Release 0.11.28 (#2174)

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

apps/next/CHANGELOG.md

@@ -1,5 +1,60 @@
 # @llamaindex/doc
 
+## 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
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+
+## 0.2.50
+
+### Patch Changes
+
+- Updated dependencies [b6409b6]
+  - @llamaindex/openai@0.4.15
+
+## 0.2.49
+
+### Patch Changes
+
+- Updated dependencies [4b51791]
+  - @llamaindex/cloud@4.1.1
+  - llamaindex@0.11.26
+
+## 0.2.48
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+- Updated dependencies [049471b]
+  - @llamaindex/cloud@4.1.0
+  - llamaindex@0.11.25
+
 ## 0.2.47
 
 ### Patch Changes

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.47",
+  "version": "0.2.53",
   "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/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 +1,30 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.188
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.0.187
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.0.186
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
 ## 0.0.185
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.185",
+  "version": "0.0.189",
   "type": "module",
   "private": true,
   "scripts": {

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

@@ -1,5 +1,25 @@
 # @llamaindex/llama-parse-browser-test
 
+## 0.0.86
+
+### Patch Changes
+
+- @llamaindex/cloud@4.1.2
+
+## 0.0.85
+
+### Patch Changes
+
+- Updated dependencies [4b51791]
+  - @llamaindex/cloud@4.1.1
+
+## 0.0.84
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - @llamaindex/cloud@4.1.0
+
 ## 0.0.83
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.83",
+  "version": "0.0.86",
   "type": "module",
   "scripts": {
     "dev": "vite",

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,30 @@
 # @llamaindex/next-agent-test
 
+## 0.1.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.1.188
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.1.187
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.1.186
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
 ## 0.1.185
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.185",
+  "version": "0.1.189",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,30 @@
 # test-edge-runtime
 
+## 0.1.188
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.1.187
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.1.186
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.1.185
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
 ## 0.1.184
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.184",
+  "version": "0.1.188",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,45 @@
 # @llamaindex/next-node-runtime
 
+## 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
+
+- @llamaindex/huggingface@0.1.26
+
+## 0.1.57
+
+### Patch Changes
+
+- @llamaindex/huggingface@0.1.25
+
+## 0.1.56
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.1.55
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
 ## 0.1.54
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.54",
+  "version": "0.1.60",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,30 @@
 # vite-import-llamaindex
 
+## 0.0.55
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.54
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.0.53
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.0.52
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
 ## 0.0.51
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.51",
+  "version": "0.0.55",
   "type": "module",
   "scripts": {
     "build": "vite build",

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

@@ -1,5 +1,30 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.188
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.0.187
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.0.186
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
 ## 0.0.185
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.185",
+  "version": "0.0.189",
   "type": "module",
   "private": true,
   "scripts": {

examples/CHANGELOG.md

@@ -1,5 +1,133 @@
 # examples
 
+## 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
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+  - @llamaindex/clip@0.0.72
+  - @llamaindex/deepinfra@0.0.72
+  - @llamaindex/deepseek@0.0.34
+  - @llamaindex/fireworks@0.0.32
+  - @llamaindex/groq@0.0.88
+  - @llamaindex/huggingface@0.1.26
+  - @llamaindex/jinaai@0.0.32
+  - @llamaindex/perplexity@0.0.29
+  - @llamaindex/azure@0.1.33
+  - @llamaindex/together@0.0.32
+  - @llamaindex/vllm@0.0.58
+  - @llamaindex/xai@0.0.19
+
+## 0.3.37
+
+### Patch Changes
+
+- Updated dependencies [47a6f5f]
+- Updated dependencies [b80f33e]
+- Updated dependencies [b6409b6]
+- Updated dependencies [b80f33e]
+  - @llamaindex/ollama@0.1.20
+  - @llamaindex/anthropic@0.3.22
+  - @llamaindex/openai@0.4.15
+  - @llamaindex/clip@0.0.71
+  - @llamaindex/deepinfra@0.0.71
+  - @llamaindex/deepseek@0.0.33
+  - @llamaindex/fireworks@0.0.31
+  - @llamaindex/groq@0.0.87
+  - @llamaindex/huggingface@0.1.25
+  - @llamaindex/jinaai@0.0.31
+  - @llamaindex/perplexity@0.0.28
+  - @llamaindex/azure@0.1.32
+  - @llamaindex/together@0.0.31
+  - @llamaindex/vllm@0.0.57
+  - @llamaindex/xai@0.0.18
+
+## 0.3.36
+
+### Patch Changes
+
+- Updated dependencies [4b51791]
+- Updated dependencies [971d37c]
+  - @llamaindex/cloud@4.1.1
+  - @llamaindex/deepseek@0.0.32
+  - llamaindex@0.11.26
+
 ## 0.3.35
 
 ### Patch Changes

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/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/anthropic/opus-4.1.ts

@@ -0,0 +1,14 @@
+import { anthropic } from "@llamaindex/anthropic";
+import { agent } from "@llamaindex/workflow";
+
+(async function () {
+  const workflow = agent({
+    llm: anthropic({
+      model: "claude-4-1-opus",
+    }),
+  });
+  const result = await workflow.run(
+    "What are three compounds we should consider investigating to advance research into new antibiotics? Why should we consider them?",
+  );
+  console.log(result.data.result);
+})();

examples/models/ollama/gpt-oss.ts

@@ -0,0 +1,9 @@
+import { ollama } from "@llamaindex/ollama";
+
+(async () => {
+  const llm = ollama({
+    model: "gpt-oss:20b",
+  });
+  const response = await llm.complete({ prompt: "How are you?" });
+  console.log("Response:", response.text);
+})();

examples/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/examples",
-  "version": "0.3.35",
+  "version": "0.3.40",
   "private": true,
   "scripts": {
     "lint": "eslint .",
@@ -11,52 +11,52 @@
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@azure/search-documents": "^12.1.0",
-    "@llamaindex/anthropic": "^0.3.21",
-    "@llamaindex/assemblyai": "^0.1.18",
-    "@llamaindex/astra": "^0.0.33",
-    "@llamaindex/azure": "^0.1.31",
-    "@llamaindex/bm25-retriever": "^0.0.8",
-    "@llamaindex/chroma": "^0.0.33",
-    "@llamaindex/clip": "^0.0.70",
-    "@llamaindex/cloud": "^4.0.28",
-    "@llamaindex/cohere": "^0.0.33",
-    "@llamaindex/core": "^0.6.19",
-    "@llamaindex/deepinfra": "^0.0.70",
-    "@llamaindex/deepseek": "^0.0.31",
-    "@llamaindex/discord": "^0.1.18",
-    "@llamaindex/elastic-search": "^0.1.19",
+    "@llamaindex/anthropic": "^0.3.23",
+    "@llamaindex/assemblyai": "^0.1.19",
+    "@llamaindex/astra": "^0.0.34",
+    "@llamaindex/azure": "^0.1.35",
+    "@llamaindex/bm25-retriever": "^0.0.9",
+    "@llamaindex/chroma": "^0.0.34",
+    "@llamaindex/clip": "^0.0.74",
+    "@llamaindex/cloud": "^4.1.2",
+    "@llamaindex/cohere": "^0.0.34",
+    "@llamaindex/core": "^0.6.20",
+    "@llamaindex/deepinfra": "^0.0.74",
+    "@llamaindex/deepseek": "^0.0.36",
+    "@llamaindex/discord": "^0.1.19",
+    "@llamaindex/elastic-search": "^0.1.20",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/firestore": "^1.0.26",
-    "@llamaindex/fireworks": "^0.0.30",
-    "@llamaindex/google": "^0.3.18",
-    "@llamaindex/groq": "^0.0.86",
-    "@llamaindex/huggingface": "^0.1.24",
-    "@llamaindex/jinaai": "^0.0.30",
-    "@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": "^0.1.19",
-    "@llamaindex/openai": "^0.4.14",
-    "@llamaindex/perplexity": "^0.0.27",
-    "@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": "^0.0.30",
-    "@llamaindex/tools": "^0.1.9",
-    "@llamaindex/upstash": "^0.0.33",
-    "@llamaindex/vercel": "^0.1.19",
-    "@llamaindex/vllm": "^0.0.56",
-    "@llamaindex/voyage-ai": "^1.0.25",
-    "@llamaindex/weaviate": "^0.0.34",
-    "@llamaindex/workflow": "^1.1.20",
-    "@llamaindex/xai": "^0.0.17",
+    "@llamaindex/firestore": "^1.0.27",
+    "@llamaindex/fireworks": "^0.0.34",
+    "@llamaindex/google": "^0.3.20",
+    "@llamaindex/groq": "^0.0.90",
+    "@llamaindex/huggingface": "^0.1.28",
+    "@llamaindex/jinaai": "^0.0.34",
+    "@llamaindex/milvus": "^0.1.29",
+    "@llamaindex/mistral": "^0.1.20",
+    "@llamaindex/mixedbread": "^0.0.34",
+    "@llamaindex/mongodb": "^0.0.35",
+    "@llamaindex/node-parser": "^2.0.20",
+    "@llamaindex/notion": "^0.1.19",
+    "@llamaindex/ollama": "^0.1.21",
+    "@llamaindex/openai": "^0.4.18",
+    "@llamaindex/perplexity": "^0.0.31",
+    "@llamaindex/pinecone": "^0.1.20",
+    "@llamaindex/portkey-ai": "^0.0.62",
+    "@llamaindex/postgres": "^0.0.63",
+    "@llamaindex/qdrant": "^0.1.30",
+    "@llamaindex/readers": "^3.1.19",
+    "@llamaindex/replicate": "^0.0.62",
+    "@llamaindex/supabase": "^0.1.21",
+    "@llamaindex/together": "^0.0.34",
+    "@llamaindex/tools": "^0.1.10",
+    "@llamaindex/upstash": "^0.0.34",
+    "@llamaindex/vercel": "^0.1.20",
+    "@llamaindex/vllm": "^0.0.60",
+    "@llamaindex/voyage-ai": "^1.0.26",
+    "@llamaindex/weaviate": "^0.0.35",
+    "@llamaindex/workflow": "^1.1.22",
+    "@llamaindex/xai": "^0.0.21",
     "@notionhq/client": "^4.0.0",
     "@pinecone-database/pinecone": "^4.0.0",
     "@vercel/postgres": "^0.10.0",
@@ -65,13 +65,14 @@
     "commander": "^12.1.0",
     "dotenv": "^17.2.0",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.11.24",
+    "llamaindex": "^0.11.28",
     "mongodb": "6.7.0",
     "postgres": "^3.4.4",
     "wikipedia": "^2.1.2",
     "zod": "^3.25.76"
   },
   "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 +1,30 @@
 # @llamaindex/autotool
 
+## 8.0.28
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 8.0.27
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 8.0.26
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 8.0.25
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
 ## 8.0.24
 
 ### Patch Changes

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

@@ -1,5 +1,34 @@
 # @llamaindex/autotool-01-node-example
 
+## 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
+
+- llamaindex@0.11.26
+- @llamaindex/autotool@8.0.26
+
+## 0.0.133
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+  - @llamaindex/autotool@8.0.25
+
 ## 0.0.132
 
 ### 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": "0.0.132"
+  "version": "0.0.136"
 }

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "8.0.24",
+  "version": "8.0.28",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",

packages/cloud/CHANGELOG.md

@@ -1,5 +1,24 @@
 # @llamaindex/cloud
 
+## 4.1.2
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
+## 4.1.1
+
+### Patch Changes
+
+- 4b51791: Add deprecation to README
+
+## 4.1.0
+
+### Minor Changes
+
+- 049471b: Add deprecation warning
+
 ## 4.0.28
 
 ### Patch Changes

packages/cloud/README.md

@@ -1,8 +1,9 @@
 # @llamaindex/cloud
 
-> LlamaCloud is a new generation of managed parsing, ingestion, and retrieval services, designed to bring production-grade context-augmentation to your LLM and RAG applications.
-
-For more information, see the [API documentation](https://docs.cloud.llamaindex.ai/).
+> [!WARNING]  
+> This package has been deprecated since version 4.1.0.
+> Please migrate to [llama-cloud-services](https://www.npmjs.com/package/llama-cloud-services).
+> See the documentation: https://docs.cloud.llamaindex.ai
 
 ## License
 

packages/cloud/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloud",
-  "version": "4.0.28",
+  "version": "4.1.2",
   "type": "module",
   "license": "MIT",
   "scripts": {

packages/cloud/src/api.ts

@@ -1,3 +1,10 @@
+// Deprecation warning
+console.warn(`
+The package @llamaindex/cloud has been deprecated since version 4.1.0
+ * Please migrate to llama-cloud-services.
+ * See the documentation: https://docs.cloud.llamaindex.ai
+`);
+
 import { client } from "./client/client.gen";
 
 client.setConfig({

packages/cloud/src/beta/agent/index.ts

@@ -1,3 +1,10 @@
+// Deprecation warning
+console.warn(`
+The package @llamaindex/cloud has been deprecated since version 4.1.0
+ * Please migrate to llama-cloud-services.
+ * See the documentation: https://docs.cloud.llamaindex.ai
+`);
+
 export { AgentClient, createAgentDataClient } from "./client";
 
 export type {

packages/cloud/src/parse.ts

@@ -1,3 +1,10 @@
+// Deprecation warning
+console.warn(`
+The package @llamaindex/cloud has been deprecated since version 4.1.0
+ * Please migrate to llama-cloud-services.
+ * See the documentation: https://docs.cloud.llamaindex.ai
+`);
+
 import { createClient, createConfig } from "@hey-api/client-fetch";
 import { createWorkflow, type InferWorkflowEventData } from "@llama-flow/core";
 import { createStatefulMiddleware } from "@llama-flow/core/middleware/state";

packages/community/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/community
 
+## 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": "0.0.102",
   "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 +1,11 @@
 # @llamaindex/core
 
+## 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": "0.6.20",
   "description": "LlamaIndex Core Module",
   "exports": {
     "./agent": {

packages/core/src/llms/base.ts

@@ -1,4 +1,6 @@
 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 { callToolToMessage, getToolCallsFromResponse } from "./tool-call";
@@ -18,6 +20,7 @@ import type {
   PartialToolCall,
   ToolCallLLMMessageOptions,
 } from "./type";
+import { isZodSchema } from "./utils";
 
 export abstract class BaseLLM<
   AdditionalChatOptions extends object = object,
@@ -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 = responseFormat.safeParse(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/utils.ts

@@ -1,3 +1,4 @@
+import { z } from "zod";
 import type {
   ChatMessage,
   MessageContentImageDataDetail,
@@ -26,3 +27,15 @@ export function addContentPart<AdditionalMessageOptions extends object>(
     }
   }
 }
+
+export function isZodSchema(obj: unknown): obj is z.ZodType {
+  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" &&
+    "_def" in obj
+  );
+}

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

@@ -4,6 +4,7 @@ import { z } from "zod";
 import { zodToJsonSchema } from "zod-to-json-schema";
 import type { JSONValue } from "../global";
 import type { BaseTool, ToolMetadata } from "../llms";
+import { isZodSchema } from "../llms/utils";
 
 export class FunctionTool<
   T,
@@ -94,7 +95,7 @@ export class FunctionTool<
     ) {
       const { execute, parameters, ...restConfig } = fnOrConfig;
 
-      if (parameters instanceof z.ZodSchema) {
+      if (isZodSchema(parameters)) {
         const jsonSchema = zodToJsonSchema(parameters);
         return new FunctionTool(
           execute,
@@ -105,7 +106,6 @@ export class FunctionTool<
           parameters,
         );
       }
-
       return new FunctionTool(execute, fnOrConfig);
     }
 

packages/experimental/CHANGELOG.md

@@ -1,5 +1,30 @@
 # @llamaindex/experimental
 
+## 0.0.205
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
+## 0.0.204
+
+### Patch Changes
+
+- llamaindex@0.11.27
+
+## 0.0.203
+
+### Patch Changes
+
+- llamaindex@0.11.26
+
+## 0.0.202
+
+### Patch Changes
+
+- Updated dependencies [049471b]
+  - llamaindex@0.11.25
+
 ## 0.0.201
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.201",
+  "version": "0.0.205",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,37 @@
 # llamaindex
 
+## 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
+
+- Updated dependencies [4b51791]
+  - @llamaindex/cloud@4.1.1
+
+## 0.11.25
+
+### Patch Changes
+
+- 049471b: Moved LlamaCloudFileService, LlamaCloudIndex and LlamaCloudRetriever to llama-cloud-services
+- Updated dependencies [049471b]
+  - @llamaindex/cloud@4.1.0
+
 ## 0.11.24
 
 ### Patch Changes

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.11.24",
+  "version": "0.11.28",
   "license": "MIT",
   "type": "module",
   "keywords": [

packages/llamaindex/src/cloud/index.ts

@@ -1,3 +1,9 @@
+console.warn(`
+The classes LlamaCloudFileService, LlamaCloudIndex and LlamaCloudRetriever have been moved to the package llama-cloud-services.
+ * Please migrate your imports to llama-cloud-services, e.g. import { LlamaCloudIndex } from "llama-cloud-services";
+ * See the documentation: https://docs.cloud.llamaindex.ai
+`);
+
 export { LLamaCloudFileService } from "./LLamaCloudFileService.js";
 export { LlamaCloudIndex } from "./LlamaCloudIndex.js";
 export {

packages/llamaindex/tests/CHANGELOG.md

@@ -1,5 +1,33 @@
 # @llamaindex/core-test
 
+## 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
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+
+## 0.1.16
+
+### Patch Changes
+
+- Updated dependencies [b6409b6]
+  - @llamaindex/openai@0.4.15
+
 ## 0.1.15
 
 ### Patch Changes

packages/llamaindex/tests/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llamaindex-test",
   "private": true,
-  "version": "0.1.15",
+  "version": "0.1.19",
   "type": "module",
   "scripts": {
     "test": "vitest run"

packages/node-parser/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/node-parser
 
+## 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": "2.0.20",
   "description": "Node parser for LlamaIndex",
   "type": "module",
   "exports": {

packages/providers/anthropic/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @llamaindex/anthropic
 
+## 0.3.23
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
+## 0.3.22
+
+### Patch Changes
+
+- b80f33e: Fix: prompt caching (moved from beta)
+- b80f33e: Feat: add claude opus 4.1
+
 ## 0.3.21
 
 ### Patch Changes

packages/providers/anthropic/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/anthropic",
   "description": "Anthropic Adapter for LlamaIndex",
-  "version": "0.3.21",
+  "version": "0.3.23",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -28,19 +28,20 @@
   "scripts": {
     "build": "bunchee",
     "dev": "bunchee --watch",
-    "test": "vitest run"
+    "test": "vitest run",
+    "type-check": "tsc -b --diagnostics"
   },
   "devDependencies": {
-    "vitest": "^2.1.5",
     "@llamaindex/core": "workspace:*",
-    "@llamaindex/env": "workspace:*"
+    "@llamaindex/env": "workspace:*",
+    "vitest": "^2.1.5"
   },
   "peerDependencies": {
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*"
   },
   "dependencies": {
-    "@anthropic-ai/sdk": "0.37.0",
+    "@anthropic-ai/sdk": "0.58.0",
     "remeda": "^2.17.3"
   }
 }

packages/providers/anthropic/src/llm.ts

@@ -1,15 +1,16 @@
 import type { ClientOptions } from "@anthropic-ai/sdk";
 import { Anthropic as SDKAnthropic } from "@anthropic-ai/sdk";
 import type {
-  BetaCacheControlEphemeral,
-  BetaTextBlockParam,
-} from "@anthropic-ai/sdk/resources/beta/index";
-import type { TextBlock } from "@anthropic-ai/sdk/resources/index";
+  CacheControlEphemeral,
+  Message,
+  TextBlock,
+} from "@anthropic-ai/sdk/resources/index";
 import type {
   MessageCreateParams,
   MessageCreateParamsBase,
   MessageParam,
   Model,
+  TextBlockParam,
   ThinkingBlock,
   Tool,
   ToolUseBlock,
@@ -116,7 +117,15 @@ export const ALL_AVAILABLE_V4_MODELS = {
   "claude-4-0-sonnet": { contextWindow: 200000 },
   "claude-4-sonnet-20240514": { contextWindow: 200000 },
   "claude-4-0-opus": { contextWindow: 200000 },
+  "claude-4-1-opus": { contextWindow: 200000 },
   "claude-4-opus-20240514": { contextWindow: 200000 },
+  "claude-sonnet-4-0": { contextWindow: 200000 },
+  "claude-sonnet-4-20250514": { contextWindow: 200000 },
+  "claude-opus-4-0": { contextWindow: 200000 },
+  "claude-opus-4-20250514": { contextWindow: 200000 },
+  "claude-4-sonnet-20250514": { contextWindow: 200000 },
+  "claude-4-opus-20250514": { contextWindow: 200000 },
+  "claude-opus-4-1-20250805": { contextWindow: 200000 },
 };
 
 export const ALL_AVAILABLE_ANTHROPIC_MODELS = {
@@ -137,6 +146,7 @@ const AVAILABLE_ANTHROPIC_MODELS_WITHOUT_DATE: { [key: string]: string } = {
   "claude-3-7-sonnet": "claude-3-7-sonnet-20250219",
   "claude-4-0-sonnet": "claude-sonnet-4-20250514",
   "claude-4-0-opus": "claude-opus-4-20250514",
+  "claude-4-1-opus": "claude-opus-4-1-20250805",
 } as { [key in keyof typeof ALL_AVAILABLE_ANTHROPIC_MODELS]: string };
 
 export type AnthropicAdditionalChatOptions = Pick<
@@ -144,7 +154,7 @@ export type AnthropicAdditionalChatOptions = Pick<
   "thinking"
 >;
 export type AnthropicToolCallLLMMessageOptions = ToolCallLLMMessageOptions & {
-  cache_control?: BetaCacheControlEphemeral | null;
+  cache_control?: CacheControlEphemeral | null;
   thinking?: string | undefined;
   thinking_signature?: string | undefined;
 };
@@ -462,20 +472,20 @@ export class Anthropic extends ToolCallLLM<
     const { messages, stream, tools } = params;
 
     // Handle system messages
-    let systemPrompt: string | BetaTextBlockParam[] | null = null;
+    let systemPrompt: string | TextBlockParam[] | null = null;
     const systemMessages = messages.filter(
       (message) => message.role === "system",
     );
 
     if (systemMessages.length > 0) {
-      systemPrompt = systemMessages.map((message): BetaTextBlockParam => {
+      systemPrompt = systemMessages.map((message): TextBlockParam => {
         const textContent = extractText(message.content);
         if (message.options && "cache_control" in message.options) {
           return {
             type: "text" as const,
             text: textContent,
             cache_control: message.options
-              .cache_control as BetaCacheControlEphemeral,
+              .cache_control as CacheControlEphemeral,
           };
         }
         return {
@@ -485,17 +495,9 @@ export class Anthropic extends ToolCallLLM<
       });
     }
 
-    const beta =
-      Array.isArray(systemPrompt) &&
-      systemPrompt.some((message) => "cache_control" in message);
+    const anthropic = this.session.anthropic;
 
-    let anthropic = this.session.anthropic;
-    if (beta) {
-      // @ts-expect-error type casting
-      anthropic = anthropic.beta.promptCaching;
-    }
-
-    const apiParams: MessageCreateParams = {
+    const apiParams: MessageCreateParamsBase = {
       model: this.getModelName(this.model),
       messages: this.mergeConsecutiveMessages(
         this.formatMessages(messages.filter((m) => m.role !== "system")),
@@ -521,7 +523,7 @@ export class Anthropic extends ToolCallLLM<
       return this.streamChat(anthropic, apiParams);
     }
 
-    const response = await anthropic.messages.create(apiParams);
+    const response = (await anthropic.messages.create(apiParams)) as Message;
 
     const thinkingBlock = response.content.find(
       (content): content is ThinkingBlock => content.type === "thinking",

packages/providers/assemblyai/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/assemblyai
 
+## 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": "0.1.19",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/aws/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/community
 
+## 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": "0.0.116",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

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

@@ -546,6 +546,8 @@ 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 +559,8 @@ 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 +1,35 @@
 # @llamaindex/clip
 
+## 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
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+
+## 0.0.71
+
+### Patch Changes
+
+- Updated dependencies [b6409b6]
+  - @llamaindex/openai@0.4.15
+
 ## 0.0.70
 
 ### Patch Changes

packages/providers/clip/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/clip",
   "description": "Clip Embedding Adapter for LlamaIndex",
-  "version": "0.0.70",
+  "version": "0.0.74",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/cohere/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/cohere
 
+## 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": "0.0.34",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/deepinfra/CHANGELOG.md

@@ -1,5 +1,35 @@
 # @llamaindex/deepinfra
 
+## 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
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+
+## 0.0.71
+
+### Patch Changes
+
+- Updated dependencies [b6409b6]
+  - @llamaindex/openai@0.4.15
+
 ## 0.0.70
 
 ### Patch Changes

packages/providers/deepinfra/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepinfra",
   "description": "Deepinfra Adapter for LlamaIndex",
-  "version": "0.0.70",
+  "version": "0.0.74",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/deepseek/CHANGELOG.md

@@ -1,5 +1,39 @@
 # @llamaindex/deepseek
 
+## 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
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [b6409b6]
+  - @llamaindex/openai@0.4.15
+
+## 0.0.32
+
+### Patch Changes
+
+- 971d37c: fix: contextwindow metadata
+
 ## 0.0.31
 
 ### Patch Changes

packages/providers/deepseek/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepseek",
   "description": "DeepSeek Adapter for LlamaIndex",
-  "version": "0.0.31",
+  "version": "0.0.36",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/deepseek/src/llm.ts

@@ -4,7 +4,7 @@ import { OpenAI } from "@llamaindex/openai";
 export const DEEPSEEK_MODELS = {
   "deepseek-coder": { contextWindow: 128000 },
   "deepseek-chat": { contextWindow: 128000 },
-};
+} as const;
 
 type DeepSeekModelName = keyof typeof DEEPSEEK_MODELS;
 const DEFAULT_MODEL: DeepSeekModelName = "deepseek-coder";

packages/providers/discord/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/discord
 
+## 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": "0.1.19",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/excel/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/excel
 
+## 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": "0.1.20",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/fireworks/CHANGELOG.md

@@ -1,5 +1,33 @@
 # @llamaindex/fireworks
 
+## 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
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+
+## 0.0.31
+
+### Patch Changes
+
+- Updated dependencies [b6409b6]
+  - @llamaindex/openai@0.4.15
+
 ## 0.0.30
 
 ### Patch Changes

packages/providers/fireworks/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/fireworks",
   "description": "Fireworks Adapter for LlamaIndex",
-  "version": "0.0.30",
+  "version": "0.0.34",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/google/CHANGELOG.md

@@ -1,5 +1,18 @@
 # @llamaindex/google
 
+## 0.3.20
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
+## 0.3.19
+
+### Patch Changes
+
+- c93bb02: chore: remove streaming logs
+
 ## 0.3.18
 
 ### Patch Changes

packages/providers/google/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/google",
   "description": "Google Adapter for LlamaIndex",
-  "version": "0.3.18",
+  "version": "0.3.20",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/google/src/base.ts

@@ -226,9 +226,6 @@ export class Gemini extends ToolCallLLM<GeminiAdditionalChatOptions> {
     const config = this.prepareChatConfig(params);
     const { message, history } = await this.prepareChatContext(params.messages);
 
-    console.log("history", JSON.stringify(history, null, 2));
-    console.log("message", JSON.stringify(message, null, 2));
-
     const chat = this.client.chats.create({
       model: this.model,
       config,

packages/providers/groq/CHANGELOG.md

@@ -1,5 +1,33 @@
 # @llamaindex/groq
 
+## 0.0.90
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
+## 0.0.89
+
+### Patch Changes
+
+- @llamaindex/openai@0.4.17
+
+## 0.0.88
+
+### Patch Changes
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+
+## 0.0.87
+
+### Patch Changes
+
+- Updated dependencies [b6409b6]
+  - @llamaindex/openai@0.4.15
+
 ## 0.0.86
 
 ### Patch Changes

packages/providers/groq/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/groq",
   "description": "Groq Adapter for LlamaIndex",
-  "version": "0.0.86",
+  "version": "0.0.90",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/huggingface/CHANGELOG.md

@@ -1,5 +1,35 @@
 # @llamaindex/huggingface
 
+## 0.1.28
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
+## 0.1.27
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+  - @llamaindex/openai@0.4.17
+
+## 0.1.26
+
+### Patch Changes
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+
+## 0.1.25
+
+### Patch Changes
+
+- Updated dependencies [b6409b6]
+  - @llamaindex/openai@0.4.15
+
 ## 0.1.24
 
 ### Patch Changes

packages/providers/huggingface/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/huggingface",
   "description": "Huggingface Adapter for LlamaIndex",
-  "version": "0.1.24",
+  "version": "0.1.28",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/jinaai/CHANGELOG.md

@@ -1,5 +1,35 @@
 # @llamaindex/jinaai
 
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+  - @llamaindex/openai@0.4.17
+
+## 0.0.32
+
+### Patch Changes
+
+- Updated dependencies [4c70376]
+  - @llamaindex/openai@0.4.16
+
+## 0.0.31
+
+### Patch Changes
+
+- Updated dependencies [b6409b6]
+  - @llamaindex/openai@0.4.15
+
 ## 0.0.30
 
 ### Patch Changes

packages/providers/jinaai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/jinaai",
   "description": "JinaAI Adapter for LlamaIndex",
-  "version": "0.0.30",
+  "version": "0.0.34",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/mistral/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/mistral
 
+## 0.1.20
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.1.19
 
 ### Patch Changes

packages/providers/mistral/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/mistral",
   "description": "Mistral Adapter for LlamaIndex",
-  "version": "0.1.19",
+  "version": "0.1.20",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/mixedbread/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/mixedbread
 
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.0.33
 
 ### Patch Changes

packages/providers/mixedbread/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/mixedbread",
   "description": "Mixedbread Adapter for LlamaIndex",
-  "version": "0.0.33",
+  "version": "0.0.34",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/notion/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/notion
 
+## 0.1.19
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
 ## 0.1.18
 
 ### Patch Changes

packages/providers/notion/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/notion",
   "description": "Notion Reader for LlamaIndex",
-  "version": "0.1.18",
+  "version": "0.1.19",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/ollama/CHANGELOG.md

@@ -1,5 +1,18 @@
 # @llamaindex/ollama
 
+## 0.1.21
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
+## 0.1.20
+
+### Patch Changes
+
+- 47a6f5f: chore: bump ollama package to support gpt-oss
+
 ## 0.1.19
 
 ### Patch Changes

packages/providers/ollama/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/ollama",
   "description": "Ollama Adapter for LlamaIndex",
-  "version": "0.1.19",
+  "version": "0.1.21",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -34,7 +34,7 @@
     "@llamaindex/env": "workspace:*"
   },
   "dependencies": {
-    "ollama": "^0.5.10",
+    "ollama": "^0.5.16",
     "remeda": "^2.17.3"
   },
   "peerDependencies": {

packages/providers/openai/CHANGELOG.md

@@ -1,5 +1,31 @@
 # @llamaindex/openai
 
+## 0.4.18
+
+### Patch Changes
+
+- 001a515: chore: add minimal reasoning effort for gpt5
+- 9d7d205: fix: fix the problem that the usage field in the streaming response was not handled correctly
+
+## 0.4.17
+
+### Patch Changes
+
+- Updated dependencies [0267bb0]
+  - @llamaindex/core@0.6.20
+
+## 0.4.16
+
+### Patch Changes
+
+- 4c70376: Add gpt-5 support
+
+## 0.4.15
+
+### Patch Changes
+
+- b6409b6: chore: bump openai version
+
 ## 0.4.14
 
 ### Patch Changes

packages/providers/openai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/openai",
   "description": "OpenAI Adapter for LlamaIndex",
-  "version": "0.4.14",
+  "version": "0.4.18",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",
@@ -40,6 +40,6 @@
     "@llamaindex/env": "workspace:*"
   },
   "dependencies": {
-    "openai": "^4.102.0"
+    "openai": "^5.12.0"
   }
 }