",
-    "@llamaindex/postgres": "^0.0.34",
-    "@llamaindex/qdrant": "^0.1.1",
-    "@llamaindex/readers": "^2.0.1",
-    "@llamaindex/replicate": "^0.0.34",
-    "@llamaindex/upstash": "^0.0.6",
-    "@llamaindex/vercel": "^0.0.12",
-    "@llamaindex/vllm": "^0.0.23",
-    "@llamaindex/weaviate": "^0.0.6",
-    "@llamaindex/workflow": "^0.0.11",
+    "@llamaindex/firestore": "^1.0.3",
+    "@llamaindex/google": "^0.0.12",
+    "@llamaindex/groq": "^0.0.56",
+    "@llamaindex/huggingface": "^0.0.41",
+    "@llamaindex/milvus": "^0.1.5",
+    "@llamaindex/mistral": "^0.0.10",
+    "@llamaindex/mixedbread": "^0.0.10",
+    "@llamaindex/mongodb": "^0.0.10",
+    "@llamaindex/node-parser": "^1.0.5",
+    "@llamaindex/ollama": "^0.0.45",
+    "@llamaindex/openai": "^0.1.57",
+    "@llamaindex/pinecone": "^0.0.10",
+    "@llamaindex/portkey-ai": "^0.0.38",
+    "@llamaindex/postgres": "^0.0.38",
+    "@llamaindex/qdrant": "^0.1.5",
+    "@llamaindex/readers": "^2.0.5",
+    "@llamaindex/replicate": "^0.0.38",
+    "@llamaindex/upstash": "^0.0.10",
+    "@llamaindex/vercel": "^0.0.16",
+    "@llamaindex/vllm": "^0.0.27",
+    "@llamaindex/voyage-ai": "^1.0.2",
+    "@llamaindex/weaviate": "^0.0.10",
+    "@llamaindex/workflow": "^0.0.12",
     "@notionhq/client": "^2.2.15",
     "@pinecone-database/pinecone": "^4.0.0",
     "@vercel/postgres": "^0.10.0",
@@ -50,11 +52,12 @@
     "commander": "^12.1.0",
     "dotenv": "^16.4.5",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.9.1",
+    "llamaindex": "^0.9.6",
     "mongodb": "6.7.0",
     "pathe": "^1.1.2",
     "postgres": "^3.4.4",
-    "wikipedia": "^2.1.2"
+    "wikipedia": "^2.1.2",
+    "zod": "^3.23.8"
   },
   "devDependencies": {
     "@types/node": "^22.9.0",

examples/toolsStream.ts

@@ -15,7 +15,7 @@ async function main() {
     tools: [
       {
         metadata: {
-          name: "wikipedia_tool",
+          name: "wikipedia_search",
           description: "A tool that uses a query engine to search Wikipedia.",
           parameters: {
             type: "object",

examples/voyage-ai/embedding.ts

@@ -0,0 +1,17 @@
+import { VoyageAIEmbedding } from "@llamaindex/voyage-ai";
+
+async function main() {
+  // API token can be provided as an environment variable too
+  // using VOYAGE_API_TOKEN variable
+  const apiKey = process.env.VOYAGE_API_TOKEN ?? "YOUR_API_TOKEN";
+  const model = "voyage-3-lite";
+  const embedModel = new VoyageAIEmbedding({
+    model,
+    apiKey,
+  });
+  const texts = ["hello", "world"];
+  const embeddings = await embedModel.getTextEmbeddingsBatch(texts);
+  console.log(`\nWe have ${embeddings.length} embeddings`);
+}
+
+main().catch(console.error);

examples/wiki.ts

@@ -14,7 +14,7 @@ type WikipediaToolParams = {
 };
 
 const DEFAULT_META_DATA: ToolMetadata<JSONSchemaType<WikipediaParameter>> = {
-  name: "wikipedia_tool",
+  name: "wikipedia_search",
   description: "A tool that uses a query engine to search Wikipedia.",
   parameters: {
     type: "object",

packages/autotool/CHANGELOG.md

@@ -1,5 +1,37 @@
 # @llamaindex/autotool
 
+## 6.0.6
+
+### Patch Changes
+
+- llamaindex@0.9.6
+
+## 6.0.5
+
+### Patch Changes
+
+- llamaindex@0.9.5
+
+## 6.0.4
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - llamaindex@0.9.4
+
+## 6.0.3
+
+### Patch Changes
+
+- llamaindex@0.9.3
+
+## 6.0.2
+
+### Patch Changes
+
+- Updated dependencies [88d776f]
+  - llamaindex@0.9.2
+
 ## 6.0.1
 
 ### Patch Changes

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

@@ -1,5 +1,42 @@
 # @llamaindex/autotool-01-node-example
 
+## 0.0.87
+
+### Patch Changes
+
+- llamaindex@0.9.6
+- @llamaindex/autotool@6.0.6
+
+## 0.0.86
+
+### Patch Changes
+
+- llamaindex@0.9.5
+- @llamaindex/autotool@6.0.5
+
+## 0.0.85
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - llamaindex@0.9.4
+  - @llamaindex/autotool@6.0.4
+
+## 0.0.84
+
+### Patch Changes
+
+- llamaindex@0.9.3
+- @llamaindex/autotool@6.0.3
+
+## 0.0.83
+
+### Patch Changes
+
+- Updated dependencies [88d776f]
+  - llamaindex@0.9.2
+  - @llamaindex/autotool@6.0.2
+
 ## 0.0.82
 
 ### Patch Changes

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

@@ -13,5 +13,5 @@
   "scripts": {
     "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
   },
-  "version": "0.0.82"
+  "version": "0.0.87"
 }

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

@@ -1,5 +1,42 @@
 # @llamaindex/autotool-02-next-example
 
+## 0.1.131
+
+### Patch Changes
+
+- llamaindex@0.9.6
+- @llamaindex/autotool@6.0.6
+
+## 0.1.130
+
+### Patch Changes
+
+- llamaindex@0.9.5
+- @llamaindex/autotool@6.0.5
+
+## 0.1.129
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - llamaindex@0.9.4
+  - @llamaindex/autotool@6.0.4
+
+## 0.1.128
+
+### Patch Changes
+
+- llamaindex@0.9.3
+- @llamaindex/autotool@6.0.3
+
+## 0.1.127
+
+### Patch Changes
+
+- Updated dependencies [88d776f]
+  - llamaindex@0.9.2
+  - @llamaindex/autotool@6.0.2
+
 ## 0.1.126
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool-02-next-example",
   "private": true,
-  "version": "0.1.126",
+  "version": "0.1.131",
   "scripts": {
     "dev": "next dev",
     "build": "next build",
@@ -15,7 +15,7 @@
     "dotenv": "^16.3.1",
     "llamaindex": "workspace:*",
     "lucide-react": "^0.460.0",
-    "next": "15.0.3",
+    "next": "15.1.7",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-markdown": "^9.0.1",

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "6.0.1",
+  "version": "6.0.6",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",
@@ -77,7 +77,7 @@
     "@types/node": "^22.9.0",
     "bunchee": "6.3.4",
     "llamaindex": "workspace:*",
-    "next": "15.0.3",
+    "next": "15.1.7",
     "rollup": "^4.28.1",
     "tsx": "^4.19.0",
     "typescript": "^5.7.2",

packages/cloud/CHANGELOG.md

@@ -1,5 +1,39 @@
 # @llamaindex/cloud
 
+## 3.0.6
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+
+## 3.0.5
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+
+## 3.0.4
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - @llamaindex/core@0.5.3
+
+## 3.0.3
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+
+## 3.0.2
+
+### Patch Changes
+
+- c902fcb: chore: bump llamacloud openapi
+
 ## 3.0.1
 
 ### Patch Changes

packages/cloud/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloud",
-  "version": "3.0.1",
+  "version": "3.0.6",
   "type": "module",
   "license": "MIT",
   "scripts": {

packages/cloud/src/reader.ts

@@ -4,6 +4,7 @@ import { fs, getEnv, path } from "@llamaindex/env";
 import {
   type Body_upload_file_api_v1_parsing_upload_post,
   type ParserLanguages,
+  type ParsingMode,
   getJobApiV1ParsingJobJobIdGet,
   getJobImageResultApiV1ParsingJobJobIdResultImageNameGet,
   getJobJsonResultApiV1ParsingJobJobIdResultJsonGet,
@@ -127,6 +128,26 @@ export class LlamaParseReader extends FileReader {
 
   readonly #client: Client;
 
+  output_tables_as_HTML: boolean = false;
+  input_s3_region?: string | undefined;
+  output_s3_region?: string | undefined;
+  preserve_layout_alignment_across_pages?: boolean | undefined;
+  spreadsheet_extract_sub_tables?: boolean | undefined;
+  formatting_instruction?: string | undefined;
+  parse_mode?: ParsingMode | undefined;
+  system_prompt?: string | undefined;
+  system_prompt_append?: string | undefined;
+  user_prompt?: string | undefined;
+  job_timeout_in_seconds?: number | undefined;
+  job_timeout_extra_time_per_page_in_seconds?: number | undefined;
+  strict_mode_image_extraction?: boolean | undefined;
+  strict_mode_image_ocr?: boolean | undefined;
+  strict_mode_reconstruction?: boolean | undefined;
+  strict_mode_buggy_font?: boolean | undefined;
+  ignore_document_elements_for_layout_detection?: boolean | undefined;
+  complemental_formatting_instruction?: string | undefined;
+  content_guideline_instruction?: string | undefined;
+
   constructor(
     params: Partial<Omit<LlamaParseReader, "language" | "apiKey">> & {
       language?: ParserLanguages | ParserLanguages[] | undefined;
@@ -252,6 +273,29 @@ export class LlamaParseReader extends FileReader {
       structured_output_json_schema_name:
         this.structured_output_json_schema_name,
       extract_layout: this.extract_layout,
+      output_tables_as_HTML: this.output_tables_as_HTML,
+      input_s3_region: this.input_s3_region,
+      output_s3_region: this.output_s3_region,
+      preserve_layout_alignment_across_pages:
+        this.preserve_layout_alignment_across_pages,
+      spreadsheet_extract_sub_tables: this.spreadsheet_extract_sub_tables,
+      formatting_instruction: this.formatting_instruction,
+      parse_mode: this.parse_mode,
+      system_prompt: this.system_prompt,
+      system_prompt_append: this.system_prompt_append,
+      user_prompt: this.user_prompt,
+      job_timeout_in_seconds: this.job_timeout_in_seconds,
+      job_timeout_extra_time_per_page_in_seconds:
+        this.job_timeout_extra_time_per_page_in_seconds,
+      strict_mode_image_extraction: this.strict_mode_image_extraction,
+      strict_mode_image_ocr: this.strict_mode_image_ocr,
+      strict_mode_reconstruction: this.strict_mode_reconstruction,
+      strict_mode_buggy_font: this.strict_mode_buggy_font,
+      ignore_document_elements_for_layout_detection:
+        this.ignore_document_elements_for_layout_detection,
+      complemental_formatting_instruction:
+        this.complemental_formatting_instruction,
+      content_guideline_instruction: this.content_guideline_instruction,
     } satisfies {
       [Key in keyof Body_upload_file_api_v1_parsing_upload_post]-?:
         | Body_upload_file_api_v1_parsing_upload_post[Key]

packages/community/CHANGELOG.md

@@ -1,5 +1,34 @@
 # @llamaindex/community
 
+## 0.0.87
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+
+## 0.0.86
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+
+## 0.0.85
+
+### Patch Changes
+
+- 1914b52: Added Claude 3.7 Sonnet support
+- Updated dependencies [cb021e7]
+  - @llamaindex/core@0.5.3
+
+## 0.0.84
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+
 ## 0.0.83
 
 ### Patch Changes

packages/community/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.83",
+  "version": "0.0.87",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

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

@@ -6,7 +6,19 @@ export type ToolChoice =
   | { type: "auto" }
   | { type: "tool"; name: string };
 
-export type AnthropicAdditionalChatOptions = { toolChoice: ToolChoice };
+export interface ThinkingConfigDisabled {
+  type: "disabled";
+}
+
+export interface ThinkingConfigEnabled {
+  budget_tokens: number;
+  type: "enabled";
+}
+
+export type AnthropicAdditionalChatOptions = {
+  toolChoice: ToolChoice;
+  thinking?: ThinkingConfigDisabled | ThinkingConfigEnabled;
+};
 
 type Usage = {
   input_tokens: number;

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

@@ -69,6 +69,7 @@ export const BEDROCK_MODELS = {
   ANTHROPIC_CLAUDE_3_5_SONNET: "anthropic.claude-3-5-sonnet-20240620-v1:0",
   ANTHROPIC_CLAUDE_3_5_SONNET_V2: "anthropic.claude-3-5-sonnet-20241022-v2:0",
   ANTHROPIC_CLAUDE_3_5_HAIKU: "anthropic.claude-3-5-haiku-20241022-v1:0",
+  ANTHROPIC_CLAUDE_3_7_SONNET: "anthropic.claude-3-7-sonnet-20250219-v1:0",
   META_LLAMA2_13B_CHAT: "meta.llama2-13b-chat-v1",
   META_LLAMA2_70B_CHAT: "meta.llama2-70b-chat-v1",
   META_LLAMA3_8B_INSTRUCT: "meta.llama3-8b-instruct-v1:0",
@@ -100,6 +101,8 @@ export const INFERENCE_BEDROCK_MODELS = {
     "us.anthropic.claude-3-5-sonnet-20240620-v1:0",
   US_ANTHROPIC_CLAUDE_3_5_SONNET_V2:
     "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
+  US_ANTHROPIC_CLAUDE_3_7_SONNET:
+    "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
   US_META_LLAMA_3_2_1B_INSTRUCT: "us.meta.llama3-2-1b-instruct-v1:0",
   US_META_LLAMA_3_2_3B_INSTRUCT: "us.meta.llama3-2-3b-instruct-v1:0",
   US_META_LLAMA_3_2_11B_INSTRUCT: "us.meta.llama3-2-11b-instruct-v1:0",
@@ -113,6 +116,8 @@ export const INFERENCE_BEDROCK_MODELS = {
   EU_ANTHROPIC_CLAUDE_3_SONNET: "eu.anthropic.claude-3-sonnet-20240229-v1:0",
   EU_ANTHROPIC_CLAUDE_3_5_SONNET:
     "eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
+  EU_ANTHROPIC_CLAUDE_3_7_SONNET:
+    "eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
   EU_META_LLAMA_3_2_1B_INSTRUCT: "eu.meta.llama3-2-1b-instruct-v1:0",
   EU_META_LLAMA_3_2_3B_INSTRUCT: "eu.meta.llama3-2-3b-instruct-v1:0",
 };
@@ -132,6 +137,8 @@ export const INFERENCE_TO_BEDROCK_MAP: Record<
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET,
   [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_SONNET]:
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
+  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_7_SONNET]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
   [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_SONNET_V2]:
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
   [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_HAIKU]:
@@ -158,6 +165,8 @@ export const INFERENCE_TO_BEDROCK_MAP: Record<
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET,
   [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_5_SONNET]:
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
+  [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_7_SONNET]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
   [INFERENCE_BEDROCK_MODELS.EU_META_LLAMA_3_2_1B_INSTRUCT]:
     BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
   [INFERENCE_BEDROCK_MODELS.EU_META_LLAMA_3_2_3B_INSTRUCT]:
@@ -191,6 +200,7 @@ const CHAT_ONLY_MODELS = {
   [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET]: 200000,
   [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2]: 200000,
   [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU]: 200000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET]: 200000,
   [BEDROCK_MODELS.META_LLAMA2_13B_CHAT]: 2048,
   [BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 4096,
   [BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 8192,
@@ -230,6 +240,7 @@ export const STREAMING_MODELS = new Set([
   BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
   BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
   BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
   BEDROCK_MODELS.META_LLAMA2_13B_CHAT,
   BEDROCK_MODELS.META_LLAMA2_70B_CHAT,
   BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT,
@@ -256,6 +267,7 @@ export const TOOL_CALL_MODELS: BEDROCK_MODELS[] = [
   BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
   BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
   BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
   BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
   BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
   BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
@@ -294,6 +306,7 @@ export const BEDROCK_MODEL_MAX_TOKENS: Partial<Record<BEDROCK_MODELS, number>> =
     [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET]: 4096,
     [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2]: 8192,
     [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU]: 8192,
+    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET]: 8192,
     [BEDROCK_MODELS.META_LLAMA2_13B_CHAT]: 2048,
     [BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 2048,
     [BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 2048,

packages/core/CHANGELOG.md

@@ -1,5 +1,29 @@
 # @llamaindex/core
 
+## 0.5.5
+
+### Patch Changes
+
+- 5668970: feat: Support AgentWorkflow
+
+## 0.5.4
+
+### Patch Changes
+
+- ad3c7f1: fix: streaming issues with LLMAgent
+
+## 0.5.3
+
+### Patch Changes
+
+- cb021e7: feat(node-parser): support async function
+
+## 0.5.2
+
+### Patch Changes
+
+- d952e68: Refine synthesizer will now return an empty string as the response if an empty array of source nodes were provided. Before it would throw an internal error converting undefined to ReadableStream.
+
 ## 0.5.1
 
 ### Patch Changes

packages/core/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.5.1",
+  "version": "0.5.5",
   "description": "LlamaIndex Core Module",
   "exports": {
     "./agent": {

packages/core/src/agent/base.ts

@@ -193,7 +193,7 @@ export abstract class AgentWorker<
     return new ReadableStream<
       TaskStepOutput<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
     >({
-      start: async (controller) => {
+      pull: async (controller) => {
         for await (const stepOutput of taskOutputStream) {
           this.#taskSet.add(stepOutput.taskStep);
           if (stepOutput.isLast) {
@@ -209,23 +209,31 @@ export abstract class AgentWorker<
             }
             const { output, taskStep } = stepOutput;
             if (output instanceof ReadableStream) {
-              const [pipStream, finalStream] = output.tee();
-              stepOutput.output = finalStream;
-              const reader = pipStream.getReader();
-              const { value } = await reader.read();
-              reader.releaseLock();
-              let content: string = value!.delta;
-              for await (const chunk of pipStream) {
-                content += chunk.delta;
-              }
-              taskStep.context.store.messages = [
-                ...taskStep.context.store.messages,
-                {
-                  role: "assistant",
-                  content,
-                  options: value!.options,
-                },
-              ];
+              let content = "";
+              let options: AdditionalMessageOptions | undefined = undefined;
+              const transformedStream = output.pipeThrough(
+                new TransformStream({
+                  transform(chunk, controller) {
+                    content += chunk.delta;
+                    if (!options && chunk.options) {
+                      options = chunk.options;
+                    }
+                    controller.enqueue(chunk); // Pass the chunk through unchanged
+                  },
+                  // When stream finishes, store the accumulated message in context
+                  flush() {
+                    taskStep.context.store.messages = [
+                      ...taskStep.context.store.messages,
+                      {
+                        role: "assistant",
+                        content,
+                        options,
+                      },
+                    ];
+                  },
+                }),
+              );
+              stepOutput.output = transformedStream;
             }
             controller.enqueue(stepOutput);
             controller.close();

packages/core/src/llms/type.ts

@@ -215,6 +215,10 @@ export type ToolMetadata<
    * @link https://json-schema.org/understanding-json-schema
    */
   parameters?: Parameters;
+  /**
+   * Whether the tool requires workflow context to be passed in.
+   */
+  requireContext?: boolean;
 };
 
 /**

packages/core/src/node-parser/base.ts

@@ -7,21 +7,27 @@ import {
   TextNode,
   TransformComponent,
 } from "../schema";
+import { isPromise } from "../utils";
 
-export abstract class NodeParser extends TransformComponent<BaseNode[]> {
+export abstract class NodeParser<
+  Result extends TextNode[] | Promise<TextNode[]> =
+    | TextNode[]
+    | Promise<TextNode[]>,
+> extends TransformComponent<Result> {
   includeMetadata: boolean = true;
   includePrevNextRel: boolean = true;
 
   constructor() {
-    super((nodes: BaseNode[]): BaseNode[] => {
+    super((nodes: BaseNode[]): Result => {
+      // alex: should we fix `as` type?
       return this.getNodesFromDocuments(nodes as TextNode[]);
     });
   }
 
   protected postProcessParsedNodes(
-    nodes: TextNode[],
+    nodes: Awaited<Result>,
     parentDocMap: Map<string, TextNode>,
-  ): TextNode[] {
+  ): Awaited<Result> {
     nodes.forEach((node, i) => {
       const parentDoc = parentDocMap.get(node.sourceNode?.nodeId || "");
 
@@ -73,9 +79,9 @@ export abstract class NodeParser extends TransformComponent<BaseNode[]> {
   protected abstract parseNodes(
     documents: TextNode[],
     showProgress?: boolean,
-  ): TextNode[];
+  ): Result;
 
-  public getNodesFromDocuments(documents: TextNode[]): TextNode[] {
+  public getNodesFromDocuments(documents: TextNode[]): Result {
     const docsId: Map<string, TextNode> = new Map(
       documents.map((doc) => [doc.id_, doc]),
     );
@@ -85,20 +91,36 @@ export abstract class NodeParser extends TransformComponent<BaseNode[]> {
       documents,
     });
 
-    const nodes = this.postProcessParsedNodes(
-      this.parseNodes(documents),
-      docsId,
-    );
+    const parsedNodes = this.parseNodes(documents);
+    if (isPromise(parsedNodes)) {
+      return parsedNodes.then((parsedNodes) => {
+        const nodes = this.postProcessParsedNodes(
+          parsedNodes as Awaited<Result>,
+          docsId,
+        );
 
-    callbackManager.dispatchEvent("node-parsing-end", {
-      nodes,
-    });
+        callbackManager.dispatchEvent("node-parsing-end", {
+          nodes,
+        });
 
-    return nodes;
+        return nodes;
+      }) as Result;
+    } else {
+      const nodes = this.postProcessParsedNodes(
+        parsedNodes as Awaited<Result>,
+        docsId,
+      );
+
+      callbackManager.dispatchEvent("node-parsing-end", {
+        nodes,
+      });
+
+      return nodes;
+    }
   }
 }
 
-export abstract class TextSplitter extends NodeParser {
+export abstract class TextSplitter extends NodeParser<TextNode[]> {
   abstract splitText(text: string): string[];
 
   public splitTexts(texts: string[]): string[] {

packages/core/src/node-parser/markdown.ts

@@ -6,7 +6,7 @@ import {
 } from "../schema";
 import { NodeParser } from "./base";
 
-export class MarkdownNodeParser extends NodeParser {
+export class MarkdownNodeParser extends NodeParser<TextNode[]> {
   override parseNodes(nodes: TextNode[], showProgress?: boolean): TextNode[] {
     return nodes.reduce<TextNode[]>((allNodes, node) => {
       const markdownNodes = this.getNodesFromNode(node);

packages/core/src/node-parser/sentence-window.ts

@@ -9,7 +9,7 @@ import {
 import { NodeParser } from "./base";
 import { splitBySentenceTokenizer, type TextSplitterFn } from "./utils";
 
-export class SentenceWindowNodeParser extends NodeParser {
+export class SentenceWindowNodeParser extends NodeParser<TextNode[]> {
   static DEFAULT_WINDOW_SIZE = 3;
   static DEFAULT_WINDOW_METADATA_KEY = "window";
   static DEFAULT_ORIGINAL_TEXT_METADATA_KEY = "originalText";

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

@@ -116,7 +116,14 @@ class Refine extends BaseSynthesizer {
       }
     }
 
-    // fixme: no source nodes provided, cannot fix right now due to lack of context
+    if (response === undefined) {
+      response = stream
+        ? (async function* () {
+            yield "";
+          })()
+        : "";
+    }
+
     if (typeof response === "string") {
       return EngineResponse.fromResponse(response, false, nodes);
     } else {

packages/core/src/tools/function-tool.ts

@@ -59,14 +59,28 @@ export class FunctionTool<T, R extends JSONValue | Promise<JSONValue>>
   }
 
   call = (input: T) => {
+    if (this.#metadata.requireContext) {
+      const inputWithContext = input as Record<string, unknown>;
+      if (!inputWithContext.context) {
+        throw new Error(
+          "Tool call requires context, but context parameter is missing",
+        );
+      }
+    }
     if (this.#zodType) {
       const result = this.#zodType.safeParse(input);
       if (result.success) {
-        return this.#fn.call(null, result.data);
+        if (this.#metadata.requireContext) {
+          const { context } = input as Record<string, unknown>;
+          return this.#fn.call(null, { context, ...result.data });
+        } else {
+          return this.#fn.call(null, result.data);
+        }
       } else {
         console.warn(result.error.errors);
       }
     }
+
     return this.#fn.call(null, input);
   };
 }

packages/core/src/utils/index.ts

@@ -1,5 +1,9 @@
 import type { JSONValue } from "../global";
 
+export const isPromise = <T>(obj: unknown): obj is Promise<T> => {
+  return obj != null && typeof obj === "object" && "then" in obj;
+};
+
 export const isAsyncIterable = (
   obj: unknown,
 ): obj is AsyncIterable<unknown> => {

packages/core/tests/agents.test.ts

@@ -1,4 +1,5 @@
-import { validateAgentParams } from "@llamaindex/core/agent";
+import { LLMAgent, validateAgentParams } from "@llamaindex/core/agent";
+import { MockLLM } from "@llamaindex/core/utils";
 import { expect, test } from "vitest";
 import { ZodError } from "zod";
 
@@ -33,3 +34,62 @@ test("validate agent params", () => {
     ],
   });
 });
+
+test("LLMAgent streaming: first chunk should be available immediately", async () => {
+  const responseMessage =
+    "This is a very long response message that should take a while to stream";
+  const timeBetweenToken = 20; // delay time between tokens
+
+  const agent = new LLMAgent({
+    tools: [],
+    llm: new MockLLM({ responseMessage, timeBetweenToken }),
+  });
+
+  const startTime = Date.now();
+  const stream = await agent.chat({ message: "Hello", stream: true });
+
+  let fullResponse = "";
+  let timeToGetFirstChunk: number | undefined;
+
+  for await (const chunk of stream) {
+    expect(chunk).toHaveProperty("delta");
+    fullResponse += chunk.delta;
+    if (timeToGetFirstChunk === undefined) {
+      timeToGetFirstChunk = Date.now() - startTime;
+    }
+  }
+
+  expect(fullResponse).toBe(responseMessage);
+
+  // the first chunk should be available immediately and no need the whole response to be sent
+  expect(timeToGetFirstChunk).toBeLessThan(500);
+});
+
+test("LLMAgent create task: first task should be executed immediately", async () => {
+  const responseMessage =
+    "This is a very long response message that should take a while to stream";
+  const timeBetweenToken = 20; // delay time between tokens
+
+  const agent = new LLMAgent({
+    tools: [],
+    llm: new MockLLM({ responseMessage, timeBetweenToken }),
+  });
+
+  const startTime = Date.now();
+  const task = agent.createTask("Write a long paragraph", true, false, []);
+
+  let timeToGetFirstChunk: number | undefined;
+  let output: ReadableStream | undefined;
+  for await (const stepOutput of task) {
+    if (timeToGetFirstChunk === undefined) {
+      timeToGetFirstChunk = Date.now() - startTime;
+    }
+    if (stepOutput.output instanceof ReadableStream) {
+      output = stepOutput.output;
+    }
+  }
+
+  expect(timeToGetFirstChunk).toBeLessThan(500);
+  expect(output).toBeDefined();
+  expect(output).toBeInstanceOf(ReadableStream);
+});

packages/core/tests/memory/chat-memory-buffer.test.ts

@@ -66,9 +66,9 @@ describe("ChatMemoryBuffer", () => {
     expect(result).toEqual([...inputMessages, ...storedMessages]);
   });
 
-  test("getMessages throws error when initial token count exceeds limit", () => {
+  test("getMessages throws error when initial token count exceeds limit", async () => {
     const buffer = new ChatMemoryBuffer({ tokenLimit: 10 });
-    expect(async () => buffer.getMessages(undefined, 20)).rejects.toThrow(
+    await expect(async () => buffer.getMessages(undefined, 20)).rejects.toThrow(
       "Initial token count exceeds token limit",
     );
   });

packages/core/tests/node-parser/node-parser.test.ts

@@ -0,0 +1,24 @@
+import { NodeParser } from "@llamaindex/core/node-parser";
+import { TextNode } from "@llamaindex/core/schema";
+import { describe, expect, test } from "vitest";
+
+describe("NodeParser", () => {
+  test("node parser should allow async parse function", async () => {
+    class MyNodeParser extends NodeParser<Promise<TextNode[]>> {
+      protected async parseNodes(documents: TextNode[]): Promise<TextNode[]> {
+        await new Promise((resolve) => setTimeout(resolve, 1000));
+        return documents;
+      }
+    }
+
+    const nodeParser = new MyNodeParser();
+    const nodes = [
+      new TextNode({
+        text: "Hello, world!",
+      }),
+    ];
+    const result = nodeParser(nodes);
+    expect(result).toBeInstanceOf(Promise);
+    await expect(result).resolves.toEqual(nodes);
+  });
+});

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

@@ -1,4 +1,4 @@
-import { describe, expect, test, vi } from "vitest";
+import { beforeEach, describe, expect, test, vi } from "vitest";
 import type { LLMMetadata } from "../../llms/dist/index.js";
 import { getResponseSynthesizer } from "../../response-synthesizers/dist/index.js";
 import { Document } from "../../schema/dist/index.js";
@@ -10,26 +10,69 @@ const mockLllm = () => ({
       return response;
     }
 
-    function* gen() {
-      // yield a few times to make sure each chunk has the sourceNodes
-      yield response;
-      yield response;
-      yield response;
-    }
-
-    return gen();
+    return {
+      [Symbol.asyncIterator]: function* gen() {
+        // yield a few times to make sure each chunk has the sourceNodes
+        yield response;
+        yield response;
+        yield response;
+      },
+    };
   }),
   chat: vi.fn(),
   metadata: {} as unknown as LLMMetadata,
 });
 
+describe("refine response synthesizer", () => {
+  let synthesizer: ReturnType<typeof getResponseSynthesizer<"refine">>;
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  const isAsyncIterable = (obj: any): boolean =>
+    obj[Symbol.asyncIterator] !== undefined;
+
+  beforeEach(() => {
+    synthesizer = getResponseSynthesizer("refine", {
+      llm: mockLllm(),
+    });
+  });
+
+  describe("getResponse", () => {
+    test("should return async iterable of EngineResponse when stream is true and sourceNodes are empty", async () => {
+      const response = await synthesizer.getResponse(
+        "unimportant query",
+        [],
+        true,
+      );
+
+      expect(isAsyncIterable(response)).toBe(true);
+      for await (const chunk of response) {
+        expect(chunk.message.content).toEqual("");
+      }
+    });
+
+    test("should return non async iterable when stream is false and sourceNodes are empty", async () => {
+      const response = await synthesizer.getResponse(
+        "unimportant query",
+        [],
+        false,
+      );
+
+      expect(isAsyncIterable(response)).toBe(false);
+      expect(response.message.content).toEqual("");
+    });
+  });
+});
+
 describe("compact and refine response synthesizer", () => {
+  let synthesizer: ReturnType<typeof getResponseSynthesizer<"compact">>;
+
+  beforeEach(() => {
+    synthesizer = getResponseSynthesizer("compact", {
+      llm: mockLllm(),
+    });
+  });
+
   describe("synthesize", () => {
     test("should return original sourceNodes with response when stream = false", async () => {
-      const synthesizer = getResponseSynthesizer("compact", {
-        llm: mockLllm(),
-      });
-
       const sourceNode = { node: new Document({}), score: 1 };
 
       const response = await synthesizer.synthesize(
@@ -44,10 +87,6 @@ describe("compact and refine response synthesizer", () => {
     });
 
     test("should return original sourceNodes with response when stream = true", async () => {
-      const synthesizer = getResponseSynthesizer("compact", {
-        llm: mockLllm(),
-      });
-
       const sourceNode = { node: new Document({}), score: 1 };
 
       const response = await synthesizer.synthesize(

packages/experimental/CHANGELOG.md

@@ -1,5 +1,37 @@
 # @llamaindex/experimental
 
+## 0.0.156
+
+### Patch Changes
+
+- llamaindex@0.9.6
+
+## 0.0.155
+
+### Patch Changes
+
+- llamaindex@0.9.5
+
+## 0.0.154
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - llamaindex@0.9.4
+
+## 0.0.153
+
+### Patch Changes
+
+- llamaindex@0.9.3
+
+## 0.0.152
+
+### Patch Changes
+
+- Updated dependencies [88d776f]
+  - llamaindex@0.9.2
+
 ## 0.0.151
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.151",
+  "version": "0.0.156",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,56 @@
 # llamaindex
 
+## 0.9.6
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+  - @llamaindex/workflow@0.0.12
+  - @llamaindex/cloud@3.0.6
+  - @llamaindex/node-parser@1.0.5
+  - @llamaindex/openai@0.1.57
+
+## 0.9.5
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+  - @llamaindex/cloud@3.0.5
+  - @llamaindex/node-parser@1.0.4
+  - @llamaindex/openai@0.1.56
+
+## 0.9.4
+
+### Patch Changes
+
+- cb021e7: feat(node-parser): support async function
+- Updated dependencies [cb256f2]
+- Updated dependencies [cb021e7]
+  - @llamaindex/openai@0.1.55
+  - @llamaindex/core@0.5.3
+  - @llamaindex/cloud@3.0.4
+  - @llamaindex/node-parser@1.0.3
+
+## 0.9.3
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+  - @llamaindex/cloud@3.0.3
+  - @llamaindex/node-parser@1.0.2
+  - @llamaindex/openai@0.1.54
+
+## 0.9.2
+
+### Patch Changes
+
+- 88d776f: fix: enhance error message in llamacloud
+- Updated dependencies [c902fcb]
+  - @llamaindex/cloud@3.0.2
+
 ## 0.9.1
 
 ### Patch Changes

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.9.1",
+  "version": "0.9.6",
   "license": "MIT",
   "type": "module",
   "keywords": [
@@ -25,6 +25,7 @@
     "@llamaindex/env": "workspace:*",
     "@llamaindex/node-parser": "workspace:*",
     "@llamaindex/openai": "workspace:*",
+    "@llamaindex/workflow": "workspace:*",
     "@types/lodash": "^4.17.7",
     "@types/node": "^22.9.0",
     "ajv": "^8.17.1",

packages/llamaindex/src/cloud/utils.ts

@@ -31,6 +31,11 @@ export function initService({ apiKey, baseUrl }: ClientParams = {}) {
     request.headers.set("Authorization", `Bearer ${token}`);
     return request;
   });
+  client.interceptors.error.use((error) => {
+    throw new Error(
+      `LlamaCloud API request failed. Error details: ${JSON.stringify(error)}`,
+    );
+  });
   if (!token) {
     throw new Error(
       "API Key is required for LlamaCloudIndex. Please pass the apiKey parameter",

packages/llamaindex/src/index.edge.ts

@@ -65,6 +65,7 @@ export * from "@llamaindex/core/storage/doc-store";
 export * from "@llamaindex/core/storage/index-store";
 export * from "@llamaindex/core/storage/kv-store";
 export * from "@llamaindex/core/utils";
+export * from "@llamaindex/workflow/agent";
 export * from "./agent/index.js";
 export * from "./cloud/index.js";
 export * from "./embeddings/index.js";

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

@@ -296,7 +296,7 @@ export class KeywordTableIndex extends BaseIndex<KeywordTable> {
       await docStore.setDocumentHash(doc.id_, doc.hash);
     }
 
-    const nodes = Settings.nodeParser.getNodesFromDocuments(documents);
+    const nodes = await Settings.nodeParser.getNodesFromDocuments(documents);
     const index = await KeywordTableIndex.init({
       nodes,
       storageContext,

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

@@ -145,7 +145,7 @@ export class SummaryIndex extends BaseIndex<IndexList> {
       await docStore.setDocumentHash(doc.id_, doc.hash);
     }
 
-    const nodes = Settings.nodeParser.getNodesFromDocuments(documents);
+    const nodes = await Settings.nodeParser.getNodesFromDocuments(documents);
 
     const index = await SummaryIndex.init({
       nodes,

packages/node-parser/CHANGELOG.md

@@ -1,5 +1,33 @@
 # @llamaindex/node-parser
 
+## 1.0.5
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+
+## 1.0.4
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+
+## 1.0.3
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - @llamaindex/core@0.5.3
+
+## 1.0.2
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+
 ## 1.0.1
 
 ### Patch Changes

packages/node-parser/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/node-parser",
-  "version": "1.0.1",
+  "version": "1.0.5",
   "description": "Node parser for LlamaIndex",
   "type": "module",
   "exports": {

packages/providers/anthropic/CHANGELOG.md

@@ -1,5 +1,45 @@
 # @llamaindex/anthropic
 
+## 0.2.3
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+
+## 0.2.2
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+
+## 0.2.1
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - @llamaindex/core@0.5.3
+
+## 0.2.0
+
+### Minor Changes
+
+- 3564244: Add support for claude 3.7 thinking (and set default temperature to 1)
+
+### Patch Changes
+
+- a9c6144: Stream thinking tokens
+- 3564244: add support for claude 3.7
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+
+## 0.1.2
+
+### Patch Changes
+
+- be74207: fix: dont add empty text block to tool call
+
 ## 0.1.1
 
 ### Patch Changes

packages/providers/anthropic/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/anthropic",
   "description": "Anthropic Adapter for LlamaIndex",
-  "version": "0.1.1",
+  "version": "0.2.3",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -35,7 +35,7 @@
     "vitest": "^2.1.5"
   },
   "dependencies": {
-    "@anthropic-ai/sdk": "0.32.1",
+    "@anthropic-ai/sdk": "0.37.0",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
     "remeda": "^2.17.3"

packages/providers/anthropic/src/llm.ts

@@ -6,6 +6,8 @@ import type {
 } from "@anthropic-ai/sdk/resources/beta/index";
 import type { TextBlock } from "@anthropic-ai/sdk/resources/index";
 import type {
+  MessageCreateParams,
+  MessageCreateParamsBase,
   MessageParam,
   Model,
   Tool,
@@ -102,10 +104,17 @@ export const ALL_AVAILABLE_V3_5_MODELS = {
   "claude-3-5-haiku-20241022": { contextWindow: 200000 },
 };
 
+export const ALL_AVAILABLE_V3_7_MODELS = {
+  "claude-3-7-sonnet": { contextWindow: 200000 },
+  "claude-3-7-sonnet-20250219": { contextWindow: 200000 },
+  "claude-3-7-sonnet-latest": { contextWindow: 200000 },
+};
+
 export const ALL_AVAILABLE_ANTHROPIC_MODELS = {
   ...ALL_AVAILABLE_ANTHROPIC_LEGACY_MODELS,
   ...ALL_AVAILABLE_V3_MODELS,
   ...ALL_AVAILABLE_V3_5_MODELS,
+  ...ALL_AVAILABLE_V3_7_MODELS,
 } satisfies {
   [key in Model]: { contextWindow: number };
 };
@@ -115,11 +124,16 @@ const AVAILABLE_ANTHROPIC_MODELS_WITHOUT_DATE: { [key: string]: string } = {
   "claude-3-sonnet": "claude-3-sonnet-20240229",
   "claude-3-haiku": "claude-3-haiku-20240307",
   "claude-3-5-sonnet": "claude-3-5-sonnet-20240620",
+  "claude-3-7-sonnet": "claude-3-7-sonnet-20250219",
 } as { [key in keyof typeof ALL_AVAILABLE_ANTHROPIC_MODELS]: string };
 
-export type AnthropicAdditionalChatOptions = object;
+export type AnthropicAdditionalChatOptions = Pick<
+  MessageCreateParamsBase,
+  "thinking"
+>;
 export type AnthropicToolCallLLMMessageOptions = ToolCallLLMMessageOptions & {
   cache_control?: BetaCacheControlEphemeral | null;
+  thinking?: string | undefined;
 };
 
 export class Anthropic extends ToolCallLLM<
@@ -129,8 +143,9 @@ export class Anthropic extends ToolCallLLM<
   // Per completion Anthropic params
   model: keyof typeof ALL_AVAILABLE_ANTHROPIC_MODELS | ({} & string);
   temperature: number;
-  topP: number;
+  topP?: number | undefined;
   maxTokens?: number | undefined;
+  additionalChatOptions?: AnthropicAdditionalChatOptions | undefined;
 
   // Anthropic session params
   apiKey?: string | undefined;
@@ -141,13 +156,14 @@ export class Anthropic extends ToolCallLLM<
   constructor(init?: Partial<Anthropic>) {
     super();
     this.model = init?.model ?? "claude-3-opus";
-    this.temperature = init?.temperature ?? 0.1;
-    this.topP = init?.topP ?? 0.999; // Per Ben Mann
+    this.temperature = init?.temperature ?? 1; // default in anthropic is 1
+    this.topP = init?.topP;
     this.maxTokens = init?.maxTokens ?? undefined;
 
     this.apiKey = init?.apiKey ?? undefined;
     this.maxRetries = init?.maxRetries ?? 10;
     this.timeout = init?.timeout ?? 60 * 1000; // Default is 60 seconds
+    this.additionalChatOptions = init?.additionalChatOptions;
     this.session =
       init?.session ??
       getAnthropicSession({
@@ -165,7 +181,7 @@ export class Anthropic extends ToolCallLLM<
     return {
       model: this.model,
       temperature: this.temperature,
-      topP: this.topP,
+      topP: this.topP ?? 0, // XXX: topP needs to be returned but might be undefined for Anthropic
       maxTokens: this.maxTokens,
       contextWindow:
         this.model in ALL_AVAILABLE_ANTHROPIC_MODELS
@@ -207,23 +223,26 @@ export class Anthropic extends ToolCallLLM<
       }
 
       if ("toolCall" in options) {
-        const formattedMessage: MessageParam = {
-          role: "assistant",
-          content: [
-            {
-              type: "text" as const,
-              text: extractText(message.content),
-            },
-            ...options.toolCall.map((tool) => ({
-              type: "tool_use" as const,
-              id: tool.id,
-              name: tool.name,
-              input: this.parseToolInput(tool.input),
-            })),
-          ],
-        };
+        const text = extractText(message.content);
 
-        return formattedMessage;
+        const content: MessageParam["content"] = [];
+        if (text && text.trim().length > 0) {
+          // don't add empty text blocks
+          content.push({
+            type: "text" as const,
+            text: text,
+          });
+        }
+        content.push(
+          ...options.toolCall.map((tool) => ({
+            type: "tool_use" as const,
+            id: tool.id,
+            name: tool.name,
+            input: this.parseToolInput(tool.input),
+          })),
+        );
+
+        return { role: "assistant", content } satisfies MessageParam;
       }
 
       // Handle tool results
@@ -362,8 +381,14 @@ export class Anthropic extends ToolCallLLM<
   @wrapLLMEvent
   async chat(
     params:
-      | LLMChatParamsNonStreaming<AnthropicToolCallLLMMessageOptions>
-      | LLMChatParamsStreaming<AnthropicToolCallLLMMessageOptions>,
+      | LLMChatParamsNonStreaming<
+          AnthropicAdditionalChatOptions,
+          AnthropicToolCallLLMMessageOptions
+        >
+      | LLMChatParamsStreaming<
+          AnthropicAdditionalChatOptions,
+          AnthropicToolCallLLMMessageOptions
+        >,
   ): Promise<
     | ChatResponse<AnthropicToolCallLLMMessageOptions>
     | AsyncIterable<ChatResponseChunk<AnthropicToolCallLLMMessageOptions>>
@@ -404,28 +429,29 @@ export class Anthropic extends ToolCallLLM<
       anthropic = anthropic.beta.promptCaching;
     }
 
-    if (stream) {
-      if (tools) {
-        console.error("Tools are not supported in streaming mode");
-      }
-      return this.streamChat(
-        messages.filter((m) => m.role !== "system"),
-        systemPrompt,
-        anthropic,
-      );
-    }
-
-    const apiParams = {
+    const apiParams: MessageCreateParams = {
       model: this.getModelName(this.model),
       messages: this.mergeConsecutiveMessages(
         this.formatMessages(messages.filter((m) => m.role !== "system")),
       ),
       max_tokens: this.maxTokens ?? 4096,
       temperature: this.temperature,
-      top_p: this.topP,
+      ...(this.topP ? { top_p: this.topP } : {}),
       ...(systemPrompt && { system: systemPrompt }),
+      ...Object.assign(
+        {},
+        this.additionalChatOptions,
+        params.additionalChatOptions,
+      ),
     };
 
+    if (stream) {
+      if (tools) {
+        console.error("Tools are not supported in streaming mode");
+      }
+      return this.streamChat(anthropic, apiParams);
+    }
+
     if (tools?.length) {
       Object.assign(apiParams, {
         tools: this.prepareToolsForAPI(tools),
@@ -442,7 +468,10 @@ export class Anthropic extends ToolCallLLM<
       raw: response,
       message: {
         content: response.content
-          .filter((content): content is TextBlock => content.type === "text")
+          .filter(
+            (content): content is TextBlock =>
+              content.type === "text" && content.text?.trim().length > 0,
+          )
           .map((content) => ({
             type: "text" as const,
             text: content.text,
@@ -466,36 +495,36 @@ export class Anthropic extends ToolCallLLM<
   }
 
   protected async *streamChat(
-    messages: ChatMessage<AnthropicToolCallLLMMessageOptions>[],
-    systemPrompt: string | Array<BetaTextBlockParam> | null,
     anthropic: SDKAnthropic,
+    params: MessageCreateParams,
   ): AsyncIterable<ChatResponseChunk<AnthropicToolCallLLMMessageOptions>> {
     const stream = await anthropic.messages.create({
-      model: this.getModelName(this.model),
-      messages: this.formatMessages(messages),
-      max_tokens: this.maxTokens ?? 4096,
-      temperature: this.temperature,
-      top_p: this.topP,
+      ...params,
       stream: true,
-      ...(systemPrompt && { system: systemPrompt }),
     });
 
     let idx_counter: number = 0;
     for await (const part of stream) {
-      const content =
-        part.type === "content_block_delta"
-          ? part.delta.type === "text_delta"
-            ? part.delta.text
-            : part.delta
+      const textContent =
+        part.type === "content_block_delta" && part.delta.type === "text_delta"
+          ? part.delta.text
           : undefined;
 
-      if (typeof content !== "string") continue;
+      const thinking =
+        part.type === "content_block_delta" &&
+        part.delta.type === "thinking_delta"
+          ? part.delta.thinking
+          : undefined;
+
+      if (!textContent && !thinking) continue;
 
       idx_counter++;
       yield {
         raw: part,
-        delta: content,
-        options: {},
+        delta: textContent ?? "",
+        options: {
+          thinking: thinking,
+        },
       };
     }
     return;

packages/providers/clip/CHANGELOG.md

@@ -1,5 +1,38 @@
 # @llamaindex/clip
 
+## 0.0.41
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+  - @llamaindex/openai@0.1.57
+
+## 0.0.40
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+  - @llamaindex/openai@0.1.56
+
+## 0.0.39
+
+### Patch Changes
+
+- Updated dependencies [cb256f2]
+- Updated dependencies [cb021e7]
+  - @llamaindex/openai@0.1.55
+  - @llamaindex/core@0.5.3
+
+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+  - @llamaindex/openai@0.1.54
+
 ## 0.0.37
 
 ### Patch Changes

packages/providers/clip/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/clip",
   "description": "Clip Embedding Adapter for LlamaIndex",
-  "version": "0.0.37",
+  "version": "0.0.41",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/cohere/CHANGELOG.md

@@ -1,5 +1,33 @@
 # @llamaindex/cohere
 
+## 0.0.10
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+
+## 0.0.9
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+
+## 0.0.8
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - @llamaindex/core@0.5.3
+
+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+
 ## 0.0.6
 
 ### Patch Changes

packages/providers/cohere/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/cohere",
   "description": "Cohere Adapter for LlamaIndex",
-  "version": "0.0.6",
+  "version": "0.0.10",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/deepinfra/CHANGELOG.md

@@ -1,5 +1,38 @@
 # @llamaindex/deepinfra
 
+## 0.0.41
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+  - @llamaindex/openai@0.1.57
+
+## 0.0.40
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+  - @llamaindex/openai@0.1.56
+
+## 0.0.39
+
+### Patch Changes
+
+- Updated dependencies [cb256f2]
+- Updated dependencies [cb021e7]
+  - @llamaindex/openai@0.1.55
+  - @llamaindex/core@0.5.3
+
+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+  - @llamaindex/openai@0.1.54
+
 ## 0.0.37
 
 ### Patch Changes

packages/providers/deepinfra/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepinfra",
   "description": "Deepinfra Adapter for LlamaIndex",
-  "version": "0.0.37",
+  "version": "0.0.41",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/google/CHANGELOG.md

@@ -1,5 +1,33 @@
 # @llamaindex/google
 
+## 0.0.12
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+
+## 0.0.11
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+
+## 0.0.10
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - @llamaindex/core@0.5.3
+
+## 0.0.9
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+
 ## 0.0.8
 
 ### Patch Changes

packages/providers/google/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/google",
   "description": "Google Adapter for LlamaIndex",
-  "version": "0.0.8",
+  "version": "0.0.12",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/groq/CHANGELOG.md

@@ -1,5 +1,30 @@
 # @llamaindex/groq
 
+## 0.0.56
+
+### Patch Changes
+
+- @llamaindex/openai@0.1.57
+
+## 0.0.55
+
+### Patch Changes
+
+- @llamaindex/openai@0.1.56
+
+## 0.0.54
+
+### Patch Changes
+
+- Updated dependencies [cb256f2]
+  - @llamaindex/openai@0.1.55
+
+## 0.0.53
+
+### Patch Changes
+
+- @llamaindex/openai@0.1.54
+
 ## 0.0.52
 
 ### Patch Changes

packages/providers/groq/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/groq",
   "description": "Groq Adapter for LlamaIndex",
-  "version": "0.0.52",
+  "version": "0.0.56",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/huggingface/CHANGELOG.md

@@ -1,5 +1,38 @@
 # @llamaindex/huggingface
 
+## 0.0.41
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+  - @llamaindex/openai@0.1.57
+
+## 0.0.40
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+  - @llamaindex/openai@0.1.56
+
+## 0.0.39
+
+### Patch Changes
+
+- Updated dependencies [cb256f2]
+- Updated dependencies [cb021e7]
+  - @llamaindex/openai@0.1.55
+  - @llamaindex/core@0.5.3
+
+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+  - @llamaindex/openai@0.1.54
+
 ## 0.0.37
 
 ### Patch Changes

packages/providers/huggingface/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/huggingface",
   "description": "Huggingface Adapter for LlamaIndex",
-  "version": "0.0.37",
+  "version": "0.0.41",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/mistral/CHANGELOG.md

@@ -1,5 +1,33 @@
 # @llamaindex/mistral
 
+## 0.0.10
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+
+## 0.0.9
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+
+## 0.0.8
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - @llamaindex/core@0.5.3
+
+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+
 ## 0.0.6
 
 ### Patch Changes

packages/providers/mistral/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/mistral",
   "description": "Mistral Adapter for LlamaIndex",
-  "version": "0.0.6",
+  "version": "0.0.10",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/mixedbread/CHANGELOG.md

@@ -1,5 +1,33 @@
 # @llamaindex/mixedbread
 
+## 0.0.10
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+
+## 0.0.9
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+
+## 0.0.8
+
+### Patch Changes
+
+- Updated dependencies [cb021e7]
+  - @llamaindex/core@0.5.3
+
+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+
 ## 0.0.6
 
 ### Patch Changes

packages/providers/mixedbread/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/mixedbread",
   "description": "Mixedbread Adapter for LlamaIndex",
-  "version": "0.0.6",
+  "version": "0.0.10",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",