Release 0.5.27 (#1195)

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

.github/workflows/test.yml

@@ -12,6 +12,10 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+env:
+  POSTGRES_USER: runneradmin
+  POSTGRES_HOST_AUTH_METHOD: trust
+
 jobs:
   e2e:
     strategy:
@@ -22,9 +26,17 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-
+      - uses: ankane/setup-postgres@v1
+        with:
+          database: llamaindex_node_test
+          dev-files: true
+      - run: |
+          cd /tmp
+          git clone --branch v0.7.0 https://github.com/pgvector/pgvector.git
+          cd pgvector
+          make
+          sudo make install
       - uses: pnpm/action-setup@v4
-
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -42,7 +54,6 @@ jobs:
         node-version: [18.x, 20.x, 22.x]
     name: Test on Node.js ${{ matrix.node-version }}
     runs-on: ubuntu-latest
-
     steps:
       - uses: actions/checkout@v4
       - uses: pnpm/action-setup@v4
@@ -92,7 +103,7 @@ jobs:
           - nextjs-agent
           - nextjs-edge-runtime
           - nextjs-node-runtime
-    #          - waku-query-engine
+          - waku-query-engine
     runs-on: ubuntu-latest
     name: Build LlamaIndex Example (${{ matrix.packages }})
     steps:
@@ -131,6 +142,9 @@ jobs:
       - name: Pack @llamaindex/cloud
         run: pnpm pack --pack-destination ${{ runner.temp }}
         working-directory: packages/cloud
+      - name: Pack @llamaindex/openai
+        run: pnpm pack --pack-destination ${{ runner.temp }}
+        working-directory: packages/llm/openai
       - name: Pack @llamaindex/core
         run: pnpm pack --pack-destination ${{ runner.temp }}
         working-directory: packages/core

README.md

@@ -36,9 +36,44 @@ For now, browser support is limited due to the lack of support for [AsyncLocalSt
 npm install llamaindex
 pnpm install llamaindex
 yarn add llamaindex
-jsr install @llamaindex/core
 ```
 
+### Setup TypeScript
+
+```json5
+{
+  compilerOptions: {
+    // ⬇️ add this line to your tsconfig.json
+    moduleResolution: "bundler", // or "node16"
+  },
+}
+```
+
+<details>
+   <summary>Why?</summary>
+  We are shipping both ESM and CJS module, and compatible with Vercel Edge, Cloudflare Workers, and other serverless platforms.
+
+So we are using [conditional exports](https://nodejs.org/api/packages.html#conditional-exports) to support all environments.
+
+This is a kind of modern way of shipping packages, but might cause TypeScript type check to fail because of legacy module resolution.
+
+Imaging you put output file into `/dist/openai.js` but you are importing `llamaindex/openai` in your code, and set `package.json` like this:
+
+```json
+{
+  "exports": {
+    "./openai": "./dist/openai.js"
+  }
+}
+```
+
+In old module resolution, TypeScript will not be able to find the module because it is not follow the file structure, even you run `node index.js` successfully. (on Node.js >=16)
+
+See more about [moduleResolution](https://www.typescriptlang.org/docs/handbook/modules/theory.html#module-resolution) or
+[TypeScript 5.0 blog](https://devblogs.microsoft.com/typescript/announcing-typescript-5-0/#--moduleresolution-bundler7).
+
+</details>
+
 ### Node.js
 
 ```ts
@@ -154,6 +189,21 @@ export async function chatWithAgent(
 }
 ```
 
+### Vite
+
+We have some wasm dependencies for better performance. You can use `vite-plugin-wasm` to load them.
+
+```ts
+import wasm from "vite-plugin-wasm";
+
+export default {
+  plugins: [wasm()],
+  ssr: {
+    external: ["tiktoken"],
+  },
+};
+```
+
 ## Playground
 
 Check out our NextJS playground at https://llama-playground.vercel.app/. The source is available at https://github.com/run-llama/ts-playground

apps/docs/CHANGELOG.md

@@ -1,5 +1,40 @@
 # docs
 
+## 0.0.68
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+
+## 0.0.67
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+
+## 0.0.66
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+
+## 0.0.65
+
+### Patch Changes
+
+- llamaindex@0.5.24
+
+## 0.0.64
+
+### Patch Changes
+
+- llamaindex@0.5.23
+
 ## 0.0.63
 
 ### Patch Changes

apps/docs/docs/guides/agents/2_create_agent.mdx

@@ -50,10 +50,10 @@ We want to see what our agent is up to, so we're going to hook into some events
 
 ```javascript
 Settings.callbackManager.on("llm-tool-call", (event) => {
-  console.log(event.detail.payload);
+  console.log(event.detail);
 });
 Settings.callbackManager.on("llm-tool-result", (event) => {
-  console.log(event.detail.payload);
+  console.log(event.detail);
 });
 ```
 

apps/docs/docs/modules/storage.md

@@ -4,12 +4,19 @@ sidebar_position: 7
 
 # Storage
 
-Storage in LlamaIndex.TS works automatically once you've configured a `StorageContext` object. Just configure the `persistDir` and attach it to an index.
+Storage in LlamaIndex.TS works automatically once you've configured a
+`StorageContext` object.
 
-Right now, only saving and loading from disk is supported, with future integrations planned!
+## Local Storage
+
+You can configure the `persistDir` and attach it to an index.
 
 ```typescript
-import { Document, VectorStoreIndex, storageContextFromDefaults } from "./src";
+import {
+  Document,
+  VectorStoreIndex,
+  storageContextFromDefaults,
+} from "llamaindex";
 
 const storageContext = await storageContextFromDefaults({
   persistDir: "./storage",
@@ -21,6 +28,33 @@ const index = await VectorStoreIndex.fromDocuments([document], {
 });
 ```
 
+## PostgreSQL Storage
+
+You can configure the `schemaName`, `tableName`, `namespace`, and
+`connectionString`. If a `connectionString` is not
+provided, it will use the environment variables `PGHOST`, `PGUSER`,
+`PGPASSWORD`, `PGDATABASE` and `PGPORT`.
+
+```typescript
+import {
+  Document,
+  VectorStoreIndex,
+  PostgresDocumentStore,
+  PostgresIndexStore,
+  storageContextFromDefaults,
+} from "llamaindex";
+
+const storageContext = await storageContextFromDefaults({
+  docStore: new PostgresDocumentStore(),
+  indexStore: new PostgresIndexStore(),
+});
+
+const document = new Document({ text: "Test Text" });
+const index = await VectorStoreIndex.fromDocuments([document], {
+  storageContext,
+});
+```
+
 ## API Reference
 
 - [StorageContext](../api/interfaces/StorageContext.md)

apps/docs/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docs",
-  "version": "0.0.63",
+  "version": "0.0.68",
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",

examples/deepinfra/embedding.ts

@@ -3,7 +3,7 @@ import { DeepInfraEmbedding } from "llamaindex";
 async function main() {
   // API token can be provided as an environment variable too
   // using DEEPINFRA_API_TOKEN variable
-  const apiToken = "YOUR_API_TOKEN" ?? process.env.DEEPINFRA_API_TOKEN;
+  const apiToken = process.env.DEEPINFRA_API_TOKEN ?? "YOUR_API_TOKEN";
   const model = "BAAI/bge-large-en-v1.5";
   const embedModel = new DeepInfraEmbedding({
     model,

package.json

@@ -38,6 +38,9 @@
     "overrides": {
       "trim": "1.0.1",
       "protobufjs": "7.2.6"
+    },
+    "patchedDependencies": {
+      "python-format-js@1.4.3": "patches/python-format-js@1.4.3.patch"
     }
   },
   "lint-staged": {

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

@@ -1,5 +1,45 @@
 # @llamaindex/autotool-01-node-example
 
+## 0.0.8
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+  - @llamaindex/autotool@2.0.1
+
+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+  - @llamaindex/autotool@2.0.1
+
+## 0.0.6
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+  - @llamaindex/autotool@2.0.1
+
+## 0.0.5
+
+### Patch Changes
+
+- llamaindex@0.5.24
+- @llamaindex/autotool@2.0.1
+
+## 0.0.4
+
+### Patch Changes
+
+- llamaindex@0.5.23
+- @llamaindex/autotool@2.0.1
+
 ## 0.0.3
 
 ### 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": "0.0.3"
+  "version": "0.0.8"
 }

packages/autotool/examples/01_node/src/index.ts

@@ -16,7 +16,7 @@ const openai = new OpenAI();
     stream: false,
   });
 
-  const toolCalls = response.choices[0].message.tool_calls ?? [];
+  const toolCalls = response.choices[0]!.message.tool_calls ?? [];
   for (const toolCall of toolCalls) {
     toolCall.function.name;
   }

packages/autotool/examples/02_nextjs/CHANGELOG.md

@@ -1,5 +1,45 @@
 # @llamaindex/autotool-02-next-example
 
+## 0.1.52
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.51
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.50
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.49
+
+### Patch Changes
+
+- llamaindex@0.5.24
+- @llamaindex/autotool@2.0.1
+
+## 0.1.48
+
+### Patch Changes
+
+- llamaindex@0.5.23
+- @llamaindex/autotool@2.0.1
+
 ## 0.1.47
 
 ### Patch Changes

packages/autotool/examples/02_nextjs/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool-02-next-example",
   "private": true,
-  "version": "0.1.47",
+  "version": "0.1.52",
   "scripts": {
     "dev": "next dev",
     "build": "next build",

packages/autotool/package.json

@@ -51,7 +51,7 @@
     "unplugin": "^1.12.2"
   },
   "peerDependencies": {
-    "llamaindex": "^0.5.22",
+    "llamaindex": "^0.5.27",
     "openai": "^4",
     "typescript": "^4"
   },

packages/autotool/src/index.ts

@@ -16,11 +16,16 @@ const openaiToolsAtom = atom<ChatCompletionTool[]>((get) => {
   const metadata = get(toolMetadataAtom);
   return metadata.map(([metadata]) => ({
     type: "function",
-    function: {
-      parameters: metadata.parameters,
-      name: metadata.name,
-      description: metadata.description,
-    },
+    function: metadata.parameters
+      ? {
+          parameters: metadata.parameters,
+          name: metadata.name,
+          description: metadata.description,
+        }
+      : {
+          name: metadata.name,
+          description: metadata.description,
+        },
   }));
 });
 

packages/autotool/src/internal/index.ts

@@ -17,7 +17,7 @@ export type Info = {
  * @internal
  */
 export type InfoString = {
-  originalFunction?: string;
+  originalFunction: string | undefined;
   parameterMapping: Record<string, number>;
 };
 

packages/cloud/CHANGELOG.md

@@ -1,5 +1,17 @@
 # @llamaindex/cloud
 
+## 0.2.4
+
+### Patch Changes
+
+- 4810364: fix: bump version
+
+## 0.2.3
+
+### Patch Changes
+
+- 0bf8d80: fix: bump version
+
 ## 0.2.2
 
 ### Patch Changes

packages/cloud/openapi-ts.config.ts

@@ -4,6 +4,7 @@ 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",
+  client: "@hey-api/client-fetch",
   output: {
     path: "./src/client",
     format: "prettier",

packages/cloud/package.json

@@ -1,10 +1,10 @@
 {
   "name": "@llamaindex/cloud",
-  "version": "0.2.2",
+  "version": "0.2.4",
   "type": "module",
   "license": "MIT",
   "scripts": {
-    "generate": "pnpm dlx @hey-api/openapi-ts@0.49.0",
+    "generate": "pnpx @hey-api/openapi-ts@0.53.0",
     "build": "pnpm run generate && bunchee"
   },
   "files": [
@@ -34,7 +34,8 @@
     "directory": "packages/cloud"
   },
   "devDependencies": {
-    "@hey-api/openapi-ts": "^0.52.11",
+    "@hey-api/client-fetch": "^0.2.4",
+    "@hey-api/openapi-ts": "^0.53.0",
     "bunchee": "5.3.2"
   }
 }

packages/community/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/community
 
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [711c814]
+  - @llamaindex/core@0.1.12
+
 ## 0.0.32
 
 ### Patch Changes

packages/community/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.32",
+  "version": "0.0.33",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

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

@@ -28,9 +28,9 @@ export const mergeNeighboringSameRoleMessages = (
 ): 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,
+      if (index > 0 && messages[index - 1]!.role === current.role) {
+        result[result.length - 1]!.content = [
+          ...result[result.length - 1]!.content,
           ...current.content,
         ];
       } else {
@@ -128,7 +128,7 @@ export const mapChatMessagesToAnthropicMessages = <
       );
     })
     .filter((message: AnthropicMessage) => {
-      const content = message.content[0];
+      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")
@@ -151,12 +151,12 @@ export const extractDataUrlComponents = (
 } => {
   const parts = dataUrl.split(";base64,");
 
-  if (parts.length !== 2 || !parts[0].startsWith("data:")) {
+  if (parts.length !== 2 || !parts[0]!.startsWith("data:")) {
     throw new Error("Invalid data URL");
   }
 
-  const mimeType = parts[0].slice(5);
-  const base64 = parts[1];
+  const mimeType = parts[0]!.slice(5);
+  const base64 = parts[1]!;
 
   return {
     mimeType,

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

@@ -153,12 +153,15 @@ export const TOOL_CALL_MODELS = [
 
 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];
+  return PROVIDERS[providerName]!;
 };
 
 export type BedrockModelParams = {

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

@@ -34,7 +34,7 @@ export class MetaProvider extends Provider<MetaStreamEvent> {
     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],
+      result.generation.trim().split(TOKENS.TOOL_CALL)[1]!,
     );
     return [
       {

packages/core/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/core
 
+## 0.1.12
+
+### Patch Changes
+
+- 711c814: fix: patch `python-format-js`
+
 ## 0.1.11
 
 ### Patch Changes

packages/core/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.1.11",
+  "version": "0.1.12",
   "description": "LlamaIndex Core Module",
   "exports": {
     "./node-parser": {
@@ -129,6 +129,20 @@
         "types": "./dist/prompts/index.d.ts",
         "default": "./dist/prompts/index.js"
       }
+    },
+    "./indices": {
+      "require": {
+        "types": "./dist/indices/index.d.cts",
+        "default": "./dist/indices/index.cjs"
+      },
+      "import": {
+        "types": "./dist/indices/index.d.ts",
+        "default": "./dist/indices/index.js"
+      },
+      "default": {
+        "types": "./dist/indices/index.d.ts",
+        "default": "./dist/indices/index.js"
+      }
     }
   },
   "files": [

packages/core/src/embeddings/base.ts

@@ -34,7 +34,7 @@ export abstract class BaseEmbedding extends TransformComponent {
         const embeddings = await this.getTextEmbeddingsBatch(texts, options);
 
         for (let i = 0; i < nodes.length; i++) {
-          nodes[i].embedding = embeddings[i];
+          nodes[i]!.embedding = embeddings[i];
         }
 
         return nodes;
@@ -120,7 +120,7 @@ export async function batchEmbeddings<T>(
   const curBatch: T[] = [];
 
   for (let i = 0; i < queue.length; i++) {
-    curBatch.push(queue[i]);
+    curBatch.push(queue[i]!);
     if (i == queue.length - 1 || curBatch.length == chunkSize) {
       const embeddings = await embedFunc(curBatch);
 

packages/core/src/embeddings/utils.ts

@@ -35,20 +35,20 @@ export function similarity(
   function norm(x: number[]): number {
     let result = 0;
     for (let i = 0; i < x.length; i++) {
-      result += x[i] * x[i];
+      result += x[i]! * x[i]!;
     }
     return Math.sqrt(result);
   }
 
   switch (mode) {
     case SimilarityType.EUCLIDEAN: {
-      const difference = embedding1.map((x, i) => x - embedding2[i]);
+      const difference = embedding1.map((x, i) => x - embedding2[i]!);
       return -norm(difference);
     }
     case SimilarityType.DOT_PRODUCT: {
       let result = 0;
       for (let i = 0; i < embedding1.length; i++) {
-        result += embedding1[i] * embedding2[i];
+        result += embedding1[i]! * embedding2[i]!;
       }
       return result;
     }

packages/core/src/global/settings.ts

@@ -1,4 +1,5 @@
 import type { Tokenizer } from "@llamaindex/env";
+import type { LLM } from "../llms";
 import {
   type CallbackManager,
   getCallbackManager,
@@ -10,6 +11,7 @@ import {
   setChunkSize,
   withChunkSize,
 } from "./settings/chunk-size";
+import { getLLM, setLLM, withLLM } from "./settings/llm";
 import {
   getTokenizer,
   setTokenizer,
@@ -17,6 +19,15 @@ import {
 } from "./settings/tokenizer";
 
 export const Settings = {
+  get llm() {
+    return getLLM();
+  },
+  set llm(llm) {
+    setLLM(llm);
+  },
+  withLLM<Result>(llm: LLM, fn: () => Result): Result {
+    return withLLM(llm, fn);
+  },
   get tokenizer() {
     return getTokenizer();
   },

packages/core/src/global/settings/llm.ts

@@ -0,0 +1,23 @@
+import { AsyncLocalStorage } from "@llamaindex/env";
+import type { LLM } from "../../llms";
+
+const llmAsyncLocalStorage = new AsyncLocalStorage<LLM>();
+let globalLLM: LLM | undefined;
+
+export function getLLM(): LLM {
+  const currentLLM = globalLLM ?? llmAsyncLocalStorage.getStore();
+  if (!currentLLM) {
+    throw new Error(
+      "Cannot find LLM, please set `Settings.llm = ...` on the top of your code",
+    );
+  }
+  return currentLLM;
+}
+
+export function setLLM(llm: LLM): void {
+  globalLLM = llm;
+}
+
+export function withLLM<Result>(llm: LLM, fn: () => Result): Result {
+  return llmAsyncLocalStorage.run(llm, fn);
+}

packages/core/src/indices/index.ts

@@ -0,0 +1,5 @@
+export {
+  PromptHelper,
+  getBiggestPrompt,
+  type PromptHelperOptions,
+} from "./prompt-helper";

packages/core/src/indices/prompt-helper.ts

@@ -1,17 +1,17 @@
+import { type Tokenizer, tokenizers } from "@llamaindex/env";
 import {
   DEFAULT_CHUNK_OVERLAP_RATIO,
   DEFAULT_CONTEXT_WINDOW,
   DEFAULT_NUM_OUTPUTS,
   DEFAULT_PADDING,
-} from "@llamaindex/core/global";
-import { SentenceSplitter } from "@llamaindex/core/node-parser";
-import type { PromptTemplate } from "@llamaindex/core/prompts";
-import { type Tokenizer, tokenizers } from "@llamaindex/env";
+} from "../global";
+import { SentenceSplitter } from "../node-parser";
+import type { PromptTemplate } from "../prompts";
 
 /**
  * Get the empty prompt text given a prompt.
  */
-export function getEmptyPromptTxt(prompt: PromptTemplate) {
+function getEmptyPromptTxt(prompt: PromptTemplate) {
   return prompt.format({
     ...Object.fromEntries(
       [...prompt.templateVars.keys()].map((key) => [key, ""]),
@@ -23,14 +23,23 @@ export function getEmptyPromptTxt(prompt: PromptTemplate) {
  * Get biggest empty prompt size from a list of prompts.
  * Used to calculate the maximum size of inputs to the LLM.
  */
-export function getBiggestPrompt(prompts: PromptTemplate[]) {
+export function getBiggestPrompt(prompts: PromptTemplate[]): PromptTemplate {
   const emptyPromptTexts = prompts.map(getEmptyPromptTxt);
   const emptyPromptLengths = emptyPromptTexts.map((text) => text.length);
   const maxEmptyPromptLength = Math.max(...emptyPromptLengths);
   const maxEmptyPromptIndex = emptyPromptLengths.indexOf(maxEmptyPromptLength);
-  return prompts[maxEmptyPromptIndex];
+  return prompts[maxEmptyPromptIndex]!;
 }
 
+export type PromptHelperOptions = {
+  contextWindow?: number;
+  numOutput?: number;
+  chunkOverlapRatio?: number;
+  chunkSizeLimit?: number;
+  tokenizer?: Tokenizer;
+  separator?: string;
+};
+
 /**
  * A collection of helper functions for working with prompts.
  */
@@ -38,19 +47,19 @@ export class PromptHelper {
   contextWindow = DEFAULT_CONTEXT_WINDOW;
   numOutput = DEFAULT_NUM_OUTPUTS;
   chunkOverlapRatio = DEFAULT_CHUNK_OVERLAP_RATIO;
-  chunkSizeLimit?: number;
+  chunkSizeLimit: number | undefined;
   tokenizer: Tokenizer;
   separator = " ";
 
-  // eslint-disable-next-line max-params
-  constructor(
-    contextWindow = DEFAULT_CONTEXT_WINDOW,
-    numOutput = DEFAULT_NUM_OUTPUTS,
-    chunkOverlapRatio = DEFAULT_CHUNK_OVERLAP_RATIO,
-    chunkSizeLimit?: number,
-    tokenizer?: Tokenizer,
-    separator = " ",
-  ) {
+  constructor(options: PromptHelperOptions = {}) {
+    const {
+      contextWindow = DEFAULT_CONTEXT_WINDOW,
+      numOutput = DEFAULT_NUM_OUTPUTS,
+      chunkOverlapRatio = DEFAULT_CHUNK_OVERLAP_RATIO,
+      chunkSizeLimit,
+      tokenizer,
+      separator = " ",
+    } = options;
     this.contextWindow = contextWindow;
     this.numOutput = numOutput;
     this.chunkOverlapRatio = chunkOverlapRatio;
@@ -79,7 +88,7 @@ export class PromptHelper {
     prompt: PromptTemplate,
     numChunks = 1,
     padding = 5,
-  ) {
+  ): number {
     const availableContextSize = this.getAvailableContextSize(prompt);
 
     const result = Math.floor(availableContextSize / numChunks) - padding;
@@ -104,7 +113,12 @@ export class PromptHelper {
       throw new Error("Got 0 as available chunk size");
     }
     const chunkOverlap = this.chunkOverlapRatio * chunkSize;
-    return new SentenceSplitter({ chunkSize, chunkOverlap });
+    return new SentenceSplitter({
+      chunkSize,
+      chunkOverlap,
+      separator: this.separator,
+      tokenizer: this.tokenizer,
+    });
   }
 
   /**

packages/core/src/llms/type.ts

@@ -103,7 +103,7 @@ export type LLMMetadata = {
   model: string;
   temperature: number;
   topP: number;
-  maxTokens?: number;
+  maxTokens?: number | undefined;
   contextWindow: number;
   tokenizer: Tokenizers | undefined;
 };
@@ -141,7 +141,7 @@ export interface LLMCompletionParamsStreaming extends LLMCompletionParamsBase {
 
 export interface LLMCompletionParamsNonStreaming
   extends LLMCompletionParamsBase {
-  stream?: false | null;
+  stream?: false | null | undefined;
 }
 
 export type MessageContentTextDetail = {

packages/core/src/node-parser/base.ts

@@ -122,7 +122,7 @@ export abstract class MetadataAwareTextSplitter extends TextSplitter {
       throw new TypeError("`texts` and `metadata` must have the same length");
     }
     return texts.flatMap((text, i) =>
-      this.splitTextMetadataAware(text, metadata[i]),
+      this.splitTextMetadataAware(text, metadata[i]!),
     );
   }
 

packages/core/src/node-parser/markdown.ts

@@ -35,8 +35,8 @@ export class MarkdownNodeParser extends NodeParser {
         }
         metadata = this.updateMetadata(
           metadata,
-          headerMatch[2],
-          headerMatch[1].trim().length,
+          headerMatch[2]!,
+          headerMatch[1]!.trim().length,
         );
         currentSection = `${headerMatch[2]}\n`;
       } else {
@@ -63,7 +63,7 @@ export class MarkdownNodeParser extends NodeParser {
     for (let i = 1; i < newHeaderLevel; i++) {
       const key = `Header_${i}`;
       if (key in headersMetadata) {
-        updatedHeaders[key] = headersMetadata[key];
+        updatedHeaders[key] = headersMetadata[key]!;
       }
     }
 
@@ -76,10 +76,10 @@ export class MarkdownNodeParser extends NodeParser {
     node: TextNode,
     metadata: Metadata,
   ): TextNode {
-    const newNode = buildNodeFromSplits([textSplit], node, undefined)[0];
+    const newNode = buildNodeFromSplits([textSplit], node, undefined)[0]!;
 
     if (this.includeMetadata) {
-      newNode.metadata = { ...newNode.metadata, ...metadata };
+      newNode.metadata = { ...newNode!.metadata, ...metadata };
     }
 
     return newNode;

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

@@ -168,9 +168,9 @@ export class SentenceSplitter extends MetadataAwareTextSplitter {
       let lastIndex = lastChunk.length - 1;
       while (
         lastIndex >= 0 &&
-        currentChunkLength + lastChunk[lastIndex][1] <= this.chunkOverlap
+        currentChunkLength + lastChunk[lastIndex]![1] <= this.chunkOverlap
       ) {
-        const [text, length] = lastChunk[lastIndex];
+        const [text, length] = lastChunk[lastIndex]!;
         currentChunkLength += length;
         currentChunk.unshift([text, length]);
         lastIndex -= 1;
@@ -178,7 +178,7 @@ export class SentenceSplitter extends MetadataAwareTextSplitter {
     };
 
     while (splits.length > 0) {
-      const curSplit = splits[0];
+      const curSplit = splits[0]!;
       if (curSplit.tokenSize > chunkSize) {
         throw new Error("Single token exceeded chunk size");
       }

packages/core/src/node-parser/utils.ts

@@ -5,7 +5,7 @@ export type TextSplitterFn = (text: string) => string[];
 
 const truncateText = (text: string, textSplitter: TextSplitter): string => {
   const chunks = textSplitter.splitText(text);
-  return chunks[0];
+  return chunks[0] ?? text;
 };
 
 const splitTextKeepSeparator = (text: string, separator: string): string[] => {

packages/core/src/prompts/base.ts

@@ -18,7 +18,7 @@ export type BasePromptTemplateOptions<
     // loose type for better type inference
     | readonly string[];
   options?: Partial<Record<TemplatesVar[number] | (string & {}), string>>;
-  outputParser?: BaseOutputParser;
+  outputParser?: BaseOutputParser | undefined;
   templateVarMappings?: Partial<
     Record<Vars[number] | (string & {}), TemplatesVar[number] | (string & {})>
   >;
@@ -34,7 +34,7 @@ export abstract class BasePromptTemplate<
   metadata: Metadata = {};
   templateVars: Set<string> = new Set();
   options: Partial<Record<TemplatesVar[number] | (string & {}), string>> = {};
-  outputParser?: BaseOutputParser;
+  outputParser: BaseOutputParser | undefined;
   templateVarMappings: Partial<
     Record<Vars[number] | (string & {}), TemplatesVar[number] | (string & {})>
   > = {};

packages/core/src/prompts/mixin.ts

@@ -45,21 +45,21 @@ export abstract class PromptMixin {
 
     for (const key in prompts) {
       if (key.includes(":")) {
-        const [module_name, sub_key] = key.split(":");
+        const [moduleName, subKey] = key.split(":") as [string, string];
 
-        if (!subPrompt[module_name]) {
-          subPrompt[module_name] = {};
+        if (!subPrompt[moduleName]) {
+          subPrompt[moduleName] = {};
         }
-        subPrompt[module_name][sub_key] = prompts[key];
+        subPrompt[moduleName][subKey] = prompts[key]!;
       }
     }
 
-    for (const [module_name, subPromptDict] of Object.entries(subPrompt)) {
-      if (!promptModules[module_name]) {
-        throw new Error(`Module ${module_name} not found.`);
+    for (const [moduleName, subPromptDict] of Object.entries(subPrompt)) {
+      if (!promptModules[moduleName]) {
+        throw new Error(`Module ${moduleName} not found.`);
       }
 
-      const moduleToUpdate = promptModules[module_name];
+      const moduleToUpdate = promptModules[moduleName];
 
       moduleToUpdate.updatePrompts(subPromptDict);
     }

packages/core/src/schema/node.ts

@@ -38,13 +38,15 @@ export type RelatedNodeType<T extends Metadata = Metadata> =
   | RelatedNodeInfo<T>[];
 
 export type BaseNodeParams<T extends Metadata = Metadata> = {
-  id_?: string;
-  metadata?: T;
-  excludedEmbedMetadataKeys?: string[];
-  excludedLlmMetadataKeys?: string[];
-  relationships?: Partial<Record<NodeRelationship, RelatedNodeType<T>>>;
-  hash?: string;
-  embedding?: number[];
+  id_?: string | undefined;
+  metadata?: T | undefined;
+  excludedEmbedMetadataKeys?: string[] | undefined;
+  excludedLlmMetadataKeys?: string[] | undefined;
+  relationships?:
+    | Partial<Record<NodeRelationship, RelatedNodeType<T>>>
+    | undefined;
+  hash?: string | undefined;
+  embedding?: number[] | undefined;
 };
 
 /**
@@ -58,7 +60,7 @@ export abstract class BaseNode<T extends Metadata = Metadata> {
    * Set to a UUID by default.
    */
   id_: string;
-  embedding?: number[];
+  embedding: number[] | undefined;
 
   // Metadata fields
   metadata: T;
@@ -198,11 +200,11 @@ export abstract class BaseNode<T extends Metadata = Metadata> {
 
 export type TextNodeParams<T extends Metadata = Metadata> =
   BaseNodeParams<T> & {
-    text?: string;
-    textTemplate?: string;
-    startCharIdx?: number;
-    endCharIdx?: number;
-    metadataSeparator?: string;
+    text?: string | undefined;
+    textTemplate?: string | undefined;
+    startCharIdx?: number | undefined;
+    endCharIdx?: number | undefined;
+    metadataSeparator?: string | undefined;
   };
 
 /**
@@ -418,7 +420,7 @@ export class ImageDocument<T extends Metadata = Metadata> extends ImageNode<T> {
  */
 export interface NodeWithScore<T extends Metadata = Metadata> {
   node: BaseNode<T>;
-  score?: number;
+  score?: number | undefined;
 }
 
 export enum ModalityType {

packages/core/src/schema/type/engine–response.ts

@@ -3,7 +3,7 @@ import { extractText } from "../../utils";
 import type { Metadata, NodeWithScore } from "../node";
 
 export class EngineResponse implements ChatResponse, ChatResponseChunk {
-  sourceNodes?: NodeWithScore[];
+  sourceNodes: NodeWithScore[] | undefined;
 
   metadata: Metadata = {};
 

packages/core/src/utils/llms.ts

@@ -74,12 +74,12 @@ export const extractDataUrlComponents = (
 } => {
   const parts = dataUrl.split(";base64,");
 
-  if (parts.length !== 2 || !parts[0].startsWith("data:")) {
+  if (parts.length !== 2 || !parts[0]!.startsWith("data:")) {
     throw new Error("Invalid data URL");
   }
 
-  const mimeType = parts[0].slice(5);
-  const base64 = parts[1];
+  const mimeType = parts[0]!.slice(5);
+  const base64 = parts[1]!;
 
   return {
     mimeType,

packages/core/tests/node-parser/markdown.test.ts

@@ -19,12 +19,12 @@ Header 2 content
     ]);
 
     expect(splits.length).toBe(2);
-    expect(splits[0].metadata).toEqual({ Header_1: "Main Header" });
-    expect(splits[1].metadata).toEqual({ Header_1: "Header 2" });
-    expect(splits[0].getContent(MetadataMode.NONE)).toStrictEqual(
+    expect(splits[0]!.metadata).toEqual({ Header_1: "Main Header" });
+    expect(splits[1]!.metadata).toEqual({ Header_1: "Header 2" });
+    expect(splits[0]!.getContent(MetadataMode.NONE)).toStrictEqual(
       "Main Header\n\nHeader 1 content",
     );
-    expect(splits[1].getContent(MetadataMode.NONE)).toStrictEqual(
+    expect(splits[1]!.getContent(MetadataMode.NONE)).toStrictEqual(
       "Header 2\nHeader 2 content",
     );
   });
@@ -89,16 +89,16 @@ Content
       }),
     ]);
     expect(splits.length).toBe(4);
-    expect(splits[0].metadata).toEqual({ Header_1: "Main Header" });
-    expect(splits[1].metadata).toEqual({
+    expect(splits[0]!.metadata).toEqual({ Header_1: "Main Header" });
+    expect(splits[1]!.metadata).toEqual({
       Header_1: "Main Header",
       Header_2: "Sub-header",
     });
-    expect(splits[2].metadata).toEqual({
+    expect(splits[2]!.metadata).toEqual({
       Header_1: "Main Header",
       Header_2: "Sub-header",
       Header_3: "Sub-sub header",
     });
-    expect(splits[3].metadata).toEqual({ Header_1: "New title" });
+    expect(splits[3]!.metadata).toEqual({ Header_1: "New title" });
   });
 });

packages/core/tests/node-parser/sentence-spiller.test.ts

@@ -22,7 +22,7 @@ describe("SentenceSplitter", () => {
     });
     const result = sentenceSplitter.getNodesFromDocuments([doc]);
     expect(result.length).toEqual(1);
-    const node = result[0];
+    const node = result[0]!;
     // check not the same object
     expect(node.metadata).not.toBe(doc.metadata);
     expect(node.excludedLlmMetadataKeys).not.toBe(doc.excludedLlmMetadataKeys);

packages/experimental/CHANGELOG.md

@@ -1,5 +1,40 @@
 # @llamaindex/experimental
 
+## 0.0.77
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+
+## 0.0.76
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+
+## 0.0.75
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+
+## 0.0.74
+
+### Patch Changes
+
+- llamaindex@0.5.24
+
+## 0.0.73
+
+### Patch Changes
+
+- llamaindex@0.5.23
+
 ## 0.0.72
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.72",
+  "version": "0.0.77",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,49 @@
 # llamaindex
 
+## 0.5.27
+
+### Patch Changes
+
+- 7edeb1c: feat: decouple openai from `llamaindex` module
+
+  This should be a non-breaking change, but just you can now only install `@llamaindex/openai` to reduce the bundle size in the future
+
+- Updated dependencies [7edeb1c]
+  - @llamaindex/openai@0.1.1
+
+## 0.5.26
+
+### Patch Changes
+
+- ffe0cd1: faet: add openai o1 support
+- ffe0cd1: feat: add PostgreSQL storage
+
+## 0.5.25
+
+### Patch Changes
+
+- 4810364: fix: handle `RouterQueryEngine` with string query
+- d3bc663: refactor: export vector store only in nodejs environment on top level
+
+  If you see some missing modules error, please change vector store related imports to `llamaindex/vector-store`
+
+- Updated dependencies [4810364]
+  - @llamaindex/cloud@0.2.4
+
+## 0.5.24
+
+### Patch Changes
+
+- Updated dependencies [0bf8d80]
+  - @llamaindex/cloud@0.2.3
+
+## 0.5.23
+
+### Patch Changes
+
+- Updated dependencies [711c814]
+  - @llamaindex/core@0.1.12
+
 ## 0.5.22
 
 ### Patch Changes

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

@@ -1,5 +1,40 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.61
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+
+## 0.0.60
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+
+## 0.0.59
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+
+## 0.0.58
+
+### Patch Changes
+
+- llamaindex@0.5.24
+
+## 0.0.57
+
+### Patch Changes
+
+- llamaindex@0.5.23
+
 ## 0.0.56
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.56",
+  "version": "0.0.61",
   "type": "module",
   "private": true,
   "scripts": {

packages/llamaindex/e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,40 @@
 # @llamaindex/next-agent-test
 
+## 0.1.61
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+
+## 0.1.60
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+
+## 0.1.59
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+
+## 0.1.58
+
+### Patch Changes
+
+- llamaindex@0.5.24
+
+## 0.1.57
+
+### Patch Changes
+
+- llamaindex@0.5.23
+
 ## 0.1.56
 
 ### Patch Changes

packages/llamaindex/e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.56",
+  "version": "0.1.61",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,40 @@
 # test-edge-runtime
 
+## 0.1.60
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+
+## 0.1.59
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+
+## 0.1.58
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+
+## 0.1.57
+
+### Patch Changes
+
+- llamaindex@0.5.24
+
+## 0.1.56
+
+### Patch Changes
+
+- llamaindex@0.5.23
+
 ## 0.1.55
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.55",
+  "version": "0.1.60",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,40 @@
 # @llamaindex/next-node-runtime
 
+## 0.0.42
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+
+## 0.0.41
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+
+## 0.0.40
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+
+## 0.0.39
+
+### Patch Changes
+
+- llamaindex@0.5.24
+
+## 0.0.38
+
+### Patch Changes
+
+- llamaindex@0.5.23
+
 ## 0.0.37
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.0.37",
+  "version": "0.0.42",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,40 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.61
+
+### Patch Changes
+
+- Updated dependencies [7edeb1c]
+  - llamaindex@0.5.27
+
+## 0.0.60
+
+### Patch Changes
+
+- Updated dependencies [ffe0cd1]
+- Updated dependencies [ffe0cd1]
+  - llamaindex@0.5.26
+
+## 0.0.59
+
+### Patch Changes
+
+- Updated dependencies [4810364]
+- Updated dependencies [d3bc663]
+  - llamaindex@0.5.25
+
+## 0.0.58
+
+### Patch Changes
+
+- llamaindex@0.5.24
+
+## 0.0.57
+
+### Patch Changes
+
+- llamaindex@0.5.23
+
 ## 0.0.56
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.56",
+  "version": "0.0.61",
   "type": "module",
   "private": true,
   "scripts": {
@@ -20,6 +20,7 @@
     "@types/react-dom": "18.3.0",
     "autoprefixer": "10.4.20",
     "tailwindcss": "3.4.10",
-    "typescript": "5.5.4"
+    "typescript": "5.5.4",
+    "vite-plugin-wasm": "^3.3.0"
   }
 }

packages/llamaindex/e2e/examples/waku-query-engine/src/pages/_layout.tsx

@@ -11,15 +11,22 @@ export default async function RootLayout({ children }: RootLayoutProps) {
   const data = await getData();
 
   return (
-    <div className="font-['Nunito']">
-      <meta property="description" content={data.description} />
-      <link rel="icon" type="image/png" href={data.icon} />
-      <Header />
-      <main className="m-6 flex items-center *:min-h-64 *:min-w-64 lg:m-0 lg:min-h-svh lg:justify-center">
-        {children}
-      </main>
-      <Footer />
-    </div>
+    <html>
+      <head>
+        <meta property="description" content={data.description} />
+        <link rel="icon" type="image/png" href={data.icon} />
+        <title>LlamaIndex Waku Example</title>
+      </head>
+      <body>
+        <div className="font-['Nunito']">
+          <Header />
+          <main className="m-6 flex items-center *:min-h-64 *:min-w-64 lg:m-0 lg:min-h-svh lg:justify-center">
+            {children}
+          </main>
+          <Footer />
+        </div>
+      </body>
+    </html>
   );
 }
 
@@ -31,7 +38,6 @@ const getData = async () => {
 
   return data;
 };
-
 export const getConfig = async () => {
   return {
     render: "static",

packages/llamaindex/e2e/examples/waku-query-engine/vite.config.ts

@@ -0,0 +1,8 @@
+import wasm from "vite-plugin-wasm";
+
+export default {
+  plugins: [wasm()],
+  ssr: {
+    external: ["tiktoken"],
+  },
+};

packages/llamaindex/e2e/fixtures/embeddings/OpenAIEmbedding.ts

@@ -1,51 +0,0 @@
-import { TransformComponent } from "@llamaindex/core/schema";
-import {
-  BaseEmbedding,
-  BaseNode,
-  SimilarityType,
-  type EmbeddingInfo,
-  type MessageContentDetail,
-} from "llamaindex";
-
-export class OpenAIEmbedding
-  extends TransformComponent
-  implements BaseEmbedding
-{
-  embedInfo?: EmbeddingInfo | undefined;
-  embedBatchSize = 512;
-
-  constructor() {
-    super(async (nodes: BaseNode[], _options?: any): Promise<BaseNode[]> => {
-      nodes.forEach((node) => (node.embedding = [0]));
-      return nodes;
-    });
-  }
-
-  async getQueryEmbedding(query: MessageContentDetail) {
-    return [0];
-  }
-
-  async getTextEmbedding(text: string) {
-    return [0];
-  }
-
-  async getTextEmbeddings(texts: string[]) {
-    return [[0]];
-  }
-
-  async getTextEmbeddingsBatch(texts: string[]) {
-    return [[0]];
-  }
-
-  similarity(
-    embedding1: number[],
-    embedding2: number[],
-    mode?: SimilarityType,
-  ) {
-    return 1;
-  }
-
-  truncateMaxTokens(input: string[]): string[] {
-    return input;
-  }
-}

packages/llamaindex/e2e/fixtures/llm/openai.ts

@@ -12,6 +12,15 @@ import type {
 import { deepStrictEqual, strictEqual } from "node:assert";
 import { llmCompleteMockStorage } from "../../node/utils.js";
 
+import { TransformComponent } from "@llamaindex/core/schema";
+import {
+  BaseEmbedding,
+  BaseNode,
+  SimilarityType,
+  type EmbeddingInfo,
+  type MessageContentDetail,
+} from "llamaindex";
+
 export function getOpenAISession() {
   return {};
 }
@@ -22,6 +31,7 @@ export function isFunctionCallingModel() {
 
 export class OpenAI implements LLM {
   supportToolCall = true;
+
   get metadata() {
     return {
       model: "mock-model",
@@ -32,6 +42,7 @@ export class OpenAI implements LLM {
       isFunctionCallingModel: true,
     };
   }
+
   chat(
     params: LLMChatParamsStreaming<Record<string, unknown>>,
   ): Promise<AsyncIterable<ChatResponseChunk>>;
@@ -48,8 +59,8 @@ export class OpenAI implements LLM {
         llmCompleteMockStorage.llmEventStart.shift()!["messages"];
       strictEqual(params.messages.length, chatMessage.length);
       for (let i = 0; i < chatMessage.length; i++) {
-        strictEqual(params.messages[i].role, chatMessage[i].role);
-        deepStrictEqual(params.messages[i].content, chatMessage[i].content);
+        strictEqual(params.messages[i]!.role, chatMessage[i]!.role);
+        deepStrictEqual(params.messages[i]!.content, chatMessage[i]!.content);
       }
 
       if (llmCompleteMockStorage.llmEventEnd.length > 0) {
@@ -64,7 +75,7 @@ export class OpenAI implements LLM {
                 if (idx === -1) {
                   break;
                 }
-                const chunk = llmCompleteMockStorage.llmEventStream[idx].chunk;
+                const chunk = llmCompleteMockStorage.llmEventStream[idx]!.chunk;
                 llmCompleteMockStorage.llmEventStream.splice(idx, 1);
                 yield chunk;
               }
@@ -77,6 +88,7 @@ export class OpenAI implements LLM {
     }
     throw new Error("Method not implemented.");
   }
+
   complete(
     params: LLMCompletionParamsStreaming,
   ): Promise<AsyncIterable<CompletionResponse>>;
@@ -90,8 +102,8 @@ export class OpenAI implements LLM {
       const chatMessage =
         llmCompleteMockStorage.llmEventStart.shift()!["messages"];
       strictEqual(1, chatMessage.length);
-      strictEqual("user", chatMessage[0].role);
-      strictEqual(params.prompt, chatMessage[0].content);
+      strictEqual("user", chatMessage[0]!.role);
+      strictEqual(params.prompt, chatMessage[0]!.content);
     }
     if (llmCompleteMockStorage.llmEventEnd.length > 0) {
       const response = llmCompleteMockStorage.llmEventEnd.shift()!["response"];
@@ -103,3 +115,46 @@ export class OpenAI implements LLM {
     throw new Error("Method not implemented.");
   }
 }
+
+export class OpenAIEmbedding
+  extends TransformComponent
+  implements BaseEmbedding
+{
+  embedInfo?: EmbeddingInfo;
+  embedBatchSize = 512;
+
+  constructor() {
+    super(async (nodes: BaseNode[], _options?: any): Promise<BaseNode[]> => {
+      nodes.forEach((node) => (node.embedding = [0]));
+      return nodes;
+    });
+  }
+
+  async getQueryEmbedding(query: MessageContentDetail) {
+    return [0];
+  }
+
+  async getTextEmbedding(text: string) {
+    return [0];
+  }
+
+  async getTextEmbeddings(texts: string[]) {
+    return [[0]];
+  }
+
+  async getTextEmbeddingsBatch(texts: string[]) {
+    return [[0]];
+  }
+
+  similarity(
+    embedding1: number[],
+    embedding2: number[],
+    mode?: SimilarityType,
+  ) {
+    return 1;
+  }
+
+  truncateMaxTokens(input: string[]): string[] {
+    return input;
+  }
+}

packages/llamaindex/e2e/mock-module.js

@@ -13,8 +13,14 @@ export async function resolve(specifier, context, nextResolve) {
     return result;
   }
   const targetUrl = fileURLToPath(result.url).replace(/\.js$/, ".ts");
-  const relativePath = relative(packageDistDir, targetUrl);
-  if (relativePath.startsWith(".") || relativePath.startsWith("/")) {
+  let relativePath = relative(packageDistDir, targetUrl);
+  // todo: make it more generic if we have more sub modules fixtures in the future
+  if (relativePath.startsWith("../../llm/openai")) {
+    relativePath = relativePath.replace(
+      "../../llm/openai/dist/index.ts",
+      "llm/openai.ts",
+    );
+  } else if (relativePath.startsWith(".") || relativePath.startsWith("/")) {
     return result;
   }
   const url = pathToFileURL(join(fixturesDir, relativePath)).toString();

packages/llamaindex/e2e/node/issue.e2e.ts

@@ -0,0 +1,67 @@
+import { LLMSingleSelector, Settings } from "llamaindex";
+import assert from "node:assert";
+import { test } from "node:test";
+import { mockLLMEvent } from "./utils.js";
+
+await test("#1177", async (t) => {
+  await mockLLMEvent(t, "#1177");
+  await t.test(async () => {
+    const selector = new LLMSingleSelector({
+      llm: Settings.llm,
+    });
+    {
+      const result = await selector.select(
+        [
+          {
+            description: "Math calculation",
+          },
+          {
+            description: "Search from google",
+          },
+        ],
+        "calculate 2 + 2",
+      );
+      assert.equal(result.selections.length, 1);
+      assert.equal(result.selections.at(0)!.index, 0);
+    }
+    {
+      const result = await selector.select(
+        [
+          {
+            description: "Math calculation",
+          },
+          {
+            description: "Search from google",
+          },
+        ],
+        {
+          query: "calculate 2 + 2",
+        },
+      );
+      assert.equal(result.selections.length, 1);
+      assert.equal(result.selections.at(0)!.index, 0);
+    }
+    {
+      const result = await selector.select(
+        [
+          {
+            description: "Math calculation",
+          },
+          {
+            description: "Search from google",
+          },
+        ],
+        {
+          query: [
+            {
+              type: "text",
+              text: "calculate 2 + 2",
+            },
+          ],
+        },
+      );
+      assert.equal(result.selections.length, 1);
+      assert.equal(result.selections.at(0)!.index, 0);
+    }
+  });
+});

packages/llamaindex/e2e/node/openai.e2e.ts

@@ -163,11 +163,11 @@ For questions about more specific sections, please use the vector_tool.`,
     }),
   ];
 
-  const originalCall = queryEngineTools[1].call.bind(queryEngineTools[1]);
+  const originalCall = queryEngineTools[1]!.call.bind(queryEngineTools[1]);
   const mockCall = t.mock.fn(({ query }: { query: string }) => {
     return originalCall({ query });
   });
-  queryEngineTools[1].call = mockCall;
+  queryEngineTools[1]!.call = mockCall;
 
   const toolMapping = SimpleToolNodeMapping.fromObjects(queryEngineTools);
 

packages/llamaindex/e2e/node/snapshot/#1177.snap

@@ -0,0 +1,67 @@
+{
+  "llmEventStart": [
+    {
+      "id": "PRESERVE_0",
+      "messages": [
+        {
+          "content": "Some choices are given below. It is provided in a numbered list (1 to 42), where each item in the list corresponds to a summary.\n---------------------\n(1) Math calculation(2) Search from google\n---------------------\nUsing only the choices above and not prior knowledge, return the choice that is most relevant to the question: 'calculate 2 + 2'\n\n\nThe output should be ONLY JSON formatted as a JSON instance.\n\nHere is an example:\n[\n    {\n        \"choice\": 1,\n        \"reason\": \"<insert reason for choice>\"\n    },\n    ...\n]\n",
+          "role": "user"
+        }
+      ]
+    },
+    {
+      "id": "PRESERVE_1",
+      "messages": [
+        {
+          "content": "Some choices are given below. It is provided in a numbered list (1 to 42), where each item in the list corresponds to a summary.\n---------------------\n(1) Math calculation(2) Search from google\n---------------------\nUsing only the choices above and not prior knowledge, return the choice that is most relevant to the question: 'calculate 2 + 2'\n\n\nThe output should be ONLY JSON formatted as a JSON instance.\n\nHere is an example:\n[\n    {\n        \"choice\": 1,\n        \"reason\": \"<insert reason for choice>\"\n    },\n    ...\n]\n",
+          "role": "user"
+        }
+      ]
+    },
+    {
+      "id": "PRESERVE_2",
+      "messages": [
+        {
+          "content": "Some choices are given below. It is provided in a numbered list (1 to 42), where each item in the list corresponds to a summary.\n---------------------\n(1) Math calculation(2) Search from google\n---------------------\nUsing only the choices above and not prior knowledge, return the choice that is most relevant to the question: 'calculate 2 + 2'\n\n\nThe output should be ONLY JSON formatted as a JSON instance.\n\nHere is an example:\n[\n    {\n        \"choice\": 1,\n        \"reason\": \"<insert reason for choice>\"\n    },\n    ...\n]\n",
+          "role": "user"
+        }
+      ]
+    }
+  ],
+  "llmEventEnd": [
+    {
+      "id": "PRESERVE_0",
+      "response": {
+        "raw": null,
+        "message": {
+          "content": "[\n    {\n        \"choice\": 1,\n        \"reason\": \"The question 'calculate 2 + 2' is directly asking for a math calculation, which corresponds to choice 1.\"\n    }\n]",
+          "role": "assistant",
+          "options": {}
+        }
+      }
+    },
+    {
+      "id": "PRESERVE_1",
+      "response": {
+        "raw": null,
+        "message": {
+          "content": "[\n    {\n        \"choice\": 1,\n        \"reason\": \"The question 'calculate 2 + 2' is asking for a mathematical calculation, which directly corresponds to choice 1: Math calculation.\"\n    }\n]",
+          "role": "assistant",
+          "options": {}
+        }
+      }
+    },
+    {
+      "id": "PRESERVE_2",
+      "response": {
+        "raw": null,
+        "message": {
+          "content": "[\n    {\n        \"choice\": 1,\n        \"reason\": \"The question 'calculate 2 + 2' is asking for a mathematical calculation, which directly corresponds to choice 1: Math calculation.\"\n    }\n]",
+          "role": "assistant",
+          "options": {}
+        }
+      }
+    }
+  ],
+  "llmEventStream": []
+}

packages/llamaindex/e2e/node/vector-store/pg-vector-store.test.ts

@@ -0,0 +1,90 @@
+import { Document, VectorStoreQueryMode } from "llamaindex";
+import { PGVectorStore } from "llamaindex/vector-store/PGVectorStore";
+import assert from "node:assert";
+import { test } from "node:test";
+import pg from "pg";
+import { registerTypes } from "pgvector/pg";
+
+let pgClient: pg.Client | pg.Pool;
+test.afterEach(async () => {
+  await pgClient.end();
+});
+
+await test("init with client", async () => {
+  pgClient = new pg.Client({
+    database: "llamaindex_node_test",
+  });
+  await pgClient.connect();
+  await pgClient.query("CREATE EXTENSION IF NOT EXISTS vector");
+  await registerTypes(pgClient);
+  const vectorStore = new PGVectorStore(pgClient);
+  assert.deepStrictEqual(await vectorStore.client(), pgClient);
+});
+
+await test("init with pool", async () => {
+  pgClient = new pg.Pool({
+    database: "llamaindex_node_test",
+  });
+  await pgClient.query("CREATE EXTENSION IF NOT EXISTS vector");
+  const client = await pgClient.connect();
+  await registerTypes(client);
+  const vectorStore = new PGVectorStore(client);
+  assert.deepStrictEqual(await vectorStore.client(), client);
+  client.release();
+});
+
+await test("init without client", async () => {
+  const vectorStore = new PGVectorStore({
+    database: "llamaindex_node_test",
+  });
+  pgClient = (await vectorStore.client()) as pg.Client;
+  assert.notDeepStrictEqual(pgClient, undefined);
+});
+
+await test("simple node", async () => {
+  const dimensions = 3;
+  const schemaName =
+    "llamaindex_vector_store_test_" + Math.random().toString(36).substring(7);
+  const nodeId = "5bb16627-f6c0-459c-bb18-71642813ef21";
+  const node = new Document({
+    text: "hello world",
+    id_: nodeId,
+    embedding: [0.1, 0.2, 0.3],
+  });
+  const vectorStore = new PGVectorStore({
+    database: "llamaindex_node_test",
+    dimensions,
+    schemaName,
+  });
+
+  await vectorStore.add([node]);
+
+  {
+    const result = await vectorStore.query({
+      mode: VectorStoreQueryMode.DEFAULT,
+      similarityTopK: 1,
+      queryEmbedding: [1, 2, 3],
+    });
+    const actualJSON = result.nodes![0]!.toJSON();
+    assert.deepStrictEqual(actualJSON, {
+      ...node.toJSON(),
+      hash: actualJSON.hash,
+      metadata: actualJSON.metadata,
+    });
+    assert.deepStrictEqual(result.ids, [nodeId]);
+    assert.deepStrictEqual(result.similarities, [1]);
+  }
+
+  await vectorStore.delete(nodeId);
+
+  {
+    const result = await vectorStore.query({
+      mode: VectorStoreQueryMode.DEFAULT,
+      similarityTopK: 1,
+      queryEmbedding: [1, 2, 3],
+    });
+    assert.deepStrictEqual(result.nodes, []);
+  }
+
+  pgClient = (await vectorStore.client()) as pg.Client;
+});

packages/llamaindex/e2e/package.json

@@ -10,7 +10,6 @@
   },
   "devDependencies": {
     "@faker-js/faker": "^8.4.1",
-    "@llamaindex/core": "workspace:*",
     "@types/node": "^22.5.1",
     "consola": "^3.2.3",
     "llamaindex": "workspace:*",

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.5.22",
+  "version": "0.5.27",
   "license": "MIT",
   "type": "module",
   "keywords": [
@@ -33,6 +33,7 @@
     "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
+    "@llamaindex/openai": "workspace:*",
     "@mistralai/mistralai": "^1.0.4",
     "@mixedbread-ai/sdk": "^2.2.11",
     "@pinecone-database/pinecone": "^3.0.2",
@@ -56,11 +57,9 @@
     "md-utils-ts": "^2.0.0",
     "mongodb": "^6.7.0",
     "notion-md-crawler": "^1.0.0",
-    "openai": "^4.57.0",
+    "openai": "^4.60.0",
     "papaparse": "^5.4.1",
     "pathe": "^1.1.2",
-    "pg": "^8.12.0",
-    "pgvector": "^0.2.0",
     "portkey-ai": "0.1.16",
     "rake-modified": "^1.0.8",
     "string-strip-html": "^13.4.8",
@@ -72,11 +71,19 @@
     "zod": "^3.23.8"
   },
   "peerDependencies": {
-    "@notionhq/client": "^2.2.15"
+    "@notionhq/client": "^2.2.15",
+    "pg": "^8.12.0",
+    "pgvector": "0.2.0"
   },
   "peerDependenciesMeta": {
     "@notionhq/client": {
       "optional": true
+    },
+    "pg": {
+      "optional": true
+    },
+    "pgvector": {
+      "optional": true
     }
   },
   "devDependencies": {
@@ -85,6 +92,8 @@
     "@swc/core": "^1.7.22",
     "concurrently": "^8.2.2",
     "glob": "^11.0.0",
+    "pg": "^8.12.0",
+    "pgvector": "0.2.0",
     "typescript": "^5.5.4"
   },
   "engines": {

packages/llamaindex/src/ChatHistory.ts

@@ -5,7 +5,7 @@ import {
 } from "@llamaindex/core/prompts";
 import { extractText, messagesToHistory } from "@llamaindex/core/utils";
 import { tokenizers, type Tokenizer } from "@llamaindex/env";
-import { OpenAI } from "./llm/openai.js";
+import { OpenAI } from "@llamaindex/openai";
 
 /**
  * A ChatHistory is used to keep the state of back and forth chat messages
@@ -42,7 +42,7 @@ export class SimpleChatHistory extends ChatHistory {
   messages: ChatMessage[];
   private messagesBefore: number;
 
-  constructor(init?: Partial<SimpleChatHistory>) {
+  constructor(init?: { messages?: ChatMessage[] | undefined }) {
     super();
     this.messages = init?.messages ?? [];
     this.messagesBefore = this.messages.length;
@@ -118,7 +118,7 @@ export class SummaryChatHistory extends ChatHistory {
       // remove oldest message until the chat history is short enough for the context window
       messagesToSummarize.shift();
     } while (
-      this.tokenizer.encode(promptMessages[0].content).length >
+      this.tokenizer.encode(promptMessages[0]!.content).length >
       this.tokensToSummarize
     );
 
@@ -146,7 +146,7 @@ export class SummaryChatHistory extends ChatHistory {
 
   public getLastSummary(): ChatMessage | null {
     const lastSummaryIndex = this.getLastSummaryIndex();
-    return lastSummaryIndex ? this.messages[lastSummaryIndex] : null;
+    return lastSummaryIndex ? this.messages[lastSummaryIndex]! : null;
   }
 
   private get systemMessages() {
@@ -174,10 +174,10 @@ export class SummaryChatHistory extends ChatHistory {
       // and convert summary message so it can be send to the LLM
       const summaryMessage: ChatMessage = transformSummary
         ? {
-            content: `Summary of the conversation so far: ${this.messages[lastSummaryIndex].content}`,
+            content: `Summary of the conversation so far: ${this.messages[lastSummaryIndex]!.content}`,
             role: "system",
           }
-        : this.messages[lastSummaryIndex];
+        : this.messages[lastSummaryIndex]!;
       return [summaryMessage, ...this.messages.slice(lastSummaryIndex + 1)];
     }
   }

packages/llamaindex/src/QuestionGenerator.ts

@@ -8,12 +8,12 @@ import {
 import type { QueryType } from "@llamaindex/core/query-engine";
 import type { BaseOutputParser } from "@llamaindex/core/schema";
 import { extractText, toToolDescriptions } from "@llamaindex/core/utils";
+import { OpenAI } from "@llamaindex/openai";
 import { SubQuestionOutputParser } from "./OutputParser.js";
 import type {
   BaseQuestionGenerator,
   SubQuestion,
 } from "./engines/query/types.js";
-import { OpenAI } from "./llm/openai.js";
 import type { StructuredOutput } from "./types.js";
 
 /**

packages/llamaindex/src/Retriever.ts

@@ -13,6 +13,8 @@ export type RetrieveParams = {
 export interface BaseRetriever {
   retrieve(params: RetrieveParams): Promise<NodeWithScore[]>;
 
-  // to be deprecated soon
-  serviceContext?: ServiceContext;
+  /**
+   * @deprecated to be deprecated soon
+   */
+  serviceContext?: ServiceContext | undefined;
 }

packages/llamaindex/src/ServiceContext.ts

@@ -1,12 +1,11 @@
 import type { BaseEmbedding } from "@llamaindex/core/embeddings";
+import { PromptHelper } from "@llamaindex/core/indices";
 import type { LLM } from "@llamaindex/core/llms";
 import {
   type NodeParser,
   SentenceSplitter,
 } from "@llamaindex/core/node-parser";
-import { PromptHelper } from "./PromptHelper.js";
-import { OpenAIEmbedding } from "./embeddings/OpenAIEmbedding.js";
-import { OpenAI } from "./llm/openai.js";
+import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
 
 /**
  * The ServiceContext is a collection of components that are used in different parts of the application.

packages/llamaindex/src/Settings.ts

@@ -2,9 +2,9 @@ import {
   type CallbackManager,
   Settings as CoreSettings,
 } from "@llamaindex/core/global";
-import { OpenAI } from "./llm/openai.js";
+import { OpenAI } from "@llamaindex/openai";
 
-import { PromptHelper } from "./PromptHelper.js";
+import { PromptHelper } from "@llamaindex/core/indices";
 
 import type { BaseEmbedding } from "@llamaindex/core/embeddings";
 import type { LLM } from "@llamaindex/core/llms";
@@ -27,13 +27,12 @@ export type PromptConfig = {
 
 export interface Config {
   prompt: PromptConfig;
-  llm: LLM | null;
   promptHelper: PromptHelper | null;
   embedModel: BaseEmbedding | null;
   nodeParser: NodeParser | null;
   callbackManager: CallbackManager | null;
-  chunkSize?: number;
-  chunkOverlap?: number;
+  chunkSize: number | undefined;
+  chunkOverlap: number | undefined;
 }
 
 /**
@@ -41,12 +40,10 @@ export interface Config {
  */
 class GlobalSettings implements Config {
   #prompt: PromptConfig = {};
-  #llm: LLM | null = null;
   #promptHelper: PromptHelper | null = null;
   #nodeParser: NodeParser | null = null;
   #chunkOverlap?: number;
 
-  #llmAsyncLocalStorage = new AsyncLocalStorage<LLM>();
   #promptHelperAsyncLocalStorage = new AsyncLocalStorage<PromptHelper>();
   #nodeParserAsyncLocalStorage = new AsyncLocalStorage<NodeParser>();
   #chunkOverlapAsyncLocalStorage = new AsyncLocalStorage<number>();
@@ -62,19 +59,21 @@ class GlobalSettings implements Config {
   }
 
   get llm(): LLM {
-    if (this.#llm === null) {
-      this.#llm = new OpenAI();
+    // fixme: we might need check internal error instead of try-catch here
+    try {
+      CoreSettings.llm;
+    } catch (error) {
+      CoreSettings.llm = new OpenAI();
     }
-
-    return this.#llmAsyncLocalStorage.getStore() ?? this.#llm;
+    return CoreSettings.llm;
   }
 
   set llm(llm: LLM) {
-    this.#llm = llm;
+    CoreSettings.llm = llm;
   }
 
   withLLM<Result>(llm: LLM, fn: () => Result): Result {
-    return this.#llmAsyncLocalStorage.run(llm, fn);
+    return CoreSettings.withLLM(llm, fn);
   }
 
   get promptHelper(): PromptHelper {
@@ -159,7 +158,9 @@ class GlobalSettings implements Config {
   }
 
   set chunkOverlap(chunkOverlap: number | undefined) {
-    this.#chunkOverlap = chunkOverlap;
+    if (typeof chunkOverlap === "number") {
+      this.#chunkOverlap = chunkOverlap;
+    }
   }
 
   withChunkOverlap<Result>(chunkOverlap: number, fn: () => Result): Result {

packages/llamaindex/src/agent/base.ts

@@ -53,7 +53,7 @@ export function createTaskOutputStream<
         nextSteps: new Set(),
       };
       if (steps.length > 0) {
-        step.prevStep = steps[steps.length - 1];
+        step.prevStep = steps[steps.length - 1]!;
       }
       const taskOutputs: TaskStepOutput<
         Model,
@@ -77,7 +77,7 @@ export function createTaskOutputStream<
       context.logger.log("Finished step(id, %s).", step.id);
       // fixme: support multi-thread when there are multiple outputs
       // todo: for now we pretend there is only one task output
-      const { isLast, taskStep } = taskOutputs[0];
+      const { isLast, taskStep } = taskOutputs[0]!;
       context = {
         ...taskStep.context,
         store: {

packages/llamaindex/src/agent/openai.ts

@@ -1,5 +1,5 @@
+import { OpenAI } from "@llamaindex/openai";
 import { Settings } from "../Settings.js";
-import { OpenAI } from "../llm/openai.js";
 import { LLMAgent, LLMAgentWorker, type LLMAgentParams } from "./llm.js";
 
 // This is likely not necessary anymore but leaving it here just incase it's in use elsewhere

packages/llamaindex/src/agent/react.ts

@@ -89,8 +89,8 @@ function extractFinalResponse(
     );
   }
 
-  const thought = match[1].trim();
-  const answer = match[2].trim();
+  const thought = match[1]!.trim();
+  const answer = match[2]!.trim();
   return [thought, answer];
 }
 
@@ -108,9 +108,9 @@ function extractToolUse(
     );
   }
 
-  const thought = match[1].trim();
-  const action = match[2].trim();
-  const actionInput = match[3].trim();
+  const thought = match[1]!.trim();
+  const action = match[2]!.trim();
+  const actionInput = match[3]!.trim();
   return [thought, action, actionInput];
 }
 

packages/llamaindex/src/cloud/LLamaCloudFileService.ts

@@ -12,9 +12,14 @@ export class LLamaCloudFileService {
   public static async getAllProjectsWithPipelines() {
     initService();
     try {
-      const projects = await ProjectsService.listProjectsApiV1ProjectsGet();
-      const pipelines =
-        await PipelinesService.searchPipelinesApiV1PipelinesGet();
+      const { data: projects } =
+        await ProjectsService.listProjectsApiV1ProjectsGet({
+          throwOnError: true,
+        });
+      const { data: pipelines } =
+        await PipelinesService.searchPipelinesApiV1PipelinesGet({
+          throwOnError: true,
+        });
       return projects.map((project) => ({
         ...project,
         pipelines: pipelines.filter((p) => p.project_id === project.id),
@@ -35,11 +40,12 @@ export class LLamaCloudFileService {
     customMetadata: Record<string, any> = {},
   ) {
     initService();
-    const file = await FilesService.uploadFileApiV1FilesPost({
-      projectId,
-      formData: {
+    const { data: file } = await FilesService.uploadFileApiV1FilesPost({
+      path: { project_id: projectId },
+      body: {
         upload_file: uploadFile,
       },
+      throwOnError: true,
     });
     const files = [
       {
@@ -48,19 +54,24 @@ export class LLamaCloudFileService {
       },
     ];
     await PipelinesService.addFilesToPipelineApiV1PipelinesPipelineIdFilesPut({
-      pipelineId,
-      requestBody: files,
+      path: {
+        pipeline_id: pipelineId,
+      },
+      body: files,
     });
 
     // Wait 2s for the file to be processed
     const maxAttempts = 20;
     let attempt = 0;
     while (attempt < maxAttempts) {
-      const result =
+      const { data: result } =
         await PipelinesService.getPipelineFileStatusApiV1PipelinesPipelineIdFilesFileIdStatusGet(
           {
-            pipelineId,
-            fileId: file.id,
+            path: {
+              pipeline_id: pipelineId,
+              file_id: file.id,
+            },
+            throwOnError: true,
           },
         );
       if (result.status === "ERROR") {
@@ -83,16 +94,24 @@ export class LLamaCloudFileService {
    */
   public static async getFileUrl(pipelineId: string, filename: string) {
     initService();
-    const allPipelineFiles =
+    const { data: allPipelineFiles } =
       await PipelinesService.listPipelineFilesApiV1PipelinesPipelineIdFilesGet({
-        pipelineId,
+        path: {
+          pipeline_id: pipelineId,
+        },
+        throwOnError: true,
       });
     const file = allPipelineFiles.find((file) => file.name === filename);
     if (!file?.file_id) return null;
-    const fileContent =
+    const { data: fileContent } =
       await FilesService.readFileContentApiV1FilesIdContentGet({
-        id: file.file_id,
-        projectId: file.project_id,
+        path: {
+          id: file.file_id,
+        },
+        query: {
+          project_id: file.project_id,
+        },
+        throwOnError: true,
       });
     return fileContent.url;
   }

packages/llamaindex/src/cloud/LlamaCloudIndex.ts

@@ -13,8 +13,8 @@ import { getAppBaseUrl, getProjectId, initService } from "./utils.js";
 import { PipelinesService, ProjectsService } from "@llamaindex/cloud/api";
 import { SentenceSplitter } from "@llamaindex/core/node-parser";
 import { getEnv } from "@llamaindex/env";
+import { OpenAIEmbedding } from "@llamaindex/openai";
 import { Settings } from "../Settings.js";
-import { OpenAIEmbedding } from "../embeddings/OpenAIEmbedding.js";
 
 export class LlamaCloudIndex {
   params: CloudConstructorParams;
@@ -38,10 +38,13 @@ export class LlamaCloudIndex {
     }
 
     while (true) {
-      const pipelineStatus =
+      const { data: pipelineStatus } =
         await PipelinesService.getPipelineStatusApiV1PipelinesPipelineIdStatusGet(
           {
-            pipelineId,
+            path: {
+              pipeline_id: pipelineId,
+            },
+            throwOnError: true,
           },
         );
 
@@ -90,9 +93,14 @@ export class LlamaCloudIndex {
       const docsToRemove = new Set<string>();
 
       for (const doc of pendingDocs) {
-        const { status } =
+        const {
+          data: { status },
+        } =
           await PipelinesService.getPipelineDocumentStatusApiV1PipelinesPipelineIdDocumentsDocumentIdStatusGet(
-            { pipelineId, documentId: doc },
+            {
+              path: { pipeline_id: pipelineId, document_id: doc },
+              throwOnError: true,
+            },
           );
 
         if (status === "NOT_STARTED" || status === "IN_PROGRESS") {
@@ -136,12 +144,16 @@ export class LlamaCloudIndex {
     name?: string,
     projectName?: string,
   ): Promise<string> {
-    const pipelines = await PipelinesService.searchPipelinesApiV1PipelinesGet({
-      projectId: await this.getProjectId(projectName),
-      pipelineName: name ?? this.params.name,
-    });
+    const { data: pipelines } =
+      await PipelinesService.searchPipelinesApiV1PipelinesGet({
+        path: {
+          project_id: await this.getProjectId(projectName),
+          project_name: name ?? this.params.name,
+        },
+        throwOnError: true,
+      });
 
-    return pipelines[0].id;
+    return pipelines[0]!.id;
   }
 
   public async getProjectId(
@@ -177,26 +189,37 @@ export class LlamaCloudIndex {
       transformations: params.transformations ?? defaultTransformations,
     });
 
-    const project = await ProjectsService.upsertProjectApiV1ProjectsPut({
-      organizationId: params.organizationId,
-      requestBody: {
-        name: params.projectName ?? "default",
-      },
-    });
+    const { data: project } =
+      await ProjectsService.upsertProjectApiV1ProjectsPut({
+        path: {
+          organization_id: params.organizationId,
+        },
+        body: {
+          name: params.projectName ?? "default",
+        },
+        throwOnError: true,
+      });
 
     if (!project.id) {
       throw new Error("Project ID should be defined");
     }
 
-    const pipeline = await PipelinesService.upsertPipelineApiV1PipelinesPut({
-      projectId: project.id,
-      requestBody: {
-        name: params.name,
-        configured_transformations:
-          pipelineCreateParams.configured_transformations,
-        pipeline_type: pipelineCreateParams.pipeline_type,
-      },
-    });
+    const { data: pipeline } =
+      await PipelinesService.upsertPipelineApiV1PipelinesPut({
+        path: {
+          project_id: project.id,
+        },
+        body: pipelineCreateParams.configured_transformations
+          ? {
+              name: params.name,
+              configured_transformations:
+                pipelineCreateParams.configured_transformations,
+            }
+          : {
+              name: params.name,
+            },
+        throwOnError: true,
+      });
 
     if (!pipeline.id) {
       throw new Error("Pipeline ID must be defined");
@@ -208,8 +231,10 @@ export class LlamaCloudIndex {
 
     await PipelinesService.upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut(
       {
-        pipelineId: pipeline.id,
-        requestBody: params.documents.map((doc) => ({
+        path: {
+          pipeline_id: pipeline.id,
+        },
+        body: params.documents.map((doc) => ({
           metadata: doc.metadata,
           text: doc.text,
           excluded_embed_metadata_keys: doc.excludedEmbedMetadataKeys,
@@ -220,10 +245,11 @@ export class LlamaCloudIndex {
     );
 
     while (true) {
-      const pipelineStatus =
+      const { data: pipelineStatus } =
         await PipelinesService.getPipelineStatusApiV1PipelinesPipelineIdStatusGet(
           {
-            pipelineId: pipeline.id,
+            path: { pipeline_id: pipeline.id },
+            throwOnError: true,
           },
         );
 
@@ -299,8 +325,10 @@ export class LlamaCloudIndex {
 
     await PipelinesService.createBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPost(
       {
-        pipelineId: pipelineId,
-        requestBody: [
+        path: {
+          pipeline_id: pipelineId,
+        },
+        body: [
           {
             metadata: document.metadata,
             text: document.text,
@@ -327,8 +355,10 @@ export class LlamaCloudIndex {
 
     await PipelinesService.deletePipelineDocumentApiV1PipelinesPipelineIdDocumentsDocumentIdDelete(
       {
-        pipelineId,
-        documentId: document.id_,
+        path: {
+          pipeline_id: pipelineId,
+          document_id: document.id_,
+        },
       },
     );
 
@@ -347,8 +377,10 @@ export class LlamaCloudIndex {
 
     await PipelinesService.upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut(
       {
-        pipelineId,
-        requestBody: [
+        path: {
+          pipeline_id: pipelineId,
+        },
+        body: [
           {
             metadata: document.metadata,
             text: document.text,

packages/llamaindex/src/cloud/LlamaCloudRetriever.ts

@@ -59,20 +59,27 @@ export class LlamaCloudRetriever implements BaseRetriever {
     query,
     preFilters,
   }: RetrieveParams): Promise<NodeWithScore[]> {
-    const pipelines = await PipelinesService.searchPipelinesApiV1PipelinesGet({
-      projectId: await getProjectId(this.projectName, this.organizationId),
-      pipelineName: this.pipelineName,
-    });
+    const { data: pipelines } =
+      await PipelinesService.searchPipelinesApiV1PipelinesGet({
+        query: {
+          project_id: await getProjectId(this.projectName, this.organizationId),
+          project_name: this.pipelineName,
+        },
+        throwOnError: true,
+      });
 
-    if (pipelines.length === 0 || !pipelines[0].id) {
+    if (pipelines.length === 0 || !pipelines[0]!.id) {
       throw new Error(
         `No pipeline found with name ${this.pipelineName} in project ${this.projectName}`,
       );
     }
 
-    const pipeline =
+    const { data: pipeline } =
       await PipelinesService.getPipelineApiV1PipelinesPipelineIdGet({
-        pipelineId: pipelines[0].id,
+        path: {
+          pipeline_id: pipelines[0]!.id,
+        },
+        throwOnError: true,
       });
 
     if (!pipeline) {
@@ -81,15 +88,18 @@ export class LlamaCloudRetriever implements BaseRetriever {
       );
     }
 
-    const results =
+    const { data: results } =
       await PipelinesService.runSearchApiV1PipelinesPipelineIdRetrievePost({
-        pipelineId: pipeline.id,
-        requestBody: {
+        throwOnError: true,
+        path: {
+          pipeline_id: pipeline.id,
+        },
+        body: {
           ...this.retrieveParams,
           query: extractText(query),
           search_filters:
             this.retrieveParams.filters ?? (preFilters as MetadataFilters),
-          dense_similarity_top_k: this.retrieveParams.similarityTopK,
+          dense_similarity_top_k: this.retrieveParams.similarityTopK!,
         },
       });
 

packages/llamaindex/src/cloud/config.ts

@@ -5,7 +5,7 @@ import type {
 } from "@llamaindex/cloud/api";
 import { SentenceSplitter } from "@llamaindex/core/node-parser";
 import { BaseNode, type TransformComponent } from "@llamaindex/core/schema";
-import { OpenAIEmbedding } from "../embeddings/OpenAIEmbedding.js";
+import { OpenAIEmbedding } from "@llamaindex/openai";
 
 export type GetPipelineCreateParams = {
   pipelineName: string;

packages/llamaindex/src/cloud/type.ts

@@ -1,10 +1,13 @@
 import type { ServiceContext } from "../ServiceContext.js";
 
-export type ClientParams = { apiKey?: string; baseUrl?: string };
+export type ClientParams = {
+  apiKey?: string | undefined;
+  baseUrl?: string | undefined;
+};
 
 export type CloudConstructorParams = {
   name: string;
   projectName: string;
-  organizationId?: string;
-  serviceContext?: ServiceContext;
+  organizationId?: string | undefined;
+  serviceContext?: ServiceContext | undefined;
 } & ClientParams;

packages/llamaindex/src/cloud/utils.ts

@@ -1,4 +1,4 @@
-import { OpenAPI, ProjectsService } from "@llamaindex/cloud/api";
+import { client, ProjectsService } from "@llamaindex/cloud/api";
 import { DEFAULT_BASE_URL } from "@llamaindex/core/global";
 import { getEnv } from "@llamaindex/env";
 import type { ClientParams } from "./type.js";
@@ -8,13 +8,26 @@ function getBaseUrl(baseUrl?: string): string {
 }
 
 export function getAppBaseUrl(): string {
-  return OpenAPI.BASE.replace(/api\./, "");
+  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 = {}) {
-  OpenAPI.TOKEN = apiKey ?? getEnv("LLAMA_CLOUD_API_KEY");
-  OpenAPI.BASE = getBaseUrl(baseUrl);
-  if (!OpenAPI.TOKEN) {
+  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;
+  });
+  if (!token) {
     throw new Error(
       "API Key is required for LlamaCloudIndex. Please pass the apiKey parameter",
     );
@@ -25,10 +38,15 @@ export async function getProjectId(
   projectName: string,
   organizationId?: string,
 ): Promise<string> {
-  const projects = await ProjectsService.listProjectsApiV1ProjectsGet({
-    projectName: projectName,
-    organizationId: organizationId,
-  });
+  const { data: projects } = await ProjectsService.listProjectsApiV1ProjectsGet(
+    {
+      path: {
+        project_name: projectName,
+        organization_id: organizationId,
+      },
+      throwOnError: true,
+    },
+  );
 
   if (projects.length === 0) {
     throw new Error(
@@ -40,7 +58,7 @@ export async function getProjectId(
     );
   }
 
-  const project = projects[0];
+  const project = projects[0]!;
 
   if (!project.id) {
     throw new Error(`No project found with name ${projectName}`);

packages/llamaindex/src/embeddings/DeepInfraEmbedding.ts

@@ -87,7 +87,7 @@ export class DeepInfraEmbedding extends BaseEmbedding {
   async getTextEmbedding(text: string): Promise<number[]> {
     const texts = mapPrefixWithInputs(this.textPrefix, [text]);
     const embeddings = await this.getDeepInfraEmbedding(texts);
-    return embeddings[0];
+    return embeddings[0]!;
   }
 
   async getQueryEmbedding(
@@ -97,7 +97,7 @@ export class DeepInfraEmbedding extends BaseEmbedding {
     if (text) {
       const queries = mapPrefixWithInputs(this.queryPrefix, [text]);
       const embeddings = await this.getDeepInfraEmbedding(queries);
-      return embeddings[0];
+      return embeddings[0]!;
     } else {
       return null;
     }

packages/llamaindex/src/embeddings/JinaAIEmbedding.ts

@@ -37,13 +37,13 @@ export class JinaAIEmbedding extends MultiModalEmbedding {
 
   async getTextEmbedding(text: string): Promise<number[]> {
     const result = await this.getJinaEmbedding({ input: [{ text }] });
-    return result.data[0].embedding;
+    return result.data[0]!.embedding;
   }
 
   async getImageEmbedding(image: ImageType): Promise<number[]> {
     const img = await this.getImageInput(image);
     const result = await this.getJinaEmbedding({ input: [img] });
-    return result.data[0].embedding;
+    return result.data[0]!.embedding;
   }
 
   // Retrieve multiple text embeddings in a single request
@@ -81,7 +81,7 @@ export class JinaAIEmbedding extends MultiModalEmbedding {
   ): Promise<{ bytes: string } | { url: string }> {
     if (isLocal(image) || image instanceof Blob) {
       const base64 = await imageToDataUrl(image);
-      const bytes = base64.split(",")[1];
+      const bytes = base64.split(",")[1]!;
       return { bytes };
     } else {
       return { url: image.toString() };

packages/llamaindex/src/embeddings/MixedbreadAIEmbeddings.ts

@@ -105,8 +105,10 @@ export class MixedbreadAIEmbeddings extends BaseEmbedding {
     }
 
     this.embedBatchSize = params?.embedBatchSize ?? 128;
-    this.embedInfo = params?.embedInfo;
-    this.requestParams = {
+    if (params?.embedInfo) {
+      this.embedInfo = params?.embedInfo;
+    }
+    this.requestParams = <EmbeddingsRequestWithoutInput>{
       model: params?.model ?? "mixedbread-ai/mxbai-embed-large-v1",
       normalized: params?.normalized,
       dimensions: params?.dimensions,
@@ -123,10 +125,16 @@ export class MixedbreadAIEmbeddings extends BaseEmbedding {
         "user-agent": "@mixedbread-ai/llamaindex-ts-sdk",
       },
     };
-    this.client = new MixedbreadAIClient({
-      apiKey,
-      environment: params?.baseUrl,
-    });
+    this.client = new MixedbreadAIClient(
+      params?.baseUrl
+        ? {
+            apiKey,
+            environment: params?.baseUrl,
+          }
+        : {
+            apiKey,
+          },
+    );
   }
 
   /**
@@ -140,7 +148,7 @@ export class MixedbreadAIEmbeddings extends BaseEmbedding {
    * console.log(result);
    */
   async getTextEmbedding(text: string): Promise<number[]> {
-    return (await this.getTextEmbeddings([text]))[0];
+    return (await this.getTextEmbeddings([text]))[0]!;
   }
 
   /**

packages/llamaindex/src/embeddings/MultiModalEmbedding.ts

@@ -39,7 +39,7 @@ export abstract class MultiModalEmbedding extends BaseEmbedding {
       _options,
     );
     for (let i = 0; i < textNodes.length; i++) {
-      textNodes[i].embedding = embeddings[i];
+      textNodes[i]!.embedding = embeddings[i];
     }
 
     const imageEmbeddings = await batchEmbeddings(
@@ -49,7 +49,7 @@ export abstract class MultiModalEmbedding extends BaseEmbedding {
       _options,
     );
     for (let i = 0; i < imageNodes.length; i++) {
-      imageNodes[i].embedding = imageEmbeddings[i];
+      imageNodes[i]!.embedding = imageEmbeddings[i];
     }
 
     return nodes;

packages/llamaindex/src/embeddings/OpenAIEmbedding.ts

@@ -1,146 +1 @@
-import { BaseEmbedding } from "@llamaindex/core/embeddings";
-import { Tokenizers } from "@llamaindex/env";
-import type { ClientOptions as OpenAIClientOptions } from "openai";
-import type { AzureOpenAIConfig } from "../llm/azure.js";
-import {
-  getAzureConfigFromEnv,
-  getAzureModel,
-  shouldUseAzure,
-} from "../llm/azure.js";
-import type { OpenAISession } from "../llm/openai.js";
-import { getOpenAISession } from "../llm/openai.js";
-
-export const ALL_OPENAI_EMBEDDING_MODELS = {
-  "text-embedding-ada-002": {
-    dimensions: 1536,
-    maxTokens: 8192,
-    tokenizer: Tokenizers.CL100K_BASE,
-  },
-  "text-embedding-3-small": {
-    dimensions: 1536,
-    dimensionOptions: [512, 1536],
-    maxTokens: 8192,
-    tokenizer: Tokenizers.CL100K_BASE,
-  },
-  "text-embedding-3-large": {
-    dimensions: 3072,
-    dimensionOptions: [256, 1024, 3072],
-    maxTokens: 8192,
-    tokenizer: Tokenizers.CL100K_BASE,
-  },
-};
-
-type ModelKeys = keyof typeof ALL_OPENAI_EMBEDDING_MODELS;
-
-export class OpenAIEmbedding extends BaseEmbedding {
-  /** embeddding model. defaults to "text-embedding-ada-002" */
-  model: string;
-  /** number of dimensions of the resulting vector, for models that support choosing fewer dimensions. undefined will default to model default */
-  dimensions: number | undefined;
-
-  // OpenAI session params
-
-  /** api key */
-  apiKey?: string = undefined;
-  /** maximum number of retries, default 10 */
-  maxRetries: number;
-  /** timeout in ms, default 60 seconds  */
-  timeout?: number;
-  /** other session options for OpenAI */
-  additionalSessionOptions?: Omit<
-    Partial<OpenAIClientOptions>,
-    "apiKey" | "maxRetries" | "timeout"
-  >;
-
-  /** session object */
-  session: OpenAISession;
-
-  /**
-   * OpenAI Embedding
-   * @param init - initial parameters
-   */
-  constructor(init?: Partial<OpenAIEmbedding> & { azure?: AzureOpenAIConfig }) {
-    super();
-
-    this.model = init?.model ?? "text-embedding-ada-002";
-    this.dimensions = init?.dimensions; // if no dimensions provided, will be undefined/not sent to OpenAI
-
-    this.embedBatchSize = init?.embedBatchSize ?? 10;
-    this.maxRetries = init?.maxRetries ?? 10;
-
-    this.timeout = init?.timeout ?? 60 * 1000; // Default is 60 seconds
-    this.additionalSessionOptions = init?.additionalSessionOptions;
-
-    // find metadata for model
-    const key = Object.keys(ALL_OPENAI_EMBEDDING_MODELS).find(
-      (key) => key === this.model,
-    ) as ModelKeys | undefined;
-    if (key) {
-      this.embedInfo = ALL_OPENAI_EMBEDDING_MODELS[key];
-    }
-
-    if (init?.azure || shouldUseAzure()) {
-      const azureConfig = {
-        ...getAzureConfigFromEnv({
-          model: getAzureModel(this.model),
-        }),
-        ...init?.azure,
-      };
-
-      this.apiKey = azureConfig.apiKey;
-      this.session =
-        init?.session ??
-        getOpenAISession({
-          azure: true,
-          maxRetries: this.maxRetries,
-          timeout: this.timeout,
-          ...this.additionalSessionOptions,
-          ...azureConfig,
-        });
-    } else {
-      this.apiKey = init?.apiKey ?? undefined;
-      this.session =
-        init?.session ??
-        getOpenAISession({
-          apiKey: this.apiKey,
-          maxRetries: this.maxRetries,
-          timeout: this.timeout,
-          ...this.additionalSessionOptions,
-        });
-    }
-  }
-
-  /**
-   * Get embeddings for a batch of texts
-   * @param texts
-   * @param options
-   */
-  private async getOpenAIEmbedding(input: string[]): Promise<number[][]> {
-    // TODO: ensure this for every sub class by calling it in the base class
-    input = this.truncateMaxTokens(input);
-
-    const { data } = await this.session.openai.embeddings.create({
-      model: this.model,
-      dimensions: this.dimensions, // only sent to OpenAI if set by user
-      input,
-    });
-
-    return data.map((d) => d.embedding);
-  }
-
-  /**
-   * Get embeddings for a batch of texts
-   * @param texts
-   */
-  getTextEmbeddings = async (texts: string[]): Promise<number[][]> => {
-    return this.getOpenAIEmbedding(texts);
-  };
-
-  /**
-   * Get embeddings for a single text
-   * @param texts
-   */
-  async getTextEmbedding(text: string): Promise<number[]> {
-    return (await this.getOpenAIEmbedding([text]))[0];
-  }
-}
+export * from "@llamaindex/openai";

packages/llamaindex/src/embeddings/fireworks.ts

@@ -1,5 +1,5 @@
 import { getEnv } from "@llamaindex/env";
-import { OpenAIEmbedding } from "./OpenAIEmbedding.js";
+import { OpenAIEmbedding } from "@llamaindex/openai";
 
 export class FireworksEmbedding extends OpenAIEmbedding {
   constructor(init?: Partial<OpenAIEmbedding>) {

packages/llamaindex/src/embeddings/together.ts

@@ -1,5 +1,5 @@
 import { getEnv } from "@llamaindex/env";
-import { OpenAIEmbedding } from "./OpenAIEmbedding.js";
+import { OpenAIEmbedding } from "@llamaindex/openai";
 
 export class TogetherEmbedding extends OpenAIEmbedding {
   constructor(init?: Partial<OpenAIEmbedding>) {

packages/llamaindex/src/engines/chat/ContextChatEngine.ts

@@ -38,16 +38,16 @@ export class ContextChatEngine extends PromptMixin implements ChatEngine {
   chatModel: LLM;
   chatHistory: ChatHistory;
   contextGenerator: ContextGenerator & PromptMixin;
-  systemPrompt?: string;
+  systemPrompt?: string | undefined;
 
   constructor(init: {
     retriever: BaseRetriever;
-    chatModel?: LLM;
-    chatHistory?: ChatMessage[];
-    contextSystemPrompt?: ContextSystemPrompt;
-    nodePostprocessors?: BaseNodePostprocessor[];
-    systemPrompt?: string;
-    contextRole?: MessageType;
+    chatModel?: LLM | undefined;
+    chatHistory?: ChatMessage[] | undefined;
+    contextSystemPrompt?: ContextSystemPrompt | undefined;
+    nodePostprocessors?: BaseNodePostprocessor[] | undefined;
+    systemPrompt?: string | undefined;
+    contextRole?: MessageType | undefined;
   }) {
     super();
     this.chatModel = init.chatModel ?? Settings.llm;

packages/llamaindex/src/engines/chat/DefaultContextGenerator.ts

@@ -23,10 +23,10 @@ export class DefaultContextGenerator
 
   constructor(init: {
     retriever: BaseRetriever;
-    contextSystemPrompt?: ContextSystemPrompt;
-    nodePostprocessors?: BaseNodePostprocessor[];
-    contextRole?: MessageType;
-    metadataMode?: MetadataMode;
+    contextSystemPrompt?: ContextSystemPrompt | undefined;
+    nodePostprocessors?: BaseNodePostprocessor[] | undefined;
+    contextRole?: MessageType | undefined;
+    metadataMode?: MetadataMode | undefined;
   }) {
     super();
 

packages/llamaindex/src/engines/query/RouterQueryEngine.ts

@@ -64,9 +64,9 @@ export class RouterQueryEngine extends PromptMixin implements QueryEngine {
   constructor(init: {
     selector: BaseSelector;
     queryEngineTools: RouterQueryEngineTool[];
-    serviceContext?: ServiceContext;
-    summarizer?: TreeSummarize;
-    verbose?: boolean;
+    serviceContext?: ServiceContext | undefined;
+    summarizer?: TreeSummarize | undefined;
+    verbose?: boolean | undefined;
   }) {
     super();
 
@@ -138,14 +138,14 @@ export class RouterQueryEngine extends PromptMixin implements QueryEngine {
     if (result.selections.length > 1) {
       const responses: EngineResponse[] = [];
       for (let i = 0; i < result.selections.length; i++) {
-        const engineInd = result.selections[i];
-        const logStr = `Selecting query engine ${engineInd.index}: ${result.selections[i].index}.`;
+        const engineInd = result.selections[i]!;
+        const logStr = `Selecting query engine ${engineInd.index}: ${result.selections[i]!.index}.`;
 
         if (this.verbose) {
           console.log(logStr + "\n");
         }
 
-        const selectedQueryEngine = this.queryEngines[engineInd.index];
+        const selectedQueryEngine = this.queryEngines[engineInd.index]!;
         responses.push(
           await selectedQueryEngine.query({
             query: extractText(query),
@@ -163,15 +163,15 @@ export class RouterQueryEngine extends PromptMixin implements QueryEngine {
 
         return finalResponse;
       } else {
-        return responses[0];
+        return responses[0]!;
       }
     } else {
       let selectedQueryEngine;
 
       try {
-        selectedQueryEngine = this.queryEngines[result.selections[0].index];
+        selectedQueryEngine = this.queryEngines[result.selections[0]!.index];
 
-        const logStr = `Selecting query engine ${result.selections[0].index}: ${result.selections[0].reason}`;
+        const logStr = `Selecting query engine ${result.selections[0]!.index}: ${result.selections[0]!.reason}`;
 
         if (this.verbose) {
           console.log(logStr + "\n");

packages/llamaindex/src/evaluation/Faithfulness.ts

@@ -22,16 +22,16 @@ export class FaithfulnessEvaluator
   extends PromptMixin
   implements BaseEvaluator
 {
-  private serviceContext?: ServiceContext;
+  private serviceContext?: ServiceContext | undefined;
   private raiseError: boolean;
   private evalTemplate: FaithfulnessTextQAPrompt;
   private refineTemplate: FaithfulnessRefinePrompt;
 
   constructor(params?: {
-    serviceContext?: ServiceContext;
-    raiseError?: boolean;
-    faithfulnessSystemPrompt?: FaithfulnessTextQAPrompt;
-    faithFulnessRefinePrompt?: FaithfulnessRefinePrompt;
+    serviceContext?: ServiceContext | undefined;
+    raiseError?: boolean | undefined;
+    faithfulnessSystemPrompt?: FaithfulnessTextQAPrompt | undefined;
+    faithFulnessRefinePrompt?: FaithfulnessRefinePrompt | undefined;
   }) {
     super();
     this.serviceContext = params?.serviceContext;

packages/llamaindex/src/evaluation/Relevancy.ts

@@ -16,14 +16,14 @@ import type {
 } from "./types.js";
 
 type RelevancyParams = {
-  serviceContext?: ServiceContext;
-  raiseError?: boolean;
-  evalTemplate?: RelevancyEvalPrompt;
-  refineTemplate?: RelevancyRefinePrompt;
+  serviceContext?: ServiceContext | undefined;
+  raiseError?: boolean | undefined;
+  evalTemplate?: RelevancyEvalPrompt | undefined;
+  refineTemplate?: RelevancyRefinePrompt | undefined;
 };
 
 export class RelevancyEvaluator extends PromptMixin implements BaseEvaluator {
-  private serviceContext?: ServiceContext;
+  private serviceContext?: ServiceContext | undefined;
   private raiseError: boolean;
 
   private evalTemplate: RelevancyEvalPrompt;

packages/llamaindex/src/evaluation/utils.ts

@@ -1,7 +1,7 @@
 export const defaultEvaluationParser = (
   evalResponse: string,
 ): [number, string] => {
-  const [scoreStr, reasoningStr] = evalResponse.split("\n");
+  const [scoreStr, reasoningStr] = evalResponse.split("\n") as [string, string];
   const score = parseFloat(scoreStr);
   const reasoning = reasoningStr.trim();
   return [score, reasoning];

packages/llamaindex/src/extractors/MetadataExtractors.ts

@@ -1,7 +1,7 @@
 import type { LLM } from "@llamaindex/core/llms";
 import type { BaseNode } from "@llamaindex/core/schema";
 import { MetadataMode, TextNode } from "@llamaindex/core/schema";
-import { OpenAI } from "../llm/index.js";
+import { OpenAI } from "@llamaindex/openai";
 import {
   defaultKeywordExtractorPromptTemplate,
   defaultQuestionAnswerPromptTemplate,
@@ -173,7 +173,7 @@ export class TitleExtractor extends BaseExtractor {
 
     return nodesToExtractTitle.map((node) => {
       return {
-        documentTitle: titlesByDocument[node.sourceNode?.nodeId ?? ""],
+        documentTitle: titlesByDocument[node.sourceNode?.nodeId ?? ""]!,
       };
     });
   }

packages/llamaindex/src/extractors/types.ts

@@ -52,20 +52,20 @@ export abstract class BaseExtractor extends TransformComponent {
     const curMetadataList = await this.extract(newNodes);
 
     for (const idx in newNodes) {
-      newNodes[idx].metadata = {
-        ...newNodes[idx].metadata,
+      newNodes[idx]!.metadata = {
+        ...newNodes[idx]!.metadata,
         ...curMetadataList[idx],
       };
     }
 
     for (const idx in newNodes) {
       if (excludedEmbedMetadataKeys) {
-        newNodes[idx].excludedEmbedMetadataKeys.concat(
+        newNodes[idx]!.excludedEmbedMetadataKeys.concat(
           excludedEmbedMetadataKeys,
         );
       }
       if (excludedLlmMetadataKeys) {
-        newNodes[idx].excludedLlmMetadataKeys.concat(excludedLlmMetadataKeys);
+        newNodes[idx]!.excludedLlmMetadataKeys.concat(excludedLlmMetadataKeys);
       }
       if (!this.disableTemplateRewrite) {
         if (newNodes[idx] instanceof TextNode) {

packages/llamaindex/src/index.edge.ts

@@ -30,6 +30,7 @@ export type {
   LLMToolCallEvent,
   LLMToolResultEvent,
 } from "@llamaindex/core/global";
+export * from "@llamaindex/core/indices";
 export * from "@llamaindex/core/llms";
 export * from "@llamaindex/core/prompts";
 export * from "@llamaindex/core/schema";
@@ -62,7 +63,6 @@ export * from "./nodeParsers/index.js";
 export * from "./objects/index.js";
 export * from "./OutputParser.js";
 export * from "./postprocessors/index.js";
-export * from "./PromptHelper.js";
 export * from "./QuestionGenerator.js";
 export * from "./Retriever.js";
 export * from "./selectors/index.js";

packages/llamaindex/src/index.ts

@@ -17,3 +17,7 @@ export { GeminiVertexSession } from "./llm/gemini/vertex.js";
 // Expose AzureDynamicSessionTool for node.js runtime only
 export { JinaAIEmbedding } from "./embeddings/JinaAIEmbedding.js";
 export { AzureDynamicSessionTool } from "./tools/AzureDynamicSessionTool.node.js";
+
+// Don't export vector store modules for non-node.js runtime on top level,
+//  as we cannot guarantee that they will work in other environments
+export * from "./vector-store.js";

packages/llamaindex/src/indices/BaseIndex.ts

@@ -43,10 +43,10 @@ export class KeywordTable extends IndexStruct {
 }
 
 export interface BaseIndexInit<T> {
-  serviceContext?: ServiceContext;
+  serviceContext?: ServiceContext | undefined;
   storageContext: StorageContext;
   docStore: BaseDocumentStore;
-  indexStore?: BaseIndexStore;
+  indexStore?: BaseIndexStore | undefined;
   indexStruct: T;
 }
 
@@ -55,10 +55,10 @@ export interface BaseIndexInit<T> {
  * they can be retrieved for our queries.
  */
 export abstract class BaseIndex<T> {
-  serviceContext?: ServiceContext;
+  serviceContext?: ServiceContext | undefined;
   storageContext: StorageContext;
   docStore: BaseDocumentStore;
-  indexStore?: BaseIndexStore;
+  indexStore?: BaseIndexStore | undefined;
   indexStruct: T;
 
   constructor(init: BaseIndexInit<T>) {