Release 0.2.11 (#765)

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

.changeset/clever-dodos-judge.md

@@ -1,6 +0,0 @@
----
-"llamaindex": patch
-"@llamaindex/edge": patch
----
-
-refactor: use ollama official sdk

.changeset/smooth-zoos-whisper.md

@@ -1,6 +0,0 @@
----
-"llamaindex": patch
-"@llamaindex/edge": patch
----
-
-feat: support output to json format

.github/workflows/lint_on_push_or_pull.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:

.github/workflows/publish.yml

@@ -14,7 +14,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:

.github/workflows/release.yml

@@ -0,0 +1,57 @@
+name: Release
+
+on:
+  push:
+    branches:
+      - main
+
+concurrency: ${{ github.workflow }}-${{ github.ref }}
+
+jobs:
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v3
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "pnpm"
+
+      - name: Install dependencies
+        run: pnpm install
+
+      - name: Add auth token to .npmrc file
+        run: |
+          cat << EOF >> ".npmrc"
+            //registry.npmjs.org/:_authToken=$NPM_TOKEN
+          EOF
+        env:
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
+
+      - name: Get changeset status
+        id: get-changeset-status
+        run: |
+          pnpm changeset status --output .changeset/status.json
+          new_version=$(jq -r '.releases[] | select(.name == "llamaindex") | .newVersion' < .changeset/status.json)
+          rm -v .changeset/status.json
+          echo "new-version=${new_version}" >> "$GITHUB_OUTPUT"
+
+      - name: Create Release Pull Request or Publish to npm
+        id: changesets
+        uses: changesets/action@v1
+        with:
+          commit: Release ${{ steps.get-changeset-status.outputs.new-version }}
+          title: Release ${{ steps.get-changeset-status.outputs.new-version }}
+          # update version PR with the latest changesets
+          version: pnpm new-version
+          # build package and call changeset publish
+          publish: pnpm release
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}

.github/workflows/test.yml

@@ -17,16 +17,18 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        node-version: [18.x, 20.x, 21.x]
+        node-version: [18.x, 20.x, 22.x]
     name: E2E on Node.js ${{ matrix.node-version }}
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+
+      - uses: pnpm/action-setup@v3
+
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version-file: ".nvmrc"
+          node-version: ${{ matrix.node-version }}
           cache: "pnpm"
       - name: Install dependencies
         run: pnpm install
@@ -37,13 +39,13 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        node-version: [18.x, 20.x, 21.x]
+        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@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -58,7 +60,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -87,7 +89,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
@@ -105,7 +107,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - uses: pnpm/action-setup@v2
+      - uses: pnpm/action-setup@v3
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:

CONTRIBUTING.md

@@ -91,16 +91,10 @@ Please send a descriptive changeset for each PR.
 
 ## Publishing (maintainers only)
 
-To publish a new version of the library, first create a new version:
+The [Release Github Action](.github/workflows/release.yml) is automatically generating and updating a
+PR called "Release {version}".
 
-```shell
-pnpm new-version
-```
+This PR will update the `package.json` and `CHANGELOG.md` files of each package according to
+the current changesets in the [.changeset](.changeset/) folder.
 
-If everything looks good, commit the generated files and release the new version:
-
-```shell
-pnpm release
-git push # push to the main branch
-git push --tags
-```
+If this PR is merged it will automatically add version tags to the repository and publish the updated packages to NPM.

README.md

@@ -114,14 +114,21 @@ Add the following config to your `next.config.js` to ignore specific packages in
 /** @type {import('next').NextConfig} */
 const nextConfig = {
   experimental: {
-    serverComponentsExternalPackages: ["pdf2json", "@zilliz/milvus2-sdk-node"],
+    serverComponentsExternalPackages: [
+      "pdf2json",
+      "@zilliz/milvus2-sdk-node",
+      "sharp",
+      "onnxruntime-node",
+    ],
   },
   webpack: (config) => {
-    config.resolve.alias = {
-      ...config.resolve.alias,
-      sharp$: false,
-      "onnxruntime-node$": false,
-    };
+    config.externals.push({
+      pdf2json: "commonjs pdf2json",
+      "@zilliz/milvus2-sdk-node": "commonjs @zilliz/milvus2-sdk-node",
+      sharp: "commonjs sharp",
+      "onnxruntime-node": "commonjs onnxruntime-node",
+    });
+
     return config;
   },
 };

apps/docs/CHANGELOG.md

@@ -1,5 +1,14 @@
 # docs
 
+## 0.0.5
+
+### Patch Changes
+
+- Updated dependencies [87142b2]
+- Updated dependencies [5a6cc0e]
+- Updated dependencies [87142b2]
+  - llamaindex@0.2.11
+
 ## 0.0.4
 
 ### Patch Changes

apps/docs/docs/modules/embeddings/available_embeddings/jinaai.md

@@ -0,0 +1,21 @@
+# Jina AI
+
+To use Jina AI embeddings, you need to import `JinaAIEmbedding` from `llamaindex`.
+
+```ts
+import { JinaAIEmbedding, Settings } from "llamaindex";
+
+Settings.embedModel = new JinaAIEmbedding();
+
+const document = new Document({ text: essay, id_: "essay" });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+
+const queryEngine = index.asQueryEngine();
+
+const query = "What is the meaning of life?";
+
+const results = await queryEngine.query({
+  query,
+});
+```

apps/docs/docs/modules/node_postprocessors/jinaai_reranker.md

@@ -0,0 +1,71 @@
+# Jina AI Reranker
+
+The Jina AI Reranker is a postprocessor that uses the Jina AI Reranker API to rerank the results of a search query.
+
+## Setup
+
+Firstly, you will need to install the `llamaindex` package.
+
+```bash
+pnpm install llamaindex
+```
+
+Now, you will need to sign up for an API key at [Jina AI](https://jina.ai/reranker). Once you have your API key you can import the necessary modules and create a new instance of the `JinaAIReranker` class.
+
+```ts
+import {
+  JinaAIReranker,
+  Document,
+  OpenAI,
+  VectorStoreIndex,
+  Settings,
+} from "llamaindex";
+```
+
+## Load and index documents
+
+For this example, we will use a single document. In a real-world scenario, you would have multiple documents to index.
+
+```ts
+const document = new Document({ text: essay, id_: "essay" });
+
+Settings.llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.1 });
+
+const index = await VectorStoreIndex.fromDocuments([document]);
+```
+
+## Increase similarity topK to retrieve more results
+
+The default value for `similarityTopK` is 2. This means that only the most similar document will be returned. To retrieve more results, you can increase the value of `similarityTopK`.
+
+```ts
+const retriever = index.asRetriever();
+retriever.similarityTopK = 5;
+```
+
+## Create a new instance of the JinaAIReranker class
+
+Then you can create a new instance of the `JinaAIReranker` class and pass in the number of results you want to return.
+The Jina AI Reranker API key is set in the `JINAAI_API_KEY` environment variable.
+
+```bash
+export JINAAI_API_KEY=<YOUR API KEY>
+```
+
+```ts
+const nodePostprocessor = new JinaAIReranker({
+  topN: 5,
+});
+```
+
+## Create a query engine with the retriever and node postprocessor
+
+```ts
+const queryEngine = index.asQueryEngine({
+  retriever,
+  nodePostprocessors: [nodePostprocessor],
+});
+
+// log the response
+const response = await queryEngine.query("Where did the author grown up?");
+```

apps/docs/docusaurus.config.js

@@ -163,7 +163,7 @@ const config = {
       "docusaurus-plugin-typedoc",
       {
         entryPoints: ["../../packages/core/src/index.ts"],
-        tsconfig: "../../packages/core/tsconfig.json",
+        tsconfig: "../../tsconfig.json",
         readme: "none",
         sourceLinkTemplate:
           "https://github.com/run-llama/LlamaIndexTS/blob/{gitRevision}/{path}#L{line}",

apps/docs/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docs",
-  "version": "0.0.4",
+  "version": "0.0.5",
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",
@@ -20,6 +20,7 @@
     "@llamaindex/examples": "workspace:*",
     "@mdx-js/react": "^3.0.1",
     "clsx": "^2.1.0",
+    "llamaindex": "workspace:*",
     "postcss": "^8.4.38",
     "prism-react-renderer": "^2.3.1",
     "raw-loader": "^4.0.2",

examples/multimodal/clip.ts

@@ -1,16 +1,5 @@
-import * as fs from "fs";
 import { ClipEmbedding, similarity, SimilarityType } from "llamaindex";
 
-async function loadImageFromDisk(path: string) {
-  try {
-    const file = fs.readFileSync(path);
-    return new Blob([file]);
-  } catch (error) {
-    console.error(`Error loading image from disk: ${error}`);
-    return null;
-  }
-}
-
 async function main() {
   const clip = new ClipEmbedding();
 
@@ -23,8 +12,7 @@ async function main() {
   // Get image embedding
   const image =
     "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg";
-  const blobImage = await loadImageFromDisk("./data/football-match.jpg");
-  const imageEmbedding = await clip.getImageEmbedding(blobImage || image);
+  const imageEmbedding = await clip.getImageEmbedding(image);
 
   // Calc similarity
   const sim1 = similarity(

examples/multimodal/load.ts

@@ -4,7 +4,6 @@ import {
   VectorStoreIndex,
   storageContextFromDefaults,
 } from "llamaindex";
-import { DocStoreStrategy } from "llamaindex/ingestion/strategies/index";
 
 import * as path from "path";
 
@@ -32,7 +31,6 @@ async function generateDatasource() {
     });
     await VectorStoreIndex.fromDocuments(documents, {
       storageContext,
-      docStoreStrategy: DocStoreStrategy.NONE,
     });
   });
   console.log(`Storage successfully generated in ${ms / 1000}s.`);

examples/readers/package.json

@@ -3,20 +3,21 @@
   "private": true,
   "type": "module",
   "scripts": {
-    "start": "node --loader ts-node/esm ./src/simple-directory-reader.ts",
-    "start:csv": "node --loader ts-node/esm ./src/csv.ts",
-    "start:docx": "node --loader ts-node/esm ./src/docx.ts",
-    "start:html": "node --loader ts-node/esm ./src/html.ts",
-    "start:markdown": "node --loader ts-node/esm ./src/markdown.ts",
-    "start:pdf": "node --loader ts-node/esm ./src/pdf.ts",
-    "start:llamaparse": "node --loader ts-node/esm ./src/llamaparse.ts"
+    "start": "node --import tsx ./src/simple-directory-reader.ts",
+    "start:csv": "node --import tsx ./src/csv.ts",
+    "start:docx": "node --import tsx ./src/docx.ts",
+    "start:html": "node --import tsx ./src/html.ts",
+    "start:markdown": "node --import tsx ./src/markdown.ts",
+    "start:pdf": "node --import tsx ./src/pdf.ts",
+    "start:llamaparse": "node --import tsx ./src/llamaparse.ts",
+    "start:notion": "node --import tsx ./src/notion.ts"
   },
   "dependencies": {
     "llamaindex": "*"
   },
   "devDependencies": {
     "@types/node": "^20.12.7",
-    "ts-node": "^10.9.2",
-    "typescript": "^5.4.3"
+    "tsx": "^4.7.2",
+    "typescript": "^5.4.5"
   }
 }

examples/readers/src/notion.ts

@@ -7,7 +7,7 @@ import { createInterface } from "node:readline/promises";
 
 program
   .argument("[page]", "Notion page id (must be provided)")
-  .action(async (page, _options, command) => {
+  .action(async (page, _options) => {
     // Initializing a client
 
     if (!process.env.NOTION_TOKEN) {
@@ -55,7 +55,7 @@ program
           .filter((page) => page !== null);
         console.log("Found pages:");
         console.table(pages);
-        console.log(`To run, run ts-node ${command.name()} [page id]`);
+        console.log(`To run, run with [page id]`);
         return;
       }
     }

packages/core/CHANGELOG.md

@@ -1,5 +1,13 @@
 # llamaindex
 
+## 0.2.11
+
+### Patch Changes
+
+- 87142b2: refactor: use ollama official sdk
+- 5a6cc0e: feat: support jina ai embedding and reranker
+- 87142b2: feat: support output to json format
+
 ## 0.2.10
 
 ### Patch Changes

packages/core/e2e/node/claude.e2e.ts

@@ -2,7 +2,7 @@ import { consola } from "consola";
 import { Anthropic, FunctionTool, Settings, type LLM } from "llamaindex";
 import { AnthropicAgent } from "llamaindex/agent/anthropic";
 import { extractText } from "llamaindex/llm/utils";
-import { ok } from "node:assert";
+import { ok, strictEqual } from "node:assert";
 import { beforeEach, test } from "node:test";
 import { sumNumbersTool } from "./fixtures/tools.js";
 import { mockLLMEvent } from "./utils.js";
@@ -71,10 +71,12 @@ await test("anthropic agent", async (t) => {
         },
       ],
     });
-    const { response } = await agent.chat({
+    const { response, sources } = await agent.chat({
       message: "What is the weather in San Francisco?",
     });
     consola.debug("response:", response.message.content);
+
+    strictEqual(sources.length, 1);
     ok(extractText(response.message.content).includes("35"));
   });
 

packages/core/e2e/node/openai.e2e.ts

@@ -13,6 +13,7 @@ import {
   SummaryIndex,
   VectorStoreIndex,
   type LLM,
+  type ToolOutput,
 } from "llamaindex";
 import { extractText } from "llamaindex/llm/utils";
 import { ok, strictEqual } from "node:assert";
@@ -222,10 +223,12 @@ await test("agent with object function call", async (t) => {
         ),
       ],
     });
-    const { response } = await agent.chat({
+    const { response, sources } = await agent.chat({
       message: "What is the weather in San Francisco?",
     });
     consola.debug("response:", response.message.content);
+
+    strictEqual(sources.length, 1);
     ok(extractText(response.message.content).includes("72"));
   });
 });
@@ -253,10 +256,12 @@ await test("agent", async (t) => {
         },
       ],
     });
-    const { response } = await agent.chat({
+    const { response, sources } = await agent.chat({
       message: "What is the weather in San Francisco?",
     });
     consola.debug("response:", response.message.content);
+
+    strictEqual(sources.length, 1);
     ok(extractText(response.message.content).includes("35"));
   });
 
@@ -290,9 +295,10 @@ await test("agent", async (t) => {
     const agent = new OpenAIAgent({
       tools: [showUniqueId],
     });
-    const { response } = await agent.chat({
+    const { response, sources } = await agent.chat({
       message: "My name is Alex Yang. What is my unique id?",
     });
+    strictEqual(sources.length, 1);
     ok(extractText(response.message.content).includes(uniqueId));
   });
 
@@ -301,10 +307,11 @@ await test("agent", async (t) => {
       tools: [sumNumbersTool],
     });
 
-    const { response } = await openaiAgent.chat({
+    const { response, sources } = await openaiAgent.chat({
       message: "how much is 1 + 1?",
     });
 
+    strictEqual(sources.length, 1);
     ok(extractText(response.message.content).includes("2"));
   });
 });
@@ -319,18 +326,21 @@ await test("agent stream", async (t) => {
       tools: [sumNumbersTool, divideNumbersTool],
     });
 
-    const { response } = await agent.chat({
+    const stream = await agent.chat({
       message: "Divide 16 by 2 then add 20",
       stream: true,
     });
 
     let message = "";
+    let soruces: ToolOutput[] = [];
 
-    for await (const chunk of response) {
-      message += chunk.delta;
+    for await (const { response, sources: _sources } of stream) {
+      message += response.delta;
+      soruces = _sources;
     }
 
     strictEqual(fn.mock.callCount(), 2);
+    strictEqual(soruces.length, 2);
     ok(message.includes("28"));
     Settings.callbackManager.off("llm-tool-call", fn);
   });

packages/core/e2e/tsconfig.json

@@ -4,14 +4,11 @@
     "outDir": "./lib",
     "module": "node16",
     "moduleResolution": "node16",
-    "target": "ESNext"
+    "target": "ESNext",
+    "lib": ["ES2022"],
+    "types": ["node"]
   },
-  "include": [
-    "./**/*.ts",
-    "./mock-module.js",
-    "./mock-register.js",
-    "./fixtures"
-  ],
+  "include": ["./node", "./mock-module.js", "./mock-register.js", "./fixtures"],
   "references": [
     {
       "path": "../../core/tsconfig.json"

packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.2.10",
+  "version": "0.2.11",
   "expectedMinorVersion": "2",
   "license": "MIT",
   "type": "module",
@@ -12,7 +12,6 @@
     "@llamaindex/cloud": "0.0.5",
     "@llamaindex/env": "workspace:*",
     "@mistralai/mistralai": "^0.1.3",
-    "@notionhq/client": "^2.2.15",
     "@pinecone-database/pinecone": "^2.2.0",
     "@qdrant/js-client-rest": "^1.8.2",
     "@types/lodash": "^4.17.0",
@@ -31,7 +30,7 @@
     "mammoth": "^1.7.1",
     "md-utils-ts": "^2.0.0",
     "mongodb": "^6.5.0",
-    "notion-md-crawler": "^0.0.2",
+    "notion-md-crawler": "^1.0.0",
     "ollama": "^0.5.0",
     "openai": "^4.38.0",
     "papaparse": "^5.4.1",
@@ -45,7 +44,11 @@
     "wikipedia": "^2.1.2",
     "wink-nlp": "^1.14.3"
   },
+  "peerDependencies": {
+    "@notionhq/client": "^2.2.15"
+  },
   "devDependencies": {
+    "@notionhq/client": "^2.2.15",
     "@swc/cli": "^0.3.12",
     "@swc/core": "^1.4.16",
     "concurrently": "^8.2.2",

packages/core/src/Node.ts

@@ -326,6 +326,37 @@ export class ImageNode<T extends Metadata = Metadata> extends TextNode<T> {
     const absPath = path.resolve(this.id_);
     return new URL(`file://${absPath}`);
   }
+
+  // Calculates the image part of the hash
+  private generateImageHash() {
+    const hashFunction = createSHA256();
+
+    if (this.image instanceof Blob) {
+      // TODO: ideally we should use the blob's content to calculate the hash:
+      // hashFunction.update(new Uint8Array(await this.image.arrayBuffer()));
+      // as this is async, we're using the node's ID for the time being
+      hashFunction.update(this.id_);
+    } else if (this.image instanceof URL) {
+      hashFunction.update(this.image.toString());
+    } else if (typeof this.image === "string") {
+      hashFunction.update(this.image);
+    } else {
+      throw new Error(
+        `Unknown image type: ${typeof this.image}. Can't calculate hash`,
+      );
+    }
+
+    return hashFunction.digest();
+  }
+
+  generateHash() {
+    const hashFunction = createSHA256();
+    // calculates hash based on hash of both components (image and text)
+    hashFunction.update(super.generateHash());
+    hashFunction.update(this.generateImageHash());
+
+    return hashFunction.digest();
+  }
 }
 
 export class ImageDocument<T extends Metadata = Metadata> extends ImageNode<T> {

packages/core/src/agent/base.ts

@@ -1,5 +1,6 @@
 import { pipeline, randomUUID } from "@llamaindex/env";
 import {
+  type ChatEngine,
   type ChatEngineParamsNonStreaming,
   type ChatEngineParamsStreaming,
 } from "../engines/chat/index.js";
@@ -171,8 +172,9 @@ export async function* createTaskImpl<
 }
 
 export type AgentStreamChatResponse<Options extends object> = {
-  response: ReadableStream<ChatResponseChunk<Options>>;
-  sources: ToolOutput[];
+  response: ChatResponseChunk<Options>;
+  // sources of the response, will emit when new tool outputs are available
+  sources?: ToolOutput[];
 };
 
 export type AgentChatResponse<Options extends object> = {
@@ -276,7 +278,12 @@ export abstract class AgentRunner<
   >
     ? AdditionalMessageOptions
     : never,
-> {
+> implements
+    ChatEngine<
+      AgentChatResponse<AdditionalMessageOptions>,
+      ReadableStream<AgentStreamChatResponse<AdditionalMessageOptions>>
+    >
+{
   readonly #llm: AI;
   readonly #tools:
     | BaseToolWithCall[]
@@ -370,13 +377,13 @@ export abstract class AgentRunner<
   ): Promise<AgentChatResponse<AdditionalMessageOptions>>;
   async chat(
     params: ChatEngineParamsStreaming,
-  ): Promise<AgentStreamChatResponse<AdditionalMessageOptions>>;
+  ): Promise<ReadableStream<AgentStreamChatResponse<AdditionalMessageOptions>>>;
   @wrapEventCaller
   async chat(
     params: ChatEngineParamsNonStreaming | ChatEngineParamsStreaming,
   ): Promise<
     | AgentChatResponse<AdditionalMessageOptions>
-    | AgentStreamChatResponse<AdditionalMessageOptions>
+    | ReadableStream<AgentStreamChatResponse<AdditionalMessageOptions>>
   > {
     const task = await this.createTask(params.message, !!params.stream);
     const stepOutput = await pipeline(
@@ -397,14 +404,26 @@ export abstract class AgentRunner<
     const { output, taskStep } = stepOutput;
     this.#chatHistory = [...taskStep.context.store.messages];
     if (isAsyncIterable(output)) {
-      return {
-        response: output,
-        sources: [...taskStep.context.store.toolOutputs],
-      } satisfies AgentStreamChatResponse<AdditionalMessageOptions>;
+      return output.pipeThrough<
+        AgentStreamChatResponse<AdditionalMessageOptions>
+      >(
+        new TransformStream({
+          transform(chunk, controller) {
+            controller.enqueue({
+              response: chunk,
+              get sources() {
+                return [...taskStep.context.store.toolOutputs];
+              },
+            });
+          },
+        }),
+      );
     } else {
       return {
         response: output,
-        sources: [...taskStep.context.store.toolOutputs],
+        get sources() {
+          return [...taskStep.context.store.toolOutputs];
+        },
       } satisfies AgentChatResponse<AdditionalMessageOptions>;
     }
   }

packages/core/src/cloud/LlamaCloudIndex.ts

@@ -5,7 +5,7 @@ import { RetrieverQueryEngine } from "../engines/query/RetrieverQueryEngine.js";
 import type { TransformComponent } from "../ingestion/types.js";
 import type { BaseNodePostprocessor } from "../postprocessors/types.js";
 import type { BaseSynthesizer } from "../synthesizers/types.js";
-import type { BaseQueryEngine } from "../types.js";
+import type { QueryEngine } from "../types.js";
 import type { CloudRetrieveParams } from "./LlamaCloudRetriever.js";
 import { LlamaCloudRetriever } from "./LlamaCloudRetriever.js";
 import { getPipelineCreate } from "./config.js";
@@ -178,7 +178,7 @@ export class LlamaCloudIndex {
       preFilters?: unknown;
       nodePostprocessors?: BaseNodePostprocessor[];
     } & CloudRetrieveParams,
-  ): BaseQueryEngine {
+  ): QueryEngine {
     const retriever = new LlamaCloudRetriever({
       ...this.params,
       ...params,

packages/core/src/embeddings/JinaAIEmbedding.ts

@@ -0,0 +1,29 @@
+import { getEnv } from "@llamaindex/env";
+import { OpenAIEmbedding } from "./OpenAIEmbedding.js";
+
+export class JinaAIEmbedding extends OpenAIEmbedding {
+  constructor(init?: Partial<OpenAIEmbedding>) {
+    const {
+      apiKey = getEnv("JINAAI_API_KEY"),
+      additionalSessionOptions = {},
+      model = "jina-embeddings-v2-base-en",
+      ...rest
+    } = init ?? {};
+
+    if (!apiKey) {
+      throw new Error(
+        "Set Jina AI API Key in JINAAI_API_KEY env variable. Get one for free or top up your key at https://jina.ai/embeddings",
+      );
+    }
+
+    additionalSessionOptions.baseURL =
+      additionalSessionOptions.baseURL ?? "https://api.jina.ai/v1";
+
+    super({
+      apiKey,
+      additionalSessionOptions,
+      model,
+      ...rest,
+    });
+  }
+}

packages/core/src/embeddings/index.ts

@@ -1,5 +1,6 @@
 export * from "./ClipEmbedding.js";
 export * from "./HuggingFaceEmbedding.js";
+export * from "./JinaAIEmbedding.js";
 export * from "./MistralAIEmbedding.js";
 export * from "./MultiModalEmbedding.js";
 export { OllamaEmbedding } from "./OllamaEmbedding.js";

packages/core/src/engines/chat/CondenseQuestionChatEngine.ts

@@ -12,7 +12,7 @@ import { wrapEventCaller } from "../../internal/context/EventCaller.js";
 import type { ChatMessage, LLM } from "../../llm/index.js";
 import { extractText, streamReducer } from "../../llm/utils.js";
 import { PromptMixin } from "../../prompts/index.js";
-import type { BaseQueryEngine } from "../../types.js";
+import type { QueryEngine } from "../../types.js";
 import type {
   ChatEngine,
   ChatEngineParamsNonStreaming,
@@ -33,13 +33,13 @@ export class CondenseQuestionChatEngine
   extends PromptMixin
   implements ChatEngine
 {
-  queryEngine: BaseQueryEngine;
+  queryEngine: QueryEngine;
   chatHistory: ChatHistory;
   llm: LLM;
   condenseMessagePrompt: CondenseQuestionPrompt;
 
   constructor(init: {
-    queryEngine: BaseQueryEngine;
+    queryEngine: QueryEngine;
     chatHistory: ChatMessage[];
     serviceContext?: ServiceContext;
     condenseMessagePrompt?: CondenseQuestionPrompt;

packages/core/src/engines/chat/types.ts

@@ -23,21 +23,21 @@ export interface ChatEngineParamsNonStreaming extends ChatEngineParamsBase {
   stream?: false | null;
 }
 
-export interface ChatEngineAgentParams extends ChatEngineParamsBase {
-  toolChoice?: string | Record<string, any>;
-  stream?: boolean;
-}
-
 /**
  * A ChatEngine is used to handle back and forth chats between the application and the LLM.
  */
-export interface ChatEngine {
+export interface ChatEngine<
+  // synchronous response
+  R = Response,
+  // asynchronous response
+  AR extends AsyncIterable<unknown> = AsyncIterable<R>,
+> {
   /**
    * Send message along with the class's current chat history to the LLM.
    * @param params
    */
-  chat(params: ChatEngineParamsStreaming): Promise<AsyncIterable<Response>>;
-  chat(params: ChatEngineParamsNonStreaming): Promise<Response>;
+  chat(params: ChatEngineParamsStreaming): Promise<AR>;
+  chat(params: ChatEngineParamsNonStreaming): Promise<R>;
 
   /**
    * Resets the chat history so that it's empty.

packages/core/src/engines/query/RetrieverQueryEngine.ts

@@ -7,7 +7,7 @@ import { PromptMixin } from "../../prompts/Mixin.js";
 import type { BaseSynthesizer } from "../../synthesizers/index.js";
 import { ResponseSynthesizer } from "../../synthesizers/index.js";
 import type {
-  BaseQueryEngine,
+  QueryEngine,
   QueryEngineParamsNonStreaming,
   QueryEngineParamsStreaming,
 } from "../../types.js";
@@ -15,10 +15,7 @@ import type {
 /**
  * A query engine that uses a retriever to query an index and then synthesizes the response.
  */
-export class RetrieverQueryEngine
-  extends PromptMixin
-  implements BaseQueryEngine
-{
+export class RetrieverQueryEngine extends PromptMixin implements QueryEngine {
   retriever: BaseRetriever;
   responseSynthesizer: BaseSynthesizer;
   nodePostprocessors: BaseNodePostprocessor[];

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

@@ -7,14 +7,14 @@ import type { BaseSelector } from "../../selectors/index.js";
 import { LLMSingleSelector } from "../../selectors/index.js";
 import { TreeSummarize } from "../../synthesizers/index.js";
 import type {
-  BaseQueryEngine,
   QueryBundle,
+  QueryEngine,
   QueryEngineParamsNonStreaming,
   QueryEngineParamsStreaming,
 } from "../../types.js";
 
 type RouterQueryEngineTool = {
-  queryEngine: BaseQueryEngine;
+  queryEngine: QueryEngine;
   description: string;
 };
 
@@ -54,9 +54,9 @@ async function combineResponses(
 /**
  * A query engine that uses multiple query engines and selects the best one.
  */
-export class RouterQueryEngine extends PromptMixin implements BaseQueryEngine {
+export class RouterQueryEngine extends PromptMixin implements QueryEngine {
   private selector: BaseSelector;
-  private queryEngines: BaseQueryEngine[];
+  private queryEngines: QueryEngine[];
   private metadatas: RouterQueryEngineMetadata[];
   private summarizer: TreeSummarize;
   private verbose: boolean;

packages/core/src/engines/query/SubQuestionQueryEngine.ts

@@ -11,8 +11,8 @@ import {
 } from "../../synthesizers/index.js";
 
 import type {
-  BaseQueryEngine,
   BaseTool,
+  QueryEngine,
   QueryEngineParamsNonStreaming,
   QueryEngineParamsStreaming,
   ToolMetadata,
@@ -24,10 +24,7 @@ import type { BaseQuestionGenerator, SubQuestion } from "./types.js";
 /**
  * SubQuestionQueryEngine decomposes a question into subquestions and then
  */
-export class SubQuestionQueryEngine
-  extends PromptMixin
-  implements BaseQueryEngine
-{
+export class SubQuestionQueryEngine extends PromptMixin implements QueryEngine {
   responseSynthesizer: BaseSynthesizer;
   questionGen: BaseQuestionGenerator;
   queryEngines: BaseTool[];

packages/core/src/indices/BaseIndex.ts

@@ -8,7 +8,7 @@ import type { BaseDocumentStore } from "../storage/docStore/types.js";
 import type { BaseIndexStore } from "../storage/indexStore/types.js";
 import type { VectorStore } from "../storage/vectorStore/types.js";
 import type { BaseSynthesizer } from "../synthesizers/types.js";
-import type { BaseQueryEngine } from "../types.js";
+import type { QueryEngine } from "../types.js";
 import { IndexStruct } from "./IndexStruct.js";
 import { IndexStructType } from "./json-to-index-struct.js";
 
@@ -87,7 +87,7 @@ export abstract class BaseIndex<T> {
   abstract asQueryEngine(options?: {
     retriever?: BaseRetriever;
     responseSynthesizer?: BaseSynthesizer;
-  }): BaseQueryEngine;
+  }): QueryEngine;
 
   /**
    * Insert a document into the index.

packages/core/src/indices/keyword/index.ts

@@ -17,7 +17,7 @@ import type { StorageContext } from "../../storage/StorageContext.js";
 import { storageContextFromDefaults } from "../../storage/StorageContext.js";
 import type { BaseDocumentStore } from "../../storage/docStore/types.js";
 import type { BaseSynthesizer } from "../../synthesizers/index.js";
-import type { BaseQueryEngine } from "../../types.js";
+import type { QueryEngine } from "../../types.js";
 import type { BaseIndexInit } from "../BaseIndex.js";
 import { BaseIndex, KeywordTable } from "../BaseIndex.js";
 import { IndexStructType } from "../json-to-index-struct.js";
@@ -234,7 +234,7 @@ export class KeywordTableIndex extends BaseIndex<KeywordTable> {
     responseSynthesizer?: BaseSynthesizer;
     preFilters?: unknown;
     nodePostprocessors?: BaseNodePostprocessor[];
-  }): BaseQueryEngine {
+  }): QueryEngine {
     const { retriever, responseSynthesizer } = options ?? {};
     return new RetrieverQueryEngine(
       retriever ?? this.asRetriever(),

packages/core/src/indices/summary/index.ts

@@ -23,7 +23,7 @@ import {
   CompactAndRefine,
   ResponseSynthesizer,
 } from "../../synthesizers/index.js";
-import type { BaseQueryEngine } from "../../types.js";
+import type { QueryEngine } from "../../types.js";
 import type { BaseIndexInit } from "../BaseIndex.js";
 import { BaseIndex } from "../BaseIndex.js";
 import { IndexList, IndexStructType } from "../json-to-index-struct.js";
@@ -171,7 +171,7 @@ export class SummaryIndex extends BaseIndex<IndexList> {
     responseSynthesizer?: BaseSynthesizer;
     preFilters?: unknown;
     nodePostprocessors?: BaseNodePostprocessor[];
-  }): BaseQueryEngine & RetrieverQueryEngine {
+  }): QueryEngine & RetrieverQueryEngine {
     let { retriever, responseSynthesizer } = options ?? {};
 
     if (!retriever) {

packages/core/src/indices/vectorStore/index.ts

@@ -37,7 +37,7 @@ import type {
 import type { BaseIndexStore } from "../../storage/indexStore/types.js";
 import { VectorStoreQueryMode } from "../../storage/vectorStore/types.js";
 import type { BaseSynthesizer } from "../../synthesizers/types.js";
-import type { BaseQueryEngine } from "../../types.js";
+import type { QueryEngine } from "../../types.js";
 import type { BaseIndexInit } from "../BaseIndex.js";
 import { BaseIndex } from "../BaseIndex.js";
 import { IndexDict, IndexStructType } from "../json-to-index-struct.js";
@@ -284,7 +284,7 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
     responseSynthesizer?: BaseSynthesizer;
     preFilters?: MetadataFilters;
     nodePostprocessors?: BaseNodePostprocessor[];
-  }): BaseQueryEngine & RetrieverQueryEngine {
+  }): QueryEngine & RetrieverQueryEngine {
     const { retriever, responseSynthesizer } = options ?? {};
     return new RetrieverQueryEngine(
       retriever ?? this.asRetriever(),

packages/core/src/ingestion/IngestionPipeline.ts

@@ -94,20 +94,20 @@ export class IngestionPipeline {
     documents?: Document[],
     nodes?: BaseNode[],
   ): Promise<BaseNode[]> {
-    const inputNodes: BaseNode[] = [];
+    const inputNodes: BaseNode[][] = [];
     if (documents) {
-      inputNodes.push(...documents);
+      inputNodes.push(documents);
     }
     if (nodes) {
-      inputNodes.push(...nodes);
+      inputNodes.push(nodes);
     }
     if (this.documents) {
-      inputNodes.push(...this.documents);
+      inputNodes.push(this.documents);
     }
     if (this.reader) {
-      inputNodes.push(...(await this.reader.loadData()));
+      inputNodes.push(await this.reader.loadData());
     }
-    return inputNodes;
+    return inputNodes.flat();
   }
 
   async run(

packages/core/src/postprocessors/rerankers/JinaAIReranker.ts

@@ -0,0 +1,89 @@
+import { getEnv } from "@llamaindex/env";
+import type { NodeWithScore } from "../../Node.js";
+import { MetadataMode } from "../../Node.js";
+import type { BaseNodePostprocessor } from "../types.js";
+
+interface JinaAIRerankerResult {
+  index: number;
+  document?: {
+    text?: string;
+  };
+  relevance_score: number;
+}
+
+export class JinaAIReranker implements BaseNodePostprocessor {
+  model: string = "jina-reranker-v1-base-en";
+  topN?: number;
+  apiKey?: string = undefined;
+
+  constructor(init?: Partial<JinaAIReranker>) {
+    this.topN = init?.topN ?? 2;
+    this.model = init?.model ?? "jina-reranker-v1-base-en";
+    this.apiKey = getEnv("JINAAI_API_KEY");
+
+    if (!this.apiKey) {
+      throw new Error(
+        "Set Jina AI API Key in JINAAI_API_KEY env variable. Get one for free or top up your key at https://jina.ai/reranker",
+      );
+    }
+  }
+
+  async rerank(
+    query: string,
+    documents: string[],
+    topN: number | undefined = this.topN,
+  ): Promise<JinaAIRerankerResult[]> {
+    const url = "https://api.jina.ai/v1/rerank";
+    const headers = {
+      "Content-Type": "application/json",
+      Authorization: `Bearer ${this.apiKey}`,
+    };
+    const data = {
+      model: this.model,
+      query: query,
+      documents: documents,
+      top_n: topN,
+    };
+
+    try {
+      const response = await fetch(url, {
+        method: "POST",
+        headers: headers,
+        body: JSON.stringify(data),
+      });
+      const jsonData = await response.json();
+
+      return jsonData.results;
+    } catch (error) {
+      console.error("Error while reranking:", error);
+      throw new Error("Failed to rerank documents due to an API error");
+    }
+  }
+
+  async postprocessNodes(
+    nodes: NodeWithScore[],
+    query?: string,
+  ): Promise<NodeWithScore[]> {
+    if (nodes.length === 0) {
+      return [];
+    }
+
+    if (query === undefined) {
+      throw new Error("JinaAIReranker requires a query");
+    }
+
+    const documents = nodes.map((n) => n.node.getContent(MetadataMode.ALL));
+    const results = await this.rerank(query, documents, this.topN);
+    const newNodes: NodeWithScore[] = [];
+
+    for (const result of results) {
+      const node = nodes[result.index];
+      newNodes.push({
+        node: node.node,
+        score: result.relevance_score,
+      });
+    }
+
+    return newNodes;
+  }
+}

packages/core/src/postprocessors/rerankers/index.ts

@@ -1 +1,2 @@
 export * from "./CohereRerank.js";
+export * from "./JinaAIReranker.js";

packages/core/src/readers/ImageReader.ts

@@ -19,7 +19,7 @@ export class ImageReader implements FileReader {
     file: string,
     fs: GenericFileSystem = defaultFS,
   ): Promise<Document[]> {
-    const dataBuffer = await fs.readFile(file);
+    const dataBuffer = await fs.readRawFile(file);
     const blob = new Blob([dataBuffer]);
     return [new ImageDocument({ image: blob, id_: file })];
   }

packages/core/src/readers/NotionReader.ts

@@ -1,21 +1,9 @@
-import type { Client } from "@notionhq/client";
-import type { Crawler, Pages } from "notion-md-crawler";
+import type { Crawler, CrawlerOptions, Page } from "notion-md-crawler";
 import { crawler, pageToString } from "notion-md-crawler";
 import { Document } from "../Node.js";
 import type { BaseReader } from "./type.js";
 
-type OptionalSerializers = Parameters<Crawler>[number]["serializers"];
-
-/**
- * Options for initializing the NotionReader class
- * @typedef {Object} NotionReaderOptions
- * @property {Client} client - The Notion Client object for API interactions
- * @property {OptionalSerializers} [serializers] - Option to customize serialization. See [the url](https://github.com/TomPenguin/notion-md-crawler/tree/main) for details.
- */
-type NotionReaderOptions = {
-  client: Client;
-  serializers?: OptionalSerializers;
-};
+type NotionReaderOptions = Pick<CrawlerOptions, "client" | "serializers">;
 
 /**
  * Notion pages are retrieved recursively and converted to Document objects.
@@ -25,7 +13,7 @@ type NotionReaderOptions = {
  * Please refer to [this document](https://www.notion.so/help/create-integrations-with-the-notion-api) for details.
  */
 export class NotionReader implements BaseReader {
-  private crawl: ReturnType<Crawler>;
+  private readonly crawl: ReturnType<Crawler>;
 
   /**
    * Constructor for the NotionReader class
@@ -37,10 +25,10 @@ export class NotionReader implements BaseReader {
 
   /**
    * Converts Pages to an array of Document objects
-   * @param {Pages} pages - The Notion pages to convert (Return value of `loadPages`)
+   * @param {Page} pages - The Notion pages to convert (Return value of `loadPages`)
    * @returns {Document[]} An array of Document objects
    */
-  toDocuments(pages: Pages): Document[] {
+  toDocuments(pages: Page[]): Document[] {
     return Object.values(pages).map((page) => {
       const text = pageToString(page);
       return new Document({
@@ -54,10 +42,21 @@ export class NotionReader implements BaseReader {
   /**
    * Loads recursively the Notion page with the specified root page ID.
    * @param {string} rootPageId - The root Notion page ID
-   * @returns {Promise<Pages>} A Promise that resolves to a Pages object(Convertible with the `toDocuments` method)
+   * @returns {Promise<Page[]>} A Promise that resolves to a Pages object(Convertible with the `toDocuments` method)
    */
-  async loadPages(rootPageId: string): Promise<Pages> {
-    return this.crawl(rootPageId);
+  async loadPages(rootPageId: string): Promise<Page[]> {
+    const iter = this.crawl(rootPageId);
+    const pages: Page[] = [];
+    for await (const result of iter) {
+      if (result.success) {
+        pages.push(result.page);
+      } else {
+        console.error(
+          `Failed to load page (${result.failure.parentId}): ${result.failure.reason}`,
+        );
+      }
+    }
+    return pages;
   }
 
   /**

packages/core/src/readers/SimpleDirectoryReader.edge.ts

@@ -1,6 +1,6 @@
 import type { CompleteFileSystem } from "@llamaindex/env";
 import { defaultFS, path } from "@llamaindex/env";
-import { Document } from "../Node.js";
+import { Document, type Metadata } from "../Node.js";
 import { walk } from "../storage/FileSystem.js";
 import { TextFileReader } from "./TextFileReader.js";
 import type { BaseReader } from "./type.js";
@@ -89,6 +89,7 @@ export class SimpleDirectoryReader implements BaseReader {
         }
 
         const fileDocs = await reader.loadData(filePath, fs);
+        fileDocs.forEach(addMetaData(filePath));
 
         // Observer can still cancel addition of the resulting docs from this file
         if (this.doObserverCheck("file", filePath, ReaderStatus.COMPLETE)) {
@@ -124,3 +125,10 @@ export class SimpleDirectoryReader implements BaseReader {
     return true;
   }
 }
+
+function addMetaData(filePath: string): (doc: Document<Metadata>) => void {
+  return (doc: Document<Metadata>) => {
+    doc.metadata["file_path"] = path.resolve(filePath);
+    doc.metadata["file_name"] = path.basename(filePath);
+  };
+}

packages/core/src/tools/QueryEngineTool.ts

@@ -1,5 +1,5 @@
 import type { JSONSchemaType } from "ajv";
-import type { BaseQueryEngine, BaseTool, ToolMetadata } from "../types.js";
+import type { BaseTool, QueryEngine, ToolMetadata } from "../types.js";
 
 const DEFAULT_NAME = "query_engine_tool";
 const DEFAULT_DESCRIPTION =
@@ -17,7 +17,7 @@ const DEFAULT_PARAMETERS: JSONSchemaType<QueryEngineParam> = {
 };
 
 export type QueryEngineToolParams = {
-  queryEngine: BaseQueryEngine;
+  queryEngine: QueryEngine;
   metadata: ToolMetadata<JSONSchemaType<QueryEngineParam>>;
 };
 
@@ -26,7 +26,7 @@ export type QueryEngineParam = {
 };
 
 export class QueryEngineTool implements BaseTool<QueryEngineParam> {
-  private queryEngine: BaseQueryEngine;
+  private queryEngine: QueryEngine;
   metadata: ToolMetadata<JSONSchemaType<QueryEngineParam>>;
 
   constructor({ queryEngine, metadata }: QueryEngineToolParams) {

packages/core/src/types.ts

@@ -22,7 +22,7 @@ export interface QueryEngineParamsNonStreaming extends QueryEngineParamsBase {
 /**
  * A query engine is a question answerer that can use one or more steps.
  */
-export interface BaseQueryEngine {
+export interface QueryEngine {
   /**
    * Query the query engine and get a response.
    * @param params

packages/core/tests/Document.test.ts

@@ -1,4 +1,4 @@
-import { Document } from "llamaindex/Node";
+import { Document, ImageDocument } from "llamaindex/Node";
 import { describe, expect, test } from "vitest";
 
 describe("Document", () => {
@@ -6,4 +6,16 @@ describe("Document", () => {
     const doc = new Document({ text: "text", id_: "docId" });
     expect(doc).toBeDefined();
   });
+
+  test("should generate different hash for different image contents", () => {
+    const imageNode1 = new ImageDocument({
+      id_: "image",
+      image: "data:image/png;base64,sample_image_content1",
+    });
+    const imageNode2 = new ImageDocument({
+      id_: "image",
+      image: "data:image/png;base64,sample_image_content2",
+    });
+    expect(imageNode1.hash).not.toBe(imageNode2.hash);
+  });
 });

packages/core/tests/ingestion/ingestion-pipeline.test.ts

@@ -0,0 +1,22 @@
+import { Document } from "llamaindex/Node";
+import { IngestionPipeline } from "llamaindex/ingestion/IngestionPipeline";
+import { test } from "vitest";
+
+// Refs: https://github.com/run-llama/LlamaIndexTS/pull/760
+test("load large data should not cause RangeError #760", async () => {
+  const pipeline = new IngestionPipeline({
+    reader: {
+      loadData: async () => {
+        return Array.from(
+          { length: 1e6 },
+          (_, i) =>
+            new Document({
+              id_: `${i}`,
+              text: "some text",
+            }),
+        );
+      },
+    },
+  });
+  await pipeline.prepareInput();
+});

packages/edge/e2e/test-edge-runtime/CHANGELOG.md

@@ -1,5 +1,13 @@
 # test-edge-runtime
 
+## 0.1.3
+
+### Patch Changes
+
+- Updated dependencies [87142b2]
+- Updated dependencies [87142b2]
+  - @llamaindex/edge@0.2.11
+
 ## 0.1.2
 
 ### Patch Changes

packages/edge/e2e/test-edge-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "test-edge-runtime",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -14,7 +14,7 @@
     "react-dom": "^18"
   },
   "devDependencies": {
-    "@types/node": "^20",
+    "@types/node": "^20.12.7",
     "@types/react": "^18",
     "@types/react-dom": "^18",
     "typescript": "^5"

packages/edge/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/edge",
-  "version": "0.2.10",
+  "version": "0.2.11",
   "license": "MIT",
   "type": "module",
   "dependencies": {
@@ -11,7 +11,6 @@
     "@llamaindex/cloud": "0.0.5",
     "@llamaindex/env": "workspace:*",
     "@mistralai/mistralai": "^0.1.3",
-    "@notionhq/client": "^2.2.15",
     "@pinecone-database/pinecone": "^2.2.0",
     "@qdrant/js-client-rest": "^1.8.2",
     "@types/lodash": "^4.17.0",
@@ -30,7 +29,7 @@
     "mammoth": "^1.7.1",
     "md-utils-ts": "^2.0.0",
     "mongodb": "^6.5.0",
-    "notion-md-crawler": "^0.0.2",
+    "notion-md-crawler": "^1.0.0",
     "ollama": "^0.5.0",
     "openai": "^4.38.0",
     "papaparse": "^5.4.1",
@@ -82,5 +81,17 @@
     "update:deps": "node scripts/update-deps.js",
     "build:core": "pnpm --filter llamaindex build && cp -r ../core/dist . && rm -rf dist/cjs",
     "build": "pnpm run update:deps && pnpm run build:core && pnpm copy"
+  },
+  "devDependencies": {
+    "@notionhq/client": "^2.2.15",
+    "@swc/cli": "^0.3.12",
+    "@swc/core": "^1.4.16",
+    "concurrently": "^8.2.2",
+    "glob": "^10.3.12",
+    "madge": "^7.0.0",
+    "typescript": "^5.4.5"
+  },
+  "peerDependencies": {
+    "@notionhq/client": "^2.2.15"
   }
 }

packages/edge/scripts/update-deps.js

@@ -10,6 +10,8 @@ const edgePackagePath = path.join(process.cwd(), "package.json");
 const edgePackage = readJson(edgePackagePath);
 const corePackage = readJson(corePackagePath);
 edgePackage.dependencies = corePackage.dependencies;
+edgePackage.devDependencies = corePackage.devDependencies;
+edgePackage.peerDependencies = corePackage.peerDependencies;
 edgePackage.version = corePackage.version;
 writeJson(edgePackagePath, edgePackage);
 execSync("pnpm install --lockfile-only", { stdio: "inherit" });

packages/experimental/CHANGELOG.md

@@ -1,5 +1,14 @@
 # @llamaindex/experimental
 
+## 0.0.14
+
+### Patch Changes
+
+- Updated dependencies [87142b2]
+- Updated dependencies [5a6cc0e]
+- Updated dependencies [87142b2]
+  - llamaindex@0.2.11
+
 ## 0.0.13
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.13",
+  "version": "0.0.14",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/experimental/src/engines/query/JSONQueryEngine.ts

@@ -5,7 +5,7 @@ import { Response } from "llamaindex";
 import { serviceContextFromDefaults, type ServiceContext } from "llamaindex";
 
 import type {
-  BaseQueryEngine,
+  QueryEngine,
   QueryEngineParamsNonStreaming,
   QueryEngineParamsStreaming,
 } from "llamaindex";
@@ -89,7 +89,7 @@ type OutputProcessor = typeof defaultOutputProcessor;
 /**
  * A JSON query engine that uses JSONPath to query a JSON object.
  */
-export class JSONQueryEngine implements BaseQueryEngine {
+export class JSONQueryEngine implements QueryEngine {
   jsonValue: JSONSchemaType;
   jsonSchema: JSONSchemaType;
   serviceContext: ServiceContext;

pnpm-lock.yaml

@@ -70,6 +70,9 @@ importers:
       clsx:
         specifier: ^2.1.0
         version: 2.1.0
+      llamaindex:
+        specifier: workspace:*
+        version: link:../../packages/core
       postcss:
         specifier: ^8.4.38
         version: 8.4.38
@@ -178,12 +181,12 @@ importers:
       '@types/node':
         specifier: ^20.12.7
         version: 20.12.7
-      ts-node:
-        specifier: ^10.9.2
-        version: 10.9.2(@swc/core@1.4.16(@swc/helpers@0.5.2))(@types/node@20.12.7)(typescript@5.4.3)
+      tsx:
+        specifier: ^4.7.2
+        version: 4.7.2
       typescript:
-        specifier: ^5.4.3
-        version: 5.4.3
+        specifier: ^5.4.5
+        version: 5.4.5
 
   packages/core:
     dependencies:
@@ -208,9 +211,6 @@ importers:
       '@mistralai/mistralai':
         specifier: ^0.1.3
         version: 0.1.3(encoding@0.1.13)
-      '@notionhq/client':
-        specifier: ^2.2.15
-        version: 2.2.15(encoding@0.1.13)
       '@pinecone-database/pinecone':
         specifier: ^2.2.0
         version: 2.2.0
@@ -266,8 +266,8 @@ importers:
         specifier: ^6.5.0
         version: 6.5.0
       notion-md-crawler:
-        specifier: ^0.0.2
-        version: 0.0.2(encoding@0.1.13)
+        specifier: ^1.0.0
+        version: 1.0.0(encoding@0.1.13)
       ollama:
         specifier: ^0.5.0
         version: 0.5.0
@@ -305,6 +305,9 @@ importers:
         specifier: ^1.14.3
         version: 1.14.3
     devDependencies:
+      '@notionhq/client':
+        specifier: ^2.2.15
+        version: 2.2.15(encoding@0.1.13)
       '@swc/cli':
         specifier: ^0.3.12
         version: 0.3.12(@swc/core@1.4.16(@swc/helpers@0.5.2))(chokidar@3.6.0)
@@ -371,9 +374,6 @@ importers:
       '@mistralai/mistralai':
         specifier: ^0.1.3
         version: 0.1.3(encoding@0.1.13)
-      '@notionhq/client':
-        specifier: ^2.2.15
-        version: 2.2.15(encoding@0.1.13)
       '@pinecone-database/pinecone':
         specifier: ^2.2.0
         version: 2.2.0
@@ -429,8 +429,8 @@ importers:
         specifier: ^6.5.0
         version: 6.5.0
       notion-md-crawler:
-        specifier: ^0.0.2
-        version: 0.0.2(encoding@0.1.13)
+        specifier: ^1.0.0
+        version: 1.0.0(encoding@0.1.13)
       ollama:
         specifier: ^0.5.0
         version: 0.5.0
@@ -467,6 +467,28 @@ importers:
       wink-nlp:
         specifier: ^1.14.3
         version: 1.14.3
+    devDependencies:
+      '@notionhq/client':
+        specifier: ^2.2.15
+        version: 2.2.15(encoding@0.1.13)
+      '@swc/cli':
+        specifier: ^0.3.12
+        version: 0.3.12(@swc/core@1.4.16(@swc/helpers@0.5.2))(chokidar@3.6.0)
+      '@swc/core':
+        specifier: ^1.4.16
+        version: 1.4.16(@swc/helpers@0.5.2)
+      concurrently:
+        specifier: ^8.2.2
+        version: 8.2.2
+      glob:
+        specifier: ^10.3.12
+        version: 10.3.12
+      madge:
+        specifier: ^7.0.0
+        version: 7.0.0(typescript@5.4.5)
+      typescript:
+        specifier: ^5.4.5
+        version: 5.4.5
 
   packages/edge/e2e/test-edge-runtime:
     dependencies:
@@ -484,8 +506,8 @@ importers:
         version: 18.2.0(react@18.2.0)
     devDependencies:
       '@types/node':
-        specifier: ^20
-        version: 20.11.20
+        specifier: ^20.12.7
+        version: 20.12.7
       '@types/react':
         specifier: ^18
         version: 18.2.65
@@ -2542,9 +2564,6 @@ packages:
   '@types/node@18.19.31':
     resolution: {integrity: sha512-ArgCD39YpyyrtFKIqMDvjz79jto5fcI/SVUs2HwB+f0dAzq68yqOdyaSivLiLugSziTpNXLQrVb7RZFmdZzbhA==}
 
-  '@types/node@20.11.20':
-    resolution: {integrity: sha512-7/rR21OS+fq8IyHTgtLkDK949uzsa6n8BkziAKtPVpugIkO6D+/ooXMvzXxDnZrmtXVfjb1bKQafYpb8s89LOg==}
-
   '@types/node@20.12.7':
     resolution: {integrity: sha512-wq0cICSkRLVaf3UGLMGItu/PtdY7oaXaI/RVU+xliKVOtRna3PRY57ZDfztpDL0n11vfymMUnXv8QwYCO7L1wg==}
 
@@ -6128,8 +6147,8 @@ packages:
     resolution: {integrity: sha512-IO9QvjUMWxPQQhs60oOu10CRkWCiZzSUkzbXGGV9pviYl1fXYcvkzQ5jV9z8Y6un8ARoVRl4EtC6v6jNqbaJ/w==}
     engines: {node: '>=14.16'}
 
-  notion-md-crawler@0.0.2:
-    resolution: {integrity: sha512-lE3/DFMrg7GSbl1sBfDuLVLyxw+yjdarPVm1JGfQ6eONEbNGgO+BdZxpwwZQ1uYeEJurAXMXb/AXT8GKYjKAyg==}
+  notion-md-crawler@1.0.0:
+    resolution: {integrity: sha512-mdB6zn/i32qO2C7X7wZLDpWvFryO3bPYMuBfFgmTPomnfEtIejdQJNVaZzw2GapM82lfWZ5dfsZp3s3UL4p1Fg==}
 
   npm-run-path@2.0.2:
     resolution: {integrity: sha512-lJxZYlT4DW/bRUtFh1MQIWqmLwQfAxnqWG4HhEdjMlkrJYnJn0Jrr2u3mgxqaWsdiBc76TYkTG/mhrnYTuzfHw==}
@@ -11356,10 +11375,6 @@ snapshots:
     dependencies:
       undici-types: 5.26.5
 
-  '@types/node@20.11.20':
-    dependencies:
-      undici-types: 5.26.5
-
   '@types/node@20.12.7':
     dependencies:
       undici-types: 5.26.5
@@ -15772,7 +15787,7 @@ snapshots:
 
   normalize-url@8.0.1: {}
 
-  notion-md-crawler@0.0.2(encoding@0.1.13):
+  notion-md-crawler@1.0.0(encoding@0.1.13):
     dependencies:
       '@notionhq/client': 2.2.15(encoding@0.1.13)
       md-utils-ts: 2.0.0
@@ -17787,26 +17802,6 @@ snapshots:
 
   ts-graphviz@1.8.2: {}
 
-  ts-node@10.9.2(@swc/core@1.4.16(@swc/helpers@0.5.2))(@types/node@20.12.7)(typescript@5.4.3):
-    dependencies:
-      '@cspotcode/source-map-support': 0.8.1
-      '@tsconfig/node10': 1.0.9
-      '@tsconfig/node12': 1.0.11
-      '@tsconfig/node14': 1.0.3
-      '@tsconfig/node16': 1.0.4
-      '@types/node': 20.12.7
-      acorn: 8.11.3
-      acorn-walk: 8.3.2
-      arg: 4.1.3
-      create-require: 1.1.1
-      diff: 4.0.2
-      make-error: 1.3.6
-      typescript: 5.4.3
-      v8-compile-cache-lib: 3.0.1
-      yn: 3.1.1
-    optionalDependencies:
-      '@swc/core': 1.4.16(@swc/helpers@0.5.2)
-
   ts-node@10.9.2(@swc/core@1.4.16(@swc/helpers@0.5.2))(@types/node@20.12.7)(typescript@5.4.5):
     dependencies:
       '@cspotcode/source-map-support': 0.8.1