chore: remove cloud package

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

apps/next/CHANGELOG.md

@@ -1,5 +1,50 @@
 # @llamaindex/doc
 
+## 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

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.44",
+  "version": "0.2.48",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",
@@ -16,7 +16,6 @@
     "@huggingface/transformers": "^3.5.0",
     "@icons-pack/react-simple-icons": "^10.1.0",
     "@llamaindex/chat-ui-docs": "^0.0.5",
-    "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/node-parser": "workspace:*",
     "@llamaindex/openai": "workspace:*",

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/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 +1,30 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 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

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.182",
+  "version": "0.0.186",
   "type": "module",
   "private": true,
   "scripts": {

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

@@ -1,5 +1,25 @@
 # @llamaindex/llama-parse-browser-test
 
+## 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

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.81",
+  "version": "0.0.84",
   "type": "module",
   "scripts": {
     "dev": "vite",
@@ -14,6 +14,6 @@
     "vite-plugin-wasm": "^3.4.1"
   },
   "dependencies": {
-    "@llamaindex/cloud": "workspace:*"
+    "llama-cloud-services": "^0.1.0"
   }
 }

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,30 @@
 # @llamaindex/next-agent-test
 
+## 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

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.182",
+  "version": "0.1.186",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,30 @@
 # test-edge-runtime
 
+## 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

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.181",
+  "version": "0.1.185",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,34 @@
 # @llamaindex/next-node-runtime
 
+## 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

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.51",
+  "version": "0.1.55",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,30 @@
 # vite-import-llamaindex
 
+## 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

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

@@ -1,7 +1,7 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.48",
+  "version": "0.0.52",
   "type": "module",
   "scripts": {
     "build": "vite build",

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

@@ -1,5 +1,30 @@
 # @llamaindex/waku-query-engine-test
 
+## 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

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.182",
+  "version": "0.0.186",
   "type": "module",
   "private": true,
   "scripts": {

examples/CHANGELOG.md

@@ -1,5 +1,111 @@
 # examples
 
+## 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

examples/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/examples",
-  "version": "0.3.33",
+  "version": "0.3.35",
   "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": "^0.3.19",
-    "@llamaindex/assemblyai": "^0.1.16",
-    "@llamaindex/astra": "^0.0.31",
-    "@llamaindex/azure": "^0.1.29",
-    "@llamaindex/bm25-retriever": "^0.0.6",
-    "@llamaindex/chroma": "^0.0.31",
-    "@llamaindex/clip": "^0.0.68",
-    "@llamaindex/cloud": "^4.0.26",
-    "@llamaindex/cohere": "^0.0.31",
-    "@llamaindex/core": "^0.6.17",
-    "@llamaindex/deepinfra": "^0.0.68",
-    "@llamaindex/deepseek": "^0.0.29",
-    "@llamaindex/discord": "^0.1.16",
-    "@llamaindex/elastic-search": "^0.1.17",
+    "@llamaindex/anthropic": "^0.3.21",
+    "@llamaindex/assemblyai": "^0.1.18",
+    "@llamaindex/astra": "^0.0.33",
+    "@llamaindex/azure": "^0.1.31",
+    "@llamaindex/bm25-retriever": "^0.0.8",
+    "@llamaindex/chroma": "^0.0.33",
+    "@llamaindex/clip": "^0.0.70",
+    "llama-cloud-services": "^0.1.0",
+    "@llamaindex/cohere": "^0.0.33",
+    "@llamaindex/core": "^0.6.19",
+    "@llamaindex/deepinfra": "^0.0.70",
+    "@llamaindex/deepseek": "^0.0.31",
+    "@llamaindex/discord": "^0.1.18",
+    "@llamaindex/elastic-search": "^0.1.19",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/firestore": "^1.0.24",
-    "@llamaindex/fireworks": "^0.0.28",
-    "@llamaindex/google": "^0.3.16",
-    "@llamaindex/groq": "^0.0.84",
-    "@llamaindex/huggingface": "^0.1.22",
-    "@llamaindex/jinaai": "^0.0.28",
-    "@llamaindex/milvus": "^0.1.26",
-    "@llamaindex/mistral": "^0.1.17",
-    "@llamaindex/mixedbread": "^0.0.31",
-    "@llamaindex/mongodb": "^0.0.32",
-    "@llamaindex/node-parser": "^2.0.17",
-    "@llamaindex/notion": "^0.1.16",
-    "@llamaindex/ollama": "^0.1.17",
-    "@llamaindex/openai": "^0.4.12",
-    "@llamaindex/perplexity": "^0.0.25",
-    "@llamaindex/pinecone": "^0.1.17",
-    "@llamaindex/portkey-ai": "^0.0.59",
-    "@llamaindex/postgres": "^0.0.60",
-    "@llamaindex/qdrant": "^0.1.27",
-    "@llamaindex/readers": "^3.1.16",
-    "@llamaindex/replicate": "^0.0.59",
-    "@llamaindex/supabase": "^0.1.18",
-    "@llamaindex/together": "^0.0.28",
-    "@llamaindex/tools": "^0.1.7",
-    "@llamaindex/upstash": "^0.0.31",
-    "@llamaindex/vercel": "^0.1.17",
-    "@llamaindex/vllm": "^0.0.54",
-    "@llamaindex/voyage-ai": "^1.0.23",
-    "@llamaindex/weaviate": "^0.0.32",
-    "@llamaindex/workflow": "^1.1.17",
-    "@llamaindex/xai": "^0.0.15",
+    "@llamaindex/firestore": "^1.0.26",
+    "@llamaindex/fireworks": "^0.0.30",
+    "@llamaindex/google": "^0.3.18",
+    "@llamaindex/groq": "^0.0.86",
+    "@llamaindex/huggingface": "^0.1.24",
+    "@llamaindex/jinaai": "^0.0.30",
+    "@llamaindex/milvus": "^0.1.28",
+    "@llamaindex/mistral": "^0.1.19",
+    "@llamaindex/mixedbread": "^0.0.33",
+    "@llamaindex/mongodb": "^0.0.34",
+    "@llamaindex/node-parser": "^2.0.19",
+    "@llamaindex/notion": "^0.1.18",
+    "@llamaindex/ollama": "^0.1.19",
+    "@llamaindex/openai": "^0.4.14",
+    "@llamaindex/perplexity": "^0.0.27",
+    "@llamaindex/pinecone": "^0.1.19",
+    "@llamaindex/portkey-ai": "^0.0.61",
+    "@llamaindex/postgres": "^0.0.62",
+    "@llamaindex/qdrant": "^0.1.29",
+    "@llamaindex/readers": "^3.1.18",
+    "@llamaindex/replicate": "^0.0.61",
+    "@llamaindex/supabase": "^0.1.20",
+    "@llamaindex/together": "^0.0.30",
+    "@llamaindex/tools": "^0.1.9",
+    "@llamaindex/upstash": "^0.0.33",
+    "@llamaindex/vercel": "^0.1.19",
+    "@llamaindex/vllm": "^0.0.56",
+    "@llamaindex/voyage-ai": "^1.0.25",
+    "@llamaindex/weaviate": "^0.0.34",
+    "@llamaindex/workflow": "^1.1.20",
+    "@llamaindex/xai": "^0.0.17",
     "@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": "^0.11.21",
+    "llamaindex": "^0.11.24",
     "mongodb": "6.7.0",
     "postgres": "^3.4.4",
     "wikipedia": "^2.1.2",

examples/readers/package.json

@@ -9,10 +9,7 @@
     "start:html": "node --import tsx ./src/html.ts",
     "start:markdown": "node --import tsx ./src/markdown.ts",
     "start:pdf": "node --import tsx ./src/pdf.ts",
-    "start:llamaparse": "node --import tsx ./src/llamaparse.ts",
     "start:notion": "node --import tsx ./src/notion.ts",
-    "start:llamaparse-dir": "node --import tsx ./src/simple-directory-reader-with-llamaparse.ts",
-    "start:llamaparse-json": "node --import tsx ./src/llamaparse-json.ts",
     "start:discord": "node --import tsx ./src/discord.ts",
     "start:json": "node --import tsx ./src/json.ts",
     "start:obsidian": "node --import tsx ./src/obsidian.ts",
@@ -20,7 +17,7 @@
     "start:excel": "node --import tsx ./src/excel.ts"
   },
   "dependencies": {
-    "@llamaindex/cloud": "workspace:* || ^2.0.24",
+    "llama-cloud-services": "^0.1.0",
     "@llamaindex/excel": "workspace:*",
     "@llamaindex/readers": "workspace:* || ^1.0.25",
     "@notionhq/client": "^4.0.0",

packages/autotool/CHANGELOG.md

@@ -1,5 +1,30 @@
 # @llamaindex/autotool
 
+## 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

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

@@ -1,5 +1,34 @@
 # @llamaindex/autotool-01-node-example
 
+## 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

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

@@ -13,5 +13,5 @@
   "scripts": {
     "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
   },
-  "version": "0.0.129"
+  "version": "0.0.133"
 }

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "8.0.21",
+  "version": "8.0.25",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",

packages/cloud/README.md

@@ -1,9 +0,0 @@
-# @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/).
-
-## License
-
-MIT

packages/cloud/api/package.json

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

packages/cloud/beta/agent/package.json

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

packages/cloud/openapi-ts.config.ts

@@ -1,24 +0,0 @@
-import { defaultPlugins, defineConfig } from "@hey-api/openapi-ts";
-
-export default defineConfig({
-  // you can download this file to get the latest version of the OpenAPI document
-  // @link https://api.cloud.llamaindex.ai/api/openapi.json
-  input: "./openapi.json",
-  output: {
-    path: "./src/client",
-    format: "prettier",
-    lint: "eslint",
-  },
-  plugins: [
-    ...defaultPlugins,
-    "@hey-api/client-fetch",
-    "zod",
-    "@hey-api/schemas",
-    "@hey-api/sdk",
-    {
-      enums: "javascript",
-      identifierCase: "PascalCase",
-      name: "@hey-api/typescript",
-    },
-  ],
-});

packages/cloud/package.json

@@ -1,97 +0,0 @@
-{
-  "name": "@llamaindex/cloud",
-  "version": "4.0.26",
-  "type": "module",
-  "license": "MIT",
-  "scripts": {
-    "generate": "./node_modules/.bin/openapi-ts",
-    "build": "pnpm run generate && bunchee",
-    "dev": "bunchee --watch"
-  },
-  "files": [
-    "openapi.json",
-    "./api",
-    "./reader",
-    "./parse",
-    "./beta/agent"
-  ],
-  "exports": {
-    "./openapi.json": "./openapi.json",
-    "./beta/agent": {
-      "require": {
-        "types": "./beta/agent/dist/index.d.cts",
-        "default": "./beta/agent/dist/index.cjs"
-      },
-      "import": {
-        "types": "./beta/agent/dist/index.d.ts",
-        "default": "./beta/agent/dist/index.js"
-      },
-      "default": "./beta/agent/dist/index.js"
-    },
-    "./api": {
-      "require": {
-        "types": "./api/dist/index.d.cts",
-        "default": "./api/dist/index.cjs"
-      },
-      "import": {
-        "types": "./api/dist/index.d.ts",
-        "default": "./api/dist/index.js"
-      },
-      "default": "./api/dist/index.js"
-    },
-    "./reader": {
-      "require": {
-        "types": "./reader/dist/index.d.cts",
-        "default": "./reader/dist/index.cjs"
-      },
-      "import": {
-        "types": "./reader/dist/index.d.ts",
-        "default": "./reader/dist/index.js"
-      },
-      "default": "./reader/dist/index.js"
-    },
-    "./parse": {
-      "require": {
-        "types": "./parse/dist/index.d.cts",
-        "default": "./parse/dist/index.cjs"
-      },
-      "import": {
-        "types": "./parse/dist/index.d.ts",
-        "default": "./parse/dist/index.js"
-      },
-      "default": "./parse/dist/index.js"
-    },
-    ".": {
-      "require": {
-        "types": "./reader/dist/index.d.cts",
-        "default": "./reader/dist/index.cjs"
-      },
-      "import": {
-        "types": "./reader/dist/index.d.ts",
-        "default": "./reader/dist/index.js"
-      },
-      "default": "./reader/dist/index.js"
-    }
-  },
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
-    "directory": "packages/cloud"
-  },
-  "devDependencies": {
-    "@hey-api/client-fetch": "^0.10.1",
-    "@hey-api/openapi-ts": "^0.67.5",
-    "@llama-flow/core": "^0.4.1",
-    "@llamaindex/core": "workspace:*",
-    "@llamaindex/env": "workspace:*"
-  },
-  "peerDependencies": {
-    "@llama-flow/core": "^0.4.1",
-    "@llamaindex/core": "workspace:*",
-    "@llamaindex/env": "workspace:*"
-  },
-  "dependencies": {
-    "p-retry": "^6.2.1",
-    "zod": "^3.25.76"
-  }
-}

packages/cloud/parse/package.json

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

packages/cloud/reader/package.json

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

packages/cloud/src/api.ts

@@ -1,11 +0,0 @@
-import { client } from "./client/client.gen";
-
-client.setConfig({
-  baseUrl: "https://api.cloud.llamaindex.ai/",
-  headers: {
-    "X-SDK-Name": "llamaindex-ts",
-  },
-});
-
-export * from "./client";
-export { client };

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

@@ -1,329 +0,0 @@
-import { createClient, createConfig } from "@hey-api/client-fetch";
-import { getEnv } from "@llamaindex/env";
-import {
-  aggregateAgentDataApiV1BetaAgentDataAggregatePost,
-  createAgentDataApiV1BetaAgentDataPost,
-  deleteAgentDataApiV1BetaAgentDataItemIdDelete,
-  getAgentDataApiV1BetaAgentDataItemIdGet,
-  searchAgentDataApiV1BetaAgentDataSearchPost,
-  updateAgentDataApiV1BetaAgentDataItemIdPut,
-  type AgentData,
-  type AggregateGroup,
-} from "../../client";
-import type {
-  AggregateAgentDataOptions,
-  SearchAgentDataOptions,
-  TypedAgentData,
-  TypedAgentDataItems,
-  TypedAggregateGroup,
-  TypedAggregateGroupItems,
-} from "./types";
-
-/**
- * Async client for agent data operations
- */
-export class AgentClient<T = unknown> {
-  private client: ReturnType<typeof createClient>;
-  private baseUrl: string;
-  private headers: Record<string, string>;
-  private collection: string;
-  private agentUrlId: string;
-
-  constructor({
-    apiKey = getEnv("LLAMA_CLOUD_API_KEY"),
-    baseUrl = "https://api.cloud.llamaindex.ai/",
-    collection = "default",
-    agentUrlId = "_public",
-  }: {
-    apiKey?: string;
-    baseUrl?: string;
-    collection?: string;
-    agentUrlId?: string;
-  }) {
-    this.baseUrl = baseUrl;
-
-    this.headers = {
-      "X-SDK-Name": "llamaindex-ts",
-      ...(apiKey && { Authorization: `Bearer ${apiKey}` }),
-    };
-
-    this.client = createClient(
-      createConfig({
-        baseUrl: this.baseUrl,
-        headers: this.headers,
-      }),
-    );
-
-    this.collection = collection;
-    this.agentUrlId = agentUrlId;
-  }
-
-  /**
-   * Create new agent data
-   */
-  async createItem(data: T): Promise<TypedAgentData<T>> {
-    const response = await createAgentDataApiV1BetaAgentDataPost({
-      throwOnError: true,
-      body: {
-        agent_slug: this.agentUrlId,
-        collection: this.collection,
-        data: data as Record<string, unknown>,
-      },
-      client: this.client,
-    });
-
-    return this.transformResponse(response.data);
-  }
-
-  /**
-   * Get agent data by ID
-   */
-  async getItem(id: string): Promise<TypedAgentData<T> | null> {
-    try {
-      const response = await getAgentDataApiV1BetaAgentDataItemIdGet({
-        throwOnError: true,
-        path: { item_id: id },
-        client: this.client,
-      });
-
-      return this.transformResponse(response.data);
-    } catch (error) {
-      if (
-        error instanceof Error &&
-        "response" in error &&
-        (error as { response?: { status?: number } }).response?.status === 404
-      ) {
-        return null;
-      }
-      throw error;
-    }
-  }
-
-  /**
-   * Update agent data
-   */
-  async updateItem(id: string, data: T): Promise<TypedAgentData<T>> {
-    const response = await updateAgentDataApiV1BetaAgentDataItemIdPut({
-      throwOnError: true,
-      path: { item_id: id },
-      body: {
-        data: data as Record<string, unknown>,
-      },
-      client: this.client,
-    });
-
-    return this.transformResponse(response.data);
-  }
-
-  /**
-   * Delete agent data
-   */
-  async deleteItem(id: string): Promise<void> {
-    await deleteAgentDataApiV1BetaAgentDataItemIdDelete({
-      throwOnError: true,
-      path: { item_id: id },
-      client: this.client,
-    });
-  }
-
-  /**
-   * Search agent data
-   */
-  async search(
-    options: SearchAgentDataOptions,
-  ): Promise<TypedAgentDataItems<T>> {
-    const response = await searchAgentDataApiV1BetaAgentDataSearchPost({
-      throwOnError: true,
-      body: {
-        agent_slug: this.agentUrlId,
-        ...(this.collection !== undefined && {
-          collection: this.collection,
-        }),
-        ...(options.filter !== undefined && { filter: options.filter }),
-        ...(options.orderBy !== undefined && { order_by: options.orderBy }),
-        ...(options.pageSize !== undefined && { page_size: options.pageSize }),
-        ...(options.offset !== undefined && { offset: options.offset }),
-        ...(options.includeTotal !== undefined && {
-          include_total: options.includeTotal,
-        }),
-      },
-      client: this.client,
-    });
-
-    const result: TypedAgentDataItems<T> = {
-      items: response.data.items.map((item: AgentData) =>
-        this.transformResponse(item),
-      ),
-    };
-
-    if (
-      response.data.total_size !== null &&
-      response.data.total_size !== undefined
-    ) {
-      result.totalSize = response.data.total_size;
-    }
-
-    if (
-      response.data.next_page_token !== null &&
-      response.data.next_page_token !== undefined
-    ) {
-      result.nextPageToken = response.data.next_page_token;
-    }
-
-    return result;
-  }
-
-  /**
-   * Aggregate agent data into groups
-   */
-  async aggregate(
-    options: AggregateAgentDataOptions,
-  ): Promise<TypedAggregateGroupItems<T>> {
-    const response = await aggregateAgentDataApiV1BetaAgentDataAggregatePost({
-      throwOnError: true,
-      body: {
-        agent_slug: this.agentUrlId,
-        ...(this.collection !== undefined && {
-          collection: this.collection,
-        }),
-        ...(options.filter !== undefined && { filter: options.filter }),
-        ...(options.groupBy !== undefined && { group_by: options.groupBy }),
-        ...(options.count !== undefined && { count: options.count }),
-        ...(options.first !== undefined && { first: options.first }),
-        ...(options.orderBy !== undefined && { order_by: options.orderBy }),
-        ...(options.offset !== undefined && { offset: options.offset }),
-        ...(options.pageSize !== undefined && { page_size: options.pageSize }),
-      },
-      client: this.client,
-    });
-
-    const result: TypedAggregateGroupItems<T> = {
-      items: response.data.items.map((item) =>
-        this.transformAggregateResponse(item),
-      ),
-    };
-
-    if (
-      response.data.total_size !== null &&
-      response.data.total_size !== undefined
-    ) {
-      result.totalSize = response.data.total_size;
-    }
-
-    if (
-      response.data.next_page_token !== null &&
-      response.data.next_page_token !== undefined
-    ) {
-      result.nextPageToken = response.data.next_page_token;
-    }
-
-    return result;
-  }
-
-  /**
-   * Transform API response to typed data
-   */
-  private transformResponse(data: AgentData): TypedAgentData<T> {
-    const result: TypedAgentData<T> = {
-      id: data.id!,
-      agentUrlId: data.agent_slug,
-      data: data.data as T,
-      createdAt: new Date(data.created_at!),
-      updatedAt: new Date(data.updated_at!),
-    };
-
-    if (data.collection !== undefined) {
-      result.collection = data.collection;
-    }
-
-    return result;
-  }
-
-  /**
-   * Transform API aggregate response to typed data
-   */
-  private transformAggregateResponse(
-    data: AggregateGroup,
-  ): TypedAggregateGroup<T> {
-    const result: TypedAggregateGroup<T> = {
-      groupKey: data.group_key,
-    };
-
-    if (data.count !== null && data.count !== undefined) {
-      result.count = data.count;
-    }
-
-    if (data.first_item !== null && data.first_item !== undefined) {
-      result.firstItem = data.first_item as T;
-    }
-
-    return result;
-  }
-}
-
-export interface AgentDataClientOptions<T = unknown> {
-  /** API key for the client */
-  apiKey?: string;
-  /** Base URL for the client */
-  /** Base URL of the llama cloud api */
-  baseUrl?: string;
-  /** If running in an agent runtime, optionally provide the window url to infer the agent url id */
-  windowUrl?: string;
-  /** Agent URL ID for the client, if not provided, it will be inferred from the window url, or fall back to "default" */
-  agentUrlId?: string;
-  /** Collection name for the client, defaults to "default" */
-  collection?: string;
-}
-/**
- * Create a new AsyncAgentDataClient instance. Does it's best to infer an agent url id from environment.
- * Pass in the window url and/or env to infer the agent url id from them.
- * @param options - The options for the client
- * @returns A new AgentClient instance
- */
-export function createAgentDataClient<T = unknown>({
-  apiKey,
-  baseUrl,
-  windowUrl,
-  env,
-  agentUrlId,
-  collection = "default",
-}: {
-  apiKey?: string;
-  baseUrl?: string;
-  windowUrl?: string;
-  env?: Record<string, string>;
-  agentUrlId?: string;
-  collection?: string;
-} = {}): AgentClient<T> {
-  if (env && !agentUrlId) {
-    agentUrlId =
-      env.LLAMA_DEPLOY_DEPLOYMENT_NAME ||
-      env.NEXT_PUBLIC_LLAMA_DEPLOY_DEPLOYMENT_NAME ||
-      env.VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME;
-  }
-  if (windowUrl && !agentUrlId) {
-    try {
-      const url = new URL(windowUrl);
-      const path = url.pathname;
-      const isLocalhost = // local agents should default to _public, otherwise a full deployment is required
-        url.hostname.includes("localhost") ||
-        url.hostname.includes("127.0.0.1");
-      if (path.startsWith("/deployments/") && !isLocalhost) {
-        // /deployments/<agent-url-id>/ui/ -> ["", "deployments", "<agent-url-id>", "ui"]
-        agentUrlId = path.split("/")[2];
-      }
-    } catch (error) {
-      console.warn(
-        "Failed to infer agent url id from window url, falling back to default",
-        error,
-      );
-    }
-  }
-
-  return new AgentClient({
-    ...(apiKey && { apiKey }),
-    ...(baseUrl && { baseUrl }),
-    ...(agentUrlId && { agentUrlId }),
-    collection,
-  });
-}

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

@@ -1,16 +0,0 @@
-export { AgentClient, createAgentDataClient } from "./client";
-
-export type {
-  AggregateAgentDataOptions,
-  ComparisonOperator,
-  ExtractedData,
-  FilterOperation,
-  SearchAgentDataOptions,
-  StatusType,
-  TypedAgentData,
-  TypedAgentDataItems,
-  TypedAggregateGroup,
-  TypedAggregateGroupItems,
-} from "./types";
-
-export { StatusType as StatusTypeEnum } from "./types";

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

@@ -1,138 +0,0 @@
-import type { FilterOperation as RawFilterOperation } from "../../client/types.gen";
-/**
- * Status types for agent data processing
- */
-export const StatusType = {
-  ERROR: "error",
-  ACCEPTED: "accepted",
-  REJECTED: "rejected",
-  PENDING_REVIEW: "pending_review",
-} as const;
-
-export type StatusType = (typeof StatusType)[keyof typeof StatusType];
-
-export const ComparisonOperator = {
-  GT: "gt",
-  GTE: "gte",
-  LT: "lt",
-  LTE: "lte",
-  EQ: "eq",
-  INCLUDES: "includes",
-} as const;
-
-export type ComparisonOperator =
-  (typeof ComparisonOperator)[keyof typeof ComparisonOperator];
-
-/**
- * Filter operation for searching/filtering agent data
- */
-export type FilterOperation = RawFilterOperation;
-
-/**
- * Base extracted data interface
- */
-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;
-  /** 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 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. */
-  file_name?: string;
-  /** The hash of the file that was used to extract the data. */
-  file_hash?: string;
-  /** Additional metadata about the extracted data, such as errors, tokens, etc. */
-  metadata?: Record<string, unknown>;
-}
-
-/**
- * TypedAgentData interface for typed agent data
- */
-export interface TypedAgentData<T = unknown> {
-  /** The unique ID of the agent data record. */
-  id: string;
-  /** The ID of the agent that created the data. */
-  agentUrlId: string;
-  /** The collection of the agent data. */
-  collection?: string;
-  /** The data of the agent data. Usually an ExtractedData&lt;SomeOtherType&gt; */
-  data: T;
-  /** The date and time the data was created. */
-  createdAt: Date;
-  /** The date and time the data was last updated. */
-  updatedAt: Date;
-}
-
-/**
- * Paginated response of typed agent data items
- */
-export interface TypedAgentDataItems<T = unknown> {
-  items: TypedAgentData<T>[];
-  totalSize?: number;
-  nextPageToken?: string;
-}
-
-/**
- * Options for listing agent data
- */
-export interface SearchAgentDataOptions {
-  /** Filter options for the list. */
-  filter?: Record<string, FilterOperation>;
-  /** Order by options for the list. */
-  orderBy?: string;
-  /** Page size for the list. */
-  pageSize?: number;
-  /** Offset for the list. */
-  offset?: number;
-  /**
-   * Whether to include the total number of items in the response.
-   * Should use only for first request to build total pagination, and not subsequent requests.
-   */
-  includeTotal?: boolean;
-}
-
-/**
- * Options for aggregating agent data
- */
-export interface AggregateAgentDataOptions {
-  /** Filter options for the aggregation. */
-  filter?: Record<string, FilterOperation>;
-  /** Fields to group by. */
-  groupBy?: string[];
-  /** Whether to count the number of items in each group. */
-  count?: boolean;
-  /** Whether to return the first item in each group. */
-  first?: boolean;
-  /** Order by options for the aggregation. */
-  orderBy?: string;
-  /** Offset for the aggregation. */
-  offset?: number;
-  /** Page size for the aggregation. */
-  pageSize?: number;
-}
-
-/**
- * Single aggregation group result
- */
-export interface TypedAggregateGroup<T = unknown> {
-  /** The group key values */
-  groupKey: Record<string, unknown>;
-  /** Count of items in the group */
-  count?: number;
-  /** First item in the group */
-  firstItem?: T;
-}
-
-/**
- * Paginated response of aggregated agent data
- */
-export interface TypedAggregateGroupItems<T = unknown> {
-  items: TypedAggregateGroup<T>[];
-  totalSize?: number;
-  nextPageToken?: string;
-}

packages/cloud/src/events.ts

@@ -1,55 +0,0 @@
-import { workflowEvent } from "@llama-flow/core";
-import { zodEvent } from "@llama-flow/core/util/zod";
-import { z } from "zod";
-import { parseFormSchema } from "./schema";
-
-export const uploadEvent = zodEvent(
-  parseFormSchema.merge(
-    z.object({
-      file: z
-        .string()
-        .or(z.instanceof(File))
-        .or(z.instanceof(Blob))
-        .or(z.instanceof(Uint8Array))
-        .optional()
-        .describe("input"),
-    }),
-  ),
-  {
-    debugLabel: "upload",
-    uniqueId: "52099967-34a8-419b-8950-c859eab60145",
-  },
-);
-export const checkStatusEvent = workflowEvent<string>({
-  debugLabel: "check-status",
-  uniqueId: "462157fc-1ded-4ba7-9bc4-3e870395bd20",
-});
-export const checkStatusSuccessEvent = workflowEvent<string>({
-  debugLabel: "check-status-success",
-  uniqueId: "360b7641-30f7-456e-851d-104bb5e3f8d2",
-});
-export const requestMarkdownEvent = workflowEvent<string>({
-  debugLabel: "markdown-request",
-  uniqueId: "aa4c2e3c-0f09-4035-aab6-c72719c877cc",
-});
-export const requestTextEvent = workflowEvent<string>({
-  debugLabel: "text-request",
-  uniqueId: "6976536e-5399-4285-9455-0b70f1dfc92b",
-});
-export const requestJsonEvent = workflowEvent<string>({
-  debugLabel: "json-request",
-  uniqueId: "9fc4a330-52ad-4aac-8092-a650998b7f6f",
-});
-
-export const markdownResultEvent = workflowEvent<string>({
-  debugLabel: "markdown-result",
-  uniqueId: "2dfb57c8-73d1-4394-bea8-f05246d934d4",
-});
-export const textResultEvent = workflowEvent<string>({
-  debugLabel: "text-result",
-  uniqueId: "a27deec6-b24f-4eda-a5ac-ba2fb2bf37c8",
-});
-export const jsonResultEvent = workflowEvent<unknown>({
-  debugLabel: "json-result",
-  uniqueId: "e086e6bd-a612-4f25-ab41-9b31dcb8af86",
-});

packages/cloud/src/parse.ts

@@ -1,225 +0,0 @@
-import { createClient, createConfig } from "@hey-api/client-fetch";
-import { createWorkflow, type InferWorkflowEventData } from "@llama-flow/core";
-import { createStatefulMiddleware } from "@llama-flow/core/middleware/state";
-import { withTraceEvents } from "@llama-flow/core/middleware/trace-events";
-import { pRetryHandler } from "@llama-flow/core/util/p-retry";
-import { fs, getEnv, path } from "@llamaindex/env";
-import {
-  type BodyUploadFileApiV1ParsingUploadPost,
-  getJobApiV1ParsingJobJobIdGet,
-  getJobJsonResultApiV1ParsingJobJobIdResultJsonGet,
-  getJobResultApiV1ParsingJobJobIdResultMarkdownGet,
-  getJobTextResultApiV1ParsingJobJobIdResultTextGet,
-  type StatusEnum,
-  uploadFileApiV1ParsingUploadPost,
-} from "./client";
-import {
-  checkStatusEvent,
-  checkStatusSuccessEvent,
-  jsonResultEvent,
-  markdownResultEvent,
-  requestJsonEvent,
-  requestMarkdownEvent,
-  requestTextEvent,
-  textResultEvent,
-  uploadEvent,
-} from "./events";
-
-export type LlamaParseWorkflowParams = {
-  region?: "us" | "eu" | "us-staging";
-  apiKey?: string;
-};
-
-const URLS = {
-  us: "https://api.cloud.llamaindex.ai",
-  eu: "https://api.cloud.eu.llamaindex.ai",
-  "us-staging": "https://api.staging.llamaindex.ai",
-} as const;
-
-const { withState, getContext } = createStatefulMiddleware(
-  (params: LlamaParseWorkflowParams) => {
-    const apiKey = params.apiKey ?? getEnv("LLAMA_CLOUD_API_KEY");
-    const region = params.region ?? "us";
-    if (!apiKey) {
-      throw new Error("LLAMA_CLOUD_API_KEY is not set");
-    }
-    return {
-      cache: {} as Record<string, StatusEnum>,
-      client: createClient(
-        createConfig({
-          baseUrl: URLS[region],
-          headers: {
-            Authorization: `Bearer ${apiKey}`,
-          },
-        }),
-      ),
-    };
-  },
-);
-
-const llamaParseWorkflow = withState(withTraceEvents(createWorkflow()));
-
-llamaParseWorkflow.handle([uploadEvent], async ({ data: form }) => {
-  const { state } = getContext();
-  const finalForm = { ...form };
-  if ("file" in form) {
-    // support loads from the file system
-    const file = form?.file;
-    const isFilePath = typeof file === "string";
-    const data = isFilePath ? await fs.readFile(file) : file;
-    const filename: string | undefined = isFilePath
-      ? path.basename(file)
-      : undefined;
-    finalForm.file = data
-      ? globalThis.File && filename
-        ? new File([data], filename)
-        : new Blob([data])
-      : undefined;
-  }
-  const {
-    data: { id, status },
-  } = await uploadFileApiV1ParsingUploadPost({
-    throwOnError: true,
-    body: {
-      ...finalForm,
-    } as BodyUploadFileApiV1ParsingUploadPost,
-    client: state.client,
-  });
-  state.cache[id] = status;
-  return checkStatusEvent.with(id);
-});
-
-llamaParseWorkflow.handle(
-  [checkStatusEvent],
-  pRetryHandler(
-    async ({ data: uuid }) => {
-      const { state } = getContext();
-      if (state.cache[uuid] === "SUCCESS") {
-        return checkStatusSuccessEvent.with(uuid);
-      }
-      const {
-        data: { status },
-      } = await getJobApiV1ParsingJobJobIdGet({
-        throwOnError: true,
-        path: {
-          job_id: uuid,
-        },
-        client: state.client,
-      });
-      state.cache[uuid] = status;
-      if (status === "SUCCESS") {
-        return checkStatusSuccessEvent.with(uuid);
-      }
-      throw new Error(`LLamaParse status: ${status}`);
-    },
-    {
-      retries: 100,
-    },
-  ),
-);
-
-//#region sub workflow
-llamaParseWorkflow.handle([requestMarkdownEvent], async ({ data: job_id }) => {
-  const { state } = getContext();
-  const { data } = await getJobResultApiV1ParsingJobJobIdResultMarkdownGet({
-    throwOnError: true,
-    path: {
-      job_id,
-    },
-    client: state.client,
-  });
-  return markdownResultEvent.with(data.markdown);
-});
-
-llamaParseWorkflow.handle([requestTextEvent], async ({ data: job_id }) => {
-  const { state } = getContext();
-  const { data } = await getJobTextResultApiV1ParsingJobJobIdResultTextGet({
-    throwOnError: true,
-    path: {
-      job_id,
-    },
-    client: state.client,
-  });
-  return textResultEvent.with(data.text);
-});
-
-llamaParseWorkflow.handle([requestJsonEvent], async ({ data: job_id }) => {
-  const { state } = getContext();
-  const { data } = await getJobJsonResultApiV1ParsingJobJobIdResultJsonGet({
-    throwOnError: true,
-    path: {
-      job_id,
-    },
-    client: state.client,
-  });
-  return jsonResultEvent.with(data.pages);
-});
-//#endregion
-
-export type ParseJob = {
-  get jobId(): string;
-  get signal(): AbortSignal;
-  get context(): ReturnType<typeof llamaParseWorkflow.createContext>;
-  get form(): InferWorkflowEventData<typeof uploadEvent>;
-
-  markdown(): Promise<string>;
-  text(): Promise<string>;
-  //eslint-disable-next-line @typescript-eslint/no-explicit-any
-  json(): Promise<any[]>;
-};
-
-export const upload = async (
-  params: InferWorkflowEventData<typeof uploadEvent> & LlamaParseWorkflowParams,
-): Promise<ParseJob> => {
-  //#region upload event
-  const context = llamaParseWorkflow.createContext(params);
-  const { stream, sendEvent } = context;
-  const ev = uploadEvent.with(params);
-  sendEvent(ev);
-
-  const uploadThread = await llamaParseWorkflow
-    .substream(ev, stream)
-    .until((ev) => checkStatusSuccessEvent.include(ev))
-    .toArray();
-  //#region
-  const jobId: string = uploadThread.at(-1)!.data;
-  return {
-    get signal() {
-      // lazy load
-      return context.signal;
-    },
-    get jobId() {
-      return jobId;
-    },
-    get form() {
-      return ev.data;
-    },
-    get context() {
-      return context;
-    },
-    async markdown(): Promise<string> {
-      const requestEv = requestMarkdownEvent.with(jobId);
-      const { sendEvent, stream } = llamaParseWorkflow.createContext(params);
-      sendEvent(requestEv);
-      const markdownThread = await stream.until(markdownResultEvent).toArray();
-      return markdownThread.at(-1)!.data;
-    },
-    async text(): Promise<string> {
-      const requestEv = requestTextEvent.with(jobId);
-      const { sendEvent, stream } = llamaParseWorkflow.createContext(params);
-      sendEvent(requestEv);
-      const textThread = await stream.until(textResultEvent).toArray();
-      return textThread.at(-1)!.data;
-    },
-    //eslint-disable-next-line @typescript-eslint/no-explicit-any
-    async json(): Promise<any[]> {
-      const requestEv = requestJsonEvent.with(jobId);
-      const { sendEvent, stream } = llamaParseWorkflow.createContext(params);
-      sendEvent(requestEv);
-      const jsonThread = await stream
-        .until((ev) => jsonResultEvent.include(ev))
-        .toArray();
-      return jsonThread.at(-1)!.data;
-    },
-  };
-};

packages/cloud/src/reader.ts

@@ -1,781 +0,0 @@
-/* eslint-disable @typescript-eslint/no-explicit-any */
-import { type Client, createClient, createConfig } from "@hey-api/client-fetch";
-import { Document, FileReader } from "@llamaindex/core/schema";
-import { fs, getEnv, path } from "@llamaindex/env";
-import {
-  type BodyUploadFileApiParsingUploadPost,
-  type FailPageMode,
-  type ParserLanguages,
-  type ParsingMode,
-  getJobApiV1ParsingJobJobIdGet,
-  getJobImageResultApiV1ParsingJobJobIdResultImageNameGet,
-  getJobJsonResultApiV1ParsingJobJobIdResultJsonGet,
-  getJobResultApiV1ParsingJobJobIdResultMarkdownGet,
-  getJobTextResultApiV1ParsingJobJobIdResultTextGet,
-  uploadFileApiV1ParsingUploadPost,
-} from "./api";
-import { sleep } from "./utils";
-
-export type Language = ParserLanguages;
-export type ResultType = "text" | "markdown" | "json";
-
-// Export the backoff pattern type.
-export type BackoffPattern = "constant" | "linear" | "exponential";
-
-// TODO: should move into @llamaindex/env
-type WriteStream = {
-  write: (text: string) => void;
-};
-
-// Do not modify this variable or cause type errors
-// eslint-disable-next-line no-var
-var process: any;
-
-/**
- * Represents a reader for parsing files using the LlamaParse API.
- * See https://github.com/run-llama/llama_parse
- */
-export class LlamaParseReader extends FileReader {
-  project_id?: string | undefined;
-  organization_id?: string | undefined;
-  // The API key for the LlamaParse API. Can be set as an environment variable: LLAMA_CLOUD_API_KEY
-  apiKey: string;
-  // The base URL of the Llama Cloud Platform.
-  baseUrl: string = "https://api.cloud.llamaindex.ai";
-  // The result type for the parser.
-  resultType: ResultType = "text";
-  // The interval in seconds to check if the parsing is done.
-  checkInterval: number = 1;
-  // The maximum timeout in seconds to wait for the parsing to finish.
-  maxTimeout = 2000;
-  // Whether to print the progress of the parsing.
-  verbose = true;
-  // The language to parse the file in.
-  language: ParserLanguages[] = ["en"];
-
-  // New polling options:
-  // Controls the backoff mode: "constant", "linear", or "exponential".
-  backoffPattern: BackoffPattern = "linear";
-  // Maximum interval in seconds between polls.
-  maxCheckInterval: number = 5;
-  // Maximum number of retryable errors before giving up.
-  maxErrorCount: number = 4;
-
-  // The parsing instruction for the parser. Backend default is an empty string.
-  parsingInstruction?: string | undefined;
-  // Whether to ignore diagonal text (when the text rotation in degrees is not 0, 90, 180, or 270). Backend default is false.
-  skipDiagonalText?: boolean | undefined;
-  // Whether to ignore the cache and re-process the document. Documents are cached for 48 hours after job completion. Backend default is false.
-  invalidateCache?: boolean | undefined;
-  // Whether the document should not be cached. Backend default is false.
-  doNotCache?: boolean | undefined;
-  // Whether to use a faster mode to extract text (skipping OCR and table/heading reconstruction). Not compatible with gpt4oMode. Backend default is false.
-  fastMode?: boolean | undefined;
-  // Whether to keep columns in the text according to document layout. May reduce reconstruction accuracy and LLM/embedings performance.
-  doNotUnrollColumns?: boolean | undefined;
-  // A templated page separator for splitting text. If not set, default is "\n---\n".
-  pageSeparator?: string | undefined;
-  // A templated prefix to add at the beginning of each page.
-  pagePrefix?: string | undefined;
-  // A templated suffix to add at the end of each page.
-  pageSuffix?: string | undefined;
-  // Deprecated. Use vendorMultimodal params. Whether to use gpt-4o to extract text.
-  gpt4oMode: boolean = false;
-  // Deprecated. Use vendorMultimodal params. The API key for GPT-4o. Can be set via LLAMA_CLOUD_GPT4O_API_KEY.
-  gpt4oApiKey?: string | undefined;
-  // The bounding box margins as a string.
-  boundingBox?: string | undefined;
-  // The target pages (comma separated list, starting at 0).
-  targetPages?: string | undefined;
-  // Whether to ignore errors during parsing.
-  ignoreErrors: boolean = true;
-  // Whether to split by page using the pageSeparator (or "\n---\n" as default).
-  splitByPage: boolean = true;
-  // Whether to use the vendor multimodal API.
-  useVendorMultimodalModel: boolean = false;
-  // The model name for the vendor multimodal API.
-  vendorMultimodalModelName?: string | undefined;
-  // The API key for the multimodal API. Can be set via LLAMA_CLOUD_VENDOR_MULTIMODAL_API_KEY.
-  vendorMultimodalApiKey?: string | undefined;
-
-  webhookUrl?: string | undefined;
-  premiumMode?: boolean | undefined;
-  takeScreenshot?: boolean | undefined;
-  disableOcr?: boolean | undefined;
-  disableReconstruction?: boolean | undefined;
-  inputS3Path?: string | undefined;
-  outputS3PathPrefix?: string | undefined;
-  continuousMode?: boolean | undefined;
-  isFormattingInstruction?: boolean | undefined;
-  annotateLinks?: boolean | undefined;
-  azureOpenaiDeploymentName?: string | undefined;
-  azureOpenaiEndpoint?: string | undefined;
-  azureOpenaiApiVersion?: string | undefined;
-  azureOpenaiKey?: string | undefined;
-  auto_mode?: boolean | undefined;
-  auto_mode_trigger_on_image_in_page?: boolean | undefined;
-  auto_mode_trigger_on_table_in_page?: boolean | undefined;
-  auto_mode_trigger_on_text_in_page?: string | undefined;
-  auto_mode_trigger_on_regexp_in_page?: string | undefined;
-  bbox_bottom?: number | undefined;
-  bbox_left?: number | undefined;
-  bbox_right?: number | undefined;
-  bbox_top?: number | undefined;
-  disable_image_extraction?: boolean | undefined;
-  extract_charts?: boolean | undefined;
-  guess_xlsx_sheet_name?: boolean | undefined;
-  html_make_all_elements_visible?: boolean | undefined;
-  html_remove_fixed_elements?: boolean | undefined;
-  html_remove_navigation_elements?: boolean | undefined;
-  http_proxy?: string | undefined;
-  input_url?: string | undefined;
-  max_pages?: number | undefined;
-  output_pdf_of_document?: boolean | undefined;
-  structured_output?: boolean | undefined;
-  structured_output_json_schema?: string | undefined;
-  structured_output_json_schema_name?: string | undefined;
-  extract_layout?: boolean | undefined;
-
-  // numWorkers is implemented in SimpleDirectoryReader
-  stdout?: WriteStream | undefined;
-
-  readonly #client: Client;
-
-  output_tables_as_HTML: boolean = false;
-  input_s3_region?: string | undefined;
-  output_s3_region?: string | undefined;
-  preserve_layout_alignment_across_pages?: boolean | undefined;
-  spreadsheet_extract_sub_tables?: boolean | undefined;
-  formatting_instruction?: string | undefined;
-  parse_mode?: ParsingMode | undefined;
-  system_prompt?: string | undefined;
-  system_prompt_append?: string | undefined;
-  user_prompt?: string | undefined;
-  job_timeout_in_seconds?: number | undefined;
-  job_timeout_extra_time_per_page_in_seconds?: number | undefined;
-  strict_mode_image_extraction?: boolean | undefined;
-  strict_mode_image_ocr?: boolean | undefined;
-  strict_mode_reconstruction?: boolean | undefined;
-  strict_mode_buggy_font?: boolean | undefined;
-  ignore_document_elements_for_layout_detection?: boolean | undefined;
-  complemental_formatting_instruction?: string | undefined;
-  content_guideline_instruction?: string | undefined;
-  adaptive_long_table?: boolean | undefined;
-  model?: string | undefined;
-  auto_mode_configuration_json?: string | undefined;
-  compact_markdown_table?: boolean | undefined;
-  markdown_table_multiline_header_separator?: string | undefined;
-  page_error_tolerance?: number | undefined;
-  replace_failed_page_mode?: FailPageMode | undefined;
-  replace_failed_page_with_error_message_prefix?: string | undefined;
-  replace_failed_page_with_error_message_suffix?: string | undefined;
-  save_images?: boolean | undefined;
-  preset?: string | undefined;
-  high_res_ocr?: boolean | undefined;
-  outlined_table_extraction?: boolean | undefined;
-  hide_headers?: boolean | undefined;
-  hide_footers?: boolean | undefined;
-  page_header_prefix?: string | undefined;
-  page_header_suffix?: string | undefined;
-  page_footer_prefix?: string | undefined;
-  page_footer_suffix?: string | undefined;
-  merge_tables_across_pages_in_markdown?: boolean | undefined;
-
-  constructor(
-    params: Partial<Omit<LlamaParseReader, "language" | "apiKey">> & {
-      language?: ParserLanguages | ParserLanguages[] | undefined;
-      apiKey?: string | undefined;
-    } = {},
-  ) {
-    super();
-    Object.assign(this, params);
-    this.language = Array.isArray(this.language)
-      ? this.language
-      : [this.language];
-    this.stdout =
-      (params.stdout ?? typeof process !== "undefined")
-        ? process!.stdout
-        : undefined;
-    const apiKey = params.apiKey ?? getEnv("LLAMA_CLOUD_API_KEY");
-    if (!apiKey) {
-      throw new Error(
-        "API Key is required for LlamaParseReader. Please pass the apiKey parameter or set the LLAMA_CLOUD_API_KEY environment variable.",
-      );
-    }
-    this.apiKey = apiKey;
-    if (this.baseUrl.endsWith("/")) {
-      this.baseUrl = this.baseUrl.slice(0, -1);
-    }
-    if (this.baseUrl.endsWith("/api/parsing")) {
-      this.baseUrl = this.baseUrl.slice(0, -"/api/parsing".length);
-    }
-
-    if (params.gpt4oMode) {
-      params.gpt4oApiKey =
-        params.gpt4oApiKey ?? getEnv("LLAMA_CLOUD_GPT4O_API_KEY");
-
-      this.gpt4oApiKey = params.gpt4oApiKey;
-    }
-    if (params.useVendorMultimodalModel) {
-      params.vendorMultimodalApiKey =
-        params.vendorMultimodalApiKey ??
-        getEnv("LLAMA_CLOUD_VENDOR_MULTIMODAL_API_KEY");
-
-      this.vendorMultimodalApiKey = params.vendorMultimodalApiKey;
-    }
-
-    this.#client = createClient(
-      createConfig({
-        headers: {
-          Authorization: `Bearer ${this.apiKey}`,
-        },
-        baseUrl: this.baseUrl,
-      }),
-    );
-  }
-
-  /**
-   * Creates a job for the LlamaParse API.
-   *
-   * @param data - The file data as a Uint8Array.
-   * @param filename - Optional filename for the file.
-   * @returns A Promise resolving to the job ID as a string.
-   */
-  async #createJob(
-    data: Uint8Array | string,
-    filename?: string,
-  ): Promise<string> {
-    if (this.verbose) {
-      console.log("Started uploading the file");
-    }
-
-    let file: File | Blob | null = null;
-    let input_s3_path: string | undefined = this.inputS3Path;
-    let input_url: string | undefined = this.input_url;
-    if (typeof data !== "string") {
-      // TODO: remove Blob usage when we drop Node.js 18 support
-      file =
-        globalThis.File && filename
-          ? new File([data], filename)
-          : new Blob([data]);
-    } else if (data.startsWith("s3://")) {
-      input_s3_path = data;
-    } else if (data.startsWith("http://") || data.startsWith("https://")) {
-      input_url = data;
-    }
-
-    const body = {
-      file,
-      input_s3_path,
-      input_url,
-      language: this.language,
-      parsing_instruction: this.parsingInstruction,
-      skip_diagonal_text: this.skipDiagonalText,
-      invalidate_cache: this.invalidateCache,
-      do_not_cache: this.doNotCache,
-      fast_mode: this.fastMode,
-      do_not_unroll_columns: this.doNotUnrollColumns,
-      page_separator: this.pageSeparator,
-      page_prefix: this.pagePrefix,
-      page_suffix: this.pageSuffix,
-      gpt4o_mode: this.gpt4oMode,
-      gpt4o_api_key: this.gpt4oApiKey,
-      bounding_box: this.boundingBox,
-      target_pages: this.targetPages,
-      use_vendor_multimodal_model: this.useVendorMultimodalModel,
-      vendor_multimodal_model_name: this.vendorMultimodalModelName,
-      vendor_multimodal_api_key: this.vendorMultimodalApiKey,
-      premium_mode: this.premiumMode,
-      webhook_url: this.webhookUrl,
-      take_screenshot: this.takeScreenshot,
-      disable_ocr: this.disableOcr,
-      disable_reconstruction: this.disableReconstruction,
-      output_s3_path_prefix: this.outputS3PathPrefix,
-      continuous_mode: this.continuousMode,
-      is_formatting_instruction: this.isFormattingInstruction,
-      annotate_links: this.annotateLinks,
-      azure_openai_deployment_name: this.azureOpenaiDeploymentName,
-      azure_openai_endpoint: this.azureOpenaiEndpoint,
-      azure_openai_api_version: this.azureOpenaiApiVersion,
-      azure_openai_key: this.azureOpenaiKey,
-      auto_mode: this.auto_mode,
-      auto_mode_trigger_on_image_in_page:
-        this.auto_mode_trigger_on_image_in_page,
-      auto_mode_trigger_on_table_in_page:
-        this.auto_mode_trigger_on_table_in_page,
-      auto_mode_trigger_on_text_in_page: this.auto_mode_trigger_on_text_in_page,
-      auto_mode_trigger_on_regexp_in_page:
-        this.auto_mode_trigger_on_regexp_in_page,
-      bbox_bottom: this.bbox_bottom,
-      bbox_left: this.bbox_left,
-      bbox_right: this.bbox_right,
-      bbox_top: this.bbox_top,
-      disable_image_extraction: this.disable_image_extraction,
-      extract_charts: this.extract_charts,
-      guess_xlsx_sheet_name: this.guess_xlsx_sheet_name,
-      html_make_all_elements_visible: this.html_make_all_elements_visible,
-      html_remove_fixed_elements: this.html_remove_fixed_elements,
-      html_remove_navigation_elements: this.html_remove_navigation_elements,
-      http_proxy: this.http_proxy,
-      max_pages: this.max_pages,
-      output_pdf_of_document: this.output_pdf_of_document,
-      structured_output: this.structured_output,
-      structured_output_json_schema: this.structured_output_json_schema,
-      structured_output_json_schema_name:
-        this.structured_output_json_schema_name,
-      extract_layout: this.extract_layout,
-      output_tables_as_HTML: this.output_tables_as_HTML,
-      input_s3_region: this.input_s3_region,
-      output_s3_region: this.output_s3_region,
-      preserve_layout_alignment_across_pages:
-        this.preserve_layout_alignment_across_pages,
-      spreadsheet_extract_sub_tables: this.spreadsheet_extract_sub_tables,
-      formatting_instruction: this.formatting_instruction,
-      parse_mode: this.parse_mode,
-      system_prompt: this.system_prompt,
-      system_prompt_append: this.system_prompt_append,
-      user_prompt: this.user_prompt,
-      job_timeout_in_seconds: this.job_timeout_in_seconds,
-      job_timeout_extra_time_per_page_in_seconds:
-        this.job_timeout_extra_time_per_page_in_seconds,
-      strict_mode_image_extraction: this.strict_mode_image_extraction,
-      strict_mode_image_ocr: this.strict_mode_image_ocr,
-      strict_mode_reconstruction: this.strict_mode_reconstruction,
-      strict_mode_buggy_font: this.strict_mode_buggy_font,
-      ignore_document_elements_for_layout_detection:
-        this.ignore_document_elements_for_layout_detection,
-      complemental_formatting_instruction:
-        this.complemental_formatting_instruction,
-      content_guideline_instruction: this.content_guideline_instruction,
-      adaptive_long_table: this.adaptive_long_table,
-      model: this.model,
-      auto_mode_configuration_json: this.auto_mode_configuration_json,
-      compact_markdown_table: this.compact_markdown_table,
-      markdown_table_multiline_header_separator:
-        this.markdown_table_multiline_header_separator,
-      page_error_tolerance: this.page_error_tolerance,
-      replace_failed_page_mode: this.replace_failed_page_mode,
-      replace_failed_page_with_error_message_prefix:
-        this.replace_failed_page_with_error_message_prefix,
-      replace_failed_page_with_error_message_suffix:
-        this.replace_failed_page_with_error_message_suffix,
-      save_images: this.save_images,
-      preset: this.preset,
-      high_res_ocr: this.high_res_ocr,
-      outlined_table_extraction: this.outlined_table_extraction,
-      hide_headers: this.hide_headers,
-      hide_footers: this.hide_footers,
-      page_header_prefix: this.page_header_prefix,
-      page_header_suffix: this.page_header_suffix,
-      page_footer_prefix: this.page_footer_prefix,
-      page_footer_suffix: this.page_footer_suffix,
-      merge_tables_across_pages_in_markdown:
-        this.merge_tables_across_pages_in_markdown,
-    } satisfies {
-      [Key in keyof BodyUploadFileApiParsingUploadPost]-?:
-        | BodyUploadFileApiParsingUploadPost[Key]
-        | undefined;
-    } as unknown as BodyUploadFileApiParsingUploadPost;
-
-    const response = await uploadFileApiV1ParsingUploadPost({
-      client: this.#client,
-      throwOnError: true,
-      query: {
-        project_id: this.project_id ?? null,
-        organization_id: this.organization_id ?? null,
-      },
-      signal: AbortSignal.timeout(this.maxTimeout * 1000),
-      body,
-    });
-
-    return response.data.id;
-  }
-
-  /**
-   * Retrieves the result of a parsing job.
-   *
-   * Uses a polling loop with retry logic. Each API call is retried
-   * up to maxErrorCount times if it fails with a 5XX or socket error.
-   * The delay between polls increases according to the specified backoffPattern ("constant", "linear", or "exponential"),
-   * capped by maxCheckInterval.
-   *
-   * @param jobId - The job ID.
-   * @param resultType - The type of result to fetch ("text", "json", or "markdown").
-   * @returns A Promise resolving to the job result.
-   */
-  private async getJobResult(
-    jobId: string,
-    resultType: "text" | "json" | "markdown",
-  ): Promise<any> {
-    let tries = 0;
-    let currentInterval = this.checkInterval;
-    const { default: pRetry } = await import("p-retry");
-
-    while (true) {
-      await sleep(currentInterval * 1000);
-
-      // Wraps the API call in a retry
-      let result;
-      try {
-        result = await pRetry(
-          () =>
-            getJobApiV1ParsingJobJobIdGet({
-              client: this.#client,
-              throwOnError: true,
-              path: { job_id: jobId },
-              signal: AbortSignal.timeout(this.maxTimeout * 1000),
-            }),
-          {
-            retries: this.maxErrorCount,
-            onFailedAttempt: (error) => {
-              // Retry only on 5XX or socket errors.
-              const status = (error.cause as any)?.response?.status;
-              if (
-                !(
-                  (status && status >= 500 && status < 600) ||
-                  ((error.cause as any)?.code &&
-                    ((error.cause as any).code === "ECONNRESET" ||
-                      (error.cause as any).code === "ETIMEDOUT" ||
-                      (error.cause as any).code === "ECONNREFUSED"))
-                )
-              ) {
-                throw error;
-              }
-              if (this.verbose) {
-                console.warn(
-                  `Attempting to get job ${jobId} result (attempt ${error.attemptNumber}) failed. Retrying...`,
-                );
-              }
-            },
-          },
-        );
-      } catch (e: any) {
-        throw new Error(
-          `Max error count reached for job ${jobId}: ${e.message}`,
-        );
-      }
-
-      const { data } = result;
-      const status = (data as Record<string, unknown>)["status"];
-
-      if (status === "SUCCESS") {
-        let resultData;
-        switch (resultType) {
-          case "json": {
-            resultData =
-              await getJobJsonResultApiV1ParsingJobJobIdResultJsonGet({
-                client: this.#client,
-                throwOnError: true,
-                path: { job_id: jobId },
-                query: {
-                  organization_id: this.organization_id ?? null,
-                },
-                signal: AbortSignal.timeout(this.maxTimeout * 1000),
-              });
-            break;
-          }
-          case "markdown": {
-            resultData =
-              await getJobResultApiV1ParsingJobJobIdResultMarkdownGet({
-                client: this.#client,
-                throwOnError: true,
-                path: { job_id: jobId },
-                query: {
-                  organization_id: this.organization_id ?? null,
-                },
-                signal: AbortSignal.timeout(this.maxTimeout * 1000),
-              });
-            break;
-          }
-          case "text": {
-            resultData =
-              await getJobTextResultApiV1ParsingJobJobIdResultTextGet({
-                client: this.#client,
-                throwOnError: true,
-                path: { job_id: jobId },
-                query: {
-                  organization_id: this.organization_id ?? null,
-                },
-                signal: AbortSignal.timeout(this.maxTimeout * 1000),
-              });
-            break;
-          }
-        }
-        return resultData.data;
-      } else if (status === "PENDING") {
-        if (this.verbose && tries % 10 === 0) {
-          this.stdout?.write(".");
-        }
-        tries++;
-      } else {
-        if (this.verbose) {
-          console.error(
-            `Received error response ${status} for job ${jobId}. Got Error Code: ${data.error_code} and Error Message: ${data.error_message}`,
-          );
-        }
-        throw new Error(
-          `Failed to parse the file: ${jobId}, status: ${status}`,
-        );
-      }
-
-      // Adjust the polling interval based on the backoff pattern.
-      if (this.backoffPattern === "exponential") {
-        currentInterval = Math.min(currentInterval * 2, this.maxCheckInterval);
-      } else if (this.backoffPattern === "linear") {
-        currentInterval = Math.min(
-          currentInterval + this.checkInterval,
-          this.maxCheckInterval,
-        );
-      } else if (this.backoffPattern === "constant") {
-        currentInterval = this.checkInterval;
-      }
-    }
-  }
-
-  override async loadData(filePath?: string): Promise<Document[]> {
-    if (!filePath) {
-      if (this.input_url) {
-        return this.loadDataAsContent(this.input_url, this.input_url);
-      } else if (this.inputS3Path) {
-        return this.loadDataAsContent(this.inputS3Path, this.inputS3Path);
-      } else {
-        throw new TypeError("File path is required");
-      }
-    } else {
-      const data =
-        filePath.startsWith("s3://") ||
-        filePath.startsWith("http://") ||
-        filePath.startsWith("https://")
-          ? filePath
-          : await fs.readFile(filePath);
-      return this.loadDataAsContent(data, filePath);
-    }
-  }
-
-  /**
-   * Loads data from a file and returns an array of Document objects.
-   * To be used with resultType "text" or "markdown".
-   *
-   * @param fileContent - The content of the file as a Uint8Array.
-   * @param filename - Optional filename for the file.
-   * @returns A Promise that resolves to an array of Document objects.
-   */
-  async loadDataAsContent(
-    fileContent: Uint8Array | string,
-    filename?: string,
-  ): Promise<Document[]> {
-    return this.#createJob(fileContent, filename)
-      .then(async (jobId) => {
-        if (this.verbose) {
-          console.log(`Started parsing the file under job id ${jobId}`);
-        }
-
-        // Return results as Document objects.
-        const jobResults = await this.getJobResult(jobId, this.resultType);
-        const resultText = jobResults[this.resultType];
-
-        // Split the text by separator if splitByPage is true.
-        if (this.splitByPage) {
-          return this.splitTextBySeparator(resultText);
-        }
-
-        return [new Document({ text: resultText })];
-      })
-      .catch((error) => {
-        console.warn(
-          `Error while parsing the file with: ${error.message ?? error.detail}`,
-        );
-        if (this.ignoreErrors) {
-          return [];
-        } else {
-          throw error;
-        }
-      });
-  }
-
-  /**
-   * Loads data from a file and returns an array of JSON objects.
-   * To be used with resultType "json".
-   *
-   * @param filePathOrContent - The file path or the file content as a Uint8Array.
-   * @returns A Promise that resolves to an array of JSON objects.
-   */
-  async loadJson(
-    filePathOrContent: string | Uint8Array,
-  ): Promise<Record<string, any>[]> {
-    let jobId;
-    const isFilePath =
-      typeof filePathOrContent === "string" &&
-      !(
-        filePathOrContent.startsWith("s3://") ||
-        filePathOrContent.startsWith("http://") ||
-        filePathOrContent.startsWith("https://")
-      );
-    try {
-      const data = isFilePath
-        ? await fs.readFile(filePathOrContent)
-        : filePathOrContent;
-      // Create a job for the file.
-      jobId = await this.#createJob(
-        data,
-        isFilePath ? path.basename(filePathOrContent) : undefined,
-      );
-      if (this.verbose) {
-        console.log(`Started parsing the file under job id ${jobId}`);
-      }
-
-      // Return results as an array of JSON objects.
-      const resultJson = await this.getJobResult(jobId, "json");
-      resultJson.job_id = jobId;
-      resultJson.file_path = isFilePath ? filePathOrContent : undefined;
-      return [resultJson];
-    } catch (e) {
-      console.error(`Error while parsing the file under job id ${jobId}`, e);
-      if (this.ignoreErrors) {
-        return [];
-      } else {
-        throw e;
-      }
-    }
-  }
-
-  /**
-   * Downloads and saves images from a given JSON result to a specified download path.
-   * Currently only supports resultType "json".
-   *
-   * @param jsonResult - The JSON result containing image information.
-   * @param downloadPath - The path where the downloaded images will be saved.
-   * @returns A Promise that resolves to an array of image objects.
-   */
-  async getImages(
-    jsonResult: Record<string, any>[],
-    downloadPath: string,
-  ): Promise<Record<string, any>[]> {
-    try {
-      // Create download directory if it doesn't exist (checks for write access).
-      try {
-        await fs.access(downloadPath);
-      } catch {
-        await fs.mkdir(downloadPath, { recursive: true });
-      }
-
-      const images: Record<string, any>[] = [];
-      for (const result of jsonResult) {
-        const jobId = result.job_id;
-        for (const page of result.pages) {
-          if (this.verbose) {
-            console.log(`> Image for page ${page.page}: ${page.images}`);
-          }
-          for (const image of page.images) {
-            const imageName = image.name;
-            const imagePath = await this.getImagePath(
-              downloadPath,
-              jobId,
-              imageName,
-            );
-            await this.fetchAndSaveImage(imageName, imagePath, jobId);
-            // Assign metadata to the image.
-            image.path = imagePath;
-            image.job_id = jobId;
-            image.original_pdf_path = result.file_path;
-            image.page_number = page.page;
-            images.push(image);
-          }
-        }
-      }
-      return images;
-    } catch (e) {
-      console.error(`Error while downloading images from the parsed result`, e);
-      if (this.ignoreErrors) {
-        return [];
-      } else {
-        throw e;
-      }
-    }
-  }
-
-  /**
-   * Constructs the file path for an image.
-   *
-   * @param downloadPath - The base download directory.
-   * @param jobId - The job ID.
-   * @param imageName - The image name.
-   * @returns A Promise that resolves to the full image path.
-   */
-  private async getImagePath(
-    downloadPath: string,
-    jobId: string,
-    imageName: string,
-  ): Promise<string> {
-    return path.join(downloadPath, `${jobId}-${imageName}`);
-  }
-
-  /**
-   * Fetches an image from the API and saves it to the specified path.
-   *
-   * @param imageName - The name of the image.
-   * @param imagePath - The local path to save the image.
-   * @param jobId - The associated job ID.
-   */
-  private async fetchAndSaveImage(
-    imageName: string,
-    imagePath: string,
-    jobId: string,
-  ): Promise<void> {
-    const response =
-      await getJobImageResultApiV1ParsingJobJobIdResultImageNameGet({
-        client: this.#client,
-        path: {
-          job_id: jobId,
-          name: imageName,
-        },
-      });
-    if (response.error) {
-      throw new Error(`Failed to download image: ${response.error.detail}`);
-    }
-    const blob = (await response.data) as Blob;
-    // Write the image buffer to the specified imagePath.
-    await fs.writeFile(imagePath, new Uint8Array(await blob.arrayBuffer()));
-  }
-
-  /**
-   * Filters out invalid values (null, undefined, empty string) for specific parameters.
-   *
-   * @param params - The parameters object.
-   * @param keysToCheck - The keys to check for valid values.
-   * @returns A new object with filtered parameters.
-   */
-  private filterSpecificParams(
-    params: Record<string, any>,
-    keysToCheck: string[],
-  ): Record<string, any> {
-    const filteredParams: Record<string, any> = {};
-    for (const [key, value] of Object.entries(params)) {
-      if (keysToCheck.includes(key)) {
-        if (value !== null && value !== undefined && value !== "") {
-          filteredParams[key] = value;
-        }
-      } else {
-        filteredParams[key] = value;
-      }
-    }
-    return filteredParams;
-  }
-
-  /**
-   * Splits text into Document objects using the page separator.
-   *
-   * @param text - The text to be split.
-   * @returns An array of Document objects.
-   */
-  private splitTextBySeparator(text: string): Document[] {
-    const separator = this.pageSeparator ?? "\n---\n";
-    const textChunks = text.split(separator);
-    return textChunks.map(
-      (docChunk: string) =>
-        new Document({
-          text: docChunk,
-        }),
-    );
-  }
-}

packages/cloud/src/schema.ts

@@ -1,131 +0,0 @@
-import { FailPageMode, ParserLanguages, ParsingMode } from "./client";
-
-import { z } from "zod";
-
-type Language = ParserLanguages;
-const VALUES: [Language, ...Language[]] = [
-  ParserLanguages.EN,
-  ...Object.values(ParserLanguages),
-];
-const languageSchema = z.enum(VALUES);
-
-const PARSE_PRESETS = [
-  "fast",
-  "balanced",
-  "premium",
-  "structured",
-  "auto",
-  "scientific",
-  "invoice",
-  "slides",
-  "_carlyle",
-] as const;
-
-export const parsePresetSchema = z.enum(PARSE_PRESETS);
-
-export const parseFormSchema = z.object({
-  adaptive_long_table: z.boolean().optional(),
-  annotate_links: z.boolean().optional(),
-  auto_mode: z.boolean().optional(),
-  auto_mode_trigger_on_image_in_page: z.boolean().optional(),
-  auto_mode_trigger_on_table_in_page: z.boolean().optional(),
-  auto_mode_trigger_on_text_in_page: z.string().optional(),
-  auto_mode_trigger_on_regexp_in_page: z.string().optional(),
-  auto_mode_configuration_json: z.string().optional(),
-  azure_openai_api_version: z.string().optional(),
-  azure_openai_deployment_name: z.string().optional(),
-  azure_openai_endpoint: z.string().optional(),
-  azure_openai_key: z.string().optional(),
-  bbox_bottom: z.number().min(0).max(1).optional(),
-  bbox_left: z.number().min(0).max(1).optional(),
-  bbox_right: z.number().min(0).max(1).optional(),
-  bbox_top: z.number().min(0).max(1).optional(),
-  disable_ocr: z.boolean().optional(),
-  disable_reconstruction: z.boolean().optional(),
-  disable_image_extraction: z.boolean().optional(),
-  do_not_cache: z.coerce.boolean().optional(),
-  do_not_unroll_columns: z.coerce.boolean().optional(),
-  extract_charts: z.boolean().optional(),
-  guess_xlsx_sheet_name: z.boolean().optional(),
-  html_make_all_elements_visible: z.boolean().optional(),
-  html_remove_fixed_elements: z.boolean().optional(),
-  html_remove_navigation_elements: z.boolean().optional(),
-  http_proxy: z
-    .string()
-    .url(
-      'Set a valid URL for the HTTP proxy, e.g., "http://proxy.example.com:8080"',
-    )
-    .refine(
-      (url) => {
-        try {
-          const parsedUrl = new URL(url);
-          return (
-            parsedUrl.protocol === "http:" || parsedUrl.protocol === "https:"
-          );
-        } catch {
-          return false;
-        }
-      },
-      {
-        message: "Invalid HTTP proxy URL",
-      },
-    )
-    .optional(),
-  input_s3_path: z.string().optional(),
-  input_s3_region: z.string().optional(),
-  input_url: z.string().optional(),
-  invalidate_cache: z.boolean().optional(),
-  language: z.array(languageSchema).optional(),
-  extract_layout: z.boolean().optional(),
-  max_pages: z.number().nullable().optional(),
-  output_pdf_of_document: z.boolean().optional(),
-  output_s3_path_prefix: z.string().optional(),
-  output_s3_region: z.string().optional(),
-  page_prefix: z.string().optional(),
-  page_separator: z.string().optional(),
-  page_suffix: z.string().optional(),
-  preserve_layout_alignment_across_pages: z.boolean().optional(),
-  skip_diagonal_text: z.boolean().optional(),
-  spreadsheet_extract_sub_tables: z.boolean().optional(),
-  structured_output: z.boolean().optional(),
-  structured_output_json_schema: z.string().optional(),
-  structured_output_json_schema_name: z.string().optional(),
-  take_screenshot: z.boolean().optional(),
-  target_pages: z.string().optional(),
-  vendor_multimodal_api_key: z.string().optional(),
-  vendor_multimodal_model_name: z.string().optional(),
-  model: z.string().optional(),
-  webhook_url: z.string().url().optional(),
-  parse_mode: z.nativeEnum(ParsingMode).nullable().optional(),
-  system_prompt: z.string().optional(),
-  system_prompt_append: z.string().optional(),
-  user_prompt: z.string().optional(),
-  job_timeout_in_seconds: z.number().optional(),
-  job_timeout_extra_time_per_page_in_seconds: z.number().optional(),
-  strict_mode_image_extraction: z.boolean().optional(),
-  strict_mode_image_ocr: z.boolean().optional(),
-  strict_mode_reconstruction: z.boolean().optional(),
-  strict_mode_buggy_font: z.boolean().optional(),
-  save_images: z.boolean().optional(),
-  ignore_document_elements_for_layout_detection: z.boolean().optional(),
-  output_tables_as_HTML: z.boolean().optional(),
-  use_vendor_multimodal_model: z.boolean().optional(),
-  bounding_box: z.string().optional(),
-  gpt4o_mode: z.boolean().optional(),
-  gpt4o_api_key: z.string().optional(),
-  complemental_formatting_instruction: z.string().optional(),
-  content_guideline_instruction: z.string().optional(),
-  premium_mode: z.boolean().optional(),
-  is_formatting_instruction: z.boolean().optional(),
-  continuous_mode: z.boolean().optional(),
-  parsing_instruction: z.string().optional(),
-  fast_mode: z.boolean().optional(),
-  formatting_instruction: z.string().optional(),
-  preset: parsePresetSchema.optional(),
-  compact_markdown_table: z.boolean().optional(),
-  markdown_table_multiline_header_separator: z.string().optional(),
-  page_error_tolerance: z.number().min(0).max(1).optional(),
-  replace_failed_page_mode: z.nativeEnum(FailPageMode).nullable().optional(),
-  replace_failed_page_with_error_message_prefix: z.string().optional(),
-  replace_failed_page_with_error_message_suffix: z.string().optional(),
-});

packages/cloud/src/utils.ts

@@ -1,3 +0,0 @@
-export async function sleep(ms: number): Promise<void> {
-  return new Promise((resolve) => setTimeout(resolve, ms));
-}

packages/cloud/turbo.json

@@ -1,9 +0,0 @@
-{
-  "$schema": "https://turbo.build/schema.json",
-  "extends": ["//"],
-  "tasks": {
-    "build": {
-      "outputs": ["**/dist/**", "src/client/**"]
-    }
-  }
-}

packages/community/CHANGELOG.md

@@ -1,152 +1,27 @@
-# @llamaindex/cloud
+# @llamaindex/community
 
-## 4.0.26
+## 0.0.101
 
 ### Patch Changes
 
-- Updated dependencies [38da40b]
-  - @llamaindex/core@0.6.17
+- Updated dependencies [f9f1de9]
+  - @llamaindex/core@0.6.19
 
-## 4.0.25
+## 0.0.100
 
 ### Patch Changes
 
-- 2967d57: Default to \_public agent url id
-- Updated dependencies [a8ec08c]
-  - @llamaindex/core@0.6.16
+- Updated dependencies [f29799e]
+- Updated dependencies [7224c06]
+  - @llamaindex/core@0.6.18
 
-## 4.0.24
+## 0.0.99
 
 ### Patch Changes
 
-- Updated dependencies [7ad3411]
-- Updated dependencies [5da5b3c]
-  - @llamaindex/core@0.6.15
+- c65a2dc: Deprecate community package and link to AWS package
 
-## 4.0.23
-
-### Patch Changes
-
-- a1b1598: fix: add generic types into agent data responses
-
-## 4.0.22
-
-### Patch Changes
-
-- d2be868: Bug fixes for new beta agent-data cloud API
-
-## 4.0.21
-
-### Patch Changes
-
-- 579ca0c: chore: bump sdk version
-
-## 4.0.20
-
-### Patch Changes
-
-- 48b0d88: fix: exports in `api` submodule
-- f185772: fix(cloud): missing file
-
-## 4.0.19
-
-### Patch Changes
-
-- 5a0ed1f: feat: init agent api on cloud sdk
-- 5a0ed1f: feat: init agent api on cloud sdk
-- Updated dependencies [8eeac33]
-  - @llamaindex/core@0.6.14
-
-## 4.0.18
-
-### Patch Changes
-
-- 47a7555: chore: bump sdk version
-
-## 4.0.17
-
-### Patch Changes
-
-- Updated dependencies [d578889]
-- Updated dependencies [0fcc92f]
-- Updated dependencies [515a8b9]
-  - @llamaindex/core@0.6.13
-
-## 4.0.16
-
-### Patch Changes
-
-- Updated dependencies [7039e1a]
-- Updated dependencies [7039e1a]
-  - @llamaindex/core@0.6.12
-
-## 4.0.15
-
-### Patch Changes
-
-- Updated dependencies [a89e187]
-- Updated dependencies [62699b7]
-- Updated dependencies [c5b2691]
-- Updated dependencies [d8ac8d3]
-  - @llamaindex/core@0.6.11
-
-## 4.0.14
-
-### Patch Changes
-
-- Updated dependencies [1b5af14]
-  - @llamaindex/core@0.6.10
-
-## 4.0.13
-
-### Patch Changes
-
-- Updated dependencies [71598f8]
-  - @llamaindex/core@0.6.9
-
-## 4.0.12
-
-### Patch Changes
-
-- Updated dependencies [c927457]
-  - @llamaindex/core@0.6.8
-
-## 4.0.11
-
-### Patch Changes
-
-- 76ff23d: Fix pRetry not working with CommonJS
-
-## 4.0.10
-
-### Patch Changes
-
-- Updated dependencies [59601dd]
-  - @llamaindex/core@0.6.7
-
-## 4.0.9
-
-### Patch Changes
-
-- 3703f90: feat(parse): add upload API
-
-## 4.0.8
-
-### Patch Changes
-
-- Updated dependencies [680b529]
-- Updated dependencies [361a685]
-  - @llamaindex/core@0.6.6
-
-## 4.0.7
-
-### Patch Changes
-
-- 40f5f41: Improve the loadJson function in LlamaParseReader to align with loadData by allowing URL inputs. Ensures s3://, http://, and https:// paths are not treated as local file paths.
-- Updated dependencies [d671ed6]
-  - @llamaindex/core@0.6.5
-
-## 4.0.6
+## 0.0.98
 
 ### Patch Changes
 
@@ -154,33 +29,33 @@
   - @llamaindex/core@0.6.4
   - @llamaindex/env@0.1.30
 
-## 4.0.5
-
-### Patch Changes
-
-- 2225ffd: feat: bump llama cloud sdk
-
-## 4.0.4
+## 0.0.97
 
 ### Patch Changes
 
 - Updated dependencies [3ee8c83]
   - @llamaindex/core@0.6.3
 
-## 4.0.3
+## 0.0.96
 
 ### Patch Changes
 
-- 41191d0: fix(parse): file input
+- e9bf442: fix: update the tool call schema for nova
 
-## 4.0.2
+## 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
 
-## 4.0.1
+## 0.0.93
 
 ### Patch Changes
 
@@ -188,75 +63,77 @@
 - Updated dependencies [eaf326e]
   - @llamaindex/core@0.6.1
 
-## 4.0.0
+## 0.0.92
+
+### Patch Changes
+
+- 1325178: fix: stringify all tool results for anthropic on bedrock
+
+## 0.0.91
 
 ### Patch Changes
 
-- bf56fc0: chore: bump sdk openapi.json
 - 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
 
-## 3.0.9
+## 0.0.90
 
 ### Patch Changes
 
 - Updated dependencies [40ee761]
   - @llamaindex/core@0.5.8
 
-## 3.0.8
+## 0.0.89
 
 ### Patch Changes
 
 - Updated dependencies [4bac71d]
   - @llamaindex/core@0.5.7
 
-## 3.0.7
+## 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
 
-## 3.0.6
+## 0.0.87
 
 ### Patch Changes
 
 - Updated dependencies [5668970]
   - @llamaindex/core@0.5.5
 
-## 3.0.5
+## 0.0.86
 
 ### Patch Changes
 
 - Updated dependencies [ad3c7f1]
   - @llamaindex/core@0.5.4
 
-## 3.0.4
+## 0.0.85
 
 ### Patch Changes
 
+- 1914b52: Added Claude 3.7 Sonnet support
 - Updated dependencies [cb021e7]
   - @llamaindex/core@0.5.3
 
-## 3.0.3
+## 0.0.84
 
 ### Patch Changes
 
 - Updated dependencies [d952e68]
   - @llamaindex/core@0.5.2
 
-## 3.0.2
-
-### Patch Changes
-
-- c902fcb: chore: bump llamacloud openapi
-
-## 3.0.1
+## 0.0.83
 
 ### Patch Changes
 
@@ -264,7 +141,7 @@
   - @llamaindex/env@0.1.28
   - @llamaindex/core@0.5.1
 
-## 3.0.0
+## 0.0.82
 
 ### Patch Changes
 
@@ -272,7 +149,7 @@
 - Updated dependencies [d924c63]
   - @llamaindex/core@0.5.0
 
-## 2.0.24
+## 0.0.81
 
 ### Patch Changes
 
@@ -281,7 +158,7 @@
   - @llamaindex/core@0.4.23
   - @llamaindex/env@0.1.27
 
-## 2.0.23
+## 0.0.80
 
 ### Patch Changes
 
@@ -290,54 +167,47 @@
   - @llamaindex/core@0.4.22
   - @llamaindex/env@0.1.26
 
-## 2.0.22
+## 0.0.79
 
 ### Patch Changes
 
-- d6c270e: feat: support pass project and org id to llama parse reader
 - Updated dependencies [9456616]
 - Updated dependencies [1931bbc]
   - @llamaindex/core@0.4.21
 
-## 2.0.21
+## 0.0.78
 
 ### Patch Changes
 
-- 5dec9f9: chore: bump sdk deps version
-- fd9c829: chore: bump llamacloud openapi
 - Updated dependencies [d211b7a]
   - @llamaindex/core@0.4.20
 
-## 2.0.20
-
-### Patch Changes
-
-- 012495b: chore: bump llamacloud sdk
-
-## 2.0.19
+## 0.0.77
 
 ### Patch Changes
 
+- 24caf93: fix: added inference profile mapping for nova models"
 - Updated dependencies [a9b5b99]
   - @llamaindex/core@0.4.19
 
-## 2.0.18
+## 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
 
-## 2.0.17
+## 0.0.75
 
 ### Patch Changes
 
 - Updated dependencies [3d1808b]
   - @llamaindex/core@0.4.17
 
-## 2.0.16
+## 0.0.74
 
 ### Patch Changes
 
@@ -346,7 +216,7 @@
   - @llamaindex/core@0.4.16
   - @llamaindex/env@0.1.24
 
-## 2.0.15
+## 0.0.73
 
 ### Patch Changes
 
@@ -354,7 +224,7 @@
   - @llamaindex/env@0.1.23
   - @llamaindex/core@0.4.15
 
-## 2.0.14
+## 0.0.72
 
 ### Patch Changes
 
@@ -362,7 +232,7 @@
   - @llamaindex/env@0.1.22
   - @llamaindex/core@0.4.14
 
-## 2.0.13
+## 0.0.71
 
 ### Patch Changes
 
@@ -371,21 +241,21 @@
   - @llamaindex/core@0.4.13
   - @llamaindex/env@0.1.21
 
-## 2.0.12
+## 0.0.70
 
 ### Patch Changes
 
 - Updated dependencies [ef4f63d]
   - @llamaindex/core@0.4.12
 
-## 2.0.11
+## 0.0.69
 
 ### Patch Changes
 
 - Updated dependencies [6d22fa2]
   - @llamaindex/core@0.4.11
 
-## 2.0.10
+## 0.0.68
 
 ### Patch Changes
 
@@ -393,21 +263,21 @@
 - Updated dependencies [c69605f]
   - @llamaindex/core@0.4.10
 
-## 2.0.9
+## 0.0.67
 
 ### Patch Changes
 
 - Updated dependencies [7ae6eaa]
   - @llamaindex/core@0.4.9
 
-## 2.0.8
+## 0.0.66
 
 ### Patch Changes
 
 - Updated dependencies [f865c98]
   - @llamaindex/core@0.4.8
 
-## 2.0.7
+## 0.0.65
 
 ### Patch Changes
 
@@ -415,7 +285,7 @@
 - Updated dependencies [fd8c882]
   - @llamaindex/core@0.4.7
 
-## 2.0.6
+## 0.0.64
 
 ### Patch Changes
 
@@ -423,7 +293,7 @@
   - @llamaindex/env@0.1.20
   - @llamaindex/core@0.4.6
 
-## 2.0.5
+## 0.0.63
 
 ### Patch Changes
 
@@ -431,7 +301,7 @@
   - @llamaindex/core@0.4.5
   - @llamaindex/env@0.1.19
 
-## 2.0.4
+## 0.0.62
 
 ### Patch Changes
 
@@ -439,14 +309,15 @@
   - @llamaindex/env@0.1.18
   - @llamaindex/core@0.4.4
 
-## 2.0.3
+## 0.0.61
 
 ### Patch Changes
 
+- 487782c: Add missing inference endpoints for Haiku 3.5
 - Updated dependencies [95a5cc6]
   - @llamaindex/core@0.4.3
 
-## 2.0.2
+## 0.0.60
 
 ### Patch Changes
 
@@ -454,14 +325,20 @@
   - @llamaindex/env@0.1.17
   - @llamaindex/core@0.4.2
 
-## 2.0.1
+## 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
 
-## 2.0.0
+## 0.0.57
 
 ### Patch Changes
 
@@ -471,21 +348,21 @@
 - Updated dependencies [620c63c]
   - @llamaindex/core@0.4.0
 
-## 1.0.8
+## 0.0.56
 
 ### Patch Changes
 
 - Updated dependencies [60b185f]
   - @llamaindex/core@0.3.7
 
-## 1.0.7
+## 0.0.55
 
 ### Patch Changes
 
 - Updated dependencies [691c5bc]
   - @llamaindex/core@0.3.6
 
-## 1.0.6
+## 0.0.54
 
 ### Patch Changes
 
@@ -493,27 +370,27 @@
   - @llamaindex/env@0.1.16
   - @llamaindex/core@0.3.5
 
-## 1.0.5
+## 0.0.53
 
 ### Patch Changes
 
 - Updated dependencies [e2a0876]
   - @llamaindex/core@0.3.4
 
-## 1.0.4
+## 0.0.52
 
 ### Patch Changes
 
-- 06f632b: fix(cloud): allow filename in llama parse
+- a5a75f6: feat: added sonnet 3.5 v2
 
-## 1.0.3
+## 0.0.51
 
 ### Patch Changes
 
 - Updated dependencies [0493f67]
   - @llamaindex/core@0.3.3
 
-## 1.0.2
+## 0.0.50
 
 ### Patch Changes
 
@@ -521,19 +398,17 @@
   - @llamaindex/env@0.1.15
   - @llamaindex/core@0.3.2
 
-## 1.0.1
+## 0.0.49
 
 ### Patch Changes
 
-- 4c38c1b: fix(cloud): do not detect file type in llama parse
-- 24d065f: Log Parse Job Errors when verbose is enabled
 - 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
 
-## 1.0.0
+## 0.0.48
 
 ### Patch Changes
 
@@ -541,21 +416,21 @@
 - Updated dependencies [96fc69c]
   - @llamaindex/core@0.3.0
 
-## 0.2.14
+## 0.0.47
 
 ### Patch Changes
 
 - Updated dependencies [5f67820]
   - @llamaindex/core@0.2.12
 
-## 0.2.13
+## 0.0.46
 
 ### Patch Changes
 
 - Updated dependencies [ee697fb]
   - @llamaindex/core@0.2.11
 
-## 0.2.12
+## 0.0.45
 
 ### Patch Changes
 
@@ -563,19 +438,20 @@
 - Updated dependencies [468bda5]
   - @llamaindex/core@0.2.10
 
-## 0.2.11
+## 0.0.44
 
 ### Patch Changes
 
-- 0b20ff9: fix: package.json format
+- Updated dependencies [b17d439]
+  - @llamaindex/core@0.2.9
 
-## 0.2.10
+## 0.0.43
 
 ### Patch Changes
 
-- 981811e: fix(cloud): llama parse reader save image incorrectly
+- 2774e80: feat: added meta3.2 support via Bedrock including vision, tool call and inference region support
 
-## 0.2.9
+## 0.0.42
 
 ### Patch Changes
 
@@ -584,41 +460,54 @@
   - @llamaindex/core@0.2.8
   - @llamaindex/env@0.1.13
 
-## 0.2.8
+## 0.0.41
 
 ### Patch Changes
 
-- ac41ed3: feat: bump cloud sdk version
+- Updated dependencies [6cce3b1]
+  - @llamaindex/core@0.2.7
 
-## 0.2.7
+## 0.0.40
 
 ### Patch Changes
 
-- fb36eff: fix: backport for node.js 18
+- 50e6b57: feat: add Amazon Bedrock Retriever
+- Updated dependencies [8b7fdba]
+  - @llamaindex/core@0.2.6
 
-  There could have one missing API in the node.js 18, so we need to backport it to make it work.
+## 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
 
-- d24d3d1: fix: print warning when llama parse reader has error
 - Updated dependencies [2cd1383]
   - @llamaindex/core@0.2.3
 
-## 0.2.6
+## 0.0.36
 
 ### Patch Changes
 
-- b42adeb: fix: get job result in llama parse reader
 - Updated dependencies [749b43a]
   - @llamaindex/core@0.2.2
 
-## 0.2.5
+## 0.0.35
 
 ### Patch Changes
 
-- 85c2e19: feat: `@llamaindex/cloud` package update
-
-  - Bump to latest openapi schema
-  - Move LlamaParse class from llamaindex, this will allow you use llamaparse in more non-node.js environment
-
 - Updated dependencies [ac07e3c]
 - Updated dependencies [70ccb4a]
 - Updated dependencies [1a6137b]
@@ -626,56 +515,263 @@
   - @llamaindex/core@0.2.1
   - @llamaindex/env@0.1.11
 
-## 0.2.4
+## 0.0.34
 
 ### Patch Changes
 
-- 4810364: fix: bump version
+- Updated dependencies [11feef8]
+  - @llamaindex/core@0.2.0
 
-## 0.2.3
+## 0.0.33
 
 ### Patch Changes
 
-- 0bf8d80: fix: bump version
+- Updated dependencies [711c814]
+  - @llamaindex/core@0.1.12
 
-## 0.2.2
+## 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
 
-## 0.2.1
+## 0.0.28
 
 ### Patch Changes
 
-- 1f680d7: chore: bump llamacloud api
+- Updated dependencies [04b2f8e]
+  - @llamaindex/core@0.1.7
 
-## 0.2.0
-
-### Minor Changes
-
-- 3ed6acc: feat: cloud api change
-
-## 0.1.4
+## 0.0.27
 
 ### Patch Changes
 
-- 36ddec4: fix: typo in custom page separator parameter for LlamaParse
+- Updated dependencies [0452af9]
+  - @llamaindex/core@0.1.6
 
-## 0.1.3
+## 0.0.26
 
 ### Patch Changes
 
-- 1c444d5: feat(cloud): update openapi.json
+- 224d507: fix: prevent tool calling getting mixed with conversation
+- 376d29a: feat: added tool calling and agent support for llama3.1 504B
 
-## 0.1.2
+## 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
 
-## 0.1.1
+## 0.0.15
 
 ### Patch Changes
 
-- 321c39d: fix: generate api as class
+- 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

@@ -5,19 +5,15 @@
     "outDir": "./dist/type",
     "tsBuildInfoFile": "./dist/.tsbuildinfo",
     "emitDeclarationOnly": true,
-    "moduleResolution": "Bundler",
-    "skipLibCheck": true,
-    "strict": true,
-    "types": []
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "types": ["node"]
   },
   "include": ["./src"],
   "exclude": ["node_modules"],
   "references": [
     {
-      "path": "../core/tsconfig.json"
-    },
-    {
-      "path": "../env/tsconfig.json"
+      "path": "../llamaindex/tsconfig.json"
     }
   ]
 }

packages/core/CHANGELOG.md

@@ -1,5 +1,18 @@
 # @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

packages/core/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.6.17",
+  "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/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";
@@ -38,6 +39,11 @@ export type MemoryOptions<TMessageOptions extends object = object> = {
    * 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<
@@ -76,6 +82,10 @@ export class Memory<
    * The default LLM to use for memory retrieval.
    */
   private llm: LLM | undefined;
+  /**
+   * Logger for memory operations
+   */
+  private logger: Logger;
 
   constructor(
     messages: MemoryMessage<TMessageOptions>[] = [],
@@ -87,6 +97,7 @@ 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 = {
@@ -309,7 +320,7 @@ export class Memory<
           addedTokenCount += messageTokenCount;
         }
       } catch (error) {
-        console.warn(
+        this.logger.warn(
           `Failed to get content from memory block ${block.id}:`,
           error,
         );
@@ -371,7 +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/experimental/CHANGELOG.md

@@ -1,5 +1,30 @@
 # @llamaindex/experimental
 
+## 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

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.198",
+  "version": "0.0.202",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,42 @@
 # llamaindex
 
+## 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

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.11.21",
+  "version": "0.11.25",
   "license": "MIT",
   "type": "module",
   "keywords": [
@@ -20,13 +20,13 @@
     "llamaindex"
   ],
   "dependencies": {
-    "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
     "@llamaindex/node-parser": "workspace:*",
     "@llamaindex/workflow": "workspace:*",
     "@types/lodash": "^4.17.7",
     "@types/node": "^24.0.13",
+    "llama-cloud-services": "^0.1.0",
     "lodash": "^4.17.21",
     "magic-bytes.js": "^1.10.0"
   },

packages/llamaindex/src/cloud/LLamaCloudFileService.ts

@@ -1,120 +0,0 @@
-import {
-  addFilesToPipelineApiApiV1PipelinesPipelineIdFilesPut,
-  getPipelineFileStatusApiV1PipelinesPipelineIdFilesFileIdStatusGet,
-  listPipelineFilesApiV1PipelinesPipelineIdFilesGet,
-  listProjectsApiV1ProjectsGet,
-  readFileContentApiV1FilesIdContentGet,
-  searchPipelinesApiV1PipelinesGet,
-  uploadFileApiV1FilesPost,
-} from "@llamaindex/cloud/api";
-import { initService } from "./utils.js";
-
-export class LLamaCloudFileService {
-  /**
-   * Get list of projects, each project contains a list of pipelines
-   */
-  public static async getAllProjectsWithPipelines() {
-    initService();
-    try {
-      const { data: projects } = await listProjectsApiV1ProjectsGet({
-        throwOnError: true,
-      });
-      const { data: pipelines } = await searchPipelinesApiV1PipelinesGet({
-        throwOnError: true,
-      });
-      return projects.map((project) => ({
-        ...project,
-        pipelines: pipelines.filter((p) => p.project_id === project.id),
-      }));
-    } catch (error) {
-      console.error("Error listing projects and pipelines:", error);
-      return [];
-    }
-  }
-
-  /**
-   * Upload a file to a pipeline in LlamaCloud
-   */
-  public static async addFileToPipeline(
-    projectId: string,
-    pipelineId: string,
-    uploadFile: File | Blob,
-    // eslint-disable-next-line @typescript-eslint/no-explicit-any
-    customMetadata: Record<string, any> = {},
-  ) {
-    initService();
-    const { data: file } = await uploadFileApiV1FilesPost({
-      query: { project_id: projectId },
-      body: {
-        upload_file: uploadFile,
-      },
-      throwOnError: true,
-    });
-    const files = [
-      {
-        file_id: file.id,
-        custom_metadata: { file_id: file.id, ...customMetadata },
-      },
-    ];
-    await addFilesToPipelineApiApiV1PipelinesPipelineIdFilesPut({
-      path: {
-        pipeline_id: pipelineId,
-      },
-      body: files,
-    });
-
-    // Wait 2s for the file to be processed
-    const maxAttempts = 20;
-    let attempt = 0;
-    while (attempt < maxAttempts) {
-      const { data: result } =
-        await getPipelineFileStatusApiV1PipelinesPipelineIdFilesFileIdStatusGet(
-          {
-            path: {
-              pipeline_id: pipelineId,
-              file_id: file.id,
-            },
-            throwOnError: true,
-          },
-        );
-      if (result.status === "ERROR") {
-        throw new Error(`File processing failed: ${JSON.stringify(result)}`);
-      }
-      if (result.status === "SUCCESS") {
-        // File is ingested - return the file id
-        return file.id;
-      }
-      attempt += 1;
-      await new Promise((resolve) => setTimeout(resolve, 100)); // Sleep for 100ms
-    }
-    throw new Error(
-      `File processing did not complete after ${maxAttempts} attempts. Check your LlamaCloud index at https://cloud.llamaindex.ai/project/${projectId}/deploy/${pipelineId} for more details.`,
-    );
-  }
-
-  /**
-   * Get download URL for a file in LlamaCloud
-   */
-  public static async getFileUrl(pipelineId: string, filename: string) {
-    initService();
-    const { data: allPipelineFiles } =
-      await listPipelineFilesApiV1PipelinesPipelineIdFilesGet({
-        path: {
-          pipeline_id: pipelineId,
-        },
-        throwOnError: true,
-      });
-    const file = allPipelineFiles.find((file) => file.name === filename);
-    if (!file?.file_id) return null;
-    const { data: fileContent } = await readFileContentApiV1FilesIdContentGet({
-      path: {
-        id: file.file_id,
-      },
-      query: {
-        project_id: file.project_id,
-      },
-      throwOnError: true,
-    });
-    return fileContent.url;
-  }
-}

packages/llamaindex/src/cloud/LlamaCloudIndex.ts

@@ -1,414 +0,0 @@
-import type { BaseNodePostprocessor } from "@llamaindex/core/postprocessor";
-import type { BaseQueryEngine } from "@llamaindex/core/query-engine";
-import type { BaseSynthesizer } from "@llamaindex/core/response-synthesizers";
-import type { Document } from "@llamaindex/core/schema";
-import { RetrieverQueryEngine } from "../engines/query/RetrieverQueryEngine.js";
-import type { CloudRetrieveParams } from "./LlamaCloudRetriever.js";
-import { LlamaCloudRetriever } from "./LlamaCloudRetriever.js";
-import type { CloudConstructorParams } from "./type.js";
-import {
-  getAppBaseUrl,
-  getPipelineId,
-  getProjectId,
-  initService,
-} from "./utils.js";
-
-import {
-  createBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPost,
-  deletePipelineDocumentApiV1PipelinesPipelineIdDocumentsDocumentIdDelete,
-  getPipelineDocumentStatusApiV1PipelinesPipelineIdDocumentsDocumentIdStatusGet,
-  getPipelineStatusApiV1PipelinesPipelineIdStatusGet,
-  type PipelineCreateReadable,
-  searchPipelinesApiV1PipelinesGet,
-  upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut,
-  upsertPipelineApiV1PipelinesPut,
-} from "@llamaindex/cloud/api";
-import type { BaseRetriever } from "@llamaindex/core/retriever";
-import { getEnv } from "@llamaindex/env";
-import type { QueryToolParams } from "../indices/BaseIndex.js";
-import { Settings } from "../Settings.js";
-import { QueryEngineTool } from "../tools/QueryEngineTool.js";
-
-export class LlamaCloudIndex {
-  params: CloudConstructorParams;
-
-  constructor(params: CloudConstructorParams) {
-    this.params = params;
-    initService(this.params);
-  }
-
-  private async waitForPipelineIngestion(
-    verbose = Settings.debug,
-    raiseOnError = false,
-  ): Promise<void> {
-    const pipelineId = await this.getPipelineId();
-
-    if (verbose) {
-      console.log("Waiting for pipeline ingestion: ");
-    }
-
-    while (true) {
-      const { data: pipelineStatus } =
-        await getPipelineStatusApiV1PipelinesPipelineIdStatusGet({
-          path: {
-            pipeline_id: pipelineId,
-          },
-          throwOnError: true,
-        });
-
-      if (pipelineStatus.status === "SUCCESS") {
-        if (verbose) {
-          console.log("Pipeline ingestion completed successfully");
-        }
-        break;
-      }
-
-      if (pipelineStatus.status === "ERROR") {
-        if (verbose) {
-          console.error("Pipeline ingestion failed");
-        }
-
-        if (raiseOnError) {
-          throw new Error("Pipeline ingestion failed");
-        }
-      }
-
-      if (verbose) {
-        process.stdout.write(".");
-      }
-
-      await new Promise((resolve) => setTimeout(resolve, 1000));
-    }
-  }
-
-  private async waitForDocumentIngestion(
-    docIds: string[],
-    verbose = Settings.debug,
-    raiseOnError = false,
-  ): Promise<void> {
-    const pipelineId = await this.getPipelineId();
-
-    if (verbose) {
-      console.log("Loading data: ");
-    }
-
-    const pendingDocs = new Set(docIds);
-
-    while (pendingDocs.size) {
-      const docsToRemove = new Set<string>();
-
-      for (const doc of pendingDocs) {
-        const {
-          data: { status },
-        } =
-          await getPipelineDocumentStatusApiV1PipelinesPipelineIdDocumentsDocumentIdStatusGet(
-            {
-              path: { pipeline_id: pipelineId, document_id: doc },
-              throwOnError: true,
-            },
-          );
-
-        if (status === "NOT_STARTED" || status === "IN_PROGRESS") {
-          continue;
-        }
-
-        if (status === "ERROR") {
-          if (verbose) {
-            console.error(`Document ingestion failed for ${doc}`);
-          }
-
-          if (raiseOnError) {
-            throw new Error(`Document ingestion failed for ${doc}`);
-          }
-        }
-
-        docsToRemove.add(doc);
-      }
-
-      for (const doc of docsToRemove) {
-        pendingDocs.delete(doc);
-      }
-
-      if (pendingDocs.size) {
-        if (verbose) {
-          process.stdout.write(".");
-        }
-
-        await new Promise((resolve) => setTimeout(resolve, 500));
-      }
-    }
-
-    if (verbose) {
-      console.log("Done!");
-    }
-
-    await this.waitForPipelineIngestion(verbose, raiseOnError);
-  }
-
-  public async getPipelineId(
-    name?: string,
-    projectName?: string,
-    organizationId?: string,
-  ): Promise<string> {
-    return await getPipelineId(
-      name ?? this.params.name,
-      projectName ?? this.params.projectName,
-      organizationId ?? this.params.organizationId,
-    );
-  }
-
-  public async getProjectId(
-    projectName?: string,
-    organizationId?: string,
-  ): Promise<string> {
-    return await getProjectId(
-      projectName ?? this.params.projectName,
-      organizationId ?? this.params.organizationId,
-    );
-  }
-
-  /**
-   * Adds documents to the given index parameters. If the index does not exist, it will be created.
-   *
-   * @param params - An object containing the following properties:
-   *   - documents: An array of Document objects to be added to the index.
-   *   - verbose: Optional boolean to enable verbose logging.
-   *   - Additional properties from CloudConstructorParams.
-   * @returns A Promise that resolves to a new LlamaCloudIndex instance.
-   */
-  static async fromDocuments(
-    params: {
-      documents: Document[];
-      verbose?: boolean;
-    } & CloudConstructorParams,
-    config?: {
-      embedding: PipelineCreateReadable["embedding_config"];
-      transform: PipelineCreateReadable["transform_config"];
-    },
-  ): Promise<LlamaCloudIndex> {
-    const index = new LlamaCloudIndex({ ...params });
-    await index.ensureIndex({ ...config, verbose: params.verbose ?? false });
-    await index.addDocuments(params.documents, params.verbose);
-    return index;
-  }
-
-  async addDocuments(documents: Document[], verbose?: boolean): Promise<void> {
-    const apiUrl = getAppBaseUrl();
-    const projectId = await this.getProjectId();
-    const pipelineId = await this.getPipelineId();
-
-    await upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut({
-      path: {
-        pipeline_id: pipelineId,
-      },
-      body: documents.map((doc) => ({
-        metadata: doc.metadata,
-        text: doc.text,
-        excluded_embed_metadata_keys: doc.excludedEmbedMetadataKeys,
-        excluded_llm_metadata_keys: doc.excludedEmbedMetadataKeys,
-        id: doc.id_,
-      })),
-    });
-
-    while (true) {
-      const { data: pipelineStatus } =
-        await getPipelineStatusApiV1PipelinesPipelineIdStatusGet({
-          path: { pipeline_id: pipelineId },
-          throwOnError: true,
-        });
-
-      if (pipelineStatus.status === "SUCCESS") {
-        console.info(
-          "Documents ingested successfully, pipeline is ready to use",
-        );
-        break;
-      }
-
-      if (pipelineStatus.status === "ERROR") {
-        console.error(
-          `Some documents failed to ingest, check your pipeline logs at ${apiUrl}/project/${projectId}/deploy/${pipelineId}`,
-        );
-        throw new Error("Some documents failed to ingest");
-      }
-
-      if (pipelineStatus.status === "PARTIAL_SUCCESS") {
-        console.info(
-          `Documents ingestion partially succeeded, to check a more complete status check your pipeline at ${apiUrl}/project/${projectId}/deploy/${pipelineId}`,
-        );
-        break;
-      }
-
-      if (verbose) {
-        process.stdout.write(".");
-      }
-
-      await new Promise((resolve) => setTimeout(resolve, 1000));
-    }
-
-    if (verbose) {
-      console.info(
-        `Ingestion completed, find your index at ${apiUrl}/project/${projectId}/deploy/${pipelineId}`,
-      );
-    }
-  }
-
-  asRetriever(params: CloudRetrieveParams = {}): BaseRetriever {
-    return new LlamaCloudRetriever({ ...this.params, ...params });
-  }
-
-  asQueryEngine(
-    params?: {
-      responseSynthesizer?: BaseSynthesizer;
-      preFilters?: unknown;
-      nodePostprocessors?: BaseNodePostprocessor[];
-    } & CloudRetrieveParams,
-  ): BaseQueryEngine {
-    const retriever = new LlamaCloudRetriever({
-      ...this.params,
-      ...params,
-    });
-    return new RetrieverQueryEngine(
-      retriever,
-      params?.responseSynthesizer,
-      params?.nodePostprocessors,
-    );
-  }
-
-  asQueryTool(params: QueryToolParams): QueryEngineTool {
-    if (params.options) {
-      params.retriever = this.asRetriever(params.options);
-    }
-
-    return new QueryEngineTool({
-      queryEngine: this.asQueryEngine(params),
-      metadata: params?.metadata,
-      includeSourceNodes: params?.includeSourceNodes ?? false,
-    });
-  }
-
-  queryTool(params: QueryToolParams): QueryEngineTool {
-    return this.asQueryTool(params);
-  }
-
-  async insert(document: Document) {
-    const pipelineId = await this.getPipelineId();
-
-    await createBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPost({
-      path: {
-        pipeline_id: pipelineId,
-      },
-      body: [
-        {
-          metadata: document.metadata,
-          text: document.text,
-          excluded_embed_metadata_keys: document.excludedLlmMetadataKeys,
-          excluded_llm_metadata_keys: document.excludedEmbedMetadataKeys,
-          id: document.id_,
-        },
-      ],
-    });
-
-    await this.waitForDocumentIngestion([document.id_]);
-  }
-
-  async delete(document: Document) {
-    const pipelineId = await this.getPipelineId();
-
-    await deletePipelineDocumentApiV1PipelinesPipelineIdDocumentsDocumentIdDelete(
-      {
-        path: {
-          pipeline_id: pipelineId,
-          document_id: document.id_,
-        },
-      },
-    );
-
-    await this.waitForPipelineIngestion();
-  }
-
-  async refreshDoc(document: Document) {
-    const pipelineId = await this.getPipelineId();
-
-    await upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut({
-      path: {
-        pipeline_id: pipelineId,
-      },
-      body: [
-        {
-          metadata: document.metadata,
-          text: document.text,
-          excluded_embed_metadata_keys: document.excludedLlmMetadataKeys,
-          excluded_llm_metadata_keys: document.excludedEmbedMetadataKeys,
-          id: document.id_,
-        },
-      ],
-    });
-
-    await this.waitForDocumentIngestion([document.id_]);
-  }
-
-  public async ensureIndex(config?: {
-    embedding?: PipelineCreateReadable["embedding_config"];
-    transform?: PipelineCreateReadable["transform_config"];
-    verbose?: boolean;
-  }): Promise<void> {
-    const projectId = await this.getProjectId();
-
-    const { data: pipelines } = await searchPipelinesApiV1PipelinesGet({
-      query: {
-        project_id: projectId,
-        pipeline_name: this.params.name,
-      },
-      throwOnError: true,
-    });
-
-    if (pipelines.length === 0) {
-      // no pipeline found, create a new one
-      let embeddingConfig = config?.embedding;
-      if (!embeddingConfig) {
-        // no embedding config provided, use OpenAI as default
-        const openAIApiKey = getEnv("OPENAI_API_KEY");
-        const embeddingModel = getEnv("EMBEDDING_MODEL");
-        if (!openAIApiKey || !embeddingModel) {
-          throw new Error(
-            "No embedding configuration provided. Fallback to OpenAI embedding model. OPENAI_API_KEY and EMBEDDING_MODEL environment variables must be set.",
-          );
-        }
-        embeddingConfig = {
-          type: "OPENAI_EMBEDDING",
-          component: {
-            api_key: openAIApiKey,
-            model_name: embeddingModel,
-          },
-        };
-      }
-
-      let transformConfig = config?.transform;
-      if (!transformConfig) {
-        transformConfig = {
-          mode: "auto",
-          chunk_size: 1024,
-          chunk_overlap: 200,
-        };
-      }
-
-      const { data: pipeline } = await upsertPipelineApiV1PipelinesPut({
-        query: {
-          project_id: projectId,
-        },
-        body: {
-          name: this.params.name,
-          embedding_config: embeddingConfig,
-          transform_config: transformConfig,
-        },
-        throwOnError: true,
-      });
-
-      if (config?.verbose) {
-        console.log(
-          `Created pipeline ${pipeline.id} with name ${pipeline.name}`,
-        );
-      }
-    }
-  }
-}

packages/llamaindex/src/cloud/LlamaCloudRetriever.ts

@@ -1,103 +0,0 @@
-import {
-  type MetadataFilter,
-  type MetadataFilters,
-  type RetrievalParams,
-  runSearchApiV1PipelinesPipelineIdRetrievePost,
-  type TextNodeWithScore,
-} from "@llamaindex/cloud/api";
-import { DEFAULT_PROJECT_NAME } from "@llamaindex/core/global";
-import type { QueryBundle } from "@llamaindex/core/query-engine";
-import { BaseRetriever } from "@llamaindex/core/retriever";
-import type { NodeWithScore } from "@llamaindex/core/schema";
-import { jsonToNode, ObjectType } from "@llamaindex/core/schema";
-import { extractText } from "@llamaindex/core/utils";
-import type { ClientParams, CloudConstructorParams } from "./type.js";
-import { getPipelineId, initService } from "./utils.js";
-
-export type CloudRetrieveParams = Omit<
-  RetrievalParams,
-  "query" | "search_filters" | "dense_similarity_top_k"
-> & { similarityTopK?: number; filters?: MetadataFilters };
-
-export class LlamaCloudRetriever extends BaseRetriever {
-  clientParams: ClientParams;
-  retrieveParams: CloudRetrieveParams;
-  organizationId?: string;
-  projectName: string = DEFAULT_PROJECT_NAME;
-  pipelineName: string;
-
-  private resultNodesToNodeWithScore(
-    nodes: TextNodeWithScore[],
-  ): NodeWithScore[] {
-    return nodes.map((node: TextNodeWithScore) => {
-      const textNode = jsonToNode(node.node, ObjectType.TEXT);
-      textNode.metadata = {
-        ...textNode.metadata,
-        ...node.node.extra_info, // append LlamaCloud extra_info to node metadata (file_name, pipeline_id, etc.)
-      };
-      return {
-        // Currently LlamaCloud only supports text nodes
-        node: textNode,
-        score: node.score ?? undefined,
-      };
-    });
-  }
-
-  // LlamaCloud expects null values for filters, but LlamaIndexTS uses undefined for empty values
-  // This function converts the undefined values to null
-  private convertFilter(filters?: MetadataFilters): MetadataFilters | null {
-    if (!filters) return null;
-
-    const processFilter = (
-      filter: MetadataFilter | MetadataFilters,
-    ): MetadataFilter | MetadataFilters => {
-      if ("filters" in filter) {
-        // type MetadataFilters
-        return { ...filter, filters: filter.filters.map(processFilter) };
-      }
-      return { ...filter, value: filter.value ?? null };
-    };
-
-    return { ...filters, filters: filters.filters.map(processFilter) };
-  }
-
-  constructor(params: CloudConstructorParams & CloudRetrieveParams) {
-    super();
-    this.clientParams = { apiKey: params.apiKey, baseUrl: params.baseUrl };
-    initService(this.clientParams);
-    this.retrieveParams = params;
-    this.pipelineName = params.name;
-    if (params.projectName) {
-      this.projectName = params.projectName;
-    }
-    if (params.organizationId) {
-      this.organizationId = params.organizationId;
-    }
-  }
-
-  async _retrieve(query: QueryBundle): Promise<NodeWithScore[]> {
-    const pipelineId = await getPipelineId(
-      this.pipelineName,
-      this.projectName,
-      this.organizationId,
-    );
-
-    const filters = this.convertFilter(this.retrieveParams.filters);
-
-    const { data: results } =
-      await runSearchApiV1PipelinesPipelineIdRetrievePost({
-        throwOnError: true,
-        path: {
-          pipeline_id: pipelineId,
-        },
-        body: {
-          ...this.retrieveParams,
-          query: extractText(query),
-          search_filters: filters,
-          dense_similarity_top_k: this.retrieveParams.similarityTopK!,
-        },
-      });
-
-    return this.resultNodesToNodeWithScore(results.retrieval_nodes);
-  }
-}

packages/llamaindex/src/cloud/index.ts

@@ -1,7 +1,7 @@
-export { LLamaCloudFileService } from "./LLamaCloudFileService.js";
-export { LlamaCloudIndex } from "./LlamaCloudIndex.js";
-export {
-  LlamaCloudRetriever,
-  type CloudRetrieveParams,
-} from "./LlamaCloudRetriever.js";
-export type { CloudConstructorParams } from "./type.js";
+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 * from "llama-cloud-services";

packages/llamaindex/src/cloud/type.ts

@@ -1,10 +0,0 @@
-export type ClientParams = {
-  apiKey?: string | undefined;
-  baseUrl?: string | undefined;
-};
-
-export type CloudConstructorParams = {
-  name: string;
-  projectName: string;
-  organizationId?: string | undefined;
-} & ClientParams;

packages/llamaindex/src/cloud/utils.ts

@@ -1,97 +0,0 @@
-import {
-  client,
-  listProjectsApiV1ProjectsGet,
-  searchPipelinesApiV1PipelinesGet,
-} from "@llamaindex/cloud/api";
-import { DEFAULT_BASE_URL } from "@llamaindex/core/global";
-import { getEnv } from "@llamaindex/env";
-import type { ClientParams } from "./type.js";
-
-function getBaseUrl(baseUrl?: string): string {
-  return baseUrl ?? getEnv("LLAMA_CLOUD_BASE_URL") ?? DEFAULT_BASE_URL;
-}
-
-export function getAppBaseUrl(): string {
-  return client.getConfig().baseUrl?.replace(/api\./, "") ?? "";
-}
-
-// fixme: refactor this to init at the top level or module level
-let initOnce = false;
-export function initService({ apiKey, baseUrl }: ClientParams = {}) {
-  if (initOnce) {
-    return;
-  }
-  initOnce = true;
-  client.setConfig({
-    baseUrl: getBaseUrl(baseUrl),
-    throwOnError: true,
-  });
-  const token = apiKey ?? getEnv("LLAMA_CLOUD_API_KEY");
-  client.interceptors.request.use((request) => {
-    request.headers.set("Authorization", `Bearer ${token}`);
-    return request;
-  });
-  client.interceptors.error.use((error) => {
-    throw new Error(
-      `LlamaCloud API request failed. Error details: ${JSON.stringify(error)}`,
-    );
-  });
-  if (!token) {
-    throw new Error(
-      "API Key is required for LlamaCloudIndex. Please pass the apiKey parameter",
-    );
-  }
-}
-
-export async function getProjectId(
-  projectName: string,
-  organizationId?: string,
-): Promise<string> {
-  const { data: projects } = await listProjectsApiV1ProjectsGet({
-    query: {
-      project_name: projectName,
-      organization_id: organizationId ?? null,
-    },
-    throwOnError: true,
-  });
-
-  if (projects.length === 0) {
-    throw new Error(
-      `Unknown project name ${projectName}. Please confirm a managed project with this name exists.`,
-    );
-  } else if (projects.length > 1) {
-    throw new Error(
-      `Multiple projects found with name ${projectName}. Please specify organization_id.`,
-    );
-  }
-
-  const project = projects[0]!;
-
-  if (!project.id) {
-    throw new Error(`No project found with name ${projectName}`);
-  }
-
-  return project.id;
-}
-
-export async function getPipelineId(
-  name: string,
-  projectName: string,
-  organizationId?: string,
-): Promise<string> {
-  const { data: pipelines } = await searchPipelinesApiV1PipelinesGet({
-    query: {
-      project_id: await getProjectId(projectName, organizationId),
-      pipeline_name: name,
-    },
-    throwOnError: true,
-  });
-
-  if (pipelines.length === 0 || !pipelines[0]!.id) {
-    throw new Error(
-      `No pipeline found with name ${name} in project ${projectName}`,
-    );
-  }
-
-  return pipelines[0]!.id;
-}

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() {
@@ -273,7 +278,9 @@ export class SimpleVectorStore extends BaseVectorStore {
   static async fromPersistPath(
     persistPath: string,
     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);

packages/llamaindex/tests/CHANGELOG.md

@@ -1,5 +1,17 @@
 # @llamaindex/core-test
 
+## 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

packages/llamaindex/tests/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llamaindex-test",
   "private": true,
-  "version": "0.1.13",
+  "version": "0.1.15",
   "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/node-parser/CHANGELOG.md

@@ -1,5 +1,20 @@
 # @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

packages/node-parser/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/node-parser",
-  "version": "2.0.17",
+  "version": "2.0.19",
   "description": "Node parser for LlamaIndex",
   "type": "module",
   "exports": {