Release (#2164)

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

apps/next/CHANGELOG.md

@@ -1,5 +1,92 @@
 # @llamaindex/doc
 
+## 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
+
+- Updated dependencies [c3bf3c7]
+- Updated dependencies [f9f1de9]
+  - @llamaindex/cloud@4.0.28
+  - @llamaindex/core@0.6.19
+  - llamaindex@0.11.24
+  - @llamaindex/node-parser@2.0.19
+  - @llamaindex/openai@0.4.14
+  - @llamaindex/readers@3.1.18
+  - @llamaindex/workflow@1.1.20
+
+## 0.2.46
+
+### Patch Changes
+
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/workflow@1.1.19
+  - @llamaindex/core@0.6.18
+  - llamaindex@0.11.23
+  - @llamaindex/cloud@4.0.27
+  - @llamaindex/node-parser@2.0.18
+  - @llamaindex/openai@0.4.13
+  - @llamaindex/readers@3.1.17
+
+## 0.2.45
+
+### Patch Changes
+
+- Updated dependencies [9ed3195]
+  - @llamaindex/workflow@1.1.18
+  - llamaindex@0.11.22
+
+## 0.2.44
+
+### Patch Changes
+
+- 38da40b: feat: VectoryMemoryBlock
+- Updated dependencies [38da40b]
+  - @llamaindex/core@0.6.17
+  - @llamaindex/cloud@4.0.26
+  - llamaindex@0.11.21
+  - @llamaindex/node-parser@2.0.17
+  - @llamaindex/openai@0.4.12
+  - @llamaindex/readers@3.1.16
+  - @llamaindex/workflow@1.1.17
+
+## 0.2.43
+
+### Patch Changes
+
+- ea15e75: Minor updates in deployment docs
+
 ## 0.2.42
 
 ### Patch Changes

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.42",
+  "version": "0.2.51",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",

apps/next/src/content/docs/llamaindex/getting_started/installation/nextjs.mdx

@@ -77,7 +77,7 @@ export async function POST(request: NextRequest) {
     const agent = await initializeAgent();
     const result = await agent.run(message);
     
-    return NextResponse.json({ response: result.result });
+    return NextResponse.json({ response: result.data });
   } catch (error) {
     console.error("Chat error:", error);
     return NextResponse.json(
@@ -132,7 +132,7 @@ export default async function handler(
     const agent = await initializeAgent();
     const result = await agent.run(message);
     
-    res.json({ response: result.result });
+    res.json({ response: result.data });
   } catch (error) {
     console.error("Chat error:", error);
     res.status(500).json({ error: "Internal server error" });
@@ -220,7 +220,7 @@ export async function POST(request: NextRequest) {
     });
 
     const result = await myAgent.run(message);
-    return NextResponse.json({ response: result.result });
+    return NextResponse.json({ response: result.data });
   } catch (error) {
     return NextResponse.json({ error: error.message }, { status: 500 });
   }
@@ -233,11 +233,40 @@ Implement streaming for better user experience:
 
 ```typescript
 // app/api/chat-stream/route.ts
+import { agent } from "@llamaindex/workflow";
+import { tool } from "llamaindex";
+import { openai } from "@llamaindex/openai";
 import { agentStreamEvent } from "@llamaindex/workflow";
 import { NextRequest } from "next/server";
+import { z } from "zod";
 
-// Assume myAgent is initialized elsewhere
-declare const myAgent: any;
+// Initialize agent once (consider using a singleton pattern)
+let myAgent: any = null;
+
+async function initializeAgent() {
+  if (myAgent) return myAgent;
+  
+  try {
+    const greetTool = tool({
+      name: "greet",
+      description: "Greets a user with their name",
+      parameters: z.object({
+        name: z.string(),
+      }),
+      execute: ({ name }) => `Hello, ${name}! How can I help you today?`,
+    });
+
+    myAgent = agent({
+      tools: [greetTool],
+      llm: openai({ model: "gpt-4o-mini" }),
+    });
+    
+    return myAgent;
+  } catch (error) {
+    console.error("Failed to initialize agent:", error);
+    throw error;
+  }
+}
 
 export async function POST(request: NextRequest) {
   const { message } = await request.json();
@@ -245,9 +274,10 @@ export async function POST(request: NextRequest) {
   const stream = new ReadableStream({
     async start(controller) {
       try {
-        const context = myAgent.runStream(message);
+        const agent = await initializeAgent();
+        const events = agent.runStream(message);
         
-        for await (const event of context) {
+        for await (const event of events) {
           if (agentStreamEvent.include(event)) {
             controller.enqueue(new TextEncoder().encode(event.data.delta));
           }

apps/next/src/content/docs/llamaindex/getting_started/installation/server-apis.mdx

@@ -63,7 +63,7 @@ app.post('/api/chat', async (req, res) => {
   try {
     const { message } = req.body;
     const result = await myAgent.run(message);
-    res.json({ response: result.result });
+    res.json({ response: result.data });
   } catch (error) {
     res.status(500).json({ error: 'Chat failed' });
   }
@@ -110,7 +110,7 @@ fastify.post('/api/chat', async (request, reply) => {
   try {
     const { message } = request.body as { message: string };
     const result = await myAgent.run(message);
-    return { response: result.result };
+    return { response: result.data };
   } catch (error) {
     reply.status(500).send({ error: 'Chat failed' });
   }
@@ -162,7 +162,7 @@ app.post("/api/chat", async (c) => {
   
   try {
     const result = await myAgent.run(message);
-    return c.json({ response: result.result });
+    return c.json({ response: result.data });
   } catch (error) {
     return c.json({ error: error.message }, 500);
   }
@@ -187,9 +187,9 @@ app.post('/api/chat-stream', async (req, res) => {
   });
   
   try {
-    const context = myAgent.runStream(message);
+    const events = myAgent.runStream(message);
     
-    for await (const event of context) {
+    for await (const event of events) {
       if (agentStreamEvent.include(event)) {
         res.write(event.data.delta);
       }

apps/next/src/content/docs/llamaindex/getting_started/installation/serverless.mdx

@@ -34,7 +34,7 @@ export default {
       const { message } = await request.json();
       const result = await myAgent.run(message);
       
-      return new Response(JSON.stringify({ response: result.result }), {
+      return new Response(JSON.stringify({ response: result.data }), {
         headers: { "Content-Type": "application/json" },
       });
     } catch (error) {
@@ -83,7 +83,7 @@ export default async function handler(req, res) {
   
   try {
     const result = await myAgent.run(message);
-    res.json({ response: result.result });
+    res.json({ response: result.data });
   } catch (error) {
     res.status(500).json({ error: error.message });
   }
@@ -124,7 +124,7 @@ export async function POST(request: NextRequest) {
     });
 
     const result = await myAgent.run(message);
-    return NextResponse.json({ response: result.result });
+    return NextResponse.json({ response: result.data });
   } catch (error) {
     return NextResponse.json({ error: error.message }, { status: 500 });
   }
@@ -173,7 +173,7 @@ export const handler: APIGatewayProxyHandler = async (event, context) => {
         "Content-Type": "application/json",
         "Access-Control-Allow-Origin": "*",
       },
-      body: JSON.stringify({ response: result.result }),
+      body: JSON.stringify({ response: result.data }),
     };
   } catch (error) {
     return {
@@ -222,7 +222,7 @@ export const handler: Handler = async (event, context) => {
     
     return {
       statusCode: 200,
-      body: JSON.stringify({ response: result.result }),
+      body: JSON.stringify({ response: result.data }),
     };
   } catch (error) {
     return {

apps/next/src/content/docs/llamaindex/integration/mcp-toolbox.mdx

@@ -0,0 +1,85 @@
+---
+title: MCP Toolbox For Databases
+description: MCP Toolbox for Databases is an open source MCP server for databases.
+---
+
+# MCP Toolbox for Databases
+
+[MCP Toolbox for Databases](https://github.com/googleapis/genai-toolbox) is an open source MCP server for databases. It was designed with enterprise-grade and production-quality in mind. It enables you to develop tools easier, faster, and more securely by handling the complexities such as connection pooling, authentication, and more.
+
+Toolbox Tools can be seemlessly integrated with LlamaIndex applications. For more
+information on [getting
+started](https://googleapis.github.io/genai-toolbox/getting-started/local_quickstart_js/) or
+[configuring](https://googleapis.github.io/genai-toolbox/getting-started/configure/)
+Toolbox, see the
+[documentation](https://googleapis.github.io/genai-toolbox/getting-started/introduction/).
+
+![architecture](/images/mcp_db_toolbox.png)
+
+### Configure and deploy
+
+Toolbox is an open source server that you deploy and manage yourself. For more
+instructions on deploying and configuring, see the official Toolbox
+documentation:
+
+* [Installing the Server](https://googleapis.github.io/genai-toolbox/getting-started/introduction/#installing-the-server)
+* [Configuring Toolbox](https://googleapis.github.io/genai-toolbox/getting-started/configure/)
+
+### Install client SDK
+
+LlamaIndex relies on the `@toolbox-sdk/core` node package to use Toolbox. Install the
+package before getting started:
+
+```shell
+npm install @toolbox-sdk/core
+```
+
+### Loading Toolbox Tools
+
+Once your Toolbox server is configured and up and running, you can load tools
+from your server using the SDK:
+
+```javascript
+import { gemini, GEMINI_MODEL } from "@llamaindex/google";
+import { agent } from "@llamaindex/workflow";
+import { tool } from "llamaindex";
+import { ToolboxClient } from "@toolbox-sdk/core";
+
+// Initialize LLM
+const llm = gemini({
+  model: GEMINI_MODEL.GEMINI_2_0_FLASH,
+  apiKey: process.env.GOOGLE_API_KEY,
+});
+
+// Replace with your Toolbox Server URL
+const URL = 'https://127.0.0.1:5000';
+
+const client = new ToolboxClient("http://127.0.0.1:5000");
+const toolboxTools = await client.loadToolset("my-toolset");
+
+const getTool = (toolboxTool) => tool({
+  name: toolboxTool.getName(),
+  description: toolboxTool.getDescription(),
+  parameters: toolboxTool.getParamSchema(),
+  execute: toolboxTool
+});
+const tools = toolboxTools.map(getTool);
+
+const myAgent = agent({
+  tools: tools,
+  llm,
+  memory,
+  systemPrompt: prompt,
+});
+const result = await myAgent.run(query);
+console.log(result);
+```
+
+### Advanced Toolbox Features
+
+Toolbox has a variety of features to make developing Gen AI tools for databases seamless.
+For more information, read more about the following:
+
+- [Authenticated Parameters](https://googleapis.github.io/genai-toolbox/resources/tools/#authenticated-parameters): bind tool inputs to values from OIDC tokens automatically, making it easy to run sensitive queries without potentially leaking data
+- [Authorized Invocations](https://googleapis.github.io/genai-toolbox/resources/tools/#authorized-invocations): restrict access to use a tool based on the users Auth token
+- [OpenTelemetry](https://googleapis.github.io/genai-toolbox/how-to/export_telemetry/): get metrics and tracing from Toolbox with [OpenTelemetry](https://opentelemetry.io/docs/)

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

@@ -1,5 +1,5 @@
 {
   "title": "Integration",
   "description": "See our integrations",
-  "pages": ["open-llm-metry", "lang-trace", "vercel"]
+  "pages": ["open-llm-metry", "lang-trace", "mcp-toolbox", "vercel"]
 }

apps/next/src/content/docs/llamaindex/modules/agents/low-level.mdx

@@ -0,0 +1,164 @@
+---
+title: Low-Level LLM Execution
+---
+
+Sometimes your need more control over LLM interactions than what high-level agents provide. The `llm.exec` method makes it simple for you to make a single LLM call with tools but hides the complexity of executing the tools and generating the tool messages.
+
+## When to Use `llm.exec`
+
+Use `llm.exec` when you need to:
+- Build custom agent logic in [workflow](/docs/llamaindex/modules/agents/workflows) steps
+- Have precise control over message handling and tool execution
+
+## Basic Usage
+
+The `llm.exec` method takes messages and tools as parameter and executes one LLM call.
+The LLM might either request to call one or more of the tools or generate an assistant message as result.
+For each tool call that is requested, `llm.exec` executes it and generates the two tool call messages (call and result). If no tool call is requested, just the assistant message is returned. 
+
+```ts
+import { openai } from "@llamaindex/openai";
+import { ChatMessage, tool } from "llamaindex";
+import z from "zod";
+
+const llm = openai({ model: "gpt-4.1-mini" });
+const messages = [
+  {
+    content: "What's the weather like in San Francisco?",
+    role: "user",
+  } as ChatMessage,
+];
+
+const { newMessages, toolCalls } = await llm.exec({
+  messages,
+  tools: [
+    tool({
+      name: "get_weather",
+      description: "Get the current weather for a location",
+      parameters: z.object({
+        address: z.string().describe("The address"),
+      }),
+      execute: ({ address }) => {
+        return `It's sunny in ${address}!`;
+      },
+    }),
+  ],
+});
+
+// Add the new messages (including tool calls and responses) to your conversation
+messages.push(...newMessages);
+```
+
+> `newMessages` is an array as each tool call generates two messages: a tool call message and the tool call result message.
+
+## Agent Loop Pattern
+
+A common pattern is to use `llm.exec` in a loop until the LLM stops making tool calls:
+
+```ts
+import { openai } from "@llamaindex/openai";
+import { ChatMessage, tool } from "llamaindex";
+import z from "zod";
+
+async function runAgentLoop() {
+  const llm = openai({ model: "gpt-4.1-mini" });
+  const messages = [
+    {
+      content: "What's the weather like in San Francisco?",
+      role: "user",
+    } as ChatMessage,
+  ];
+
+  let exit = false;
+  do {
+    const { newMessages, toolCalls } = await llm.exec({
+      messages,
+      tools: [
+        tool({
+          name: "get_weather",
+          description: "Get the current weather for a location",
+          parameters: z.object({
+            address: z.string().describe("The address"),
+          }),
+          execute: ({ address }) => {
+            return `It's sunny in ${address}!`;
+          },
+        }),
+      ],
+    });
+    
+    console.log(newMessages);
+    messages.push(...newMessages);
+    
+    // Exit when no more tool calls are made
+    exit = toolCalls.length === 0;
+  } while (!exit);
+}
+```
+
+## Streaming Support
+
+For real-time responses, use the `stream` option to get the assistant's response as streamed tokens:
+
+```ts
+import { openai } from "@llamaindex/openai";
+import { tool } from "llamaindex";
+import z from "zod";
+
+async function streamingAgentLoop() {
+  const llm = openai({ model: "gpt-4o-mini" });
+  const messages = [
+    {
+      content: "What's the weather like in San Francisco?",
+      role: "user",
+    } as ChatMessage,
+  ];
+
+  let exit = false;
+  do {
+    const { stream, newMessages, toolCalls } = await llm.exec({
+      messages,
+      tools: [
+        tool({
+          name: "get_weather",
+          description: "Get the current weather for a location",
+          parameters: z.object({
+            address: z.string().describe("The address"),
+          }),
+          execute: ({ address }) => {
+            return `It's sunny in ${address}!`;
+          },
+        }),
+      ],
+      stream: true,
+    });
+    
+    // Stream the response token by token
+    for await (const chunk of stream) {
+      process.stdout.write(chunk.delta);
+    }
+    
+    messages.push(...newMessages());
+    
+    exit = toolCalls.length === 0;
+  } while (!exit);
+}
+```
+
+> `newMessages` is a function when streaming. The reason is that the result only is available after streaming. Calling it before, will throw an error.
+
+## Return Values
+
+`llm.exec` returns an object with:
+
+- **`newMessages`**: Array of new chat messages including the LLM response and any tool call messages (call or result). This is a function return the array when streaming.
+- **`toolCalls`**: Array of tool calls made by the LLM
+- **`stream`**: Async iterable for streaming responses (only when `stream: true`)
+
+## Best Practices
+
+For using `llm.exec` in an agent loop, take care to:
+
+1. **Maintain message history**: Always add `newMessages` to your conversation history
+2. **Set exit conditions**: Implement proper logic to avoid infinite loops
+

apps/next/src/content/docs/llamaindex/modules/agents/meta.json

@@ -1,4 +1,10 @@
 {
   "title": "Agents",
-  "pages": ["tool", "agent_workflow", "workflows", "natural_language_workflow"]
+  "pages": [
+    "tool",
+    "agent_workflow",
+    "workflows",
+    "low-level",
+    "natural_language_workflow"
+  ]
 }

apps/next/src/content/docs/llamaindex/modules/agents/tool/index.mdx

@@ -101,6 +101,9 @@ const agent = agent({
 });
 ```
 
+You can also use [MCP Toolbox for
+Databases](/docs/llamaindex/integration/mcp-toolbox) to interact with MCP tools.
+
 
 ## Function tool
 

apps/next/src/content/docs/llamaindex/modules/data/memory/index.mdx

@@ -106,34 +106,40 @@ const memory = createMemory({
 
 Long-term memory is represented as `Memory Block` objects. These objects contain information that are from previous user sessions or from the beginning of the current conversation. When memory is retrieved (by calling `getLLM`), the short-term and long-term memories are merged together within the given `tokenLimit`. 
 
-Currently, there are two predefined memory blocks:
+Currently, there are three predefined memory blocks:
 
 - `staticBlock`: A memory block that stores a static piece of information.
 - `factExtractionBlock`: A memory block that extracts facts from the chat history.
+- `vectorBlock`: A memory block that stores and retrieves chat messages from a vector database using semantic similarity search. Messages are stored individually and retrieved based on their relevance to recent conversation context. Here we've passed in the `vectorStore` to use to store and retrieve the chat messages.
 
 This sounds a bit complicated, but it's actually quite simple. Let's look at an example:
 
 ```ts
-import { createMemory, factExtractionBlock, staticBlock } from "llamaindex";
+import { createMemory, factExtractionBlock, staticBlock, vectorBlock } from "llamaindex";
+import { QdrantVectorStore } from "@llamaindex/qdrant";
+import { OpenAIEmbedding } from "@llamaindex/openai";
 
 const memoryBlocks= [
   staticBlock({
-    id: "core_info",
     content: "My name is Logan, and I live in Saskatoon. I work at LlamaIndex.",
   }),
   factExtractionBlock({
-    id: "user-extracted_info",
     priority: 1,
     llm: llm,
     maxFacts: 50,
   }),
+  vectorBlock({
+    vectorStore: new QdrantVectorStore({ url: "http://localhost:6333" }),
+    priority: 2,
+  }),
 ];
 ```
 
-Here, we've setup two memory blocks:
+Here, we've setup three memory blocks:
 
-- `core_info`: A static memory block that stores some core information about the user. This information will always be inserted into the memory. The type used is `MessageContent` to support multi-modal content.
-- `extracted_info`: An extracted memory block that will extract information from the chat history. Here we've passed in the `llm` to use to extract facts from the chat history, and set the `maxFacts` to 50. If the number of extracted facts exceeds this limit, the `maxFacts` will be automatically summarized and reduced to leave room for new information.
+- `staticBlock`: A static memory block that stores some core information about the user. This information will always be inserted into the memory. The type used is `MessageContent` to support multi-modal content.
+- `factExtractionBlock`: An extracted memory block that will extract information from the chat history. Here we've passed in the `llm` to use to extract facts from the chat history, and set the `maxFacts` to 50. If the number of extracted facts exceeds this limit, the `maxFacts` will be automatically summarized and reduced to leave room for new information.
+- `vectorBlock`: A vector memory block that will store in a vector database and retrieve them from there. Messages are stored individually and retrieved based on their relevance to recent conversation context. Here we've passed in the `vectorStore` to use to store and retrieve the chat messages.
 
 You'll also notice that we've set the `priority` for the `factExtractionBlock` block. This is used to determine the handling when the memory blocks content (i.e. long-term memory) + short-term memory exceeds the token limit on the `Memory` object.
 
@@ -158,6 +164,46 @@ When memory is retrieved (using `getLLM`), the short-term and long-term memories
 
 The amount of short-term memory included is specified by the `shortTermTokenLimitRatio`. If it's set to `0.7`, 70% of the `tokenLimit` is used for short-term memory (not including the static memory block).
 
+
+#### VectorBlock Configuration Options
+
+The `vectorBlock` offers several configuration options to customize its behavior:
+
+```ts
+vectorBlock({
+  vectorStore: new QdrantVectorStore({ url: "http://localhost:6333" }),
+  priority: 2,
+  retrievalContextWindow: 5, // Number of recent messages to use for context when retrieving
+  formatTemplate: new PromptTemplate({ template: "Context: {{ context }}" }), // Custom formatting template
+  nodePostprocessors: [/* custom postprocessors */], // Apply processing to retrieved nodes
+  queryOptions: {
+    similarityTopK: 3, // Number of top similar results to return (default: 2)
+    mode: VectorStoreQueryMode.DEFAULT, // Query mode for the vector store
+    sessionFilterKey: "session_id", // Metadata key for session filtering (default: "session_id")
+    // Custom filters can be added here - session filter is automatically included
+    filters: {
+      filters: [
+        { key: "custom_field", value: "custom_value", operator: "==" }
+      ],
+      condition: "and"
+    }
+  }
+})
+```
+
+**Key Configuration Options:**
+
+- **`retrievalContextWindow`**: Number of recent messages to consider when creating the retrieval query (default: 5). A larger window provides more context but may be less precise.
+- **`formatTemplate`**: Template for formatting retrieved information before adding to memory. Defaults to a simple context template.
+- **`nodePostprocessors`**: Array of postprocessors to apply to retrieved nodes, useful for filtering or transforming results.
+- **`queryOptions.similarityTopK`**: Number of most similar messages to retrieve from the vector store (default: 2).
+- **`queryOptions.sessionFilterKey`**: Metadata key used to isolate memory between different sessions (default: "session_id").
+- **`queryOptions.filters`**: Additional metadata filters for retrieval. The session filter is automatically added to ensure memory isolation.
+
+**Session Isolation:**
+
+The vectorBlock automatically adds a session filter using the block's ID to ensure that memories from different sessions don't interfere with each other. This filter uses the `sessionFilterKey` (default: "session_id") and can be customized if needed.
+
 ## Persistence with Snapshots
 
 Save and restore memory state:

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

@@ -5,13 +5,13 @@ title: Bedrock
 ## Installation
 
 ```package-install
-npm i llamaindex @llamaindex/community
+npm i llamaindex @llamaindex/aws
 ```
 
 ## Usage
 
 ```ts
-import { BEDROCK_MODELS, Bedrock } from "@llamaindex/community";
+import { BEDROCK_MODELS, Bedrock } from "@llamaindex/aws";
 
 Settings.llm = new Bedrock({
   model: BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
@@ -23,9 +23,19 @@ Settings.llm = new Bedrock({
 });
 ```
 
-Currently only supports Anthropic and Meta models:
+Supported models are listed below (accessible by BEDROCK_MODELS).
 
 ```ts
+AMAZON_TITAN_TG1_LARGE = "amazon.titan-tg1-large";
+AMAZON_TITAN_TEXT_EXPRESS_V1 = "amazon.titan-text-express-v1";
+AI21_J2_GRANDE_INSTRUCT = "ai21.j2-grande-instruct";
+AI21_J2_JUMBO_INSTRUCT = "ai21.j2-jumbo-instruct";
+AI21_J2_MID = "ai21.j2-mid";
+AI21_J2_MID_V1 = "ai21.j2-mid-v1";
+AI21_J2_ULTRA = "ai21.j2-ultra";
+AI21_J2_ULTRA_V1 = "ai21.j2-ultra-v1";
+COHERE_COMMAND_TEXT_V14 = "cohere.command-text-v14";
+
 ANTHROPIC_CLAUDE_INSTANT_1 = "anthropic.claude-instant-v1";
 ANTHROPIC_CLAUDE_2 = "anthropic.claude-v2";
 ANTHROPIC_CLAUDE_2_1 = "anthropic.claude-v2:1";
@@ -33,7 +43,12 @@ ANTHROPIC_CLAUDE_3_SONNET = "anthropic.claude-3-sonnet-20240229-v1:0";
 ANTHROPIC_CLAUDE_3_HAIKU = "anthropic.claude-3-haiku-20240307-v1:0";
 ANTHROPIC_CLAUDE_3_OPUS = "anthropic.claude-3-opus-20240229-v1:0"; // available on us-west-2
 ANTHROPIC_CLAUDE_3_5_SONNET = "anthropic.claude-3-5-sonnet-20240620-v1:0";
+ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "anthropic.claude-3-5-sonnet-20241022-v2:0";
 ANTHROPIC_CLAUDE_3_5_HAIKU = "anthropic.claude-3-5-haiku-20241022-v1:0";
+ANTHROPIC_CLAUDE_3_7_SONNET = "anthropic.claude-3-7-sonnet-20250219-v1:0";
+ANTHROPIC_CLAUDE_4_SONNET = "anthropic.claude-sonnet-4-20250514-v1:0";
+ANTHROPIC_CLAUDE_4_OPUS = "anthropic.claude-opus-4-20250514-v1:0";
+
 META_LLAMA2_13B_CHAT = "meta.llama2-13b-chat-v1";
 META_LLAMA2_70B_CHAT = "meta.llama2-70b-chat-v1";
 META_LLAMA3_8B_INSTRUCT = "meta.llama3-8b-instruct-v1:0";
@@ -45,41 +60,66 @@ META_LLAMA3_2_1B_INSTRUCT = "meta.llama3-2-1b-instruct-v1:0"; // only available
 META_LLAMA3_2_3B_INSTRUCT = "meta.llama3-2-3b-instruct-v1:0"; // only available via inference endpoints (see below)
 META_LLAMA3_2_11B_INSTRUCT = "meta.llama3-2-11b-instruct-v1:0"; // only available via inference endpoints (see below), multimodal and function call supported
 META_LLAMA3_2_90B_INSTRUCT = "meta.llama3-2-90b-instruct-v1:0"; // only available via inference endpoints (see below), multimodal and function call supported
+META_LLAMA3_3_70B_INSTRUCT = "meta.llama3-3-70b-instruct-v1:0";
+
+MISTRAL_7B_INSTRUCT = "mistral.mistral-7b-instruct-v0:2";
+MISTRAL_MIXTRAL_7B_INSTRUCT = "mistral.mixtral-8x7b-instruct-v0:1";
+MISTRAL_MIXTRAL_LARGE_2402 = "mistral.mistral-large-2402-v1:0";
+
 AMAZON_NOVA_PREMIER_1 = "amazon.nova-premier-v1:0";
 AMAZON_NOVA_PRO_1 = "amazon.nova-pro-v1:0";
 AMAZON_NOVA_LITE_1 = "amazon.nova-lite-v1:0";
 AMAZON_NOVA_MICRO_1 = "amazon.nova-micro-v1:0";
 ```
 
-You can also use Bedrock's Inference endpoints by using the model names:
+You can also use Bedrock's Inference endpoints by using the model names (accessible by INFERENCE_BEDROCK_MODELS).
+Note that the region must be set correctly.
 
 ```ts
-// US
+//US
 US_ANTHROPIC_CLAUDE_3_HAIKU = "us.anthropic.claude-3-haiku-20240307-v1:0";
+US_ANTHROPIC_CLAUDE_3_5_HAIKU = "us.anthropic.claude-3-5-haiku-20241022-v1:0";
 US_ANTHROPIC_CLAUDE_3_OPUS = "us.anthropic.claude-3-opus-20240229-v1:0";
 US_ANTHROPIC_CLAUDE_3_SONNET = "us.anthropic.claude-3-sonnet-20240229-v1:0";
 US_ANTHROPIC_CLAUDE_3_5_SONNET = "us.anthropic.claude-3-5-sonnet-20240620-v1:0";
-US_ANTHROPIC_CLAUDE_3_5_SONNET_V2 =
-  "us.anthropic.claude-3-5-sonnet-20241022-v2:0";
+US_ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "us.anthropic.claude-3-5-sonnet-20241022-v2:0";
+US_ANTHROPIC_CLAUDE_3_7_SONNET = "us.anthropic.claude-3-7-sonnet-20250219-v1:0";
+US_ANTHROPIC_CLAUDE_4_SONNET = "us.anthropic.claude-sonnet-4-20250514-v1:0";
+US_ANTHROPIC_CLAUDE_4_OPUS = "us.anthropic.claude-opus-4-20250514-v1:0";
 US_META_LLAMA_3_2_1B_INSTRUCT = "us.meta.llama3-2-1b-instruct-v1:0";
 US_META_LLAMA_3_2_3B_INSTRUCT = "us.meta.llama3-2-3b-instruct-v1:0";
 US_META_LLAMA_3_2_11B_INSTRUCT = "us.meta.llama3-2-11b-instruct-v1:0";
 US_META_LLAMA_3_2_90B_INSTRUCT = "us.meta.llama3-2-90b-instruct-v1:0";
-US_AMAZON_NOVA_PRO_1 = "us.amazon.nova-premier-v1:0";
+US_META_LLAMA_3_3_70B_INSTRUCT = "us.meta.llama3-3-70b-instruct-v1:0";
+US_AMAZON_NOVA_PREMIER_1 = "us.amazon.nova-premier-v1:0";
 US_AMAZON_NOVA_PRO_1 = "us.amazon.nova-pro-v1:0";
 US_AMAZON_NOVA_LITE_1 = "us.amazon.nova-lite-v1:0";
 US_AMAZON_NOVA_MICRO_1 = "us.amazon.nova-micro-v1:0";
 
-// EU
+//EU
 EU_ANTHROPIC_CLAUDE_3_HAIKU = "eu.anthropic.claude-3-haiku-20240307-v1:0";
+EU_ANTHROPIC_CLAUDE_3_5_HAIKU = "eu.anthropic.claude-3-5-haiku-20240307-v1:0";
 EU_ANTHROPIC_CLAUDE_3_SONNET = "eu.anthropic.claude-3-sonnet-20240229-v1:0";
 EU_ANTHROPIC_CLAUDE_3_5_SONNET = "eu.anthropic.claude-3-5-sonnet-20240620-v1:0";
+EU_ANTHROPIC_CLAUDE_3_7_SONNET = "eu.anthropic.claude-3-7-sonnet-20250219-v1:0";
+EU_ANTHROPIC_CLAUDE_4_SONNET = "eu.anthropic.claude-sonnet-4-20250514-v1:0";
+EU_ANTHROPIC_CLAUDE_4_OPUS = "eu.anthropic.claude-opus-4-20250514-v1:0";
 EU_META_LLAMA_3_2_1B_INSTRUCT = "eu.meta.llama3-2-1b-instruct-v1:0";
 EU_META_LLAMA_3_2_3B_INSTRUCT = "eu.meta.llama3-2-3b-instruct-v1:0";
-EU_AMAZON_NOVA_PRO_1 = "eu.amazon.nova-premier-v1:0";
+EU_AMAZON_NOVA_PREMIER_1 = "eu.amazon.nova-premier-v1:0";
 EU_AMAZON_NOVA_PRO_1 = "eu.amazon.nova-pro-v1:0";
 EU_AMAZON_NOVA_LITE_1 = "eu.amazon.nova-lite-v1:0";
 EU_AMAZON_NOVA_MICRO_1 = "eu.amazon.nova-micro-v1:0";
+
+//APAC
+APAC_ANTHROPIC_CLAUDE_3_5_SONNET = "apac.anthropic.claude-3-5-sonnet-20240620-v1:0";
+APAC_ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "apac.anthropic.claude-3-5-sonnet-20241022-v2:0";
+APAC_ANTHROPIC_CLAUDE_3_7_SONNET = "apac.anthropic.claude-3-7-sonnet-20250219-v1:0";
+APAC_ANTHROPIC_CLAUDE_3_HAIKU = "apac.anthropic.claude-3-haiku-20240307-v1:0";
+APAC_ANTHROPIC_CLAUDE_3_SONNET = "apac.anthropic.claude-3-sonnet-20240229-v1:0";
+APAC_AMAZON_NOVA_PRO_1 = "apac.amazon.nova-pro-v1:0";
+APAC_AMAZON_NOVA_LITE_1 = "apac.amazon.nova-lite-v1:0";
+APAC_AMAZON_NOVA_MICRO_1 = "apac.amazon.nova-micro-v1:0";
 ```
 
 Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url format, e.g. `data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==`
@@ -87,10 +127,11 @@ Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url f
 ## Full Example
 
 ```ts
-import { BEDROCK_MODELS, Bedrock } from "llamaindex";
+import { INFERENCE_BEDROCK_MODELS, Bedrock } from "@llamaindex/aws";
 
 Settings.llm = new Bedrock({
-  model: BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
+  model: INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_SONNET,
+  region: "us-east-1",
 });
 
 async function main() {
@@ -119,7 +160,7 @@ async function main() {
 ## Agent Example
 
 ```ts
-import { BEDROCK_MODELS, Bedrock } from "@llamaindex/community";
+import { BEDROCK_MODELS, Bedrock } from "@llamaindex/aws";
 import { tool } from "llamaindex";
 import { agent } from "@llamaindex/workflow";
 import { z } from "zod";

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

@@ -1,5 +1,42 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 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
+
+- llamaindex@0.11.24
+
+## 0.0.184
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.0.183
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.0.182
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
 ## 0.0.181
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.181",
+  "version": "0.0.187",
   "type": "module",
   "private": true,
   "scripts": {

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

@@ -1,5 +1,38 @@
 # @llamaindex/llama-parse-browser-test
 
+## 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
+
+- Updated dependencies [c3bf3c7]
+  - @llamaindex/cloud@4.0.28
+
+## 0.0.82
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.27
+
+## 0.0.81
+
+### Patch Changes
+
+- @llamaindex/cloud@4.0.26
+
 ## 0.0.80
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.80",
+  "version": "0.0.85",
   "type": "module",
   "scripts": {
     "dev": "vite",

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,42 @@
 # @llamaindex/next-agent-test
 
+## 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
+
+- llamaindex@0.11.24
+
+## 0.1.184
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.1.183
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.1.182
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
 ## 0.1.181
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.181",
+  "version": "0.1.187",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,42 @@
 # test-edge-runtime
 
+## 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
+
+- llamaindex@0.11.24
+
+## 0.1.183
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.1.182
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.1.181
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
 ## 0.1.180
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.180",
+  "version": "0.1.186",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,60 @@
 # @llamaindex/next-node-runtime
 
+## 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
+
+- llamaindex@0.11.24
+- @llamaindex/huggingface@0.1.24
+- @llamaindex/readers@3.1.18
+
+## 0.1.53
+
+### Patch Changes
+
+- llamaindex@0.11.23
+- @llamaindex/huggingface@0.1.23
+- @llamaindex/readers@3.1.17
+
+## 0.1.52
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.1.51
+
+### Patch Changes
+
+- llamaindex@0.11.21
+- @llamaindex/huggingface@0.1.22
+- @llamaindex/readers@3.1.16
+
 ## 0.1.50
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.50",
+  "version": "0.1.58",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,42 @@
 # vite-import-llamaindex
 
+## 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
+
+- llamaindex@0.11.24
+
+## 0.0.50
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.0.49
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.0.48
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
 ## 0.0.47
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.47",
+  "version": "0.0.53",
   "type": "module",
   "scripts": {
     "build": "vite build",

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

@@ -1,5 +1,42 @@
 # @llamaindex/waku-query-engine-test
 
+## 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
+
+- llamaindex@0.11.24
+
+## 0.0.184
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.0.183
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.0.182
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
 ## 0.0.181
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.181",
+  "version": "0.0.187",
   "type": "module",
   "private": true,
   "scripts": {

e2e/node/vector-store/pinecone.e2e.ts

@@ -23,7 +23,7 @@ await test("pinecone", async (t) => {
   });
 
   const vectorStore = new PineconeVectorStore({
-    embeddingModel: openaiEmbedding,
+    embedModel: openaiEmbedding,
   });
 
   t.after(async () => {

examples/CHANGELOG.md

@@ -1,5 +1,216 @@
 # examples
 
+## 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
+
+- Updated dependencies [c3bf3c7]
+- Updated dependencies [f9f1de9]
+  - @llamaindex/cloud@4.0.28
+  - @llamaindex/core@0.6.19
+  - llamaindex@0.11.24
+  - @llamaindex/node-parser@2.0.19
+  - @llamaindex/anthropic@0.3.21
+  - @llamaindex/assemblyai@0.1.18
+  - @llamaindex/clip@0.0.70
+  - @llamaindex/cohere@0.0.33
+  - @llamaindex/deepinfra@0.0.70
+  - @llamaindex/discord@0.1.18
+  - @llamaindex/google@0.3.18
+  - @llamaindex/huggingface@0.1.24
+  - @llamaindex/jinaai@0.0.30
+  - @llamaindex/mistral@0.1.19
+  - @llamaindex/mixedbread@0.0.33
+  - @llamaindex/notion@0.1.18
+  - @llamaindex/ollama@0.1.19
+  - @llamaindex/openai@0.4.14
+  - @llamaindex/perplexity@0.0.27
+  - @llamaindex/portkey-ai@0.0.61
+  - @llamaindex/replicate@0.0.61
+  - @llamaindex/bm25-retriever@0.0.8
+  - @llamaindex/astra@0.0.33
+  - @llamaindex/azure@0.1.31
+  - @llamaindex/chroma@0.0.33
+  - @llamaindex/elastic-search@0.1.19
+  - @llamaindex/firestore@1.0.26
+  - @llamaindex/milvus@0.1.28
+  - @llamaindex/mongodb@0.0.34
+  - @llamaindex/pinecone@0.1.19
+  - @llamaindex/postgres@0.0.62
+  - @llamaindex/qdrant@0.1.29
+  - @llamaindex/supabase@0.1.20
+  - @llamaindex/upstash@0.0.33
+  - @llamaindex/weaviate@0.0.34
+  - @llamaindex/vercel@0.1.19
+  - @llamaindex/voyage-ai@1.0.25
+  - @llamaindex/readers@3.1.18
+  - @llamaindex/tools@0.1.9
+  - @llamaindex/workflow@1.1.20
+  - @llamaindex/deepseek@0.0.31
+  - @llamaindex/fireworks@0.0.30
+  - @llamaindex/groq@0.0.86
+  - @llamaindex/together@0.0.30
+  - @llamaindex/vllm@0.0.56
+  - @llamaindex/xai@0.0.17
+
+## 0.3.34
+
+### Patch Changes
+
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/workflow@1.1.19
+  - @llamaindex/core@0.6.18
+  - llamaindex@0.11.23
+  - @llamaindex/cloud@4.0.27
+  - @llamaindex/node-parser@2.0.18
+  - @llamaindex/anthropic@0.3.20
+  - @llamaindex/assemblyai@0.1.17
+  - @llamaindex/clip@0.0.69
+  - @llamaindex/cohere@0.0.32
+  - @llamaindex/deepinfra@0.0.69
+  - @llamaindex/discord@0.1.17
+  - @llamaindex/google@0.3.17
+  - @llamaindex/huggingface@0.1.23
+  - @llamaindex/jinaai@0.0.29
+  - @llamaindex/mistral@0.1.18
+  - @llamaindex/mixedbread@0.0.32
+  - @llamaindex/notion@0.1.17
+  - @llamaindex/ollama@0.1.18
+  - @llamaindex/openai@0.4.13
+  - @llamaindex/perplexity@0.0.26
+  - @llamaindex/portkey-ai@0.0.60
+  - @llamaindex/replicate@0.0.60
+  - @llamaindex/bm25-retriever@0.0.7
+  - @llamaindex/astra@0.0.32
+  - @llamaindex/azure@0.1.30
+  - @llamaindex/chroma@0.0.32
+  - @llamaindex/elastic-search@0.1.18
+  - @llamaindex/firestore@1.0.25
+  - @llamaindex/milvus@0.1.27
+  - @llamaindex/mongodb@0.0.33
+  - @llamaindex/pinecone@0.1.18
+  - @llamaindex/postgres@0.0.61
+  - @llamaindex/qdrant@0.1.28
+  - @llamaindex/supabase@0.1.19
+  - @llamaindex/upstash@0.0.32
+  - @llamaindex/weaviate@0.0.33
+  - @llamaindex/vercel@0.1.18
+  - @llamaindex/voyage-ai@1.0.24
+  - @llamaindex/readers@3.1.17
+  - @llamaindex/tools@0.1.8
+  - @llamaindex/deepseek@0.0.30
+  - @llamaindex/fireworks@0.0.29
+  - @llamaindex/groq@0.0.85
+  - @llamaindex/together@0.0.29
+  - @llamaindex/vllm@0.0.55
+  - @llamaindex/xai@0.0.16
+
+## 0.3.33
+
+### Patch Changes
+
+- Updated dependencies [38da40b]
+  - @llamaindex/core@0.6.17
+  - @llamaindex/cloud@4.0.26
+  - llamaindex@0.11.21
+  - @llamaindex/node-parser@2.0.17
+  - @llamaindex/anthropic@0.3.19
+  - @llamaindex/assemblyai@0.1.16
+  - @llamaindex/clip@0.0.68
+  - @llamaindex/cohere@0.0.31
+  - @llamaindex/deepinfra@0.0.68
+  - @llamaindex/discord@0.1.16
+  - @llamaindex/google@0.3.16
+  - @llamaindex/huggingface@0.1.22
+  - @llamaindex/jinaai@0.0.28
+  - @llamaindex/mistral@0.1.17
+  - @llamaindex/mixedbread@0.0.31
+  - @llamaindex/notion@0.1.16
+  - @llamaindex/ollama@0.1.17
+  - @llamaindex/openai@0.4.12
+  - @llamaindex/perplexity@0.0.25
+  - @llamaindex/portkey-ai@0.0.59
+  - @llamaindex/replicate@0.0.59
+  - @llamaindex/bm25-retriever@0.0.6
+  - @llamaindex/astra@0.0.31
+  - @llamaindex/azure@0.1.29
+  - @llamaindex/chroma@0.0.31
+  - @llamaindex/elastic-search@0.1.17
+  - @llamaindex/firestore@1.0.24
+  - @llamaindex/milvus@0.1.26
+  - @llamaindex/mongodb@0.0.32
+  - @llamaindex/pinecone@0.1.17
+  - @llamaindex/postgres@0.0.60
+  - @llamaindex/qdrant@0.1.27
+  - @llamaindex/supabase@0.1.18
+  - @llamaindex/upstash@0.0.31
+  - @llamaindex/weaviate@0.0.32
+  - @llamaindex/vercel@0.1.17
+  - @llamaindex/voyage-ai@1.0.23
+  - @llamaindex/readers@3.1.16
+  - @llamaindex/tools@0.1.7
+  - @llamaindex/workflow@1.1.17
+  - @llamaindex/deepseek@0.0.29
+  - @llamaindex/fireworks@0.0.28
+  - @llamaindex/groq@0.0.84
+  - @llamaindex/together@0.0.28
+  - @llamaindex/vllm@0.0.54
+  - @llamaindex/xai@0.0.15
+
 ## 0.3.32
 
 ### Patch Changes

examples/agents/memory/vector-block.ts

@@ -0,0 +1,150 @@
+/**
+ * Example: Vector Memory Block
+ *
+ * This example demonstrates how to use the VectorMemoryBlock to store and retrieve
+ * conversation history using vector similarity search. The vector memory block
+ * stores messages in a vector store and can retrieve relevant context based on
+ * semantic similarity to recent messages.
+ */
+
+import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
+import { QdrantVectorStore } from "@llamaindex/qdrant";
+import { createMemory, vectorBlock } from "llamaindex";
+
+// Set up the LLM and embedding model
+const llm = new OpenAI({ model: "gpt-4.1-mini" });
+const embedModel = new OpenAIEmbedding({ model: "text-embedding-3-small" });
+
+// Simulate a conversation with some context
+// This conversation has 8 messages, which is more than the token limit of 100 tokens (set below)
+// The last 4 messages are kept in to short term memory block (as their tokens are in the limit)
+// Whereas the first 5 messages are added to long term memory block (in here we will use the vector memory block with Qdrant)
+const CONVERSATION_TURNS = [
+  //// This is the first 5 messages that are added to long term memory block (vector memory block)
+  {
+    role: "user",
+    content: "Hi, I'm Sarah and I work as a data scientist at Google.",
+  },
+  {
+    role: "assistant",
+    content:
+      "Hello Sarah! It's great to meet you. Data science at Google must be exciting!",
+  },
+  {
+    role: "user",
+    content:
+      "Yes, I specialize in machine learning and natural language processing.",
+  },
+  {
+    role: "assistant",
+    content: "That's impressive! ML and NLP are fascinating fields.",
+  },
+  {
+    role: "user",
+    content:
+      "I have a PhD in Computer Science from Stanford, and I love hiking on weekends.",
+  },
+
+  //// This is the last 4 messages that are added to short term memory block
+  {
+    role: "assistant",
+    content:
+      "Wow, Stanford PhD! And hiking is a great way to unwind from tech work.",
+  },
+  {
+    role: "user",
+    content: "I also have two cats named Whiskers and Mittens.",
+  },
+  {
+    role: "assistant",
+    content:
+      "Cats make wonderful companions! Whiskers and Mittens are cute names.",
+  },
+  {
+    role: "user",
+    content: "Summary information about Sarah and her cats",
+  },
+];
+
+async function main() {
+  console.log("=== Vector Memory Block Example ===\n");
+
+  /**
+   * Create a vector store. You can quickly get a local instance of Qdrant running with Docker:
+   * ```bash
+   * docker pull qdrant/qdrant
+   * docker run -p 6333:6333 qdrant/qdrant
+   * ```
+   *
+   * Go to http://localhost:6333/dashboard#/collections to see your data
+   */
+  const vectorStore = new QdrantVectorStore({
+    url: "http://localhost:6333",
+    embedModel,
+  });
+
+  // Create a vector memory block using the factory function
+  const vectorMemoryBlock = vectorBlock({
+    vectorStore,
+    priority: 5,
+  });
+
+  // Create a memory store with the vector memory block
+  const memory = createMemory([], {
+    llm,
+    memoryBlocks: [vectorMemoryBlock],
+    tokenLimit: 100,
+    shortTermTokenLimitRatio: 0.7,
+  });
+
+  // Store the conversation history in the vector memory
+  console.log(`Adding ${CONVERSATION_TURNS.length} messages to the memory...`);
+  for (const message of CONVERSATION_TURNS) {
+    await memory.add(message);
+  }
+
+  // Retrieve relevant context for the current user request
+  console.log("Retrieving relevant context...");
+  const chatHistory = await memory.getLLM();
+
+  // You will see there's 1 generated context message from vector memory block, and 4 messages from short term memory block
+  console.log("Chat memory:", chatHistory);
+
+  // Now simulate the assistant responding with context
+  console.log("\nAssistant response with context:");
+  const response = await llm.chat({
+    messages: chatHistory,
+  });
+  console.log(response.message.content);
+
+  // Try adding more messages to the memory
+  const newMessages = [
+    {
+      role: "user",
+      content: "Write a long paragraph about weather in Tokyo",
+    },
+    {
+      role: "assistant",
+      content:
+        "The weather in Tokyo is sunny and warm. The temperature is around 20 degrees Celsius. The weather is very nice and the people are friendly.",
+    },
+    {
+      role: "user",
+      content: "What is the weather in Tokyo?",
+    },
+  ];
+  // Add the new messages to the memory
+  for (const message of newMessages) {
+    await memory.add(message);
+  }
+
+  // Try retrieving the new messages
+  const newChatHistory = await memory.getLLM();
+  // You can see now that new chat history will contain the nodes (separated by `\n`) in the
+  // context message that is generated by the vector memory block
+  // The number of retrieved nodes is set by `similarityTopK` in `queryOptions` of `vectorBlock`
+  // (default `similarityTopK` is 2)
+  console.log("New chat history:", newChatHistory);
+}
+
+main().catch(console.error);

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": "0.3.32",
+  "version": "0.3.38",
   "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": "^0.3.18",
-    "@llamaindex/assemblyai": "^0.1.15",
-    "@llamaindex/astra": "^0.0.30",
-    "@llamaindex/azure": "^0.1.28",
-    "@llamaindex/bm25-retriever": "^0.0.5",
-    "@llamaindex/chroma": "^0.0.30",
-    "@llamaindex/clip": "^0.0.67",
-    "@llamaindex/cloud": "^4.0.25",
-    "@llamaindex/cohere": "^0.0.30",
-    "@llamaindex/core": "^0.6.16",
-    "@llamaindex/deepinfra": "^0.0.67",
-    "@llamaindex/deepseek": "^0.0.28",
-    "@llamaindex/discord": "^0.1.15",
-    "@llamaindex/elastic-search": "^0.1.16",
+    "@llamaindex/anthropic": "^0.3.22",
+    "@llamaindex/assemblyai": "^0.1.18",
+    "@llamaindex/astra": "^0.0.33",
+    "@llamaindex/azure": "^0.1.33",
+    "@llamaindex/bm25-retriever": "^0.0.8",
+    "@llamaindex/chroma": "^0.0.33",
+    "@llamaindex/clip": "^0.0.72",
+    "@llamaindex/cloud": "^4.1.1",
+    "@llamaindex/cohere": "^0.0.33",
+    "@llamaindex/core": "^0.6.19",
+    "@llamaindex/deepinfra": "^0.0.72",
+    "@llamaindex/deepseek": "^0.0.34",
+    "@llamaindex/discord": "^0.1.18",
+    "@llamaindex/elastic-search": "^0.1.19",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/firestore": "^1.0.23",
-    "@llamaindex/fireworks": "^0.0.27",
-    "@llamaindex/google": "^0.3.15",
-    "@llamaindex/groq": "^0.0.83",
-    "@llamaindex/huggingface": "^0.1.21",
-    "@llamaindex/jinaai": "^0.0.27",
-    "@llamaindex/milvus": "^0.1.25",
-    "@llamaindex/mistral": "^0.1.16",
-    "@llamaindex/mixedbread": "^0.0.30",
-    "@llamaindex/mongodb": "^0.0.31",
-    "@llamaindex/node-parser": "^2.0.16",
-    "@llamaindex/notion": "^0.1.15",
-    "@llamaindex/ollama": "^0.1.16",
-    "@llamaindex/openai": "^0.4.11",
-    "@llamaindex/perplexity": "^0.0.24",
-    "@llamaindex/pinecone": "^0.1.16",
-    "@llamaindex/portkey-ai": "^0.0.58",
-    "@llamaindex/postgres": "^0.0.59",
-    "@llamaindex/qdrant": "^0.1.26",
-    "@llamaindex/readers": "^3.1.15",
-    "@llamaindex/replicate": "^0.0.58",
-    "@llamaindex/supabase": "^0.1.17",
-    "@llamaindex/together": "^0.0.27",
-    "@llamaindex/tools": "^0.1.6",
-    "@llamaindex/upstash": "^0.0.30",
-    "@llamaindex/vercel": "^0.1.16",
-    "@llamaindex/vllm": "^0.0.53",
-    "@llamaindex/voyage-ai": "^1.0.22",
-    "@llamaindex/weaviate": "^0.0.31",
-    "@llamaindex/workflow": "^1.1.16",
-    "@llamaindex/xai": "^0.0.14",
+    "@llamaindex/firestore": "^1.0.26",
+    "@llamaindex/fireworks": "^0.0.32",
+    "@llamaindex/google": "^0.3.18",
+    "@llamaindex/groq": "^0.0.88",
+    "@llamaindex/huggingface": "^0.1.26",
+    "@llamaindex/jinaai": "^0.0.32",
+    "@llamaindex/milvus": "^0.1.28",
+    "@llamaindex/mistral": "^0.1.19",
+    "@llamaindex/mixedbread": "^0.0.33",
+    "@llamaindex/mongodb": "^0.0.34",
+    "@llamaindex/node-parser": "^2.0.19",
+    "@llamaindex/notion": "^0.1.18",
+    "@llamaindex/ollama": "^0.1.20",
+    "@llamaindex/openai": "^0.4.16",
+    "@llamaindex/perplexity": "^0.0.29",
+    "@llamaindex/pinecone": "^0.1.19",
+    "@llamaindex/portkey-ai": "^0.0.61",
+    "@llamaindex/postgres": "^0.0.62",
+    "@llamaindex/qdrant": "^0.1.29",
+    "@llamaindex/readers": "^3.1.18",
+    "@llamaindex/replicate": "^0.0.61",
+    "@llamaindex/supabase": "^0.1.20",
+    "@llamaindex/together": "^0.0.32",
+    "@llamaindex/tools": "^0.1.9",
+    "@llamaindex/upstash": "^0.0.33",
+    "@llamaindex/vercel": "^0.1.19",
+    "@llamaindex/vllm": "^0.0.58",
+    "@llamaindex/voyage-ai": "^1.0.25",
+    "@llamaindex/weaviate": "^0.0.34",
+    "@llamaindex/workflow": "^1.1.20",
+    "@llamaindex/xai": "^0.0.19",
     "@notionhq/client": "^4.0.0",
     "@pinecone-database/pinecone": "^4.0.0",
     "@vercel/postgres": "^0.10.0",
@@ -65,7 +65,7 @@
     "commander": "^12.1.0",
     "dotenv": "^17.2.0",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.11.20",
+    "llamaindex": "^0.11.26",
     "mongodb": "6.7.0",
     "postgres": "^3.4.4",
     "wikipedia": "^2.1.2",

examples/storage/qdrantdb/with-gemini.ts

@@ -15,7 +15,7 @@ async function main() {
   const vectorStore = new QdrantVectorStore({
     url: process.env.QDRANT_URL,
     apiKey: process.env.QDRANT_API_KEY,
-    embeddingModel: embedding,
+    embedModel: embedding,
     collectionName: "gemini_test",
   });
   const storageContext = await storageContextFromDefaults({ vectorStore });

examples/storage/qdrantdb/with-jina.ts

@@ -16,7 +16,7 @@ async function main() {
   const vectorStore = new QdrantVectorStore({
     url: process.env.QDRANT_URL,
     apiKey: process.env.QDRANT_API_KEY,
-    embeddingModel: embedding,
+    embedModel: embedding,
     collectionName: "jina_test",
   });
   const storageContext = await storageContextFromDefaults({ vectorStore });

packages/autotool/CHANGELOG.md

@@ -1,5 +1,42 @@
 # @llamaindex/autotool
 
+## 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
+
+- llamaindex@0.11.24
+
+## 8.0.23
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 8.0.22
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 8.0.21
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
 ## 8.0.20
 
 ### Patch Changes

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

@@ -1,5 +1,48 @@
 # @llamaindex/autotool-01-node-example
 
+## 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
+
+- llamaindex@0.11.24
+- @llamaindex/autotool@8.0.24
+
+## 0.0.131
+
+### Patch Changes
+
+- llamaindex@0.11.23
+- @llamaindex/autotool@8.0.23
+
+## 0.0.130
+
+### Patch Changes
+
+- llamaindex@0.11.22
+- @llamaindex/autotool@8.0.22
+
+## 0.0.129
+
+### Patch Changes
+
+- llamaindex@0.11.21
+- @llamaindex/autotool@8.0.21
+
 ## 0.0.128
 
 ### 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": "0.0.128"
+  "version": "0.0.134"
 }

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "8.0.20",
+  "version": "8.0.26",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",

packages/cloud/CHANGELOG.md

@@ -1,5 +1,40 @@
 # @llamaindex/cloud
 
+## 4.1.1
+
+### Patch Changes
+
+- 4b51791: Add deprecation to README
+
+## 4.1.0
+
+### Minor Changes
+
+- 049471b: Add deprecation warning
+
+## 4.0.28
+
+### Patch Changes
+
+- c3bf3c7: Adding support for citations to beta agent data schema
+- Updated dependencies [f9f1de9]
+  - @llamaindex/core@0.6.19
+
+## 4.0.27
+
+### Patch Changes
+
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/core@0.6.18
+
+## 4.0.26
+
+### Patch Changes
+
+- Updated dependencies [38da40b]
+  - @llamaindex/core@0.6.17
+
 ## 4.0.25
 
 ### 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": "4.0.25",
+  "version": "4.1.1",
   "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/beta/agent/types.ts

@@ -28,6 +28,29 @@ export type ComparisonOperator =
  */
 export type FilterOperation = RawFilterOperation;
 
+/**
+ * Metadata for an extracted field, including confidence and citation information
+ */
+export interface ExtractedFieldMetadata {
+  /** The confidence score for the field, combined with parsing confidence if applicable */
+  confidence?: number;
+  /** The confidence score for the field based on the extracted text only */
+  extracted_confidence?: number;
+  /** The page number that the field occurred on */
+  page_number?: number;
+  /** The original text this field's value was derived from */
+  matching_text?: string;
+}
+
+/**
+ * Dictionary mapping field names to their metadata
+ * Values can be ExtractedFieldMetadata objects, nested dictionaries, or arrays
+ */
+export type ExtractedFieldMetadataDict = Record<
+  string,
+  ExtractedFieldMetadata | Record<string, unknown> | unknown[]
+>;
+
 /**
  * Base extracted data interface
  */
@@ -35,11 +58,13 @@ export interface ExtractedData<T = unknown> {
   /** The original data that was extracted from the document. For tracking changes. Should not be updated. */
   original_data: T;
   /** The latest state of the data. Will differ if data has been updated. */
-  data?: T;
+  data: T;
   /** The status of the extracted data. Prefer to use the StatusType values, but any string is allowed. */
   status: StatusType | string;
-  /** Confidence scores, if any, for each primitive field in the original_data data. */
-  confidence?: Record<string, unknown>;
+  /** The overall confidence score for the extracted data. */
+  overall_confidence?: number;
+  /** Page links, and perhaps eventually bounding boxes, for individual fields in the extracted data. */
+  field_metadata?: ExtractedFieldMetadataDict;
   /** The ID of the file that was used to extract the data. */
   file_id?: string;
   /** The name of the file that was used to extract the data. */

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

@@ -0,0 +1,777 @@
+# @llamaindex/community
+
+## 0.0.101
+
+### Patch Changes
+
+- Updated dependencies [f9f1de9]
+  - @llamaindex/core@0.6.19
+
+## 0.0.100
+
+### Patch Changes
+
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/core@0.6.18
+
+## 0.0.99
+
+### Patch Changes
+
+- c65a2dc: Deprecate community package and link to AWS package
+
+## 0.0.98
+
+### Patch Changes
+
+- Updated dependencies [9b2e25a]
+  - @llamaindex/core@0.6.4
+  - @llamaindex/env@0.1.30
+
+## 0.0.97
+
+### Patch Changes
+
+- Updated dependencies [3ee8c83]
+  - @llamaindex/core@0.6.3
+
+## 0.0.96
+
+### Patch Changes
+
+- e9bf442: fix: update the tool call schema for nova
+
+## 0.0.95
+
+### Patch Changes
+
+- 411dcea: Add Nova Premier to AWS Nova models. Add EU endpoints
+
+## 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
+
+- Updated dependencies [40ee761]
+  - @llamaindex/core@0.5.8
+
+## 0.0.89
+
+### Patch Changes
+
+- Updated dependencies [4bac71d]
+  - @llamaindex/core@0.5.7
+
+## 0.0.88
+
+### Patch Changes
+
+- e28c29d: Added Llama 3.3 70B Instruct support
+- Updated dependencies [beb922b]
+  - @llamaindex/env@0.1.29
+  - @llamaindex/core@0.5.6
+
+## 0.0.87
+
+### Patch Changes
+
+- Updated dependencies [5668970]
+  - @llamaindex/core@0.5.5
+
+## 0.0.86
+
+### Patch Changes
+
+- Updated dependencies [ad3c7f1]
+  - @llamaindex/core@0.5.4
+
+## 0.0.85
+
+### Patch Changes
+
+- 1914b52: Added Claude 3.7 Sonnet support
+- Updated dependencies [cb021e7]
+  - @llamaindex/core@0.5.3
+
+## 0.0.84
+
+### Patch Changes
+
+- Updated dependencies [d952e68]
+  - @llamaindex/core@0.5.2
+
+## 0.0.83
+
+### Patch Changes
+
+- Updated dependencies [cc50c9c]
+  - @llamaindex/env@0.1.28
+  - @llamaindex/core@0.5.1
+
+## 0.0.82
+
+### Patch Changes
+
+- Updated dependencies [6a4a737]
+- Updated dependencies [d924c63]
+  - @llamaindex/core@0.5.0
+
+## 0.0.81
+
+### Patch Changes
+
+- 1c908fd: Revert previous release (not working with CJS)
+- Updated dependencies [1c908fd]
+  - @llamaindex/core@0.4.23
+  - @llamaindex/env@0.1.27
+
+## 0.0.80
+
+### Patch Changes
+
+- cb608b5: fix: bundle output incorrect
+- Updated dependencies [cb608b5]
+  - @llamaindex/core@0.4.22
+  - @llamaindex/env@0.1.26
+
+## 0.0.79
+
+### Patch Changes
+
+- Updated dependencies [9456616]
+- Updated dependencies [1931bbc]
+  - @llamaindex/core@0.4.21
+
+## 0.0.78
+
+### Patch Changes
+
+- Updated dependencies [d211b7a]
+  - @llamaindex/core@0.4.20
+
+## 0.0.77
+
+### Patch Changes
+
+- 24caf93: fix: added inference profile mapping for nova models"
+- Updated dependencies [a9b5b99]
+  - @llamaindex/core@0.4.19
+
+## 0.0.76
+
+### Patch Changes
+
+- c1850ee: feat: Amazon Nova support via Bedrock
+- Updated dependencies [b504303]
+- Updated dependencies [e0f6cc3]
+  - @llamaindex/env@0.1.25
+  - @llamaindex/core@0.4.18
+
+## 0.0.75
+
+### Patch Changes
+
+- Updated dependencies [3d1808b]
+  - @llamaindex/core@0.4.17
+
+## 0.0.74
+
+### Patch Changes
+
+- 8be4589: chore: bump version
+- Updated dependencies [8be4589]
+  - @llamaindex/core@0.4.16
+  - @llamaindex/env@0.1.24
+
+## 0.0.73
+
+### Patch Changes
+
+- Updated dependencies [d2b2722]
+  - @llamaindex/env@0.1.23
+  - @llamaindex/core@0.4.15
+
+## 0.0.72
+
+### Patch Changes
+
+- Updated dependencies [969365c]
+  - @llamaindex/env@0.1.22
+  - @llamaindex/core@0.4.14
+
+## 0.0.71
+
+### Patch Changes
+
+- 90d265c: chore: bump version
+- Updated dependencies [90d265c]
+  - @llamaindex/core@0.4.13
+  - @llamaindex/env@0.1.21
+
+## 0.0.70
+
+### Patch Changes
+
+- Updated dependencies [ef4f63d]
+  - @llamaindex/core@0.4.12
+
+## 0.0.69
+
+### Patch Changes
+
+- Updated dependencies [6d22fa2]
+  - @llamaindex/core@0.4.11
+
+## 0.0.68
+
+### Patch Changes
+
+- Updated dependencies [a7b0ac3]
+- Updated dependencies [c69605f]
+  - @llamaindex/core@0.4.10
+
+## 0.0.67
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
+## 0.0.66
+
+### Patch Changes
+
+- Updated dependencies [f865c98]
+  - @llamaindex/core@0.4.8
+
+## 0.0.65
+
+### Patch Changes
+
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+  - @llamaindex/core@0.4.7
+
+## 0.0.64
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+  - @llamaindex/env@0.1.20
+  - @llamaindex/core@0.4.6
+
+## 0.0.63
+
+### Patch Changes
+
+- Updated dependencies [ad85bd0]
+  - @llamaindex/core@0.4.5
+  - @llamaindex/env@0.1.19
+
+## 0.0.62
+
+### Patch Changes
+
+- Updated dependencies [a8d3fa6]
+  - @llamaindex/env@0.1.18
+  - @llamaindex/core@0.4.4
+
+## 0.0.61
+
+### Patch Changes
+
+- 487782c: Add missing inference endpoints for Haiku 3.5
+- Updated dependencies [95a5cc6]
+  - @llamaindex/core@0.4.3
+
+## 0.0.60
+
+### Patch Changes
+
+- Updated dependencies [14cc9eb]
+  - @llamaindex/env@0.1.17
+  - @llamaindex/core@0.4.2
+
+## 0.0.59
+
+### Patch Changes
+
+- 47a7c3e: feat: added support for Haiku 3.5 via Bedrock
+
+## 0.0.58
+
+### Patch Changes
+
+- Updated dependencies [9c73f0a]
+  - @llamaindex/core@0.4.1
+
+## 0.0.57
+
+### Patch Changes
+
+- Updated dependencies [359fd33]
+- Updated dependencies [efb7e1b]
+- Updated dependencies [98ba1e7]
+- Updated dependencies [620c63c]
+  - @llamaindex/core@0.4.0
+
+## 0.0.56
+
+### Patch Changes
+
+- Updated dependencies [60b185f]
+  - @llamaindex/core@0.3.7
+
+## 0.0.55
+
+### Patch Changes
+
+- Updated dependencies [691c5bc]
+  - @llamaindex/core@0.3.6
+
+## 0.0.54
+
+### Patch Changes
+
+- Updated dependencies [fa60fc6]
+  - @llamaindex/env@0.1.16
+  - @llamaindex/core@0.3.5
+
+## 0.0.53
+
+### Patch Changes
+
+- Updated dependencies [e2a0876]
+  - @llamaindex/core@0.3.4
+
+## 0.0.52
+
+### Patch Changes
+
+- a5a75f6: feat: added sonnet 3.5 v2
+
+## 0.0.51
+
+### Patch Changes
+
+- Updated dependencies [0493f67]
+  - @llamaindex/core@0.3.3
+
+## 0.0.50
+
+### Patch Changes
+
+- Updated dependencies [4ba2cfe]
+  - @llamaindex/env@0.1.15
+  - @llamaindex/core@0.3.2
+
+## 0.0.49
+
+### Patch Changes
+
+- a75af83: refactor: move some llm and embedding to single package
+- Updated dependencies [ae49ff4]
+- Updated dependencies [a75af83]
+  - @llamaindex/env@0.1.14
+  - @llamaindex/core@0.3.1
+
+## 0.0.48
+
+### Patch Changes
+
+- Updated dependencies [1364e8e]
+- Updated dependencies [96fc69c]
+  - @llamaindex/core@0.3.0
+
+## 0.0.47
+
+### Patch Changes
+
+- Updated dependencies [5f67820]
+  - @llamaindex/core@0.2.12
+
+## 0.0.46
+
+### Patch Changes
+
+- Updated dependencies [ee697fb]
+  - @llamaindex/core@0.2.11
+
+## 0.0.45
+
+### Patch Changes
+
+- Updated dependencies [3489e7d]
+- Updated dependencies [468bda5]
+  - @llamaindex/core@0.2.10
+
+## 0.0.44
+
+### Patch Changes
+
+- Updated dependencies [b17d439]
+  - @llamaindex/core@0.2.9
+
+## 0.0.43
+
+### Patch Changes
+
+- 2774e80: feat: added meta3.2 support via Bedrock including vision, tool call and inference region support
+
+## 0.0.42
+
+### Patch Changes
+
+- df441e2: fix: consoleLogger is missing from `@llamaindex/env`
+- Updated dependencies [df441e2]
+  - @llamaindex/core@0.2.8
+  - @llamaindex/env@0.1.13
+
+## 0.0.41
+
+### Patch Changes
+
+- Updated dependencies [6cce3b1]
+  - @llamaindex/core@0.2.7
+
+## 0.0.40
+
+### Patch Changes
+
+- 50e6b57: feat: add Amazon Bedrock Retriever
+- Updated dependencies [8b7fdba]
+  - @llamaindex/core@0.2.6
+
+## 0.0.39
+
+### Patch Changes
+
+- Updated dependencies [d902cc3]
+  - @llamaindex/core@0.2.5
+
+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [b48bcc3]
+  - @llamaindex/core@0.2.4
+  - @llamaindex/env@0.1.12
+
+## 0.0.37
+
+### Patch Changes
+
+- Updated dependencies [2cd1383]
+  - @llamaindex/core@0.2.3
+
+## 0.0.36
+
+### Patch Changes
+
+- Updated dependencies [749b43a]
+  - @llamaindex/core@0.2.2
+
+## 0.0.35
+
+### Patch Changes
+
+- Updated dependencies [ac07e3c]
+- Updated dependencies [70ccb4a]
+- Updated dependencies [1a6137b]
+- Updated dependencies [ac07e3c]
+  - @llamaindex/core@0.2.1
+  - @llamaindex/env@0.1.11
+
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [11feef8]
+  - @llamaindex/core@0.2.0
+
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [711c814]
+  - @llamaindex/core@0.1.12
+
+## 0.0.32
+
+### Patch Changes
+
+- Updated dependencies [4648da6]
+  - @llamaindex/env@0.1.10
+  - @llamaindex/core@0.1.11
+
+## 0.0.31
+
+### Patch Changes
+
+- Updated dependencies [0148354]
+  - @llamaindex/core@0.1.10
+
+## 0.0.30
+
+### Patch Changes
+
+- Updated dependencies [e27e7dd]
+  - @llamaindex/core@0.1.9
+
+## 0.0.29
+
+### Patch Changes
+
+- 58abc57: fix: align version
+- Updated dependencies [58abc57]
+  - @llamaindex/core@0.1.8
+  - @llamaindex/env@0.1.9
+
+## 0.0.28
+
+### Patch Changes
+
+- Updated dependencies [04b2f8e]
+  - @llamaindex/core@0.1.7
+
+## 0.0.27
+
+### Patch Changes
+
+- Updated dependencies [0452af9]
+  - @llamaindex/core@0.1.6
+
+## 0.0.26
+
+### Patch Changes
+
+- 224d507: fix: prevent tool calling getting mixed with conversation
+- 376d29a: feat: added tool calling and agent support for llama3.1 504B
+
+## 0.0.25
+
+### Patch Changes
+
+- Updated dependencies [91d02a4]
+  - @llamaindex/core@0.1.5
+
+## 0.0.24
+
+### Patch Changes
+
+- 3d9a802: feat: added llama 3.1
+- Updated dependencies [15962b3]
+  - @llamaindex/core@0.1.4
+
+## 0.0.23
+
+### Patch Changes
+
+- Updated dependencies [6cf6ae6]
+  - @llamaindex/core@0.1.3
+
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - @llamaindex/core@0.1.2
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [b3681bf]
+  - @llamaindex/core@0.1.1
+
+## 0.0.20
+
+### Patch Changes
+
+- 56746c2: fix: llama3 patched to handle empty content (can happen with system) and added max tokens export
+
+## 0.0.19
+
+### Patch Changes
+
+- 16ef5dd: refactor: depends on core pacakge instead of llamaindex
+- Updated dependencies [16ef5dd]
+- Updated dependencies [16ef5dd]
+  - @llamaindex/core@0.1.0
+
+## 0.0.18
+
+### Patch Changes
+
+- llamaindex@0.4.14
+
+## 0.0.17
+
+### Patch Changes
+
+- Updated dependencies [e8f8bea]
+- Updated dependencies [304484b]
+  - llamaindex@0.4.13
+
+## 0.0.16
+
+### Patch Changes
+
+- f326ab8: chore: bump version
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+
+## 0.0.15
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
+## 0.0.14
+
+### Patch Changes
+
+- Updated dependencies [7dce3d2]
+  - llamaindex@0.4.10
+
+## 0.0.13
+
+### Patch Changes
+
+- Updated dependencies [3a96a48]
+  - llamaindex@0.4.9
+
+## 0.0.12
+
+### Patch Changes
+
+- Updated dependencies [83ebdfb]
+  - llamaindex@0.4.8
+
+## 0.0.11
+
+### Patch Changes
+
+- Updated dependencies [41fe871]
+- Updated dependencies [321c39d]
+- Updated dependencies [f7f1af0]
+  - llamaindex@0.4.7
+
+## 0.0.10
+
+### Patch Changes
+
+- Updated dependencies [1feb23b]
+- Updated dependencies [08c55ec]
+  - llamaindex@0.4.6
+
+## 0.0.9
+
+### Patch Changes
+
+- Updated dependencies [6c3e5d0]
+  - llamaindex@0.4.5
+
+## 0.0.8
+
+### Patch Changes
+
+- Updated dependencies [42eb73a]
+  - llamaindex@0.4.4
+
+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [2ef62a9]
+  - llamaindex@0.4.3
+
+## 0.0.6
+
+### Patch Changes
+
+- a87a4d1: feat: added tool support calling for Bedrock's Calude and general llm support for agents
+- Updated dependencies [a87a4d1]
+- Updated dependencies [0730140]
+  - llamaindex@0.4.2
+
+## 0.0.5
+
+### Patch Changes
+
+- ed467a9: Add model ids for Anthropic Claude 3.5 Sonnet model on Anthropic and Bedrock
+- Updated dependencies [3c47910]
+- Updated dependencies [ed467a9]
+- Updated dependencies [cba5406]
+  - llamaindex@0.4.1
+
+## 0.0.4
+
+### Patch Changes
+
+- b1a4a74: docs: updated Bedrock Opus region and added a basic README
+- Updated dependencies [436bc41]
+- Updated dependencies [a44e54f]
+- Updated dependencies [a51ed8d]
+- Updated dependencies [d3b635b]
+  - llamaindex@0.4.0
+
+## 0.0.3
+
+### Patch Changes
+
+- Updated dependencies [6bc5bdd]
+- Updated dependencies [bf25ff6]
+- Updated dependencies [e6d6576]
+  - llamaindex@0.3.17
+
+## 0.0.2
+
+### Patch Changes
+
+- 8832669: Community bedrock support added
+- Updated dependencies [11ae926]
+- Updated dependencies [631f000]
+- Updated dependencies [1378ec4]
+- Updated dependencies [6b1ded4]
+- Updated dependencies [4d4bd85]
+- Updated dependencies [24a9d1e]
+- Updated dependencies [45952de]
+- Updated dependencies [54230f0]
+- Updated dependencies [a29d835]
+- Updated dependencies [73819bf]
+  - llamaindex@0.3.16

packages/community/README.md

@@ -0,0 +1,17 @@
+# @llamaindex/community
+
+AWS package for LlamaIndexTS, deprecated, use [@llamaindex/aws](https://www.npmjs.com/package/@llamaindex/aws) instead.
+
+## Current Features:
+
+- Bedrock support for Amazon Nova models Pro, Lite and Micro
+- Bedrock support for the Anthropic Claude Models [usage](https://ts.llamaindex.ai/docs/llamaindex/modules/llms/bedrock) including the latest Sonnet 3.5 v2 and Haiku 3.5
+- Bedrock support for the Meta LLama 2, 3, 3.1 and 3.2 Models [usage](https://ts.llamaindex.ai/docs/llamaindex/modules/llms/bedrock)
+- Meta LLama3.1 405b and Llama3.2 tool call support
+- Meta 3.2 11B and 90B vision support
+- Bedrock support for querying Knowledge Base
+- Bedrock: [Supported Regions and models for cross-region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html)
+
+## LICENSE
+
+MIT

packages/community/package.json

@@ -0,0 +1,53 @@
+{
+  "name": "@llamaindex/community",
+  "description": "Community package for LlamaIndexTS",
+  "version": "0.0.101",
+  "type": "module",
+  "types": "dist/type/index.d.ts",
+  "main": "dist/cjs/index.js",
+  "exports": {
+    ".": {
+      "import": {
+        "types": "./dist/type/index.d.ts",
+        "default": "./dist/index.js"
+      },
+      "require": {
+        "types": "./dist/type/index.d.ts",
+        "default": "./dist/index.cjs"
+      }
+    },
+    "./llm/bedrock": {
+      "import": {
+        "types": "./dist/type/llm/bedrock.d.ts",
+        "default": "./dist/llm/bedrock/index.js"
+      },
+      "require": {
+        "types": "./dist/type/llm/bedrock.d.ts",
+        "default": "./dist/llm/bedrock/index.cjs"
+      }
+    }
+  },
+  "files": [
+    "dist",
+    "CHANGELOG.md",
+    "!**/*.tsbuildinfo"
+  ],
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
+    "directory": "packages/community"
+  },
+  "scripts": {
+    "build": "bunchee",
+    "dev": "bunchee --watch"
+  },
+  "devDependencies": {
+    "@types/node": "^22.9.0"
+  },
+  "dependencies": {
+    "@aws-sdk/client-bedrock-agent-runtime": "^3.706.0",
+    "@aws-sdk/client-bedrock-runtime": "^3.706.0",
+    "@llamaindex/core": "workspace:*",
+    "@llamaindex/env": "workspace:*"
+  }
+}

packages/community/src/index.ts

@@ -0,0 +1,8 @@
+export {
+  BEDROCK_MODELS,
+  BEDROCK_MODEL_MAX_TOKENS,
+  Bedrock,
+  INFERENCE_BEDROCK_MODELS,
+  INFERENCE_TO_BEDROCK_MAP,
+} from "./llm/bedrock/index.js";
+export { AmazonKnowledgeBaseRetriever } from "./retrievers/bedrock.js";

packages/community/src/llm/bedrock/amazon/provider.ts

@@ -0,0 +1,134 @@
+import type {
+  ContentBlockDelta,
+  ConverseOutput,
+  ConverseRequest,
+  ConverseResponse,
+  ConverseStreamOutput,
+  InvokeModelCommandInput,
+  InvokeModelWithResponseStreamCommandInput,
+  ResponseStream,
+} from "@aws-sdk/client-bedrock-runtime";
+import type {
+  BaseTool,
+  ChatMessage,
+  LLMMetadata,
+  ToolCall,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import { toUtf8 } from "../utils";
+
+import { Provider, type BedrockChatStreamResponse } from "../provider";
+import {
+  mapBaseToolsToAmazonTools,
+  mapChatMessagesToAmazonMessages,
+} from "./utils";
+
+export class AmazonProvider extends Provider<ConverseStreamOutput> {
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  getResultFromResponse(response: Record<string, any>): ConverseResponse {
+    return JSON.parse(toUtf8(response.body));
+  }
+
+  getToolsFromResponse<ToolContent>(response: ConverseOutput): ToolContent[] {
+    return (
+      response.message?.content
+        ?.filter((item) => item.toolUse)
+        .map(
+          (item) =>
+            ({
+              id: item.toolUse!.toolUseId,
+              name: item.toolUse!.name,
+              input: item.toolUse!.input
+                ? JSON.parse(item.toolUse!.input as string)
+                : "",
+            }) as ToolContent,
+        ) ?? []
+    );
+  }
+
+  getTextFromResponse(response: ConverseResponse): string {
+    const result = this.getResultFromResponse(response);
+    const content = result.output?.message?.content ?? [];
+    return content.map((item) => item.text).join(" ");
+  }
+
+  getTextFromStreamResponse(response: ResponseStream): string {
+    const event: ConverseStreamOutput | undefined =
+      this.getStreamingEventResponse(response);
+    if (!event || !event.contentBlockDelta) return "";
+    const delta: ContentBlockDelta | undefined = event.contentBlockDelta.delta;
+    return delta?.text || "";
+  }
+
+  async *reduceStream(
+    stream: AsyncIterable<ResponseStream>,
+  ): BedrockChatStreamResponse {
+    let toolId: string | undefined = undefined;
+    let toolName: string | undefined = undefined;
+    for await (const response of stream) {
+      const event = this.getStreamingEventResponse(response);
+      const delta = this.getTextFromStreamResponse(response);
+
+      let options: undefined | ToolCallLLMMessageOptions = undefined;
+      if (event?.contentBlockStart && event.contentBlockStart.start?.toolUse) {
+        toolId = event.contentBlockStart.start?.toolUse.toolUseId;
+        toolName = event.contentBlockStart.start?.toolUse.name;
+        continue;
+      }
+      if (
+        toolId &&
+        toolName &&
+        event?.contentBlockDelta?.delta?.toolUse?.input
+      ) {
+        options = {
+          toolCall: [
+            {
+              id: toolId,
+              name: toolName,
+              input: JSON.parse(event?.contentBlockDelta?.delta?.toolUse.input),
+            } as ToolCall,
+          ],
+        };
+        toolId = undefined;
+        toolName = undefined;
+      }
+
+      if (!delta && !options) continue;
+
+      yield {
+        delta: options ? "" : delta,
+        options,
+        raw: response,
+      };
+    }
+  }
+
+  getRequestBody<T extends ChatMessage>(
+    metadata: LLMMetadata,
+    messages: T[],
+    tools: BaseTool[] = [],
+    options: Omit<ConverseRequest, "modelId" | "messages" | "inferenceConfig">,
+  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
+    const request: Omit<ConverseRequest, "modelId"> = {
+      ...options,
+      messages: mapChatMessagesToAmazonMessages(messages),
+      inferenceConfig: {
+        maxTokens: metadata.maxTokens,
+        temperature: metadata.temperature,
+        topP: metadata.topP,
+      },
+    };
+    if (tools.length) {
+      request.toolConfig = {
+        tools: mapBaseToolsToAmazonTools(tools),
+      };
+    }
+
+    return {
+      modelId: metadata.model,
+      contentType: "application/json",
+      accept: "application/json",
+      body: JSON.stringify(request),
+    };
+  }
+}

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

@@ -0,0 +1,5 @@
+import type { ConverseRequest, Message } from "@aws-sdk/client-bedrock-runtime";
+
+export type AmazonMessages = ConverseRequest["messages"];
+
+export type AmazonMessage = Message;

packages/community/src/llm/bedrock/amazon/utils.ts

@@ -0,0 +1,141 @@
+import type {
+  ImageBlock,
+  ImageFormat,
+  Message,
+  Tool,
+} from "@aws-sdk/client-bedrock-runtime";
+import type {
+  BaseTool,
+  ChatMessage,
+  MessageContentDetail,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+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 = [
+  "image/jpeg",
+  "image/png",
+  "image/webp",
+  "image/gif",
+] as const;
+
+const ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP: Record<
+  (typeof ACCEPTED_IMAGE_MIME_TYPES)[number],
+  ImageFormat
+> = {
+  "image/jpeg": "jpeg",
+  "image/png": "png",
+  "image/webp": "webp",
+  "image/gif": "gif",
+};
+
+export const mapImageContent = (imageUrl: string): ImageBlock => {
+  if (!imageUrl.startsWith("data:"))
+    throw new Error(
+      "For Amazon 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 as keyof typeof ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP,
+    )
+  )
+    throw new Error(
+      `Amazon only accepts the following mimeTypes: ${ACCEPTED_IMAGE_MIME_TYPES.join("\n")}`,
+    );
+
+  return {
+    format:
+      ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP[
+        mimeType as keyof typeof ACCEPTED_IMAGE_MIME_TYPE_FORMAT_MAP
+      ],
+
+    // @ts-expect-error: there's a mistake in the "@aws-sdk/client-bedrock-runtime" compared to the actual api
+    source: { bytes: data },
+  };
+};
+
+export const mapMessageContentDetailToAmazonContent = <
+  T extends MessageContentDetail,
+>(
+  detail: T,
+): Message["content"] => {
+  let content: Message["content"] = [];
+
+  if (detail.type === "text") {
+    content = [{ text: detail.text }];
+  } else if (detail.type === "image_url") {
+    content = [{ image: mapImageContent(detail.image_url.url) }];
+  } else {
+    throw new Error("Unsupported content detail type");
+  }
+  return content;
+};
+
+export const mapChatMessagesToAmazonMessages = <
+  T extends ChatMessage<ToolCallLLMMessageOptions>,
+>(
+  messages: T[],
+): AmazonMessages => {
+  return messages.flatMap((msg: T): AmazonMessage[] => {
+    return mapMessageContentToMessageContentDetails(msg.content).map(
+      (detail: MessageContentDetail): AmazonMessage => {
+        if (msg.options && "toolCall" in msg.options) {
+          return {
+            role: "assistant",
+            content: msg.options.toolCall.map((call) => ({
+              toolUse: {
+                toolUseId: call.id,
+                name: call.name,
+                input: call.input as JSONObject,
+              },
+            })),
+          };
+        }
+        if (msg.options && "toolResult" in msg.options) {
+          return {
+            role: "user",
+            content: [
+              {
+                toolResult: {
+                  toolUseId: msg.options.toolResult.id,
+                  content: [
+                    {
+                      text: msg.options.toolResult.result,
+                    },
+                  ],
+                },
+              },
+            ],
+          };
+        }
+
+        return {
+          role: msg.role === "assistant" ? "assistant" : "user",
+          content: mapMessageContentDetailToAmazonContent(detail),
+        };
+      },
+    );
+  });
+};
+
+export const mapBaseToolsToAmazonTools = (tools?: BaseTool[]): Tool[] => {
+  if (!tools) return [];
+  return tools.map((tool: BaseTool) => {
+    const {
+      metadata: { parameters, ...options },
+    } = tool;
+    return {
+      toolSpec: {
+        ...options,
+        inputSchema: {
+          json: parameters,
+        },
+      },
+    } as Tool;
+  });
+};

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

@@ -0,0 +1,156 @@
+import {
+  type InvokeModelCommandInput,
+  type InvokeModelWithResponseStreamCommandInput,
+  ResponseStream,
+} from "@aws-sdk/client-bedrock-runtime";
+import type {
+  BaseTool,
+  ChatMessage,
+  LLMMetadata,
+  PartialToolCall,
+  ToolCall,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import { type BedrockChatStreamResponse, Provider } from "../provider";
+import { toUtf8 } from "../utils";
+import type {
+  AnthropicAdditionalChatOptions,
+  AnthropicNoneStreamingResponse,
+  AnthropicStreamEvent,
+  AnthropicTextContent,
+  ToolBlock,
+} from "./types";
+
+import {
+  mapBaseToolsToAnthropicTools,
+  mapChatMessagesToAnthropicMessages,
+} from "./utils";
+
+export class AnthropicProvider extends Provider<AnthropicStreamEvent> {
+  getResultFromResponse(
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    response: Record<string, any>,
+  ): AnthropicNoneStreamingResponse {
+    return JSON.parse(toUtf8(response.body));
+  }
+
+  getToolsFromResponse<AnthropicToolContent>(
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    response: Record<string, any>,
+  ): AnthropicToolContent[] {
+    const result = this.getResultFromResponse(response);
+    return result.content
+      .filter((item) => item.type === "tool_use")
+      .map((item) => item as AnthropicToolContent);
+  }
+
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  getTextFromResponse(response: Record<string, any>): string {
+    const result = this.getResultFromResponse(response);
+    return result.content
+      .filter((item) => item.type === "text")
+      .map((item) => (item as AnthropicTextContent).text)
+      .join(" ");
+  }
+
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  getTextFromStreamResponse(response: Record<string, any>): string {
+    const event = this.getStreamingEventResponse(response);
+    if (event?.type === "content_block_delta") {
+      if (event.delta.type === "text_delta") return event.delta.text;
+      if (event.delta.type === "input_json_delta")
+        return event.delta.partial_json;
+    }
+    return "";
+  }
+
+  async *reduceStream(
+    stream: AsyncIterable<ResponseStream>,
+  ): BedrockChatStreamResponse {
+    let collecting = [];
+    let tool: ToolBlock | undefined = undefined;
+    // #TODO this should be broken down into a separate consumer
+    for await (const response of stream) {
+      const delta = this.getTextFromStreamResponse(response);
+      const event = this.getStreamingEventResponse(response);
+      if (
+        event?.type === "content_block_start" &&
+        event.content_block.type === "tool_use"
+      ) {
+        tool = event.content_block;
+        continue;
+      }
+
+      if (
+        event?.type === "content_block_delta" &&
+        event.delta.type === "input_json_delta"
+      ) {
+        collecting.push(event.delta.partial_json);
+      }
+
+      let options: undefined | ToolCallLLMMessageOptions = undefined;
+      if (tool && collecting.length) {
+        const input = collecting.filter((item) => item).join("");
+        // We have all we need to parse the tool_use json
+        if (event?.type === "content_block_stop") {
+          options = {
+            toolCall: [
+              {
+                id: tool.id,
+                name: tool.name,
+                input: JSON.parse(input),
+              } as ToolCall,
+            ],
+          };
+          // reset the collection/tool
+          collecting = [];
+          tool = undefined;
+        } else {
+          options = {
+            toolCall: [
+              {
+                id: tool.id,
+                name: tool.name,
+                input,
+              } as PartialToolCall,
+            ],
+          };
+        }
+      }
+      if (!delta && !options) continue;
+
+      yield {
+        delta: options ? "" : delta,
+        options,
+        raw: response,
+      };
+    }
+  }
+
+  getRequestBody<T extends ChatMessage<ToolCallLLMMessageOptions>>(
+    metadata: LLMMetadata,
+    messages: T[],
+    tools?: BaseTool[],
+    options?: AnthropicAdditionalChatOptions,
+  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
+    const extra: Record<string, unknown> = {};
+    if (options?.toolChoice) {
+      extra["tool_choice"] = options?.toolChoice;
+    }
+    const mapped = mapChatMessagesToAnthropicMessages(messages);
+    return {
+      modelId: metadata.model,
+      contentType: "application/json",
+      accept: "application/json",
+      body: JSON.stringify({
+        anthropic_version: "bedrock-2023-05-31",
+        messages: mapped,
+        tools: mapBaseToolsToAnthropicTools(tools),
+        max_tokens: metadata.maxTokens,
+        temperature: metadata.temperature,
+        top_p: metadata.topP,
+        ...extra,
+      }),
+    };
+  }
+}

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

@@ -0,0 +1,161 @@
+import type { ToolMetadata } from "@llamaindex/core/llms";
+import type { InvocationMetrics } from "../types";
+
+export type ToolChoice =
+  | { type: "any" }
+  | { type: "auto" }
+  | { type: "tool"; name: string };
+
+export interface ThinkingConfigDisabled {
+  type: "disabled";
+}
+
+export interface ThinkingConfigEnabled {
+  budget_tokens: number;
+  type: "enabled";
+}
+
+export type AnthropicAdditionalChatOptions = {
+  toolChoice: ToolChoice;
+  thinking?: ThinkingConfigDisabled | ThinkingConfigEnabled;
+};
+
+type Usage = {
+  input_tokens: number;
+  output_tokens: number;
+};
+
+type Message = {
+  id: string;
+  type: string;
+  role: string;
+  content: string[];
+  model: string;
+  stop_reason: string | null;
+  stop_sequence: string | null;
+  usage: Usage;
+};
+
+export type ToolBlock = {
+  id: string;
+  input: unknown;
+  name: string;
+  type: "tool_use";
+};
+
+export type TextBlock = {
+  type: "text";
+  text: string;
+};
+
+type ContentBlockStart = {
+  type: "content_block_start";
+  index: number;
+  content_block: ToolBlock | TextBlock;
+};
+
+type Delta =
+  | {
+      type: "text_delta";
+      text: string;
+    }
+  | {
+      type: "input_json_delta";
+      partial_json: string;
+    };
+
+type ContentBlockDelta = {
+  type: "content_block_delta";
+  index: number;
+  delta: Delta;
+};
+
+type ContentBlockStop = {
+  type: "content_block_stop";
+  index: number;
+};
+
+type MessageDelta = {
+  type: "message_delta";
+  delta: {
+    stop_reason: string;
+    stop_sequence: string | null;
+  };
+  usage: Usage;
+};
+
+export type MessageStop = {
+  type: "message_stop";
+  "amazon-bedrock-invocationMetrics": InvocationMetrics;
+};
+
+export type AnthropicStreamEvent =
+  | { type: "message_start"; message: Message }
+  | ContentBlockStart
+  | ContentBlockDelta
+  | ContentBlockStop
+  | MessageDelta
+  | MessageStop;
+
+export type AnthropicContent =
+  | AnthropicTextContent
+  | AnthropicImageContent
+  | AnthropicToolContent
+  | AnthropicToolResultContent;
+
+export type AnthropicTextContent = {
+  type: "text";
+  text: string;
+};
+
+export type AnthropicToolContent = {
+  type: "tool_use";
+  id: string;
+  name: string;
+  input: Record<string, unknown>;
+};
+
+export type AnthropicToolResultContent = {
+  type: "tool_result";
+  tool_use_id: string;
+  content: string;
+};
+
+export type AnthropicMediaTypes =
+  | "image/jpeg"
+  | "image/png"
+  | "image/webp"
+  | "image/gif";
+
+export type AnthropicImageSource = {
+  type: "base64";
+  media_type: AnthropicMediaTypes;
+  data: string; // base64 encoded image bytes
+};
+
+export type AnthropicImageContent = {
+  type: "image";
+  source: AnthropicImageSource;
+};
+
+export type AnthropicMessage = {
+  role: "user" | "assistant";
+  content: AnthropicContent[];
+};
+
+export type AnthropicNoneStreamingResponse = {
+  id: string;
+  type: "message";
+  role: "assistant";
+  content: AnthropicContent[];
+  model: string;
+  stop_reason: "end_turn" | "max_tokens" | "stop_sequence";
+  stop_sequence?: string;
+  usage: { input_tokens: number; output_tokens: number };
+};
+
+export type AnthropicTool = {
+  name: string;
+  description: string;
+  input_schema: ToolMetadata["parameters"];
+};

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

@@ -0,0 +1,166 @@
+import type { JSONObject } from "@llamaindex/core/global";
+import type {
+  BaseTool,
+  ChatMessage,
+  MessageContent,
+  MessageContentDetail,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import { mapMessageContentToMessageContentDetails } from "../../utils";
+import { extractDataUrlComponents } from "../utils";
+import type {
+  AnthropicContent,
+  AnthropicImageContent,
+  AnthropicMediaTypes,
+  AnthropicMessage,
+  AnthropicTextContent,
+  AnthropicTool,
+} from "./types.js";
+
+const ACCEPTED_IMAGE_MIME_TYPES = [
+  "image/jpeg",
+  "image/png",
+  "image/webp",
+  "image/gif",
+];
+
+export const mergeNeighboringSameRoleMessages = (
+  messages: AnthropicMessage[],
+): AnthropicMessage[] => {
+  return messages.reduce(
+    (result: AnthropicMessage[], current: AnthropicMessage, index: number) => {
+      if (index > 0 && messages[index - 1]!.role === current.role) {
+        result[result.length - 1]!.content = [
+          ...result[result.length - 1]!.content,
+          ...current.content,
+        ];
+      } else {
+        result.push(current);
+      }
+      return result;
+    },
+    [],
+  );
+};
+
+export const mapMessageContentDetailToAnthropicContent = <
+  T extends MessageContentDetail,
+>(
+  detail: T,
+): AnthropicContent => {
+  let content: AnthropicContent;
+
+  if (detail.type === "text") {
+    content = mapTextContent(detail.text);
+  } else if (detail.type === "image_url") {
+    content = mapImageContent(detail.image_url.url);
+  } else {
+    throw new Error("Unsupported content detail type");
+  }
+  return content;
+};
+
+export const mapMessageContentToAnthropicContent = <T extends MessageContent>(
+  content: T,
+): AnthropicContent[] => {
+  return mapMessageContentToMessageContentDetails(content).map(
+    mapMessageContentDetailToAnthropicContent,
+  );
+};
+
+export const mapBaseToolsToAnthropicTools = (
+  tools?: BaseTool[],
+): AnthropicTool[] => {
+  if (!tools) return [];
+  return tools.map((tool: BaseTool) => {
+    const {
+      metadata: { parameters, ...options },
+    } = tool;
+    return {
+      ...options,
+      input_schema: parameters,
+    };
+  });
+};
+
+export const mapChatMessagesToAnthropicMessages = <
+  T extends ChatMessage<ToolCallLLMMessageOptions>,
+>(
+  messages: T[],
+): AnthropicMessage[] => {
+  const mapped = messages
+    .flatMap((msg: T): AnthropicMessage[] => {
+      if (msg.options && "toolCall" in msg.options) {
+        return [
+          {
+            role: "assistant",
+            content: msg.options.toolCall.map((call) => ({
+              type: "tool_use",
+              id: call.id,
+              name: call.name,
+              input: call.input as JSONObject,
+            })),
+          },
+        ];
+      }
+      if (msg.options && "toolResult" in msg.options) {
+        return [
+          {
+            role: "user",
+            content: [
+              {
+                type: "tool_result",
+                tool_use_id: msg.options.toolResult.id,
+                content: JSON.stringify(msg.options.toolResult.result),
+              },
+            ],
+          },
+        ];
+      }
+      return mapMessageContentToMessageContentDetails(msg.content).map(
+        (detail: MessageContentDetail): AnthropicMessage => {
+          const content = mapMessageContentDetailToAnthropicContent(detail);
+
+          return {
+            role: msg.role === "assistant" ? "assistant" : "user",
+            content: [content],
+          };
+        },
+      );
+    })
+    .filter((message: AnthropicMessage) => {
+      const content = message.content[0]!;
+      if (content.type === "text" && !content.text) return false;
+      if (content.type === "image" && !content.source.data) return false;
+      if (content.type === "image" && message.role === "assistant")
+        return false;
+      return true;
+    });
+
+  return mergeNeighboringSameRoleMessages(mapped);
+};
+
+export const mapTextContent = (text: string): AnthropicTextContent => {
+  return { type: "text", text };
+};
+
+export const mapImageContent = (imageUrl: string): AnthropicImageContent => {
+  if (!imageUrl.startsWith("data:"))
+    throw new Error(
+      "For Anthropic 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 {
+    type: "image",
+    source: {
+      type: "base64",
+      media_type: mimeType as AnthropicMediaTypes,
+      data,
+    },
+  };
+};

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

@@ -0,0 +1,513 @@
+import {
+  BedrockRuntimeClient,
+  type BedrockRuntimeClientConfig,
+  InvokeModelCommand,
+  InvokeModelWithResponseStreamCommand,
+} from "@aws-sdk/client-bedrock-runtime";
+import {
+  type ChatMessage,
+  type ChatResponse,
+  type CompletionResponse,
+  type LLMChatParamsNonStreaming,
+  type LLMChatParamsStreaming,
+  type LLMCompletionParamsNonStreaming,
+  type LLMCompletionParamsStreaming,
+  type LLMMetadata,
+  ToolCallLLM,
+  type ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import { streamConverter } from "@llamaindex/core/utils";
+import {
+  type BedrockAdditionalChatOptions,
+  type BedrockChatStreamResponse,
+  Provider,
+} from "./provider";
+
+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";
+
+// Other providers should go here
+export const PROVIDERS: { [key: string]: Provider } = {
+  anthropic: new AnthropicProvider(),
+  meta: new MetaProvider(),
+  amazon: new AmazonProvider(),
+};
+
+export type BedrockChatParamsStreaming = LLMChatParamsStreaming<
+  BedrockAdditionalChatOptions,
+  ToolCallLLMMessageOptions
+>;
+
+export type BedrockChatParamsNonStreaming = LLMChatParamsNonStreaming<
+  BedrockAdditionalChatOptions,
+  ToolCallLLMMessageOptions
+>;
+
+export type BedrockChatNonStreamResponse =
+  ChatResponse<ToolCallLLMMessageOptions>;
+
+export const BEDROCK_MODELS = {
+  AMAZON_TITAN_TG1_LARGE: "amazon.titan-tg1-large",
+  AMAZON_TITAN_TEXT_EXPRESS_V1: "amazon.titan-text-express-v1",
+  AI21_J2_GRANDE_INSTRUCT: "ai21.j2-grande-instruct",
+  AI21_J2_JUMBO_INSTRUCT: "ai21.j2-jumbo-instruct",
+  AI21_J2_MID: "ai21.j2-mid",
+  AI21_J2_MID_V1: "ai21.j2-mid-v1",
+  AI21_J2_ULTRA: "ai21.j2-ultra",
+  AI21_J2_ULTRA_V1: "ai21.j2-ultra-v1",
+  COHERE_COMMAND_TEXT_V14: "cohere.command-text-v14",
+  ANTHROPIC_CLAUDE_INSTANT_1: "anthropic.claude-instant-v1",
+  ANTHROPIC_CLAUDE_1: "anthropic.claude-v1", // EOF: No longer supported
+  ANTHROPIC_CLAUDE_2: "anthropic.claude-v2",
+  ANTHROPIC_CLAUDE_2_1: "anthropic.claude-v2:1",
+  ANTHROPIC_CLAUDE_3_SONNET: "anthropic.claude-3-sonnet-20240229-v1:0",
+  ANTHROPIC_CLAUDE_3_HAIKU: "anthropic.claude-3-haiku-20240307-v1:0",
+  ANTHROPIC_CLAUDE_3_OPUS: "anthropic.claude-3-opus-20240229-v1:0",
+  ANTHROPIC_CLAUDE_3_5_SONNET: "anthropic.claude-3-5-sonnet-20240620-v1:0",
+  ANTHROPIC_CLAUDE_3_5_SONNET_V2: "anthropic.claude-3-5-sonnet-20241022-v2:0",
+  ANTHROPIC_CLAUDE_3_5_HAIKU: "anthropic.claude-3-5-haiku-20241022-v1:0",
+  ANTHROPIC_CLAUDE_3_7_SONNET: "anthropic.claude-3-7-sonnet-20250219-v1:0",
+  META_LLAMA2_13B_CHAT: "meta.llama2-13b-chat-v1",
+  META_LLAMA2_70B_CHAT: "meta.llama2-70b-chat-v1",
+  META_LLAMA3_8B_INSTRUCT: "meta.llama3-8b-instruct-v1:0",
+  META_LLAMA3_70B_INSTRUCT: "meta.llama3-70b-instruct-v1:0",
+  META_LLAMA3_1_8B_INSTRUCT: "meta.llama3-1-8b-instruct-v1:0",
+  META_LLAMA3_1_70B_INSTRUCT: "meta.llama3-1-70b-instruct-v1:0",
+  META_LLAMA3_1_405B_INSTRUCT: "meta.llama3-1-405b-instruct-v1:0",
+  META_LLAMA3_2_1B_INSTRUCT: "meta.llama3-2-1b-instruct-v1:0",
+  META_LLAMA3_2_3B_INSTRUCT: "meta.llama3-2-3b-instruct-v1:0",
+  META_LLAMA3_2_11B_INSTRUCT: "meta.llama3-2-11b-instruct-v1:0",
+  META_LLAMA3_2_90B_INSTRUCT: "meta.llama3-2-90b-instruct-v1:0",
+  META_LLAMA3_3_70B_INSTRUCT: "meta.llama3-3-70b-instruct-v1:0",
+  MISTRAL_7B_INSTRUCT: "mistral.mistral-7b-instruct-v0:2",
+  MISTRAL_MIXTRAL_7B_INSTRUCT: "mistral.mixtral-8x7b-instruct-v0:1",
+  MISTRAL_MIXTRAL_LARGE_2402: "mistral.mistral-large-2402-v1:0",
+  AMAZON_NOVA_PREMIER_1: "amazon.nova-premier-v1:0",
+  AMAZON_NOVA_PRO_1: "amazon.nova-pro-v1:0",
+  AMAZON_NOVA_LITE_1: "amazon.nova-lite-v1:0",
+  AMAZON_NOVA_MICRO_1: "amazon.nova-micro-v1:0",
+};
+
+export type BEDROCK_MODELS =
+  (typeof BEDROCK_MODELS)[keyof typeof BEDROCK_MODELS];
+
+export const INFERENCE_BEDROCK_MODELS = {
+  US_ANTHROPIC_CLAUDE_3_HAIKU: "us.anthropic.claude-3-haiku-20240307-v1:0",
+  US_ANTHROPIC_CLAUDE_3_5_HAIKU: "us.anthropic.claude-3-5-haiku-20241022-v1:0",
+  US_ANTHROPIC_CLAUDE_3_OPUS: "us.anthropic.claude-3-opus-20240229-v1:0",
+  US_ANTHROPIC_CLAUDE_3_SONNET: "us.anthropic.claude-3-sonnet-20240229-v1:0",
+  US_ANTHROPIC_CLAUDE_3_5_SONNET:
+    "us.anthropic.claude-3-5-sonnet-20240620-v1:0",
+  US_ANTHROPIC_CLAUDE_3_5_SONNET_V2:
+    "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
+  US_ANTHROPIC_CLAUDE_3_7_SONNET:
+    "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+  US_META_LLAMA_3_2_1B_INSTRUCT: "us.meta.llama3-2-1b-instruct-v1:0",
+  US_META_LLAMA_3_2_3B_INSTRUCT: "us.meta.llama3-2-3b-instruct-v1:0",
+  US_META_LLAMA_3_2_11B_INSTRUCT: "us.meta.llama3-2-11b-instruct-v1:0",
+  US_META_LLAMA_3_2_90B_INSTRUCT: "us.meta.llama3-2-90b-instruct-v1:0",
+  US_META_LLAMA_3_3_70B_INSTRUCT: "us.meta.llama3-3-70b-instruct-v1:0",
+  US_AMAZON_NOVA_PREMIER_1: "us.amazon.nova-premier-v1:0",
+  US_AMAZON_NOVA_PRO_1: "us.amazon.nova-pro-v1:0",
+  US_AMAZON_NOVA_LITE_1: "us.amazon.nova-lite-v1:0",
+  US_AMAZON_NOVA_MICRO_1: "us.amazon.nova-micro-v1:0",
+
+  EU_ANTHROPIC_CLAUDE_3_HAIKU: "eu.anthropic.claude-3-haiku-20240307-v1:0",
+  EU_ANTHROPIC_CLAUDE_3_5_HAIKU: "eu.anthropic.claude-3-5-haiku-20240307-v1:0",
+  EU_ANTHROPIC_CLAUDE_3_SONNET: "eu.anthropic.claude-3-sonnet-20240229-v1:0",
+  EU_ANTHROPIC_CLAUDE_3_5_SONNET:
+    "eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
+  EU_ANTHROPIC_CLAUDE_3_7_SONNET:
+    "eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
+  EU_META_LLAMA_3_2_1B_INSTRUCT: "eu.meta.llama3-2-1b-instruct-v1:0",
+  EU_META_LLAMA_3_2_3B_INSTRUCT: "eu.meta.llama3-2-3b-instruct-v1:0",
+  EU_AMAZON_NOVA_PREMIER_1: "eu.amazon.nova-premier-v1:0",
+  EU_AMAZON_NOVA_PRO_1: "eu.amazon.nova-pro-v1:0",
+  EU_AMAZON_NOVA_LITE_1: "eu.amazon.nova-lite-v1:0",
+  EU_AMAZON_NOVA_MICRO_1: "eu.amazon.nova-micro-v1:0",
+};
+
+export type INFERENCE_BEDROCK_MODELS =
+  (typeof INFERENCE_BEDROCK_MODELS)[keyof typeof INFERENCE_BEDROCK_MODELS];
+
+export const INFERENCE_TO_BEDROCK_MAP: Record<
+  INFERENCE_BEDROCK_MODELS,
+  BEDROCK_MODELS
+> = {
+  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_HAIKU]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
+  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_OPUS]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS,
+  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_SONNET]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET,
+  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_SONNET]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
+  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_7_SONNET]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
+  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_SONNET_V2]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
+  [INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_HAIKU]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
+  [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_1B_INSTRUCT]:
+    BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
+  [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_3B_INSTRUCT]:
+    BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
+  [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_11B_INSTRUCT]:
+    BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT,
+  [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_90B_INSTRUCT]:
+    BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT,
+  [INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_3_70B_INSTRUCT]:
+    BEDROCK_MODELS.META_LLAMA3_3_70B_INSTRUCT,
+
+  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_PREMIER_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_PREMIER_1,
+  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_PRO_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
+  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_LITE_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
+  [INFERENCE_BEDROCK_MODELS.US_AMAZON_NOVA_MICRO_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
+
+  [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_HAIKU]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
+  [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_SONNET]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET,
+  [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_5_SONNET]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
+  [INFERENCE_BEDROCK_MODELS.EU_ANTHROPIC_CLAUDE_3_7_SONNET]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
+  [INFERENCE_BEDROCK_MODELS.EU_META_LLAMA_3_2_1B_INSTRUCT]:
+    BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
+  [INFERENCE_BEDROCK_MODELS.EU_META_LLAMA_3_2_3B_INSTRUCT]:
+    BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
+
+  [INFERENCE_BEDROCK_MODELS.EU_AMAZON_NOVA_PREMIER_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_PREMIER_1,
+  [INFERENCE_BEDROCK_MODELS.EU_AMAZON_NOVA_PRO_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
+  [INFERENCE_BEDROCK_MODELS.EU_AMAZON_NOVA_LITE_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
+  [INFERENCE_BEDROCK_MODELS.EU_AMAZON_NOVA_MICRO_1]:
+    BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
+};
+
+/*
+ * Values taken from https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html#model-parameters-claude
+ */
+
+const COMPLETION_MODELS = {
+  [BEDROCK_MODELS.AMAZON_TITAN_TG1_LARGE]: 8000,
+  [BEDROCK_MODELS.AMAZON_TITAN_TEXT_EXPRESS_V1]: 8000,
+  [BEDROCK_MODELS.AI21_J2_GRANDE_INSTRUCT]: 8000,
+  [BEDROCK_MODELS.AI21_J2_JUMBO_INSTRUCT]: 8000,
+  [BEDROCK_MODELS.AI21_J2_MID]: 8000,
+  [BEDROCK_MODELS.AI21_J2_MID_V1]: 8000,
+  [BEDROCK_MODELS.AI21_J2_ULTRA]: 8000,
+  [BEDROCK_MODELS.AI21_J2_ULTRA_V1]: 8000,
+  [BEDROCK_MODELS.COHERE_COMMAND_TEXT_V14]: 4096,
+};
+
+const CHAT_ONLY_MODELS = {
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_INSTANT_1]: 100000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_1]: 100000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_2]: 100000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_2_1]: 200000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET]: 200000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU]: 200000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS]: 200000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET]: 200000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2]: 200000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU]: 200000,
+  [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET]: 200000,
+  [BEDROCK_MODELS.META_LLAMA2_13B_CHAT]: 2048,
+  [BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 4096,
+  [BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 8192,
+  [BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT]: 8192,
+  [BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT]: 128000,
+  [BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT]: 128000,
+  [BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT]: 128000,
+  [BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT]: 131000,
+  [BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT]: 131000,
+  [BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT]: 128000,
+  [BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT]: 128000,
+  [BEDROCK_MODELS.META_LLAMA3_3_70B_INSTRUCT]: 128000,
+  [BEDROCK_MODELS.MISTRAL_7B_INSTRUCT]: 32000,
+  [BEDROCK_MODELS.MISTRAL_MIXTRAL_7B_INSTRUCT]: 32000,
+  [BEDROCK_MODELS.MISTRAL_MIXTRAL_LARGE_2402]: 32000,
+  [BEDROCK_MODELS.AMAZON_NOVA_PREMIER_1]: 300000,
+  [BEDROCK_MODELS.AMAZON_NOVA_PRO_1]: 300000,
+  [BEDROCK_MODELS.AMAZON_NOVA_LITE_1]: 300000,
+  [BEDROCK_MODELS.AMAZON_NOVA_MICRO_1]: 130000,
+};
+
+const BEDROCK_FOUNDATION_LLMS = { ...COMPLETION_MODELS, ...CHAT_ONLY_MODELS };
+
+/*
+ * Only the following models support streaming as
+ * per result of Bedrock.Client.list_foundation_models
+ * https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock/client/list_foundation_models.html
+ */
+export const STREAMING_MODELS = new Set([
+  BEDROCK_MODELS.AMAZON_TITAN_TG1_LARGE,
+  BEDROCK_MODELS.AMAZON_TITAN_TEXT_EXPRESS_V1,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_INSTANT_1,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_1,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_2,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_2_1,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
+  BEDROCK_MODELS.META_LLAMA2_13B_CHAT,
+  BEDROCK_MODELS.META_LLAMA2_70B_CHAT,
+  BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_3_70B_INSTRUCT,
+  BEDROCK_MODELS.MISTRAL_7B_INSTRUCT,
+  BEDROCK_MODELS.MISTRAL_MIXTRAL_7B_INSTRUCT,
+  BEDROCK_MODELS.MISTRAL_MIXTRAL_LARGE_2402,
+  BEDROCK_MODELS.AMAZON_NOVA_PREMIER_1,
+  BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
+  BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
+  BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
+]);
+
+export const TOOL_CALL_MODELS: BEDROCK_MODELS[] = [
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
+  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
+  BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_3_70B_INSTRUCT,
+  BEDROCK_MODELS.AMAZON_NOVA_PREMIER_1,
+  BEDROCK_MODELS.AMAZON_NOVA_PRO_1,
+  BEDROCK_MODELS.AMAZON_NOVA_LITE_1,
+  BEDROCK_MODELS.AMAZON_NOVA_MICRO_1,
+];
+
+const getProvider = (model: string): Provider => {
+  const providerName = model.split(".")[0];
+  if (!providerName) {
+    throw new Error(`Model ${model} is not supported`);
+  }
+  if (!(providerName in PROVIDERS)) {
+    throw new Error(
+      `Provider ${providerName} for model ${model} is not supported`,
+    );
+  }
+  return PROVIDERS[providerName]!;
+};
+
+export type BedrockModelParams = {
+  model: BEDROCK_MODELS | INFERENCE_BEDROCK_MODELS;
+  temperature?: number;
+  topP?: number;
+  maxTokens?: number;
+};
+
+export const BEDROCK_MODEL_MAX_TOKENS: Partial<Record<BEDROCK_MODELS, number>> =
+  {
+    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_SONNET]: 4096,
+    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU]: 4096,
+    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS]: 4096,
+    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET]: 4096,
+    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2]: 8192,
+    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU]: 8192,
+    [BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET]: 8192,
+    [BEDROCK_MODELS.META_LLAMA2_13B_CHAT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_2_11B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_2_90B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_3_70B_INSTRUCT]: 2048,
+  };
+
+const DEFAULT_BEDROCK_PARAMS = {
+  temperature: 0.1,
+  topP: 1,
+  maxTokens: 1024, // required by anthropic
+};
+
+export type BedrockParams = BedrockRuntimeClientConfig & BedrockModelParams;
+
+/**
+ * ToolCallLLM for Bedrock
+ */
+export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
+  private client: BedrockRuntimeClient;
+  protected actualModel: BEDROCK_MODELS | INFERENCE_BEDROCK_MODELS;
+  model: BEDROCK_MODELS;
+  temperature: number;
+  topP: number;
+  maxTokens?: number;
+  provider: Provider;
+  topK?: number;
+
+  // there should be no check for env variables. Bedrock can be authenticated in various ways
+  // AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and AWS_REGION are the env variables used directly by the sdk
+  constructor({
+    temperature,
+    topP,
+    maxTokens,
+    model,
+    ...params
+  }: BedrockParams) {
+    super();
+    this.actualModel = model;
+    this.model = INFERENCE_TO_BEDROCK_MAP[model] ?? model;
+    this.provider = getProvider(this.model);
+    this.maxTokens = maxTokens ?? DEFAULT_BEDROCK_PARAMS.maxTokens;
+    this.temperature = temperature ?? DEFAULT_BEDROCK_PARAMS.temperature;
+    this.topP = topP ?? DEFAULT_BEDROCK_PARAMS.topP;
+    this.client = new BedrockRuntimeClient(params);
+  }
+
+  get supportToolCall(): boolean {
+    return TOOL_CALL_MODELS.includes(this.model);
+  }
+
+  get metadata(): LLMMetadata {
+    // NOTE, Anthropic supports top_k but LLMMetadata does not
+    return {
+      model: this.model,
+      temperature: this.temperature,
+      topP: this.topP,
+      maxTokens: this.maxTokens,
+      contextWindow: BEDROCK_FOUNDATION_LLMS[this.model] ?? 128000,
+      tokenizer: undefined,
+      structuredOutput: false,
+    };
+  }
+
+  protected async nonStreamChat(
+    params: BedrockChatParamsNonStreaming,
+  ): Promise<BedrockChatNonStreamResponse> {
+    if (!this.supportToolCall && params.tools?.length) {
+      console.warn(`The model "${this.model}" doesn't support ToolCall`);
+    }
+    const input = this.provider.getRequestBody(
+      this.metadata,
+      params.messages,
+      params.tools,
+      params.additionalChatOptions,
+    );
+    const command = new InvokeModelCommand(input);
+    command.input.modelId = this.actualModel;
+
+    const response = await this.client.send(command);
+    let options: ToolCallLLMMessageOptions = {};
+    if (this.supportToolCall) {
+      const tools = this.provider.getToolsFromResponse(response);
+      if (tools.length) {
+        options = { toolCall: tools };
+      }
+    }
+    return {
+      raw: response,
+      message: {
+        role: "assistant",
+        content: this.provider.getTextFromResponse(response),
+        options,
+      },
+    };
+  }
+
+  protected async *streamChat(
+    params: BedrockChatParamsStreaming,
+  ): BedrockChatStreamResponse {
+    if (!STREAMING_MODELS.has(this.model))
+      throw new Error(`The model: ${this.model} does not support streaming`);
+
+    if (!this.supportToolCall && params.tools?.length) {
+      console.warn(`The model "${this.model}" doesn't support ToolCall`);
+    }
+
+    const input = this.provider.getRequestBody(
+      this.metadata,
+      params.messages,
+      params.tools,
+      params.additionalChatOptions,
+    );
+    const command = new InvokeModelWithResponseStreamCommand(input);
+    command.input.modelId = this.actualModel;
+
+    const response = await this.client.send(command);
+    if (response.body) yield* this.provider.reduceStream(response.body);
+  }
+
+  chat(params: BedrockChatParamsStreaming): Promise<BedrockChatStreamResponse>;
+  chat(
+    params: BedrockChatParamsNonStreaming,
+  ): Promise<BedrockChatNonStreamResponse>;
+  @wrapLLMEvent
+  async chat(
+    params: BedrockChatParamsStreaming | BedrockChatParamsNonStreaming,
+  ): Promise<BedrockChatStreamResponse | BedrockChatNonStreamResponse> {
+    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 message: ChatMessage = {
+      role: "user",
+      content: mapMessageContentToMessageContentDetails(params.prompt),
+    };
+
+    const input = this.provider.getRequestBody(this.metadata, [message]);
+
+    if (params.stream) {
+      const command = new InvokeModelWithResponseStreamCommand(input);
+      const response = await this.client.send(command);
+      if (response.body)
+        return streamConverter(response.body, (response) => {
+          return {
+            text: this.provider.getTextFromStreamResponse(response),
+            raw: response,
+          };
+        });
+    }
+
+    const command = new InvokeModelCommand(input);
+    const response = await this.client.send(command);
+    return {
+      text: this.provider.getTextFromResponse(response),
+      raw: response,
+    };
+  }
+}

packages/community/src/llm/bedrock/meta/constants.ts

@@ -0,0 +1,3 @@
+export const TOKENS = {
+  TOOL_CALL: "<|python_tag|>",
+};

packages/community/src/llm/bedrock/meta/provider.ts

@@ -0,0 +1,153 @@
+import type {
+  InvokeModelCommandInput,
+  InvokeModelWithResponseStreamCommandInput,
+  ResponseStream,
+} from "@aws-sdk/client-bedrock-runtime";
+import type {
+  BaseTool,
+  ChatMessage,
+  LLMMetadata,
+  ToolCall,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import { toUtf8 } from "../utils";
+import type { MetaNoneStreamingResponse, MetaStreamEvent } from "./types";
+
+import { randomUUID } from "@llamaindex/env";
+import { Provider, type BedrockChatStreamResponse } from "../provider";
+import { TOKENS } from "./constants";
+import {
+  mapChatMessagesToMetaLlama2Messages,
+  mapChatMessagesToMetaLlama3Messages,
+} from "./utils";
+
+export class MetaProvider extends Provider<MetaStreamEvent> {
+  getResultFromResponse(
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    response: Record<string, any>,
+  ): MetaNoneStreamingResponse {
+    return JSON.parse(toUtf8(response.body));
+  }
+
+  getToolsFromResponse<ToolContent>(
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    response: Record<string, any>,
+  ): ToolContent[] {
+    const result = this.getResultFromResponse(response);
+    if (!result.generation.trim().startsWith(TOKENS.TOOL_CALL)) return [];
+    const tool = JSON.parse(
+      result.generation.trim().split(TOKENS.TOOL_CALL)[1]!,
+    );
+    return [
+      {
+        id: randomUUID(),
+        name: tool.name,
+        input: tool.parameters,
+      } as ToolContent,
+    ];
+  }
+
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  getTextFromResponse(response: Record<string, any>): string {
+    const result = this.getResultFromResponse(response);
+    if (result.generation.trim().startsWith(TOKENS.TOOL_CALL)) return "";
+    return result.generation;
+  }
+
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  getTextFromStreamResponse(response: Record<string, any>): string {
+    const event = this.getStreamingEventResponse(response);
+    if (event?.generation) {
+      return event.generation;
+    }
+    return "";
+  }
+
+  async *reduceStream(
+    stream: AsyncIterable<ResponseStream>,
+  ): BedrockChatStreamResponse {
+    const collecting: string[] = [];
+    let toolId: string | undefined = undefined;
+    for await (const response of stream) {
+      const event = this.getStreamingEventResponse(response);
+      const delta = this.getTextFromStreamResponse(response);
+
+      // odd quirk of llama3.1, start token is \n\n
+      if (
+        !toolId &&
+        !event?.generation.trim() &&
+        event?.generation_token_count === 1 &&
+        event?.prompt_token_count !== null
+      )
+        continue;
+
+      if (delta.startsWith(TOKENS.TOOL_CALL)) {
+        toolId = randomUUID();
+        const parts = delta.split(TOKENS.TOOL_CALL).filter((part) => part);
+        collecting.push(...parts);
+        continue;
+      }
+
+      let options: undefined | ToolCallLLMMessageOptions = undefined;
+      if (toolId && event?.stop_reason === "stop") {
+        if (delta) collecting.push(delta);
+        const tool = JSON.parse(collecting.join(""));
+        options = {
+          toolCall: [
+            {
+              id: toolId,
+              name: tool.name,
+              input: tool.parameters,
+            } as ToolCall,
+          ],
+        };
+      } else if (toolId && !event?.stop_reason) {
+        collecting.push(delta);
+        continue;
+      }
+
+      if (!delta && !options) continue;
+
+      yield {
+        delta: options ? "" : delta,
+        options,
+        raw: response,
+      };
+    }
+  }
+
+  getRequestBody<T extends ChatMessage>(
+    metadata: LLMMetadata,
+    messages: T[],
+    tools: BaseTool[] = [],
+  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
+    let prompt: string = "";
+    let images: string[] = [];
+    if (metadata.model.startsWith("meta.llama3")) {
+      const mapped = mapChatMessagesToMetaLlama3Messages({
+        messages,
+        tools,
+        model: metadata.model,
+      });
+      prompt = mapped.prompt;
+      images = mapped.images;
+    } else if (metadata.model.startsWith("meta.llama2")) {
+      prompt = mapChatMessagesToMetaLlama2Messages(messages);
+    } else {
+      throw new Error(`Meta model ${metadata.model} is not supported`);
+    }
+
+    return {
+      modelId: metadata.model,
+      contentType: "application/json",
+      accept: "application/json",
+      body: JSON.stringify({
+        prompt,
+        images: images.length ? images : undefined,
+        max_gen_len: metadata.maxTokens,
+        temperature: metadata.temperature,
+        top_p: metadata.topP,
+      }),
+    };
+  }
+}

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

@@ -0,0 +1,21 @@
+import type { InvocationMetrics } from "../types";
+
+export type MetaTextContent = string;
+
+export type MetaMessage = {
+  role: "user" | "assistant" | "system" | "ipython";
+  content: MetaTextContent;
+};
+
+type MetaResponse = {
+  generation: string;
+  prompt_token_count: number;
+  generation_token_count: number;
+  stop_reason: "stop" | "length";
+};
+
+export type MetaStreamEvent = MetaResponse & {
+  "amazon-bedrock-invocationMetrics": InvocationMetrics;
+};
+
+export type MetaNoneStreamingResponse = MetaResponse;

packages/community/src/llm/bedrock/meta/utils.ts

@@ -0,0 +1,273 @@
+import type {
+  BaseTool,
+  ChatMessage,
+  LLMMetadata,
+  MessageContentTextDetail,
+  ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import { extractDataUrlComponents } from "../utils";
+import { TOKENS } from "./constants";
+import type { MetaMessage } from "./types";
+
+const getToolCallInstructionString = (tool: BaseTool): string => {
+  return `Use the function '${tool.metadata.name}' to '${tool.metadata.description}'`;
+};
+
+const getToolCallParametersString = (tool: BaseTool): string => {
+  return JSON.stringify({
+    name: tool.metadata.name,
+    description: tool.metadata.description,
+    parameters: tool.metadata.parameters
+      ? Object.entries(tool.metadata.parameters.properties).map(
+          ([name, definition]) => ({ [name]: definition }),
+        )
+      : {},
+  });
+};
+
+// ported from https://github.com/meta-llama/llama-agentic-system/blob/main/llama_agentic_system/system_prompt.py
+// NOTE: using json instead of the above xml style tool calling works more reliability
+export const getToolsPrompt_3_1 = (tools?: BaseTool[]) => {
+  if (!tools?.length) return "";
+
+  const customToolParams = tools.map((tool) => {
+    return [
+      getToolCallInstructionString(tool),
+      getToolCallParametersString(tool),
+    ].join("\n\n");
+  });
+
+  return `
+Environment: node
+
+# Tool Instructions
+- Never use ipython, always use javascript in node
+
+Cutting Knowledge Date: December 2023
+Today Date: ${new Date().toLocaleString("en-US", { year: "numeric", month: "long" })} 
+
+You have access to the following functions:
+
+${customToolParams}
+
+Think very carefully before calling functions.
+
+If a you choose to call a function ONLY reply in the following json format:
+{
+  "name": function_name,
+  "parameters": parameters,
+}
+where
+
+{
+  "name": function_name,
+  "parameters": parameters, => a JSON dict with the function argument name as key and function argument value as value.
+}
+
+Here is an example,
+
+{
+  "name": "example_function_name",
+  "parameters": {"example_name": "example_value"}
+}
+
+Reminder:
+- Function calls MUST follow the specified format
+- Required parameters MUST be specified
+- Only call one function at a time
+- Put the entire function call reply on one line
+- Always add your sources when using search results to answer the user query
+  `;
+};
+
+export const getToolsPrompt_3_2 = (tools?: BaseTool[]) => {
+  if (!tools?.length) return "";
+  return `
+You are an expert in composing functions. You are given a question and a set of possible functions.
+Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
+If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
+also point it out. You should only return the function call in tools call sections.
+
+If you decide to invoke any of the function(s), you MUST put it in the format of and start with the token: ${TOKENS.TOOL_CALL}:
+{
+  "name": function_name,
+  "parameters": parameters,
+}
+where
+
+{
+  "name": function_name,
+  "parameters": parameters, => a JSON dict with the function argument name as key and function argument value as value.
+}
+
+Here is an example,
+
+{
+  "name": "example_function_name",
+  "parameters": {"example_name": "example_value"}
+}
+
+Reminder:
+- Function calls MUST follow the specified format
+- Required parameters MUST be specified
+- Only call one function at a time
+- You SHOULD NOT include any other text in the response
+- Put the entire function call reply on one line
+
+Here is a list of functions in JSON format that you can invoke.
+
+${JSON.stringify(tools)}
+`;
+};
+
+export const mapChatRoleToMetaRole = (
+  role: ChatMessage["role"],
+): MetaMessage["role"] => {
+  if (role === "assistant") return "assistant";
+  if (role === "user") return "user";
+  return "system";
+};
+
+export const mapChatMessagesToMetaMessages = <
+  T extends ChatMessage<ToolCallLLMMessageOptions>,
+>(
+  messages: T[],
+): MetaMessage[] => {
+  return messages.flatMap((msg) => {
+    if (msg.options && "toolCall" in msg.options) {
+      return msg.options.toolCall.map((call) => ({
+        role: "assistant",
+        content: JSON.stringify({
+          id: call.id,
+          name: call.name,
+          parameters: call.input,
+        }),
+      }));
+    }
+
+    if (msg.options && "toolResult" in msg.options) {
+      return {
+        role: "ipython",
+        content: JSON.stringify(msg.options.toolResult),
+      };
+    }
+
+    let content: string = "";
+    if (typeof msg.content === "string") {
+      content = msg.content;
+    } else if (msg.content.length) {
+      content = (msg.content[0] as MessageContentTextDetail).text;
+    }
+    return {
+      role: mapChatRoleToMetaRole(msg.role),
+      content,
+    };
+  });
+};
+
+/**
+ * Documentation at https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3
+ */
+export const mapChatMessagesToMetaLlama3Messages = <T extends ChatMessage>({
+  messages,
+  model,
+  tools,
+}: {
+  messages: T[];
+  model: LLMMetadata["model"];
+  tools?: BaseTool[];
+}): { prompt: string; images: string[] } => {
+  const images: string[] = [];
+  const textMessages: T[] = [];
+
+  messages.forEach((message) => {
+    if (Array.isArray(message.content)) {
+      message.content.forEach((content) => {
+        if (content.type === "image_url") {
+          const { base64 } = extractDataUrlComponents(content.image_url.url);
+          images.push(base64);
+        } else {
+          textMessages.push(message);
+        }
+      });
+    } else {
+      textMessages.push(message);
+    }
+  });
+
+  const parts: string[] = [];
+
+  let toolsPrompt = "";
+  if (model.startsWith("meta.llama3-2")) {
+    toolsPrompt = getToolsPrompt_3_2(tools);
+  } else if (model.startsWith("meta.llama3-1")) {
+    toolsPrompt = getToolsPrompt_3_1(tools);
+  }
+  if (toolsPrompt) {
+    parts.push(
+      "<|begin_of_text|>",
+      "<|start_header_id|>system<|end_header_id|>",
+      toolsPrompt,
+      "<|eot_id|>",
+    );
+  }
+
+  const mapped = mapChatMessagesToMetaMessages(messages).map((message) => {
+    return [
+      "<|start_header_id|>",
+      message.role,
+      "<|end_header_id|>",
+      message.content,
+      "<|eot_id|>",
+    ].join("\n");
+  });
+
+  parts.push(
+    "<|begin_of_text|>",
+    ...mapped,
+    "<|start_header_id|>assistant<|end_header_id|>",
+  );
+
+  const prompt = parts.join("\n");
+  return { prompt, images };
+};
+
+/**
+ * Documentation at https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-2
+ */
+export const mapChatMessagesToMetaLlama2Messages = <T extends ChatMessage>(
+  messages: T[],
+): string => {
+  const mapped = mapChatMessagesToMetaMessages(messages);
+  let output = "<s>";
+  let insideInst = false;
+  let needsStartAgain = false;
+  for (const message of mapped) {
+    if (needsStartAgain) {
+      output += "<s>";
+      needsStartAgain = false;
+    }
+    const text = message.content;
+    if (message.role === "system") {
+      if (!insideInst) {
+        output += "[INST] ";
+        insideInst = true;
+      }
+      output += `<<SYS>>\n${text}\n<</SYS>>\n`;
+    } else if (message.role === "user") {
+      output += text;
+      if (insideInst) {
+        output += " [/INST]";
+        insideInst = false;
+      }
+    } else if (message.role === "assistant") {
+      if (insideInst) {
+        output += " [/INST]";
+        insideInst = false;
+      }
+      output += ` ${text} </s>\n`;
+      needsStartAgain = true;
+    }
+  }
+  return output;
+};

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

@@ -0,0 +1,63 @@
+import {
+  type InvokeModelCommandInput,
+  type InvokeModelWithResponseStreamCommandInput,
+  ResponseStream,
+} from "@aws-sdk/client-bedrock-runtime";
+import {
+  type BaseTool,
+  type ChatMessage,
+  type ChatResponseChunk,
+  type LLMMetadata,
+  type ToolCallLLMMessageOptions,
+} from "@llamaindex/core/llms";
+import { streamConverter } from "@llamaindex/core/utils";
+import { toUtf8 } from "./utils";
+
+export type BedrockAdditionalChatOptions = Record<string, unknown>;
+
+export type BedrockChatStreamResponse = AsyncIterable<
+  ChatResponseChunk<ToolCallLLMMessageOptions>
+>;
+
+export abstract class Provider<ProviderStreamEvent extends object = object> {
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  abstract getTextFromResponse(response: Record<string, any>): string;
+
+  // Return tool calls from none streaming calls
+  abstract getToolsFromResponse<T extends object = object>(
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    response: Record<string, any>,
+  ): T[];
+
+  getStreamingEventResponse(
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    response: Record<string, any>,
+  ): ProviderStreamEvent | undefined {
+    return response.chunk?.bytes
+      ? (JSON.parse(toUtf8(response.chunk?.bytes)) as ProviderStreamEvent)
+      : undefined;
+  }
+
+  async *reduceStream(
+    stream: AsyncIterable<ResponseStream>,
+  ): BedrockChatStreamResponse {
+    yield* streamConverter(stream, (response) => {
+      return {
+        delta: this.getTextFromStreamResponse(response),
+        raw: response,
+      };
+    });
+  }
+
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  getTextFromStreamResponse(response: Record<string, any>): string {
+    return this.getTextFromResponse(response);
+  }
+
+  abstract getRequestBody<T extends ChatMessage>(
+    metadata: LLMMetadata,
+    messages: T[],
+    tools?: BaseTool[],
+    options?: BedrockAdditionalChatOptions,
+  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput;
+}

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

@@ -0,0 +1,6 @@
+export type InvocationMetrics = {
+  inputTokenCount: number;
+  outputTokenCount: number;
+  invocationLatency: number;
+  firstByteLatency: number;
+};

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

@@ -0,0 +1,23 @@
+export const toUtf8 = (input: Uint8Array): string =>
+  new TextDecoder("utf-8").decode(input);
+
+export const extractDataUrlComponents = (
+  dataUrl: string,
+): {
+  mimeType: string;
+  base64: string;
+} => {
+  const parts = dataUrl.split(";base64,");
+
+  if (parts.length !== 2 || !parts[0]!.startsWith("data:")) {
+    throw new Error("Invalid data URL");
+  }
+
+  const mimeType = parts[0]!.slice(5);
+  const base64 = parts[1]!;
+
+  return {
+    mimeType,
+    base64,
+  };
+};

packages/community/src/llm/utils.ts

@@ -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 }];
+};

packages/community/src/retrievers/bedrock.ts

@@ -0,0 +1,165 @@
+import type { KnowledgeBaseVectorSearchConfiguration } from "@aws-sdk/client-bedrock-agent-runtime";
+import {
+  BedrockAgentRuntimeClient,
+  type BedrockAgentRuntimeClientConfig,
+  type RetrievalFilter,
+  RetrieveCommand,
+  type SearchType,
+} from "@aws-sdk/client-bedrock-agent-runtime";
+import type { QueryBundle } from "@llamaindex/core/query-engine";
+import { BaseRetriever } from "@llamaindex/core/retriever";
+import { Document, type NodeWithScore } from "@llamaindex/core/schema";
+import { extractText } from "@llamaindex/core/utils";
+
+/**
+ * Interface for the arguments required to initialize an
+ * AmazonKnowledgeBaseRetriever instance.
+ */
+export interface AmazonKnowledgeBaseRetrieverArgs {
+  knowledgeBaseId: string;
+  topK: number;
+  region: string;
+  clientOptions?: BedrockAgentRuntimeClientConfig;
+  filter?: RetrievalFilter;
+  overrideSearchType?: SearchType;
+}
+
+/**
+ * Class for interacting with Amazon Bedrock Knowledge Bases, a RAG workflow oriented service
+ * Extends the BaseRetriever class.
+ * @example
+ * ```typescript
+ * const retriever = new AmazonKnowledgeBaseRetriever({
+ *   topK: 10,
+ *   knowledgeBaseId: "YOUR_KNOWLEDGE_BASE_ID",
+ *   region: "us-east-2",
+ *   clientOptions: {
+ *     credentials: {
+ *       accessKeyId: "YOUR_ACCESS_KEY_ID",
+ *       secretAccessKey: "YOUR_SECRET_ACCESS_KEY",
+ *     },
+ *   },
+ * });
+ *
+ * const docs = await retriever.retrieve({query: "How are clouds formed?"});
+ * ```
+ */
+export class AmazonKnowledgeBaseRetriever extends BaseRetriever {
+  static lc_name() {
+    return "AmazonKnowledgeBaseRetriever";
+  }
+
+  lc_namespace = ["llamaindex", "retrievers", "amazon_bedrock_knowledge_base"];
+
+  knowledgeBaseId: string;
+
+  topK: number;
+
+  bedrockAgentRuntimeClient: BedrockAgentRuntimeClient;
+
+  filter: RetrievalFilter | undefined;
+
+  overrideSearchType: SearchType | undefined;
+
+  constructor({
+    knowledgeBaseId,
+    topK = 10,
+    clientOptions,
+    region,
+    filter,
+    overrideSearchType,
+  }: AmazonKnowledgeBaseRetrieverArgs) {
+    super();
+
+    this.topK = topK;
+    this.filter = filter;
+    this.overrideSearchType = overrideSearchType;
+    this.bedrockAgentRuntimeClient = new BedrockAgentRuntimeClient({
+      region,
+      ...clientOptions,
+    });
+    this.knowledgeBaseId = knowledgeBaseId;
+  }
+
+  /**
+   * Cleans the result text by replacing sequences of whitespace with a
+   * single space and removing ellipses.
+   * @param resText The result text to clean.
+   * @returns The cleaned result text.
+   */
+  cleanResult(resText: string) {
+    const res = resText.replace(/\s+/g, " ").replace(/\.\.\./g, "");
+    return res;
+  }
+
+  async queryKnowledgeBase(
+    query: QueryBundle,
+    topK: number,
+    filter?: RetrievalFilter,
+    overrideSearchType?: SearchType,
+  ): Promise<NodeWithScore[]> {
+    const retrieveCommand = new RetrieveCommand({
+      knowledgeBaseId: this.knowledgeBaseId,
+      retrievalQuery: {
+        text: extractText(query),
+      },
+      retrievalConfiguration: {
+        vectorSearchConfiguration: {
+          numberOfResults: topK,
+          overrideSearchType,
+          filter,
+        } as KnowledgeBaseVectorSearchConfiguration,
+      },
+    });
+
+    const retrieveResponse =
+      await this.bedrockAgentRuntimeClient.send(retrieveCommand);
+
+    return (
+      retrieveResponse.retrievalResults?.map((result) => {
+        let source;
+        switch (result.location?.type) {
+          case "CONFLUENCE":
+            source = result.location?.confluenceLocation?.url;
+            break;
+          case "S3":
+            source = result.location?.s3Location?.uri;
+            break;
+          case "SALESFORCE":
+            source = result.location?.salesforceLocation?.url;
+            break;
+          case "SHAREPOINT":
+            source = result.location?.sharePointLocation?.url;
+            break;
+          case "WEB":
+            source = result.location?.webLocation?.url;
+            break;
+          default:
+            source = result.location?.s3Location?.uri;
+            break;
+        }
+
+        return {
+          node: new Document({
+            text: this.cleanResult(result.content?.text || ""),
+            metadata: {
+              source,
+              score: result.score,
+              ...result.metadata,
+            },
+          }),
+          score: result.score ?? 1.0,
+        };
+      }) ?? []
+    );
+  }
+
+  async _retrieve(query: QueryBundle): Promise<NodeWithScore[]> {
+    return await this.queryKnowledgeBase(
+      query,
+      this.topK,
+      this.filter,
+      this.overrideSearchType,
+    );
+  }
+}

packages/community/tsconfig.json

@@ -0,0 +1,19 @@
+{
+  "extends": "../../tsconfig.json",
+  "compilerOptions": {
+    "rootDir": "./src",
+    "outDir": "./dist/type",
+    "tsBuildInfoFile": "./dist/.tsbuildinfo",
+    "emitDeclarationOnly": true,
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "types": ["node"]
+  },
+  "include": ["./src"],
+  "exclude": ["node_modules"],
+  "references": [
+    {
+      "path": "../llamaindex/tsconfig.json"
+    }
+  ]
+}

packages/core/CHANGELOG.md

@@ -1,5 +1,24 @@
 # @llamaindex/core
 
+## 0.6.19
+
+### Patch Changes
+
+- f9f1de9: Use logger interface instead of directly hardcoding console.log
+
+## 0.6.18
+
+### Patch Changes
+
+- f29799e: Add toolcall callbacks to agent workflows
+- 7224c06: Add logger and callbacks to llm.exec
+
+## 0.6.17
+
+### Patch Changes
+
+- 38da40b: feat: VectoryMemoryBlock
+
 ## 0.6.16
 
 ### Patch Changes

packages/core/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.6.16",
+  "version": "0.6.19",
   "description": "LlamaIndex Core Module",
   "exports": {
     "./agent": {

packages/core/src/agent/utils.ts

@@ -15,6 +15,7 @@ import type {
 } from "../llms";
 import { baseToolWithCallSchema } from "../schema";
 import {
+  assertIsJSONValue,
   isAsyncIterable,
   prettifyError,
   stringifyJSONToMessageContent,
@@ -227,6 +228,7 @@ export async function callTool(
       `Tool ${tool.metadata.name} (remote:${toolCall.name}) succeeded.`,
     );
     logger.log(`Output: ${JSON.stringify(output)}`);
+    assertIsJSONValue(output);
     const toolOutput: ToolOutput = {
       tool,
       input,

packages/core/src/embeddings/base.ts

@@ -1,3 +1,4 @@
+import { consoleLogger, emptyLogger, type Logger } from "@llamaindex/env";
 import type { Tokenizers } from "@llamaindex/env/tokenizers";
 import type { MessageContentDetail } from "../llms";
 import { BaseNode, MetadataMode, TransformComponent } from "../schema";
@@ -18,6 +19,7 @@ export type EmbeddingInfo = {
 export type BaseEmbeddingOptions = {
   logProgress?: boolean;
   progressCallback?: (current: number, total: number) => void;
+  logger?: Logger;
 };
 
 export abstract class BaseEmbedding extends TransformComponent<
@@ -133,6 +135,9 @@ export async function batchEmbeddings<T>(
 
   const curBatch: T[] = [];
 
+  const logger =
+    options?.logger ?? (options?.logProgress ? consoleLogger : emptyLogger);
+
   for (let i = 0; i < queue.length; i++) {
     curBatch.push(queue[i]!);
     if (i == queue.length - 1 || curBatch.length == chunkSize) {
@@ -143,7 +148,7 @@ export async function batchEmbeddings<T>(
         options?.progressCallback?.(i + 1, queue.length);
       }
       if (options?.logProgress) {
-        console.log(`getting embedding progress: ${i + 1} / ${queue.length}`);
+        logger.log(`getting embedding progress: ${i + 1} / ${queue.length}`);
       }
 
       curBatch.length = 0;

packages/core/src/llms/base.ts

@@ -1,6 +1,7 @@
+import { emptyLogger } from "@llamaindex/env";
 import { extractText } from "../utils/llms";
 import { streamConverter } from "../utils/stream";
-import { callTool, getToolCallsFromResponse } from "./tool-call";
+import { callToolToMessage, getToolCallsFromResponse } from "./tool-call";
 import type {
   ChatMessage,
   ChatResponse,
@@ -99,16 +100,19 @@ export abstract class BaseLLM<
     if (params.stream) {
       return this.streamExec(params);
     }
+    const logger = params.logger ?? emptyLogger;
     const newMessages: ChatMessage<AdditionalMessageOptions>[] = [];
     const response = await this.chat(params);
     newMessages.push(response.message);
     const toolCalls = getToolCallsFromResponse(response);
     if (params.tools && toolCalls.length > 0) {
       for (const toolCall of toolCalls) {
-        const toolResultMessage = await callTool<AdditionalMessageOptions>(
-          params.tools,
-          toolCall,
-        );
+        const toolResultMessage =
+          await callToolToMessage<AdditionalMessageOptions>(
+            params.tools,
+            toolCall,
+            logger,
+          );
         if (toolResultMessage) {
           newMessages.push(toolResultMessage);
         }
@@ -126,6 +130,7 @@ export abstract class BaseLLM<
       AdditionalMessageOptions
     >,
   ): Promise<ExecStreamResponse<AdditionalMessageOptions>> {
+    const logger = params.logger ?? emptyLogger;
     const responseStream = await this.chat(params);
     const iterator = responseStream[Symbol.asyncIterator]();
     const first = await iterator.next();
@@ -220,10 +225,12 @@ export abstract class BaseLLM<
         } as AdditionalMessageOptions,
       });
       for (const toolCall of toolCalls) {
-        const toolResultMessage = await callTool<AdditionalMessageOptions>(
-          params.tools,
-          toolCall,
-        );
+        const toolResultMessage =
+          await callToolToMessage<AdditionalMessageOptions>(
+            params.tools,
+            toolCall,
+            logger,
+          );
         if (toolResultMessage) {
           messages.push(toolResultMessage);
         }

packages/core/src/llms/tool-call.ts

@@ -1,3 +1,5 @@
+import { type Logger } from "@llamaindex/env";
+import { callTool } from "../agent/utils.js";
 import { stringifyJSONToMessageContent } from "../utils";
 import type {
   BaseTool,
@@ -35,27 +37,28 @@ export const getToolCallsFromResponse = (
   return [];
 };
 
-export const callTool = async <
+export const callToolToMessage = async <
   AdditionalMessageOptions extends object = object,
 >(
   tools: BaseTool[],
   toolCall: ToolCall,
+  logger: Logger,
 ): Promise<ChatMessage<AdditionalMessageOptions> | null> => {
   const tool = tools?.find((t) => t.metadata.name === toolCall.name);
-  // TODO: consider using BaseToolWithCall instead of BaseTool to avoid checking for tool.call
-  if (tool && tool.call) {
-    const result = await tool.call(toolCall.input);
-    const toolResultMessage: ChatMessage<AdditionalMessageOptions> = {
-      role: "user",
-      content: stringifyJSONToMessageContent(result),
-      options: {
-        toolResult: {
-          id: toolCall.id,
-          result,
-        },
-      } as AdditionalMessageOptions,
-    };
-    return toolResultMessage;
-  }
-  return null;
+
+  const toolOutput = await callTool(tool, toolCall, logger);
+
+  const toolResultMessage: ChatMessage<AdditionalMessageOptions> = {
+    role: "user",
+    content: stringifyJSONToMessageContent(toolOutput.output),
+    options: {
+      toolResult: {
+        id: toolCall.id,
+        result: toolOutput.output,
+        isError: toolOutput.isError,
+      },
+    } as AdditionalMessageOptions,
+  };
+
+  return toolResultMessage;
 };

packages/core/src/llms/type.ts

@@ -1,3 +1,4 @@
+import type { Logger } from "@llamaindex/env";
 import type { Tokenizers } from "@llamaindex/env/tokenizers";
 import type { JSONSchemaType } from "ajv";
 import { z } from "zod";
@@ -139,6 +140,7 @@ export interface LLMChatParamsBase<
   additionalChatOptions?: AdditionalChatOptions | undefined;
   tools?: BaseTool[] | undefined;
   responseFormat?: z.ZodType | object | undefined;
+  logger?: Logger | undefined;
 }
 
 export interface LLMChatParamsStreaming<

packages/core/src/memory/block/base.ts

@@ -39,7 +39,9 @@ export abstract class BaseMemoryBlock<
    *
    * @returns The memory block content as an array of ChatMessage.
    */
-  abstract get(): Promise<MemoryMessage<TAdditionalMessageOptions>[]>;
+  abstract get(
+    messages?: MemoryMessage<TAdditionalMessageOptions>[],
+  ): Promise<MemoryMessage<TAdditionalMessageOptions>[]>;
 
   /**
    * Store the messages in the memory block.

packages/core/src/memory/block/index.ts

@@ -1,3 +1,4 @@
 export { BaseMemoryBlock } from "./base";
 export { FactExtractionMemoryBlock } from "./fact";
 export { StaticMemoryBlock } from "./static";
+export { VectorMemoryBlock } from "./vector";

packages/core/src/memory/block/vector.ts

@@ -0,0 +1,250 @@
+import type { BaseEmbedding } from "../../embeddings";
+import type { BaseNodePostprocessor } from "../../postprocessor";
+import { BasePromptTemplate, defaultContextSystemPrompt } from "../../prompts";
+import type { NodeWithScore } from "../../schema";
+import { MetadataMode, TextNode } from "../../schema";
+import { extractText } from "../../utils/llms";
+import type {
+  BaseVectorStore,
+  MetadataFilter,
+  VectorStoreQuery,
+} from "../../vector-store";
+import { VectorStoreQueryMode } from "../../vector-store";
+import type { MemoryMessage } from "../types";
+import { BaseMemoryBlock, type MemoryBlockOptions } from "./base";
+
+/**
+ * The options for the vector memory block.
+ */
+export type VectorMemoryBlockOptions = {
+  /**
+   * The vector store to use for retrieval.
+   */
+  vectorStore: BaseVectorStore;
+
+  /**
+   * Maximum number of messages to include for context when retrieving.
+   * @default 5
+   */
+  retrievalContextWindow?: number;
+
+  /**
+   * Template for formatting the retrieved information.
+   * @default new PromptTemplate({ template: "{{ text }}" })
+   */
+  formatTemplate?: BasePromptTemplate;
+
+  /**
+   * List of node postprocessors to apply to the retrieved nodes containing messages.
+   *
+   * @default []
+   */
+  nodePostprocessors?: BaseNodePostprocessor[];
+
+  /**
+   * Configuration options for vector store queries when retrieving memory.
+   *
+   * @default
+   * ```typescript
+   * {
+   *   similarityTopK: 2,                    // Number of top similar results to return
+   *   mode: VectorStoreQueryMode.DEFAULT,   // Query mode for the vector store
+   *   sessionFilterKey: "session_id",       // Metadata key for session filtering
+   *   filters: {
+   *     filters: [
+   *       { key: "session_id", value: "<current block id>", operator: "==" }
+   *     ],
+   *     condition: "and"
+   *   }
+   * }
+   * ```
+   *
+   * Note: A session filter is automatically added to ensure memory isolation between blocks.
+   * If custom filters are provided, the session filter will be merged with them.
+   */
+  queryOptions?: Partial<VectorMemoryBlockQueryOptions>;
+} & MemoryBlockOptions;
+
+export type VectorMemoryBlockQueryOptions = Omit<
+  VectorStoreQuery,
+  "queryEmbedding" | "queryStr"
+> & {
+  sessionFilterKey: string;
+};
+
+/**
+ * A memory block that retrieves relevant information from a vector store.
+ *
+ * This block stores conversation history in a vector store and retrieves
+ * relevant information based on the most recent messages.
+ */
+export class VectorMemoryBlock<
+  TAdditionalMessageOptions extends object = object,
+> extends BaseMemoryBlock<TAdditionalMessageOptions> {
+  private readonly vectorStore: BaseVectorStore;
+  private readonly retrievalContextWindow: number;
+  private readonly formatTemplate: BasePromptTemplate;
+  private readonly nodePostprocessors: BaseNodePostprocessor[];
+  private readonly queryOptions: VectorMemoryBlockQueryOptions;
+
+  constructor(options: VectorMemoryBlockOptions) {
+    super(options);
+
+    // Validate vector store
+    if (!options.vectorStore.storesText) {
+      throw new Error(
+        "vectorStore must store text to be used as a retrieval memory block",
+      );
+    }
+
+    this.vectorStore = options.vectorStore;
+    this.retrievalContextWindow = options.retrievalContextWindow ?? 5;
+    this.queryOptions = this.buildDefaultQueryOptions(options.queryOptions);
+    this.formatTemplate = options.formatTemplate ?? defaultContextSystemPrompt;
+    this.nodePostprocessors = options.nodePostprocessors ?? [];
+  }
+
+  get embedModel(): BaseEmbedding {
+    return this.vectorStore.embedModel;
+  }
+
+  async get(
+    messages: MemoryMessage<TAdditionalMessageOptions>[] = [],
+  ): Promise<MemoryMessage<TAdditionalMessageOptions>[]> {
+    if (messages?.length === 0) return [];
+
+    // Use the last message or a context window of messages for the query
+    let context: MemoryMessage<TAdditionalMessageOptions>[];
+    if (
+      this.retrievalContextWindow > 1 &&
+      messages.length >= this.retrievalContextWindow
+    ) {
+      context = messages.slice(-this.retrievalContextWindow);
+    } else {
+      context = messages;
+    }
+    const queryText = context
+      .map((message) => extractText(message.content))
+      .join("\n\n");
+    if (!queryText) return [];
+
+    // Create and execute the query
+    const queryEmbedding = await this.embedModel.getTextEmbedding(queryText);
+    const query: VectorStoreQuery = {
+      queryStr: queryText,
+      queryEmbedding,
+      ...this.queryOptions,
+    };
+    const results = await this.vectorStore.query(query);
+    if (!results.nodes?.length) return [];
+
+    // Create nodes with scores
+    const nodesWithScores: NodeWithScore[] = results.nodes.map(
+      (node, index) => ({
+        node,
+        score: results.similarities?.[index] ?? undefined,
+      }),
+    );
+
+    // Apply postprocessors
+    let processedNodes = nodesWithScores;
+    for (const postprocessor of this.nodePostprocessors) {
+      processedNodes = await postprocessor.postprocessNodes(
+        processedNodes,
+        queryText,
+      );
+    }
+
+    // Format the results
+    const retrievedText = processedNodes
+      .map(({ node }) => node.getContent(MetadataMode.NONE))
+      .join("\n\n");
+
+    const formattedText = this.formatTemplate.format({
+      context: retrievedText,
+    });
+
+    // Return as memory message
+    return [
+      {
+        id: this.id,
+        role: "memory",
+        content: formattedText,
+      } as MemoryMessage<TAdditionalMessageOptions>,
+    ];
+  }
+
+  async put(
+    messages: MemoryMessage<TAdditionalMessageOptions>[],
+  ): Promise<void> {
+    if (messages.length === 0) return;
+
+    // Format messages with role, text content, and additional info
+    const texts: string[] = [];
+
+    for (const message of messages) {
+      const text = extractText(message.content);
+      if (!text) continue;
+
+      let messageText = text;
+
+      // Add additional info if present
+      const additionalInfo = (message.options ?? {}) as Record<string, unknown>;
+      if (Object.keys(additionalInfo).length > 0) {
+        messageText += `\nAdditional Info: (${JSON.stringify(additionalInfo)})`;
+      }
+
+      texts.push(`<message role='${message.role}'>${messageText}</message>`);
+    }
+
+    if (texts.length === 0) return;
+
+    // Create text node with session metadata
+    const textNode = new TextNode({
+      text: texts.join("\n"),
+      metadata: { [this.queryOptions.sessionFilterKey]: this.id },
+    });
+
+    // Get embedding for the text
+    textNode.embedding = await this.embedModel.getTextEmbedding(textNode.text);
+
+    // Add to vector store
+    await this.vectorStore.add([textNode]);
+  }
+
+  private buildDefaultQueryOptions(
+    options: Partial<VectorMemoryBlockQueryOptions> | undefined,
+  ): VectorMemoryBlockQueryOptions {
+    const {
+      similarityTopK = 2,
+      mode = VectorStoreQueryMode.DEFAULT,
+      sessionFilterKey = "session_id",
+    } = options ?? {};
+
+    let filters = options?.filters;
+
+    const sessionFilter: MetadataFilter = {
+      key: sessionFilterKey,
+      value: this.id,
+      operator: "==",
+    };
+
+    if (filters) {
+      // Only add session_id filter if it doesn't exist in the filters list
+      const sessionIdFilterExists = filters.filters.some(
+        (filter) => filter.key === sessionFilterKey,
+      );
+      if (!sessionIdFilterExists) {
+        filters.filters.push(sessionFilter);
+      }
+    } else {
+      // If no filters are provided, add the session_id filter
+      filters = {
+        filters: [sessionFilter],
+        condition: "and",
+      };
+    }
+
+    return { ...options, similarityTopK, mode, sessionFilterKey, filters };
+  }
+}

packages/core/src/memory/factories.ts

@@ -8,6 +8,10 @@ import {
   StaticMemoryBlock,
   type StaticMemoryBlockOptions,
 } from "./block/static";
+import {
+  VectorMemoryBlock,
+  type VectorMemoryBlockOptions,
+} from "./block/vector";
 import { DEFAULT_TOKEN_LIMIT, Memory, type MemoryOptions } from "./memory";
 import type { MemoryMessage } from "./types";
 
@@ -115,6 +119,17 @@ export function factExtractionBlock<TMessageOptions extends object = object>(
   return new FactExtractionMemoryBlock<TMessageOptions>(options);
 }
 
+/**
+ * create a VectorMemoryBlock
+ * @param options - Configuration options for the vector memory block
+ * @returns A new VectorMemoryBlock instance
+ */
+export function vectorBlock<TMessageOptions extends object = object>(
+  options: VectorMemoryBlockOptions,
+): VectorMemoryBlock<TMessageOptions> {
+  return new VectorMemoryBlock<TMessageOptions>(options);
+}
+
 /**
  * Creates a new Memory instance from a snapshot
  * @param snapshot The snapshot to load from

packages/core/src/memory/memory.ts

@@ -1,3 +1,4 @@
+import { consoleLogger, type Logger } from "@llamaindex/env";
 import { Settings } from "../global";
 import type { ChatMessage, LLM } from "../llms";
 import { extractText } from "../utils";
@@ -31,6 +32,18 @@ export type MemoryOptions<TMessageOptions extends object = object> = {
    * Used internally for memory restoration from snapshots.
    */
   memoryCursor?: number;
+
+  /**
+   * The default LLM to use for memory retrieval.
+   * If not provided, the default `Settings.llm` will be used.
+   * This default LLM can be overridden by the LLM passed in the `getLLM` method.
+   */
+  llm?: LLM | undefined;
+
+  /**
+   * Logger for memory operations
+   */
+  logger?: Logger;
 };
 
 export class Memory<
@@ -65,6 +78,14 @@ export class Memory<
    * The cursor for the messages that have been processed into long-term memory.
    */
   private memoryCursor: number = 0;
+  /**
+   * The default LLM to use for memory retrieval.
+   */
+  private llm: LLM | undefined;
+  /**
+   * Logger for memory operations
+   */
+  private logger: Logger;
 
   constructor(
     messages: MemoryMessage<TMessageOptions>[] = [],
@@ -76,6 +97,8 @@ export class Memory<
       options.shortTermTokenLimitRatio ?? DEFAULT_SHORT_TERM_TOKEN_LIMIT_RATIO;
     this.memoryBlocks = options.memoryBlocks ?? [];
     this.memoryCursor = options.memoryCursor ?? 0;
+    this.logger = options.logger ?? consoleLogger;
+    this.initLLM(options.llm);
 
     this.adapters = {
       ...options.customAdapters,
@@ -84,6 +107,15 @@ export class Memory<
     } as TAdapters & BuiltinAdapters<TMessageOptions>;
   }
 
+  private initLLM(llm: LLM | undefined) {
+    // safe initialize LLM without throwing error if Settings.llm hasn't been set yet
+    try {
+      this.llm = llm ?? Settings.llm;
+    } catch (error) {
+      this.llm = undefined;
+    }
+  }
+
   /**
    * Add a message to the memory
    * @param message - The message to add to the memory
@@ -160,12 +192,13 @@ export class Memory<
   /**
    * Get the messages from the memory, optionally including transient messages.
    * only return messages that are within context window of the LLM
-   * @param llm - To fit the result messages to the context window of the LLM. If not provided, the default token limit will be used.
+   * @param llm - To fit the result messages to the context window of the LLM  (fallback to default llm if not provided).
+   * If llm is not specified in both the constructor and the method, the default token limit will be used.
    * @param transientMessages - Optional transient messages to include.
    * @returns The messages from the memory, optionally including transient messages.
    */
   async getLLM(
-    llm?: LLM,
+    llm: LLM | undefined = this.llm,
     transientMessages?: ChatMessage<TMessageOptions>[],
   ): Promise<ChatMessage[]> {
     // Priority of result messages:
@@ -176,11 +209,20 @@ export class Memory<
       ? Math.ceil(contextWindow * DEFAULT_TOKEN_LIMIT_RATIO)
       : this.tokenLimit;
 
+    let blockInputMessages = this.messages;
+    if (transientMessages && transientMessages.length > 0) {
+      blockInputMessages = [
+        ...this.messages,
+        ...transientMessages.map((m) => this.adapters.llamaindex.toMemory(m)),
+      ];
+    }
+
     // Start with fixed block messages (priority=0)
     // as it must always be included in the retrieval result
     const messages = await this.getMemoryBlockMessages(
       this.memoryBlocks.filter((block) => block.priority === 0),
       tokenLimit,
+      blockInputMessages,
     );
     // remaining token limit for short-term and memory blocks content
     const remainingTokenLimit =
@@ -207,6 +249,7 @@ export class Memory<
     const longTermBlockMessages = await this.getMemoryBlockMessages(
       longTermBlocks,
       memoryBlocksTokenLimit,
+      blockInputMessages,
     );
     messages.push(...longTermBlockMessages);
 
@@ -252,6 +295,7 @@ export class Memory<
   private async getMemoryBlockMessages(
     blocks: BaseMemoryBlock<TMessageOptions>[],
     tokenLimit?: number,
+    messages?: MemoryMessage<TMessageOptions>[],
   ): Promise<ChatMessage<TMessageOptions>[]> {
     if (blocks.length === 0) {
       return [];
@@ -265,7 +309,7 @@ export class Memory<
     let addedTokenCount = 0;
     for (const block of sortedBlocks) {
       try {
-        const content = await block.get();
+        const content = await block.get(messages);
         for (const message of content) {
           const chatMessage = this.adapters.llamaindex.fromMemory(message);
           const messageTokenCount = this.countMessagesToken([chatMessage]);
@@ -276,7 +320,7 @@ export class Memory<
           addedTokenCount += messageTokenCount;
         }
       } catch (error) {
-        console.warn(
+        this.logger.warn(
           `Failed to get content from memory block ${block.id}:`,
           error,
         );
@@ -338,7 +382,7 @@ export class Memory<
       try {
         await block.put(newMessages);
       } catch (error) {
-        console.warn(
+        this.logger.warn(
           `Failed to process messages into memory block ${block.id}:`,
           error,
         );

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

@@ -1,3 +1,4 @@
+import { consoleLogger, type Logger } from "@llamaindex/env";
 import type { Tokenizer } from "@llamaindex/env/tokenizers";
 import { z } from "zod";
 import { Settings } from "../global";
@@ -48,9 +49,11 @@ export class SentenceSplitter extends MetadataAwareTextSplitter {
   #splitFns: Set<TextSplitterFn> = new Set();
   #subSentenceSplitFns: Set<TextSplitterFn> = new Set();
   #tokenizer: Tokenizer;
+  #logger: Logger;
 
   constructor(
-    params?: z.input<typeof sentenceSplitterSchema> & SplitterParams,
+    params?: z.input<typeof sentenceSplitterSchema> &
+      SplitterParams & { logger?: Logger },
   ) {
     super();
     if (params) {
@@ -66,6 +69,7 @@ export class SentenceSplitter extends MetadataAwareTextSplitter {
       this.extraAbbreviations,
     );
     this.#tokenizer = params?.tokenizer ?? Settings.tokenizer;
+    this.#logger = params?.logger ?? consoleLogger;
     this.#splitFns.add(splitBySep(this.paragraphSeparator));
     this.#splitFns.add(this.#chunkingTokenizerFn);
 
@@ -82,7 +86,7 @@ export class SentenceSplitter extends MetadataAwareTextSplitter {
         `Metadata length (${metadataLength}) is longer than chunk size (${this.chunkSize}). Consider increasing the chunk size or decreasing the size of your metadata to avoid this.`,
       );
     } else if (effectiveChunkSize < 50) {
-      console.log(
+      this.#logger.log(
         `Metadata length (${metadataLength}) is close to chunk size (${this.chunkSize}). Resulting chunks are less than 50 tokens. Consider increasing the chunk size or decreasing the size of your metadata to avoid this.`,
       );
     }

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

@@ -1,3 +1,4 @@
+import { consoleLogger, type Logger } from "@llamaindex/env";
 import type { Tokenizer } from "@llamaindex/env/tokenizers";
 import { z } from "zod";
 import { DEFAULT_CHUNK_OVERLAP, DEFAULT_CHUNK_SIZE, Settings } from "../global";
@@ -21,9 +22,11 @@ export class TokenTextSplitter extends MetadataAwareTextSplitter {
   backupSeparators: string[] = ["\n"];
   #tokenizer: Tokenizer;
   #splitFns: Array<(text: string) => string[]> = [];
+  #logger: Logger;
 
   constructor(
-    params?: SplitterParams & Partial<z.infer<typeof tokenTextSplitterSchema>>,
+    params?: SplitterParams &
+      Partial<z.infer<typeof tokenTextSplitterSchema>> & { logger?: Logger },
   ) {
     super();
 
@@ -42,6 +45,7 @@ export class TokenTextSplitter extends MetadataAwareTextSplitter {
     }
 
     this.#tokenizer = params?.tokenizer ?? Settings.tokenizer;
+    this.#logger = params?.logger ?? consoleLogger;
 
     const allSeparators = [this.separator, ...this.backupSeparators];
     this.#splitFns = allSeparators.map((sep) => splitBySep(sep));
@@ -65,7 +69,7 @@ export class TokenTextSplitter extends MetadataAwareTextSplitter {
           `Consider increasing the chunk size or decreasing the size of your metadata to avoid this.`,
       );
     } else if (effectiveChunkSize < 50) {
-      console.warn(
+      this.#logger.warn(
         `Metadata length (${metadataLength}) is close to chunk size (${this.chunkSize}). ` +
           `Resulting chunks are less than 50 tokens. Consider increasing the chunk size or decreasing the size of your metadata to avoid this.`,
       );
@@ -148,7 +152,7 @@ export class TokenTextSplitter extends MetadataAwareTextSplitter {
       const splitLength = this.tokenSize(split);
 
       if (splitLength > chunkSize) {
-        console.warn(
+        this.#logger.warn(
           `Got a split of size ${splitLength}, larger than chunk size ${chunkSize}.`,
         );
       }

packages/core/src/storage/doc-store/kv-document-store.ts

@@ -1,3 +1,4 @@
+import { consoleLogger, type Logger } from "@llamaindex/env";
 import { DEFAULT_NAMESPACE } from "../../global";
 import { BaseNode, ObjectType, type StoredValue } from "../../schema";
 import type { BaseKVStore } from "../kv-store";
@@ -16,13 +17,19 @@ export class KVDocumentStore extends BaseDocumentStore {
   private nodeCollection: string;
   private refDocCollection: string;
   private metadataCollection: string;
+  private logger: Logger;
 
-  constructor(kvstore: BaseKVStore, namespace: string = DEFAULT_NAMESPACE) {
+  constructor(
+    kvstore: BaseKVStore,
+    namespace: string = DEFAULT_NAMESPACE,
+    options?: { logger?: Logger },
+  ) {
     super();
     this.kvstore = kvstore;
     this.nodeCollection = `${namespace}/data`;
     this.refDocCollection = `${namespace}/ref_doc_info`;
     this.metadataCollection = `${namespace}/metadata`;
+    this.logger = options?.logger ?? consoleLogger;
   }
 
   async docs(): Promise<Record<string, BaseNode>> {
@@ -33,7 +40,7 @@ export class KVDocumentStore extends BaseDocumentStore {
       if (isValidDocJson(value)) {
         docs[key] = jsonToDoc(value, this.serializer);
       } else {
-        console.warn(`Invalid JSON for docId ${key}`);
+        this.logger.warn(`Invalid JSON for docId ${key}`);
       }
     }
     return docs;

packages/core/src/storage/index-store/index.ts

@@ -1,4 +1,4 @@
-import { path } from "@llamaindex/env";
+import { path, type Logger } from "@llamaindex/env";
 import { IndexStruct, jsonToIndexStruct } from "../../data-structs";
 import {
   DEFAULT_INDEX_STORE_PERSIST_FILENAME,
@@ -8,8 +8,8 @@ import {
 import {
   BaseInMemoryKVStore,
   BaseKVStore,
-  type DataType,
   SimpleKVStore,
+  type DataType,
 } from "../kv-store";
 
 export const DEFAULT_PERSIST_PATH = path.join(
@@ -84,16 +84,23 @@ export class SimpleIndexStore extends KVIndexStore {
 
   static async fromPersistDir(
     persistDir: string = DEFAULT_PERSIST_DIR,
+    options?: { logger?: Logger },
   ): Promise<SimpleIndexStore> {
     const persistPath = path.join(
       persistDir,
       DEFAULT_INDEX_STORE_PERSIST_FILENAME,
     );
-    return this.fromPersistPath(persistPath);
+    return this.fromPersistPath(persistPath, options);
   }
 
-  static async fromPersistPath(persistPath: string): Promise<SimpleIndexStore> {
-    const simpleKVStore = await SimpleKVStore.fromPersistPath(persistPath);
+  static async fromPersistPath(
+    persistPath: string,
+    options?: { logger?: Logger },
+  ): Promise<SimpleIndexStore> {
+    const simpleKVStore = await SimpleKVStore.fromPersistPath(
+      persistPath,
+      options,
+    );
     return new SimpleIndexStore(simpleKVStore);
   }
 

packages/core/src/storage/kv-store/index.ts

@@ -1,4 +1,4 @@
-import { fs, path } from "@llamaindex/env";
+import { consoleLogger, fs, path, type Logger } from "@llamaindex/env";
 
 import { DEFAULT_COLLECTION } from "../../global";
 import type { StoredValue } from "../../schema";
@@ -98,7 +98,11 @@ export class SimpleKVStore extends BaseKVStore {
     await fs.writeFile(persistPath, JSON.stringify(this.data));
   }
 
-  static async fromPersistPath(persistPath: string): Promise<SimpleKVStore> {
+  static async fromPersistPath(
+    persistPath: string,
+    options?: { logger?: Logger },
+  ): Promise<SimpleKVStore> {
+    const logger = options?.logger ?? consoleLogger;
     const dirPath = path.dirname(persistPath);
     if (!(await exists(dirPath))) {
       await fs.mkdir(dirPath, { recursive: true });
@@ -106,7 +110,7 @@ export class SimpleKVStore extends BaseKVStore {
 
     let data: DataType = {};
     if (!(await exists(persistPath))) {
-      console.info(`Starting new store from path: ${persistPath}`);
+      logger.log(`Starting new store from path: ${persistPath}`);
     } else {
       try {
         const fileData = await fs.readFile(persistPath);

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

@@ -1,3 +1,4 @@
+import { consoleLogger, type Logger } from "@llamaindex/env";
 import type { JSONSchemaType } from "ajv";
 import { z } from "zod";
 import { zodToJsonSchema } from "zod-to-json-schema";
@@ -14,11 +15,13 @@ export class FunctionTool<
   #additionalArg: AdditionalToolArgument | undefined;
   readonly #metadata: ToolMetadata<JSONSchemaType<T>>;
   readonly #zodType: z.ZodType<T> | null = null;
+  readonly #logger: Logger;
   constructor(
     fn: (input: T, additionalArg?: AdditionalToolArgument) => R,
     metadata: ToolMetadata<JSONSchemaType<T>>,
     zodType?: z.ZodType<T>,
     additionalArg?: AdditionalToolArgument,
+    logger?: Logger,
   ) {
     this.#fn = fn;
     this.#metadata = metadata;
@@ -26,6 +29,7 @@ export class FunctionTool<
       this.#zodType = zodType;
     }
     this.#additionalArg = additionalArg;
+    this.#logger = logger ?? consoleLogger;
   }
 
   static from<T, AdditionalToolArgument extends object = object>(
@@ -140,7 +144,7 @@ export class FunctionTool<
       if (result.success) {
         params = result.data;
       } else {
-        console.warn(result.error.errors);
+        this.#logger.warn(result.error.errors);
       }
     }
     return this.#fn.call(null, params, this.#additionalArg);

packages/core/src/vector-store/index.ts

@@ -101,7 +101,9 @@ export type VectorStoreByType = {
 };
 
 export type VectorStoreBaseParams = {
+  // @deprecated: use embedModel instead
   embeddingModel?: BaseEmbedding | undefined;
+  embedModel?: BaseEmbedding | undefined;
 };
 
 export abstract class BaseVectorStore<Client = unknown, T = unknown> {
@@ -117,7 +119,8 @@ export abstract class BaseVectorStore<Client = unknown, T = unknown> {
   ): Promise<VectorStoreQueryResult>;
 
   protected constructor(params?: VectorStoreBaseParams) {
-    this.embedModel = params?.embeddingModel ?? Settings.embedModel;
+    this.embedModel =
+      params?.embedModel ?? params?.embeddingModel ?? Settings.embedModel;
   }
 }
 

packages/experimental/CHANGELOG.md

@@ -1,5 +1,42 @@
 # @llamaindex/experimental
 
+## 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
+
+- llamaindex@0.11.24
+
+## 0.0.200
+
+### Patch Changes
+
+- llamaindex@0.11.23
+
+## 0.0.199
+
+### Patch Changes
+
+- llamaindex@0.11.22
+
+## 0.0.198
+
+### Patch Changes
+
+- llamaindex@0.11.21
+
 ## 0.0.197
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.197",
+  "version": "0.0.203",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,59 @@
 # llamaindex
 
+## 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
+
+- Updated dependencies [c3bf3c7]
+- Updated dependencies [f9f1de9]
+  - @llamaindex/cloud@4.0.28
+  - @llamaindex/core@0.6.19
+  - @llamaindex/node-parser@2.0.19
+  - @llamaindex/workflow@1.1.20
+
+## 0.11.23
+
+### Patch Changes
+
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/workflow@1.1.19
+  - @llamaindex/core@0.6.18
+  - @llamaindex/cloud@4.0.27
+  - @llamaindex/node-parser@2.0.18
+
+## 0.11.22
+
+### Patch Changes
+
+- Updated dependencies [9ed3195]
+  - @llamaindex/workflow@1.1.18
+
+## 0.11.21
+
+### Patch Changes
+
+- Updated dependencies [38da40b]
+  - @llamaindex/core@0.6.17
+  - @llamaindex/cloud@4.0.26
+  - @llamaindex/node-parser@2.0.17
+  - @llamaindex/workflow@1.1.17
+
 ## 0.11.20
 
 ### Patch Changes

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.11.20",
+  "version": "0.11.26",
   "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/src/storage/docStore/SimpleDocumentStore.ts

@@ -8,7 +8,7 @@ import {
   BaseInMemoryKVStore,
   SimpleKVStore,
 } from "@llamaindex/core/storage/kv-store";
-import { path } from "@llamaindex/env";
+import { path, type Logger } from "@llamaindex/env";
 import _ from "lodash";
 
 // eslint-disable-next-line @typescript-eslint/no-explicit-any
@@ -27,19 +27,28 @@ export class SimpleDocumentStore extends KVDocumentStore {
   static async fromPersistDir(
     persistDir: string = DEFAULT_PERSIST_DIR,
     namespace?: string,
+    options?: { logger?: Logger },
   ): Promise<SimpleDocumentStore> {
     const persistPath = path.join(
       persistDir,
       DEFAULT_DOC_STORE_PERSIST_FILENAME,
     );
-    return await SimpleDocumentStore.fromPersistPath(persistPath, namespace);
+    return await SimpleDocumentStore.fromPersistPath(
+      persistPath,
+      namespace,
+      options,
+    );
   }
 
   static async fromPersistPath(
     persistPath: string,
     namespace?: string,
+    options?: { logger?: Logger },
   ): Promise<SimpleDocumentStore> {
-    const simpleKVStore = await SimpleKVStore.fromPersistPath(persistPath);
+    const simpleKVStore = await SimpleKVStore.fromPersistPath(
+      persistPath,
+      options,
+    );
     return new SimpleDocumentStore(simpleKVStore, namespace);
   }
 

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

@@ -18,7 +18,7 @@ import {
   type VectorStoreQuery,
   type VectorStoreQueryResult,
 } from "@llamaindex/core/vector-store";
-import { fs, path } from "@llamaindex/env";
+import { consoleLogger, fs, path, type Logger } from "@llamaindex/env";
 import { exists } from "../storage/FileSystem.js";
 
 const LEARNER_MODES = new Set<VectorStoreQueryMode>([
@@ -139,9 +139,14 @@ export class SimpleVectorStore extends BaseVectorStore {
   static async fromPersistDir(
     persistDir: string = DEFAULT_PERSIST_DIR,
     embedModel?: BaseEmbedding,
+    options?: { logger?: Logger },
   ): Promise<SimpleVectorStore> {
     const persistPath = path.join(persistDir, "vector_store.json");
-    return await SimpleVectorStore.fromPersistPath(persistPath, embedModel);
+    return await SimpleVectorStore.fromPersistPath(
+      persistPath,
+      embedModel,
+      options,
+    );
   }
 
   client() {
@@ -272,8 +277,10 @@ export class SimpleVectorStore extends BaseVectorStore {
 
   static async fromPersistPath(
     persistPath: string,
-    embeddingModel?: BaseEmbedding,
+    embedModel?: BaseEmbedding,
+    options?: { logger?: Logger },
   ): Promise<SimpleVectorStore> {
+    const logger = options?.logger ?? consoleLogger;
     const dirPath = path.dirname(persistPath);
     if (!(await exists(dirPath))) {
       await fs.mkdir(dirPath, { recursive: true });
@@ -281,7 +288,7 @@ export class SimpleVectorStore extends BaseVectorStore {
 
     let dataDict: Record<string, unknown> = {};
     if (!(await exists(persistPath))) {
-      console.info(`Starting new store from path: ${persistPath}`);
+      logger.log(`Starting new store from path: ${persistPath}`);
     } else {
       try {
         const fileData = await fs.readFile(persistPath);
@@ -300,20 +307,20 @@ export class SimpleVectorStore extends BaseVectorStore {
     data.textIdToRefDocId = dataDict.textIdToRefDocId ?? {};
     // @ts-expect-error TS2322
     data.metadataDict = dataDict.metadataDict ?? {};
-    const store = new SimpleVectorStore({ data, embeddingModel });
+    const store = new SimpleVectorStore({ data, embedModel });
     store.persistPath = persistPath;
     return store;
   }
 
   static fromDict(
     saveDict: SimpleVectorStoreData,
-    embeddingModel?: BaseEmbedding,
+    embedModel?: BaseEmbedding,
   ): SimpleVectorStore {
     const data = new SimpleVectorStoreData();
     data.embeddingDict = saveDict.embeddingDict;
     data.textIdToRefDocId = saveDict.textIdToRefDocId;
     data.metadataDict = saveDict.metadataDict;
-    return new SimpleVectorStore({ data, embeddingModel });
+    return new SimpleVectorStore({ data, embedModel });
   }
 
   toDict(): SimpleVectorStoreData {

packages/llamaindex/tests/CHANGELOG.md

@@ -1,5 +1,37 @@
 # @llamaindex/core-test
 
+## 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
+
+- @llamaindex/openai@0.4.14
+
+## 0.1.14
+
+### Patch Changes
+
+- @llamaindex/openai@0.4.13
+
+## 0.1.13
+
+### Patch Changes
+
+- @llamaindex/openai@0.4.12
+
 ## 0.1.12
 
 ### Patch Changes

packages/llamaindex/tests/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llamaindex-test",
   "private": true,
-  "version": "0.1.12",
+  "version": "0.1.17",
   "type": "module",
   "scripts": {
     "test": "vitest run"

packages/llamaindex/tests/storage/StorageContext.test.ts

@@ -47,22 +47,31 @@ describe("StorageContext", () => {
 
   test("persists and loads", async () => {
     const doc = new Document({ text: "test document" });
-    const consoleInfoSpy = vi
-      .spyOn(console, "info")
-      .mockImplementation(() => {});
+    // Create a Logger that spies on log (info) calls
+    const spyLogger = {
+      log: vi.fn(),
+      error: vi.fn(),
+      warn: vi.fn(),
+    };
 
     // storage context from individual stores
     const storageContext = await storageContextFromDefaults({
-      docStore: await SimpleDocumentStore.fromPersistDir(testDir),
-      vectorStore: await SimpleVectorStore.fromPersistDir(testDir),
-      indexStore: await SimpleIndexStore.fromPersistDir(testDir),
+      docStore: await SimpleDocumentStore.fromPersistDir(testDir, undefined, {
+        logger: spyLogger,
+      }),
+      vectorStore: await SimpleVectorStore.fromPersistDir(testDir, undefined, {
+        logger: spyLogger,
+      }),
+      indexStore: await SimpleIndexStore.fromPersistDir(testDir, {
+        logger: spyLogger,
+      }),
     });
 
     const index = await VectorStoreIndex.fromDocuments([doc], {
       storageContext,
     });
-    expect(consoleInfoSpy).toHaveBeenCalledTimes(3);
-    expect(consoleInfoSpy).toHaveBeenCalledWith(
+    expect(spyLogger.log).toHaveBeenCalledTimes(3);
+    expect(spyLogger.log).toHaveBeenCalledWith(
       expect.stringContaining("Starting new store"),
     );
     expect(index).toBeDefined();
@@ -75,13 +84,19 @@ describe("StorageContext", () => {
     // Check that the test data files exist
     await expectTestDataFilesExist(testDir);
 
-    consoleInfoSpy.mockClear();
+    spyLogger.log.mockClear();
 
     // Now, load it again. Since data was persisted, we should not see the error.
     const newStorageContext = await storageContextFromDefaults({
-      docStore: await SimpleDocumentStore.fromPersistDir(testDir),
-      vectorStore: await SimpleVectorStore.fromPersistDir(testDir),
-      indexStore: await SimpleIndexStore.fromPersistDir(testDir),
+      docStore: await SimpleDocumentStore.fromPersistDir(testDir, undefined, {
+        logger: spyLogger,
+      }),
+      vectorStore: await SimpleVectorStore.fromPersistDir(testDir, undefined, {
+        logger: spyLogger,
+      }),
+      indexStore: await SimpleIndexStore.fromPersistDir(testDir, {
+        logger: spyLogger,
+      }),
     });
 
     const loadedIndex = await VectorStoreIndex.init({
@@ -94,9 +109,7 @@ describe("StorageContext", () => {
 
     await expectTestDataFilesExist(testDir);
 
-    expect(consoleInfoSpy).not.toHaveBeenCalled();
-
-    consoleInfoSpy.mockRestore();
+    expect(spyLogger.log).not.toHaveBeenCalled();
   });
 
   test("throws error on corrupted data", async () => {

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

@@ -59,7 +59,7 @@ describe("SimpleVectorStore", () => {
       }),
     ];
     store = new SimpleVectorStore({
-      embeddingModel: {} as BaseEmbedding, // Mocking the embedModel
+      embedModel: {} as BaseEmbedding, // Mocking the embedModel
       data: {
         embeddingDict: {},
         textIdToRefDocId: {},

packages/node-parser/CHANGELOG.md

@@ -1,5 +1,27 @@
 # @llamaindex/node-parser
 
+## 2.0.19
+
+### Patch Changes
+
+- Updated dependencies [f9f1de9]
+  - @llamaindex/core@0.6.19
+
+## 2.0.18
+
+### Patch Changes
+
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/core@0.6.18
+
+## 2.0.17
+
+### Patch Changes
+
+- Updated dependencies [38da40b]
+  - @llamaindex/core@0.6.17
+
 ## 2.0.16
 
 ### Patch Changes