Release 0.11.29 (#2188)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>

.github/workflows/test.yml

@@ -105,6 +105,7 @@ jobs:
         run: |
           pnpm pack --pack-destination ${{ runner.temp }} -C packages/llamaindex
           pnpm pack --pack-destination ${{ runner.temp }} -C packages/workflow
+          pnpm pack --pack-destination ${{ runner.temp }} -C packages/core
       - name: Install packed packages
         run: npm add ${{ runner.temp }}/*.tgz
         working-directory: e2e/npm
@@ -162,7 +163,7 @@ jobs:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           directory: e2e/examples/vite-import-llamaindex
           skip_step: "install"
-          build_script: build
+          build_script: ci-build
           package_manager: pnpm
 
   typecheck-examples:
@@ -203,7 +204,7 @@ jobs:
             fi
           done
       - name: Install
-        run: npm add ${{ runner.temp }}/*.tgz
+        run: npm add ${{ runner.temp }}/*.tgz --legacy-peer-deps
         working-directory: ${{ runner.temp }}/examples
       - name: Run Type Check
         run: npx tsc --project ./tsconfig.json

apps/next/CHANGELOG.md

@@ -1,5 +1,44 @@
 # @llamaindex/doc
 
+## 0.2.54
+
+### Patch Changes
+
+- ed37c64: Addition of APAC_ANTHROPIC_CLAUDE_4_SONNET type/record in @llamaindex/aws for APAC support for claude 4 sonnet per issue 2184.
+- Updated dependencies [8929dcf]
+- Updated dependencies [5da1cda]
+  - llamaindex@0.11.29
+  - @llamaindex/core@0.6.21
+  - @llamaindex/workflow@1.1.23
+  - @llamaindex/openai@0.4.19
+  - @llamaindex/cloud@4.1.3
+  - @llamaindex/node-parser@2.0.21
+  - @llamaindex/readers@3.1.20
+
+## 0.2.53
+
+### Patch Changes
+
+- Updated dependencies [1995b38]
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/workflow@1.1.22
+  - @llamaindex/openai@0.4.18
+  - llamaindex@0.11.28
+
+## 0.2.52
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+  - @llamaindex/cloud@4.1.2
+  - llamaindex@0.11.27
+  - @llamaindex/node-parser@2.0.20
+  - @llamaindex/openai@0.4.17
+  - @llamaindex/readers@3.1.19
+  - @llamaindex/workflow@1.1.21
+
 ## 0.2.51
 
 ### Patch Changes

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.51",
+  "version": "0.2.54",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",
@@ -15,7 +15,7 @@
   "dependencies": {
     "@huggingface/transformers": "^3.5.0",
     "@icons-pack/react-simple-icons": "^10.1.0",
-    "@llamaindex/chat-ui-docs": "^0.0.5",
+    "@llamaindex/chat-ui-docs": "^0.1.0",
     "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/node-parser": "workspace:*",

apps/next/src/content/docs/llamaindex/modules/models/llms/bedrock.mdx

@@ -115,6 +115,7 @@ EU_AMAZON_NOVA_MICRO_1 = "eu.amazon.nova-micro-v1:0";
 APAC_ANTHROPIC_CLAUDE_3_5_SONNET = "apac.anthropic.claude-3-5-sonnet-20240620-v1:0";
 APAC_ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "apac.anthropic.claude-3-5-sonnet-20241022-v2:0";
 APAC_ANTHROPIC_CLAUDE_3_7_SONNET = "apac.anthropic.claude-3-7-sonnet-20250219-v1:0";
+APAC_ANTHROPIC_CLAUDE_4_SONNET = "apac.anthropic.claude-sonnet-4-20250514-v1:0";
 APAC_ANTHROPIC_CLAUDE_3_HAIKU = "apac.anthropic.claude-3-haiku-20240307-v1:0";
 APAC_ANTHROPIC_CLAUDE_3_SONNET = "apac.anthropic.claude-3-sonnet-20240229-v1:0";
 APAC_AMAZON_NOVA_PRO_1 = "apac.amazon.nova-pro-v1:0";

apps/next/src/content/docs/llamaindex/tutorials/custom_model_per_request.mdx

@@ -0,0 +1,47 @@
+---
+title: Custom Model Per Request 
+---
+
+There are scenarios, such as the case of a multi-tenant backend API, where it may be required to handle each request with a custom model.
+
+In such a scenario, modifying the `Settings` object directly as follows is not recommended:
+
+```typescript
+import { Settings } from 'llamaindex';
+import { OpenAIEmbedding } from '@llamaindex/embeddings-openai';
+
+Settings.embedModel = new OpenAIEmbedding({ apiKey: 'CLIENT_API_KEY' });
+Settings.llm = openai({ apiKey: key,  model: 'gpt-4o' })
+```
+
+Setting `llm` and `embedModel` directly will lead to unpredictable responses, since `Settings` is global and mutable.
+This can lead to race conditions, as each request modifies `Settings.embedModel` or `Settings.llm`.
+
+The recommended approach is to use `Settings.withEmbedModel` or `Settings.withLLM` as follows:
+
+```typescript
+const embedModel = new OpenAIEmbedding({
+  apiKey: process.env.OPENAI_API_KEY,
+});
+const llm = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
+
+const llmResponse = await Settings.withEmbedModel(embedModel, async () => {
+  return Settings.withLLM(llm, async () => {
+    const path = "node_modules/llamaindex/examples/abramov.txt";
+    const essay = await fs.readFile(path, "utf-8");
+    // Create Document object with essay
+    const document = new Document({ text: essay, id_: path });
+    // Split text and create embeddings. Store them in a VectorStoreIndex
+    const index = await VectorStoreIndex.fromDocuments([document]);
+    // Query the index
+    const queryEngine = index.asQueryEngine();
+    const { message, sourceNodes } = await queryEngine.query({
+      query: "What did the author do in college?",
+    });
+    // Return response with sources
+    return message.content;
+  });
+});
+```
+
+The full example can be found [here](https://github.com/run-llama/LlamaIndexTS/tree/main/examples/local-settings).

apps/next/src/content/docs/llamaindex/tutorials/local_llm.mdx

@@ -93,4 +93,4 @@ async function main() {
 main().catch(console.error);
 ```
 
-You can see the [full example file](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/vectorIndexLocal.ts).
+You can see the [full example file](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/index/vectorIndexLocal.ts).

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

@@ -7,6 +7,7 @@
     "workflows",
     "local_llm",
     "chatbot",
-    "structured_data_extraction"
+    "structured_data_extraction",
+    "custom_model_per_request"
   ]
 }

apps/next/src/content/docs/llamaindex/tutorials/structured_data_extraction.mdx

@@ -46,3 +46,31 @@ You should expect output something like:
   ]
 }
 ```
+
+## Using the `exec` method
+
+Many LLMs do not natively support structured output, and often rely exclusively on prompt or context engineering.
+
+In this sense, we proved you with an alternative for structured data extraction, using the `exec` method with `responseFormat`.
+
+For example, you can, in a new folder, install our Anthropic integration and `zod` v3:
+
+```package-install
+npm init
+npm i -D typescript @types/node
+npm i @llamaindex/anthropic zod@3.25.76
+```
+
+And then try extracting data with this code:
+
+<include cwd>../../examples/agents/tools/response-format-exec.ts</include>
+
+The output should look like this:
+
+```json
+{
+  "title": "La Divina Commedia",
+  "author": "Dante Alighieri",
+  "year": 1321
+}
+```

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

@@ -1,5 +1,24 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.190
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.0.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.188
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
 ## 0.0.187
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.187",
+  "version": "0.0.190",
   "type": "module",
   "private": true,
   "scripts": {

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

@@ -1,5 +1,17 @@
 # @llamaindex/llama-parse-browser-test
 
+## 0.0.87
+
+### Patch Changes
+
+- @llamaindex/cloud@4.1.3
+
+## 0.0.86
+
+### Patch Changes
+
+- @llamaindex/cloud@4.1.2
+
 ## 0.0.85
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.85",
+  "version": "0.0.87",
   "type": "module",
   "scripts": {
     "dev": "vite",
@@ -10,7 +10,7 @@
   },
   "devDependencies": {
     "typescript": "^5.8.3",
-    "vite": "^6.3.3",
+    "vite": "^6.3.6",
     "vite-plugin-wasm": "^3.4.1"
   },
   "dependencies": {

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,24 @@
 # @llamaindex/next-agent-test
 
+## 0.1.190
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.1.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.1.188
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
 ## 0.1.187
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.187",
+  "version": "0.1.190",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,24 @@
 # test-edge-runtime
 
+## 0.1.189
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.1.188
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.1.187
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
 ## 0.1.186
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.186",
+  "version": "0.1.189",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,29 @@
 # @llamaindex/next-node-runtime
 
+## 0.1.61
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+  - @llamaindex/huggingface@0.1.29
+  - @llamaindex/readers@3.1.20
+
+## 0.1.60
+
+### Patch Changes
+
+- llamaindex@0.11.28
+- @llamaindex/huggingface@0.1.28
+
+## 0.1.59
+
+### Patch Changes
+
+- llamaindex@0.11.27
+- @llamaindex/huggingface@0.1.27
+- @llamaindex/readers@3.1.19
+
 ## 0.1.58
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.58",
+  "version": "0.1.61",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,24 @@
 # vite-import-llamaindex
 
+## 0.0.56
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.0.55
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.54
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
 ## 0.0.53
 
 ### Patch Changes

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

@@ -1,11 +1,12 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.53",
+  "version": "0.0.56",
   "type": "module",
   "scripts": {
     "build": "vite build",
-    "size-limit": "size-limit"
+    "size-limit": "size-limit",
+    "ci-build": "pnpm -C ../../../ build && vite build"
   },
   "size-limit": [
     {
@@ -16,7 +17,7 @@
     "@size-limit/preset-big-lib": "^11.1.6",
     "size-limit": "^11.1.6",
     "typescript": "^5.8.3",
-    "vite": "^6.3.3"
+    "vite": "^6.3.6"
   },
   "dependencies": {
     "llamaindex": "workspace:*"

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

@@ -1,5 +1,24 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.190
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.0.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.188
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
 ## 0.0.187
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.187",
+  "version": "0.0.190",
   "type": "module",
   "private": true,
   "scripts": {

e2e/node/fixtures/tools.ts

@@ -44,9 +44,7 @@ export const getWeatherTool = FunctionTool.from(
     name: "getWeather",
     description: "Get the weather for a city",
     parameters: z.object({
-      city: z.string({
-        description: "The city to get the weather for",
-      }),
+      city: z.string().describe("The city to get the weather for"),
     }),
   },
 );

examples/CHANGELOG.md

@@ -1,5 +1,135 @@
 # examples
 
+## 0.3.41
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+- Updated dependencies [5da1cda]
+- Updated dependencies [5d5cd44]
+- Updated dependencies [c40adaf]
+  - llamaindex@0.11.29
+  - @llamaindex/core@0.6.21
+  - @llamaindex/tools@0.1.11
+  - @llamaindex/workflow@1.1.23
+  - @llamaindex/ollama@0.1.22
+  - @llamaindex/openai@0.4.19
+  - @llamaindex/vercel@0.1.21
+  - @llamaindex/anthropic@0.3.24
+  - @llamaindex/google@0.3.21
+  - @llamaindex/cloud@4.1.3
+  - @llamaindex/node-parser@2.0.21
+  - @llamaindex/assemblyai@0.1.20
+  - @llamaindex/clip@0.0.75
+  - @llamaindex/cohere@0.0.35
+  - @llamaindex/deepinfra@0.0.75
+  - @llamaindex/discord@0.1.20
+  - @llamaindex/huggingface@0.1.29
+  - @llamaindex/jinaai@0.0.35
+  - @llamaindex/mistral@0.1.21
+  - @llamaindex/mixedbread@0.0.35
+  - @llamaindex/notion@0.1.20
+  - @llamaindex/perplexity@0.0.32
+  - @llamaindex/portkey-ai@0.0.63
+  - @llamaindex/replicate@0.0.63
+  - @llamaindex/bm25-retriever@0.0.10
+  - @llamaindex/astra@0.0.35
+  - @llamaindex/azure@0.1.36
+  - @llamaindex/chroma@0.0.35
+  - @llamaindex/elastic-search@0.1.21
+  - @llamaindex/firestore@1.0.28
+  - @llamaindex/milvus@0.1.30
+  - @llamaindex/mongodb@0.0.36
+  - @llamaindex/pinecone@0.1.21
+  - @llamaindex/postgres@0.0.64
+  - @llamaindex/qdrant@0.1.31
+  - @llamaindex/supabase@0.1.22
+  - @llamaindex/upstash@0.0.35
+  - @llamaindex/weaviate@0.0.36
+  - @llamaindex/voyage-ai@1.0.27
+  - @llamaindex/readers@3.1.20
+  - @llamaindex/deepseek@0.0.37
+  - @llamaindex/fireworks@0.0.35
+  - @llamaindex/groq@0.0.91
+  - @llamaindex/together@0.0.35
+  - @llamaindex/vllm@0.0.61
+  - @llamaindex/xai@0.0.22
+
+## 0.3.40
+
+### Patch Changes
+
+- Updated dependencies [1995b38]
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/workflow@1.1.22
+  - @llamaindex/openai@0.4.18
+  - llamaindex@0.11.28
+  - @llamaindex/clip@0.0.74
+  - @llamaindex/deepinfra@0.0.74
+  - @llamaindex/deepseek@0.0.36
+  - @llamaindex/fireworks@0.0.34
+  - @llamaindex/groq@0.0.90
+  - @llamaindex/huggingface@0.1.28
+  - @llamaindex/jinaai@0.0.34
+  - @llamaindex/perplexity@0.0.31
+  - @llamaindex/azure@0.1.35
+  - @llamaindex/together@0.0.34
+  - @llamaindex/vllm@0.0.60
+  - @llamaindex/xai@0.0.21
+
+## 0.3.39
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+  - @llamaindex/cloud@4.1.2
+  - llamaindex@0.11.27
+  - @llamaindex/node-parser@2.0.20
+  - @llamaindex/anthropic@0.3.23
+  - @llamaindex/assemblyai@0.1.19
+  - @llamaindex/clip@0.0.73
+  - @llamaindex/cohere@0.0.34
+  - @llamaindex/deepinfra@0.0.73
+  - @llamaindex/discord@0.1.19
+  - @llamaindex/google@0.3.20
+  - @llamaindex/huggingface@0.1.27
+  - @llamaindex/jinaai@0.0.33
+  - @llamaindex/mistral@0.1.20
+  - @llamaindex/mixedbread@0.0.34
+  - @llamaindex/notion@0.1.19
+  - @llamaindex/ollama@0.1.21
+  - @llamaindex/openai@0.4.17
+  - @llamaindex/perplexity@0.0.30
+  - @llamaindex/portkey-ai@0.0.62
+  - @llamaindex/replicate@0.0.62
+  - @llamaindex/bm25-retriever@0.0.9
+  - @llamaindex/astra@0.0.34
+  - @llamaindex/azure@0.1.34
+  - @llamaindex/chroma@0.0.34
+  - @llamaindex/elastic-search@0.1.20
+  - @llamaindex/firestore@1.0.27
+  - @llamaindex/milvus@0.1.29
+  - @llamaindex/mongodb@0.0.35
+  - @llamaindex/pinecone@0.1.20
+  - @llamaindex/postgres@0.0.63
+  - @llamaindex/qdrant@0.1.30
+  - @llamaindex/supabase@0.1.21
+  - @llamaindex/upstash@0.0.34
+  - @llamaindex/weaviate@0.0.35
+  - @llamaindex/vercel@0.1.20
+  - @llamaindex/voyage-ai@1.0.26
+  - @llamaindex/readers@3.1.19
+  - @llamaindex/tools@0.1.10
+  - @llamaindex/workflow@1.1.21
+  - @llamaindex/deepseek@0.0.35
+  - @llamaindex/fireworks@0.0.33
+  - @llamaindex/groq@0.0.89
+  - @llamaindex/together@0.0.33
+  - @llamaindex/vllm@0.0.59
+  - @llamaindex/xai@0.0.20
+
 ## 0.3.38
 
 ### Patch Changes

examples/agents/agent/blog-writer.ts

@@ -20,9 +20,7 @@ const saveFileTool = tool({
   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",
-    }),
+    content: z.string().describe("The content to save into a file"),
   }),
   execute: ({ content }: { content: string }) => {
     const filePath = os.tmpdir() + "/report.md";

examples/agents/agent/large-toolcall.ts

@@ -17,9 +17,7 @@ const userQuestion = "which are the best comedies after 2010?";
     description:
       "Execute python code in a Jupyter notebook cell and return any result, stdout, stderr, display_data, and error.",
     parameters: z.object({
-      code: z.string({
-        description: "The python code to execute in a single cell.",
-      }),
+      code: z.string().describe("The python code to execute in a single cell."),
     }),
     execute: ({ code }) => {
       console.log(

examples/agents/agent/multiple-agents.ts

@@ -26,9 +26,7 @@ const temperatureConverterTool = tool({
   description: "Convert a temperature from Fahrenheit to Celsius",
   name: "fahrenheitToCelsius",
   parameters: z.object({
-    temperature: z.number({
-      description: "The temperature in Fahrenheit",
-    }),
+    temperature: z.number().describe("The temperature in Fahrenheit"),
   }),
   execute: ({ temperature }) => {
     return ((temperature - 32) * 5) / 9;
@@ -39,9 +37,7 @@ const temperatureFetcherTool = tool({
   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",
-    }),
+    city: z.string().describe("The city to fetch the temperature for"),
   }),
   execute: ({ city }) => {
     const temperature = Math.floor(Math.random() * 58) + 32;

examples/agents/agent/with-anthropic.ts

@@ -14,9 +14,7 @@ const weatherTool = tool({
   name: "weather",
   description: "Get the weather",
   parameters: z.object({
-    location: z.string({
-      description: "The location to get the weather for",
-    }),
+    location: z.string().describe("The location to get the weather for"),
   }),
   execute: ({ location }) => {
     return `The weather in ${location} is sunny`;
@@ -27,9 +25,7 @@ const inflationTool = tool({
   name: "inflation",
   description: "Get the inflation",
   parameters: z.object({
-    location: z.string({
-      description: "The location to get the inflation for",
-    }),
+    location: z.string().describe("The location to get the inflation for"),
   }),
   execute: ({ location }) => {
     return `The inflation in ${location} is 2%`;
@@ -41,9 +37,7 @@ const saveFileTool = tool({
   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",
-    }),
+    content: z.string().describe("The content to save into a file"),
   }),
   execute: ({ content }) => {
     const filePath = "./report.md";

examples/agents/natural/joke.ts

@@ -14,11 +14,8 @@ const writeJokeSchema = z.object({
     .describe("The topic to write a joke or describe the joke to improve."),
   writtenJoke: z.optional(z.string()).describe("The written joke."),
   retriedTimes: z
-    .number()
-    .default(0)
-    .describe(
-      "The retried times for writing the joke. Always increase this from the input retriedTimes.",
-    ),
+    .optional(z.number().default(0))
+    .describe("The retried times for writing the joke."),
 });
 
 const critiqueSchema = z.object({

examples/agents/tools/response-format-exec.ts

@@ -0,0 +1,39 @@
+import { Anthropic } from "@llamaindex/anthropic";
+import { ChatMessage, ToolCall } from "llamaindex";
+import { z } from "zod";
+
+const llm = new Anthropic({ model: "claude-4-0-sonnet" });
+
+const responseSchema = z.object({
+  title: z.string().describe("The title of the book"),
+  author: z.string().describe("The author of the book"),
+  year: z.number().describe("The publication year"),
+});
+
+async function main() {
+  const messages: ChatMessage[] = [];
+  let toolCalls: ToolCall[] = [];
+  do {
+    const result = await llm.exec({
+      messages: [
+        {
+          role: "system",
+          content: `You are a book expert. Your task is, given a user message, extract the title, author and publication year of the book and output them in JSON format.`,
+        },
+        {
+          role: "user",
+          content: `I have been reading La Divina Commedia by Dante Alighieri, published in 1321, which tells the story of a guy who goes through Hell, Purgatory and Heaven just to meet his beloved ex-girlfriend.`,
+        },
+      ],
+      responseFormat: responseSchema,
+    });
+    console.log(result.newMessages[0].content);
+    messages.push(...result.newMessages);
+    toolCalls = result.toolCalls;
+  } while (toolCalls.length == 0);
+
+  console.log(messages[1].content);
+  console.log(toolCalls);
+}
+
+main().catch(console.error);

examples/agents/workflow/joke.ts

@@ -22,7 +22,7 @@ const { withState, getContext } = createStatefulMiddleware(() => ({
 const jokeFlow = withState(createWorkflow());
 
 // Define handlers for each step
-jokeFlow.handle([startEvent], async (event) => {
+jokeFlow.handle([startEvent], async (context, event) => {
   // Prompt the LLM to write a joke
   const prompt = `Write your best joke about ${event.data}. Write the joke between <joke> and </joke> tags.`;
   const response = await llm.complete({ prompt });
@@ -34,7 +34,7 @@ jokeFlow.handle([startEvent], async (event) => {
   return jokeEvent.with({ joke: joke });
 });
 
-jokeFlow.handle([jokeEvent], async (event) => {
+jokeFlow.handle([jokeEvent], async (context, event) => {
   // Prompt the LLM to critique the joke
   const prompt = `Give a thorough critique of the following joke. If the joke needs improvement, put "IMPROVE" somewhere in the critique: ${event.data.joke}`;
   const response = await llm.complete({ prompt });
@@ -50,9 +50,9 @@ jokeFlow.handle([jokeEvent], async (event) => {
   return resultEvent.with({ joke: event.data.joke, critique: response.text });
 });
 
-jokeFlow.handle([critiqueEvent], async (event) => {
+jokeFlow.handle([critiqueEvent], async (context, event) => {
   // Keep track of the number of iterations
-  const state = getContext().state;
+  const state = context.state;
   state.numIterations++;
 
   // Write a new joke based on the previous joke and critique

examples/deprecated/agents/large_toolcall_with_gpt4o.ts

@@ -29,9 +29,9 @@ async function callLLM(init: { model: string }) {
       description:
         "Execute python code in a Jupyter notebook cell and return any result, stdout, stderr, display_data, and error.",
       parameters: z.object({
-        code: z.string({
-          description: "The python code to execute in a single cell.",
-        }),
+        code: z
+          .string()
+          .describe("The python code to execute in a single cell."),
       }),
     },
   );

examples/local-settings/local-settings.ts

@@ -0,0 +1,69 @@
+import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
+import express, { Request, Response } from "express";
+import fs from "fs/promises";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
+
+const app = express();
+const port = 3000;
+
+app.get("/default", async (req: Request, res: Response) => {
+  const embedModel = new OpenAIEmbedding({
+    apiKey: process.env.OPENAI_API_KEY,
+  });
+  const llm = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
+
+  const llmResponse = await Settings.withEmbedModel(embedModel, async () => {
+    return Settings.withLLM(llm, async () => {
+      const path = "node_modules/llamaindex/examples/abramov.txt";
+      const essay = await fs.readFile(path, "utf-8");
+      // Create Document object with essay
+      const document = new Document({ text: essay, id_: path });
+      // Split text and create embeddings. Store them in a VectorStoreIndex
+      const index = await VectorStoreIndex.fromDocuments([document]);
+      // Query the index
+      const queryEngine = index.asQueryEngine();
+      const { message, sourceNodes } = await queryEngine.query({
+        query: "What did the author do in college?",
+      });
+      // Return response with sources
+      return message.content;
+    });
+  });
+  // res.send(message.content)
+  res.send(llmResponse);
+});
+
+app.get("/custom", async (req: Request, res: Response) => {
+  const embedModel = new OpenAIEmbedding({
+    apiKey: process.env.OPENAI_API_KEY,
+    model: "text-embedding-3-small",
+  });
+  const llm = new OpenAI({
+    apiKey: process.env.OPENAI_API_KEY,
+    model: "gpt-3.5-turbo",
+  });
+
+  const llmResponse = await Settings.withEmbedModel(embedModel, async () => {
+    return Settings.withLLM(llm, async () => {
+      const path = "node_modules/llamaindex/examples/abramov.txt";
+      const essay = await fs.readFile(path, "utf-8");
+      // Create Document object with essay
+      const document = new Document({ text: essay, id_: path });
+      // Split text and create embeddings. Store them in a VectorStoreIndex
+      const index = await VectorStoreIndex.fromDocuments([document]);
+      // Query the index
+      const queryEngine = index.asQueryEngine();
+      const { message, sourceNodes } = await queryEngine.query({
+        query: "What did the author do in college?",
+      });
+      // Return response with sources
+      return message.content;
+    });
+  });
+  // res.send(message.content)
+  res.send(llmResponse);
+});
+
+app.listen(port, () => {
+  console.log(`Example app listening on port ${port}`);
+});

examples/local-settings/package.json

@@ -0,0 +1,22 @@
+{
+  "name": "local-settings",
+  "version": "1.0.0",
+  "main": "index.js",
+  "private": "true",
+  "scripts": {
+    "test": "echo \"No tests for example package\""
+  },
+  "keywords": [],
+  "author": "",
+  "license": "ISC",
+  "description": "",
+  "devDependencies": {
+    "@types/express": "^5.0.3",
+    "typescript": "^5.9.2"
+  },
+  "dependencies": {
+    "@llamaindex/openai": "^0.4.16",
+    "express": "^5.1.0",
+    "llamaindex": "^0.11.26"
+  }
+}

examples/local-settings/tsconfig.json

@@ -0,0 +1,8 @@
+{
+  "extends": "../tsconfig.json",
+  "compilerOptions": {
+    "moduleResolution": "node",
+    "types": ["node", "express"]
+  },
+  "include": ["*.ts"]
+}

examples/models/gemini/live/tool-call.ts

@@ -8,9 +8,7 @@ const weatherTool = tool({
   name: "weather",
   description: "Get the weather",
   parameters: z.object({
-    location: z.string({
-      description: "The location to get the weather for",
-    }),
+    location: z.string().describe("The location to get the weather for"),
   }),
   execute: ({ location }) => {
     return `The weather in ${location} is rainy`;

examples/models/openai/responses/tool-call.ts

@@ -7,9 +7,7 @@ async function main() {
     name: "weather",
     description: "Get the weather",
     parameters: z.object({
-      location: z.string({
-        description: "The location to get the weather for",
-      }),
+      location: z.string().describe("The location to get the weather for"),
     }),
     execute: ({ location }) => {
       return `The weather in ${location} is sunny`;

examples/models/vercel/llamacloud.ts

@@ -1,6 +1,6 @@
 import { openai } from "@ai-sdk/openai";
 import { llamaindex } from "@llamaindex/vercel";
-import { streamText } from "ai";
+import { stepCountIs, streamText } from "ai";
 import { Document, LlamaCloudIndex } from "llamaindex";
 import fs from "node:fs/promises";
 
@@ -28,7 +28,7 @@ async function main() {
           "get information from your knowledge base to answer questions.", // optional description
       }),
     },
-    maxSteps: 5,
+    stopWhen: stepCountIs(5),
   });
 
   for await (const textPart of result.textStream) {

examples/models/vercel/vector-store.ts

@@ -1,6 +1,6 @@
 import { openai } from "@ai-sdk/openai";
 import { llamaindex } from "@llamaindex/vercel";
-import { streamText } from "ai";
+import { stepCountIs, streamText } from "ai";
 import { Document, VectorStoreIndex } from "llamaindex";
 
 import fs from "node:fs/promises";
@@ -24,7 +24,7 @@ async function main() {
           "get information from your knowledge base to answer questions.", // optional description
       }),
     },
-    maxSteps: 5,
+    stopWhen: stepCountIs(5),
   });
 
   for await (const textPart of result.textStream) {

examples/package.json

@@ -1,77 +1,78 @@
 {
   "name": "@llamaindex/examples",
-  "version": "0.3.38",
+  "version": "0.3.41",
   "private": true,
   "scripts": {
     "lint": "eslint .",
     "start": "echo 'To get started, run `npx tsx <path to example>`'"
   },
   "dependencies": {
-    "@ai-sdk/openai": "^1.0.5",
+    "@ai-sdk/openai": "^2.0.27",
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@azure/search-documents": "^12.1.0",
-    "@llamaindex/anthropic": "^0.3.22",
-    "@llamaindex/assemblyai": "^0.1.18",
-    "@llamaindex/astra": "^0.0.33",
-    "@llamaindex/azure": "^0.1.33",
-    "@llamaindex/bm25-retriever": "^0.0.8",
-    "@llamaindex/chroma": "^0.0.33",
-    "@llamaindex/clip": "^0.0.72",
-    "@llamaindex/cloud": "^4.1.1",
-    "@llamaindex/cohere": "^0.0.33",
-    "@llamaindex/core": "^0.6.19",
-    "@llamaindex/deepinfra": "^0.0.72",
-    "@llamaindex/deepseek": "^0.0.34",
-    "@llamaindex/discord": "^0.1.18",
-    "@llamaindex/elastic-search": "^0.1.19",
+    "@llamaindex/anthropic": "^0.3.24",
+    "@llamaindex/assemblyai": "^0.1.20",
+    "@llamaindex/astra": "^0.0.35",
+    "@llamaindex/azure": "^0.1.36",
+    "@llamaindex/bm25-retriever": "^0.0.10",
+    "@llamaindex/chroma": "^0.0.35",
+    "@llamaindex/clip": "^0.0.75",
+    "@llamaindex/cloud": "^4.1.3",
+    "@llamaindex/cohere": "^0.0.35",
+    "@llamaindex/core": "^0.6.21",
+    "@llamaindex/deepinfra": "^0.0.75",
+    "@llamaindex/deepseek": "^0.0.37",
+    "@llamaindex/discord": "^0.1.20",
+    "@llamaindex/elastic-search": "^0.1.21",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/firestore": "^1.0.26",
-    "@llamaindex/fireworks": "^0.0.32",
-    "@llamaindex/google": "^0.3.18",
-    "@llamaindex/groq": "^0.0.88",
-    "@llamaindex/huggingface": "^0.1.26",
-    "@llamaindex/jinaai": "^0.0.32",
-    "@llamaindex/milvus": "^0.1.28",
-    "@llamaindex/mistral": "^0.1.19",
-    "@llamaindex/mixedbread": "^0.0.33",
-    "@llamaindex/mongodb": "^0.0.34",
-    "@llamaindex/node-parser": "^2.0.19",
-    "@llamaindex/notion": "^0.1.18",
-    "@llamaindex/ollama": "^0.1.20",
-    "@llamaindex/openai": "^0.4.16",
-    "@llamaindex/perplexity": "^0.0.29",
-    "@llamaindex/pinecone": "^0.1.19",
-    "@llamaindex/portkey-ai": "^0.0.61",
-    "@llamaindex/postgres": "^0.0.62",
-    "@llamaindex/qdrant": "^0.1.29",
-    "@llamaindex/readers": "^3.1.18",
-    "@llamaindex/replicate": "^0.0.61",
-    "@llamaindex/supabase": "^0.1.20",
-    "@llamaindex/together": "^0.0.32",
-    "@llamaindex/tools": "^0.1.9",
-    "@llamaindex/upstash": "^0.0.33",
-    "@llamaindex/vercel": "^0.1.19",
-    "@llamaindex/vllm": "^0.0.58",
-    "@llamaindex/voyage-ai": "^1.0.25",
-    "@llamaindex/weaviate": "^0.0.34",
-    "@llamaindex/workflow": "^1.1.20",
-    "@llamaindex/xai": "^0.0.19",
+    "@llamaindex/firestore": "^1.0.28",
+    "@llamaindex/fireworks": "^0.0.35",
+    "@llamaindex/google": "^0.3.21",
+    "@llamaindex/groq": "^0.0.91",
+    "@llamaindex/huggingface": "^0.1.29",
+    "@llamaindex/jinaai": "^0.0.35",
+    "@llamaindex/milvus": "^0.1.30",
+    "@llamaindex/mistral": "^0.1.21",
+    "@llamaindex/mixedbread": "^0.0.35",
+    "@llamaindex/mongodb": "^0.0.36",
+    "@llamaindex/node-parser": "^2.0.21",
+    "@llamaindex/notion": "^0.1.20",
+    "@llamaindex/ollama": "^0.1.22",
+    "@llamaindex/openai": "^0.4.19",
+    "@llamaindex/perplexity": "^0.0.32",
+    "@llamaindex/pinecone": "^0.1.21",
+    "@llamaindex/portkey-ai": "^0.0.63",
+    "@llamaindex/postgres": "^0.0.64",
+    "@llamaindex/qdrant": "^0.1.31",
+    "@llamaindex/readers": "^3.1.20",
+    "@llamaindex/replicate": "^0.0.63",
+    "@llamaindex/supabase": "^0.1.22",
+    "@llamaindex/together": "^0.0.35",
+    "@llamaindex/tools": "^0.1.11",
+    "@llamaindex/upstash": "^0.0.35",
+    "@llamaindex/vercel": "^0.1.21",
+    "@llamaindex/vllm": "^0.0.61",
+    "@llamaindex/voyage-ai": "^1.0.27",
+    "@llamaindex/weaviate": "^0.0.36",
+    "@llamaindex/workflow": "^1.1.23",
+    "@llamaindex/xai": "^0.0.22",
     "@notionhq/client": "^4.0.0",
     "@pinecone-database/pinecone": "^4.0.0",
     "@vercel/postgres": "^0.10.0",
-    "ai": "^4.3.17",
+    "ai": "^5.0.39",
     "ajv": "^8.17.1",
     "commander": "^12.1.0",
     "dotenv": "^17.2.0",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.11.26",
+    "llamaindex": "^0.11.29",
     "mongodb": "6.7.0",
     "postgres": "^3.4.4",
     "wikipedia": "^2.1.2",
-    "zod": "^3.25.76"
+    "zod": "^4.1.5"
   },
   "devDependencies": {
+    "@types/express": "^5.0.3",
     "@types/node": "^24.0.13",
     "tsx": "^4.20.3",
     "typescript": "^5.8.3"

packages/autotool/CHANGELOG.md

@@ -1,5 +1,24 @@
 # @llamaindex/autotool
 
+## 8.0.29
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 8.0.28
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 8.0.27
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
 ## 8.0.26
 
 ### Patch Changes

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

@@ -1,5 +1,27 @@
 # @llamaindex/autotool-01-node-example
 
+## 0.0.137
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+  - @llamaindex/autotool@8.0.29
+
+## 0.0.136
+
+### Patch Changes
+
+- llamaindex@0.11.28
+- @llamaindex/autotool@8.0.28
+
+## 0.0.135
+
+### Patch Changes
+
+- llamaindex@0.11.27
+- @llamaindex/autotool@8.0.27
+
 ## 0.0.134
 
 ### 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": "0.0.134"
+  "version": "0.0.137"
 }

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "8.0.26",
+  "version": "8.0.29",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",

packages/cloud/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @llamaindex/cloud
 
+## 4.1.3
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+
+## 4.1.2
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 4.1.1
 
 ### Patch Changes

packages/cloud/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloud",
-  "version": "4.1.1",
+  "version": "4.1.3",
   "type": "module",
   "license": "MIT",
   "scripts": {

packages/community/CHANGELOG.md

@@ -1,5 +1,20 @@
 # @llamaindex/community
 
+## 0.0.103
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+
+## 0.0.102
+
+### Patch Changes
+
+- 6ebd7c2: fix: invoke complete command using the actual modelId
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.0.101
 
 ### Patch Changes

packages/community/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.101",
+  "version": "0.0.103",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

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

@@ -493,6 +493,8 @@ export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
 
     if (params.stream) {
       const command = new InvokeModelWithResponseStreamCommand(input);
+      command.input.modelId = this.actualModel;
+
       const response = await this.client.send(command);
       if (response.body)
         return streamConverter(response.body, (response) => {
@@ -504,6 +506,8 @@ export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
     }
 
     const command = new InvokeModelCommand(input);
+    command.input.modelId = this.actualModel;
+
     const response = await this.client.send(command);
     return {
       text: this.provider.getTextFromResponse(response),

packages/core/CHANGELOG.md

@@ -1,5 +1,17 @@
 # @llamaindex/core
 
+## 0.6.21
+
+### Patch Changes
+
+- 5da1cda: feat: support zod v4 & v3
+
+## 0.6.20
+
+### Patch Changes
+
+- 0267bb0: Added responseFormat to llm.exec
+
 ## 0.6.19
 
 ### Patch Changes

packages/core/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.6.19",
+  "version": "0.6.21",
   "description": "LlamaIndex Core Module",
   "exports": {
     "./agent": {
@@ -278,6 +278,17 @@
         "default": "./postprocessor/dist/index.js"
       },
       "default": "./postprocessor/dist/index.js"
+    },
+    "./zod": {
+      "require": {
+        "types": "./zod/dist/index.d.cts",
+        "default": "./zod/dist/index.cjs"
+      },
+      "import": {
+        "types": "./zod/dist/index.d.ts",
+        "default": "./zod/dist/index.js"
+      },
+      "default": "./zod/dist/index.js"
     }
   },
   "files": [
@@ -302,7 +313,8 @@
     "./vector-store",
     "./tools",
     "./data-structs",
-    "./postprocessor"
+    "./postprocessor",
+    "./zod"
   ],
   "scripts": {
     "dev": "bunchee --watch",
@@ -321,9 +333,9 @@
   },
   "dependencies": {
     "@llamaindex/env": "workspace:*",
+    "@finom/zod-to-json-schema": "3.24.11",
     "@types/node": "^24.0.13",
     "magic-bytes.js": "^1.10.0",
-    "zod": "^3.25.76",
-    "zod-to-json-schema": "^3.24.6"
+    "zod": "^4.1.5"
   }
 }

packages/core/src/agent/utils.ts

@@ -1,5 +1,4 @@
 import type { Logger } from "@llamaindex/env";
-import { z } from "zod";
 import { type JSONObject, type JSONValue, Settings } from "../global";
 import type {
   BaseTool,
@@ -13,7 +12,7 @@ import type {
   ToolCallLLMMessageOptions,
   ToolOutput,
 } from "../llms";
-import { baseToolWithCallSchema } from "../schema";
+import { agentParamsSchema } from "../schema";
 import {
   assertIsJSONValue,
   isAsyncIterable,
@@ -305,7 +304,7 @@ export function validateAgentParams<AI extends LLM>(
   params: AgentParamsBase<AI>,
 ) {
   if ("tools" in params) {
-    z.array(baseToolWithCallSchema).parse(params.tools);
+    agentParamsSchema.parse(params.tools);
   } else {
     // todo: check `params.toolRetriever` when migrate to @llamaindex/core
   }

packages/core/src/llms/base.ts

@@ -1,6 +1,9 @@
 import { emptyLogger } from "@llamaindex/env";
+import type { JSONObject } from "../global";
+import { tool } from "../tools/";
 import { extractText } from "../utils/llms";
 import { streamConverter } from "../utils/stream";
+import { isZodSchema, safeParseSchema } from "../zod";
 import { callToolToMessage, getToolCallsFromResponse } from "./tool-call";
 import type {
   ChatMessage,
@@ -97,6 +100,31 @@ export abstract class BaseLLM<
     | ExecResponse<AdditionalMessageOptions>
     | ExecStreamResponse<AdditionalMessageOptions>
   > {
+    const responseFormat = params.responseFormat;
+    if (typeof responseFormat != "undefined" && isZodSchema(responseFormat)) {
+      const structuredTool = tool({
+        name: "format_output",
+        description: "Respond with a JSON object",
+        parameters: responseFormat,
+        execute: (args) => {
+          const result = safeParseSchema(responseFormat, args);
+          if (!result.success) {
+            console.error("Invalid input from LLM:", result.error);
+            return JSON.stringify({
+              error: "Invalid schema",
+              details: result.error,
+            });
+          }
+          return result.data as JSONObject;
+        },
+      });
+      if (Array.isArray(params.tools)) {
+        params.tools.push(structuredTool);
+      } else {
+        params.tools = [structuredTool];
+      }
+      params.responseFormat = undefined;
+    }
     if (params.stream) {
       return this.streamExec(params);
     }

packages/core/src/llms/type.ts

@@ -1,9 +1,10 @@
 import type { Logger } from "@llamaindex/env";
 import type { Tokenizers } from "@llamaindex/env/tokenizers";
 import type { JSONSchemaType } from "ajv";
-import { z } from "zod";
 import type { JSONObject, JSONValue } from "../global";
 import type { ModalityType } from "../schema";
+import type { ZodSchema } from "../zod";
+
 /**
  * @internal
  */
@@ -139,7 +140,7 @@ export interface LLMChatParamsBase<
   messages: ChatMessage<AdditionalMessageOptions>[];
   additionalChatOptions?: AdditionalChatOptions | undefined;
   tools?: BaseTool[] | undefined;
-  responseFormat?: z.ZodType | object | undefined;
+  responseFormat?: ZodSchema | object | undefined;
   logger?: Logger | undefined;
 }
 
@@ -159,7 +160,7 @@ export interface LLMChatParamsNonStreaming<
 
 export interface LLMCompletionParamsBase {
   prompt: MessageContent;
-  responseFormat?: z.ZodType | object;
+  responseFormat?: ZodSchema | object;
 }
 
 export interface LLMCompletionParamsStreaming extends LLMCompletionParamsBase {

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

@@ -1,10 +1,9 @@
 import { consoleLogger, type Logger } from "@llamaindex/env";
 import type { Tokenizer } from "@llamaindex/env/tokenizers";
-import { z } from "zod";
 import { Settings } from "../global";
-import { sentenceSplitterSchema } from "../schema";
+import { sentenceSplitterSchema, type SentenceSplitterParams } from "../schema";
 import { MetadataAwareTextSplitter } from "./base";
-import type { SplitterParams } from "./type";
+import type { PartialWithUndefined, SplitterParams } from "./type";
 import {
   splitByChar,
   splitByRegex,
@@ -52,7 +51,7 @@ export class SentenceSplitter extends MetadataAwareTextSplitter {
   #logger: Logger;
 
   constructor(
-    params?: z.input<typeof sentenceSplitterSchema> &
+    params?: PartialWithUndefined<SentenceSplitterParams> &
       SplitterParams & { logger?: Logger },
   ) {
     super();

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

@@ -1,12 +1,13 @@
 import { randomUUID } from "@llamaindex/env";
-import { z } from "zod";
 import {
   buildNodeFromSplits,
   Document,
   sentenceWindowNodeParserSchema,
   TextNode,
+  type SentenceWindowNodeParserParams,
 } from "../schema";
 import { NodeParser } from "./base";
+import type { PartialWithUndefined } from "./type";
 import { splitBySentenceTokenizer, type TextSplitterFn } from "./utils";
 
 export class SentenceWindowNodeParser extends NodeParser<TextNode[]> {
@@ -20,7 +21,7 @@ export class SentenceWindowNodeParser extends NodeParser<TextNode[]> {
   sentenceSplitter: TextSplitterFn = splitBySentenceTokenizer([], true);
   idGenerator: () => string = () => randomUUID();
 
-  constructor(params?: z.input<typeof sentenceWindowNodeParserSchema>) {
+  constructor(params?: PartialWithUndefined<SentenceWindowNodeParserParams>) {
     super();
     if (params) {
       const parsedParams = sentenceWindowNodeParserSchema.parse(params);

packages/core/src/node-parser/token-text-splitter.ts

@@ -1,20 +1,16 @@
 import { consoleLogger, type Logger } from "@llamaindex/env";
 import type { Tokenizer } from "@llamaindex/env/tokenizers";
-import { z } from "zod";
 import { DEFAULT_CHUNK_OVERLAP, DEFAULT_CHUNK_SIZE, Settings } from "../global";
+import {
+  tokenTextSplitterSchema,
+  type TokenTextSplitterParams,
+} from "../schema";
 import { MetadataAwareTextSplitter } from "./base";
-import type { SplitterParams } from "./type";
+import type { PartialWithUndefined, SplitterParams } from "./type";
 import { splitByChar, splitBySep } from "./utils";
 
 const DEFAULT_METADATA_FORMAT_LEN = 2;
 
-const tokenTextSplitterSchema = z.object({
-  chunkSize: z.number().positive().default(DEFAULT_CHUNK_SIZE),
-  chunkOverlap: z.number().nonnegative().default(DEFAULT_CHUNK_OVERLAP),
-  separator: z.string().default(" "),
-  backupSeparators: z.array(z.string()).default(["\n"]),
-});
-
 export class TokenTextSplitter extends MetadataAwareTextSplitter {
   chunkSize: number = DEFAULT_CHUNK_SIZE;
   chunkOverlap: number = DEFAULT_CHUNK_OVERLAP;
@@ -26,7 +22,7 @@ export class TokenTextSplitter extends MetadataAwareTextSplitter {
 
   constructor(
     params?: SplitterParams &
-      Partial<z.infer<typeof tokenTextSplitterSchema>> & { logger?: Logger },
+      PartialWithUndefined<TokenTextSplitterParams> & { logger?: Logger },
   ) {
     super();
 

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

@@ -3,3 +3,7 @@ import type { Tokenizer } from "@llamaindex/env/tokenizers";
 export type SplitterParams = {
   tokenizer?: Tokenizer;
 };
+
+export type PartialWithUndefined<T> = {
+  [P in keyof T]?: T[P] | undefined;
+};

packages/core/src/schema/zod.ts

@@ -1,5 +1,5 @@
-import { z } from "zod";
-import { Settings } from "../global";
+import { z } from "zod/v3"; // use zod v3 to keep schemas as it is
+import { DEFAULT_CHUNK_OVERLAP, DEFAULT_CHUNK_SIZE, Settings } from "../global";
 
 export const anyFunctionSchema = z.function(z.tuple([]).rest(z.any()), z.any());
 
@@ -18,6 +18,8 @@ export const baseToolWithCallSchema = baseToolSchema.extend({
   call: z.function(),
 });
 
+export const agentParamsSchema = z.array(baseToolWithCallSchema);
+
 export const sentenceSplitterSchema = z
   .object({
     chunkSize: z
@@ -83,3 +85,16 @@ export const sentenceWindowNodeParserSchema = z.object({
     })
     .default("originalText"),
 });
+
+export const tokenTextSplitterSchema = z.object({
+  chunkSize: z.number().positive().default(DEFAULT_CHUNK_SIZE),
+  chunkOverlap: z.number().nonnegative().default(DEFAULT_CHUNK_OVERLAP),
+  separator: z.string().default(" "),
+  backupSeparators: z.array(z.string()).default(["\n"]),
+});
+
+export type SentenceSplitterParams = z.infer<typeof sentenceSplitterSchema>;
+export type TokenTextSplitterParams = z.infer<typeof tokenTextSplitterSchema>;
+export type SentenceWindowNodeParserParams = z.infer<
+  typeof sentenceWindowNodeParserSchema
+>;

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

@@ -1,9 +1,15 @@
 import { consoleLogger, type Logger } from "@llamaindex/env";
 import type { JSONSchemaType } from "ajv";
-import { z } from "zod";
-import { zodToJsonSchema } from "zod-to-json-schema";
+import type * as z3 from "zod/v3";
+import type * as z4 from "zod/v4/core";
 import type { JSONValue } from "../global";
 import type { BaseTool, ToolMetadata } from "../llms";
+import {
+  isZodSchema,
+  safeParseSchema,
+  type ZodSchema,
+  zodToJsonSchema,
+} from "../zod";
 
 export class FunctionTool<
   T,
@@ -14,12 +20,13 @@ export class FunctionTool<
   #fn: (input: T, additionalArg?: AdditionalToolArgument) => R;
   #additionalArg: AdditionalToolArgument | undefined;
   readonly #metadata: ToolMetadata<JSONSchemaType<T>>;
-  readonly #zodType: z.ZodType<T> | null = null;
+  readonly #zodType: ZodSchema<T> | null = null;
   readonly #logger: Logger;
+
   constructor(
     fn: (input: T, additionalArg?: AdditionalToolArgument) => R,
     metadata: ToolMetadata<JSONSchemaType<T>>,
-    zodType?: z.ZodType<T>,
+    zodType?: ZodSchema<T>,
     additionalArg?: AdditionalToolArgument,
     logger?: Logger,
   ) {
@@ -32,6 +39,9 @@ export class FunctionTool<
     this.#logger = logger ?? consoleLogger;
   }
 
+  // ----------------- OVERLOAD -----------------
+
+  // Plain JSON schema
   static from<T, AdditionalToolArgument extends object = object>(
     fn: (
       input: T,
@@ -39,54 +49,74 @@ export class FunctionTool<
     ) => JSONValue | Promise<JSONValue>,
     schema: ToolMetadata<JSONSchemaType<T>>,
   ): FunctionTool<T, JSONValue | Promise<JSONValue>, AdditionalToolArgument>;
-  static from<
-    R extends z.ZodType,
-    AdditionalToolArgument extends object = object,
-  >(
+
+  // Function + Object configs + Zod v3 schema
+  static from<R, AdditionalToolArgument extends object = object>(
     fn: (
-      input: z.infer<R>,
+      // @ts-expect-error <R> should extend z3.ZodTypeAny
+      // but we remove that to fix type instantiation is excessively deep and possibly infinite
+      input: z3.infer<R>,
       additionalArg?: AdditionalToolArgument,
     ) => JSONValue | Promise<JSONValue>,
-    schema: Omit<ToolMetadata, "parameters"> & {
-      parameters: R;
-    },
+    schema: Omit<ToolMetadata, "parameters"> & { parameters: R },
   ): FunctionTool<
-    z.infer<R>,
+    // @ts-expect-error <R> should extend z3.ZodTypeAny
+    // but we remove that to fix type instantiation is excessively deep and possibly infinite
+    z3.infer<R>,
     JSONValue | Promise<JSONValue>,
     AdditionalToolArgument
   >;
-  static from<
-    T,
-    R extends z.ZodType<T>,
-    AdditionalToolArgument extends object = object,
-  >(
+
+  // Function + Object configs + Zod v4 schema
+  static from<R, AdditionalToolArgument extends object = object>(
     fn: (
-      input: T,
+      input: z4.infer<R>,
       additionalArg?: AdditionalToolArgument,
     ) => JSONValue | Promise<JSONValue>,
-    schema: Omit<ToolMetadata, "parameters"> & {
-      parameters: R;
-    },
-  ): FunctionTool<T, JSONValue, AdditionalToolArgument>;
-  static from<
-    R extends z.ZodType,
-    AdditionalToolArgument extends object = object,
-  >(
+    schema: Omit<ToolMetadata, "parameters"> & { parameters: R },
+  ): FunctionTool<
+    z4.infer<R>,
+    JSONValue | Promise<JSONValue>,
+    AdditionalToolArgument
+  >;
+
+  // Object configs + Zod v3 schema
+  static from<R, AdditionalToolArgument extends object = object>(
     config: Omit<ToolMetadata, "parameters"> & {
       parameters: R;
       execute: (
-        input: z.infer<R>,
+        // @ts-expect-error <R> should extend z3.ZodTypeAny
+        // but we remove that to fix type instantiation is excessively deep and possibly infinite
+        input: z3.infer<R>,
         additionalArg?: AdditionalToolArgument,
       ) => JSONValue | Promise<JSONValue>;
     },
   ): FunctionTool<
-    z.infer<R>,
+    // @ts-expect-error <R> should extend z3.ZodTypeAny
+    // but we remove that to fix type instantiation is excessively deep and possibly infinite
+    z3.infer<R>,
     JSONValue | Promise<JSONValue>,
     AdditionalToolArgument
   >;
+
+  // Object configs + Zod v4 schema
+  static from<R, AdditionalToolArgument extends object = object>(
+    config: Omit<ToolMetadata, "parameters"> & {
+      parameters: R;
+      execute: (
+        input: z4.infer<R>,
+        additionalArg?: AdditionalToolArgument,
+      ) => JSONValue | Promise<JSONValue>;
+    },
+  ): FunctionTool<
+    z4.infer<R>,
+    JSONValue | Promise<JSONValue>,
+    AdditionalToolArgument
+  >;
+
+  // ----------------- IMPLEMENTATION -----------------
   // eslint-disable-next-line @typescript-eslint/no-explicit-any
   static from(fnOrConfig: any, schema?: any): any {
-    // Handle the case where an object with execute function is passed
     if (
       typeof schema === "undefined" &&
       typeof fnOrConfig === "object" &&
@@ -94,7 +124,7 @@ export class FunctionTool<
     ) {
       const { execute, parameters, ...restConfig } = fnOrConfig;
 
-      if (parameters instanceof z.ZodSchema) {
+      if (isZodSchema(parameters)) {
         const jsonSchema = zodToJsonSchema(parameters);
         return new FunctionTool(
           execute,
@@ -105,12 +135,10 @@ export class FunctionTool<
           parameters,
         );
       }
-
       return new FunctionTool(execute, fnOrConfig);
     }
 
-    // Handle the original cases
-    if (schema && schema.parameters instanceof z.ZodSchema) {
+    if (schema && isZodSchema(schema.parameters)) {
       const jsonSchema = zodToJsonSchema(schema.parameters);
       return new FunctionTool(
         fnOrConfig,
@@ -140,11 +168,11 @@ export class FunctionTool<
   call = (input: T) => {
     let params = input;
     if (this.#zodType) {
-      const result = this.#zodType.safeParse(input);
+      const result = safeParseSchema(this.#zodType, input);
       if (result.success) {
         params = result.data;
       } else {
-        this.#logger.warn(result.error.errors);
+        this.#logger.warn(result.error);
       }
     }
     return this.#fn.call(null, params, this.#additionalArg);

packages/core/src/zod/index.ts

@@ -0,0 +1,71 @@
+/* eslint-disable @typescript-eslint/no-explicit-any */
+
+import { zodToJsonSchema as zodToJsonSchemaV3 } from "@finom/zod-to-json-schema";
+import * as z from "zod";
+import * as z3 from "zod/v3";
+import * as z4 from "zod/v4/core";
+
+export type ZodSchema<T = any> = z3.ZodType<T> | z4.$ZodType<T>;
+
+export type ZodInfer<T extends ZodSchema> =
+  T extends z3.ZodType<any>
+    ? z3.infer<T>
+    : T extends z4.$ZodType<any>
+      ? z4.infer<T>
+      : never;
+
+// support parsing both Zod 3 schemas and Zod 4 schemas
+export function parseSchema<T>(schema: ZodSchema<T>, data: unknown): T {
+  if ("_zod" in schema) {
+    // Zod 4 schema
+    return z4.parse(schema as z4.$ZodType<T>, data);
+  } else {
+    // Zod 3 schema
+    return (schema as z3.ZodType<T>).parse(data);
+  }
+}
+
+// safe parse schema
+export function safeParseSchema<T>(schema: ZodSchema<T>, data: unknown) {
+  if ("_zod" in schema) {
+    // Zod 4 schema
+    return z4.safeParse(schema as z4.$ZodType<T>, data);
+  } else {
+    // Zod 3 schema
+    return (schema as z3.ZodType<T>).safeParse(data);
+  }
+}
+
+export function isZodSchema(obj: unknown): obj is ZodSchema {
+  return (
+    obj !== null &&
+    typeof obj === "object" &&
+    "parse" in obj &&
+    typeof (obj as { parse: unknown }).parse === "function" &&
+    "safeParse" in obj &&
+    typeof (obj as { safeParse: unknown }).safeParse === "function"
+  );
+}
+
+// zod 3 schema does not have _zod property
+export function isZodV3Schema(obj: unknown): obj is z3.ZodTypeAny {
+  return isZodSchema(obj) && !("_zod" in obj);
+}
+
+// zod 4 schema has _zod property
+export function isZodV4Schema(obj: unknown): obj is z4.$ZodType {
+  return isZodSchema(obj) && "_zod" in obj;
+}
+
+export function zodToJsonSchema(obj: ZodSchema) {
+  if (isZodV4Schema(obj)) {
+    // if schema is created from zod v4, use native toJSONSchema
+    return z4.toJSONSchema(obj);
+  }
+
+  // otherwise, use zod-to-json-schema
+  return zodToJsonSchemaV3(obj as any); // FIXME: use any to avoid type instantiation excessively
+}
+
+// re-export zod
+export { z, z3, z4 };

packages/core/tests/agents.test.ts

@@ -1,7 +1,7 @@
 import { LLMAgent, validateAgentParams } from "@llamaindex/core/agent";
 import { MockLLM } from "@llamaindex/core/llms/mock";
 import { expect, test } from "vitest";
-import { ZodError } from "zod";
+import { ZodError } from "zod/v3";
 
 test("validate agent params", () => {
   validateAgentParams({

packages/core/tests/package.json

@@ -7,6 +7,7 @@
   },
   "devDependencies": {
     "@llamaindex/core": "workspace:*",
-    "vitest": "^2.1.5"
+    "vitest": "^2.1.5",
+    "zod": "^4.1.5"
   }
 }

packages/core/tests/tools.test.ts

@@ -1,6 +1,7 @@
 import { FunctionTool, tool } from "@llamaindex/core/tools";
 import { describe, expect, test, vi } from "vitest";
-import { z } from "zod";
+import { z } from "zod/v3";
+import { z as z4 } from "zod/v4";
 
 describe("FunctionTool", () => {
   test("type system", () => {
@@ -95,4 +96,67 @@ describe("FunctionTool", () => {
     expect(hello).to.toHaveBeenCalledOnce();
     expect(hello).to.toHaveBeenCalledWith("Bob", additionalArg);
   });
+
+  test("works with Zod v4 schema", async () => {
+    const mockFn = vi.fn().mockImplementation(({ age }: { age: number }) => {
+      return `Age is ${age}`;
+    });
+
+    const schema = z4.object({
+      age: z4.number().int().min(0),
+    });
+
+    const toolV4 = FunctionTool.from(mockFn, {
+      name: "checkAge",
+      description: "Checks age",
+      parameters: schema,
+    });
+
+    const result = await toolV4.call({ age: 25 });
+    expect(result).toBe("Age is 25");
+    expect(mockFn).toHaveBeenCalledWith({ age: 25 }, undefined);
+  });
+
+  test("validates input with safeParseSchema (valid + invalid)", async () => {
+    const mockFn = vi.fn().mockImplementation(({ num }: { num: number }) => {
+      return num * 2;
+    });
+
+    const schema = z.object({
+      num: z.number(),
+    });
+
+    const toolWithValidation = FunctionTool.from(mockFn, {
+      name: "double",
+      description: "Doubles a number",
+      parameters: schema,
+    });
+
+    // valid input
+    const result = await toolWithValidation.call({ num: 10 });
+    expect(result).toBe(20);
+
+    // invalid input (string instead of number)
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    await toolWithValidation.call({ num: "oops" } as any);
+  });
+
+  test("works with plain JSON schema", async () => {
+    const mockFn = vi.fn().mockImplementation(({ msg }: { msg: string }) => {
+      return msg.toUpperCase();
+    });
+
+    const toolWithJson = FunctionTool.from(mockFn, {
+      name: "shout",
+      description: "Shouts the message",
+      parameters: {
+        type: "object",
+        properties: { msg: { type: "string" } },
+        required: ["msg"],
+      },
+    });
+
+    const result = await toolWithJson.call({ msg: "hi" });
+    expect(result).toBe("HI");
+  });
 });

packages/core/tests/zod.test.ts

@@ -0,0 +1,160 @@
+import {
+  isZodSchema,
+  isZodV3Schema,
+  isZodV4Schema,
+  parseSchema,
+  safeParseSchema,
+  zodToJsonSchema,
+} from "@llamaindex/core/zod";
+import { describe, expect, it } from "vitest";
+import { z as z3 } from "zod/v3";
+import { z as z4 } from "zod/v4";
+
+describe("Zod schema utils", () => {
+  describe("parseSchema / safeParseSchema", () => {
+    it("parses valid data with Zod v3 schema", () => {
+      const schema = z3.object({ name: z3.string() });
+      const result = parseSchema(schema, { name: "Alice" });
+      expect(result).toEqual({ name: "Alice" });
+    });
+
+    it("parses valid data with Zod v4 schema", () => {
+      const schema = z4.object({ age: z4.number() });
+      const result = parseSchema(schema, { age: 42 });
+      expect(result).toEqual({ age: 42 });
+    });
+
+    it("safeParse works with invalid data (v3)", () => {
+      const schema = z3.object({ name: z3.string() });
+      const res = safeParseSchema(schema, { name: 123 });
+      expect(res.success).toBe(false);
+    });
+
+    it("safeParse works with invalid data (v4)", () => {
+      const schema = z4.object({ age: z4.number() });
+      const res = safeParseSchema(schema, { age: "oops" });
+      expect(res.success).toBe(false);
+    });
+  });
+
+  describe("isZodV3Schema / isZodV4Schema / isZodSchema", () => {
+    it("detects a v3 schema", () => {
+      const schema = z3.string();
+      expect(isZodV3Schema(schema)).toBe(true);
+      expect(isZodSchema(schema)).toBe(true);
+      expect(isZodV4Schema(schema)).toBe(false);
+    });
+
+    it("detects a v4 schema", () => {
+      const schema = z4.string();
+      expect(isZodV4Schema(schema)).toBe(true);
+      expect(isZodSchema(schema)).toBe(true);
+      expect(isZodV3Schema(schema)).toBe(false);
+    });
+
+    it("returns false for non-schemas", () => {
+      expect(isZodSchema(123)).toBe(false);
+      expect(isZodSchema({})).toBe(false);
+    });
+  });
+
+  describe("zodToJsonSchema", () => {
+    it("converts v3 string schema", () => {
+      const schema = z3.string().min(2).max(5).describe("A short string");
+      const json = zodToJsonSchema(schema);
+      expect(json).toMatchObject({
+        type: "string",
+        minLength: 2,
+        maxLength: 5,
+        description: "A short string",
+      });
+    });
+
+    it("converts v3 object schema", () => {
+      const schema = z3.object({
+        id: z3.number(),
+        name: z3.string().optional(),
+      });
+      const json = zodToJsonSchema(schema);
+      expect(json).toMatchObject({
+        type: "object",
+        properties: {
+          id: { type: "number" },
+          name: { type: "string" },
+        },
+        required: ["id"],
+      });
+    });
+
+    it("converts v4 array schema", () => {
+      const schema = z4.array(z4.boolean());
+      const json = zodToJsonSchema(schema);
+      expect(json).toMatchObject({
+        type: "array",
+        items: { type: "boolean" },
+      });
+    });
+
+    it("converts v4 enum schema", () => {
+      const schema = z4.enum(["red", "green", "blue"]);
+      const json = zodToJsonSchema(schema);
+      expect(json).toMatchObject({
+        type: "string",
+        enum: ["red", "green", "blue"],
+      });
+    });
+
+    it("handles nested v3 objects", () => {
+      const schema = z3.object({
+        user: z3.object({
+          id: z3.number(),
+          tags: z3.array(z3.string()),
+        }),
+      });
+      const json = zodToJsonSchema(schema);
+      expect(json).toMatchObject({
+        type: "object",
+        properties: {
+          user: {
+            type: "object",
+            properties: {
+              id: { type: "number" },
+              tags: {
+                type: "array",
+                items: { type: "string" },
+              },
+            },
+            required: ["id", "tags"],
+          },
+        },
+        required: ["user"],
+      });
+    });
+
+    it("handles nested v4 objects", () => {
+      const schema = z4.object({
+        profile: z4.object({
+          email: z4.string(),
+          active: z4.boolean(),
+        }),
+      });
+      const json = zodToJsonSchema(schema);
+      expect(json).toMatchObject({
+        type: "object",
+        properties: {
+          profile: {
+            type: "object",
+            properties: {
+              email: { type: "string" },
+              active: { type: "boolean" },
+            },
+            required: ["email", "active"],
+            additionalProperties: false,
+          },
+        },
+        required: ["profile"],
+        additionalProperties: false,
+      });
+    });
+  });
+});

packages/core/zod/package.json

@@ -0,0 +1,8 @@
+{
+  "type": "module",
+  "main": "./dist/index.cjs",
+  "module": "./dist/index.js",
+  "types": "./dist/index.d.ts",
+  "exports": "./dist/index.js",
+  "private": true
+}

packages/experimental/CHANGELOG.md

@@ -1,5 +1,24 @@
 # @llamaindex/experimental
 
+## 0.0.206
+
+### Patch Changes
+
+- Updated dependencies [8929dcf]
+  - llamaindex@0.11.29
+
+## 0.0.205
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.204
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
 ## 0.0.203
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.203",
+  "version": "0.0.206",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,33 @@
 # llamaindex
 
+## 0.11.29
+
+### Patch Changes
+
+- 8929dcf: feat: vectorStoreIndex has new option progressCallback
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+  - @llamaindex/workflow@1.1.23
+  - @llamaindex/cloud@4.1.3
+  - @llamaindex/node-parser@2.0.21
+
+## 0.11.28
+
+### Patch Changes
+
+- Updated dependencies [1995b38]
+  - @llamaindex/workflow@1.1.22
+
+## 0.11.27
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+  - @llamaindex/cloud@4.1.2
+  - @llamaindex/node-parser@2.0.20
+  - @llamaindex/workflow@1.1.21
+
 ## 0.11.26
 
 ### Patch Changes

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.11.26",
+  "version": "0.11.29",
   "license": "MIT",
   "type": "module",
   "keywords": [

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

@@ -54,6 +54,7 @@ export interface VectorIndexOptions extends IndexStructOptions {
   storageContext?: StorageContext | undefined;
   vectorStores?: VectorStoreByType | undefined;
   logProgress?: boolean | undefined;
+  progressCallback?: ((progress: number, total: number) => void) | undefined;
 }
 
 export interface VectorIndexConstructorProps extends BaseIndexInit<IndexDict> {
@@ -121,6 +122,7 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
       // If nodes are passed in, then we need to update the index
       await index.buildIndexFromNodes(options.nodes, {
         logProgress: options.logProgress,
+        progressCallback: options.progressCallback,
       });
     }
     return index;
@@ -170,7 +172,12 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
    */
   async getNodeEmbeddingResults(
     nodes: BaseNode[],
-    options?: { logProgress?: boolean | undefined },
+    options?: {
+      logProgress?: boolean | undefined;
+      progressCallback?:
+        | ((progress: number, total: number) => void)
+        | undefined;
+    },
   ): Promise<BaseNode[]> {
     const nodeMap = splitNodesByType(nodes);
     for (const type in nodeMap) {
@@ -180,6 +187,7 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
       if (embedModel && nodes) {
         await embedModel(nodes, {
           logProgress: options?.logProgress,
+          progressCallback: options?.progressCallback,
         });
       }
     }
@@ -193,7 +201,12 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
    */
   async buildIndexFromNodes(
     nodes: BaseNode[],
-    options?: { logProgress?: boolean | undefined },
+    options?: {
+      logProgress?: boolean | undefined;
+      progressCallback?:
+        | ((progress: number, total: number) => void)
+        | undefined;
+    },
   ) {
     await this.insertNodes(nodes, options);
   }
@@ -361,7 +374,12 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
 
   async insertNodes(
     nodes: BaseNode[],
-    options?: { logProgress?: boolean | undefined },
+    options?: {
+      logProgress?: boolean | undefined;
+      progressCallback?:
+        | ((progress: number, total: number) => void)
+        | undefined;
+    },
   ): Promise<void> {
     if (!nodes || nodes.length === 0) {
       return;

packages/llamaindex/tests/CHANGELOG.md

@@ -1,5 +1,27 @@
 # @llamaindex/core-test
 
+## 0.1.20
+
+### Patch Changes
+
+- 8929dcf: feat: vectorStoreIndex has new option progressCallback
+- Updated dependencies [5da1cda]
+  - @llamaindex/openai@0.4.19
+
+## 0.1.19
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
+## 0.1.18
+
+### Patch Changes
+
+- @llamaindex/openai@0.4.17
+
 ## 0.1.17
 
 ### Patch Changes

packages/llamaindex/tests/indices/VectorStoreIndex.test.ts

@@ -89,4 +89,42 @@ describe("[VectorStoreIndex] use embedding model", () => {
     expect(customSpy).toHaveBeenCalled();
     expect(settingsSpy).not.toHaveBeenCalled();
   });
+
+  describe("[VectorStoreIndex] call progressCallback", () => {
+    it("should call progressCallback with correct values", async () => {
+      const documents = Array.from(
+        { length: 20 },
+        (_, i) => new Document({ text: `This is document ${i + 1}` }),
+      );
+
+      const progressCalls: Array<{ current: number; total: number }> = [];
+      const progressCallback = (current: number, total: number) => {
+        progressCalls.push({ current, total });
+      };
+
+      const embedModel = new OpenAIEmbedding();
+      mockEmbeddingModel(embedModel);
+      const embedSpy = vi.spyOn(embedModel, "getTextEmbeddingsBatch");
+
+      Settings.embedModel = embedModel;
+      const storageContext = await mockStorageContext(testDir, embedModel);
+
+      await VectorStoreIndex.fromDocuments(documents, {
+        storageContext,
+        logProgress: true,
+        progressCallback,
+      });
+
+      // Expect the embedding model to be called
+      expect(embedSpy).toHaveBeenCalled();
+
+      // Verify that progressCallback was called with correct values
+      expect(progressCalls.length).toBeGreaterThan(0);
+      expect(progressCalls[0]).toEqual({ current: 10, total: 20 });
+      expect(progressCalls[progressCalls.length - 1]).toEqual({
+        current: 20,
+        total: 20,
+      });
+    });
+  });
 });

packages/llamaindex/tests/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llamaindex-test",
   "private": true,
-  "version": "0.1.17",
+  "version": "0.1.20",
   "type": "module",
   "scripts": {
     "test": "vitest run"

packages/node-parser/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @llamaindex/node-parser
 
+## 2.0.21
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+
+## 2.0.20
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 2.0.19
 
 ### Patch Changes

packages/node-parser/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/node-parser",
-  "version": "2.0.19",
+  "version": "2.0.21",
   "description": "Node parser for LlamaIndex",
   "type": "module",
   "exports": {

packages/providers/anthropic/CHANGELOG.md

@@ -1,5 +1,20 @@
 # @llamaindex/anthropic
 
+## 0.3.24
+
+### Patch Changes
+
+- 5d5cd44: fix: anthropic temperature parameter not respecting value 0
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+
+## 0.3.23
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.3.22
 
 ### Patch Changes

packages/providers/anthropic/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/anthropic",
   "description": "Anthropic Adapter for LlamaIndex",
-  "version": "0.3.22",
+  "version": "0.3.24",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/anthropic/src/llm.ts

@@ -179,7 +179,7 @@ export class Anthropic extends ToolCallLLM<
   constructor(init?: Partial<Anthropic>) {
     super();
     this.model = init?.model ?? "claude-3-opus";
-    this.temperature = init?.temperature ?? 1; // default in anthropic is 1
+    this.temperature = init?.temperature != null ? init.temperature : 1; // default in anthropic is 1
     this.topP = init?.topP;
     this.maxTokens = init?.maxTokens ?? undefined;
 

packages/providers/assemblyai/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @llamaindex/assemblyai
 
+## 0.1.20
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+
+## 0.1.19
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.1.18
 
 ### Patch Changes

packages/providers/assemblyai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/assemblyai",
   "description": "AssemblyAI Reader for LlamaIndex",
-  "version": "0.1.18",
+  "version": "0.1.20",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/aws/CHANGELOG.md

@@ -1,5 +1,20 @@
 # @llamaindex/community
 
+## 0.0.117
+
+### Patch Changes
+
+- ed37c64: Addition of APAC_ANTHROPIC_CLAUDE_4_SONNET type/record in @llamaindex/aws for APAC support for claude 4 sonnet per issue 2184.
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+
+## 0.0.116
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.0.115
 
 ### Patch Changes

packages/providers/aws/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/aws",
   "description": "AWS package for LlamaIndexTS",
-  "version": "0.0.115",
+  "version": "0.0.117",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

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

@@ -134,13 +134,14 @@ export const INFERENCE_BEDROCK_MODELS = {
   EU_AMAZON_NOVA_PRO_1: "eu.amazon.nova-pro-v1:0",
   EU_AMAZON_NOVA_LITE_1: "eu.amazon.nova-lite-v1:0",
   EU_AMAZON_NOVA_MICRO_1: "eu.amazon.nova-micro-v1:0",
-
   APAC_ANTHROPIC_CLAUDE_3_5_SONNET:
     "apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
   APAC_ANTHROPIC_CLAUDE_3_5_SONNET_V2:
     "apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
   APAC_ANTHROPIC_CLAUDE_3_7_SONNET:
     "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
+  APAC_ANTHROPIC_CLAUDE_4_SONNET:
+    "apac.anthropic.claude-sonnet-4-20250514-v1:0q",
   APAC_ANTHROPIC_CLAUDE_3_HAIKU: "apac.anthropic.claude-3-haiku-20240307-v1:0",
   APAC_ANTHROPIC_CLAUDE_3_SONNET:
     "apac.anthropic.claude-3-sonnet-20240229-v1:0",
@@ -226,6 +227,8 @@ export const INFERENCE_TO_BEDROCK_MAP: Record<
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
   [INFERENCE_BEDROCK_MODELS.APAC_ANTHROPIC_CLAUDE_3_7_SONNET]:
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
+  [INFERENCE_BEDROCK_MODELS.APAC_ANTHROPIC_CLAUDE_4_SONNET]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_4_SONNET,
   [INFERENCE_BEDROCK_MODELS.APAC_ANTHROPIC_CLAUDE_3_HAIKU]:
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
   [INFERENCE_BEDROCK_MODELS.APAC_ANTHROPIC_CLAUDE_3_SONNET]:
@@ -546,6 +549,8 @@ export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
 
     if (params.stream) {
       const command = new InvokeModelWithResponseStreamCommand(input);
+      command.input.modelId = this.actualModel;
+
       const response = await this.client.send(command);
       if (response.body)
         return streamConverter(response.body, (response) => {
@@ -557,6 +562,8 @@ export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
     }
 
     const command = new InvokeModelCommand(input);
+    command.input.modelId = this.actualModel;
+
     const response = await this.client.send(command);
     return {
       text: this.provider.getTextFromResponse(response),

packages/providers/clip/CHANGELOG.md

@@ -1,5 +1,29 @@
 # @llamaindex/clip
 
+## 0.0.75
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+  - @llamaindex/openai@0.4.19
+
+## 0.0.74
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
+## 0.0.73
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+  - @llamaindex/openai@0.4.17
+
 ## 0.0.72
 
 ### Patch Changes

packages/providers/clip/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/clip",
   "description": "Clip Embedding Adapter for LlamaIndex",
-  "version": "0.0.72",
+  "version": "0.0.75",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/cohere/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @llamaindex/cohere
 
+## 0.0.35
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.0.33
 
 ### Patch Changes

packages/providers/cohere/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/cohere",
   "description": "Cohere Adapter for LlamaIndex",
-  "version": "0.0.33",
+  "version": "0.0.35",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/deepinfra/CHANGELOG.md

@@ -1,5 +1,29 @@
 # @llamaindex/deepinfra
 
+## 0.0.75
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+  - @llamaindex/openai@0.4.19
+
+## 0.0.74
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
+## 0.0.73
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+  - @llamaindex/openai@0.4.17
+
 ## 0.0.72
 
 ### Patch Changes

packages/providers/deepinfra/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepinfra",
   "description": "Deepinfra Adapter for LlamaIndex",
-  "version": "0.0.72",
+  "version": "0.0.75",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/deepseek/CHANGELOG.md

@@ -1,5 +1,26 @@
 # @llamaindex/deepseek
 
+## 0.0.37
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/openai@0.4.19
+
+## 0.0.36
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
+## 0.0.35
+
+### Patch Changes
+
+- @llamaindex/openai@0.4.17
+
 ## 0.0.34
 
 ### Patch Changes

packages/providers/deepseek/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepseek",
   "description": "DeepSeek Adapter for LlamaIndex",
-  "version": "0.0.34",
+  "version": "0.0.37",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/discord/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @llamaindex/discord
 
+## 0.1.20
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+
+## 0.1.19
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.1.18
 
 ### Patch Changes

packages/providers/discord/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/discord",
   "description": "Discord Reader for LlamaIndex",
-  "version": "0.1.18",
+  "version": "0.1.20",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/excel/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @llamaindex/excel
 
+## 0.1.21
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+
+## 0.1.20
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.1.19
 
 ### Patch Changes

packages/providers/excel/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/excel",
   "description": "Excel Reader for LlamaIndex",
-  "version": "0.1.19",
+  "version": "0.1.21",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/fireworks/CHANGELOG.md

@@ -1,5 +1,26 @@
 # @llamaindex/fireworks
 
+## 0.0.35
+
+### Patch Changes
+
+- Updated dependencies [5da1cda]
+  - @llamaindex/openai@0.4.19
+
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
+## 0.0.33
+
+### Patch Changes
+
+- @llamaindex/openai@0.4.17
+
 ## 0.0.32
 
 ### Patch Changes

packages/providers/fireworks/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/fireworks",
   "description": "Fireworks Adapter for LlamaIndex",
-  "version": "0.0.32",
+  "version": "0.0.35",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/google/CHANGELOG.md

@@ -1,5 +1,20 @@
 # @llamaindex/google
 
+## 0.3.21
+
+### Patch Changes
+
+- c40adaf: Add latest google models to lib
+- Updated dependencies [5da1cda]
+  - @llamaindex/core@0.6.21
+
+## 0.3.20
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.3.19
 
 ### Patch Changes

packages/providers/google/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/google",
   "description": "Google Adapter for LlamaIndex",
-  "version": "0.3.19",
+  "version": "0.3.21",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",