Release 0.9.15 (#1807 )

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
fix: handle error when streaming workflow (#1808 )
2026-07-02 20:13:52 -04:00 · 2025-04-02 17:08:47 +07:00 · 2025-04-02 16:26:01 +07:00 · 2025-04-02 16:21:43 +07:00 · 2025-04-01 22:20:06 +07:00 · 2025-04-01 12:59:10 +02:00
242 changed files with 10923 additions and 516 deletions
@@ -1,7 +0,0 @@
---
-"@llamaindex/readers": patch
-"@llamaindex/core": patch
-"@llamaindex/doc": patch
---
-
-Expose more content to fix the issue with unavailable documentation links, and adjust the documentation based on the latest code.
@@ -1,5 +0,0 @@
---
-"@llamaindex/google": patch
---
-
-Added saftey setting parameter for gemini
@@ -1,5 +0,0 @@
---
-"@llamaindex/pinecone": minor
---
-
-Fix deleting of document by id in PineconeVectorStore
@@ -1,13 +0,0 @@
---
-"@llamaindex/huggingface": minor
-"@llamaindex/anthropic": minor
-"@llamaindex/mistral": minor
-"@llamaindex/google": minor
-"@llamaindex/ollama": minor
-"@llamaindex/openai": minor
-"@llamaindex/core": minor
-"@llamaindex/examples": minor
---
-
-Added support for structured output in the chat api of openai and ollama
-Added structured output parameter in the provider
@@ -1,5 +0,0 @@
---
-"@llamaindex/cloud": patch
---
-
-chore: bump sdk openapi.json
@@ -1,5 +0,0 @@
---
-"@llamaindex/azure": patch
---
-
-Add `fromConnectionString` method to azure storage libs to track the usage vCore.
@@ -1,5 +0,0 @@
---
-"@llamaindex/tools": patch
---
-
-feat: @llamaindex/tools
@@ -1,8 +0,0 @@
---
-"@llamaindex/mistral": minor
-"@llamaindex/examples": minor
---
-
-Added support for function calling in mistral provider
-Update model list for mistral provider
-Added example for the tool call in mistral
@@ -1,8 +0,0 @@
---
-"@llamaindex/cloud": patch
-"@llamaindex/community": patch
-"@llamaindex/core": patch
-"@llamaindex/readers": patch
---
-
-fix: add retry handling logic to parser reader and fix lint issues
@@ -1,5 +1,75 @@
 # @llamaindex/doc

+## 0.2.4
+
+### Patch Changes
+
+- 9c63f3f: Add support for openai responses api
+- Updated dependencies [9c63f3f]
+- Updated dependencies [c515a32]
+  - @llamaindex/openai@0.3.0
+  - @llamaindex/core@0.6.2
+  - @llamaindex/workflow@1.0.2
+  - llamaindex@0.9.15
+  - @llamaindex/cloud@4.0.2
+  - @llamaindex/node-parser@2.0.2
+  - @llamaindex/readers@3.0.2
+
+## 0.2.3
+
+### Patch Changes
+
+- 648cfb5: Add support for supabase vector store
+  Added doc for the supbase vector store
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+- Updated dependencies [9d951b2]
+  - @llamaindex/core@0.6.1
+  - llamaindex@0.9.14
+  - @llamaindex/cloud@4.0.1
+  - @llamaindex/node-parser@2.0.1
+  - @llamaindex/openai@0.2.1
+  - @llamaindex/readers@3.0.1
+  - @llamaindex/workflow@1.0.1
+
+## 0.2.2
+
+### Patch Changes
+
+- e98033e: docs: correct the number of indexes
+
+## 0.2.1
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+
+## 0.2.0
+
+### Minor Changes
+
+- f1db9b3: Adding an options parameter to vercel tool to tailor responses
+
+### Patch Changes
+
+- 21bebfc: Expose more content to fix the issue with unavailable documentation links, and adjust the documentation based on the latest code.
+- 2b39cef: Added documentation for structured output in openai and ollama
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [bf56fc0]
+- Updated dependencies [f8a86e4]
+- Updated dependencies [5189b44]
+- Updated dependencies [58a9446]
+  - @llamaindex/readers@3.0.0
+  - @llamaindex/core@0.6.0
+  - @llamaindex/openai@0.2.0
+  - @llamaindex/cloud@4.0.0
+  - @llamaindex/workflow@1.0.0
+  - llamaindex@0.9.12
+  - @llamaindex/node-parser@2.0.0
+
 ## 0.1.11

 ### Patch Changes
@@ -4,6 +4,8 @@ const withMDX = createMDX();

 /** @type {import('next').NextConfig} */
 const config = {
+  // default timeout for static generation is 60s, but we need to increase it to 10 minutes due to the large number of document pages
+  staticPageGenerationTimeout: 600,
  reactStrictMode: true,
  eslint: {
    ignoreDuringBuilds: true,
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/doc",
-  "version": "0.1.11",
+  "version": "0.2.4",
  "private": true,
  "scripts": {
    "postinstall": "fumadocs-mdx",
@@ -84,6 +84,7 @@ const queryTool = llamaindex({
  model: openai("gpt-4"),
  index,
  description: "Search through the documents",
+  options: { fields: ["sourceNodes", "messages"]}
 });

 // Use the tool with Vercel's AI SDK
@@ -2,7 +2,7 @@
 title: Index
 ---

-An index is the basic container and organization for your data. LlamaIndex.TS supports two indexes:
+An index is the basic container and organization for your data. LlamaIndex.TS supports three indexes:

 - `VectorStoreIndex` - will send the top-k `Node`s to the LLM when generating a response. The default top-k is 2.
 - `SummaryIndex` - will send every `Node` in the index to the LLM in order to generate a response
@@ -56,10 +56,10 @@ const vectorStore = new QdrantVectorStore({

 ```ts
 const document = new Document({ text: essay, id_: path });
-
-const index = await VectorStoreIndex.fromDocuments([document], {
-  vectorStore,
-});
+const storageContext = await storageContextFromDefaults({ vectorStore });
+  const index = await VectorStoreIndex.fromDocuments([document], {
+    storageContext,
+  });
 ```

 ## Query the index
@@ -91,11 +91,11 @@ async function main() {
  });

  const document = new Document({ text: essay, id_: path });
-
+  const storageContext = await storageContextFromDefaults({ vectorStore });
  const index = await VectorStoreIndex.fromDocuments([document], {
-    vectorStore,
+    storageContext,
  });
-
+  
  const queryEngine = index.asQueryEngine();

  const response = await queryEngine.query({
@@ -0,0 +1,166 @@
+---
+title: Supabase Vector Store
+---
+
+[supabase.com](https://supabase.com/)
+
+To use this vector store, you need a Supabase project. You can create one at [supabase.com](https://supabase.com/).
+
+## Installation
+
+import { Tab, Tabs } from "fumadocs-ui/components/tabs";
+
+<Tabs groupId="install" items={["npm", "yarn", "pnpm"]} persist>
+  ```shell tab="npm"
+  npm install llamaindex @llamaindex/supabase
+  ```
+
+  ```shell tab="yarn"
+  yarn add llamaindex @llamaindex/supabase
+  ```
+
+  ```shell tab="pnpm"
+  pnpm add llamaindex @llamaindex/supabase
+  ```
+</Tabs>
+
+## Database Setup
+
+Before using the vector store, you need to:
+1. Enable the `pgvector` extension
+2. Create a table for storing vectors
+3. Create a vector similarity search function
+
+```sql
+create table documents (
+id uuid primary key,
+content text,
+metadata jsonb,
+embedding vector(1536)
+);
+```
+
+-- Create a function for similarity search
+```sql
+create function match_documents (
+query_embedding vector(1536),
+match_count int
+) returns table (
+id uuid,
+content text,
+metadata jsonb,
+embedding vector(1536),
+similarity float
+)
+language plpgsql
+as $$
+begin
+return query
+select
+id,
+content,
+metadata,
+embedding,
+1 - (embedding <=> query_embedding) as similarity
+from documents
+order by embedding <=> query_embedding
+limit match_count;
+end;
+$$;
+```
+
+## Importing the modules
+
+```ts
+import { Document, VectorStoreIndex } from "llamaindex";
+import { SupabaseVectorStore } from "@llamaindex/supabase";
+```
+
+## Setup Supabase
+
+```ts
+const vectorStore = new SupabaseVectorStore({
+  supabaseUrl: process.env.SUPABASE_URL,
+  supabaseKey: process.env.SUPABASE_KEY,
+  table: "documents",
+});
+```
+
+## Setup the index
+
+```ts
+const documents = [
+  new Document({ 
+    text: "Sample document text",
+    metadata: { source: "example" }
+  })
+];
+
+const storageContext = await storageContextFromDefaults({ vectorStore });
+const index = await VectorStoreIndex.fromDocuments(documents, {
+  storageContext,
+});
+```
+
+## Query the index
+
+```ts
+const queryEngine = index.asQueryEngine();
+
+const response = await queryEngine.query({
+  query: "What is in the document?",
+});
+
+// Output response
+console.log(response.toString());
+```
+
+## Full code
+
+```ts
+import { Document, VectorStoreIndex, storageContextFromDefaults } from "llamaindex";
+import { SupabaseVectorStore } from "@llamaindex/supabase";
+
+async function main() {
+  // Initialize the vector store
+  const vectorStore = new SupabaseVectorStore({
+    supabaseUrl: process.env.SUPABASE_URL,
+    supabaseKey: process.env.SUPABASE_KEY,
+    table: "documents",
+  });
+
+  // Create sample documents
+  const documents = [
+    new Document({
+      text: "Vector search enables semantic similarity search",
+      metadata: {
+        source: "research_paper",
+        author: "Jane Smith",
+      },
+    }),
+  ];
+
+  // Create storage context
+  const storageContext = await storageContextFromDefaults({ vectorStore });
+
+  // Create and store embeddings
+  const index = await VectorStoreIndex.fromDocuments(documents, {
+    storageContext,
+  });
+
+  // Query the index
+  const queryEngine = index.asQueryEngine();
+  const response = await queryEngine.query({
+    query: "What is vector search?",
+  });
+
+  // Output response
+  console.log(response.toString());
+}
+
+main().catch(console.error);
+```
+
+## API Reference
+
+- [SupabaseVectorStore](/docs/api/classes/SupabaseVectorStore)
@@ -55,6 +55,35 @@ const results = await queryEngine.query({
 });
 ```

+## Using JSON Response Format
+
+You can configure Ollama to return responses in JSON format:
+
+```ts
+import { Ollama } from "@llamaindex/llms/ollama";
+import { z } from "zod";
+
+// Simple JSON format
+const llm = new Ollama({ 
+  model: "llama2", 
+  temperature: 0,
+  responseFormat: { type: "json_object" }
+});
+
+// Using Zod schema for validation
+const responseSchema = z.object({
+  summary: z.string(),
+  topics: z.array(z.string()),
+  sentiment: z.enum(["positive", "negative", "neutral"])
+});
+
+const llm = new Ollama({ 
+  model: "llama2", 
+  temperature: 0,
+  responseFormat: responseSchema  
+});
+```
+
 ## Full Example

 ```ts
@@ -46,6 +46,289 @@ or
 Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0, apiKey: <YOUR_API_KEY>, baseURL: "https://api.scaleway.ai/v1" });
 ```

+## Using OpenAI Responses API
+
+The OpenAI Responses API provides enhanced functionality for handling complex interactions, including built-in tools, annotations, and streaming responses. Here's how to use it:
+
+### Basic Setup
+
+```ts
+import { openaiResponses } from "@llamaindex/openai";
+
+const llm = openaiResponses({
+  model: "gpt-4o",
+  temperature: 0.1,
+  maxOutputTokens: 1000
+});
+```
+
+### Message Content Types
+
+The API supports different types of message content, including text and images:
+
+```ts
+const response = await llm.chat({
+  messages: [
+    {
+      role: "user",
+      content: [
+        {
+          type: "input_text",
+          text: "What's in this image?"
+        },
+        {
+          type: "input_image",
+          image_url: "https://example.com/image.jpg",
+          detail: "auto" // Optional: can be "auto", "low", or "high"
+        }
+      ]
+    }
+  ]
+});
+```
+
+### Advanced Features
+
+#### Built-in Tools
+
+```ts
+const llm = openaiResponses({
+  model: "gpt-4o",
+  builtInTools: [
+    {
+      type: "function",
+      name: "search_files",
+      description: "Search through available files"
+    }
+  ],
+  strict: true // Enable strict mode for tool calls
+});
+```
+
+#### Response Tracking and Storage
+
+```ts
+const llm = openaiResponses({
+  trackPreviousResponses: true, // Enable response tracking
+  store: true, // Store responses for future reference
+  user: "user-123", // Associate responses with a user
+  callMetadata: { // Add custom metadata
+    sessionId: "session-123",
+    context: "customer-support"
+  }
+});
+```
+
+#### Streaming Responses
+
+```ts
+const response = await llm.chat({
+  messages: [
+    {
+      role: "user",
+      content: "Generate a long response"
+    }
+  ],
+  stream: true // Enable streaming
+});
+
+for await (const chunk of response) {
+  console.log(chunk.delta); // Process each chunk of the response
+}
+```
+
+### Configuration Options
+
+The OpenAI Responses API supports various configuration options:
+
+```ts
+const llm = openaiResponses({
+  // Model and basic settings
+  model: "gpt-4o",
+  temperature: 0.1,
+  topP: 1,
+  maxOutputTokens: 1000,
+  
+  // API configuration
+  apiKey: "your-api-key",
+  baseURL: "custom-endpoint",
+  maxRetries: 10,
+  timeout: 60000,
+  
+  // Response handling
+  trackPreviousResponses: false,
+  store: false,
+  strict: false,
+  
+  // Additional options
+  instructions: "Custom instructions for the model",
+  truncation: "auto", // Can be "auto", "disabled", or null
+  include: ["citations", "reasoning"] // Specify what to include in responses
+});
+```
+
+### Response Structure
+
+The API returns responses with rich metadata and optional annotations:
+
+```ts
+interface ResponseStructure {
+  message: {
+    content: string;
+    role: "assistant";
+    options: {
+      built_in_tool_calls: Array<ToolCall>;
+      annotations?: Array<Citation | URLCitation | FilePath>;
+      refusal?: string;
+      reasoning?: ReasoningItem;
+      usage?: ResponseUsage;
+      toolCall?: Array<PartialToolCall>;
+    }
+  }
+}
+```
+
+### Best Practices
+
+1. Use `trackPreviousResponses` when you need conversation continuity
+2. Enable `strict` mode when using tools to ensure accurate function calls
+3. Set appropriate `maxOutputTokens` to control response length
+4. Use `annotations` to track citations and references in responses
+5. Implement error handling for potential API failures and retries
+
+## Using JSON Response Format
+
+You can configure OpenAI to return responses in JSON format:
+
+```ts
+Settings.llm = new OpenAI({ 
+  model: "gpt-4o", 
+  temperature: 0,
+  responseFormat: { type: "json_object" }  
+});
+
+// You can also use a Zod schema to validate the response structure
+import { z } from "zod";
+
+const responseSchema = z.object({
+  summary: z.string(),  
+  topics: z.array(z.string()),
+  sentiment: z.enum(["positive", "negative", "neutral"])
+});
+
+Settings.llm = new OpenAI({ 
+  model: "gpt-4o", 
+  temperature: 0,
+  responseFormat: responseSchema  
+});
+```
+
+## Response Formats
+
+The OpenAI LLM supports different response formats to structure the output in specific ways. There are two main approaches to formatting responses:
+
+### 1. JSON Object Format
+
+The simplest way to get structured JSON responses is using the `json_object` response format:
+
+```ts
+Settings.llm = new OpenAI({ 
+  model: "gpt-4o", 
+  temperature: 0,
+  responseFormat: { type: "json_object" }  
+});
+
+const response = await llm.chat({
+  messages: [
+    {
+      role: "system",
+      content: "You are a helpful assistant that outputs JSON."
+    },
+    {
+      role: "user", 
+      content: "Summarize this meeting transcript"
+    }
+  ]
+});
+
+// Response will be valid JSON
+console.log(response.message.content);
+```
+
+### 2. Schema Validation with Zod
+
+For more robust type safety and validation, you can use Zod schemas to define the expected response structure:
+
+```ts
+import { z } from "zod";
+
+// Define the response schema
+const meetingSchema = z.object({
+  summary: z.string(),
+  participants: z.array(z.string()),
+  actionItems: z.array(z.string()),
+  nextSteps: z.string()
+});
+
+// Configure the LLM with the schema
+Settings.llm = new OpenAI({ 
+  model: "gpt-4o", 
+  temperature: 0,
+  responseFormat: meetingSchema
+});
+
+const response = await llm.chat({
+  messages: [
+    {
+      role: "user",
+      content: "Summarize this meeting transcript" 
+    }
+  ]
+});
+
+// Response will be typed and validated according to the schema
+const result = response.message.content;
+console.log(result.summary);
+console.log(result.actionItems);
+```
+
+### Response Format Options
+
+The response format can be configured in two ways:
+
+1. At LLM initialization:
+```ts
+const llm = new OpenAI({
+  model: "gpt-4o",
+  responseFormat: { type: "json_object" } // or a Zod schema
+});
+```
+
+2. Per request:
+```ts
+const response = await llm.chat({
+  messages: [...],
+  responseFormat: { type: "json_object" } // or a Zod schema
+});
+```
+
+The response format options are:
+
+- `{ type: "json_object" }` - Returns responses as JSON objects
+- `zodSchema` - A Zod schema that defines and validates the response structure
+
+### Best Practices
+
+1. Use JSON object format for simple structured responses
+2. Use Zod schemas when you need:
+   - Type safety
+   - Response validation
+   - Complex nested structures
+   - Specific field constraints
+3. Set a low temperature (e.g. 0) when using structured outputs for more reliable formatting
+4. Include clear instructions in system or user messages about the expected response format
+5. Handle potential parsing errors when working with JSON responses
+
 ## Load and index documents

 For this example, we will use a single document. In a real-world scenario, you would have multiple documents to index.
@@ -7,9 +7,59 @@ A tool can be called to perform custom actions, or retrieve extra information ba
 A result from a tool call can be used by subsequent steps in a workflow, or to compute a final answer.
 For example, a "weather tool" could fetch some live weather information from a geographical location.

+## Tool Function
+
+The `tool` function is a utility provided to define a tool that can be used by an agent. It takes a function and a configuration object as arguments. The configuration object includes the tool's name, description, and parameters.
+
+### Parameters with Zod
+
+The `parameters` field in the tool configuration is defined using `zod`, a TypeScript-first schema declaration and validation library. `zod` allows you to specify the expected structure and types of the input parameters, ensuring that the data passed to the tool is valid.
+
+Example:
+```ts
+import { agent, tool } from "llamaindex";
+import { z } from "zod";
+
+// first arg is LLM input, second is bound arg
+const queryKnowledgeBase = async ({ question }, { userToken }) => {
+  const response = await fetch(`https://knowledge-base.com?token=${userToken}&query=${question}`);
+  // ...
+};
+
+// define tool with zod validation
+const kbTool = tool(queryKnowledgeBase, {
+  name: 'queryKnowledgeBase',
+  description: 'Query knowledge base',
+  parameters: z.object({
+    question: z.string({
+      description: 'The user question',
+    }),
+  }),
+});
+
+```
+In this example, `z.object` is used to define a schema for the `parameters` where `question` is expected to be a string. This ensures that any input to the tool adheres to the specified structure, providing a layer of type safety and validation.
+
+
+## Built-in tools
+
+You can import built-in tools from the `@llamaindex/tools` package.
+
+```ts
+import { agent } from "llamaindex";
+import { wiki } from "@llamaindex/tools";
+
+const researchAgent = agent({
+  name: "WikiAgent",
+  description: "Gathering information from the internet",
+  systemPrompt: `You are a research agent. Your role is to gather information from the internet using the provided tools.`,
+  tools: [wiki()],
+});
+```
+
 ## Function tool

-Function tools are implemented with the `FunctionTool` class.
+You can still use the `FunctionTool` class to define a tool.
 A `FunctionTool` is constructed from a function with signature
 ```ts
 (input: T, additionalArg?: AdditionalToolArgument) => R
@@ -1,5 +1,31 @@
 # @llamaindex/cloudflare-worker-agent-test

+## 0.0.149
+
+### Patch Changes
+
+- llamaindex@0.9.15
+
+## 0.0.148
+
+### Patch Changes
+
+- Updated dependencies [9d951b2]
+  - llamaindex@0.9.14
+
+## 0.0.147
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+
+## 0.0.146
+
+### Patch Changes
+
+- llamaindex@0.9.12
+
 ## 0.0.145

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.145",
+  "version": "0.0.149",
  "type": "module",
  "private": true,
  "scripts": {
@@ -1,5 +1,25 @@
 # @llamaindex/llama-parse-browser-test

+## 0.0.57
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.2
+
+## 0.0.56
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.1
+
+## 0.0.55
+
+### Patch Changes
+
+- Updated dependencies [bf56fc0]
+- Updated dependencies [5189b44]
+  - @llamaindex/cloud@4.0.0
+
 ## 0.0.54

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/llama-parse-browser-test",
  "private": true,
-  "version": "0.0.54",
+  "version": "0.0.57",
  "type": "module",
  "scripts": {
    "dev": "vite",
@@ -10,7 +10,7 @@
  },
  "devDependencies": {
    "typescript": "^5.7.3",
-    "vite": "^5.4.12",
+    "vite": "^5.4.16",
    "vite-plugin-wasm": "^3.3.0"
  },
  "dependencies": {
@@ -1,5 +1,31 @@
 # @llamaindex/next-agent-test

+## 0.1.149
+
+### Patch Changes
+
+- llamaindex@0.9.15
+
+## 0.1.148
+
+### Patch Changes
+
+- Updated dependencies [9d951b2]
+  - llamaindex@0.9.14
+
+## 0.1.147
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+
+## 0.1.146
+
+### Patch Changes
+
+- llamaindex@0.9.12
+
 ## 0.1.145

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/next-agent-test",
-  "version": "0.1.145",
+  "version": "0.1.149",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -1,5 +1,31 @@
 # test-edge-runtime

+## 0.1.148
+
+### Patch Changes
+
+- llamaindex@0.9.15
+
+## 0.1.147
+
+### Patch Changes
+
+- Updated dependencies [9d951b2]
+  - llamaindex@0.9.14
+
+## 0.1.146
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+
+## 0.1.145
+
+### Patch Changes
+
+- llamaindex@0.9.12
+
 ## 0.1.144

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.144",
+  "version": "0.1.148",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -1,5 +1,40 @@
 # @llamaindex/next-node-runtime

+## 0.1.15
+
+### Patch Changes
+
+- llamaindex@0.9.15
+- @llamaindex/huggingface@0.1.2
+- @llamaindex/readers@3.0.2
+
+## 0.1.14
+
+### Patch Changes
+
+- Updated dependencies [9d951b2]
+  - llamaindex@0.9.14
+  - @llamaindex/huggingface@0.1.1
+  - @llamaindex/readers@3.0.1
+
+## 0.1.13
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+
+## 0.1.12
+
+### Patch Changes
+
+- Updated dependencies [21bebfc]
+- Updated dependencies [91a18e7]
+- Updated dependencies [5189b44]
+  - @llamaindex/readers@3.0.0
+  - @llamaindex/huggingface@0.1.0
+  - llamaindex@0.9.12
+
 ## 0.1.11

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.11",
+  "version": "0.1.15",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -1,5 +1,31 @@
 # vite-import-llamaindex

+## 0.0.15
+
+### Patch Changes
+
+- llamaindex@0.9.15
+
+## 0.0.14
+
+### Patch Changes
+
+- Updated dependencies [9d951b2]
+  - llamaindex@0.9.14
+
+## 0.0.13
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+
+## 0.0.12
+
+### Patch Changes
+
+- llamaindex@0.9.12
+
 ## 0.0.11

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "vite-import-llamaindex",
  "private": true,
-  "version": "0.0.11",
+  "version": "0.0.15",
  "type": "module",
  "scripts": {
    "build": "vite build",
@@ -16,7 +16,7 @@
    "@size-limit/preset-big-lib": "^11.1.6",
    "size-limit": "^11.1.6",
    "typescript": "^5.7.3",
-    "vite": "^6.1.0"
+    "vite": "^5.4.16"
  },
  "dependencies": {
    "llamaindex": "workspace:*"
@@ -1,5 +1,31 @@
 # @llamaindex/waku-query-engine-test

+## 0.0.149
+
+### Patch Changes
+
+- llamaindex@0.9.15
+
+## 0.0.148
+
+### Patch Changes
+
+- Updated dependencies [9d951b2]
+  - llamaindex@0.9.14
+
+## 0.0.147
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+
+## 0.0.146
+
+### Patch Changes
+
+- llamaindex@0.9.12
+
 ## 0.0.145

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.145",
+  "version": "0.0.149",
  "type": "module",
  "private": true,
  "scripts": {
@@ -0,0 +1 @@
+20
@@ -1,5 +1,178 @@
 # examples

+## 0.3.2
+
+### Patch Changes
+
+- 9c63f3f: Add support for openai responses api
+- Updated dependencies [9c63f3f]
+- Updated dependencies [c515a32]
+  - @llamaindex/openai@0.3.0
+  - @llamaindex/google@0.2.2
+  - @llamaindex/core@0.6.2
+  - @llamaindex/workflow@1.0.2
+  - llamaindex@0.9.15
+  - @llamaindex/clip@0.0.48
+  - @llamaindex/deepinfra@0.0.48
+  - @llamaindex/deepseek@0.0.8
+  - @llamaindex/fireworks@0.0.8
+  - @llamaindex/groq@0.0.63
+  - @llamaindex/huggingface@0.1.2
+  - @llamaindex/jinaai@0.0.8
+  - @llamaindex/perplexity@0.0.5
+  - @llamaindex/azure@0.1.11
+  - @llamaindex/elastic-search@0.1.2
+  - @llamaindex/milvus@0.1.11
+  - @llamaindex/qdrant@0.1.11
+  - @llamaindex/supabase@0.1.1
+  - @llamaindex/together@0.0.8
+  - @llamaindex/vllm@0.0.34
+  - @llamaindex/cloud@4.0.2
+  - @llamaindex/node-parser@2.0.2
+  - @llamaindex/anthropic@0.3.2
+  - @llamaindex/cohere@0.0.16
+  - @llamaindex/mistral@0.1.2
+  - @llamaindex/mixedbread@0.0.16
+  - @llamaindex/ollama@0.1.2
+  - @llamaindex/portkey-ai@0.0.44
+  - @llamaindex/replicate@0.0.44
+  - @llamaindex/astra@0.0.16
+  - @llamaindex/chroma@0.0.16
+  - @llamaindex/firestore@1.0.9
+  - @llamaindex/mongodb@0.0.16
+  - @llamaindex/pinecone@0.1.2
+  - @llamaindex/postgres@0.0.44
+  - @llamaindex/upstash@0.0.16
+  - @llamaindex/weaviate@0.0.16
+  - @llamaindex/vercel@0.1.2
+  - @llamaindex/voyage-ai@1.0.8
+  - @llamaindex/readers@3.0.2
+  - @llamaindex/tools@0.0.4
+
+## 0.3.1
+
+### Patch Changes
+
+- 648cfb5: Add support for supabase vector store
+  Added doc for the supbase vector store
+- Updated dependencies [648cfb5]
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+- Updated dependencies [9d951b2]
+  - @llamaindex/supabase@0.1.0
+  - @llamaindex/core@0.6.1
+  - llamaindex@0.9.14
+  - @llamaindex/tools@0.0.3
+  - @llamaindex/cloud@4.0.1
+  - @llamaindex/node-parser@2.0.1
+  - @llamaindex/anthropic@0.3.1
+  - @llamaindex/clip@0.0.47
+  - @llamaindex/cohere@0.0.15
+  - @llamaindex/deepinfra@0.0.47
+  - @llamaindex/google@0.2.1
+  - @llamaindex/huggingface@0.1.1
+  - @llamaindex/jinaai@0.0.7
+  - @llamaindex/mistral@0.1.1
+  - @llamaindex/mixedbread@0.0.15
+  - @llamaindex/ollama@0.1.1
+  - @llamaindex/openai@0.2.1
+  - @llamaindex/perplexity@0.0.4
+  - @llamaindex/portkey-ai@0.0.43
+  - @llamaindex/replicate@0.0.43
+  - @llamaindex/astra@0.0.15
+  - @llamaindex/azure@0.1.10
+  - @llamaindex/chroma@0.0.15
+  - @llamaindex/elastic-search@0.1.1
+  - @llamaindex/firestore@1.0.8
+  - @llamaindex/milvus@0.1.10
+  - @llamaindex/mongodb@0.0.15
+  - @llamaindex/pinecone@0.1.1
+  - @llamaindex/postgres@0.0.43
+  - @llamaindex/qdrant@0.1.10
+  - @llamaindex/upstash@0.0.15
+  - @llamaindex/weaviate@0.0.15
+  - @llamaindex/vercel@0.1.1
+  - @llamaindex/voyage-ai@1.0.7
+  - @llamaindex/readers@3.0.1
+  - @llamaindex/workflow@1.0.1
+  - @llamaindex/deepseek@0.0.7
+  - @llamaindex/fireworks@0.0.7
+  - @llamaindex/groq@0.0.62
+  - @llamaindex/together@0.0.7
+  - @llamaindex/vllm@0.0.33
+
+## 0.3.0
+
+### Minor Changes
+
+- 91a18e7: Added support for structured output in the chat api of openai and ollama
+  Added structured output parameter in the provider
+- d1c1f99: Added support for function calling in mistral provider
+  Update model list for mistral provider
+  Added example for the tool call in mistral
+
+### Patch Changes
+
+- 2509353: Added support for elastic search vector store
+- Updated dependencies [21bebfc]
+- Updated dependencies [77e24ce]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [2509353]
+- Updated dependencies [da06e45]
+- Updated dependencies [2a0a899]
+- Updated dependencies [050cd53]
+- Updated dependencies [91a18e7]
+- Updated dependencies [bf56fc0]
+- Updated dependencies [f1db9b3]
+- Updated dependencies [da8068e]
+- Updated dependencies [c7ff323]
+- Updated dependencies [f8a86e4]
+- Updated dependencies [d1c1f99]
+- Updated dependencies [5189b44]
+- Updated dependencies [3fd4cc3]
+- Updated dependencies [04f8c96]
+- Updated dependencies [58a9446]
+  - @llamaindex/readers@3.0.0
+  - @llamaindex/core@0.6.0
+  - @llamaindex/tools@0.0.2
+  - @llamaindex/elastic-search@0.1.0
+  - @llamaindex/google@0.2.0
+  - @llamaindex/pinecone@0.1.0
+  - @llamaindex/huggingface@0.1.0
+  - @llamaindex/anthropic@0.3.0
+  - @llamaindex/mistral@0.1.0
+  - @llamaindex/ollama@0.1.0
+  - @llamaindex/openai@0.2.0
+  - @llamaindex/cloud@4.0.0
+  - @llamaindex/vercel@0.1.0
+  - @llamaindex/azure@0.1.9
+  - @llamaindex/workflow@1.0.0
+  - @llamaindex/mongodb@0.0.14
+  - llamaindex@0.9.12
+  - @llamaindex/node-parser@2.0.0
+  - @llamaindex/clip@0.0.46
+  - @llamaindex/cohere@0.0.14
+  - @llamaindex/deepinfra@0.0.46
+  - @llamaindex/jinaai@0.0.6
+  - @llamaindex/mixedbread@0.0.14
+  - @llamaindex/perplexity@0.0.3
+  - @llamaindex/portkey-ai@0.0.42
+  - @llamaindex/replicate@0.0.42
+  - @llamaindex/astra@0.0.14
+  - @llamaindex/chroma@0.0.14
+  - @llamaindex/firestore@1.0.7
+  - @llamaindex/milvus@0.1.9
+  - @llamaindex/postgres@0.0.42
+  - @llamaindex/qdrant@0.1.9
+  - @llamaindex/upstash@0.0.14
+  - @llamaindex/weaviate@0.0.14
+  - @llamaindex/voyage-ai@1.0.6
+  - @llamaindex/deepseek@0.0.6
+  - @llamaindex/fireworks@0.0.6
+  - @llamaindex/groq@0.0.61
+  - @llamaindex/together@0.0.6
+  - @llamaindex/vllm@0.0.32
+
 ## 0.2.10

 ### Patch Changes
@@ -0,0 +1,51 @@
+import {
+  AgentStream,
+  AgentToolCallResult,
+  Document,
+  VectorStoreIndex,
+  agent,
+  openai,
+} from "llamaindex";
+
+async function main() {
+  const index = await VectorStoreIndex.fromDocuments([
+    new Document({
+      text: "Cats have a specialized collarbone that allows them to always land on their feet when they fall.",
+    }),
+    new Document({
+      text: "Dogs have a sense of smell that is 10,000 to 100,000 times more acute than humans.",
+    }),
+    new Document({
+      text: "Cats are known for their agility and ability to jump high.",
+    }),
+  ]);
+
+  const myAgent = agent({
+    llm: openai({ model: "gpt-4o" }),
+    tools: [
+      index.queryTool({
+        options: { similarityTopK: 2 },
+        includeSourceNodes: true,
+      }),
+    ],
+  });
+
+  const context = myAgent.run("The fact about cats");
+
+  for await (const event of context) {
+    if (event instanceof AgentToolCallResult) {
+      console.log(
+        "Using these retrieved information to answer the question:\n",
+        event.data.toolOutput.result,
+      );
+    } else if (event instanceof AgentStream) {
+      for (const chunk of event.data.delta) {
+        process.stdout.write(chunk);
+      }
+    }
+  }
+}
+
+void main().then(() => {
+  console.log("Done");
+});
@@ -0,0 +1,30 @@
+import { openaiResponses } from "@llamaindex/openai";
+import { wiki } from "@llamaindex/tools";
+import { agent, tool } from "llamaindex";
+import { z } from "zod";
+
+const workflow = agent({
+  tools: [
+    tool({
+      name: "weather",
+      description: "Get the weather",
+      parameters: z.object({
+        location: z.string().describe("The location to get the weather for"),
+      }),
+      execute: ({ location }) => `The weather in ${location} is sunny`,
+    }),
+    wiki(),
+  ],
+  llm: openaiResponses({
+    model: "gpt-4o-mini",
+  }),
+});
+
+async function main() {
+  const result = await workflow.run(
+    "What is the weather in New York? What's the history of New York from Wikipedia in 3 sentences?",
+  );
+  console.log(result.data);
+}
+
+void main();
@@ -0,0 +1,33 @@
+import { openaiResponses } from "@llamaindex/openai";
+
+async function main() {
+  const llm = openaiResponses({
+    model: "gpt-4o",
+    maxOutputTokens: 1000,
+    apiKey: process.env.MY_OPENAI_API_KEY,
+  });
+
+  const response = await llm.chat({
+    messages: [
+      {
+        role: "user",
+        content: [
+          {
+            type: "text",
+            text: "What's in this image? Describe it in detail.",
+          },
+          {
+            type: "image_url",
+            image_url: {
+              url: "https://storage.googleapis.com/cloud-samples-data/vision/face/faces.jpeg",
+            },
+          },
+        ],
+      },
+    ],
+  });
+
+  console.log("Single Image Analysis:", response.message.content);
+}
+
+main().catch(console.error);
@@ -0,0 +1,22 @@
+import { openaiResponses } from "@llamaindex/openai";
+
+async function main() {
+  const llm = openaiResponses({
+    model: "gpt-4o-mini",
+    temperature: 0.1,
+  });
+
+  // Basic chat example
+  const response = await llm.chat({
+    messages: [
+      {
+        role: "user",
+        content: "What is the capital of France?",
+      },
+    ],
+  });
+
+  console.log(response.message.content);
+}
+
+main().catch(console.error);
@@ -0,0 +1,26 @@
+import { openaiResponses } from "@llamaindex/openai";
+
+async function main() {
+  const llm = openaiResponses({
+    model: "gpt-4o-mini",
+    temperature: 0.1,
+  });
+
+  const stream = await llm.chat({
+    messages: [
+      { content: "You want to talk in rhymes.", role: "system" },
+      {
+        content:
+          "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
+        role: "user",
+      },
+    ],
+    stream: true,
+  });
+
+  for await (const chunk of stream) {
+    process.stdout.write(chunk.delta);
+  }
+}
+
+main().catch(console.error);
@@ -0,0 +1,37 @@
+import { openaiResponses } from "@llamaindex/openai";
+import { tool } from "llamaindex";
+
+import { z } from "zod";
+async function main() {
+  const weatherTool = tool({
+    name: "weather",
+    description: "Get the weather",
+    parameters: z.object({
+      location: z.string({
+        description: "The location to get the weather for",
+      }),
+    }),
+    execute: ({ location }) => {
+      return `The weather in ${location} is sunny`;
+    },
+  });
+
+  const llm = openaiResponses({
+    model: "gpt-4o-mini",
+    temperature: 0.1,
+  });
+
+  const response = await llm.chat({
+    messages: [
+      {
+        role: "user",
+        content: "What is the weather in New York?",
+      },
+    ],
+    tools: [weatherTool],
+  });
+
+  console.log(response.message.options);
+}
+
+main().catch(console.error);
@@ -0,0 +1,23 @@
+import { openaiResponses } from "@llamaindex/openai";
+
+async function main() {
+  const llm = openaiResponses({
+    model: "gpt-4o",
+    temperature: 0.1,
+    builtInTools: [{ type: "web_search_preview" }],
+  });
+
+  // Streaming chat example
+  const response = await llm.chat({
+    messages: [
+      {
+        role: "user",
+        content: "What are the latest developments in AI?",
+      },
+    ],
+  });
+
+  console.log(response.message.content);
+}
+
+main().catch(console.error);
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/examples",
-  "version": "0.2.10",
+  "version": "0.3.2",
  "private": true,
  "scripts": {
    "lint": "eslint .",
@@ -11,45 +11,47 @@
    "@azure/cosmos": "^4.1.1",
    "@azure/identity": "^4.4.1",
    "@azure/search-documents": "^12.1.0",
-    "@llamaindex/anthropic": "^0.2.6",
-    "@llamaindex/astra": "^0.0.13",
-    "@llamaindex/azure": "^0.1.8",
-    "@llamaindex/chroma": "^0.0.13",
-    "@llamaindex/clip": "^0.0.45",
-    "@llamaindex/cloud": "^3.0.9",
-    "@llamaindex/cohere": "^0.0.13",
-    "@llamaindex/core": "^0.5.8",
-    "@llamaindex/deepinfra": "^0.0.45",
+    "@llamaindex/anthropic": "^0.3.2",
+    "@llamaindex/astra": "^0.0.16",
+    "@llamaindex/azure": "^0.1.11",
+    "@llamaindex/chroma": "^0.0.16",
+    "@llamaindex/clip": "^0.0.48",
+    "@llamaindex/cloud": "^4.0.2",
+    "@llamaindex/cohere": "^0.0.16",
+    "@llamaindex/core": "^0.6.2",
+    "@llamaindex/deepinfra": "^0.0.48",
    "@llamaindex/env": "^0.1.29",
-    "@llamaindex/firestore": "^1.0.6",
-    "@llamaindex/google": "^0.1.2",
-    "@llamaindex/groq": "^0.0.60",
-    "@llamaindex/huggingface": "^0.0.45",
-    "@llamaindex/milvus": "^0.1.8",
-    "@llamaindex/mistral": "^0.0.14",
-    "@llamaindex/mixedbread": "^0.0.13",
-    "@llamaindex/mongodb": "^0.0.13",
-    "@llamaindex/node-parser": "^1.0.8",
-    "@llamaindex/ollama": "^0.0.48",
-    "@llamaindex/openai": "^0.1.61",
-    "@llamaindex/pinecone": "^0.0.13",
-    "@llamaindex/portkey-ai": "^0.0.41",
-    "@llamaindex/postgres": "^0.0.41",
-    "@llamaindex/qdrant": "^0.1.8",
-    "@llamaindex/readers": "^2.0.8",
-    "@llamaindex/replicate": "^0.0.41",
-    "@llamaindex/upstash": "^0.0.13",
-    "@llamaindex/vercel": "^0.0.19",
-    "@llamaindex/vllm": "^0.0.31",
-    "@llamaindex/voyage-ai": "^1.0.5",
-    "@llamaindex/weaviate": "^0.0.13",
-    "@llamaindex/workflow": "^0.0.16",
-    "@llamaindex/deepseek": "^0.0.5",
-    "@llamaindex/fireworks": "^0.0.5",
-    "@llamaindex/together": "^0.0.5",
-    "@llamaindex/jinaai": "^0.0.5",
-    "@llamaindex/perplexity": "^0.0.2",
-    "@llamaindex/tools": "^0.0.1",
+    "@llamaindex/firestore": "^1.0.9",
+    "@llamaindex/google": "^0.2.2",
+    "@llamaindex/groq": "^0.0.63",
+    "@llamaindex/huggingface": "^0.1.2",
+    "@llamaindex/milvus": "^0.1.11",
+    "@llamaindex/mistral": "^0.1.2",
+    "@llamaindex/mixedbread": "^0.0.16",
+    "@llamaindex/mongodb": "^0.0.16",
+    "@llamaindex/elastic-search": "^0.1.2",
+    "@llamaindex/node-parser": "^2.0.2",
+    "@llamaindex/ollama": "^0.1.2",
+    "@llamaindex/openai": "^0.3.0",
+    "@llamaindex/pinecone": "^0.1.2",
+    "@llamaindex/portkey-ai": "^0.0.44",
+    "@llamaindex/postgres": "^0.0.44",
+    "@llamaindex/qdrant": "^0.1.11",
+    "@llamaindex/readers": "^3.0.2",
+    "@llamaindex/replicate": "^0.0.44",
+    "@llamaindex/upstash": "^0.0.16",
+    "@llamaindex/vercel": "^0.1.2",
+    "@llamaindex/vllm": "^0.0.34",
+    "@llamaindex/voyage-ai": "^1.0.8",
+    "@llamaindex/weaviate": "^0.0.16",
+    "@llamaindex/workflow": "^1.0.2",
+    "@llamaindex/deepseek": "^0.0.8",
+    "@llamaindex/fireworks": "^0.0.8",
+    "@llamaindex/together": "^0.0.8",
+    "@llamaindex/jinaai": "^0.0.8",
+    "@llamaindex/perplexity": "^0.0.5",
+    "@llamaindex/supabase": "^0.1.1",
+    "@llamaindex/tools": "^0.0.4",
    "@notionhq/client": "^2.2.15",
    "@pinecone-database/pinecone": "^4.0.0",
    "@vercel/postgres": "^0.10.0",
@@ -58,7 +60,7 @@
    "commander": "^12.1.0",
    "dotenv": "^16.4.5",
    "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.9.11",
+    "llamaindex": "^0.9.15",
    "mongodb": "6.7.0",
    "postgres": "^3.4.4",
    "wikipedia": "^2.1.2",
@@ -0,0 +1,73 @@
+import { ElasticSearchVectorStore } from "@llamaindex/elastic-search";
+import {
+  gemini,
+  GEMINI_EMBEDDING_MODEL,
+  GEMINI_MODEL,
+  GeminiEmbedding,
+} from "@llamaindex/google";
+import {
+  Document,
+  Settings,
+  storageContextFromDefaults,
+  VectorStoreIndex,
+} from "llamaindex";
+async function main() {
+  Settings.embedModel = new GeminiEmbedding({
+    model: GEMINI_EMBEDDING_MODEL.TEXT_EMBEDDING_004,
+  });
+  Settings.llm = gemini({
+    model: GEMINI_MODEL.GEMINI_PRO_1_5_FLASH,
+  });
+  // Create sample documents
+  const documents = [
+    new Document({
+      text: "Elastic search is a powerful search engine",
+      metadata: {
+        source: "tech_docs",
+        author: "John Doe",
+      },
+    }),
+    new Document({
+      text: "Vector search enables semantic similarity search",
+      metadata: {
+        source: "research_paper",
+        author: "Jane Smith",
+      },
+    }),
+    new Document({
+      text: "Elasticsearch supports various distance metrics for vector search",
+      metadata: {
+        source: "tech_docs",
+        author: "Bob Wilson",
+      },
+    }),
+  ];
+
+  // Initialize ElasticSearch Vector Store
+  const vectorStore = new ElasticSearchVectorStore({
+    indexName: "llamaindex-demo",
+    esCloudId: process.env.ES_CLOUD_ID,
+    esApiKey: process.env.ES_API_KEY,
+  });
+
+  // Create storage context with the vector store
+  const storageContext = await storageContextFromDefaults({
+    vectorStore,
+  });
+
+  // Create and store embeddings in ElasticSearch
+  const index = await VectorStoreIndex.fromDocuments(documents, {
+    storageContext,
+  });
+
+  // Query the index
+  const queryEngine = index.asQueryEngine();
+
+  // Simple query
+  const response = await queryEngine.query({
+    query: "What is vector search?",
+  });
+  console.log("Basic Query Response:", response.toString());
+}
+
+main().catch(console.error);
@@ -0,0 +1,8 @@
+{
+  "name": "elastic-search-vector-store",
+  "type": "module",
+  "private": true,
+  "scripts": {
+    "start": "npx tsx index.ts"
+  }
+}
@@ -0,0 +1,75 @@
+import {
+  gemini,
+  GEMINI_EMBEDDING_MODEL,
+  GEMINI_MODEL,
+  GeminiEmbedding,
+} from "@llamaindex/google";
+import { SupabaseVectorStore } from "@llamaindex/supabase";
+import {
+  Document,
+  Settings,
+  storageContextFromDefaults,
+  VectorStoreIndex,
+} from "llamaindex";
+async function main() {
+  Settings.embedModel = new GeminiEmbedding({
+    model: GEMINI_EMBEDDING_MODEL.TEXT_EMBEDDING_004,
+  });
+  Settings.llm = gemini({
+    model: GEMINI_MODEL.GEMINI_PRO_1_5_FLASH,
+  });
+  // Create sample documents
+  const documents = [
+    new Document({
+      text: "Supbase is a powerful Database engine",
+      metadata: {
+        source: "tech_docs",
+        author: "John Doe",
+      },
+    }),
+    new Document({
+      text: "Vector search enables semantic similarity search",
+      metadata: {
+        source: "research_paper",
+        author: "Jane Smith",
+      },
+    }),
+    new Document({
+      text: "Supbase vector store supports various distance metrics for vector search",
+      metadata: {
+        source: "tech_docs",
+        author: "Bob Wilson",
+      },
+    }),
+  ];
+
+  // Initialize ElasticSearch Vector Store
+  const vectorStore = new SupabaseVectorStore({
+    supabaseUrl: process.env.SUPABASE_URL,
+    supabaseKey: process.env.SUPABASE_KEY,
+    table: "document",
+  });
+
+  // await vectorStore.delete("fc079c38-2af4-4782-96e4-955c28608fcf");
+
+  // Create storage context with the vector store
+  const storageContext = await storageContextFromDefaults({
+    vectorStore,
+  });
+
+  // Create and store embeddings in ElasticSearch
+  const index = await VectorStoreIndex.fromDocuments(documents, {
+    storageContext,
+  });
+
+  // Query the index
+  const queryEngine = index.asQueryEngine();
+
+  // Simple query
+  const response = await queryEngine.query({
+    query: "What is vector search?",
+  });
+  console.log("Basic Query Response:", response.toString());
+}
+
+main().catch(console.error);
@@ -0,0 +1,8 @@
+{
+  "name": "vector-store-supabase",
+  "type": "module",
+  "private": true,
+  "scripts": {
+    "start": "npx tsx index.ts"
+  }
+}
@@ -35,7 +35,8 @@
    "prettier-plugin-tailwindcss": "^0.6.11",
    "turbo": "^2.4.4",
    "typescript": "^5.7.3",
-    "typescript-eslint": "^8.18.0"
+    "typescript-eslint": "^8.18.0",
+    "vitest": "^3.1.1"
  },
  "packageManager": "pnpm@9.12.3",
  "lint-staged": {
@@ -1,5 +1,31 @@
 # @llamaindex/autotool

+## 6.0.15
+
+### Patch Changes
+
+- llamaindex@0.9.15
+
+## 6.0.14
+
+### Patch Changes
+
+- Updated dependencies [9d951b2]
+  - llamaindex@0.9.14
+
+## 6.0.13
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+
+## 6.0.12
+
+### Patch Changes
+
+- llamaindex@0.9.12
+
 ## 6.0.11

 ### Patch Changes
@@ -1,5 +1,35 @@
 # @llamaindex/autotool-01-node-example

+## 0.0.96
+
+### Patch Changes
+
+- llamaindex@0.9.15
+- @llamaindex/autotool@6.0.15
+
+## 0.0.95
+
+### Patch Changes
+
+- Updated dependencies [9d951b2]
+  - llamaindex@0.9.14
+  - @llamaindex/autotool@6.0.14
+
+## 0.0.94
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+  - @llamaindex/autotool@6.0.13
+
+## 0.0.93
+
+### Patch Changes
+
+- llamaindex@0.9.12
+- @llamaindex/autotool@6.0.12
+
 ## 0.0.92

 ### Patch Changes
@@ -13,5 +13,5 @@
  "scripts": {
    "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
  },
-  "version": "0.0.92"
+  "version": "0.0.96"
 }
@@ -6,7 +6,7 @@
    "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
    "directory": "packages/autotool"
  },
-  "version": "6.0.11",
+  "version": "6.0.15",
  "description": "auto transpile your JS function to LLM Agent compatible",
  "files": [
    "dist",
@@ -1,5 +1,32 @@
 # @llamaindex/cloud

+## 4.0.2
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+  - @llamaindex/core@0.6.2
+
+## 4.0.1
+
+### Patch Changes
+
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+  - @llamaindex/core@0.6.1
+
+## 4.0.0
+
+### Patch Changes
+
+- bf56fc0: chore: bump sdk openapi.json
+- 5189b44: fix: add retry handling logic to parser reader and fix lint issues
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [5189b44]
+  - @llamaindex/core@0.6.0
+
 ## 3.0.9

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/cloud",
-  "version": "3.0.9",
+  "version": "4.0.2",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -1,5 +1,38 @@
 # @llamaindex/community

+## 0.0.94
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+  - @llamaindex/core@0.6.2
+
+## 0.0.93
+
+### Patch Changes
+
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+  - @llamaindex/core@0.6.1
+
+## 0.0.92
+
+### Patch Changes
+
+- 1325178: fix: stringify all tool results for anthropic on bedrock
+
+## 0.0.91
+
+### Patch Changes
+
+- 5189b44: fix: add retry handling logic to parser reader and fix lint issues
+- 3fd4cc3: feat: use google's new gen ai library to support multimodal output
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [5189b44]
+  - @llamaindex/core@0.6.0
+
 ## 0.0.90

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/community",
  "description": "Community package for LlamaIndexTS",
-  "version": "0.0.90",
+  "version": "0.0.94",
  "type": "module",
  "types": "dist/type/index.d.ts",
  "main": "dist/cjs/index.js",
@@ -10,12 +10,10 @@ import type {
  MessageContentDetail,
  ToolCallLLMMessageOptions,
 } from "@llamaindex/core/llms";
-import {
-  extractDataUrlComponents,
-  mapMessageContentToMessageContentDetails,
-} from "../utils";
+import { extractDataUrlComponents } from "../utils";

 import type { JSONObject } from "@llamaindex/core/global";
+import { mapMessageContentToMessageContentDetails } from "../../utils";
 import type { AmazonMessage, AmazonMessages } from "./types";

 const ACCEPTED_IMAGE_MIME_TYPES = [
@@ -6,10 +6,8 @@ import type {
  MessageContentDetail,
  ToolCallLLMMessageOptions,
 } from "@llamaindex/core/llms";
-import {
-  extractDataUrlComponents,
-  mapMessageContentToMessageContentDetails,
-} from "../utils";
+import { mapMessageContentToMessageContentDetails } from "../../utils";
+import { extractDataUrlComponents } from "../utils";
 import type {
  AnthropicContent,
  AnthropicImageContent,
@@ -113,7 +111,7 @@ export const mapChatMessagesToAnthropicMessages = <
              {
                type: "tool_result",
                tool_use_id: msg.options.toolResult.id,
-                content: msg.options.toolResult.result,
+                content: JSON.stringify(msg.options.toolResult.result),
              },
            ],
          },
@@ -22,9 +22,9 @@ import {
  type BedrockChatStreamResponse,
  Provider,
 } from "./provider";
-import { mapMessageContentToMessageContentDetails } from "./utils";

 import { wrapLLMEvent } from "@llamaindex/core/decorator";
+import { mapMessageContentToMessageContentDetails } from "../utils";
 import { AmazonProvider } from "./amazon/provider";
 import { AnthropicProvider } from "./anthropic/provider";
 import { MetaProvider } from "./meta/provider";
@@ -1,14 +1,3 @@
-import type {
-  MessageContent,
-  MessageContentDetail,
-} from "@llamaindex/core/llms";
-
-export const mapMessageContentToMessageContentDetails = (
-  content: MessageContent,
-): MessageContentDetail[] => {
-  return Array.isArray(content) ? content : [{ type: "text", text: content }];
-};
-
 export const toUtf8 = (input: Uint8Array): string =>
  new TextDecoder("utf-8").decode(input);

@@ -0,0 +1,10 @@
+import type {
+  MessageContent,
+  MessageContentDetail,
+} from "@llamaindex/core/llms";
+
+export const mapMessageContentToMessageContentDetails = (
+  content: MessageContent,
+): MessageContentDetail[] => {
+  return Array.isArray(content) ? content : [{ type: "text", text: content }];
+};
@@ -1,5 +1,31 @@
 # @llamaindex/core

+## 0.6.2
+
+### Patch Changes
+
+- 9c63f3f: Add support for openai responses api
+
+## 0.6.1
+
+### Patch Changes
+
+- 1b6f368: Support loading from URLs for all readers extending FileReader
+- eaf326e: Fix passing right llm setting from SimpleChatEngine to ChatMemoryBuffer
+
+## 0.6.0
+
+### Minor Changes
+
+- 91a18e7: Added support for structured output in the chat api of openai and ollama
+  Added structured output parameter in the provider
+
+### Patch Changes
+
+- 21bebfc: Expose more content to fix the issue with unavailable documentation links, and adjust the documentation based on the latest code.
+- 93bc0ff: fix: include additional options for context chat engine
+- 5189b44: fix: add retry handling logic to parser reader and fix lint issues
+
 ## 0.5.8

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/core",
  "type": "module",
-  "version": "0.5.8",
+  "version": "0.6.2",
  "description": "LlamaIndex Core Module",
  "exports": {
    "./agent": {
@@ -102,6 +102,7 @@ export class ContextChatEngine extends PromptMixin implements BaseChatEngine {
      const stream = await this.chatModel.chat({
        messages: requestMessages.messages,
        stream: true,
+        additionalChatOptions: params.chatOptions as object,
      });
      return streamConverter(
        streamReducer({
@@ -117,6 +118,7 @@ export class ContextChatEngine extends PromptMixin implements BaseChatEngine {
    }
    const response = await this.chatModel.chat({
      messages: requestMessages.messages,
+      additionalChatOptions: params.chatOptions as object,
    });
    chatHistory.put(response.message);
    return EngineResponse.fromChatResponse(response, requestMessages.nodes);
@@ -24,8 +24,12 @@ export class SimpleChatEngine implements BaseChatEngine {
  }

  constructor(init?: Partial<SimpleChatEngine>) {
-    this.memory = init?.memory ?? new ChatMemoryBuffer();
    this.llm = init?.llm ?? Settings.llm;
+    this.memory =
+      init?.memory ??
+      new ChatMemoryBuffer({
+        llm: this.llm,
+      });
  }

  chat(params: NonStreamingChatEngineParams): Promise<EngineResponse>;
@@ -40,6 +44,7 @@ export class SimpleChatEngine implements BaseChatEngine {

    const chatHistory = params.chatHistory
      ? new ChatMemoryBuffer({
+          llm: this.llm,
          chatHistory:
            params.chatHistory instanceof BaseMemory
              ? await params.chatHistory.getMessages()
@@ -2,7 +2,6 @@ import type { Tokenizers } from "@llamaindex/env/tokenizers";
 import type { JSONSchemaType } from "ajv";
 import { z } from "zod";
 import type { JSONObject, JSONValue } from "../global";
-
 /**
 * @internal
 */
@@ -55,7 +54,12 @@ export interface LLM<
  ): Promise<CompletionResponse>;
 }

-export type MessageType = "user" | "assistant" | "system" | "memory";
+export type MessageType =
+  | "user"
+  | "assistant"
+  | "system"
+  | "memory"
+  | "developer";

 export type TextChatMessage<AdditionalMessageOptions extends object = object> =
  {
@@ -156,6 +160,7 @@ export type MessageContentTextDetail = {
 export type MessageContentImageDetail = {
  type: "image_url";
  image_url: { url: string };
+  detail?: "high" | "low" | "auto";
 };

 export type MessageContentDetail =
@@ -63,8 +63,29 @@ export abstract class FileReader<T extends BaseNode = Document>
  ): Promise<T[]>;

  async loadData(filePath: string): Promise<T[]> {
-    const fileContent = await fs.readFile(filePath);
-    const filename = path.basename(filePath);
+    let fileContent: Uint8Array;
+    let filename: string;
+
+    // Check if filePath is a URL
+    if (filePath.startsWith("http://") || filePath.startsWith("https://")) {
+      // Handle URL
+      const response = await fetch(filePath);
+      if (!response.ok) {
+        throw new Error(
+          `Failed to fetch URL: ${filePath}, status: ${response.status}`,
+        );
+      }
+      const buffer = await response.arrayBuffer();
+      fileContent = new Uint8Array(buffer);
+      // Extract filename from URL
+      const url = new URL(filePath);
+      filename = path.basename(url.pathname) || "url_document";
+    } else {
+      // Handle local file
+      fileContent = await fs.readFile(filePath);
+      filename = path.basename(filePath);
+    }
+
    const docs = await this.loadDataAsContent(fileContent, filename);
    docs.forEach(FileReader.addMetaData(filePath));
    return docs;
@@ -0,0 +1,91 @@
+/* eslint-disable @typescript-eslint/no-explicit-any */
+import { Document, FileReader } from "@llamaindex/core/schema";
+import { fs, path } from "@llamaindex/env";
+import { TextDecoder, TextEncoder } from "util";
+import { afterEach, beforeEach, describe, expect, test, vi } from "vitest";
+
+// Mock implementation of FileReader for testing
+class TestFileReader extends FileReader<Document> {
+  async loadDataAsContent(
+    fileContent: Uint8Array,
+    filename?: string,
+  ): Promise<Document[]> {
+    const text = new TextDecoder().decode(fileContent);
+    return [new Document({ text, metadata: { filename } })];
+  }
+}
+
+describe("FileReader", () => {
+  let reader: TestFileReader;
+  let mockFetch: any;
+  let mockFsReadFile: any;
+
+  beforeEach(() => {
+    reader = new TestFileReader();
+
+    // Mock fetch for URL tests
+    mockFetch = vi.fn();
+    global.fetch = mockFetch;
+
+    // Mock fs.readFile for local file tests
+    mockFsReadFile = vi.spyOn(fs, "readFile");
+  });
+
+  afterEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  test("loadData should load content from a local file", async () => {
+    const testFilePath = "/path/to/test.txt";
+    const testContent = "Test file content";
+    const testContentBuffer = new TextEncoder().encode(testContent);
+
+    mockFsReadFile.mockResolvedValue(testContentBuffer);
+
+    const result = await reader.loadData(testFilePath);
+
+    expect(mockFsReadFile).toHaveBeenCalledWith(testFilePath);
+    expect(result).toHaveLength(1);
+    expect(result[0]).toBeInstanceOf(Document);
+    expect(result[0]?.getText()).toBe(testContent);
+    expect(result[0]?.metadata.file_path).toBe(path.resolve(testFilePath));
+    expect(result[0]?.metadata.file_name).toBe("test.txt");
+  });
+
+  test("loadData should load content from a URL", async () => {
+    const testUrl = "https://example.com/test.txt";
+    const testContent = "Test URL content";
+    const testContentBuffer = new TextEncoder().encode(testContent);
+
+    // Mock fetch response
+    mockFetch.mockResolvedValue({
+      ok: true,
+      arrayBuffer: () => Promise.resolve(testContentBuffer.buffer),
+    });
+
+    const result = await reader.loadData(testUrl);
+
+    expect(mockFetch).toHaveBeenCalledWith(testUrl);
+    expect(result).toHaveLength(1);
+    expect(result[0]).toBeInstanceOf(Document);
+    expect(result[0]?.getText()).toBe(testContent);
+    expect(result[0]?.metadata.file_path).toBe(path.resolve(testUrl));
+    expect(result[0]?.metadata.file_name).toBe("test.txt");
+  });
+
+  test("loadData should throw an error for failed URL fetch", async () => {
+    const testUrl = "https://example.com/not-found.txt";
+
+    // Mock failed fetch response
+    mockFetch.mockResolvedValue({
+      ok: false,
+      status: 404,
+    });
+
+    await expect(reader.loadData(testUrl)).rejects.toThrow(
+      `Failed to fetch URL: ${testUrl}, status: 404`,
+    );
+
+    expect(mockFetch).toHaveBeenCalledWith(testUrl);
+  });
+});
@@ -0,0 +1,14 @@
+import { SimpleChatEngine } from "@llamaindex/core/chat-engine";
+import { ChatMemoryBuffer } from "@llamaindex/core/memory";
+import { MockLLM } from "@llamaindex/core/utils";
+import { describe, expect, test } from "vitest";
+
+describe("SimpleChatEngine", () => {
+  test("constructor initializes with provided LLM", () => {
+    const llm = new MockLLM();
+    const engine = new SimpleChatEngine({ llm });
+    expect(engine.llm).toBe(llm);
+    expect(engine.memory).toBeInstanceOf(ChatMemoryBuffer);
+    expect((engine.memory as ChatMemoryBuffer).tokenLimit).toBe(768);
+  });
+});
@@ -1,5 +1,31 @@
 # @llamaindex/experimental

+## 0.0.165
+
+### Patch Changes
+
+- llamaindex@0.9.15
+
+## 0.0.164
+
+### Patch Changes
+
+- Updated dependencies [9d951b2]
+  - llamaindex@0.9.14
+
+## 0.0.163
+
+### Patch Changes
+
+- Updated dependencies [75d6e29]
+  - llamaindex@0.9.13
+
+## 0.0.162
+
+### Patch Changes
+
+- llamaindex@0.9.12
+
 ## 0.0.161

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/experimental",
  "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.161",
+  "version": "0.0.165",
  "type": "module",
  "types": "dist/type/index.d.ts",
  "main": "dist/cjs/index.js",
@@ -1,5 +1,53 @@
 # llamaindex

+## 0.9.15
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+- Updated dependencies [c515a32]
+  - @llamaindex/openai@0.3.0
+  - @llamaindex/core@0.6.2
+  - @llamaindex/workflow@1.0.2
+  - @llamaindex/cloud@4.0.2
+  - @llamaindex/node-parser@2.0.2
+
+## 0.9.14
+
+### Patch Changes
+
+- 9d951b2: feat: support llamacloud in @llamaindex/server
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+  - @llamaindex/core@0.6.1
+  - @llamaindex/cloud@4.0.1
+  - @llamaindex/node-parser@2.0.1
+  - @llamaindex/openai@0.2.1
+  - @llamaindex/workflow@1.0.1
+
+## 0.9.13
+
+### Patch Changes
+
+- 75d6e29: feat: response source nodes in query tool output
+
+## 0.9.12
+
+### Patch Changes
+
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [bf56fc0]
+- Updated dependencies [f8a86e4]
+- Updated dependencies [5189b44]
+- Updated dependencies [58a9446]
+  - @llamaindex/core@0.6.0
+  - @llamaindex/openai@0.2.0
+  - @llamaindex/cloud@4.0.0
+  - @llamaindex/workflow@1.0.0
+  - @llamaindex/node-parser@2.0.0
+
 ## 0.9.11

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "llamaindex",
-  "version": "0.9.11",
+  "version": "0.9.15",
  "license": "MIT",
  "type": "module",
  "keywords": [
@@ -25,7 +25,9 @@ import {
 } from "@llamaindex/cloud/api";
 import type { BaseRetriever } from "@llamaindex/core/retriever";
 import { getEnv } from "@llamaindex/env";
+import type { QueryToolParams } from "../indices/BaseIndex.js";
 import { Settings } from "../Settings.js";
+import { QueryEngineTool } from "../tools/QueryEngineTool.js";

 export class LlamaCloudIndex {
  params: CloudConstructorParams;
@@ -272,6 +274,22 @@ export class LlamaCloudIndex {
    );
  }

+  asQueryTool(params: QueryToolParams): QueryEngineTool {
+    if (params.options) {
+      params.retriever = this.asRetriever(params.options);
+    }
+
+    return new QueryEngineTool({
+      queryEngine: this.asQueryEngine(params),
+      metadata: params?.metadata,
+      includeSourceNodes: params?.includeSourceNodes ?? false,
+    });
+  }
+
+  queryTool(params: QueryToolParams): QueryEngineTool {
+    return this.asQueryTool(params);
+  }
+
  async insert(document: Document) {
    const pipelineId = await this.getPipelineId();

@@ -41,6 +41,7 @@ export type QueryToolParams = (
 ) & {
  responseSynthesizer?: BaseSynthesizer;
  metadata?: ToolMetadata<JSONSchemaType<QueryEngineParam>> | undefined;
+  includeSourceNodes?: boolean;
 };

 /**
@@ -98,6 +99,7 @@ export abstract class BaseIndex<T> {
    return new QueryEngineTool({
      queryEngine: this.asQueryEngine(params),
      metadata: params?.metadata,
+      includeSourceNodes: params?.includeSourceNodes ?? false,
    });
  }

@@ -1,3 +1,4 @@
+import type { JSONValue } from "@llamaindex/core/global";
 import type { BaseTool, ToolMetadata } from "@llamaindex/core/llms";
 import type { BaseQueryEngine } from "@llamaindex/core/query-engine";
 import type { JSONSchemaType } from "ajv";
@@ -20,6 +21,7 @@ const DEFAULT_PARAMETERS: JSONSchemaType<QueryEngineParam> = {
 export type QueryEngineToolParams = {
  queryEngine: BaseQueryEngine;
  metadata?: ToolMetadata<JSONSchemaType<QueryEngineParam>> | undefined;
+  includeSourceNodes?: boolean;
 };

 export type QueryEngineParam = {
@@ -29,19 +31,32 @@ export type QueryEngineParam = {
 export class QueryEngineTool implements BaseTool<QueryEngineParam> {
  private queryEngine: BaseQueryEngine;
  metadata: ToolMetadata<JSONSchemaType<QueryEngineParam>>;
+  includeSourceNodes: boolean;

-  constructor({ queryEngine, metadata }: QueryEngineToolParams) {
+  constructor({
+    queryEngine,
+    metadata,
+    includeSourceNodes,
+  }: QueryEngineToolParams) {
    this.queryEngine = queryEngine;
    this.metadata = {
      name: metadata?.name ?? DEFAULT_NAME,
      description: metadata?.description ?? DEFAULT_DESCRIPTION,
      parameters: metadata?.parameters ?? DEFAULT_PARAMETERS,
    };
+    this.includeSourceNodes = includeSourceNodes ?? false;
  }

  async call({ query }: QueryEngineParam) {
    const response = await this.queryEngine.query({ query });

-    return response.message.content;
+    if (!this.includeSourceNodes) {
+      return { content: response.message.content };
+    }
+
+    return {
+      content: response.message.content,
+      sourceNodes: response.sourceNodes,
+    } as unknown as JSONValue;
  }
 }
@@ -1,5 +1,30 @@
 # @llamaindex/node-parser

+## 2.0.2
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+  - @llamaindex/core@0.6.2
+
+## 2.0.1
+
+### Patch Changes
+
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+  - @llamaindex/core@0.6.1
+
+## 2.0.0
+
+### Patch Changes
+
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [5189b44]
+  - @llamaindex/core@0.6.0
+
 ## 1.0.8

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/node-parser",
-  "version": "1.0.8",
+  "version": "2.0.2",
  "description": "Node parser for LlamaIndex",
  "type": "module",
  "exports": {
@@ -1,5 +1,35 @@
 # @llamaindex/anthropic

+## 0.3.2
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+  - @llamaindex/core@0.6.2
+
+## 0.3.1
+
+### Patch Changes
+
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+  - @llamaindex/core@0.6.1
+
+## 0.3.0
+
+### Minor Changes
+
+- 91a18e7: Added support for structured output in the chat api of openai and ollama
+  Added structured output parameter in the provider
+
+### Patch Changes
+
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [5189b44]
+  - @llamaindex/core@0.6.0
+
 ## 0.2.6

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/anthropic",
  "description": "Anthropic Adapter for LlamaIndex",
-  "version": "0.2.6",
+  "version": "0.3.2",
  "type": "module",
  "main": "./dist/index.cjs",
  "module": "./dist/index.js",
@@ -1,5 +1,33 @@
 # @llamaindex/clip

+## 0.0.48
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+  - @llamaindex/openai@0.3.0
+  - @llamaindex/core@0.6.2
+
+## 0.0.47
+
+### Patch Changes
+
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+  - @llamaindex/core@0.6.1
+  - @llamaindex/openai@0.2.1
+
+## 0.0.46
+
+### Patch Changes
+
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [5189b44]
+  - @llamaindex/core@0.6.0
+  - @llamaindex/openai@0.2.0
+
 ## 0.0.45

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/clip",
  "description": "Clip Embedding Adapter for LlamaIndex",
-  "version": "0.0.45",
+  "version": "0.0.48",
  "type": "module",
  "types": "dist/index.d.ts",
  "main": "dist/index.cjs",
@@ -1,5 +1,30 @@
 # @llamaindex/cohere

+## 0.0.16
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+  - @llamaindex/core@0.6.2
+
+## 0.0.15
+
+### Patch Changes
+
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+  - @llamaindex/core@0.6.1
+
+## 0.0.14
+
+### Patch Changes
+
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [5189b44]
+  - @llamaindex/core@0.6.0
+
 ## 0.0.13

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/cohere",
  "description": "Cohere Adapter for LlamaIndex",
-  "version": "0.0.13",
+  "version": "0.0.16",
  "type": "module",
  "main": "./dist/index.cjs",
  "module": "./dist/index.js",
@@ -1,5 +1,33 @@
 # @llamaindex/deepinfra

+## 0.0.48
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+  - @llamaindex/openai@0.3.0
+  - @llamaindex/core@0.6.2
+
+## 0.0.47
+
+### Patch Changes
+
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+  - @llamaindex/core@0.6.1
+  - @llamaindex/openai@0.2.1
+
+## 0.0.46
+
+### Patch Changes
+
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [5189b44]
+  - @llamaindex/core@0.6.0
+  - @llamaindex/openai@0.2.0
+
 ## 0.0.45

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/deepinfra",
  "description": "Deepinfra Adapter for LlamaIndex",
-  "version": "0.0.45",
+  "version": "0.0.48",
  "type": "module",
  "main": "./dist/index.cjs",
  "module": "./dist/index.js",
@@ -1,5 +1,25 @@
 # @llamaindex/deepseek

+## 0.0.8
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+  - @llamaindex/openai@0.3.0
+
+## 0.0.7
+
+### Patch Changes
+
+- @llamaindex/openai@0.2.1
+
+## 0.0.6
+
+### Patch Changes
+
+- Updated dependencies [91a18e7]
+  - @llamaindex/openai@0.2.0
+
 ## 0.0.5

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/deepseek",
  "description": "DeepSeek Adapter for LlamaIndex",
-  "version": "0.0.5",
+  "version": "0.0.8",
  "type": "module",
  "main": "./dist/index.cjs",
  "module": "./dist/index.js",
@@ -1,5 +1,25 @@
 # @llamaindex/fireworks

+## 0.0.8
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+  - @llamaindex/openai@0.3.0
+
+## 0.0.7
+
+### Patch Changes
+
+- @llamaindex/openai@0.2.1
+
+## 0.0.6
+
+### Patch Changes
+
+- Updated dependencies [91a18e7]
+  - @llamaindex/openai@0.2.0
+
 ## 0.0.5

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/fireworks",
  "description": "Fireworks Adapter for LlamaIndex",
-  "version": "0.0.5",
+  "version": "0.0.8",
  "type": "module",
  "main": "./dist/index.cjs",
  "module": "./dist/index.js",
@@ -1,5 +1,39 @@
 # @llamaindex/google

+## 0.2.2
+
+### Patch Changes
+
+- 9c63f3f: Add support for openai responses api
+- Updated dependencies [9c63f3f]
+  - @llamaindex/core@0.6.2
+
+## 0.2.1
+
+### Patch Changes
+
+- Updated dependencies [1b6f368]
+- Updated dependencies [eaf326e]
+  - @llamaindex/core@0.6.1
+
+## 0.2.0
+
+### Minor Changes
+
+- 91a18e7: Added support for structured output in the chat api of openai and ollama
+  Added structured output parameter in the provider
+
+### Patch Changes
+
+- da06e45: fix: don't ignore parts that only have inline data for google studio
+- 2a0a899: Added saftey setting parameter for gemini
+- 3fd4cc3: feat: use google's new gen ai library to support multimodal output
+- Updated dependencies [21bebfc]
+- Updated dependencies [93bc0ff]
+- Updated dependencies [91a18e7]
+- Updated dependencies [5189b44]
+  - @llamaindex/core@0.6.0
+
 ## 0.1.2

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/google",
  "description": "Google Adapter for LlamaIndex",
-  "version": "0.1.2",
+  "version": "0.2.2",
  "type": "module",
  "main": "./dist/index.cjs",
  "module": "./dist/index.js",
@@ -34,6 +34,7 @@
  },
  "dependencies": {
    "@google-cloud/vertexai": "1.9.0",
+    "@google/genai": "^0.4.0",
    "@google/generative-ai": "0.21.0",
    "@llamaindex/core": "workspace:*",
    "@llamaindex/env": "workspace:*"
@@ -63,7 +63,7 @@ export const GEMINI_MODEL_INFO_MAP: Record<GEMINI_MODEL, GeminiModelInfo> = {
  [GEMINI_MODEL.GEMINI_2_0_PRO_EXPERIMENTAL]: { contextWindow: 2 * 10 ** 6 },
 };

-const SUPPORT_TOOL_CALL_MODELS: GEMINI_MODEL[] = [
+export const SUPPORT_TOOL_CALL_MODELS: GEMINI_MODEL[] = [
  GEMINI_MODEL.GEMINI_PRO,
  GEMINI_MODEL.GEMINI_PRO_VISION,
  GEMINI_MODEL.GEMINI_PRO_1_5_PRO_PREVIEW,
@@ -79,7 +79,7 @@ const SUPPORT_TOOL_CALL_MODELS: GEMINI_MODEL[] = [
  GEMINI_MODEL.GEMINI_2_0_PRO_EXPERIMENTAL,
 ];

-const DEFAULT_GEMINI_PARAMS = {
+export const DEFAULT_GEMINI_PARAMS = {
  model: GEMINI_MODEL.GEMINI_PRO,
  temperature: 0.1,
  topP: 1,
@@ -3,4 +3,10 @@ export * from "./types";
 export * from "./utils";
 export * from "./vertex";

+export {
+  GoogleStudio,
+  Modality,
+  getGoogleStudioInlineData,
+} from "./studio/index.js";
+
 export * from "./GeminiEmbedding";
@@ -0,0 +1,262 @@
+import {
+  GenerateContentResponse,
+  GoogleGenAI,
+  Modality,
+  type Blob,
+  type GenerateContentConfig,
+  type GoogleGenAIOptions,
+} from "@google/genai";
+import {
+  ToolCallLLM,
+  type ChatResponse,
+  type ChatResponseChunk,
+  type CompletionResponse,
+  type LLMChatParamsNonStreaming,
+  type LLMChatParamsStreaming,
+  type LLMCompletionParamsNonStreaming,
+  type LLMCompletionParamsStreaming,
+  type LLMMetadata,
+  type ToolCall,
+  type ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+export { Modality };
+
+import { streamConverter } from "@llamaindex/core/utils";
+
+import { wrapLLMEvent } from "@llamaindex/core/decorator";
+import type { JSONObject } from "@llamaindex/core/global";
+import { DEFAULT_GEMINI_PARAMS, SUPPORT_TOOL_CALL_MODELS } from "../base";
+import type { GEMINI_MODEL } from "../types";
+import {
+  mapChatMessagesToGoogleFunctions,
+  mapChatMessagesToGoogleMessages,
+  mapMessageContentDetailToGooglePart,
+  mapMessageContentToMessageContentDetails,
+} from "./utils";
+
+export type GoogleAdditionalChatOptions = { config: GenerateContentConfig };
+
+export type GoogleChatStreamResponse = AsyncIterable<
+  ChatResponseChunk<
+    ToolCallLLMMessageOptions & {
+      data?: Blob[];
+    }
+  >
+>;
+
+export type GoogleChatParamsStreaming = LLMChatParamsStreaming<
+  GoogleAdditionalChatOptions,
+  ToolCallLLMMessageOptions
+>;
+
+export type GoogleChatParamsNonStreaming = LLMChatParamsNonStreaming<
+  GoogleAdditionalChatOptions,
+  ToolCallLLMMessageOptions
+>;
+
+export type GoogleChatNonStreamResponse =
+  ChatResponse<ToolCallLLMMessageOptions>;
+
+export const getGoogleStudioInlineData = (
+  response: GenerateContentResponse,
+): Blob[] => {
+  return response.candidates
+    ?.flatMap((candidate) => candidate.content?.parts)
+    .map((part) => part?.inlineData)
+    .filter((data) => data) as Blob[];
+};
+
+export type GoogleModelParams = {
+  model: GEMINI_MODEL;
+  temperature?: number;
+  topP?: number;
+  maxTokens?: number;
+};
+
+export type GoogleParams = GoogleGenAIOptions & GoogleModelParams;
+
+export class GoogleStudio extends ToolCallLLM<GoogleAdditionalChatOptions> {
+  client: GoogleGenAI;
+  model: GEMINI_MODEL;
+  temperature: number;
+  topP: number;
+  maxTokens?: number | undefined;
+  topK?: number;
+
+  constructor({
+    temperature,
+    topP,
+    maxTokens,
+    model,
+    ...params
+  }: GoogleParams) {
+    super();
+    this.model = model;
+    this.maxTokens = maxTokens ?? DEFAULT_GEMINI_PARAMS.maxTokens;
+    this.temperature = temperature ?? DEFAULT_GEMINI_PARAMS.temperature;
+    this.topP = topP ?? DEFAULT_GEMINI_PARAMS.topP;
+    this.client = new GoogleGenAI(params);
+  }
+
+  get supportToolCall(): boolean {
+    return SUPPORT_TOOL_CALL_MODELS.includes(this.model);
+  }
+
+  get metadata(): LLMMetadata {
+    return {
+      model: this.model,
+      temperature: this.temperature,
+      topP: this.topP,
+      maxTokens: this.maxTokens,
+      contextWindow: 128000,
+      tokenizer: undefined,
+      structuredOutput: false,
+    };
+  }
+
+  getToolCallsFromResponse(response: GenerateContentResponse): ToolCall[] {
+    if (!response.functionCalls) return [];
+    return response.functionCalls.map((call) => ({
+      id: call.id ?? "",
+      name: call.name ?? "",
+      input: call.args as JSONObject,
+    }));
+  }
+
+  protected async nonStreamChat(
+    params: GoogleChatParamsNonStreaming,
+  ): Promise<GoogleChatNonStreamResponse> {
+    if (!this.supportToolCall && params.tools?.length) {
+      console.warn(`The model "${this.model}" doesn't support ToolCall`);
+    }
+
+    const config: GenerateContentConfig =
+      params.additionalChatOptions?.config ?? {};
+    if (params.tools?.length) {
+      if (config.responseModalities?.includes(Modality.IMAGE)) {
+        console.warn("Tools are currently not supported with Modality.IMAGE");
+      } else {
+        config.tools = mapChatMessagesToGoogleFunctions(params.tools);
+      }
+    }
+    const response = await this.client.models.generateContent({
+      model: this.model,
+      contents: mapChatMessagesToGoogleMessages(params.messages),
+      config,
+    });
+
+    if (this.supportToolCall) {
+      const tools = this.getToolCallsFromResponse(response);
+      if (tools.length) {
+        return {
+          raw: response,
+          message: {
+            role: "assistant",
+            content: "",
+            options: { toolCall: tools },
+          },
+        };
+      }
+    }
+    return {
+      raw: response,
+      message: {
+        role: "assistant",
+        content: response.text ?? "",
+        options: {
+          inlineData: getGoogleStudioInlineData(response),
+        },
+      },
+    };
+  }
+
+  protected async *streamChat(
+    params: GoogleChatParamsStreaming,
+  ): GoogleChatStreamResponse {
+    if (!this.supportToolCall && params.tools?.length) {
+      console.warn(`The model "${this.model}" doesn't support ToolCall`);
+    }
+    const config: GenerateContentConfig =
+      params.additionalChatOptions?.config ?? {};
+    if (params.tools?.length) {
+      if (config.responseModalities?.includes(Modality.IMAGE)) {
+        console.warn("Tools are currently not supported with Modality.IMAGE");
+      } else {
+        config.tools = mapChatMessagesToGoogleFunctions(params.tools);
+      }
+    }
+    const response = await this.client.models.generateContentStream({
+      model: this.model,
+      contents: mapChatMessagesToGoogleMessages(params.messages),
+      config,
+    });
+    yield* streamConverter(response, (response) => {
+      if (response.functionCalls?.length) {
+        return {
+          delta: "",
+          raw: response,
+          options: {
+            toolCall: this.getToolCallsFromResponse(response),
+          },
+        };
+      }
+
+      return {
+        delta: response.text ?? "",
+        raw: response,
+        options: {
+          inlineData: getGoogleStudioInlineData(response),
+        },
+      };
+    });
+  }
+
+  chat(params: GoogleChatParamsStreaming): Promise<GoogleChatStreamResponse>;
+  chat(
+    params: GoogleChatParamsNonStreaming,
+  ): Promise<GoogleChatNonStreamResponse>;
+  @wrapLLMEvent
+  async chat(
+    params: GoogleChatParamsStreaming | GoogleChatParamsNonStreaming,
+  ): Promise<GoogleChatStreamResponse | GoogleChatNonStreamResponse> {
+    if (params.stream) {
+      return this.streamChat(params);
+    }
+    return this.nonStreamChat(params);
+  }
+
+  complete(
+    params: LLMCompletionParamsStreaming,
+  ): Promise<AsyncIterable<CompletionResponse>>;
+  complete(
+    params: LLMCompletionParamsNonStreaming,
+  ): Promise<CompletionResponse>;
+  async complete(
+    params: LLMCompletionParamsStreaming | LLMCompletionParamsNonStreaming,
+  ): Promise<CompletionResponse | AsyncIterable<CompletionResponse>> {
+    const contents = mapMessageContentToMessageContentDetails(
+      params.prompt,
+    ).map(mapMessageContentDetailToGooglePart);
+    if (params.stream) {
+      const response = await this.client.models.generateContentStream({
+        model: this.model,
+        contents,
+      });
+      return streamConverter(response, (response) => {
+        return {
+          text: response.text ?? "",
+          raw: response,
+        };
+      });
+    }
+    const response = await this.client.models.generateContent({
+      model: this.model,
+      contents,
+    });
+
+    return {
+      text: response.text || "",
+      raw: response,
+    };
+  }
+}
@@ -0,0 +1,136 @@
+import type {
+  ContentListUnion,
+  ContentUnion,
+  Part,
+  Schema,
+  ToolListUnion,
+} from "@google/genai";
+import type {
+  BaseTool,
+  ChatMessage,
+  MessageContentDetail,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import { extractDataUrlComponents } from "@llamaindex/core/utils";
+
+import type { MessageContent } from "@llamaindex/core/llms";
+
+export const mapMessageContentToMessageContentDetails = (
+  content: MessageContent,
+): MessageContentDetail[] => {
+  return Array.isArray(content) ? content : [{ type: "text", text: content }];
+};
+
+const ACCEPTED_IMAGE_MIME_TYPES = ["image/jpeg", "image/png"];
+
+export const mapTextPart = (text: string): Part => {
+  return { text };
+};
+
+export const mapImagePart = (imageUrl: string): Part => {
+  if (!imageUrl.startsWith("data:"))
+    throw new Error(
+      "For Google please only use base64 data url, e.g.: data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==",
+    );
+  const { mimeType, base64: data } = extractDataUrlComponents(imageUrl);
+  if (!ACCEPTED_IMAGE_MIME_TYPES.includes(mimeType))
+    throw new Error(
+      `Anthropic only accepts the following mimeTypes: ${ACCEPTED_IMAGE_MIME_TYPES.join("\n")}`,
+    );
+
+  return {
+    inlineData: {
+      mimeType,
+      data,
+    },
+  };
+};
+
+export const mapMessageContentDetailToGooglePart = <
+  T extends MessageContentDetail,
+>(
+  detail: T,
+): Part => {
+  let part: Part;
+
+  if (detail.type === "text") {
+    part = mapTextPart(detail.text);
+  } else if (detail.type === "image_url") {
+    part = mapImagePart(detail.image_url.url);
+  } else {
+    throw new Error("Unsupported content detail type");
+  }
+  return part;
+};
+export const mapChatMessagesToGoogleFunctions = (
+  tools: BaseTool[],
+): ToolListUnion => {
+  return [
+    {
+      functionDeclarations: tools.map((tool) => ({
+        response: tool.metadata.parameters as Schema,
+        description: tool.metadata.description,
+        name: tool.metadata.name,
+      })),
+    },
+  ];
+};
+
+export const mapChatMessagesToGoogleMessages = <
+  T extends ChatMessage<ToolCallLLMMessageOptions>,
+>(
+  messages: T[],
+): ContentListUnion => {
+  const functionNames: Record<string, string> = {};
+  messages.forEach((msg: T) => {
+    if (msg.options && "toolCall" in msg.options) {
+      const mapped = msg.options.toolCall.reduce(
+        (result, item) => {
+          result[item.id] = item.name;
+          return result;
+        },
+        {} as Record<string, string>,
+      );
+
+      Object.assign(functionNames, mapped);
+    }
+  });
+  return messages.flatMap((msg: T): ContentListUnion => {
+    if (msg.options && "toolResult" in msg.options) {
+      return {
+        role: "user",
+        parts: [
+          {
+            functionResponse: {
+              name: functionNames[msg.options.toolResult.id] ?? "",
+              response: msg.options.toolResult,
+            },
+          },
+        ],
+      };
+    }
+
+    if (msg.options && "toolCall" in msg.options) {
+      return {
+        role: "model",
+        parts: msg.options.toolCall.map((call) => ({
+          functionCall: {
+            name: call.name,
+            args: call.input as Record<string, unknown>,
+          },
+        })),
+      };
+    }
+    return mapMessageContentToMessageContentDetails(msg.content)
+      .map((detail: MessageContentDetail): ContentUnion | null => {
+        const part = mapMessageContentDetailToGooglePart(detail);
+        if (!part.text && !part.inlineData) return null;
+
+        return {
+          role: msg.role === "assistant" ? "model" : "user",
+          parts: [part],
+        };
+      })
+      .filter((content) => content) as ContentUnion;
+  });
+};
@@ -181,7 +181,7 @@ export const mapBaseToolToGeminiFunctionDeclaration = (
 export class GeminiHelper {
  // Gemini only has user and model roles. Put the rest in user role.
  public static readonly ROLES_TO_GEMINI: Record<
-    MessageType,
+    Exclude<MessageType, "developer">,
    GeminiMessageRole
  > = {
    user: "user",
@@ -285,7 +285,9 @@ export class GeminiHelper {
    if (message.options && "toolResult" in message.options) {
      return "function";
    }
-    return GeminiHelper.ROLES_TO_GEMINI[message.role];
+    return GeminiHelper.ROLES_TO_GEMINI[
+      message.role as Exclude<MessageType, "developer">
+    ];
  }

  public static chatMessageToGemini(
@@ -1,5 +1,25 @@
 # @llamaindex/groq

+## 0.0.63
+
+### Patch Changes
+
+- Updated dependencies [9c63f3f]
+  - @llamaindex/openai@0.3.0
+
+## 0.0.62
+
+### Patch Changes
+
+- @llamaindex/openai@0.2.1
+
+## 0.0.61
+
+### Patch Changes
+
+- Updated dependencies [91a18e7]
+  - @llamaindex/openai@0.2.0
+
 ## 0.0.60

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/groq",
  "description": "Groq Adapter for LlamaIndex",
-  "version": "0.0.60",
+  "version": "0.0.63",
  "type": "module",
  "main": "./dist/index.cjs",
  "module": "./dist/index.js",
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
github-actions[bot]	9a27b6d94a	Release 0.9.15 (#1807 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-04-02 17:08:47 +07:00
Thuc Pham	8c02684f0f	fix: handle error when streaming workflow (#1808 )	2025-04-02 16:26:01 +07:00
ANKIT VARSHNEY	9c63f3f94e	feat: openai responses api (#1801 )	2025-04-02 16:21:43 +07:00
Thuc Pham	c515a324f6	feat: return raw output for agent toolcall result (#1806 )	2025-04-01 22:20:06 +07:00
github-actions[bot]	c70d7b9930	Release 0.9.14 (#1799 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-04-01 12:59:10 +02:00
Marcus Schiesser	1b6f368a3f	feat: Support loading from URLs for all readers extending FileReader (#1805 )	2025-04-01 17:39:59 +07:00
Thuc Pham	9d951b288f	feat: support llamacloud in @llamaindex/server (#1796 )	2025-04-01 17:39:39 +07:00
dependabot[bot]	5fe16697a2	chore(deps-dev): bump vite from 5.4.15 to 5.4.16 (#1804 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-04-01 16:49:36 +07:00
Marcus Schiesser	189d8a83ac	chore: use node 20 for examples (#1803 )	2025-03-31 17:21:19 +07:00
ANKIT VARSHNEY	648cfb5cb5	feat: supbase vector store (#1790 )	2025-03-29 15:14:28 +07:00
Marcus Schiesser	eaf326ee90	fix: passing right llm setting from SimpleChatEngine to ChatMemoryBuffer (#1798 )	2025-03-28 18:20:52 +07:00
github-actions[bot]	fc1bedf438	Release (#1794 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2025-03-28 15:22:44 +07:00
Thuc Pham	164cf7a6df	fix: custom next server start fail (#1795 )	2025-03-28 15:09:57 +07:00
Zhanghao	e98033e2cc	docs: correct the number of indexes (#1793 )	2025-03-27 16:33:52 +02:00
dependabot[bot]	c0ffc7b434	chore(deps-dev): bump vite from 5.4.14 to 5.4.15 (#1787 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-03-26 20:43:49 +07:00
github-actions[bot]	9cf88e9f3f	Release 0.9.13 (#1783 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>	2025-03-26 10:31:29 +02:00
Thuc Pham	75d6e29187	feat: response source nodes in query tool output (#1784 )	2025-03-26 15:24:53 +07:00
Parham Saidi	132517877e	fix: stringify all tool results for anthropic on bedrock (#1786 )	2025-03-25 21:16:44 +07:00
Thuc Pham	299008b34f	feat: copy create-llama to @llamaindex/servers (#1780 )	2025-03-25 11:55:44 +02:00
Thuc Pham	482ed67690	fix: document deployment fail due to static generation timed out (#1779 )	2025-03-24 11:12:09 +02:00
github-actions[bot]	9aeec9089b	Release 0.9.12 (#1744 ) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>	2025-03-24 14:34:45 +07:00
Daniel Bank	f1db9b3d48	feat: vercel tool response fields options (#1765 )	2025-03-24 14:25:26 +07:00
ANKIT VARSHNEY	25093531cf	feat: elastic search vector store (#1777 )	2025-03-24 14:18:42 +07:00
Thuc Pham	f8a86e4eff	feat: @llamaindex/server (#1759 )	2025-03-21 19:14:19 +07:00
ANKIT VARSHNEY	04f8c96caa	feat: add support for mongodb document store (#1771 )	2025-03-21 16:16:49 +07:00
Jorge Luis Middleton	43053f9e16	Update qdrant.mdx documentation (#1770 )	2025-03-21 10:06:25 +02:00
Parham Saidi	93bc0ffd21	fix: context engine additional options not being passed (#1772 )	2025-03-21 01:49:43 +07:00
Huu Le	58a9446220	Fix wrong multi-agent setup (#1767 )	2025-03-20 14:55:25 +03:00
Parham Saidi	da06e4550b	fix: include inline data check for GoogleStudio (#1769 )	2025-03-20 14:50:47 +03:00
Parham Saidi	3fd4cc383e	feat: google multimodal output using their new gen ai library (#1762 )	2025-03-19 21:43:39 +02:00
ANKIT VARSHNEY	2b39ceffa6	docs: doc for structured output (#1761 )	2025-03-19 14:15:11 +07:00
Thuc Pham	77e24cec65	fix: crypto is not defined when running on node18 (#1763 )	2025-03-19 08:38:16 +02:00