Release 0.3.17 (#920)

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

.eslintrc.cjs

@@ -1,3 +1,5 @@
+const { join } = require("node:path");
+
 module.exports = {
   root: true,
   extends: [
@@ -6,7 +8,7 @@ module.exports = {
     "plugin:@typescript-eslint/recommended-type-checked-only",
   ],
   parserOptions: {
-    project: true,
+    project: join(__dirname, "tsconfig.eslint.json"),
     __tsconfigRootDir: __dirname,
   },
   settings: {
@@ -23,6 +25,7 @@ module.exports = {
         ignoreIIFE: true,
       },
     ],
+    "no-debugger": "error",
     "@typescript-eslint/await-thenable": "off",
     "@typescript-eslint/ban-ts-comment": "off",
     "@typescript-eslint/ban-types": "off",

apps/docs/CHANGELOG.md

@@ -1,5 +1,14 @@
 # docs
 
+## 0.0.25
+
+### Patch Changes
+
+- Updated dependencies [6bc5bdd]
+- Updated dependencies [bf25ff6]
+- Updated dependencies [e6d6576]
+  - llamaindex@0.3.17
+
 ## 0.0.24
 
 ### Patch Changes

apps/docs/docs/modules/evaluation/modules/correctness.md

@@ -21,7 +21,7 @@ export OPENAI_API_KEY=your-api-key
 Import the required modules:
 
 ```ts
-import { CorrectnessEvaluator, OpenAI, Settings } from "llamaindex";
+import { CorrectnessEvaluator, OpenAI, Settings, Response } from "llamaindex";
 ```
 
 Let's setup gpt-4 for better results:
@@ -45,7 +45,7 @@ const evaluator = new CorrectnessEvaluator();
 
 const result = await evaluator.evaluateResponse({
   query,
-  response,
+  response: new Response(response),
 });
 
 console.log(

apps/docs/docs/modules/evaluation/modules/relevancy.md

@@ -21,7 +21,13 @@ export OPENAI_API_KEY=your-api-key
 Import the required modules:
 
 ```ts
-import { RelevancyEvaluator, OpenAI, Settings } from "llamaindex";
+import {
+  RelevancyEvaluator,
+  OpenAI,
+  Settings,
+  Document,
+  VectorStoreIndex,
+} from "llamaindex";
 ```
 
 Let's setup gpt-4 for better results:

apps/docs/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docs",
-  "version": "0.0.24",
+  "version": "0.0.25",
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",

examples/agent/large_toolcall_with_gpt4o.ts

@@ -0,0 +1,74 @@
+import { FunctionTool, OpenAI, ToolCallOptions } from "llamaindex";
+
+(async () => {
+  // The tool call will generate a partial JSON for `gpt-4-turbo`
+  // See thread: https://community.openai.com/t/gpt-4o-doesnt-consistently-respect-json-schema-on-tool-use/751125/7
+
+  const models = ["gpt-4o", "gpt-4-turbo"];
+  for (const model of models) {
+    const validJSON = await callLLM({ model });
+    console.log(
+      `LLM call resulting in large tool input with '${model}': LLM generates ${validJSON ? "valid" : "invalid"} JSON.`,
+    );
+  }
+})();
+
+async function callLLM(init: Partial<OpenAI>) {
+  const csvData =
+    "Country,Average Height (cm)\nNetherlands,156\nDenmark,158\nNorway,160";
+
+  const userQuestion = "Describe data in this csv";
+
+  // fake code interpreter tool
+  const interpreterTool = FunctionTool.from(
+    ({ code }: { code: string }) => code,
+    {
+      name: "interpreter",
+      description:
+        "Execute python code in a Jupyter notebook cell and return any result, stdout, stderr, display_data, and error.",
+      parameters: {
+        type: "object",
+        properties: {
+          code: {
+            type: "string",
+            description: "The python code to execute in a single cell.",
+          },
+        },
+        required: ["code"],
+      },
+    },
+  );
+
+  const systemPrompt =
+    "You are a Python interpreter.\n- You are given tasks to complete and you run python code to solve them.\n- The python code runs in a Jupyter notebook. Every time you call $(interpreter) tool, the python code is executed in a separate cell. It's okay to make multiple calls to $(interpreter).\n- Display visualizations using matplotlib or any other visualization library directly in the notebook. Shouldn't save the visualizations to a file, just return the base64 encoded data.\n- You can install any pip package (if it exists) if you need to but the usual packages for data analysis are already preinstalled.\n- You can run any python code you want in a secure environment.";
+
+  const llm = new OpenAI(init);
+  const response = await llm.chat({
+    tools: [interpreterTool],
+    messages: [
+      { role: "system", content: systemPrompt },
+      {
+        role: "user",
+        content: [
+          {
+            type: "text",
+            text: userQuestion,
+          },
+          {
+            type: "text",
+            text: `Use data from following CSV raw contents:\n${csvData}`,
+          },
+        ],
+      },
+    ],
+  });
+
+  const options = response.message?.options as ToolCallOptions;
+  const input = options.toolCall[0].input as string;
+  try {
+    JSON.parse(input);
+    return true;
+  } catch {
+    return false;
+  }
+}

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

@@ -1,5 +1,15 @@
 # @llamaindex/autotool-02-next-example
 
+## 0.1.9
+
+### Patch Changes
+
+- Updated dependencies [6bc5bdd]
+- Updated dependencies [bf25ff6]
+- Updated dependencies [e6d6576]
+  - llamaindex@0.3.17
+  - @llamaindex/autotool@0.0.1
+
 ## 0.1.8
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool-02-next-example",
   "private": true,
-  "version": "0.1.8",
+  "version": "0.1.9",
   "scripts": {
     "dev": "next dev",
     "build": "next build",

packages/autotool/package.json

@@ -51,7 +51,7 @@
     "unplugin": "^1.10.1"
   },
   "peerDependencies": {
-    "llamaindex": "^0.3.16",
+    "llamaindex": "^0.3.17",
     "openai": "^4",
     "typescript": "^4"
   },

packages/community/.cjs.swcrc

@@ -1,12 +0,0 @@
-{
-  "jsc": {
-    "parser": {
-      "syntax": "typescript"
-    },
-    "target": "esnext"
-  },
-  "module": {
-    "type": "commonjs",
-    "ignoreDynamic": true
-  }
-}

packages/community/.swcrc

@@ -1,8 +0,0 @@
-{
-  "jsc": {
-    "parser": {
-      "syntax": "typescript"
-    },
-    "target": "esnext"
-  }
-}

packages/community/CHANGELOG.md

@@ -1,5 +1,14 @@
 # @llamaindex/community
 
+## 0.0.3
+
+### Patch Changes
+
+- Updated dependencies [6bc5bdd]
+- Updated dependencies [bf25ff6]
+- Updated dependencies [e6d6576]
+  - llamaindex@0.3.17
+
 ## 0.0.2
 
 ### Patch Changes

packages/community/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.2",
+  "version": "0.0.3",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",
@@ -13,23 +13,24 @@
       },
       "require": {
         "types": "./dist/type/index.d.ts",
-        "default": "./dist/cjs/index.js"
+        "default": "./dist/index.cjs"
       }
     },
-    "./*": {
+    "./llm/bedrock": {
       "import": {
-        "types": "./dist/type/*.d.ts",
-        "default": "./dist/*.js"
+        "types": "./dist/type/llm/bedrock.d.ts",
+        "default": "./dist/llm/bedrock/base.js"
       },
       "require": {
-        "types": "./dist/type/*.d.ts",
-        "default": "./dist/cjs/*.js"
+        "types": "./dist/type/llm/bedrock.d.ts",
+        "default": "./dist/llm/bedrock/base.cjs"
       }
     }
   },
   "files": [
     "dist",
-    "CHANGELOG.md"
+    "CHANGELOG.md",
+    "!**/*.tsbuildinfo"
   ],
   "repository": {
     "type": "git",
@@ -37,23 +38,20 @@
     "directory": "packages/community"
   },
   "scripts": {
-    "lint": "eslint .",
-    "build": "rm -rf ./dist && pnpm run build:esm && pnpm run build:cjs && pnpm run build:type",
-    "build:esm": "swc src -d dist --strip-leading-paths --config-file ../../.swcrc",
-    "build:cjs": "swc src -d dist/cjs --strip-leading-paths --config-file ../../.cjs.swcrc",
+    "build": "rm -rf ./dist && pnpm run build:code && pnpm run build:type",
+    "build:code": "tsup",
     "build:type": "tsc -p tsconfig.json",
-    "postbuild": "node -e \"require('fs').writeFileSync('./dist/cjs/package.json', JSON.stringify({ type: 'commonjs' }))\"",
     "dev": "concurrently \"pnpm run build:esm --watch\" \"pnpm run build:cjs --watch\" \"pnpm run build:type --watch\""
   },
   "devDependencies": {
     "@swc/cli": "^0.3.12",
     "@swc/core": "^1.5.5",
     "concurrently": "^8.2.2",
-    "pathe": "^1.1.2"
+    "tsup": "^8.1.0"
   },
   "dependencies": {
     "@aws-sdk/client-bedrock-runtime": "^3.582.0",
-    "@types/node": "^20.12.11",
+    "@types/node": "^20.14.2",
     "llamaindex": "workspace:*"
   }
 }

packages/community/tsconfig.json

@@ -5,8 +5,8 @@
     "outDir": "./dist/type",
     "tsBuildInfoFile": "./dist/.tsbuildinfo",
     "emitDeclarationOnly": true,
-    "module": "node16",
-    "moduleResolution": "node16",
+    "module": "ESNext",
+    "moduleResolution": "bundler",
     "types": ["node"]
   },
   "include": ["./src"],

packages/community/tsconfig.script.json

@@ -0,0 +1,9 @@
+{
+  "extends": "../../tsconfig.json",
+  "compilerOptions": {
+    "outDir": "./dist/script/type",
+    "tsBuildInfoFile": "./dist/script/.tsbuildinfo",
+    "emitDeclarationOnly": true
+  },
+  "include": ["./tsup.config.ts"]
+}

packages/community/tsup.config.ts

@@ -0,0 +1,9 @@
+import { defineConfig } from "tsup";
+
+export default defineConfig([
+  {
+    entry: ["src/index.ts", "src/llm/bedrock/base.ts"],
+    format: ["cjs", "esm"],
+    sourcemap: true,
+  },
+]);

packages/core/CHANGELOG.md

@@ -1,5 +1,13 @@
 # llamaindex
 
+## 0.3.17
+
+### Patch Changes
+
+- 6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page seperator to LlamaParseReader
+- bf25ff6: fix: polyfill for cloudflare worker
+- e6d6576: chore: use `unpdf`
+
 ## 0.3.16
 
 ### Patch Changes

packages/core/e2e/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/core-e2e
 
+## 0.0.7
+
+### Patch Changes
+
+- bf25ff6: fix: polyfill for cloudflare worker
+
 ## 0.0.6
 
 ### Patch Changes

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

@@ -1,5 +1,15 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.18
+
+### Patch Changes
+
+- bf25ff6: fix: polyfill for cloudflare worker
+- Updated dependencies [6bc5bdd]
+- Updated dependencies [bf25ff6]
+- Updated dependencies [e6d6576]
+  - llamaindex@0.3.17
+
 ## 0.0.17
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.17",
+  "version": "0.0.18",
   "type": "module",
   "private": true,
   "scripts": {
@@ -12,13 +12,13 @@
     "cf-typegen": "wrangler types"
   },
   "devDependencies": {
-    "@cloudflare/vitest-pool-workers": "^0.2.6",
-    "@cloudflare/workers-types": "^4.20240502.0",
+    "@cloudflare/vitest-pool-workers": "^0.4.3",
+    "@cloudflare/workers-types": "^4.20240605.0",
     "@vitest/runner": "1.3.0",
     "@vitest/snapshot": "1.3.0",
     "typescript": "^5.4.5",
     "vitest": "1.3.0",
-    "wrangler": "^3.53.1"
+    "wrangler": "^3.60.1"
   },
   "dependencies": {
     "llamaindex": "workspace:*"

packages/core/e2e/examples/cloudflare-worker-agent/src/index.ts

@@ -10,10 +10,12 @@ export default {
     const agent = new OpenAIAgent({
       tools: [],
     });
+    console.log(1);
     const responseStream = await agent.chat({
       stream: true,
       message: "Hello? What is the weather today?",
     });
+    console.log(2);
     const textEncoder = new TextEncoder();
     const response = responseStream.pipeThrough<Uint8Array>(
       // @ts-expect-error: see https://github.com/cloudflare/workerd/issues/2067

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

@@ -1,5 +1,14 @@
 # @llamaindex/next-agent-test
 
+## 0.1.18
+
+### Patch Changes
+
+- Updated dependencies [6bc5bdd]
+- Updated dependencies [bf25ff6]
+- Updated dependencies [e6d6576]
+  - llamaindex@0.3.17
+
 ## 0.1.17
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.17",
+  "version": "0.1.18",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,14 @@
 # test-edge-runtime
 
+## 0.1.17
+
+### Patch Changes
+
+- Updated dependencies [6bc5bdd]
+- Updated dependencies [bf25ff6]
+- Updated dependencies [e6d6576]
+  - llamaindex@0.3.17
+
 ## 0.1.16
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.16",
+  "version": "0.1.17",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,14 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [6bc5bdd]
+- Updated dependencies [bf25ff6]
+- Updated dependencies [e6d6576]
+  - llamaindex@0.3.17
+
 ## 0.0.17
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.17",
+  "version": "0.0.18",
   "type": "module",
   "private": true,
   "scripts": {

packages/core/e2e/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core-e2e",
   "private": true,
-  "version": "0.0.6",
+  "version": "0.0.7",
   "type": "module",
   "scripts": {
     "e2e": "node --import tsx --import ./mock-register.js --test ./node/*.e2e.ts",

packages/core/jsr.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/core",
-  "version": "0.3.16",
+  "version": "0.3.17",
   "exports": "./src/index.ts",
   "imports": {
     "@llamaindex/env": "jsr:@llamaindex/env@0.1.3"

packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.3.16",
+  "version": "0.3.17",
   "expectedMinorVersion": "3",
   "license": "MIT",
   "type": "module",
@@ -52,18 +52,23 @@
     "openai": "^4.48.1",
     "papaparse": "^5.4.1",
     "pathe": "^1.1.2",
-    "pdf2json": "3.1.3",
     "pg": "^8.12.0",
     "pgvector": "^0.1.8",
     "portkey-ai": "^0.1.16",
     "rake-modified": "^1.0.8",
     "string-strip-html": "^13.4.8",
+    "unpdf": "^0.10.1",
     "wikipedia": "^2.1.2",
     "wink-nlp": "^2.3.0"
   },
   "peerDependencies": {
     "@notionhq/client": "^2.2.15"
   },
+  "peerDependenciesMeta": {
+    "@notionhq/client": {
+      "optional": true
+    }
+  },
   "devDependencies": {
     "@notionhq/client": "^2.2.15",
     "@swc/cli": "^0.3.12",
@@ -136,7 +141,8 @@
   "files": [
     "dist",
     "CHANGELOG.md",
-    "examples"
+    "examples",
+    "!**/*.tsbuildinfo"
   ],
   "repository": {
     "type": "git",

packages/core/src/agent/openai.ts

@@ -103,7 +103,6 @@ export class OpenAIAgent extends AgentRunner<OpenAI> {
         }
       }
     } else {
-      debugger;
       const responseChunkStream = new ReadableStream<
         ChatResponseChunk<ToolCallLLMMessageOptions>
       >({

packages/core/src/embeddings/CloudflareWorkerEmbedding.ts

@@ -0,0 +1,14 @@
+import type { ImageType } from "../Node.js";
+import { MultiModalEmbedding } from "./MultiModalEmbedding.js";
+
+/**
+ * Cloudflare worker doesn't support image embeddings for now
+ */
+export class CloudflareWorkerMultiModalEmbedding extends MultiModalEmbedding {
+  getImageEmbedding(images: ImageType): Promise<number[]> {
+    throw new Error("Method not implemented.");
+  }
+  getTextEmbedding(text: string): Promise<number[]> {
+    throw new Error("Method not implemented.");
+  }
+}

packages/core/src/internal/settings/image-embed-model.ts

@@ -0,0 +1,8 @@
+export async function getImageEmbedModel() {
+  if (globalThis.navigator?.userAgent === "Cloudflare-Workers") {
+    return (await import("../../embeddings/CloudflareWorkerEmbedding.js"))
+      .CloudflareWorkerMultiModalEmbedding;
+  } else {
+    return (await import("../../embeddings/ClipEmbedding.js")).ClipEmbedding;
+  }
+}

packages/core/src/readers/LlamaParseReader.ts

@@ -110,22 +110,30 @@ export class LlamaParseReader extends FileReader {
   apiKey: string;
   // The base URL of the Llama Parsing API.
   baseUrl: string = "https://api.cloud.llamaindex.ai/api/parsing";
-  // The maximum timeout in seconds to wait for the parsing to finish.
-  maxTimeout = 2000;
-  // The interval in seconds to check if the parsing is done.
-  checkInterval = 1;
-  // Whether to print the progress of the parsing.
-  verbose = true;
   // The result type for the parser.
   resultType: ResultType = "text";
+  // The interval in seconds to check if the parsing is done.
+  checkInterval = 1;
+  // The maximum timeout in seconds to wait for the parsing to finish.
+  maxTimeout = 2000;
+  // Whether to print the progress of the parsing.
+  verbose = true;
   // The language of the text to parse.
   language: Language = "en";
-  // The parsing instruction for the parser.
-  parsingInstruction: string = "";
-  // If set to true, the parser will ignore diagonal text (when the text rotation in degrees modulo 90 is not 0).
-  skipDiagonalText: boolean = false;
-  // If set to true, the cache will be ignored and the document re-processes. All document are kept in cache for 48hours after the job was completed to avoid processing the same document twice.
-  invalidateCache: boolean = false;
+  // The parsing instruction for the parser. Backend default is an empty string.
+  parsingInstruction?: string;
+  // Wether to ignore diagonal text (when the text rotation in degrees is not 0, 90, 180 or 270, so not a horizontal or vertical text). Backend default is false.
+  skipDiagonalText?: boolean;
+  // Wheter to ignore the cache and re-process the document. All documents are kept in cache for 48hours after the job was completed to avoid processing the same document twice. Backend default is false.
+  invalidateCache?: boolean;
+  // Wether the document should not be cached in the first place. Backend default is false.
+  doNotCache?: boolean;
+  // Wether to use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction. Note: Non-compatible with gpt4oMode. Backend default is false.
+  fastMode?: boolean;
+  // Wether to keep column in the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most cases.
+  doNotUnrollColumns?: boolean;
+  // The page separator to use to split the text. Default is None, which means the parser will use the default separator '\\n---\\n'.
+  pageSeperator?: string;
   // Whether to use gpt-4o to extract text from documents.
   gpt4oMode: boolean = false;
   // The API key for the GPT-4o API. Optional, lowers the cost of parsing. Can be set as an env variable: LLAMA_CLOUD_GPT4O_API_KEY.
@@ -162,14 +170,26 @@ export class LlamaParseReader extends FileReader {
 
     const body = new FormData();
     body.set("file", new Blob([data], { type: mimeType }));
-    body.append("language", this.language);
-    body.append("parsing_instruction", this.parsingInstruction);
-    body.append("skip_diagonal_text", this.skipDiagonalText.toString());
-    body.append("invalidate_cache", this.invalidateCache.toString());
-    body.append("gpt4o_mode", this.gpt4oMode.toString());
-    if (this.gpt4oMode && this.gpt4oApiKey) {
-      body.append("gpt4o_api_key", this.gpt4oApiKey);
-    }
+
+    const LlamaParseBodyParams = {
+      language: this.language,
+      parsing_instruction: this.parsingInstruction,
+      skip_diagonal_text: this.skipDiagonalText?.toString(),
+      invalidate_cache: this.invalidateCache?.toString(),
+      do_not_cache: this.doNotCache?.toString(),
+      fast_mode: this.fastMode?.toString(),
+      do_not_unroll_columns: this.doNotUnrollColumns?.toString(),
+      page_seperator: this.pageSeperator,
+      gpt4o_mode: this.gpt4oMode?.toString(),
+      gpt4o_api_key: this.gpt4oApiKey,
+    };
+
+    // Appends body with any defined LlamaParseBodyParams
+    Object.entries(LlamaParseBodyParams).forEach(([key, value]) => {
+      if (value !== undefined) {
+        body.append(key, value);
+      }
+    });
 
     const headers = {
       Authorization: `Bearer ${this.apiKey}`,

packages/core/src/readers/PDFReader.ts

@@ -1,3 +1,4 @@
+import { fs } from "@llamaindex/env";
 import { Document } from "../Node.js";
 import { FileReader } from "./type.js";
 
@@ -5,29 +6,30 @@ import { FileReader } from "./type.js";
  * Read the text of a PDF
  */
 export class PDFReader extends FileReader {
-  async loadDataAsContent(fileContent: Buffer): Promise<Document[]> {
-    const pages = await readPDF(fileContent);
-    return pages.map((text, page) => {
+  async loadData(file: string): Promise<Document[]> {
+    const content = await fs.readFile(file);
+    return this.loadDataAsContent(new Uint8Array(content.buffer));
+  }
+
+  async loadDataAsContent(content: Uint8Array): Promise<Document[]> {
+    const { totalPages, text } = await readPDF(content);
+    return text.map((text, page) => {
       const metadata = {
         page_number: page + 1,
+        total_pages: totalPages,
       };
       return new Document({ text, metadata });
     });
   }
 }
 
-async function readPDF(data: Buffer): Promise<string[]> {
-  const parser = await import("pdf2json").then(
-    ({ default: Pdfparser }) => new Pdfparser(null, true),
-  );
-  const text = await new Promise<string>((resolve, reject) => {
-    parser.on("pdfParser_dataError", (error) => {
-      reject(error);
-    });
-    parser.on("pdfParser_dataReady", () => {
-      resolve((parser as any).getRawTextContent() as string);
-    });
-    parser.parseBuffer(data);
-  });
-  return text.split(/----------------Page \(\d+\) Break----------------/g);
+async function readPDF(data: Uint8Array): Promise<{
+  totalPages: number;
+  text: string[];
+}> {
+  const { extractText } = await import("unpdf");
+  return (await extractText(data)) as {
+    totalPages: number;
+    text: string[];
+  };
 }

packages/core/src/storage/StorageContext.ts

@@ -1,6 +1,6 @@
 import { path } from "@llamaindex/env";
 import { ModalityType, ObjectType } from "../Node.js";
-import { ClipEmbedding } from "../embeddings/ClipEmbedding.js";
+import { getImageEmbedModel } from "../internal/settings/image-embed-model.js";
 import {
   DEFAULT_IMAGE_VECTOR_NAMESPACE,
   DEFAULT_NAMESPACE,
@@ -44,7 +44,7 @@ export async function storageContextFromDefaults({
     }
     if (storeImages && !(ModalityType.IMAGE in vectorStores)) {
       vectorStores[ModalityType.IMAGE] = new SimpleVectorStore({
-        embedModel: new ClipEmbedding(),
+        embedModel: new (await getImageEmbedModel())(),
       });
     }
   } else {
@@ -60,7 +60,7 @@ export async function storageContextFromDefaults({
     if (storeImages && !(ObjectType.IMAGE in vectorStores)) {
       vectorStores[ModalityType.IMAGE] = await SimpleVectorStore.fromPersistDir(
         path.join(persistDir, DEFAULT_IMAGE_VECTOR_NAMESPACE),
-        new ClipEmbedding(),
+        new (await getImageEmbedModel())(),
       );
     }
   }

packages/core/tests/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/core-test
 
+## 0.0.4
+
+### Patch Changes
+
+- e6d6576: chore: use `unpdf`
+
 ## 0.0.3
 
 ### Patch Changes

packages/core/tests/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core-test",
   "private": true,
-  "version": "0.0.3",
+  "version": "0.0.4",
   "type": "module",
   "scripts": {
     "test": "vitest run"

packages/core/tests/readers/.snap/basic.pdf.snap

@@ -0,0 +1,95 @@
+Sample PDF
+
+This is a simple PDF file. Fun fun fun.
+
+Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Phasellus facilisis odio sed mi.
+
+Curabitur suscipit. Nullam vel nisi. Etiam semper ipsum ut lectus. Proin aliquam, erat eget
+
+pharetra commodo, eros mi condimentum quam, sed commodo justo quam ut velit.
+
+Integer
+ 
+a
+ 
+erat.
+ 
+Cras
+ 
+laoreet
+ 
+ligula
+ 
+cursus
+ 
+enim.
+ 
+Aenean
+ 
+scelerisque
+ 
+velit
+ 
+et
+ 
+tellus.
+
+Vestibulum dictum aliquet sem. Nulla facilisi. Vestibulum accumsan ante vitae elit. Nulla
+
+erat dolor, blandit in, rutrum quis, semper pulvinar, enim. Nullam varius congue risus.
+
+Vivamus sollicitudin, metus ut interdum eleifend, nisi tellus pellentesque elit, tristique
+
+accumsan eros quam et risus. Suspendisse libero odio, mattis sit amet, aliquet eget,
+
+hendrerit vel, nulla. Sed vitae augue. Aliquam erat volutpat. Aliquam feugiat vulputate nisl.
+
+Suspendisse quis nulla pretium ante pretium mollis. Proin velit ligula, sagittis at, egestas a,
+
+pulvinar quis, nisl.
+
+Pellentesque sit amet lectus. Praesent pulvinar, nunc quis iaculis sagittis, justo quam
+
+lobortis tortor, sed vestibulum dui metus venenatis est. Nunc cursus ligula. Nulla facilisi.
+
+Phasellus ullamcorper consectetuer ante. Duis tincidunt, urna id condimentum luctus, nibh
+
+ante vulputate sapien, id sagittis massa orci ut enim. Pellentesque vestibulum convallis
+
+sem. Nulla consequat quam ut nisl. Nullam est. Curabitur tincidunt dapibus lorem. Proin
+
+velit turpis, scelerisque sit amet, iaculis nec, rhoncus ac, ipsum. Phasellus lorem arcu,
+
+feugiat eu, gravida eu, consequat molestie, ipsum. Nullam vel est ut ipsum volutpat
+
+feugiat. Aenean pellentesque.
+
+In mauris. Pellentesque dui nisi, iaculis eu, rhoncus in, venenatis ac, ante. Ut odio justo,
+
+scelerisque vel, facilisis non, commodo a, pede. Cras nec massa sit amet tortor volutpat
+
+varius. Donec lacinia, neque a luctus aliquet, pede massa imperdiet ante, at varius lorem
+
+pede sed sapien. Fusce erat nibh, aliquet in, eleifend eget, commodo eget, erat. Fusce
+
+consectetuer. Cras risus tortor, porttitor nec, tristique sed, convallis semper, eros. Fusce
+
+vulputate ipsum a mauris. Phasellus mollis. Curabitur sed urna. Aliquam nec sapien non
+
+nibh pulvinar convallis. Vivamus facilisis augue quis quam. Proin cursus aliquet metus.
+
+Suspendisse lacinia. Nulla at tellus ac turpis eleifend scelerisque. Maecenas a pede vitae
+
+enim commodo interdum. Donec odio. Sed sollicitudin dui vitae justo.
+
+Morbi elit nunc, facilisis a, mollis a, molestie at, lectus. Suspendisse eget mauris eu tellus
+
+molestie cursus. Duis ut magna at justo dignissim condimentum. Cum sociis natoque
+
+penatibus et magnis dis parturient montes, nascetur ridiculus mus. Vivamus varius. Ut sit
+
+amet diam suscipit mauris ornare aliquam. Sed varius. Duis arcu. Etiam tristique massa
+
+eget dui. Phasellus congue. Aenean est erat, tincidunt eget, venenatis quis, commodo at,
+
+quam.

packages/core/tests/readers/pdf-reader.test.ts

@@ -0,0 +1,27 @@
+import { PDFReader } from "llamaindex";
+import { describe, expect, test } from "vitest";
+
+describe("pdf reader", () => {
+  const reader = new PDFReader();
+  test("basic.pdf", async () => {
+    const documents = await reader.loadData("../../../examples/data/basic.pdf");
+    expect(documents.length).toBe(1);
+    expect(documents[0].metadata).toEqual({
+      page_number: 1,
+      total_pages: 1,
+    });
+    await expect(documents[0].text).toMatchFileSnapshot(
+      "./.snap/basic.pdf.snap",
+    );
+  });
+  test("brk-2022.pdf", async () => {
+    const documents = await reader.loadData(
+      "../../../examples/data/brk-2022.pdf",
+    );
+    expect(documents.length).toBe(140);
+  });
+  test("manga.pdf", async () => {
+    const documents = await reader.loadData("../../../examples/data/manga.pdf");
+    expect(documents.length).toBe(4);
+  });
+});

packages/env/package.json

@@ -48,7 +48,8 @@
   },
   "files": [
     "dist",
-    "CHANGELOG.md"
+    "CHANGELOG.md",
+    "!**/*.tsbuildinfo"
   ],
   "repository": {
     "type": "git",

packages/experimental/CHANGELOG.md

@@ -1,5 +1,14 @@
 # @llamaindex/experimental
 
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [6bc5bdd]
+- Updated dependencies [bf25ff6]
+- Updated dependencies [e6d6576]
+  - llamaindex@0.3.17
+
 ## 0.0.33
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.33",
+  "version": "0.0.34",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",
@@ -37,7 +37,8 @@
   },
   "files": [
     "dist",
-    "CHANGELOG.md"
+    "CHANGELOG.md",
+    "!**/*.tsbuildinfo"
   ],
   "repository": {
     "type": "git",

packages/wasm-tools/package.json

@@ -42,7 +42,8 @@
   },
   "files": [
     "dist",
-    "CHANGELOG.md"
+    "CHANGELOG.md",
+    "!**/*.tsbuildinfo"
   ],
   "repository": {
     "type": "git",

tsconfig.eslint.json

@@ -0,0 +1,8 @@
+{
+  "extends": "./tsconfig.json",
+  "compilerOptions": {
+    "allowJs": true
+  },
+  "include": ["."],
+  "exclude": ["**/node_modules", "**/dist", "**/lib"]
+}

tsconfig.json

@@ -20,6 +20,12 @@
     {
       "path": "./apps/docs/tsconfig.json"
     },
+    {
+      "path": "./packages/community/tsconfig.json"
+    },
+    {
+      "path": "./packages/community/tsconfig.script.json"
+    },
     {
       "path": "./packages/core/tsconfig.json"
     },