Release 0.4.12 (#1013 )

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
chore: bump version
2026-07-02 20:13:52 -04:00 · 2024-07-03 10:24:22 -07:00 · 2024-07-03 10:20:46 -07:00 · 2024-07-03 01:27:58 -07:00 · 2024-07-02 15:07:03 -07:00 · 2024-07-02 14:48:51 -07:00
135 changed files with 3352 additions and 2184 deletions
@@ -0,0 +1,28 @@
+name: Publish Preview
+on: [pull_request]
+
+jobs:
+  pre_release:
+    name: Pre Release
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v3
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "pnpm"
+
+      - name: Install dependencies
+        run: pnpm install
+
+      - name: Build
+        run: pnpm run build
+
+      - name: Pre Release
+        run: pnpx pkg-pr-new publish ./packages/*
@@ -76,7 +76,7 @@ main();
 node --import tsx ./main.ts
 ```

-### Next.js
+### React Server Component (Next.js, Waku, Redwood.JS...)

 First, you will need to add a llamaindex plugin to your Next.js project.

@@ -154,40 +154,6 @@ export async function chatWithAgent(
 }
 ```

-### Cloudflare Workers
-
-```ts
-// src/index.ts
-export default {
-  async fetch(
-    request: Request,
-    env: Env,
-    ctx: ExecutionContext,
-  ): Promise<Response> {
-    const { setEnvs } = await import("@llamaindex/env");
-    // set environment variables so that the OpenAIAgent can use them
-    setEnvs(env);
-    const { OpenAIAgent } = await import("llamaindex");
-    const agent = new OpenAIAgent({
-      tools: [],
-    });
-    const responseStream = await agent.chat({
-      stream: true,
-      message: "Hello? What is the weather today?",
-    });
-    const textEncoder = new TextEncoder();
-    const response = responseStream.pipeThrough(
-      new TransformStream({
-        transform: (chunk, controller) => {
-          controller.enqueue(textEncoder.encode(chunk.response.delta));
-        },
-      }),
-    );
-    return new Response(response);
-  },
-};
-```
-
 ## Playground

 Check out our NextJS playground at https://llama-playground.vercel.app/. The source is available at https://github.com/run-llama/ts-playground
@@ -1,5 +1,49 @@
 # docs

+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+
+## 0.0.37
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
+## 0.0.36
+
+### Patch Changes
+
+- Updated dependencies [7dce3d2]
+  - llamaindex@0.4.10
+
+## 0.0.35
+
+### Patch Changes
+
+- Updated dependencies [3a96a48]
+  - llamaindex@0.4.9
+
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [83ebdfb]
+  - llamaindex@0.4.8
+
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [41fe871]
+- Updated dependencies [321c39d]
+- Updated dependencies [f7f1af0]
+  - llamaindex@0.4.7
+
 ## 0.0.32

 ### Patch Changes
@@ -15,7 +15,7 @@ Settings.llm = new Bedrock({
 });
 ```

-Currently only supports Anthropic models:
+Currently only supports Anthropic and Meta models:

 ```ts
 ANTHROPIC_CLAUDE_INSTANT_1 = "anthropic.claude-instant-v1";
@@ -25,6 +25,10 @@ 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";
+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";
 ```

 Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url format, e.g. `data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==`
@@ -1,6 +1,6 @@
 {
  "name": "docs",
-  "version": "0.0.32",
+  "version": "0.0.38",
  "private": true,
  "scripts": {
    "docusaurus": "docusaurus",
@@ -9,7 +9,7 @@ make sure you have basic knowledge of the [LlamaIndexTS](https://ts.llamaindex.a
 # export your API key
 export OPENAI_API_KEY="sk-..."

-npx ts-node ./chatEngine.ts
+npx tsx ./chatEngine.ts
 ```

 ## Build your own RAG app
@@ -0,0 +1,54 @@
+import "dotenv/config";
+
+import {
+  DefaultAzureCredential,
+  getBearerTokenProvider,
+} from "@azure/identity";
+import { AzureDynamicSessionTool, OpenAI, ReActAgent } from "llamaindex";
+
+async function main() {
+  const credential = new DefaultAzureCredential();
+  const azureADTokenProvider = getBearerTokenProvider(
+    credential,
+    "https://cognitiveservices.azure.com/.default",
+  );
+
+  const azure = {
+    azureADTokenProvider,
+    deployment: process.env.AZURE_OPENAI_DEPLOYMENT ?? "gpt-35-turbo",
+  };
+
+  // configure LLM model
+  const llm = new OpenAI({
+    azure,
+  });
+
+  const azureDynamicSession = new AzureDynamicSessionTool();
+
+  // Create an ReActAgent with the azure dynamic session tool
+  const agent = new ReActAgent({
+    llm,
+    tools: [azureDynamicSession],
+    // verbose: true,
+    systemPrompt: `You are a Python interpreter.
+      - You are given tasks to complete and you run python code to solve them.
+      - The python code runs by the python runtime. Every time you call $(interpreter) tool, the python code is executed in a separate cell. It's okay to make multiple calls to $(interpreter).
+      - You can run any python code you want in a secure environment.
+      - For images, return the full URL, not the base64 data.
+      - Return any image content as an HTML tag with the src attribute set to the URL of the image.`,
+  });
+
+  // Chat with the agent
+  const response = await agent.chat({
+    message:
+      "plot a chart of 5 random numbers and save it to /mnt/data/chart.png",
+    stream: false,
+  });
+
+  // Print the response
+  console.log({ response });
+}
+
+void main().then(() => {
+  console.log("Done");
+});
@@ -24,7 +24,7 @@ Here are two sample scripts which work well with the sample data in the Astra Po

 Loads and queries a simple vectorstore with some documents about Astra DB

-run `ts-node astradb/example`
+run `tsx astradb/example`

 ## Movie Reviews Example

@@ -32,10 +32,10 @@ run `ts-node astradb/example`

 This sample loads the same dataset of movie reviews as the Astra Portal sample dataset. (Feel free to load the data in your the Astra Data Explorer to compare)

-run `npx ts-node astradb/load`
+run `npx tsx astradb/load`

 ### Use RAG to Query the data

 Check out your data in the Astra Data Explorer and change the sample query as you see fit.

-run `npx ts-node astradb/query`
+run `npx tsx astradb/query`
@@ -6,7 +6,7 @@ Export your OpenAI API Key using `export OPEN_API_KEY=insert your api key here`

 If you haven't installed chromadb, run `pip install chromadb`. Start the server using `chroma run`.

-Now, open a new terminal window and inside `examples`, run `pnpm dlx ts-node chromadb/test.ts`.
+Now, open a new terminal window and inside `examples`, run `pnpm dlx tsx chromadb/test.ts`.

 Here's the output for the input query `Tell me about Godfrey Cheshire's rating of La Sapienza.`:

@@ -21,7 +21,7 @@ export LLAMA_CLOUD_BASE_URL="https://api.staging.llamaindex.ai"
 This example is using the managed index named `test` from the project `default` to create a chat engine.

 ```shell
-pnpx ts-node cloud/chat.ts
+pnpx tsx cloud/chat.ts
 ```

 ## Query Engine
@@ -29,7 +29,7 @@ pnpx ts-node cloud/chat.ts
 This example shows how to use the managed index with a query engine.

 ```shell
-pnpx ts-node cloud/query.ts
+pnpx tsx cloud/query.ts
 ```

 ## Pipeline
@@ -37,5 +37,5 @@ pnpx ts-node cloud/query.ts
 This example shows how to create a managed index with a pipeline.

 ```shell
-pnpx ts-node cloud/pipeline.ts
+pnpx tsx cloud/pipeline.ts
 ```
@@ -6,7 +6,7 @@ import { ContextChatEngine, LlamaCloudIndex } from "llamaindex";
 async function main() {
  const index = new LlamaCloudIndex({
    name: "test",
-    projectName: "default",
+    projectName: "Default",
    baseUrl: process.env.LLAMA_CLOUD_BASE_URL,
    apiKey: process.env.LLAMA_CLOUD_API_KEY,
  });
@@ -19,10 +19,10 @@ async function main() {
  while (true) {
    const query = await rl.question("User: ");
    const stream = await chatEngine.chat({ message: query, stream: true });
-    console.log();
    for await (const chunk of stream) {
      process.stdout.write(chunk.response);
    }
+    process.stdout.write("\n");
  }
 }

@@ -25,10 +25,10 @@ Here are two sample scripts which work with loading and querying data from a Mil

 This sample loads the same dataset of movie reviews as sample dataset. You can install https://github.com/zilliztech/attu to inspect the loaded data.

-run `npx ts-node milvus/load`
+run `npx tsx milvus/load`

 ## Use RAG to Query the data

 Check out your data in Attu and change the sample query as you see fit.

-run `npx ts-node milvus/query`
+run `npx tsx milvus/query`
@@ -34,7 +34,7 @@ MONGODB_COLLECTION=tiny_tweets_collection
 You are now ready to import our ready-made data set into Mongo. This is the file `tinytweets.json`, a selection of approximately 1000 tweets from @seldo on Twitter in mid-2019. With your environment set up you can do this by running

 ```
-npx ts-node mongodb/1_import.ts
+npx tsx mongodb/1_import.ts
 ```

 If you don't want to use tweets, you can replace `json_file` with any other array of JSON objects, but you will need to modify some code later to make sure the correct field gets indexed. There is no LlamaIndex-specific code here; you can load your data into Mongo any way you want to.
@@ -59,7 +59,7 @@ MONGODB_VECTOR_INDEX=tiny_tweets_vector_index
 If the data you're indexing is the tweets we gave you, you're ready to go:

 ```bash
-npx ts-node mongodb/2_load_and_index.ts
+npx tsx mongodb/2_load_and_index.ts
 ```

 > Note: this script is running a couple of minutes and currently doesn't show any progress.
@@ -112,7 +112,7 @@ Now you're ready to query your data!
 You can do this by running

 ```bash
-npx ts-node mongodb/3_query.ts
+npx tsx mongodb/3_query.ts
 ```

 This sets up a connection to Atlas just like `2_load_and_index.ts` did, then it creates a [query engine](https://docs.llamaindex.ai/en/stable/understanding/querying/querying.html#getting-started) and runs a query against it.
@@ -4,6 +4,7 @@
  "version": "0.0.6",
  "dependencies": {
    "@aws-crypto/sha256-js": "^5.2.0",
+    "@azure/identity": "^4.2.1",
    "@datastax/astra-db-ts": "^1.2.1",
    "@notionhq/client": "^2.2.15",
    "@pinecone-database/pinecone": "^2.2.2",
@@ -18,7 +19,6 @@
  },
  "devDependencies": {
    "@types/node": "^20.14.1",
-    "ts-node": "^10.9.2",
    "tsx": "^4.15.6",
    "typescript": "^5.5.2"
  },
@@ -37,7 +37,7 @@ Read and follow the instructions in the README.md file located one directory up

 To import documents and save the embedding vectors to your database:

-> `npx ts-node pg-vector-store/load-docs.ts data`
+> `npx tsx pg-vector-store/load-docs.ts data`

 where data is the directory containing your input files. Using the `data` directory in the example above will read all of the files in that directory using the LlamaIndexTS default readers for each file type.

@@ -45,6 +45,6 @@ where data is the directory containing your input files. Using the `data` direct

 To query using the resulting vector store:

-> `npx ts-node pg-vector-store/query.ts`
+> `npx tsx pg-vector-store/query.ts`

 The script will prompt for a question, then process and present the answer using the PGVectorStore data and your OpenAI API key. It will continue to prompt until you enter `q`, `quit` or `exit` as the next query.
@@ -19,7 +19,7 @@ Read and follow the instructions in the README.md file located one directory up

 To import documents and save the embedding vectors to your database:

-> `npx ts-node pinecone-vector-store/load-docs.ts data`
+> `npx tsx pinecone-vector-store/load-docs.ts data`

 where data is the directory containing your input files. Using the _data_ directory in the example above will read all of the files in that directory using the llamaindexTS default readers for each file type.

@@ -29,6 +29,6 @@ where data is the directory containing your input files. Using the _data_ direct

 To query using the resulting vector store:

-> `npx ts-node pinecone-vector-store/query.ts`
+> `npx tsx pinecone-vector-store/query.ts`

 The script will prompt for a question, then process and present the answer using the PineconeVectorStore data and your OpenAI API key. It will continue to prompt until you enter `q`, `quit` or `exit` as the next query.
@@ -8,4 +8,4 @@ Add your OpenAI API Key into a file called `.env` in the parent folder of this d
 OPEN_API_KEY=sk-you-key
 ```

-Now, open a new terminal window and inside `examples`, run `npx ts-node qdrantdb/preFilters.ts`.
+Now, open a new terminal window and inside `examples`, run `npx tsx qdrantdb/preFilters.ts`.
@@ -1,5 +1,55 @@
 # @llamaindex/autotool-02-next-example

+## 0.1.22
+
+### Patch Changes
+
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+  - @llamaindex/autotool@1.0.0
+
+## 0.1.21
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+  - @llamaindex/autotool@1.0.0
+
+## 0.1.20
+
+### Patch Changes
+
+- Updated dependencies [7dce3d2]
+  - llamaindex@0.4.10
+  - @llamaindex/autotool@1.0.0
+
+## 0.1.19
+
+### Patch Changes
+
+- Updated dependencies [3a96a48]
+  - llamaindex@0.4.9
+  - @llamaindex/autotool@1.0.0
+
+## 0.1.18
+
+### Patch Changes
+
+- Updated dependencies [83ebdfb]
+  - llamaindex@0.4.8
+  - @llamaindex/autotool@1.0.0
+
+## 0.1.17
+
+### Patch Changes
+
+- Updated dependencies [41fe871]
+- Updated dependencies [321c39d]
+- Updated dependencies [f7f1af0]
+  - llamaindex@0.4.7
+  - @llamaindex/autotool@1.0.0
+
 ## 0.1.16

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/autotool-02-next-example",
  "private": true,
-  "version": "0.1.16",
+  "version": "0.1.22",
  "scripts": {
    "dev": "next dev",
    "build": "next build",
@@ -51,7 +51,7 @@
    "unplugin": "^1.10.1"
  },
  "peerDependencies": {
-    "llamaindex": "^0.4.6",
+    "llamaindex": "^0.4.12",
    "openai": "^4",
    "typescript": "^4"
  },
@@ -0,0 +1,13 @@
+# @llamaindex/cloud
+
+## 0.1.2
+
+### Patch Changes
+
+- f326ab8: chore: bump version
+
+## 0.1.1
+
+### Patch Changes
+
+- 321c39d: fix: generate api as class
@@ -5,7 +5,7 @@
 ## Usage

 ```ts
-import { OpenAPI, Service } from "@llamaindex/cloud/api";
+import { OpenAPI } from "@llamaindex/cloud/api";
 OpenAPI.TOKEN = "YOUR_API_KEY";
 OpenAPI.BASE = "https://api.cloud.llamaindex.ai/";
 // ...
@@ -9,6 +9,9 @@ export default defineConfig({
    format: "prettier",
    lint: "eslint",
  },
+  services: {
+    asClass: true,
+  },
  types: {
    enums: "javascript",
  },
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/cloud",
-  "version": "0.1.0",
+  "version": "0.1.2",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -1,4 +1 @@
-import * as Service from "./client/services.gen";
-
 export * from "./client";
-export { Service };
@@ -1,5 +1,50 @@
 # @llamaindex/community

+## 0.0.16
+
+### Patch Changes
+
+- f326ab8: chore: bump version
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+
+## 0.0.15
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
+## 0.0.14
+
+### Patch Changes
+
+- Updated dependencies [7dce3d2]
+  - llamaindex@0.4.10
+
+## 0.0.13
+
+### Patch Changes
+
+- Updated dependencies [3a96a48]
+  - llamaindex@0.4.9
+
+## 0.0.12
+
+### Patch Changes
+
+- Updated dependencies [83ebdfb]
+  - llamaindex@0.4.8
+
+## 0.0.11
+
+### Patch Changes
+
+- Updated dependencies [41fe871]
+- Updated dependencies [321c39d]
+- Updated dependencies [f7f1af0]
+  - llamaindex@0.4.7
+
 ## 0.0.10

 ### Patch Changes
@@ -5,6 +5,7 @@
 ## Current Features:

 - Bedrock support for the Anthropic Claude Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock)
+- Bedrock support for the Meta LLama 2 and 3 Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock)

 ## LICENSE

@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/community",
  "description": "Community package for LlamaIndexTS",
-  "version": "0.0.10",
+  "version": "0.0.16",
  "type": "module",
  "types": "dist/type/index.d.ts",
  "main": "dist/cjs/index.js",
@@ -1,53 +1,34 @@
 import {
  BedrockRuntimeClient,
+  type BedrockRuntimeClientConfig,
  InvokeModelCommand,
  InvokeModelWithResponseStreamCommand,
-  ResponseStream,
-  type BedrockRuntimeClientConfig,
-  type InvokeModelCommandInput,
-  type InvokeModelWithResponseStreamCommandInput,
 } from "@aws-sdk/client-bedrock-runtime";
 import type {
-  BaseTool,
  ChatMessage,
  ChatResponse,
-  ChatResponseChunk,
  CompletionResponse,
  LLMChatParamsNonStreaming,
  LLMChatParamsStreaming,
  LLMCompletionParamsNonStreaming,
  LLMCompletionParamsStreaming,
  LLMMetadata,
-  PartialToolCall,
-  ToolCall,
  ToolCallLLMMessageOptions,
 } from "llamaindex";
-import { ToolCallLLM, streamConverter, wrapLLMEvent } from "llamaindex";
-import type {
-  AnthropicNoneStreamingResponse,
-  AnthropicTextContent,
-  StreamEvent,
-  ToolBlock,
-  ToolChoice,
-} from "./types.js";
+import { streamConverter, ToolCallLLM, wrapLLMEvent } from "llamaindex";
 import {
-  mapBaseToolsToAnthropicTools,
-  mapChatMessagesToAnthropicMessages,
-  mapMessageContentToMessageContentDetails,
-  toUtf8,
-} from "./utils.js";
-
-export type BedrockAdditionalChatOptions = { toolChoice: ToolChoice };
+  type BedrockAdditionalChatOptions,
+  type BedrockChatStreamResponse,
+  Provider,
+} from "./provider";
+import { PROVIDERS } from "./providers";
+import { mapMessageContentToMessageContentDetails } from "./utils.js";

 export type BedrockChatParamsStreaming = LLMChatParamsStreaming<
  BedrockAdditionalChatOptions,
  ToolCallLLMMessageOptions
 >;

-export type BedrockChatStreamResponse = AsyncIterable<
-  ChatResponseChunk<ToolCallLLMMessageOptions>
->;
-
 export type BedrockChatParamsNonStreaming = LLMChatParamsNonStreaming<
  BedrockAdditionalChatOptions,
  ToolCallLLMMessageOptions
@@ -151,174 +132,6 @@ export const TOOL_CALL_MODELS = [
  BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
 ];

-abstract class Provider<ProviderStreamEvent extends {} = {}> {
-  abstract getTextFromResponse(response: Record<string, any>): string;
-
-  abstract getToolsFromResponse<T extends {} = {}>(
-    response: Record<string, any>,
-  ): T[];
-
-  getStreamingEventResponse(
-    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,
-      };
-    });
-  }
-
-  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;
-}
-
-class AnthropicProvider extends Provider<StreamEvent> {
-  getResultFromResponse(
-    response: Record<string, any>,
-  ): AnthropicNoneStreamingResponse {
-    return JSON.parse(toUtf8(response.body));
-  }
-
-  getToolsFromResponse<AnthropicToolContent>(
-    response: Record<string, any>,
-  ): AnthropicToolContent[] {
-    const result = this.getResultFromResponse(response);
-    return result.content
-      .filter((item) => item.type === "tool_use")
-      .map((item) => item as AnthropicToolContent);
-  }
-
-  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(" ");
-  }
-
-  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 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,
-            ],
-          };
-        }
-      }
-      const delta = this.getTextFromStreamResponse(response);
-      if (!delta && !options) continue;
-
-      yield {
-        delta,
-        options,
-        raw: response,
-      };
-    }
-  }
-
-  getRequestBody<T extends ChatMessage<ToolCallLLMMessageOptions>>(
-    metadata: LLMMetadata,
-    messages: T[],
-    tools?: BaseTool[],
-    options?: BedrockAdditionalChatOptions,
-  ): 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,
-      }),
-    };
-  }
-}
-
-// Other providers could go here
-const PROVIDERS: { [key: string]: Provider } = {
-  anthropic: new AnthropicProvider(),
-};
-
 const getProvider = (model: string): Provider => {
  const providerName = model.split(".")[0];
  if (!(providerName in PROVIDERS)) {
@@ -373,6 +186,10 @@ export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
    this.temperature = temperature ?? DEFAULT_BEDROCK_PARAMS.temperature;
    this.topP = topP ?? DEFAULT_BEDROCK_PARAMS.topP;
    this.client = new BedrockRuntimeClient(params);
+
+    if (!this.supportToolCall) {
+      console.warn(`The model "${this.model}" doesn't support ToolCall`);
+    }
  }

  get supportToolCall(): boolean {
@@ -402,10 +219,13 @@ export class Bedrock extends ToolCallLLM<BedrockAdditionalChatOptions> {
    );
    const command = new InvokeModelCommand(input);
    const response = await this.client.send(command);
-    const tools = this.provider.getToolsFromResponse(response);
-    const options: ToolCallLLMMessageOptions = tools.length
-      ? { toolCall: tools }
-      : {};
+    let options: ToolCallLLMMessageOptions = {};
+    if (this.supportToolCall) {
+      const tools = this.provider.getToolsFromResponse(response);
+      if (tools.length) {
+        options = { toolCall: tools };
+      }
+    }
    return {
      raw: response,
      message: {
@@ -0,0 +1,59 @@
+import {
+  type InvokeModelCommandInput,
+  type InvokeModelWithResponseStreamCommandInput,
+  ResponseStream,
+} from "@aws-sdk/client-bedrock-runtime";
+import {
+  type BaseTool,
+  type ChatMessage,
+  type ChatResponseChunk,
+  type LLMMetadata,
+  streamConverter,
+  type ToolCallLLMMessageOptions,
+} from "llamaindex";
+import type { ToolChoice } from "./types";
+import { toUtf8 } from "./utils";
+
+export type BedrockAdditionalChatOptions = { toolChoice: ToolChoice };
+
+export type BedrockChatStreamResponse = AsyncIterable<
+  ChatResponseChunk<ToolCallLLMMessageOptions>
+>;
+
+export abstract class Provider<ProviderStreamEvent extends {} = {}> {
+  abstract getTextFromResponse(response: Record<string, any>): string;
+
+  abstract getToolsFromResponse<T extends {} = {}>(
+    response: Record<string, any>,
+  ): T[];
+
+  getStreamingEventResponse(
+    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,
+      };
+    });
+  }
+
+  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;
+}
@@ -0,0 +1,154 @@
+import {
+  type InvokeModelCommandInput,
+  type InvokeModelWithResponseStreamCommandInput,
+  ResponseStream,
+} from "@aws-sdk/client-bedrock-runtime";
+import type {
+  BaseTool,
+  ChatMessage,
+  LLMMetadata,
+  PartialToolCall,
+  ToolCall,
+  ToolCallLLMMessageOptions,
+} from "llamaindex";
+import {
+  type BedrockAdditionalChatOptions,
+  type BedrockChatStreamResponse,
+  Provider,
+} from "../provider";
+import type {
+  AnthropicNoneStreamingResponse,
+  AnthropicStreamEvent,
+  AnthropicTextContent,
+  ToolBlock,
+} from "../types";
+import {
+  mapBaseToolsToAnthropicTools,
+  mapChatMessagesToAnthropicMessages,
+  toUtf8,
+} from "../utils";
+
+export class AnthropicProvider extends Provider<AnthropicStreamEvent> {
+  getResultFromResponse(
+    response: Record<string, any>,
+  ): AnthropicNoneStreamingResponse {
+    return JSON.parse(toUtf8(response.body));
+  }
+
+  getToolsFromResponse<AnthropicToolContent>(
+    response: Record<string, any>,
+  ): AnthropicToolContent[] {
+    const result = this.getResultFromResponse(response);
+    return result.content
+      .filter((item) => item.type === "tool_use")
+      .map((item) => item as AnthropicToolContent);
+  }
+
+  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(" ");
+  }
+
+  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 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,
+            ],
+          };
+        }
+      }
+      const delta = this.getTextFromStreamResponse(response);
+      if (!delta && !options) continue;
+
+      yield {
+        delta,
+        options,
+        raw: response,
+      };
+    }
+  }
+
+  getRequestBody<T extends ChatMessage<ToolCallLLMMessageOptions>>(
+    metadata: LLMMetadata,
+    messages: T[],
+    tools?: BaseTool[],
+    options?: BedrockAdditionalChatOptions,
+  ): 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,
+      }),
+    };
+  }
+}
@@ -0,0 +1,9 @@
+import { Provider } from "../provider";
+import { AnthropicProvider } from "./anthropic";
+import { MetaProvider } from "./meta";
+
+// Other providers should go here
+export const PROVIDERS: { [key: string]: Provider } = {
+  anthropic: new AnthropicProvider(),
+  meta: new MetaProvider(),
+};
@@ -0,0 +1,69 @@
+import type {
+  InvokeModelCommandInput,
+  InvokeModelWithResponseStreamCommandInput,
+} from "@aws-sdk/client-bedrock-runtime";
+import type { ChatMessage, LLMMetadata } from "llamaindex";
+import type { MetaNoneStreamingResponse, MetaStreamEvent } from "../types";
+import {
+  mapChatMessagesToMetaLlama2Messages,
+  mapChatMessagesToMetaLlama3Messages,
+  toUtf8,
+} from "../utils";
+
+import { Provider } from "../provider";
+
+export class MetaProvider extends Provider<MetaStreamEvent> {
+  constructor() {
+    super();
+  }
+
+  getResultFromResponse(
+    response: Record<string, any>,
+  ): MetaNoneStreamingResponse {
+    return JSON.parse(toUtf8(response.body));
+  }
+
+  getToolsFromResponse(_response: Record<string, any>): never {
+    throw new Error("Not supported by this provider.");
+  }
+
+  getTextFromResponse(response: Record<string, any>): string {
+    const result = this.getResultFromResponse(response);
+    return result.generation;
+  }
+
+  getTextFromStreamResponse(response: Record<string, any>): string {
+    const event = this.getStreamingEventResponse(response);
+    if (event?.generation) {
+      return event.generation;
+    }
+    return "";
+  }
+
+  getRequestBody<T extends ChatMessage>(
+    metadata: LLMMetadata,
+    messages: T[],
+  ): InvokeModelCommandInput | InvokeModelWithResponseStreamCommandInput {
+    let promptFunction: (messages: ChatMessage[]) => string;
+
+    if (metadata.model.startsWith("meta.llama3")) {
+      promptFunction = mapChatMessagesToMetaLlama3Messages;
+    } else if (metadata.model.startsWith("meta.llama2")) {
+      promptFunction = mapChatMessagesToMetaLlama2Messages;
+    } 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: promptFunction(messages),
+        max_gen_len: metadata.maxTokens,
+        temperature: metadata.temperature,
+        top_p: metadata.topP,
+      }),
+    };
+  }
+}
@@ -79,7 +79,7 @@ export type ToolChoice =
  | { type: "auto" }
  | { type: "tool"; name: string };

-export type StreamEvent =
+export type AnthropicStreamEvent =
  | { type: "message_start"; message: Message }
  | ContentBlockStart
  | ContentBlockDelta
@@ -93,6 +93,8 @@ export type AnthropicContent =
  | AnthropicToolContent
  | AnthropicToolResultContent;

+export type MetaTextContent = string;
+
 export type AnthropicTextContent = {
  type: "text";
  text: string;
@@ -133,6 +135,11 @@ export type AnthropicMessage = {
  content: AnthropicContent[];
 };

+export type MetaMessage = {
+  role: "user" | "assistant" | "system";
+  content: MetaTextContent;
+};
+
 export type AnthropicNoneStreamingResponse = {
  id: string;
  type: "message";
@@ -143,3 +150,16 @@ export type AnthropicNoneStreamingResponse = {
  stop_sequence?: string;
  usage: { input_tokens: number; output_tokens: number };
 };
+
+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;
@@ -4,6 +4,7 @@ import type {
  JSONObject,
  MessageContent,
  MessageContentDetail,
+  MessageContentTextDetail,
  ToolCallLLMMessageOptions,
  ToolMetadata,
 } from "llamaindex";
@@ -13,6 +14,7 @@ import type {
  AnthropicMediaTypes,
  AnthropicMessage,
  AnthropicTextContent,
+  MetaMessage,
 } from "./types.js";

 const ACCEPTED_IMAGE_MIME_TYPES = [
@@ -148,6 +150,85 @@ export const mapChatMessagesToAnthropicMessages = <
  return mergeNeighboringSameRoleMessages(mapped);
 };

+export const mapChatMessagesToMetaMessages = <T extends ChatMessage>(
+  messages: T[],
+): MetaMessage[] => {
+  return messages.map((msg) => {
+    let content: string;
+    if (typeof msg.content === "string") {
+      content = msg.content;
+    } else {
+      content = (msg.content[0] as MessageContentTextDetail).text;
+    }
+    return {
+      role:
+        msg.role === "assistant"
+          ? "assistant"
+          : msg.role === "user"
+            ? "user"
+            : "system",
+      content,
+    };
+  });
+};
+
+/**
+ * Documentation at https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3
+ */
+export const mapChatMessagesToMetaLlama3Messages = <T extends ChatMessage>(
+  messages: T[],
+): string => {
+  const mapped = mapChatMessagesToMetaMessages(messages).map((message) => {
+    const text = message.content;
+    return `<|start_header_id|>${message.role}<|end_header_id|>\n${text}\n<|eot_id|>\n`;
+  });
+  return (
+    "<|begin_of_text|>" +
+    mapped.join("\n") +
+    "\n<|start_header_id|>assistant<|end_header_id|>\n"
+  );
+};
+
+/**
+ * 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 += ` ${text} </s>\n`;
+      needsStartAgain = true;
+    }
+  }
+  return output;
+};
+
 export const mapTextContent = (text: string): AnthropicTextContent => {
  return { type: "text", text };
 };
@@ -0,0 +1,17 @@
+# @llamaindex/core
+
+## 0.0.3
+
+### Patch Changes
+
+- f326ab8: chore: bump version
+- Updated dependencies [f326ab8]
+  - @llamaindex/env@0.1.8
+
+## 0.0.2
+
+### Patch Changes
+
+- f10b41d: fix: release files
+- Updated dependencies [41fe871]
+  - @llamaindex/env@0.1.7
@@ -1,9 +1,23 @@
 {
  "name": "@llamaindex/core",
  "type": "module",
-  "version": "0.0.1",
+  "version": "0.0.3",
  "description": "LlamaIndex Core Module",
  "exports": {
+    "./llms": {
+      "require": {
+        "types": "./dist/llms/index.d.cts",
+        "default": "./dist/llms/index.cjs"
+      },
+      "import": {
+        "types": "./dist/llms/index.d.ts",
+        "default": "./dist/llms/index.js"
+      },
+      "default": {
+        "types": "./dist/llms/index.d.ts",
+        "default": "./dist/llms/index.js"
+      }
+    },
    "./decorator": {
      "require": {
        "types": "./dist/decorator/index.d.cts",
@@ -47,6 +61,9 @@
      }
    }
  },
+  "files": [
+    "dist"
+  ],
  "scripts": {
    "dev": "bunchee --watch",
    "build": "bunchee"
@@ -57,6 +74,7 @@
    "url": "https://github.com/himself65/LlamaIndexTS.git"
  },
  "devDependencies": {
+    "ajv": "^8.16.0",
    "bunchee": "^5.2.1"
  },
  "dependencies": {
@@ -0,0 +1,9 @@
+export type UUID = `${string}-${string}-${string}-${string}-${string}`;
+
+export type JSONValue = string | number | boolean | JSONObject | JSONArray;
+
+export type JSONObject = {
+  [key: string]: JSONValue;
+};
+
+export type JSONArray = Array<JSONValue>;
@@ -1 +0,0 @@
-export * from "./schema";
@@ -0,0 +1,31 @@
+export type {
+  BaseTool,
+  BaseToolWithCall,
+  ChatMessage,
+  ChatResponse,
+  ChatResponseChunk,
+  CompletionResponse,
+  LLM,
+  LLMChat,
+  LLMChatParamsBase,
+  LLMChatParamsNonStreaming,
+  LLMChatParamsStreaming,
+  LLMCompletionParamsBase,
+  LLMCompletionParamsNonStreaming,
+  LLMCompletionParamsStreaming,
+  LLMMetadata,
+  MessageContent,
+  MessageContentDetail,
+  MessageContentImageDetail,
+  MessageContentTextDetail,
+  MessageType,
+  PartialToolCall,
+  TextChatMessage,
+  ToolCall,
+  ToolCallLLMMessageOptions,
+  ToolCallOptions,
+  ToolMetadata,
+  ToolOutput,
+  ToolResult,
+  ToolResultOptions,
+} from "./type";
@@ -0,0 +1,245 @@
+import type { Tokenizers } from "@llamaindex/env";
+import type { JSONSchemaType } from "ajv";
+import type { JSONObject, JSONValue } from "../global/type";
+
+/**
+ * @internal
+ */
+export interface LLMChat<
+  AdditionalChatOptions extends object = object,
+  AdditionalMessageOptions extends object = object,
+> {
+  chat(
+    params:
+      | LLMChatParamsStreaming<AdditionalChatOptions>
+      | LLMChatParamsNonStreaming<AdditionalChatOptions>,
+  ): Promise<
+    | ChatResponse<AdditionalMessageOptions>
+    | AsyncIterable<ChatResponseChunk<AdditionalMessageOptions>>
+  >;
+}
+
+/**
+ * Unified language model interface
+ */
+export interface LLM<
+  AdditionalChatOptions extends object = object,
+  AdditionalMessageOptions extends object = object,
+> extends LLMChat<AdditionalChatOptions> {
+  metadata: LLMMetadata;
+  /**
+   * Get a chat response from the LLM
+   */
+  chat(
+    params: LLMChatParamsStreaming<
+      AdditionalChatOptions,
+      AdditionalMessageOptions
+    >,
+  ): Promise<AsyncIterable<ChatResponseChunk>>;
+  chat(
+    params: LLMChatParamsNonStreaming<
+      AdditionalChatOptions,
+      AdditionalMessageOptions
+    >,
+  ): Promise<ChatResponse<AdditionalMessageOptions>>;
+
+  /**
+   * Get a prompt completion from the LLM
+   */
+  complete(
+    params: LLMCompletionParamsStreaming,
+  ): Promise<AsyncIterable<CompletionResponse>>;
+  complete(
+    params: LLMCompletionParamsNonStreaming,
+  ): Promise<CompletionResponse>;
+}
+
+export type MessageType = "user" | "assistant" | "system" | "memory";
+
+export type TextChatMessage<AdditionalMessageOptions extends object = object> =
+  {
+    content: string;
+    role: MessageType;
+    options?: undefined | AdditionalMessageOptions;
+  };
+
+export type ChatMessage<AdditionalMessageOptions extends object = object> = {
+  content: MessageContent;
+  role: MessageType;
+  options?: undefined | AdditionalMessageOptions;
+};
+
+export interface ChatResponse<
+  AdditionalMessageOptions extends object = object,
+> {
+  message: ChatMessage<AdditionalMessageOptions>;
+  /**
+   * Raw response from the LLM
+   *
+   * If LLM response an iterable of chunks, this will be an array of those chunks
+   */
+  raw: object | null;
+}
+
+export type ChatResponseChunk<
+  AdditionalMessageOptions extends object = object,
+> = {
+  raw: object | null;
+  delta: string;
+  options?: undefined | AdditionalMessageOptions;
+};
+
+export interface CompletionResponse {
+  text: string;
+  /**
+   * Raw response from the LLM
+   *
+   * It's possible that this is `null` if the LLM response an iterable of chunks
+   */
+  raw: object | null;
+}
+
+export type LLMMetadata = {
+  model: string;
+  temperature: number;
+  topP: number;
+  maxTokens?: number;
+  contextWindow: number;
+  tokenizer: Tokenizers | undefined;
+};
+
+export interface LLMChatParamsBase<
+  AdditionalChatOptions extends object = object,
+  AdditionalMessageOptions extends object = object,
+> {
+  messages: ChatMessage<AdditionalMessageOptions>[];
+  additionalChatOptions?: AdditionalChatOptions;
+  tools?: BaseTool[];
+}
+
+export interface LLMChatParamsStreaming<
+  AdditionalChatOptions extends object = object,
+  AdditionalMessageOptions extends object = object,
+> extends LLMChatParamsBase<AdditionalChatOptions, AdditionalMessageOptions> {
+  stream: true;
+}
+
+export interface LLMChatParamsNonStreaming<
+  AdditionalChatOptions extends object = object,
+  AdditionalMessageOptions extends object = object,
+> extends LLMChatParamsBase<AdditionalChatOptions, AdditionalMessageOptions> {
+  stream?: false;
+}
+
+export interface LLMCompletionParamsBase {
+  prompt: MessageContent;
+}
+
+export interface LLMCompletionParamsStreaming extends LLMCompletionParamsBase {
+  stream: true;
+}
+
+export interface LLMCompletionParamsNonStreaming
+  extends LLMCompletionParamsBase {
+  stream?: false | null;
+}
+
+export type MessageContentTextDetail = {
+  type: "text";
+  text: string;
+};
+
+export type MessageContentImageDetail = {
+  type: "image_url";
+  image_url: { url: string };
+};
+
+export type MessageContentDetail =
+  | MessageContentTextDetail
+  | MessageContentImageDetail;
+
+/**
+ * Extended type for the content of a message that allows for multi-modal messages.
+ */
+export type MessageContent = string | MessageContentDetail[];
+
+export type ToolCall = {
+  name: string;
+  input: JSONObject;
+  id: string;
+};
+
+// happened in streaming response, the tool call is not ready yet
+export type PartialToolCall = {
+  name: string;
+  id: string;
+  // input is not ready yet, JSON.parse(input) will throw an error
+  input: string;
+};
+
+export type ToolResult = {
+  id: string;
+  result: string;
+  isError: boolean;
+};
+
+export type ToolCallOptions = {
+  toolCall: (ToolCall | PartialToolCall)[];
+};
+
+export type ToolResultOptions = {
+  toolResult: ToolResult;
+};
+
+export type ToolCallLLMMessageOptions =
+  | ToolResultOptions
+  | ToolCallOptions
+  | {};
+
+type Known =
+  | { [key: string]: Known }
+  | [Known, ...Known[]]
+  | Known[]
+  | number
+  | string
+  | boolean
+  | null;
+
+export type ToolMetadata<
+  Parameters extends Record<string, unknown> = Record<string, unknown>,
+> = {
+  description: string;
+  name: string;
+  /**
+   * OpenAI uses JSON Schema to describe the parameters that a tool can take.
+   * @link https://json-schema.org/understanding-json-schema
+   */
+  parameters?: Parameters;
+};
+
+/**
+ * Simple Tool interface. Likely to change.
+ */
+export interface BaseTool<Input = any> {
+  /**
+   * This could be undefined if the implementation is not provided,
+   *  which might be the case when communicating with a llm.
+   *
+   * @return {JSONValue | Promise<JSONValue>} The output of the tool.
+   */
+  call?: (input: Input) => JSONValue | Promise<JSONValue>;
+  metadata: // if user input any, we cannot check the schema
+  Input extends Known ? ToolMetadata<JSONSchemaType<Input>> : ToolMetadata;
+}
+
+export type BaseToolWithCall<Input = any> = Omit<BaseTool<Input>, "call"> & {
+  call: NonNullable<Pick<BaseTool<Input>, "call">["call"]>;
+};
+
+export type ToolOutput = {
+  tool: BaseTool | undefined;
+  // all of existing function calling LLMs only support object input
+  input: JSONObject;
+  output: JSONValue;
+  isError: boolean;
+};
@@ -1,5 +1,7 @@
 import { z } from "zod";

+export const anyFunctionSchema = z.function(z.tuple([]).rest(z.any()), z.any());
+
 export const toolMetadataSchema = z.object({
  description: z.string(),
  name: z.string(),
@@ -7,7 +9,7 @@ export const toolMetadataSchema = z.object({
 });

 export const baseToolSchema = z.object({
-  call: z.optional(z.function()),
+  call: anyFunctionSchema.optional(),
  metadata: toolMetadataSchema,
 });

@@ -1,5 +1,17 @@
 # @llamaindex/env

+## 0.1.8
+
+### Patch Changes
+
+- f326ab8: chore: bump version
+
+## 0.1.7
+
+### Patch Changes
+
+- 41fe871: Add support for azure dynamic session tool
+
 ## 0.1.6

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/env",
  "description": "environment wrapper, supports all JS environment including node, deno, bun, edge runtime, and cloudflare worker",
-  "version": "0.1.6",
+  "version": "0.1.8",
  "type": "module",
  "types": "dist/type/index.d.ts",
  "main": "dist/cjs/index.js",
@@ -5,6 +5,7 @@
 *
 * @module
 */
+import { createWriteStream } from "node:fs";
 import fs from "node:fs/promises";

-export { fs };
+export { createWriteStream, fs };
@@ -15,12 +15,14 @@ import { ok } from "node:assert";
 import { createHash, randomUUID } from "node:crypto";
 import { EOL } from "node:os";
 import path from "node:path";
+import { Readable } from "node:stream";
 import {
  ReadableStream,
  TransformStream,
  WritableStream,
 } from "node:stream/web";
-import { fs } from "./fs/node.js";
+import { fileURLToPath } from "node:url";
+import { createWriteStream, fs } from "./fs/node.js";
 import type { SHA256 } from "./polyfill.js";

 export function createSHA256(): SHA256 {
@@ -38,11 +40,14 @@ export function createSHA256(): SHA256 {
 export { Tokenizers, tokenizers, type Tokenizer } from "./tokenizers/node.js";
 export { AsyncLocalStorage, CustomEvent, getEnv, setEnvs } from "./utils.js";
 export {
+  createWriteStream,
  EOL,
+  fileURLToPath,
  fs,
  ok,
  path,
  randomUUID,
+  Readable,
  ReadableStream,
  TransformStream,
  WritableStream,
@@ -1,5 +1,49 @@
 # @llamaindex/experimental

+## 0.0.47
+
+### Patch Changes
+
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+
+## 0.0.46
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
+## 0.0.45
+
+### Patch Changes
+
+- Updated dependencies [7dce3d2]
+  - llamaindex@0.4.10
+
+## 0.0.44
+
+### Patch Changes
+
+- Updated dependencies [3a96a48]
+  - llamaindex@0.4.9
+
+## 0.0.43
+
+### Patch Changes
+
+- Updated dependencies [83ebdfb]
+  - llamaindex@0.4.8
+
+## 0.0.42
+
+### Patch Changes
+
+- Updated dependencies [41fe871]
+- Updated dependencies [321c39d]
+- Updated dependencies [f7f1af0]
+  - llamaindex@0.4.7
+
 ## 0.0.41

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/experimental",
  "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.41",
+  "version": "0.0.47",
  "type": "module",
  "types": "dist/type/index.d.ts",
  "main": "dist/cjs/index.js",
@@ -1,5 +1,53 @@
 # llamaindex

+## 0.4.12
+
+### Patch Changes
+
+- f326ab8: chore: bump version
+- Updated dependencies [f326ab8]
+  - @llamaindex/cloud@0.1.2
+  - @llamaindex/core@0.0.3
+  - @llamaindex/env@0.1.8
+
+## 0.4.11
+
+### Patch Changes
+
+- 8bf5b4a: fix: llama parse input spreadsheet
+
+## 0.4.10
+
+### Patch Changes
+
+- 7dce3d2: fix: disable External Filters for Gemini
+
+## 0.4.9
+
+### Patch Changes
+
+- 3a96a48: fix: anthroipic image input
+
+## 0.4.8
+
+### Patch Changes
+
+- 83ebdfb: fix: next.js build error
+
+## 0.4.7
+
+### Patch Changes
+
+- 41fe871: Add support for azure dynamic session tool
+- 321c39d: fix: generate api as class
+- f7f1af0: fix: throw error when no pipeline found
+- Updated dependencies [41fe871]
+- Updated dependencies [f10b41d]
+- Updated dependencies [321c39d]
+  - @llamaindex/env@0.1.7
+  - @llamaindex/core@0.0.2
+  - @llamaindex/cloud@0.1.1
+
 ## 0.4.6

 ### Patch Changes
@@ -1,5 +1,49 @@
 # @llamaindex/cloudflare-worker-agent-test

+## 0.0.31
+
+### Patch Changes
+
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+
+## 0.0.30
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
+## 0.0.29
+
+### Patch Changes
+
+- Updated dependencies [7dce3d2]
+  - llamaindex@0.4.10
+
+## 0.0.28
+
+### Patch Changes
+
+- Updated dependencies [3a96a48]
+  - llamaindex@0.4.9
+
+## 0.0.27
+
+### Patch Changes
+
+- Updated dependencies [83ebdfb]
+  - llamaindex@0.4.8
+
+## 0.0.26
+
+### Patch Changes
+
+- Updated dependencies [41fe871]
+- Updated dependencies [321c39d]
+- Updated dependencies [f7f1af0]
+  - llamaindex@0.4.7
+
 ## 0.0.25

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.25",
+  "version": "0.0.31",
  "type": "module",
  "private": true,
  "scripts": {
@@ -1,5 +1,49 @@
 # @llamaindex/next-agent-test

+## 0.1.31
+
+### Patch Changes
+
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+
+## 0.1.30
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
+## 0.1.29
+
+### Patch Changes
+
+- Updated dependencies [7dce3d2]
+  - llamaindex@0.4.10
+
+## 0.1.28
+
+### Patch Changes
+
+- Updated dependencies [3a96a48]
+  - llamaindex@0.4.9
+
+## 0.1.27
+
+### Patch Changes
+
+- Updated dependencies [83ebdfb]
+  - llamaindex@0.4.8
+
+## 0.1.26
+
+### Patch Changes
+
+- Updated dependencies [41fe871]
+- Updated dependencies [321c39d]
+- Updated dependencies [f7f1af0]
+  - llamaindex@0.4.7
+
 ## 0.1.25

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/next-agent-test",
-  "version": "0.1.25",
+  "version": "0.1.31",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -1,7 +1,7 @@
 "use server";
 import { createStreamableUI } from "ai/rsc";
+import type { ChatMessage } from "llamaindex";
 import { OpenAIAgent } from "llamaindex";
-import type { ChatMessage } from "llamaindex/llm/types";

 export async function chatWithAgent(
  question: string,
@@ -1,5 +1,49 @@
 # test-edge-runtime

+## 0.1.30
+
+### Patch Changes
+
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+
+## 0.1.29
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
+## 0.1.28
+
+### Patch Changes
+
+- Updated dependencies [7dce3d2]
+  - llamaindex@0.4.10
+
+## 0.1.27
+
+### Patch Changes
+
+- Updated dependencies [3a96a48]
+  - llamaindex@0.4.9
+
+## 0.1.26
+
+### Patch Changes
+
+- Updated dependencies [83ebdfb]
+  - llamaindex@0.4.8
+
+## 0.1.25
+
+### Patch Changes
+
+- Updated dependencies [41fe871]
+- Updated dependencies [321c39d]
+- Updated dependencies [f7f1af0]
+  - llamaindex@0.4.7
+
 ## 0.1.24

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.24",
+  "version": "0.1.30",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -1,5 +1,50 @@
 # @llamaindex/next-node-runtime

+## 0.0.12
+
+### Patch Changes
+
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+
+## 0.0.11
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
+## 0.0.10
+
+### Patch Changes
+
+- Updated dependencies [7dce3d2]
+  - llamaindex@0.4.10
+
+## 0.0.9
+
+### Patch Changes
+
+- Updated dependencies [3a96a48]
+  - llamaindex@0.4.9
+
+## 0.0.8
+
+### Patch Changes
+
+- 83ebdfb: fix: next.js build error
+- Updated dependencies [83ebdfb]
+  - llamaindex@0.4.8
+
+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [41fe871]
+- Updated dependencies [321c39d]
+- Updated dependencies [f7f1af0]
+  - llamaindex@0.4.7
+
 ## 0.0.6

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.0.6",
+  "version": "0.0.12",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -0,0 +1,68 @@
+"use server";
+import {
+  OpenAI,
+  OpenAIAgent,
+  QueryEngineTool,
+  Settings,
+  VectorStoreIndex,
+} from "llamaindex";
+import { HuggingFaceEmbedding } from "llamaindex/embeddings/HuggingFaceEmbedding";
+import { SimpleDirectoryReader } from "llamaindex/readers/SimpleDirectoryReader";
+
+Settings.llm = new OpenAI({
+  // eslint-disable-next-line turbo/no-undeclared-env-vars
+  apiKey: process.env.NEXT_PUBLIC_OPENAI_KEY ?? "FAKE_KEY_TO_PASS_TESTS",
+  model: "gpt-4o",
+});
+Settings.embedModel = new HuggingFaceEmbedding({
+  modelType: "BAAI/bge-small-en-v1.5",
+  quantized: false,
+});
+Settings.callbackManager.on("llm-tool-call", (event) => {
+  console.log(event.detail.payload);
+});
+Settings.callbackManager.on("llm-tool-result", (event) => {
+  console.log(event.detail.payload);
+});
+
+export async function getOpenAIModelRequest(query: string) {
+  try {
+    const currentDir = __dirname;
+
+    // load our data and create a query engine
+    const reader = new SimpleDirectoryReader();
+    const documents = await reader.loadData(currentDir);
+    const index = await VectorStoreIndex.fromDocuments(documents);
+    const retriever = index.asRetriever({
+      similarityTopK: 10,
+    });
+    const queryEngine = index.asQueryEngine({
+      retriever,
+    });
+
+    // define the query engine as a tool
+    const tools = [
+      new QueryEngineTool({
+        queryEngine: queryEngine,
+        metadata: {
+          name: "deployment_details_per_env",
+          description: `This tool can answer detailed questions about deployments happened in various environments.`,
+        },
+      }),
+    ];
+    // create the agent
+    const agent = new OpenAIAgent({ tools });
+
+    const { response } = await agent.chat({
+      message: query,
+    });
+    return {
+      message: response,
+    };
+  } catch (err) {
+    console.error(err);
+    return {
+      errors: "Error Calling OpenAI Model",
+    };
+  }
+}
@@ -0,0 +1,10 @@
+import { getOpenAIModelRequest } from "@/actions/openai";
+import { NextRequest, NextResponse } from "next/server";
+
+// POST /api/openai
+export async function POST(request: NextRequest) {
+  const body = await request.json();
+  const content = await getOpenAIModelRequest(body.query);
+
+  return NextResponse.json(content, { status: 200 });
+}
@@ -1,5 +1,49 @@
 # @llamaindex/waku-query-engine-test

+## 0.0.31
+
+### Patch Changes
+
+- Updated dependencies [f326ab8]
+  - llamaindex@0.4.12
+
+## 0.0.30
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
+## 0.0.29
+
+### Patch Changes
+
+- Updated dependencies [7dce3d2]
+  - llamaindex@0.4.10
+
+## 0.0.28
+
+### Patch Changes
+
+- Updated dependencies [3a96a48]
+  - llamaindex@0.4.9
+
+## 0.0.27
+
+### Patch Changes
+
+- Updated dependencies [83ebdfb]
+  - llamaindex@0.4.8
+
+## 0.0.26
+
+### Patch Changes
+
+- Updated dependencies [41fe871]
+- Updated dependencies [321c39d]
+- Updated dependencies [f7f1af0]
+  - llamaindex@0.4.7
+
 ## 0.0.25

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.25",
+  "version": "0.0.31",
  "type": "module",
  "private": true,
  "scripts": {
@@ -7,7 +7,7 @@ import type {
  LLMChatParamsStreaming,
  LLMCompletionParamsNonStreaming,
  LLMCompletionParamsStreaming,
-} from "llamaindex/llm/types";
+} from "llamaindex";
 import { extractText } from "llamaindex/llm/utils";
 import { deepStrictEqual, strictEqual } from "node:assert";
 import { llmCompleteMockStorage } from "../../node/utils.js";
@@ -1,6 +1,6 @@
 {
  "name": "llamaindex",
-  "version": "0.4.6",
+  "version": "0.4.12",
  "license": "MIT",
  "type": "module",
  "keywords": [
@@ -22,6 +22,7 @@
  "dependencies": {
    "@anthropic-ai/sdk": "^0.21.1",
    "@aws-crypto/sha256-js": "^5.2.0",
+    "@azure/identity": "^4.2.1",
    "@datastax/astra-db-ts": "^1.2.1",
    "@google-cloud/vertexai": "^1.2.0",
    "@google/generative-ai": "^0.12.0",
@@ -33,7 +34,8 @@
    "@mistralai/mistralai": "^0.4.0",
    "@pinecone-database/pinecone": "^2.2.2",
    "@qdrant/js-client-rest": "^1.9.0",
-    "@types/lodash": "^4.17.5",
+    "@types/lodash": "^4.17.4",
+    "@types/node": "^20.14.5",
    "@types/papaparse": "^5.3.14",
    "@types/pg": "^8.11.6",
    "@xenova/transformers": "^2.17.2",
@@ -1,8 +1,8 @@
+import type { ChatMessage, LLM, MessageType } from "@llamaindex/core/llms";
 import { tokenizers, type Tokenizer } from "@llamaindex/env";
 import type { SummaryPrompt } from "./Prompt.js";
 import { defaultSummaryPrompt, messagesToHistoryStr } from "./Prompt.js";
 import { OpenAI } from "./llm/openai.js";
-import type { ChatMessage, LLM, MessageType } from "./llm/types.js";
 import { extractText } from "./llm/utils.js";

 /**
@@ -1,9 +1,9 @@
-import type { NodeWithScore } from "@llamaindex/core/schema";
 import type {
  ChatMessage,
  ChatResponse,
  ChatResponseChunk,
-} from "./llm/types.js";
+} from "@llamaindex/core/llms";
+import type { NodeWithScore } from "@llamaindex/core/schema";
 import { extractText } from "./llm/utils.js";

 export class EngineResponse implements ChatResponse, ChatResponseChunk {
@@ -1,6 +1,5 @@
+import type { ChatMessage, ToolMetadata } from "@llamaindex/core/llms";
 import type { SubQuestion } from "./engines/query/types.js";
-import type { ChatMessage } from "./llm/types.js";
-import type { ToolMetadata } from "./types.js";

 /**
 * A SimplePrompt is a function that takes a dictionary of inputs and returns a string.
@@ -1,3 +1,4 @@
+import type { LLM, ToolMetadata } from "@llamaindex/core/llms";
 import { SubQuestionOutputParser } from "./OutputParser.js";
 import type { SubQuestionPrompt } from "./Prompt.js";
 import { buildToolsText, defaultSubQuestionPrompt } from "./Prompt.js";
@@ -6,13 +7,8 @@ import type {
  SubQuestion,
 } from "./engines/query/types.js";
 import { OpenAI } from "./llm/openai.js";
-import type { LLM } from "./llm/types.js";
 import { PromptMixin } from "./prompts/index.js";
-import type {
-  BaseOutputParser,
-  StructuredOutput,
-  ToolMetadata,
-} from "./types.js";
+import type { BaseOutputParser, StructuredOutput } from "./types.js";

 /**
 * LLMQuestionGenerator uses the LLM to generate new questions for the LLM using tools and a user query.
@@ -1,8 +1,8 @@
+import type { LLM } from "@llamaindex/core/llms";
 import { PromptHelper } from "./PromptHelper.js";
 import { OpenAIEmbedding } from "./embeddings/OpenAIEmbedding.js";
 import type { BaseEmbedding } from "./embeddings/types.js";
 import { OpenAI } from "./llm/openai.js";
-import type { LLM } from "./llm/types.js";
 import { SimpleNodeParser } from "./nodeParsers/SimpleNodeParser.js";
 import type { NodeParser } from "./nodeParsers/types.js";

@@ -5,6 +5,7 @@ import { OpenAI } from "./llm/openai.js";
 import { PromptHelper } from "./PromptHelper.js";
 import { SimpleNodeParser } from "./nodeParsers/SimpleNodeParser.js";

+import type { LLM } from "@llamaindex/core/llms";
 import { AsyncLocalStorage, getEnv } from "@llamaindex/env";
 import type { ServiceContext } from "./ServiceContext.js";
 import type { BaseEmbedding } from "./embeddings/types.js";
@@ -18,7 +19,6 @@ import {
  setEmbeddedModel,
  withEmbeddedModel,
 } from "./internal/settings/EmbedModel.js";
-import type { LLM } from "./llm/types.js";
 import type { NodeParser } from "./nodeParsers/types.js";

 export type PromptConfig = {
@@ -1,3 +1,10 @@
+import type {
+  BaseToolWithCall,
+  ChatMessage,
+  LLM,
+  MessageContent,
+  ToolOutput,
+} from "@llamaindex/core/llms";
 import { ReadableStream, TransformStream, randomUUID } from "@llamaindex/env";
 import { ChatHistory } from "../ChatHistory.js";
 import { EngineResponse } from "../EngineResponse.js";
@@ -11,9 +18,7 @@ import { wrapEventCaller } from "../internal/context/EventCaller.js";
 import { consoleLogger, emptyLogger } from "../internal/logger.js";
 import { getCallbackManager } from "../internal/settings/CallbackManager.js";
 import { isAsyncIterable } from "../internal/utils.js";
-import type { ChatMessage, LLM, MessageContent } from "../llm/index.js";
 import { ObjectRetriever } from "../objects/index.js";
-import type { BaseToolWithCall, ToolOutput } from "../types.js";
 import type {
  AgentTaskContext,
  TaskHandler,
@@ -229,13 +234,12 @@ export abstract class AgentRunner<
    const { llm, getTools, stream } = step.context;
    const lastMessage = step.context.store.messages.at(-1)!.content;
    const tools = await getTools(lastMessage);
-    const response = await llm.chat({
-      // @ts-expect-error
-      stream,
-      tools,
-      messages: [...step.context.store.messages],
-    });
    if (!stream) {
+      const response = await llm.chat({
+        stream,
+        tools,
+        messages: [...step.context.store.messages],
+      });
      await stepTools<LLM>({
        response,
        tools,
@@ -243,6 +247,11 @@ export abstract class AgentRunner<
        enqueueOutput,
      });
    } else {
+      const response = await llm.chat({
+        stream,
+        tools,
+        messages: [...step.context.store.messages],
+      });
      await stepToolsStreaming<LLM>({
        response,
        tools,
@@ -1,7 +1,6 @@
-import type { LLM } from "../llm/index.js";
+import type { BaseToolWithCall, LLM } from "@llamaindex/core/llms";
 import { ObjectRetriever } from "../objects/index.js";
 import { Settings } from "../Settings.js";
-import type { BaseToolWithCall } from "../types.js";
 import { AgentRunner, AgentWorker, type AgentParamsBase } from "./base.js";
 import { validateAgentParams } from "./utils.js";

@@ -1,18 +1,19 @@
+import type {
+  BaseTool,
+  ChatMessage,
+  ChatResponse,
+  ChatResponseChunk,
+  LLM,
+} from "@llamaindex/core/llms";
 import { randomUUID, ReadableStream } from "@llamaindex/env";
 import { getReACTAgentSystemHeader } from "../internal/prompt/react.js";
 import {
  isAsyncIterable,
  stringifyJSONToMessageContent,
 } from "../internal/utils.js";
-import {
-  type ChatMessage,
-  type ChatResponse,
-  type ChatResponseChunk,
-  type LLM,
-} from "../llm/index.js";
 import { extractText } from "../llm/utils.js";
 import { Settings } from "../Settings.js";
-import type { BaseTool, JSONObject, JSONValue } from "../types.js";
+import type { JSONObject, JSONValue } from "../types.js";
 import { AgentRunner, AgentWorker, type AgentParamsBase } from "./base.js";
 import type { TaskHandler } from "./types.js";
 import {
@@ -1,14 +1,16 @@
-import { ReadableStream } from "@llamaindex/env";
-import type { Logger } from "../internal/logger.js";
-import type { BaseEvent } from "../internal/type.js";
 import type {
+  BaseToolWithCall,
  ChatMessage,
  ChatResponse,
  ChatResponseChunk,
  LLM,
  MessageContent,
-} from "../llm/types.js";
-import type { BaseToolWithCall, ToolOutput, UUID } from "../types.js";
+  ToolOutput,
+} from "@llamaindex/core/llms";
+import { ReadableStream } from "@llamaindex/env";
+import type { Logger } from "../internal/logger.js";
+import type { BaseEvent } from "../internal/type.js";
+import type { UUID } from "../types.js";

 export type AgentTaskContext<
  Model extends LLM,
@@ -1,3 +1,15 @@
+import type {
+  BaseTool,
+  ChatMessage,
+  ChatResponse,
+  ChatResponseChunk,
+  LLM,
+  PartialToolCall,
+  TextChatMessage,
+  ToolCall,
+  ToolCallLLMMessageOptions,
+  ToolOutput,
+} from "@llamaindex/core/llms";
 import { baseToolWithCallSchema } from "@llamaindex/core/schema";
 import { ReadableStream } from "@llamaindex/env";
 import { z } from "zod";
@@ -8,17 +20,7 @@ import {
  prettifyError,
  stringifyJSONToMessageContent,
 } from "../internal/utils.js";
-import type {
-  ChatMessage,
-  ChatResponse,
-  ChatResponseChunk,
-  LLM,
-  PartialToolCall,
-  TextChatMessage,
-  ToolCall,
-  ToolCallLLMMessageOptions,
-} from "../llm/index.js";
-import type { BaseTool, JSONObject, JSONValue, ToolOutput } from "../types.js";
+import type { JSONObject, JSONValue } from "../types.js";
 import type { AgentParamsBase } from "./base.js";
 import type { TaskHandler } from "./types.js";

@@ -31,10 +33,12 @@ type StepToolsResponseParams<Model extends LLM> = {
  >[1];
 };

-type StepToolsStreamingResponseParams<Model extends LLM> =
-  StepToolsResponseParams<Model> & {
-    response: AsyncIterable<ChatResponseChunk<ToolCallLLMMessageOptions>>;
-  };
+type StepToolsStreamingResponseParams<Model extends LLM> = Omit<
+  StepToolsResponseParams<Model>,
+  "response"
+> & {
+  response: AsyncIterable<ChatResponseChunk<ToolCallLLMMessageOptions>>;
+};

 // #TODO stepTools and stepToolsStreaming should be moved to a better abstraction

@@ -83,7 +87,7 @@ export async function stepToolsStreaming<Model extends LLM>({
      }
    }

-    // If there are toolCalls but they didn't get read into the stream, used for Gemini
+    // If there are toolCalls, but they didn't get read into the stream, used for Gemini
    if (!toolCalls.size && value.options && "toolCall" in value.options) {
      value.options.toolCall.forEach((toolCall) => {
        toolCalls.set(toolCall.id, toolCall);
@@ -1,4 +1,5 @@
 import type { Anthropic } from "@anthropic-ai/sdk";
+import type { MessageContent } from "@llamaindex/core/llms";
 import type { NodeWithScore } from "@llamaindex/core/schema";
 import { CustomEvent } from "@llamaindex/env";
 import type { AgentEndEvent, AgentStartEvent } from "../agent/types.js";
@@ -12,7 +13,6 @@ import type {
  LLMStreamEvent,
  LLMToolCallEvent,
  LLMToolResultEvent,
-  MessageContent,
  RetrievalEndEvent,
  RetrievalStartEvent,
 } from "../llm/types.js";
@@ -11,8 +11,9 @@ import { getPipelineCreate } from "./config.js";
 import type { CloudConstructorParams } from "./constants.js";
 import { getAppBaseUrl, initService } from "./utils.js";

-import { Service } from "@llamaindex/cloud/api";
+import { PipelinesService, ProjectsService } from "@llamaindex/cloud/api";
 import { getEnv } from "@llamaindex/env";
+import { Settings } from "../Settings.js";
 import { OpenAIEmbedding } from "../embeddings/OpenAIEmbedding.js";
 import { SimpleNodeParser } from "../nodeParsers/SimpleNodeParser.js";

@@ -25,7 +26,7 @@ export class LlamaCloudIndex {
  }

  private async waitForPipelineIngestion(
-    verbose = false,
+    verbose = Settings.debug,
    raiseOnError = false,
  ): Promise<void> {
    const pipelineId = await this.getPipelineId(
@@ -39,9 +40,11 @@ export class LlamaCloudIndex {

    while (true) {
      const pipelineStatus =
-        await Service.getPipelineStatusApiV1PipelinesPipelineIdStatusGet({
-          pipelineId,
-        });
+        await PipelinesService.getPipelineStatusApiV1PipelinesPipelineIdStatusGet(
+          {
+            pipelineId,
+          },
+        );

      if (pipelineStatus.status === "SUCCESS") {
        if (verbose) {
@@ -70,7 +73,7 @@ export class LlamaCloudIndex {

  private async waitForDocumentIngestion(
    docIds: string[],
-    verbose = false,
+    verbose = Settings.debug,
    raiseOnError = false,
  ): Promise<void> {
    const pipelineId = await this.getPipelineId(
@@ -78,11 +81,6 @@ export class LlamaCloudIndex {
      this.params.projectName,
    );

-    const client = await initService({
-      ...this.params,
-      baseUrl: this.params.baseUrl,
-    });
-
    if (verbose) {
      console.log("Loading data: ");
    }
@@ -94,7 +92,7 @@ export class LlamaCloudIndex {

      for (const doc of pendingDocs) {
        const { status } =
-          await Service.getPipelineDocumentStatusApiV1PipelinesPipelineIdDocumentsDocumentIdStatusGet(
+          await PipelinesService.getPipelineDocumentStatusApiV1PipelinesPipelineIdDocumentsDocumentIdStatusGet(
            { pipelineId, documentId: doc },
          );

@@ -139,7 +137,7 @@ export class LlamaCloudIndex {
    name: string,
    projectName: string,
  ): Promise<string> {
-    const pipelines = await Service.searchPipelinesApiV1PipelinesGet({
+    const pipelines = await PipelinesService.searchPipelinesApiV1PipelinesGet({
      projectName,
      pipelineName: name,
    });
@@ -160,10 +158,7 @@ export class LlamaCloudIndex {
        apiKey: getEnv("OPENAI_API_KEY"),
      }),
    ];
-
-    const appUrl = getAppBaseUrl(params.baseUrl);
-
-    const client = await initService({ ...params, baseUrl: appUrl });
+    const apiUrl = getAppBaseUrl();

    const pipelineCreateParams = await getPipelineCreate({
      pipelineName: params.name,
@@ -172,7 +167,7 @@ export class LlamaCloudIndex {
      transformations: params.transformations ?? defaultTransformations,
    });

-    const project = await Service.upsertProjectApiV1ProjectsPut({
+    const project = await ProjectsService.upsertProjectApiV1ProjectsPut({
      requestBody: {
        name: params.projectName ?? "default",
      },
@@ -182,7 +177,7 @@ export class LlamaCloudIndex {
      throw new Error("Project ID should be defined");
    }

-    const pipeline = await Service.upsertPipelineApiV1PipelinesPut({
+    const pipeline = await PipelinesService.upsertPipelineApiV1PipelinesPut({
      projectId: project.id,
      requestBody: {
        name: params.name,
@@ -200,7 +195,7 @@ export class LlamaCloudIndex {
      console.log(`Created pipeline ${pipeline.id} with name ${params.name}`);
    }

-    await Service.upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut(
+    await PipelinesService.upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut(
      {
        pipelineId: pipeline.id,
        requestBody: params.documents.map((doc) => ({
@@ -215,9 +210,11 @@ export class LlamaCloudIndex {

    while (true) {
      const pipelineStatus =
-        await Service.getPipelineStatusApiV1PipelinesPipelineIdStatusGet({
-          pipelineId: pipeline.id,
-        });
+        await PipelinesService.getPipelineStatusApiV1PipelinesPipelineIdStatusGet(
+          {
+            pipelineId: pipeline.id,
+          },
+        );

      if (pipelineStatus.status === "SUCCESS") {
        console.info(
@@ -228,14 +225,14 @@ export class LlamaCloudIndex {

      if (pipelineStatus.status === "ERROR") {
        console.error(
-          `Some documents failed to ingest, check your pipeline logs at ${appUrl}/project/${project.id}/deploy/${pipeline.id}`,
+          `Some documents failed to ingest, check your pipeline logs at ${apiUrl}/project/${project.id}/deploy/${pipeline.id}`,
        );
        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 ${appUrl}/project/${project.id}/deploy/${pipeline.id}`,
+          `Documents ingestion partially succeeded, to check a more complete status check your pipeline at ${apiUrl}/project/${project.id}/deploy/${pipeline.id}`,
        );
        break;
      }
@@ -249,7 +246,7 @@ export class LlamaCloudIndex {

    if (params.verbose) {
      console.info(
-        `Ingestion completed, find your index at ${appUrl}/project/${project.id}/deploy/${pipeline.id}`,
+        `Ingestion completed, find your index at ${apiUrl}/project/${project.id}/deploy/${pipeline.id}`,
      );
    }

@@ -280,10 +277,6 @@ export class LlamaCloudIndex {
  }

  async insert(document: Document) {
-    const appUrl = getAppBaseUrl(this.params.baseUrl);
-
-    const client = await initService({ ...this.params, baseUrl: appUrl });
-
    const pipelineId = await this.getPipelineId(
      this.params.name,
      this.params.projectName,
@@ -293,7 +286,7 @@ export class LlamaCloudIndex {
      throw new Error("We couldn't find the pipeline ID for the given name");
    }

-    await Service.createBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPost(
+    await PipelinesService.createBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPost(
      {
        pipelineId: pipelineId,
        requestBody: [
@@ -312,10 +305,6 @@ export class LlamaCloudIndex {
  }

  async delete(document: Document) {
-    const appUrl = getAppBaseUrl(this.params.baseUrl);
-
-    const client = await initService({ ...this.params, baseUrl: appUrl });
-
    const pipelineId = await this.getPipelineId(
      this.params.name,
      this.params.projectName,
@@ -325,7 +314,7 @@ export class LlamaCloudIndex {
      throw new Error("We couldn't find the pipeline ID for the given name");
    }

-    await Service.deletePipelineDocumentApiV1PipelinesPipelineIdDocumentsDocumentIdDelete(
+    await PipelinesService.deletePipelineDocumentApiV1PipelinesPipelineIdDocumentsDocumentIdDelete(
      {
        pipelineId,
        documentId: document.id_,
@@ -336,10 +325,6 @@ export class LlamaCloudIndex {
  }

  async refreshDoc(document: Document) {
-    const appUrl = getAppBaseUrl(this.params.baseUrl);
-
-    const client = await initService({ ...this.params, baseUrl: appUrl });
-
    const pipelineId = await this.getPipelineId(
      this.params.name,
      this.params.projectName,
@@ -349,7 +334,7 @@ export class LlamaCloudIndex {
      throw new Error("We couldn't find the pipeline ID for the given name");
    }

-    await Service.upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut(
+    await PipelinesService.upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut(
      {
        pipelineId,
        requestBody: [
@@ -1,7 +1,7 @@
 import {
  type MetadataFilters,
+  PipelinesService,
  type RetrievalParams,
-  Service,
  type TextNodeWithScore,
 } from "@llamaindex/cloud/api";
 import type { NodeWithScore } from "@llamaindex/core/schema";
@@ -51,20 +51,21 @@ export class LlamaCloudRetriever implements BaseRetriever {
    query,
    preFilters,
  }: RetrieveParams): Promise<NodeWithScore[]> {
-    const pipelines = await Service.searchPipelinesApiV1PipelinesGet({
+    const pipelines = await PipelinesService.searchPipelinesApiV1PipelinesGet({
      projectName: this.projectName,
      pipelineName: this.pipelineName,
    });

-    if (!pipelines) {
+    if (pipelines.length === 0 || !pipelines[0].id) {
      throw new Error(
        `No pipeline found with name ${this.pipelineName} in project ${this.projectName}`,
      );
    }

-    const pipeline = await Service.getPipelineApiV1PipelinesPipelineIdGet({
-      pipelineId: pipelines[0].id,
-    });
+    const pipeline =
+      await PipelinesService.getPipelineApiV1PipelinesPipelineIdGet({
+        pipelineId: pipelines[0].id,
+      });

    if (!pipeline) {
      throw new Error(
@@ -72,16 +73,15 @@ export class LlamaCloudRetriever implements BaseRetriever {
      );
    }

-    const results = await Service.runSearchApiV1PipelinesPipelineIdRetrievePost(
-      {
+    const results =
+      await PipelinesService.runSearchApiV1PipelinesPipelineIdRetrievePost({
        pipelineId: pipeline.id,
        requestBody: {
          ...this.retrieveParams,
          query: extractText(query),
          search_filters: preFilters as MetadataFilters,
        },
-      },
-    );
+      });

    return this.resultNodesToNodeWithScore(results.retrieval_nodes);
  }
@@ -1,6 +1,5 @@
 import type { ServiceContext } from "../ServiceContext.js";

-export const DEFAULT_PIPELINE_NAME = "default";
 export const DEFAULT_PROJECT_NAME = "Default";
 export const DEFAULT_BASE_URL = "https://api.cloud.llamaindex.ai";

@@ -1,4 +1,4 @@
-import { OpenAPI, Service } from "@llamaindex/cloud/api";
+import { OpenAPI } from "@llamaindex/cloud/api";
 import { getEnv } from "@llamaindex/env";
 import type { ClientParams } from "./constants.js";
 import { DEFAULT_BASE_URL } from "./constants.js";
@@ -7,14 +7,11 @@ function getBaseUrl(baseUrl?: string): string {
  return baseUrl ?? getEnv("LLAMA_CLOUD_BASE_URL") ?? DEFAULT_BASE_URL;
 }

-export function getAppBaseUrl(baseUrl?: string): string {
-  return getBaseUrl(baseUrl).replace(/api\./, "");
+export function getAppBaseUrl(): string {
+  return OpenAPI.BASE.replace(/api\./, "");
 }

-export function initService({
-  apiKey,
-  baseUrl,
-}: ClientParams = {}): typeof Service {
+export function initService({ apiKey, baseUrl }: ClientParams = {}) {
  OpenAPI.TOKEN = apiKey ?? getEnv("LLAMA_CLOUD_API_KEY");
  OpenAPI.BASE = getBaseUrl(baseUrl);
  if (!OpenAPI.TOKEN) {
@@ -22,6 +19,4 @@ export function initService({
      "API Key is required for LlamaCloudIndex. Please pass the apiKey parameter",
    );
  }
-
-  return Service;
 }
@@ -1,5 +1,5 @@
+import type { MessageContentDetail } from "@llamaindex/core/llms";
 import { getEnv } from "@llamaindex/env";
-import type { MessageContentDetail } from "../llm/index.js";
 import { extractSingleText } from "../llm/utils.js";
 import { BaseEmbedding } from "./types.js";

@@ -1,3 +1,4 @@
+import type { MessageContentDetail } from "@llamaindex/core/llms";
 import {
  ImageNode,
  MetadataMode,
@@ -6,7 +7,6 @@ import {
  type BaseNode,
  type ImageType,
 } from "@llamaindex/core/schema";
-import type { MessageContentDetail } from "../llm/types.js";
 import { extractImage, extractSingleText } from "../llm/utils.js";
 import { BaseEmbedding, batchEmbeddings } from "./types.js";

@@ -1,8 +1,8 @@
+import type { MessageContentDetail } from "@llamaindex/core/llms";
 import type { BaseNode } from "@llamaindex/core/schema";
 import { MetadataMode } from "@llamaindex/core/schema";
 import { type Tokenizers } from "@llamaindex/env";
 import type { TransformComponent } from "../ingestion/types.js";
-import type { MessageContentDetail } from "../llm/types.js";
 import { extractSingleText } from "../llm/utils.js";
 import { truncateMaxTokens } from "./tokenizer.js";
 import { SimilarityType, similarity } from "./utils.js";
@@ -1,3 +1,4 @@
+import type { ChatMessage, LLM } from "@llamaindex/core/llms";
 import type { ChatHistory } from "../../ChatHistory.js";
 import { getHistory } from "../../ChatHistory.js";
 import type { EngineResponse } from "../../EngineResponse.js";
@@ -9,7 +10,6 @@ import {
 import type { ServiceContext } from "../../ServiceContext.js";
 import { llmFromSettingsOrContext } from "../../Settings.js";
 import { wrapEventCaller } from "../../internal/context/EventCaller.js";
-import type { ChatMessage, LLM } from "../../llm/index.js";
 import { extractText, streamReducer } from "../../llm/utils.js";
 import { PromptMixin } from "../../prompts/index.js";
 import type { QueryEngine } from "../../types.js";
@@ -1,3 +1,9 @@
+import type {
+  ChatMessage,
+  LLM,
+  MessageContent,
+  MessageType,
+} from "@llamaindex/core/llms";
 import type { ChatHistory } from "../../ChatHistory.js";
 import { getHistory } from "../../ChatHistory.js";
 import { EngineResponse } from "../../EngineResponse.js";
@@ -5,8 +11,6 @@ import type { ContextSystemPrompt } from "../../Prompt.js";
 import type { BaseRetriever } from "../../Retriever.js";
 import { Settings } from "../../Settings.js";
 import { wrapEventCaller } from "../../internal/context/EventCaller.js";
-import type { ChatMessage, LLM } from "../../llm/index.js";
-import type { MessageContent, MessageType } from "../../llm/types.js";
 import {
  extractText,
  streamConverter,
@@ -1,10 +1,10 @@
+import type { MessageContent, MessageType } from "@llamaindex/core/llms";
 import { type NodeWithScore } from "@llamaindex/core/schema";
+import type { BaseNodePostprocessor } from "../../postprocessors/index.js";
 import type { ContextSystemPrompt } from "../../Prompt.js";
 import { defaultContextSystemPrompt } from "../../Prompt.js";
-import type { BaseRetriever } from "../../Retriever.js";
-import type { MessageContent, MessageType } from "../../llm/types.js";
-import type { BaseNodePostprocessor } from "../../postprocessors/index.js";
 import { PromptMixin } from "../../prompts/index.js";
+import type { BaseRetriever } from "../../Retriever.js";
 import { createMessageContent } from "../../synthesizers/utils.js";
 import type { Context, ContextGenerator } from "./types.js";

@@ -1,9 +1,9 @@
+import type { LLM } from "@llamaindex/core/llms";
 import type { ChatHistory } from "../../ChatHistory.js";
 import { getHistory } from "../../ChatHistory.js";
 import { EngineResponse } from "../../EngineResponse.js";
 import { Settings } from "../../Settings.js";
 import { wrapEventCaller } from "../../internal/context/EventCaller.js";
-import type { LLM } from "../../llm/index.js";
 import { streamConverter, streamReducer } from "../../llm/utils.js";
 import type {
  ChatEngine,
@@ -1,8 +1,7 @@
+import type { ChatMessage, MessageContent } from "@llamaindex/core/llms";
 import type { NodeWithScore } from "@llamaindex/core/schema";
 import type { ChatHistory } from "../../ChatHistory.js";
 import type { EngineResponse } from "../../EngineResponse.js";
-import type { ChatMessage } from "../../llm/index.js";
-import type { MessageContent } from "../../llm/types.js";

 /**
 * Represents the base parameters for ChatEngine.
@@ -11,13 +11,12 @@ import {
 } from "../../synthesizers/index.js";

 import type {
-  BaseTool,
  QueryEngine,
  QueryEngineParamsNonStreaming,
  QueryEngineParamsStreaming,
-  ToolMetadata,
 } from "../../types.js";

+import type { BaseTool, ToolMetadata } from "@llamaindex/core/llms";
 import { wrapEventCaller } from "../../internal/context/EventCaller.js";
 import type { BaseQuestionGenerator, SubQuestion } from "./types.js";

@@ -1,4 +1,4 @@
-import type { ToolMetadata } from "../../types.js";
+import type { ToolMetadata } from "@llamaindex/core/llms";

 /**
 * QuestionGenerators generate new questions for the LLM using tools and a user query.
@@ -1,9 +1,9 @@
+import type { ChatMessage, LLM } from "@llamaindex/core/llms";
 import { MetadataMode } from "@llamaindex/core/schema";
-import type { ServiceContext } from "../ServiceContext.js";
-import { llmFromSettingsOrContext } from "../Settings.js";
-import type { ChatMessage, LLM } from "../llm/types.js";
 import { extractText } from "../llm/utils.js";
 import { PromptMixin } from "../prompts/Mixin.js";
+import type { ServiceContext } from "../ServiceContext.js";
+import { llmFromSettingsOrContext } from "../Settings.js";
 import type { CorrectnessSystemPrompt } from "./prompts.js";
 import {
  defaultCorrectnessSystemPrompt,
@@ -1,6 +1,6 @@
+import type { LLM } from "@llamaindex/core/llms";
 import type { BaseNode } from "@llamaindex/core/schema";
 import { MetadataMode, TextNode } from "@llamaindex/core/schema";
-import type { LLM } from "../llm/index.js";
 import { OpenAI } from "../llm/index.js";
 import {
  defaultKeywordExtractorPromptTemplate,
@@ -1,3 +1,4 @@
+export * from "@llamaindex/core/llms";
 export * from "@llamaindex/core/schema";
 export * from "./agent/index.js";
 export * from "./callbacks/CallbackManager.js";
@@ -13,3 +13,6 @@ export {

 export { type VertexGeminiSessionOptions } from "./llm/gemini/types.js";
 export { GeminiVertexSession } from "./llm/gemini/vertex.js";
+
+// Expose AzureDynamicSessionTool for node.js runtime only
+export { AzureDynamicSessionTool } from "./tools/AzureDynamicSessionTool.node.js";
@@ -31,8 +31,8 @@ import {
  simpleExtractKeywords,
 } from "./utils.js";

+import type { LLM } from "@llamaindex/core/llms";
 import { llmFromSettingsOrContext } from "../../Settings.js";
-import type { LLM } from "../../llm/types.js";
 import { extractText } from "../../llm/utils.js";

 export interface KeywordIndexOptions {
@@ -1,3 +1,4 @@
+import type { MessageContent } from "@llamaindex/core/llms";
 import {
  ImageNode,
  ModalityType,
@@ -23,7 +24,6 @@ import {
 } from "../../ingestion/strategies/index.js";
 import { wrapEventCaller } from "../../internal/context/EventCaller.js";
 import { getCallbackManager } from "../../internal/settings/CallbackManager.js";
-import type { MessageContent } from "../../llm/types.js";
 import type { BaseNodePostprocessor } from "../../postprocessors/types.js";
 import type { StorageContext } from "../../storage/StorageContext.js";
 import { storageContextFromDefaults } from "../../storage/StorageContext.js";
@@ -1,4 +1,4 @@
-import type { BaseTool } from "../../types.js";
+import type { BaseTool } from "@llamaindex/core/llms";

 export const getReACTAgentSystemHeader = (tools: BaseTool[]) => {
  const description = tools
@@ -13,19 +13,22 @@ import type {
  TextBlock,
  TextBlockParam,
 } from "@anthropic-ai/sdk/resources/index";
-import type { MessageParam } from "@anthropic-ai/sdk/resources/messages";
-import { getEnv } from "@llamaindex/env";
-import _ from "lodash";
-import type { BaseTool } from "../types.js";
-import { ToolCallLLM } from "./base.js";
 import type {
+  ImageBlockParam,
+  MessageParam,
+} from "@anthropic-ai/sdk/resources/messages";
+import type {
+  BaseTool,
  ChatMessage,
  ChatResponse,
  ChatResponseChunk,
  LLMChatParamsNonStreaming,
  LLMChatParamsStreaming,
  ToolCallLLMMessageOptions,
-} from "./types.js";
+} from "@llamaindex/core/llms";
+import { getEnv } from "@llamaindex/env";
+import _ from "lodash";
+import { ToolCallLLM } from "./base.js";
 import { extractText, wrapLLMEvent } from "./utils.js";

 export class AnthropicSession {
@@ -214,7 +217,32 @@ export class Anthropic extends ToolCallLLM<AnthropicAdditionalChatOptions> {
        }

        return {
-          content: extractText(message.content),
+          content:
+            typeof message.content === "string"
+              ? message.content
+              : message.content.map(
+                  (content): TextBlockParam | ImageBlockParam =>
+                    content.type === "text"
+                      ? {
+                          type: "text",
+                          text: content.text,
+                        }
+                      : {
+                          type: "image",
+                          source: {
+                            data: content.image_url.url.substring(
+                              content.image_url.url.indexOf(",") + 1,
+                            ),
+                            media_type:
+                              `image/${content.image_url.url.substring("data:image/".length, content.image_url.url.indexOf(";base64"))}` as
+                                | "image/jpeg"
+                                | "image/png"
+                                | "image/gif"
+                                | "image/webp",
+                            type: "base64",
+                          },
+                        },
+                ),
          role: message.role as "user" | "assistant",
        } satisfies MessageParam;
      });
@@ -9,7 +9,7 @@ import type {
  LLMCompletionParamsStreaming,
  LLMMetadata,
  ToolCallLLMMessageOptions,
-} from "./types.js";
+} from "@llamaindex/core/llms";
 import { extractText, streamConverter } from "./utils.js";

 export abstract class BaseLLM<
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
github-actions[bot]	76deca7fea	Release 0.4.12 (#1013 ) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2024-07-03 10:24:22 -07:00
Alex Yang	f326ab86d2	chore: bump version	2024-07-03 10:20:46 -07:00
Cássio de Freitas e Silva	ca8d9709e0	feat: add support for Meta LLMs in AWS Bedrock (#960 )	2024-07-03 01:27:58 -07:00
github-actions[bot]	e0af059221	Release 0.4.11 (#1008 ) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2024-07-02 15:07:03 -07:00
Alex Yang	8bf5b4acfd	fix: llama parse input spreadsheet (#1007 )	2024-07-02 14:48:51 -07:00
Alex Yang	93a003baa0	ci: pre release (#1005 )	2024-07-02 00:40:45 -07:00
github-actions[bot]	5d9b0bd3f0	Release 0.4.10 (#1003 ) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2024-07-01 23:59:52 -07:00
Alex Yang	9a5525e1b3	refactor(core): migrate llms type (#1002 )	2024-07-01 20:13:35 -07:00
Peron	7dce3d28d3	fix: disable External Filters for Gemini (#994 ) Co-authored-by: Alex Yang <himself65@outlook.com>	2024-07-01 18:28:22 -07:00
github-actions[bot]	d4c1482c1c	Release 0.4.9 (#1001 ) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2024-07-01 17:20:47 -07:00
Alex Yang	3a96a483a6	fix: anthropic image input (#999 )	2024-07-01 16:03:30 -07:00
Alex Yang	7467fce2d4	docs: remove cloudflare worker section (#1000 )	2024-07-01 16:01:55 -07:00
github-actions[bot]	06af08cac4	Release 0.4.8 (#998 ) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2024-07-01 15:07:50 -07:00
Alex Yang	83ebdfb1c5	fix: next.js binding (#997 )	2024-07-01 14:52:57 -07:00
github-actions[bot]	835b1ac000	Release 0.4.7 (#986 ) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2024-06-28 22:58:14 -07:00
Alex Yang	f10b41dbc1	chore: fix release files (#991 )	2024-06-28 13:36:55 -07:00
Wassim Chegham	41fe871e2f	feat: add support for azure dynamic session tool (#942 ) Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>	2024-06-27 13:18:05 -07:00
Alex Yang	321c39ddc7	fix: generate api as class (#988 )	2024-06-27 09:58:00 -07:00
Alex Yang	f7f1af0139	fix: llamacloud sdk edge case (#985 )	2024-06-26 23:10:04 -07:00