Release 0.5.9 (#1070)

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

apps/docs/CHANGELOG.md

@@ -1,5 +1,61 @@
 # docs
 
+## 0.0.50
+
+### Patch Changes
+
+- Updated dependencies [15962b3]
+  - llamaindex@0.5.9
+
+## 0.0.49
+
+### Patch Changes
+
+- Updated dependencies [3d5ba08]
+- Updated dependencies [d917cdc]
+  - llamaindex@0.5.8
+
+## 0.0.48
+
+### Patch Changes
+
+- Updated dependencies [ec59acd]
+  - llamaindex@0.5.7
+
+## 0.0.47
+
+### Patch Changes
+
+- Updated dependencies [2562244]
+- Updated dependencies [325aa51]
+- Updated dependencies [ab700ea]
+- Updated dependencies [92f0782]
+- Updated dependencies [6cf6ae6]
+- Updated dependencies [b7cfe5b]
+  - llamaindex@0.5.6
+
+## 0.0.46
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - llamaindex@0.5.5
+
+## 0.0.45
+
+### Patch Changes
+
+- Updated dependencies [1a65ead]
+  - llamaindex@0.5.4
+
+## 0.0.44
+
+### Patch Changes
+
+- Updated dependencies [9bbbc67]
+- Updated dependencies [b3681bf]
+  - llamaindex@0.5.3
+
 ## 0.0.43
 
 ### Patch Changes

apps/docs/docs/modules/data_loaders/discord.mdx

@@ -0,0 +1,34 @@
+import CodeBlock from "@theme/CodeBlock";
+import CodeSource from "!raw-loader!../../../../../examples/readers/src/discord";
+
+# DiscordReader
+
+DiscordReader is a simple data loader that reads all messages in a given Discord channel and returns them as Document objects.
+It uses the [@discordjs/rest](https://github.com/discordjs/discord.js/tree/main/packages/rest) library to fetch the messages.
+
+## Usage
+
+First step is to create a Discord Application and generating a bot token [here](https://discord.com/developers/applications).
+In your Discord Application, go to the `OAuth2` tab and generate an invite URL by selecting `bot` and click `Read Messages/View Channels` as wells as `Read Message History`.
+This will invite the bot with the necessary permissions to read messages.
+Copy the URL in your browser and select the server you want your bot to join.
+
+<CodeBlock language="ts">{CodeSource}</CodeBlock>
+
+### Params
+
+#### DiscordReader()
+
+- `discordToken?`: The Discord bot token.
+- `makeRequest?`: Optionally provide a custom request function for edge environments, e.g. `fetch`. See discord.js for more info.
+
+#### DiscordReader.loadData
+
+- `channelIDs`: The ID(s) of discord channels as an array of strings.
+- `limit?`: Optionally limit the number of messages to read
+- `additionalInfo?`: An optional flag to include embedded messages and attachment urls in the document.
+- `oldestFirst?`: An optional flag to return the oldest messages first.
+
+## API Reference
+
+- [DiscordReader](../../api/classes/DiscordReader.md)

apps/docs/docs/modules/data_loaders/llama_parse/index.mdx

@@ -42,10 +42,13 @@ They can be divided into two groups.
 - `fastMode?` Optional. Set to true to use the fast mode. This mode will skip OCR of images, and table/heading reconstruction. Note: Non-compatible with `gpt4oMode`.
 - `doNotUnrollColumns?` Optional. Set to true to keep the text according to document layout. Reduce reconstruction accuracy, and LLMs/embeddings performances in most cases.
 - `pageSeparator?` Optional. The page separator to use. Defaults is `\\n---\\n`.
-- `gpt4oMode` set to true to use GPT-4o to extract content. Default is `false`.
-- `gpt4oApiKey?` Optional. Set the GPT-4o API key. Lowers the cost of parsing by using your own API key. Your OpenAI account will be charged. Can also be set in the environment variable `LLAMA_CLOUD_GPT4O_API_KEY`.
+- `gpt4oMode` Deprecated. Use vendorMultimodal params. Set to true to use GPT-4o to extract content. Default is `false`.
+- `gpt4oApiKey?` Deprecated. Use vendorMultimodal params. Optional. Set the GPT-4o API key. Lowers the cost of parsing by using your own API key. Your OpenAI account will be charged. Can also be set in the environment variable `LLAMA_CLOUD_GPT4O_API_KEY`.
 - `boundingBox?` Optional. Specify an area of the document to parse. Expects the bounding box margins as a string in clockwise order, e.g. `boundingBox = "0.1,0,0,0"` to not parse the top 10% of the document.
 - `targetPages?` Optional. Specify which pages to parse by specifying them as a comma-separated list. First page is `0`.
+- `useVendorMultimodalModel` set to true to use a multimodal model. Default is `false`.
+- `vendorMultimodalModel?` Optional. Specify which multimodal model to use. Default is GPT4o. See [here](https://docs.cloud.llamaindex.ai/llamaparse/features/multimodal) for a list of available models and cost.
+- `vendorMultimodalApiKey?` Optional. Set the multimodal model API key. Can also be set in the environment variable `LLAMA_CLOUD_VENDOR_MULTIMODAL_API_KEY`.
 - `numWorkers` as in the python version, is set in `SimpleDirectoryReader`. Default is 1.
 
 ### LlamaParse with SimpleDirectoryReader

apps/docs/docs/modules/llms/available_llms/bedrock.md

@@ -29,6 +29,9 @@ META_LLAMA2_13B_CHAT = "meta.llama2-13b-chat-v1";
 META_LLAMA2_70B_CHAT = "meta.llama2-70b-chat-v1";
 META_LLAMA3_8B_INSTRUCT = "meta.llama3-8b-instruct-v1:0";
 META_LLAMA3_70B_INSTRUCT = "meta.llama3-70b-instruct-v1:0";
+META_LLAMA3_1_8B_INSTRUCT = "meta.llama3-1-8b-instruct-v1:0"; // available on us-west-2
+META_LLAMA3_1_70B_INSTRUCT = "meta.llama3-1-70b-instruct-v1:0"; // available on us-west-2
+META_LLAMA3_1_405B_INSTRUCT = "meta.llama3-1-405b-instruct-v1:0"; // preview only, available on us-west-2
 ```
 
 Sonnet, Haiku and Opus are multimodal, image_url only supports base64 data url format, e.g. `data:image/jpeg;base64,SGVsbG8sIFdvcmxkIQ==`

apps/docs/docs/modules/node_postprocessors/cohere_reranker.md

@@ -39,8 +39,9 @@ const index = await VectorStoreIndex.fromDocuments([document]);
 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;
+const retriever = index.asRetriever({
+  similarityTopK: 5,
+});
 ```
 
 ## Create a new instance of the CohereRerank class

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

@@ -39,8 +39,9 @@ const index = await VectorStoreIndex.fromDocuments([document]);
 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;
+const retriever = index.asRetriever({
+  similarityTopK: 5,
+});
 ```
 
 ## Create a new instance of the JinaAIReranker class

apps/docs/docs/modules/node_postprocessors/mixedbreadiai_reranker.md

@@ -55,8 +55,9 @@ const index = await VectorStoreIndex.fromDocuments([document]);
 The default value for `similarityTopK` is 2, which means only the most similar document will be returned. To get more results, like picking a variety of fresh breads, you can increase the value of `similarityTopK`.
 
 ```ts
-const retriever = index.asRetriever();
-retriever.similarityTopK = 5;
+const retriever = index.asRetriever({
+  similarityTopK: 5,
+});
 ```
 
 ### Step 3: Create a MixedbreadAIReranker Instance

apps/docs/docs/modules/query_engines/metadata_filtering.md

@@ -75,7 +75,7 @@ const queryEngine = index.asQueryEngine({
       {
         key: "dogId",
         value: "2",
-        filterType: "ExactMatch",
+        operator: "==",
       },
     ],
   },
@@ -88,6 +88,8 @@ const response = await queryEngine.query({
 console.log(response.toString());
 ```
 
+Besides using the equal operator (`==`), you can also use a whole set of different [operators](../../api/interfaces/MetadataFilter.md#operator) to filter your documents.
+
 ## Full Code
 
 ```ts
@@ -135,7 +137,7 @@ async function main() {
           {
             key: "dogId",
             value: "2",
-            filterType: "ExactMatch",
+            operator: "==",
           },
         ],
       },
@@ -156,3 +158,4 @@ main();
 
 - [VectorStoreIndex](../../api/classes/VectorStoreIndex.md)
 - [ChromaVectorStore](../../api/classes/ChromaVectorStore.md)
+- [MetadataFilter](../../api/interfaces/MetadataFilter.md)

apps/docs/docs/modules/retriever.md

@@ -7,8 +7,9 @@ sidebar_position: 5
 A retriever in LlamaIndex is what is used to fetch `Node`s from an index using a query string. Aa `VectorIndexRetriever` will fetch the top-k most similar nodes. Meanwhile, a `SummaryIndexRetriever` will fetch all nodes no matter the query.
 
 ```typescript
-const retriever = vector_index.asRetriever();
-retriever.similarityTopK = 3;
+const retriever = vectorIndex.asRetriever({
+  similarityTopK: 3,
+});
 
 // Fetch nodes!
 const nodesWithScore = await retriever.retrieve({ query: "query string" });

apps/docs/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docs",
-  "version": "0.0.43",
+  "version": "0.0.50",
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",
@@ -34,10 +34,10 @@
     "@docusaurus/types": "3.4.0",
     "@tsconfig/docusaurus": "2.0.3",
     "@types/node": "^20.12.11",
-    "docusaurus-plugin-typedoc": "1.0.2",
-    "typedoc": "0.26.3",
+    "docusaurus-plugin-typedoc": "1.0.3",
+    "typedoc": "0.26.4",
     "typedoc-plugin-markdown": "4.1.2",
-    "typescript": "^5.5.2"
+    "typescript": "^5.5.3"
   },
   "browserslist": {
     "production": [

examples/chatEngine.ts

@@ -16,8 +16,9 @@ Settings.chunkSize = 512;
 async function main() {
   const document = new Document({ text: essay });
   const index = await VectorStoreIndex.fromDocuments([document]);
-  const retriever = index.asRetriever();
-  retriever.similarityTopK = 5;
+  const retriever = index.asRetriever({
+    similarityTopK: 5,
+  });
   const chatEngine = new ContextChatEngine({ retriever });
   const rl = readline.createInterface({ input, output });
 

examples/chromadb/preFilters.ts

@@ -40,7 +40,7 @@ async function main() {
           {
             key: "dogId",
             value: "2",
-            filterType: "ExactMatch",
+            operator: "==",
           },
         ],
       },

examples/longText.ts

@@ -1,17 +1,16 @@
 import {
   Document,
+  SentenceSplitter,
   Settings,
-  SimpleNodeParser,
   VectorStoreIndex,
 } from "llamaindex";
 
 export const STORAGE_DIR = "./data";
 
 // Update node parser
-Settings.nodeParser = new SimpleNodeParser({
+Settings.nodeParser = new SentenceSplitter({
   chunkSize: 512,
   chunkOverlap: 20,
-  splitLongSentences: true,
 });
 (async () => {
   // generate a document with a very long sentence (9000 words long)

examples/lowlevel.ts

@@ -27,11 +27,13 @@ import {
     },
   ];
 
-  const stream = await responseSynthesizer.synthesize({
-    query: "What age am I?",
-    nodesWithScore,
-    stream: true,
-  });
+  const stream = await responseSynthesizer.synthesize(
+    {
+      query: "What age am I?",
+      nodesWithScore,
+    },
+    true,
+  );
   for await (const chunk of stream) {
     process.stdout.write(chunk.response);
   }

examples/metadata-filter/milvus.ts

@@ -0,0 +1,40 @@
+import { MilvusVectorStore, VectorStoreIndex } from "llamaindex";
+
+const collectionName = "movie_reviews";
+
+async function main() {
+  try {
+    const milvus = new MilvusVectorStore({ collection: collectionName });
+    const index = await VectorStoreIndex.fromVectorStore(milvus);
+    const retriever = index.asRetriever({ similarityTopK: 20 });
+
+    console.log("\n=====\nQuerying the index with filters");
+    const queryEngineWithFilters = index.asQueryEngine({
+      retriever,
+      preFilters: {
+        filters: [
+          {
+            key: "document_id",
+            value: "./data/movie_reviews.csv_37",
+            operator: "==",
+          },
+          {
+            key: "document_id",
+            value: "./data/movie_reviews.csv_37",
+            operator: "!=",
+          },
+        ],
+        condition: "or",
+      },
+    });
+    const resultAfterFilter = await queryEngineWithFilters.query({
+      query: "Get all movie titles.",
+    });
+    console.log(`Query from ${resultAfterFilter.sourceNodes?.length} nodes`);
+    console.log(resultAfterFilter.response);
+  } catch (e) {
+    console.error(e);
+  }
+}
+
+void main();

examples/metadata-filter/simple.ts

@@ -0,0 +1,143 @@
+import {
+  Document,
+  Settings,
+  SimpleDocumentStore,
+  VectorStoreIndex,
+  storageContextFromDefaults,
+} from "llamaindex";
+
+Settings.callbackManager.on("retrieve-end", (event) => {
+  const { nodes } = event.detail;
+  console.log("Number of retrieved nodes:", nodes.length);
+});
+
+async function getDataSource() {
+  const docs = [
+    new Document({
+      text: "The dog is brown",
+      metadata: {
+        dogId: "1",
+        private: true,
+      },
+    }),
+    new Document({
+      text: "The dog is yellow",
+      metadata: {
+        dogId: "2",
+        private: false,
+      },
+    }),
+    new Document({
+      text: "The dog is red",
+      metadata: {
+        dogId: "3",
+        private: false,
+      },
+    }),
+  ];
+  const storageContext = await storageContextFromDefaults({
+    persistDir: "./cache",
+  });
+  const numberOfDocs = Object.keys(
+    (storageContext.docStore as SimpleDocumentStore).toDict(),
+  ).length;
+  if (numberOfDocs === 0) {
+    // Generate the data source if it's empty
+    return await VectorStoreIndex.fromDocuments(docs, {
+      storageContext,
+    });
+  }
+  return await VectorStoreIndex.init({
+    storageContext,
+  });
+}
+
+async function main() {
+  const index = await getDataSource();
+  console.log(
+    "=============\nQuerying index with no filters. The output should be any color.",
+  );
+  const queryEngineNoFilters = index.asQueryEngine({
+    similarityTopK: 3,
+  });
+  const noFilterResponse = await queryEngineNoFilters.query({
+    query: "What is the color of the dog?",
+  });
+  console.log("No filter response:", noFilterResponse.toString());
+
+  console.log(
+    "\n=============\nQuerying index with dogId 2 and private false. The output always should be red.",
+  );
+  const queryEngineEQ = index.asQueryEngine({
+    preFilters: {
+      filters: [
+        {
+          key: "private",
+          value: "false",
+          operator: "==",
+        },
+        {
+          key: "dogId",
+          value: "3",
+          operator: "==",
+        },
+      ],
+    },
+    similarityTopK: 3,
+  });
+  const responseEQ = await queryEngineEQ.query({
+    query: "What is the color of the dog?",
+  });
+  console.log("Filter with dogId 2 response:", responseEQ.toString());
+
+  console.log(
+    "\n=============\nQuerying index with dogId IN (1, 3). The output should be brown and red.",
+  );
+  const queryEngineIN = index.asQueryEngine({
+    preFilters: {
+      filters: [
+        {
+          key: "dogId",
+          value: ["1", "3"],
+          operator: "in",
+        },
+      ],
+    },
+    similarityTopK: 3,
+  });
+  const responseIN = await queryEngineIN.query({
+    query: "What is the color of the dog?",
+  });
+  console.log("Filter with dogId IN (1, 3) response:", responseIN.toString());
+
+  console.log(
+    "\n=============\nQuerying index with dogId IN (1, 3). The output should be any.",
+  );
+  const queryEngineOR = index.asQueryEngine({
+    preFilters: {
+      filters: [
+        {
+          key: "private",
+          value: "false",
+          operator: "==",
+        },
+        {
+          key: "dogId",
+          value: ["1", "3"],
+          operator: "in",
+        },
+      ],
+      condition: "or",
+    },
+    similarityTopK: 3,
+  });
+  const responseOR = await queryEngineOR.query({
+    query: "What is the color of the dog?",
+  });
+  console.log(
+    "Filter with dogId with OR operator response:",
+    responseOR.toString(),
+  );
+}
+
+void main();

examples/multimodal/jina.ts

@@ -0,0 +1,83 @@
+import {
+  ImageDocument,
+  JinaAIEmbedding,
+  similarity,
+  SimilarityType,
+  SimpleDirectoryReader,
+} from "llamaindex";
+import path from "path";
+
+async function main() {
+  const jina = new JinaAIEmbedding({
+    model: "jina-clip-v1",
+  });
+
+  // Get text embeddings
+  const text1 = "a car";
+  const textEmbedding1 = await jina.getTextEmbedding(text1);
+  const text2 = "a football match";
+  const textEmbedding2 = await jina.getTextEmbedding(text2);
+
+  // Get image embedding
+  const image =
+    "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg";
+  const imageEmbedding = await jina.getImageEmbedding(image);
+
+  // Calc similarity between text and image
+  const sim1 = similarity(
+    textEmbedding1,
+    imageEmbedding,
+    SimilarityType.DEFAULT,
+  );
+  const sim2 = similarity(
+    textEmbedding2,
+    imageEmbedding,
+    SimilarityType.DEFAULT,
+  );
+
+  console.log(`Similarity between "${text1}" and the image is ${sim1}`);
+  console.log(`Similarity between "${text2}" and the image is ${sim2}`);
+
+  // Get multiple text embeddings
+  const textEmbeddings = await jina.getTextEmbeddings([text1, text2]);
+  const sim3 = similarity(
+    textEmbeddings[0],
+    textEmbeddings[1],
+    SimilarityType.DEFAULT,
+  );
+  console.log(
+    `Similarity between the two texts "${text1}" and "${text2}" is ${sim3}`,
+  );
+
+  // Get multiple image embeddings
+  const catImg1 =
+    "https://i.pinimg.com/600x315/21/48/7e/21487e8e0970dd366dafaed6ab25d8d8.jpg";
+  const catImg2 =
+    "https://i.pinimg.com/736x/c9/f2/3e/c9f23e212529f13f19bad5602d84b78b.jpg";
+  const imageEmbeddings = await jina.getImageEmbeddings([catImg1, catImg2]);
+  const sim4 = similarity(
+    imageEmbeddings[0],
+    imageEmbeddings[1],
+    SimilarityType.DEFAULT,
+  );
+  console.log(`Similarity between the two online cat images is ${sim4}`);
+
+  // Get image embeddings from multiple local files
+  const documents = await new SimpleDirectoryReader().loadData({
+    directoryPath: path.join("multimodal", "data"),
+  });
+  const localImages = documents
+    .filter((doc) => doc instanceof ImageDocument)
+    .slice(0, 2); // Get only the first two images
+  const localImageEmbeddings = await jina.getImageEmbeddings(
+    localImages.map((doc) => (doc as ImageDocument).image),
+  );
+  const sim5 = similarity(
+    localImageEmbeddings[0],
+    localImageEmbeddings[1],
+    SimilarityType.DEFAULT,
+  );
+  console.log(`Similarity between the two local images is ${sim5}`);
+}
+
+void main();

examples/package.json

@@ -9,7 +9,7 @@
     "@llamaindex/core": "^0.1.0",
     "@notionhq/client": "^2.2.15",
     "@pinecone-database/pinecone": "^2.2.2",
-    "@zilliz/milvus2-sdk-node": "^2.4.2",
+    "@zilliz/milvus2-sdk-node": "^2.4.4",
     "chromadb": "^1.8.1",
     "commander": "^12.1.0",
     "dotenv": "^16.4.5",
@@ -21,7 +21,7 @@
   "devDependencies": {
     "@types/node": "^20.14.1",
     "tsx": "^4.15.6",
-    "typescript": "^5.5.2"
+    "typescript": "^5.5.3"
   },
   "scripts": {
     "lint": "eslint ."

examples/qdrantdb/preFilters.ts

@@ -64,7 +64,7 @@ async function main() {
           {
             key: "dogId",
             value: "2",
-            filterType: "ExactMatch",
+            operator: "==",
           },
         ],
       },

examples/readers/package.json

@@ -11,8 +11,10 @@
     "start:pdf": "node --import tsx ./src/pdf.ts",
     "start:llamaparse": "node --import tsx ./src/llamaparse.ts",
     "start:notion": "node --import tsx ./src/notion.ts",
+    "start:assemblyai": "node --import tsx ./src/assemblyai.ts",
     "start:llamaparse-dir": "node --import tsx ./src/simple-directory-reader-with-llamaparse.ts",
-    "start:llamaparse-json": "node --import tsx ./src/llamaparse-json.ts"
+    "start:llamaparse-json": "node --import tsx ./src/llamaparse-json.ts",
+    "start:discord": "node --import tsx ./src/discord.ts"
   },
   "dependencies": {
     "llamaindex": "*"
@@ -20,6 +22,6 @@
   "devDependencies": {
     "@types/node": "^20.12.11",
     "tsx": "^4.15.6",
-    "typescript": "^5.5.2"
+    "typescript": "^5.5.3"
   }
 }

examples/readers/src/discord.ts

@@ -0,0 +1,20 @@
+import { DiscordReader } from "llamaindex";
+
+async function main() {
+  // Create an instance of the DiscordReader. Set token here or DISCORD_TOKEN environment variable
+  const discordReader = new DiscordReader();
+
+  // Specify the channel IDs you want to read messages from as an arry of strings
+  const channelIds = ["721374320794009630", "719596376261918720"];
+
+  // Specify the number of messages to fetch per channel
+  const limit = 10;
+
+  // Load messages from the specified channel
+  const messages = await discordReader.loadData(channelIds, limit, true);
+
+  // Print out the messages
+  console.log(messages);
+}
+
+main().catch(console.error);

examples/rerankers/CohereReranker.ts

@@ -15,9 +15,9 @@ async function main() {
 
   const index = await VectorStoreIndex.fromDocuments([document]);
 
-  const retriever = index.asRetriever();
-
-  retriever.similarityTopK = 5;
+  const retriever = index.asRetriever({
+    similarityTopK: 5,
+  });
 
   const nodePostprocessor = new CohereRerank({
     apiKey: "<COHERE_API_KEY>",

examples/split.ts

@@ -8,7 +8,7 @@ async function main() {
 
   const textSplitter = new SentenceSplitter();
 
-  const chunks = textSplitter.splitTextWithOverlaps(essay);
+  const chunks = textSplitter.splitText(essay);
 
   console.log(chunks);
 }

examples/vectorIndexCustomize.ts

@@ -18,8 +18,9 @@ async function main() {
 
   const index = await VectorStoreIndex.fromDocuments([document]);
 
-  const retriever = index.asRetriever();
-  retriever.similarityTopK = 5;
+  const retriever = index.asRetriever({
+    similarityTopK: 5,
+  });
   const nodePostprocessor = new SimilarityPostprocessor({
     similarityCutoff: 0.7,
   });

package.json

@@ -21,19 +21,19 @@
     "@changesets/cli": "^2.27.5",
     "@typescript-eslint/eslint-plugin": "^7.13.1",
     "eslint": "^8.57.0",
-    "eslint-config-next": "^14.2.4",
+    "eslint-config-next": "^14.2.5",
     "eslint-config-prettier": "^9.1.0",
     "eslint-config-turbo": "^2.0.5",
-    "eslint-plugin-react": "7.34.1",
+    "eslint-plugin-react": "7.34.3",
     "husky": "^9.0.11",
     "lint-staged": "^15.2.7",
     "madge": "^7.0.0",
     "prettier": "^3.3.2",
-    "prettier-plugin-organize-imports": "^3.2.4",
+    "prettier-plugin-organize-imports": "^4.0.0",
     "turbo": "^2.0.5",
-    "typescript": "^5.5.2"
+    "typescript": "^5.5.3"
   },
-  "packageManager": "pnpm@9.4.0",
+  "packageManager": "pnpm@9.5.0",
   "pnpm": {
     "overrides": {
       "trim": "1.0.1",

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

@@ -5,7 +5,7 @@
   "dependencies": {
     "@llamaindex/autotool": "workspace:*",
     "llamaindex": "workspace:*",
-    "openai": "^4.52.0"
+    "openai": "^4.52.5"
   },
   "devDependencies": {
     "tsx": "^4.15.6"

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

@@ -1,5 +1,68 @@
 # @llamaindex/autotool-02-next-example
 
+## 0.1.34
+
+### Patch Changes
+
+- Updated dependencies [15962b3]
+  - llamaindex@0.5.9
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.33
+
+### Patch Changes
+
+- Updated dependencies [3d5ba08]
+- Updated dependencies [d917cdc]
+  - llamaindex@0.5.8
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.32
+
+### Patch Changes
+
+- Updated dependencies [ec59acd]
+  - llamaindex@0.5.7
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.31
+
+### Patch Changes
+
+- Updated dependencies [2562244]
+- Updated dependencies [325aa51]
+- Updated dependencies [ab700ea]
+- Updated dependencies [92f0782]
+- Updated dependencies [6cf6ae6]
+- Updated dependencies [b7cfe5b]
+  - llamaindex@0.5.6
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.30
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - llamaindex@0.5.5
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.29
+
+### Patch Changes
+
+- Updated dependencies [1a65ead]
+  - llamaindex@0.5.4
+  - @llamaindex/autotool@2.0.0
+
+## 0.1.28
+
+### Patch Changes
+
+- Updated dependencies [9bbbc67]
+- Updated dependencies [b3681bf]
+  - llamaindex@0.5.3
+  - @llamaindex/autotool@2.0.0
+
 ## 0.1.27
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool-02-next-example",
   "private": true,
-  "version": "0.1.27",
+  "version": "0.1.34",
   "scripts": {
     "dev": "next dev",
     "build": "next build",
@@ -14,7 +14,7 @@
     "class-variance-authority": "^0.7.0",
     "dotenv": "^16.3.1",
     "llamaindex": "workspace:*",
-    "lucide-react": "^0.378.0",
+    "lucide-react": "^0.407.0",
     "next": "14.3.0-canary.51",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
@@ -32,6 +32,6 @@
     "cross-env": "^7.0.3",
     "postcss": "^8.4.32",
     "tailwindcss": "^3.4.4",
-    "typescript": "^5.5.2"
+    "typescript": "^5.5.3"
   }
 }

packages/autotool/package.json

@@ -47,11 +47,11 @@
   "dependencies": {
     "@swc/core": "^1.6.3",
     "jotai": "^2.8.3",
-    "typedoc": "^0.25.13",
+    "typedoc": "^0.26.4",
     "unplugin": "^1.10.1"
   },
   "peerDependencies": {
-    "llamaindex": "^0.5.2",
+    "llamaindex": "^0.5.9",
     "openai": "^4",
     "typescript": "^4"
   },
@@ -72,11 +72,11 @@
     "@types/node": "^20.12.11",
     "bunchee": "5.3.0-beta.0",
     "llamaindex": "workspace:*",
-    "next": "14.2.3",
+    "next": "14.2.5",
     "rollup": "^4.18.0",
     "tsx": "^4.15.6",
-    "typescript": "^5.5.2",
-    "vitest": "^1.6.0",
+    "typescript": "^5.5.3",
+    "vitest": "^2.0.2",
     "webpack": "^5.92.1"
   }
 }

packages/community/CHANGELOG.md

@@ -1,5 +1,34 @@
 # @llamaindex/community
 
+## 0.0.24
+
+### Patch Changes
+
+- 3d9a802: feat: added llama 3.1
+- Updated dependencies [15962b3]
+  - @llamaindex/core@0.1.4
+
+## 0.0.23
+
+### Patch Changes
+
+- Updated dependencies [6cf6ae6]
+  - @llamaindex/core@0.1.3
+
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - @llamaindex/core@0.1.2
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [b3681bf]
+  - @llamaindex/core@0.1.1
+
 ## 0.0.20
 
 ### Patch Changes

packages/community/README.md

@@ -5,7 +5,7 @@
 ## Current Features:
 
 - Bedrock support for the Anthropic Claude Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock)
-- Bedrock support for the Meta LLama 2 and 3 Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock)
+- Bedrock support for the Meta LLama 2, 3 and 3.1 Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock)
 
 ## LICENSE
 

packages/community/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.20",
+  "version": "0.0.24",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",
@@ -46,7 +46,7 @@
     "bunchee": "5.3.0-beta.0"
   },
   "dependencies": {
-    "@aws-sdk/client-bedrock-runtime": "^3.600.0",
+    "@aws-sdk/client-bedrock-runtime": "^3.613.0",
     "@llamaindex/core": "workspace:*"
   }
 }

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

@@ -60,6 +60,9 @@ export enum BEDROCK_MODELS {
   META_LLAMA2_70B_CHAT = "meta.llama2-70b-chat-v1",
   META_LLAMA3_8B_INSTRUCT = "meta.llama3-8b-instruct-v1:0",
   META_LLAMA3_70B_INSTRUCT = "meta.llama3-70b-instruct-v1:0",
+  META_LLAMA3_1_8B_INSTRUCT = "meta.llama3-1-8b-instruct-v1:0",
+  META_LLAMA3_1_70B_INSTRUCT = "meta.llama3-1-70b-instruct-v1:0",
+  META_LLAMA3_1_405B_INSTRUCT = "meta.llama3-1-405b-instruct-v1:0",
   MISTRAL_7B_INSTRUCT = "mistral.mistral-7b-instruct-v0:2",
   MISTRAL_MIXTRAL_7B_INSTRUCT = "mistral.mixtral-8x7b-instruct-v0:1",
   MISTRAL_MIXTRAL_LARGE_2402 = "mistral.mistral-large-2402-v1:0",
@@ -94,6 +97,9 @@ const CHAT_ONLY_MODELS = {
   [BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 4096,
   [BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 8192,
   [BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT]: 8192,
+  [BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT]: 128000,
+  [BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT]: 128000,
+  [BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT]: 128000,
   [BEDROCK_MODELS.MISTRAL_7B_INSTRUCT]: 32000,
   [BEDROCK_MODELS.MISTRAL_MIXTRAL_7B_INSTRUCT]: 32000,
   [BEDROCK_MODELS.MISTRAL_MIXTRAL_LARGE_2402]: 32000,
@@ -121,6 +127,9 @@ export const STREAMING_MODELS = new Set([
   BEDROCK_MODELS.META_LLAMA2_70B_CHAT,
   BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT,
   BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT,
+  BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
   BEDROCK_MODELS.MISTRAL_7B_INSTRUCT,
   BEDROCK_MODELS.MISTRAL_MIXTRAL_7B_INSTRUCT,
   BEDROCK_MODELS.MISTRAL_MIXTRAL_LARGE_2402,
@@ -160,6 +169,9 @@ export const BEDROCK_MODEL_MAX_TOKENS: Partial<Record<BEDROCK_MODELS, number>> =
     [BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 2048,
     [BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 2048,
     [BEDROCK_MODELS.META_LLAMA3_70B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_1_8B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_1_70B_INSTRUCT]: 2048,
+    [BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT]: 2048,
   };
 
 const DEFAULT_BEDROCK_PARAMS = {

packages/core/CHANGELOG.md

@@ -1,5 +1,34 @@
 # @llamaindex/core
 
+## 0.1.4
+
+### Patch Changes
+
+- 15962b3: feat: node parser refactor
+
+  Align the text splitter logic with Python; it has almost the same logic as Python; Zod checks for input and better error messages and event system.
+
+  This change will not be considered a breaking change since it doesn't have a significant output difference from the last version,
+  but some edge cases will change, like the page separator and parameter for the constructor.
+
+## 0.1.3
+
+### Patch Changes
+
+- 6cf6ae6: feat: abstract query type
+
+## 0.1.2
+
+### Patch Changes
+
+- b974eea: Add support for Metadata filters
+
+## 0.1.1
+
+### Patch Changes
+
+- b3681bf: fix: DataCloneError when using FunctionTool
+
 ## 0.1.0
 
 ### Minor Changes

packages/core/package.json

@@ -1,9 +1,37 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.1.0",
+  "version": "0.1.4",
   "description": "LlamaIndex Core Module",
   "exports": {
+    "./node-parser": {
+      "require": {
+        "types": "./dist/node-parser/index.d.cts",
+        "default": "./dist/node-parser/index.cjs"
+      },
+      "import": {
+        "types": "./dist/node-parser/index.d.ts",
+        "default": "./dist/node-parser/index.js"
+      },
+      "default": {
+        "types": "./dist/node-parser/index.d.ts",
+        "default": "./dist/node-parser/index.js"
+      }
+    },
+    "./query-engine": {
+      "require": {
+        "types": "./dist/query-engine/index.d.cts",
+        "default": "./dist/query-engine/index.cjs"
+      },
+      "import": {
+        "types": "./dist/query-engine/index.d.ts",
+        "default": "./dist/query-engine/index.js"
+      },
+      "default": {
+        "types": "./dist/query-engine/index.d.ts",
+        "default": "./dist/query-engine/index.js"
+      }
+    },
     "./llms": {
       "require": {
         "types": "./dist/llms/index.d.cts",
@@ -32,6 +60,20 @@
         "default": "./dist/decorator/index.js"
       }
     },
+    "./embeddings": {
+      "require": {
+        "types": "./dist/embeddings/index.d.cts",
+        "default": "./dist/embeddings/index.cjs"
+      },
+      "import": {
+        "types": "./dist/embeddings/index.d.ts",
+        "default": "./dist/embeddings/index.js"
+      },
+      "default": {
+        "types": "./dist/embeddings/index.d.ts",
+        "default": "./dist/embeddings/index.js"
+      }
+    },
     "./global": {
       "require": {
         "types": "./dist/global/index.d.cts",
@@ -89,7 +131,8 @@
   },
   "devDependencies": {
     "ajv": "^8.16.0",
-    "bunchee": "5.3.0-beta.0"
+    "bunchee": "5.3.0-beta.0",
+    "natural": "^7.1.0"
   },
   "dependencies": {
     "@llamaindex/env": "workspace:*",

packages/core/src/embeddings/base.ts

@@ -1,9 +1,8 @@
-import type { MessageContentDetail } from "@llamaindex/core/llms";
-import type { BaseNode } from "@llamaindex/core/schema";
-import { MetadataMode } from "@llamaindex/core/schema";
-import { extractSingleText } from "@llamaindex/core/utils";
 import { type Tokenizers } from "@llamaindex/env";
-import type { TransformComponent } from "../ingestion/types.js";
+import type { MessageContentDetail } from "../llms";
+import type { TransformComponent } from "../schema";
+import { BaseNode, MetadataMode } from "../schema";
+import { extractSingleText } from "../utils";
 import { truncateMaxTokens } from "./tokenizer.js";
 import { SimilarityType, similarity } from "./utils.js";
 
@@ -17,6 +16,10 @@ export type EmbeddingInfo = {
   tokenizer?: Tokenizers;
 };
 
+export type BaseEmbeddingOptions = {
+  logProgress?: boolean;
+};
+
 export abstract class BaseEmbedding implements TransformComponent {
   embedBatchSize = DEFAULT_EMBED_BATCH_SIZE;
   embedInfo?: EmbeddingInfo;
@@ -45,7 +48,7 @@ export abstract class BaseEmbedding implements TransformComponent {
    * Optionally override this method to retrieve multiple embeddings in a single request
    * @param texts
    */
-  async getTextEmbeddings(texts: string[]): Promise<Array<number[]>> {
+  getTextEmbeddings = async (texts: string[]): Promise<Array<number[]>> => {
     const embeddings: number[][] = [];
 
     for (const text of texts) {
@@ -54,7 +57,7 @@ export abstract class BaseEmbedding implements TransformComponent {
     }
 
     return embeddings;
-  }
+  };
 
   /**
    * Get embeddings for a batch of texts
@@ -63,22 +66,23 @@ export abstract class BaseEmbedding implements TransformComponent {
    */
   async getTextEmbeddingsBatch(
     texts: string[],
-    options?: {
-      logProgress?: boolean;
-    },
+    options?: BaseEmbeddingOptions,
   ): Promise<Array<number[]>> {
     return await batchEmbeddings(
       texts,
-      this.getTextEmbeddings.bind(this),
+      this.getTextEmbeddings,
       this.embedBatchSize,
       options,
     );
   }
 
-  async transform(nodes: BaseNode[], _options?: any): Promise<BaseNode[]> {
+  async transform(
+    nodes: BaseNode[],
+    options?: BaseEmbeddingOptions,
+  ): Promise<BaseNode[]> {
     const texts = nodes.map((node) => node.getContent(MetadataMode.EMBED));
 
-    const embeddings = await this.getTextEmbeddingsBatch(texts, _options);
+    const embeddings = await this.getTextEmbeddingsBatch(texts, options);
 
     for (let i = 0; i < nodes.length; i++) {
       nodes[i].embedding = embeddings[i];
@@ -104,9 +108,7 @@ export async function batchEmbeddings<T>(
   values: T[],
   embedFunc: EmbedFunc<T>,
   chunkSize: number,
-  options?: {
-    logProgress?: boolean;
-  },
+  options?: BaseEmbeddingOptions,
 ): Promise<Array<number[]>> {
   const resultEmbeddings: Array<number[]> = [];
 

packages/core/src/embeddings/index.ts

@@ -0,0 +1,4 @@
+export { BaseEmbedding, batchEmbeddings } from "./base";
+export type { BaseEmbeddingOptions, EmbeddingInfo } from "./base";
+export { truncateMaxTokens } from "./tokenizer";
+export { DEFAULT_SIMILARITY_TOP_K, SimilarityType, similarity } from "./utils";

packages/core/src/embeddings/utils.ts

@@ -0,0 +1,64 @@
+export const DEFAULT_SIMILARITY_TOP_K = 2;
+
+/**
+ * Similarity type
+ * Default is cosine similarity. Dot product and negative Euclidean distance are also supported.
+ */
+export enum SimilarityType {
+  DEFAULT = "cosine",
+  DOT_PRODUCT = "dot_product",
+  EUCLIDEAN = "euclidean",
+}
+
+/**
+ * The similarity between two embeddings.
+ * @param embedding1
+ * @param embedding2
+ * @param mode
+ * @returns similarity score with higher numbers meaning the two embeddings are more similar
+ */
+
+export function similarity(
+  embedding1: number[],
+  embedding2: number[],
+  mode: SimilarityType = SimilarityType.DEFAULT,
+): number {
+  if (embedding1.length !== embedding2.length) {
+    throw new Error("Embedding length mismatch");
+  }
+
+  // NOTE I've taken enough Kahan to know that we should probably leave the
+  // numeric programming to numeric programmers. The naive approach here
+  // will probably cause some avoidable loss of floating point precision
+  // ml-distance is worth watching although they currently also use the naive
+  // formulas
+  function norm(x: number[]): number {
+    let result = 0;
+    for (let i = 0; i < x.length; i++) {
+      result += x[i] * x[i];
+    }
+    return Math.sqrt(result);
+  }
+
+  switch (mode) {
+    case SimilarityType.EUCLIDEAN: {
+      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];
+      }
+      return result;
+    }
+    case SimilarityType.DEFAULT: {
+      return (
+        similarity(embedding1, embedding2, SimilarityType.DOT_PRODUCT) /
+        (norm(embedding1) * norm(embedding2))
+      );
+    }
+    default:
+      throw new Error("Not implemented yet");
+  }
+}

packages/core/src/global/settings.ts

@@ -1,3 +1,4 @@
+import type { Tokenizer } from "@llamaindex/env";
 import {
   type CallbackManager,
   getCallbackManager,
@@ -9,8 +10,22 @@ import {
   setChunkSize,
   withChunkSize,
 } from "./settings/chunk-size";
+import {
+  getTokenizer,
+  setTokenizer,
+  withTokenizer,
+} from "./settings/tokenizer";
 
 export const Settings = {
+  get tokenizer() {
+    return getTokenizer();
+  },
+  set tokenizer(tokenizer) {
+    setTokenizer(tokenizer);
+  },
+  withTokenizer<Result>(tokenizer: Tokenizer, fn: () => Result): Result {
+    return withTokenizer(tokenizer, fn);
+  },
   get chunkSize(): number | undefined {
     return getChunkSize();
   },

packages/core/src/global/settings/callback-manager.ts

@@ -6,6 +6,7 @@ import type {
   ToolCall,
   ToolOutput,
 } from "../../llms";
+import { TextNode } from "../../schema";
 import { EventCaller, getEventCaller } from "../../utils/event-caller";
 import type { UUID } from "../type";
 
@@ -33,12 +34,32 @@ export type LLMStreamEvent = {
   chunk: ChatResponseChunk;
 };
 
+export type ChunkingStartEvent = {
+  text: string[];
+};
+
+export type ChunkingEndEvent = {
+  chunks: string[];
+};
+
+export type NodeParsingStartEvent = {
+  documents: TextNode[];
+};
+
+export type NodeParsingEndEvent = {
+  nodes: TextNode[];
+};
+
 export interface LlamaIndexEventMaps {
   "llm-start": LLMStartEvent;
   "llm-end": LLMEndEvent;
   "llm-tool-call": LLMToolCallEvent;
   "llm-tool-result": LLMToolResultEvent;
   "llm-stream": LLMStreamEvent;
+  "chunking-start": ChunkingStartEvent;
+  "chunking-end": ChunkingEndEvent;
+  "node-parsing-start": NodeParsingStartEvent;
+  "node-parsing-end": NodeParsingEndEvent;
 }
 
 export class LlamaIndexCustomEvent<T = any> extends CustomEvent<T> {
@@ -105,9 +126,7 @@ export class CallbackManager {
     }
     queueMicrotask(() => {
       cbs.forEach((handler) =>
-        handler(
-          LlamaIndexCustomEvent.fromEvent(event, structuredClone(detail)),
-        ),
+        handler(LlamaIndexCustomEvent.fromEvent(event, { ...detail })),
       );
     });
   }
@@ -118,14 +137,10 @@ export const globalCallbackManager = new CallbackManager();
 const callbackManagerAsyncLocalStorage =
   new AsyncLocalStorage<CallbackManager>();
 
-let currentCallbackManager: CallbackManager | null = null;
+let currentCallbackManager: CallbackManager = globalCallbackManager;
 
 export function getCallbackManager(): CallbackManager {
-  return (
-    callbackManagerAsyncLocalStorage.getStore() ??
-    currentCallbackManager ??
-    globalCallbackManager
-  );
+  return callbackManagerAsyncLocalStorage.getStore() ?? currentCallbackManager;
 }
 
 export function setCallbackManager(callbackManager: CallbackManager) {

packages/core/src/global/settings/chunk-size.ts

@@ -1,9 +1,9 @@
 import { AsyncLocalStorage } from "@llamaindex/env";
 
 const chunkSizeAsyncLocalStorage = new AsyncLocalStorage<number | undefined>();
-let globalChunkSize: number | null = null;
+let globalChunkSize: number = 1024;
 
-export function getChunkSize(): number | undefined {
+export function getChunkSize(): number {
   return globalChunkSize ?? chunkSizeAsyncLocalStorage.getStore();
 }
 

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

@@ -0,0 +1,21 @@
+import { AsyncLocalStorage, type Tokenizer, tokenizers } from "@llamaindex/env";
+
+const chunkSizeAsyncLocalStorage = new AsyncLocalStorage<Tokenizer>();
+let globalTokenizer: Tokenizer = tokenizers.tokenizer();
+
+export function getTokenizer(): Tokenizer {
+  return globalTokenizer ?? chunkSizeAsyncLocalStorage.getStore();
+}
+
+export function setTokenizer(tokenizer: Tokenizer | undefined) {
+  if (tokenizer !== undefined) {
+    globalTokenizer = tokenizer;
+  }
+}
+
+export function withTokenizer<Result>(
+  tokenizer: Tokenizer,
+  fn: () => Result,
+): Result {
+  return chunkSizeAsyncLocalStorage.run(tokenizer, fn);
+}

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

@@ -0,0 +1,147 @@
+import { Settings } from "../global";
+import {
+  BaseNode,
+  buildNodeFromSplits,
+  MetadataMode,
+  NodeRelationship,
+  TextNode,
+  type TransformComponent,
+} from "../schema";
+
+export abstract class NodeParser implements TransformComponent {
+  includeMetadata: boolean = true;
+  includePrevNextRel: boolean = true;
+
+  protected postProcessParsedNodes(
+    nodes: TextNode[],
+    parentDocMap: Map<string, TextNode>,
+  ): TextNode[] {
+    nodes.forEach((node, i) => {
+      const parentDoc = parentDocMap.get(node.sourceNode?.nodeId || "");
+
+      if (parentDoc) {
+        const startCharIdx = parentDoc.text.indexOf(
+          node.getContent(MetadataMode.NONE),
+        );
+        if (startCharIdx >= 0) {
+          node.startCharIdx = startCharIdx;
+          node.endCharIdx =
+            startCharIdx + node.getContent(MetadataMode.NONE).length;
+        }
+        if (this.includeMetadata && node.metadata && parentDoc.metadata) {
+          node.metadata = { ...node.metadata, ...parentDoc.metadata };
+        }
+      }
+
+      if (this.includePrevNextRel && node.sourceNode) {
+        const previousNode = i > 0 ? nodes[i - 1] : null;
+        const nextNode = i < nodes.length - 1 ? nodes[i + 1] : null;
+
+        if (
+          previousNode &&
+          previousNode.sourceNode &&
+          previousNode.sourceNode.nodeId === node.sourceNode.nodeId
+        ) {
+          node.relationships = {
+            ...node.relationships,
+            [NodeRelationship.PREVIOUS]: previousNode.asRelatedNodeInfo(),
+          };
+        }
+
+        if (
+          nextNode &&
+          nextNode.sourceNode &&
+          nextNode.sourceNode.nodeId === node.sourceNode.nodeId
+        ) {
+          node.relationships = {
+            ...node.relationships,
+            [NodeRelationship.NEXT]: nextNode.asRelatedNodeInfo(),
+          };
+        }
+      }
+    });
+
+    return nodes;
+  }
+
+  protected abstract parseNodes(
+    documents: TextNode[],
+    showProgress?: boolean,
+  ): TextNode[];
+
+  public getNodesFromDocuments(documents: TextNode[]): TextNode[] {
+    const docsId: Map<string, TextNode> = new Map(
+      documents.map((doc) => [doc.id_, doc]),
+    );
+    const callbackManager = Settings.callbackManager;
+
+    callbackManager.dispatchEvent("node-parsing-start", {
+      documents,
+    });
+
+    const nodes = this.postProcessParsedNodes(
+      this.parseNodes(documents),
+      docsId,
+    );
+
+    callbackManager.dispatchEvent("node-parsing-end", {
+      nodes,
+    });
+
+    return nodes;
+  }
+
+  async transform(nodes: BaseNode[], options?: {}): Promise<BaseNode[]> {
+    return this.getNodesFromDocuments(nodes as TextNode[]);
+  }
+}
+
+export abstract class TextSplitter extends NodeParser {
+  abstract splitText(text: string): string[];
+
+  public splitTexts(texts: string[]): string[] {
+    return texts.flatMap((text) => this.splitText(text));
+  }
+
+  protected parseNodes(nodes: TextNode[]): TextNode[] {
+    return nodes.reduce<TextNode[]>((allNodes, node) => {
+      const splits = this.splitText(node.getContent(MetadataMode.ALL));
+      const nodes = buildNodeFromSplits(splits, node);
+      return allNodes.concat(nodes);
+    }, []);
+  }
+}
+
+export abstract class MetadataAwareTextSplitter extends TextSplitter {
+  abstract splitTextMetadataAware(text: string, metadata: string): string[];
+
+  splitTextsMetadataAware(texts: string[], metadata: string[]): string[] {
+    if (texts.length !== metadata.length) {
+      throw new TypeError("`texts` and `metadata` must have the same length");
+    }
+    return texts.flatMap((text, i) =>
+      this.splitTextMetadataAware(text, metadata[i]),
+    );
+  }
+
+  protected getMetadataString(node: TextNode): string {
+    const embedStr = node.getMetadataStr(MetadataMode.EMBED);
+    const llmStr = node.getMetadataStr(MetadataMode.LLM);
+    if (embedStr.length > llmStr.length) {
+      return embedStr;
+    } else {
+      return llmStr;
+    }
+  }
+
+  protected parseNodes(nodes: TextNode[]): TextNode[] {
+    return nodes.reduce<TextNode[]>((allNodes, node) => {
+      const metadataStr = this.getMetadataString(node);
+      const splits = this.splitTextMetadataAware(
+        node.getContent(MetadataMode.ALL),
+        metadataStr,
+      );
+      return allNodes.concat(buildNodeFromSplits(splits, node));
+    }, []);
+  }
+}

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

@@ -0,0 +1,24 @@
+/**
+ * Current logic is based on the following implementation:
+ * @link @link https://github.com/run-llama/llama_index/blob/cc0ea90e7e72b8e4f5069aac981d56bb1d568323/llama-index-core/llama_index/core/node_parser
+ */
+import { SentenceSplitter } from "./sentence-splitter";
+
+/**
+ * @deprecated Use `SentenceSplitter` instead
+ */
+export const SimpleNodeParser = SentenceSplitter;
+
+export { MetadataAwareTextSplitter, NodeParser, TextSplitter } from "./base";
+export { MarkdownNodeParser } from "./markdown";
+export { SentenceSplitter } from "./sentence-splitter";
+export { SentenceWindowNodeParser } from "./sentence-window";
+export type { SplitterParams } from "./type";
+export {
+  splitByChar,
+  splitByPhraseRegex,
+  splitByRegex,
+  splitBySentenceTokenizer,
+  splitBySep,
+} from "./utils";
+export type { TextSplitterFn } from "./utils";

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

@@ -0,0 +1,87 @@
+import {
+  buildNodeFromSplits,
+  type Metadata,
+  MetadataMode,
+  TextNode,
+} from "../schema";
+import { NodeParser } from "./base";
+
+export class MarkdownNodeParser extends NodeParser {
+  override parseNodes(nodes: TextNode[], showProgress?: boolean): TextNode[] {
+    return nodes.reduce<TextNode[]>((allNodes, node) => {
+      const markdownNodes = this.getNodesFromNode(node);
+      return allNodes.concat(markdownNodes);
+    }, []);
+  }
+
+  protected getNodesFromNode(node: TextNode): TextNode[] {
+    const text = node.getContent(MetadataMode.NONE);
+    const markdownNodes: TextNode[] = [];
+    const lines = text.split("\n");
+    let metadata: { [key: string]: string } = {};
+    let codeBlock = false;
+    let currentSection = "";
+
+    for (const line of lines) {
+      if (line.trim().startsWith("```")) {
+        codeBlock = !codeBlock;
+      }
+      const headerMatch = /^(#+)\s(.*)/.exec(line);
+      if (headerMatch && !codeBlock) {
+        if (currentSection !== "") {
+          markdownNodes.push(
+            this.buildNodeFromSplit(currentSection.trim(), node, metadata),
+          );
+        }
+        metadata = this.updateMetadata(
+          metadata,
+          headerMatch[2],
+          headerMatch[1].trim().length,
+        );
+        currentSection = `${headerMatch[2]}\n`;
+      } else {
+        currentSection += line + "\n";
+      }
+    }
+
+    if (currentSection !== "") {
+      markdownNodes.push(
+        this.buildNodeFromSplit(currentSection.trim(), node, metadata),
+      );
+    }
+
+    return markdownNodes;
+  }
+
+  private updateMetadata(
+    headersMetadata: { [key: string]: string },
+    newHeader: string,
+    newHeaderLevel: number,
+  ): { [key: string]: string } {
+    const updatedHeaders: { [key: string]: string } = {};
+
+    for (let i = 1; i < newHeaderLevel; i++) {
+      const key = `Header_${i}`;
+      if (key in headersMetadata) {
+        updatedHeaders[key] = headersMetadata[key];
+      }
+    }
+
+    updatedHeaders[`Header_${newHeaderLevel}`] = newHeader;
+    return updatedHeaders;
+  }
+
+  private buildNodeFromSplit(
+    textSplit: string,
+    node: TextNode,
+    metadata: Metadata,
+  ): TextNode {
+    const newNode = buildNodeFromSplits([textSplit], node, undefined)[0];
+
+    if (this.includeMetadata) {
+      newNode.metadata = { ...newNode.metadata, ...metadata };
+    }
+
+    return newNode;
+  }
+}

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

@@ -0,0 +1,226 @@
+import type { Tokenizer } from "@llamaindex/env";
+import { z } from "zod";
+import { Settings } from "../global";
+import { sentenceSplitterSchema } from "../schema";
+import { MetadataAwareTextSplitter } from "./base";
+import type { SplitterParams } from "./type";
+import {
+  splitByChar,
+  splitByRegex,
+  splitBySentenceTokenizer,
+  splitBySep,
+  type TextSplitterFn,
+} from "./utils";
+
+type _Split = {
+  text: string;
+  isSentence: boolean;
+  tokenSize: number;
+};
+
+/**
+ * Parse text with a preference for complete sentences.
+ */
+export class SentenceSplitter extends MetadataAwareTextSplitter {
+  /**
+   * The token chunk size for each chunk.
+   */
+  chunkSize: number = 1024;
+  /**
+   * The token overlap of each chunk when splitting.
+   */
+  chunkOverlap: number = 200;
+  /**
+   * Default separator for splitting into words
+   */
+  separator: string = " ";
+  /**
+   * Separator between paragraphs.
+   */
+  paragraphSeparator: string = "\n\n\n";
+  /**
+   * Backup regex for splitting into sentences.
+   */
+  secondaryChunkingRegex: string = "[^,.;。？！]+[,.;。？！]?";
+
+  #chunkingTokenizerFn = splitBySentenceTokenizer();
+  #splitFns: Set<TextSplitterFn> = new Set();
+  #subSentenceSplitFns: Set<TextSplitterFn> = new Set();
+  #tokenizer: Tokenizer;
+
+  constructor(
+    params?: z.input<typeof sentenceSplitterSchema> & SplitterParams,
+  ) {
+    super();
+    if (params) {
+      const parsedParams = sentenceSplitterSchema.parse(params);
+      this.chunkSize = parsedParams.chunkSize;
+      this.chunkOverlap = parsedParams.chunkOverlap;
+      this.separator = parsedParams.separator;
+      this.paragraphSeparator = parsedParams.paragraphSeparator;
+      this.secondaryChunkingRegex = parsedParams.secondaryChunkingRegex;
+    }
+    this.#tokenizer = params?.tokenizer ?? Settings.tokenizer;
+    this.#splitFns.add(splitBySep(this.paragraphSeparator));
+    this.#splitFns.add(this.#chunkingTokenizerFn);
+
+    this.#subSentenceSplitFns.add(splitByRegex(this.secondaryChunkingRegex));
+    this.#subSentenceSplitFns.add(splitBySep(this.separator));
+    this.#subSentenceSplitFns.add(splitByChar());
+  }
+
+  splitTextMetadataAware(text: string, metadata: string): string[] {
+    const metadataLength = this.tokenSize(metadata);
+    const effectiveChunkSize = this.chunkSize - metadataLength;
+    if (effectiveChunkSize <= 0) {
+      throw new Error(
+        `Metadata length (${metadataLength}) is longer than chunk size (${this.chunkSize}). Consider increasing the chunk size or decreasing the size of your metadata to avoid this.`,
+      );
+    } else if (effectiveChunkSize < 50) {
+      console.log(
+        `Metadata length (${metadataLength}) is close to chunk size (${this.chunkSize}). Resulting chunks are less than 50 tokens. Consider increasing the chunk size or decreasing the size of your metadata to avoid this.`,
+      );
+    }
+    return this._splitText(text, effectiveChunkSize);
+  }
+
+  splitText(text: string): string[] {
+    return this._splitText(text, this.chunkSize);
+  }
+
+  _splitText(text: string, chunkSize: number): string[] {
+    if (text === "") return [text];
+
+    const callbackManager = Settings.callbackManager;
+
+    callbackManager.dispatchEvent("chunking-start", {
+      text: [text],
+    });
+    const splits = this.#split(text, chunkSize);
+    const chunks = this.#merge(splits, chunkSize);
+
+    callbackManager.dispatchEvent("chunking-end", {
+      chunks,
+    });
+    return chunks;
+  }
+
+  #split(text: string, chunkSize: number): _Split[] {
+    const tokenSize = this.tokenSize(text);
+    if (tokenSize <= chunkSize) {
+      return [
+        {
+          text,
+          isSentence: true,
+          tokenSize,
+        },
+      ];
+    }
+    const [textSplitsByFns, isSentence] = this.#getSplitsByFns(text);
+    const textSplits: _Split[] = [];
+
+    for (const textSplit of textSplitsByFns) {
+      const tokenSize = this.tokenSize(textSplit);
+      if (tokenSize <= chunkSize) {
+        textSplits.push({
+          text: textSplit,
+          isSentence,
+          tokenSize,
+        });
+      } else {
+        const recursiveTextSplits = this.#split(textSplit, chunkSize);
+        textSplits.push(...recursiveTextSplits);
+      }
+    }
+    return textSplits;
+  }
+
+  #getSplitsByFns(text: string): [splits: string[], isSentence: boolean] {
+    for (const splitFn of this.#splitFns) {
+      const splits = splitFn(text);
+      if (splits.length > 1) {
+        return [splits, true];
+      }
+    }
+    for (const splitFn of this.#subSentenceSplitFns) {
+      const splits = splitFn(text);
+      if (splits.length > 1) {
+        return [splits, false];
+      }
+    }
+    return [[text], true];
+  }
+
+  #merge(splits: _Split[], chunkSize: number): string[] {
+    const chunks: string[] = [];
+    let currentChunk: [string, number][] = [];
+    let lastChunk: [string, number][] = [];
+    let currentChunkLength = 0;
+    let newChunk = true;
+
+    const closeChunk = (): void => {
+      chunks.push(currentChunk.map(([text]) => text).join(""));
+      lastChunk = currentChunk;
+      currentChunk = [];
+      currentChunkLength = 0;
+      newChunk = true;
+
+      let lastIndex = lastChunk.length - 1;
+      while (
+        lastIndex >= 0 &&
+        currentChunkLength + lastChunk[lastIndex][1] <= this.chunkOverlap
+      ) {
+        const [text, length] = lastChunk[lastIndex];
+        currentChunkLength += length;
+        currentChunk.unshift([text, length]);
+        lastIndex -= 1;
+      }
+    };
+
+    while (splits.length > 0) {
+      const curSplit = splits[0];
+      if (curSplit.tokenSize > chunkSize) {
+        throw new Error("Single token exceeded chunk size");
+      }
+      if (currentChunkLength + curSplit.tokenSize > chunkSize && !newChunk) {
+        closeChunk();
+      } else {
+        if (
+          curSplit.isSentence ||
+          currentChunkLength + curSplit.tokenSize <= chunkSize ||
+          newChunk
+        ) {
+          currentChunkLength += curSplit.tokenSize;
+          currentChunk.push([curSplit.text, curSplit.tokenSize]);
+          splits.shift();
+          newChunk = false;
+        } else {
+          closeChunk();
+        }
+      }
+    }
+
+    // Handle the last chunk
+    if (!newChunk) {
+      chunks.push(currentChunk.map(([text]) => text).join(""));
+    }
+
+    return this.#postprocessChunks(chunks);
+  }
+
+  /**
+   * Remove whitespace only chunks and remove leading and trailing whitespace.
+   */
+  #postprocessChunks(chunks: string[]): string[] {
+    const newChunks: string[] = [];
+    for (const chunk of chunks) {
+      const trimmedChunk = chunk.trim();
+      if (trimmedChunk !== "") {
+        newChunks.push(trimmedChunk);
+      }
+    }
+    return newChunks;
+  }
+
+  tokenSize = (text: string) => this.#tokenizer.encode(text).length;
+}

packages/core/src/node-parser/sentence-tokenizer-parser.d.ts

@@ -0,0 +1,5 @@
+declare class SentenceTokenizer {
+  tokenize(text: string): string[];
+}
+
+export { SentenceTokenizer as default };

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

@@ -0,0 +1,85 @@
+import { randomUUID } from "@llamaindex/env";
+import { z } from "zod";
+import {
+  buildNodeFromSplits,
+  Document,
+  sentenceWindowNodeParserSchema,
+  TextNode,
+} from "../schema";
+import { NodeParser } from "./base";
+import { splitBySentenceTokenizer, type TextSplitterFn } from "./utils";
+
+export class SentenceWindowNodeParser extends NodeParser {
+  static DEFAULT_WINDOW_SIZE = 3;
+  static DEFAULT_WINDOW_METADATA_KEY = "window";
+  static DEFAULT_ORIGINAL_TEXT_METADATA_KEY = "originalText";
+
+  windowSize: number;
+  windowMetadataKey: string;
+  originalTextMetadataKey: string;
+  sentenceSplitter: TextSplitterFn = splitBySentenceTokenizer();
+  idGenerator: () => string = () => randomUUID();
+
+  constructor(params?: z.input<typeof sentenceWindowNodeParserSchema>) {
+    super();
+    if (params) {
+      const parsedParams = sentenceWindowNodeParserSchema.parse(params);
+      this.windowSize = parsedParams.windowSize;
+      this.windowMetadataKey = parsedParams.windowMetadataKey;
+      this.originalTextMetadataKey = parsedParams.originalTextMetadataKey;
+    } else {
+      this.windowSize = SentenceWindowNodeParser.DEFAULT_WINDOW_SIZE;
+      this.windowMetadataKey =
+        SentenceWindowNodeParser.DEFAULT_WINDOW_METADATA_KEY;
+      this.originalTextMetadataKey =
+        SentenceWindowNodeParser.DEFAULT_ORIGINAL_TEXT_METADATA_KEY;
+    }
+  }
+
+  override parseNodes(nodes: TextNode[], showProgress?: boolean): TextNode[] {
+    return nodes.reduce<TextNode[]>((allNodes, node) => {
+      const nodes = this.buildWindowNodesFromDocuments([node]);
+      return allNodes.concat(nodes);
+    }, []);
+  }
+
+  buildWindowNodesFromDocuments(documents: Document[]): TextNode[] {
+    const allNodes: TextNode[] = [];
+
+    for (const doc of documents) {
+      const text = doc.text;
+      const textSplits = this.sentenceSplitter(text);
+      const nodes = buildNodeFromSplits(
+        textSplits,
+        doc,
+        undefined,
+        this.idGenerator,
+      );
+
+      nodes.forEach((node, i) => {
+        const windowNodes = nodes.slice(
+          Math.max(0, i - this.windowSize),
+          Math.min(i + this.windowSize + 1, nodes.length),
+        );
+
+        node.metadata[this.windowMetadataKey] = windowNodes
+          .map((n) => n.text)
+          .join(" ");
+        node.metadata[this.originalTextMetadataKey] = node.text;
+
+        node.excludedEmbedMetadataKeys.push(
+          this.windowMetadataKey,
+          this.originalTextMetadataKey,
+        );
+        node.excludedLlmMetadataKeys.push(
+          this.windowMetadataKey,
+          this.originalTextMetadataKey,
+        );
+      });
+
+      allNodes.push(...nodes);
+    }
+
+    return allNodes;
+  }
+}

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

@@ -0,0 +1,5 @@
+import type { Tokenizer } from "@llamaindex/env";
+
+export type SplitterParams = {
+  tokenizer?: Tokenizer;
+};

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

@@ -0,0 +1,53 @@
+import type { TextSplitter } from "./base";
+import SentenceTokenizerNew from "./sentence-tokenizer-parser.js";
+
+export type TextSplitterFn = (text: string) => string[];
+
+const truncateText = (text: string, textSplitter: TextSplitter): string => {
+  const chunks = textSplitter.splitText(text);
+  return chunks[0];
+};
+
+const splitTextKeepSeparator = (text: string, separator: string): string[] => {
+  const parts = text.split(separator);
+  const result = parts.map((part, index) =>
+    index > 0 ? separator + part : part,
+  );
+  return result.filter((s) => s);
+};
+
+export const splitBySep = (
+  sep: string,
+  keepSep: boolean = true,
+): TextSplitterFn => {
+  if (keepSep) {
+    return (text: string) => splitTextKeepSeparator(text, sep);
+  } else {
+    return (text: string) => text.split(sep);
+  }
+};
+
+export const splitByChar = (): TextSplitterFn => {
+  return (text: string) => text.split("");
+};
+
+let sentenceTokenizer: SentenceTokenizerNew | null = null;
+
+export const splitBySentenceTokenizer = (): TextSplitterFn => {
+  if (!sentenceTokenizer) {
+    sentenceTokenizer = new SentenceTokenizerNew();
+  }
+  const tokenizer = sentenceTokenizer;
+  return (text: string) => {
+    return tokenizer.tokenize(text);
+  };
+};
+
+export const splitByRegex = (regex: string): TextSplitterFn => {
+  return (text: string) => text.match(new RegExp(regex, "g")) || [];
+};
+
+export const splitByPhraseRegex = (): TextSplitterFn => {
+  const regex = "[^,.;]+[,.;]?";
+  return splitByRegex(regex);
+};

packages/core/src/query-engine/base.ts

@@ -0,0 +1,29 @@
+import type { MessageContent } from "../llms";
+import { EngineResponse, type NodeWithScore } from "../schema";
+
+/**
+ * @link https://docs.llamaindex.ai/en/stable/api_reference/schema/?h=querybundle#llama_index.core.schema.QueryBundle
+ *
+ *  We don't have `image_path` here, because it is included in the `query` field.
+ */
+export type QueryBundle = {
+  query: MessageContent;
+  customEmbeddings?: string[];
+  embeddings?: number[];
+};
+
+export type QueryType = string | QueryBundle;
+
+export interface BaseQueryEngine {
+  query(
+    strOrQueryBundle: QueryType,
+    stream: true,
+  ): Promise<AsyncIterable<EngineResponse>>;
+  query(strOrQueryBundle: QueryType, stream?: false): Promise<EngineResponse>;
+
+  synthesize?(
+    strOrQueryBundle: QueryType,
+    nodes: NodeWithScore[],
+    additionalSources?: Iterator<NodeWithScore>,
+  ): Promise<EngineResponse>;
+}

packages/core/src/query-engine/index.ts

@@ -0,0 +1 @@
+export type { BaseQueryEngine, QueryBundle, QueryType } from "./base";

packages/core/src/schema/index.ts

@@ -1,2 +1,4 @@
 export * from "./node";
+export type { TransformComponent } from "./type";
+export { EngineResponse } from "./type/engine–response";
 export * from "./zod";

packages/core/src/schema/node.ts

@@ -450,3 +450,48 @@ export function splitNodesByType(nodes: BaseNode[]): NodesByType {
   }
   return result;
 }
+
+export function buildNodeFromSplits(
+  textSplits: string[],
+  doc: BaseNode,
+  refDoc: BaseNode = doc,
+  idGenerator: (idx: number, refDoc: BaseNode) => string = () => randomUUID(),
+) {
+  const nodes: TextNode[] = [];
+  const relationships = {
+    [NodeRelationship.SOURCE]: refDoc.asRelatedNodeInfo(),
+  };
+
+  textSplits.forEach((textChunk, i) => {
+    if (doc instanceof ImageDocument) {
+      const imageNode = new ImageNode({
+        id_: idGenerator(i, doc),
+        text: textChunk,
+        image: doc.image,
+        embedding: doc.embedding,
+        excludedEmbedMetadataKeys: [...doc.excludedEmbedMetadataKeys],
+        excludedLlmMetadataKeys: [...doc.excludedLlmMetadataKeys],
+        metadataSeparator: doc.metadataSeparator,
+        textTemplate: doc.textTemplate,
+        relationships: { ...relationships },
+      });
+      nodes.push(imageNode);
+    } else if (doc instanceof Document || doc instanceof TextNode) {
+      const node = new TextNode({
+        id_: idGenerator(i, doc),
+        text: textChunk,
+        embedding: doc.embedding,
+        excludedEmbedMetadataKeys: [...doc.excludedEmbedMetadataKeys],
+        excludedLlmMetadataKeys: [...doc.excludedLlmMetadataKeys],
+        metadataSeparator: doc.metadataSeparator,
+        textTemplate: doc.textTemplate,
+        relationships: { ...relationships },
+      });
+      nodes.push(node);
+    } else {
+      throw new Error(`Unknown document type: ${doc.type}`);
+    }
+  });
+
+  return nodes;
+}

packages/core/src/schema/type.ts

@@ -0,0 +1,8 @@
+import type { BaseNode } from "./node";
+
+export interface TransformComponent {
+  transform<Options extends Record<string, unknown>>(
+    nodes: BaseNode[],
+    options?: Options,
+  ): Promise<BaseNode[]>;
+}

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

@@ -1,20 +1,16 @@
-import type {
-  ChatMessage,
-  ChatResponse,
-  ChatResponseChunk,
-} from "@llamaindex/core/llms";
-import type { NodeWithScore } from "@llamaindex/core/schema";
-import { extractText } from "@llamaindex/core/utils";
+import type { ChatMessage, ChatResponse, ChatResponseChunk } from "../../llms";
+import { extractText } from "../../utils";
+import type { Metadata, NodeWithScore } from "../node";
 
 export class EngineResponse implements ChatResponse, ChatResponseChunk {
   sourceNodes?: NodeWithScore[];
 
-  metadata: Record<string, unknown> = {};
+  metadata: Metadata = {};
 
   message: ChatMessage;
   raw: object | null;
 
-  #stream: boolean;
+  readonly stream: boolean;
 
   private constructor(
     chatResponse: ChatResponse,
@@ -24,7 +20,7 @@ export class EngineResponse implements ChatResponse, ChatResponseChunk {
     this.message = chatResponse.message;
     this.raw = chatResponse.raw;
     this.sourceNodes = sourceNodes;
-    this.#stream = stream;
+    this.stream = stream;
   }
 
   static fromResponse(
@@ -70,13 +66,15 @@ export class EngineResponse implements ChatResponse, ChatResponseChunk {
     );
   }
 
-  // @deprecated use 'message' instead
+  /**
+   * @deprecated Use `message` instead.
+   */
   get response(): string {
     return extractText(this.message.content);
   }
 
   get delta(): string {
-    if (!this.#stream) {
+    if (!this.stream) {
       console.warn(
         "delta is only available for streaming responses. Consider using 'message' instead.",
       );
@@ -84,7 +82,7 @@ export class EngineResponse implements ChatResponse, ChatResponseChunk {
     return extractText(this.message.content);
   }
 
-  toString() {
+  toString(): string {
     return this.response ?? "";
   }
 }

packages/core/src/schema/zod.ts

@@ -1,4 +1,5 @@
 import { z } from "zod";
+import { Settings } from "../global";
 
 export const anyFunctionSchema = z.function(z.tuple([]).rest(z.any()), z.any());
 
@@ -16,3 +17,62 @@ export const baseToolSchema = z.object({
 export const baseToolWithCallSchema = baseToolSchema.extend({
   call: z.function(),
 });
+
+export const sentenceSplitterSchema = z
+  .object({
+    chunkSize: z
+      .number({
+        description: "The token chunk size for each chunk.",
+      })
+      .gt(0)
+      .optional()
+      .default(() => Settings.chunkSize ?? 1024),
+    chunkOverlap: z
+      .number({
+        description: "The token overlap of each chunk when splitting.",
+      })
+      .gte(0)
+      .optional()
+      .default(200),
+    separator: z
+      .string({
+        description: "Default separator for splitting into words",
+      })
+      .default(" "),
+    paragraphSeparator: z
+      .string({
+        description: "Separator between paragraphs.",
+      })
+      .optional()
+      .default("\n\n\n"),
+    secondaryChunkingRegex: z
+      .string({
+        description: "Backup regex for splitting into sentences.",
+      })
+      .optional()
+      .default("[^,.;。？！]+[,.;。？！]?"),
+  })
+  .refine(
+    (data) => data.chunkOverlap < data.chunkSize,
+    "Chunk overlap must be less than chunk size.",
+  );
+
+export const sentenceWindowNodeParserSchema = z.object({
+  windowSize: z
+    .number({
+      description:
+        "The number of sentences on each side of a sentence to capture.",
+    })
+    .gt(0)
+    .default(3),
+  windowMetadataKey: z
+    .string({
+      description: "The metadata key to store the sentence window under.",
+    })
+    .default("window"),
+  originalTextMetadataKey: z
+    .string({
+      description: "The metadata key to store the original sentence in.",
+    })
+    .default("originalText"),
+});

packages/core/src/utils/llms.ts

@@ -3,15 +3,22 @@ import type {
   MessageContentDetail,
   MessageContentTextDetail,
 } from "../llms";
+import type { QueryType } from "../query-engine";
 import type { ImageType } from "../schema";
 
 /**
- * Extracts just the text from a multi-modal message or the message itself if it's just text.
+ * Extracts just the text whether from
+ *  a multi-modal message
+ *  a single text message
+ *  or a query
  *
  * @param message The message to extract text from.
  * @returns The extracted text
  */
-export function extractText(message: MessageContent): string {
+export function extractText(message: MessageContent | QueryType): string {
+  if (typeof message === "object" && "query" in message) {
+    return extractText(message.query);
+  }
   if (typeof message !== "string" && !Array.isArray(message)) {
     console.warn(
       "extractText called with non-MessageContent message, this is likely a bug.",

packages/core/src/utils/wrap-llm-event.ts

@@ -1,5 +1,5 @@
 import { AsyncLocalStorage, randomUUID } from "@llamaindex/env";
-import { getCallbackManager } from "../global/settings/callback-manager";
+import { Settings } from "../global";
 import type { ChatResponse, ChatResponseChunk, LLM, LLMChat } from "../llms";
 
 export function wrapLLMEvent<
@@ -21,7 +21,7 @@ export function wrapLLMEvent<
     LLMChat<AdditionalChatOptions, AdditionalMessageOptions>["chat"]
   > {
     const id = randomUUID();
-    getCallbackManager().dispatchEvent("llm-start", {
+    Settings.callbackManager.dispatchEvent("llm-start", {
       id,
       messages: params[0].messages,
     });
@@ -55,7 +55,7 @@ export function wrapLLMEvent<
               ...chunk.options,
             };
           }
-          getCallbackManager().dispatchEvent("llm-stream", {
+          Settings.callbackManager.dispatchEvent("llm-stream", {
             id,
             chunk,
           });
@@ -63,14 +63,14 @@ export function wrapLLMEvent<
           yield chunk;
         }
         snapshot(() => {
-          getCallbackManager().dispatchEvent("llm-end", {
+          Settings.callbackManager.dispatchEvent("llm-end", {
             id,
             response: finalResponse,
           });
         });
       };
     } else {
-      getCallbackManager().dispatchEvent("llm-end", {
+      Settings.callbackManager.dispatchEvent("llm-end", {
         id,
         response,
       });

packages/core/tests/embeddings.test.ts

@@ -1,6 +1,6 @@
+import { truncateMaxTokens } from "@llamaindex/core/embeddings";
 import { Tokenizers, tokenizers } from "@llamaindex/env";
 import { describe, expect, test } from "vitest";
-import { truncateMaxTokens } from "../../src/embeddings/tokenizer.js";
 
 describe("truncateMaxTokens", () => {
   const tokenizer = tokenizers.tokenizer(Tokenizers.CL100K_BASE);

packages/core/tests/event-system.test.ts

@@ -6,6 +6,9 @@ declare module "@llamaindex/core/global" {
     test: {
       value: number;
     };
+    functionTest: {
+      fn: ({ x }: { x: number }) => string;
+    };
   }
 }
 
@@ -42,6 +45,25 @@ describe("event system", () => {
     expect(callback).toHaveBeenCalledTimes(1);
   });
 
+  test("dispatch function tool event", async () => {
+    const testFunction = ({ x }: { x: number }) => `${x * 2}`;
+    let callback;
+    Settings.callbackManager.on(
+      "functionTest",
+      (callback = vi.fn((event) => {
+        const data = event.detail;
+        expect(data.fn).toBe(testFunction);
+      })),
+    );
+
+    Settings.callbackManager.dispatchEvent("functionTest", {
+      fn: testFunction,
+    });
+    expect(callback).toHaveBeenCalledTimes(0);
+    await new Promise((resolve) => process.nextTick(resolve));
+    expect(callback).toHaveBeenCalledTimes(1);
+  });
+
   // rollup doesn't support decorators for now
   // test('wrap event caller', async () => {
   //   class A {

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

@@ -1,5 +1,5 @@
+import { MarkdownNodeParser } from "@llamaindex/core/node-parser";
 import { Document, MetadataMode } from "@llamaindex/core/schema";
-import { MarkdownNodeParser } from "llamaindex/nodeParsers/index";
 import { describe, expect, test } from "vitest";
 
 describe("MarkdownNodeParser", () => {
@@ -19,8 +19,8 @@ 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].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",
     );
@@ -89,16 +89,16 @@ Content
       }),
     ]);
     expect(splits.length).toBe(4);
-    expect(splits[0].metadata).toEqual({ "Header 1": "Main Header" });
+    expect(splits[0].metadata).toEqual({ Header_1: "Main Header" });
     expect(splits[1].metadata).toEqual({
-      "Header 1": "Main Header",
-      "Header 2": "Sub-header",
+      Header_1: "Main Header",
+      Header_2: "Sub-header",
     });
     expect(splits[2].metadata).toEqual({
-      "Header 1": "Main Header",
-      "Header 2": "Sub-header",
-      "Header 3": "Sub-sub header",
+      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

@@ -1,12 +1,13 @@
+import { SentenceSplitter } from "@llamaindex/core/node-parser";
 import { Document } from "@llamaindex/core/schema";
-import { SimpleNodeParser } from "llamaindex/nodeParsers/index";
+import { tokenizers } from "@llamaindex/env";
 import { beforeEach, describe, expect, test } from "vitest";
 
-describe("SimpleNodeParser", () => {
-  let simpleNodeParser: SimpleNodeParser;
+describe("SentenceSplitter", () => {
+  let sentenceSplitter: SentenceSplitter;
 
   beforeEach(() => {
-    simpleNodeParser = new SimpleNodeParser({
+    sentenceSplitter = new SentenceSplitter({
       chunkSize: 1024,
       chunkOverlap: 20,
     });
@@ -19,7 +20,7 @@ describe("SimpleNodeParser", () => {
       excludedLlmMetadataKeys: ["animals"],
       excludedEmbedMetadataKeys: ["animals"],
     });
-    const result = simpleNodeParser.getNodesFromDocuments([doc]);
+    const result = sentenceSplitter.getNodesFromDocuments([doc]);
     expect(result.length).toEqual(1);
     const node = result[0];
     // check not the same object
@@ -37,4 +38,15 @@ describe("SimpleNodeParser", () => {
     // check relationship
     expect(node.sourceNode?.nodeId).toBe(doc.id_);
   });
+
+  test("split long text", async () => {
+    const longSentence = "is ".repeat(9000) + ".";
+    const document = new Document({ text: longSentence, id_: "1" });
+    const result = sentenceSplitter.getNodesFromDocuments([document]);
+    expect(result.length).toEqual(9);
+    result.forEach((node) => {
+      const { length } = tokenizers.tokenizer().encode(node.text);
+      expect(length).toBeLessThanOrEqual(1024);
+    });
+  });
 });

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

@@ -1,8 +1,5 @@
+import { SentenceWindowNodeParser } from "@llamaindex/core/node-parser";
 import { Document, MetadataMode } from "@llamaindex/core/schema";
-import {
-  DEFAULT_WINDOW_METADATA_KEY,
-  SentenceWindowNodeParser,
-} from "llamaindex/nodeParsers/index";
 import { describe, expect, test } from "vitest";
 
 describe("Tests for the SentenceWindowNodeParser class", () => {
@@ -11,7 +8,7 @@ describe("Tests for the SentenceWindowNodeParser class", () => {
     expect(sentenceWindowNodeParser).toBeDefined();
   });
   test("testing the getNodesFromDocuments method", () => {
-    const sentenceWindowNodeParser = SentenceWindowNodeParser.fromDefaults({
+    const sentenceWindowNodeParser = new SentenceWindowNodeParser({
       windowSize: 1,
     });
     const doc = new Document({ text: "Hello. Cat Mouse. Dog." });
@@ -25,7 +22,9 @@ describe("Tests for the SentenceWindowNodeParser class", () => {
       "Dog.",
     ]);
     expect(
-      resultingNodes.map((n) => n.metadata[DEFAULT_WINDOW_METADATA_KEY]),
+      resultingNodes.map(
+        (n) => n.metadata[SentenceWindowNodeParser.DEFAULT_WINDOW_METADATA_KEY],
+      ),
     ).toEqual([
       "Hello. Cat Mouse.",
       "Hello. Cat Mouse. Dog.",

packages/core/tests/node-parser/text-splitter.test.ts

@@ -1,7 +1,4 @@
-import {
-  SentenceSplitter,
-  cjkSentenceTokenizer,
-} from "llamaindex/TextSplitter";
+import { SentenceSplitter } from "@llamaindex/core/node-parser";
 import { describe, expect, test } from "vitest";
 
 describe("SentenceSplitter", () => {
@@ -10,14 +7,16 @@ describe("SentenceSplitter", () => {
     expect(sentenceSplitter).toBeDefined();
   });
 
+  test("chunk size should less than chunk", async () => {});
+
   test("splits paragraphs w/o effective chunk size", () => {
     const sentenceSplitter = new SentenceSplitter({
-      paragraphSeparator: "\n\n\n",
+      chunkSize: 9,
+      chunkOverlap: 0,
     });
     // generate the same line as above but correct syntax errors
-    const splits = sentenceSplitter.getParagraphSplits(
+    const splits = sentenceSplitter.splitText(
       "This is a paragraph.\n\n\nThis is another paragraph.",
-      undefined,
     );
     expect(splits).toEqual([
       "This is a paragraph.",
@@ -30,9 +29,8 @@ describe("SentenceSplitter", () => {
       paragraphSeparator: "\n",
     });
     // generate the same line as above but correct syntax errors
-    const splits = sentenceSplitter.getParagraphSplits(
+    const splits = sentenceSplitter.splitText(
       "This is a paragraph.\nThis is another paragraph.",
-      1000,
     );
     expect(splits).toEqual([
       "This is a paragraph.\nThis is another paragraph.",
@@ -40,10 +38,12 @@ describe("SentenceSplitter", () => {
   });
 
   test("splits sentences", () => {
-    const sentenceSplitter = new SentenceSplitter();
-    const splits = sentenceSplitter.getSentenceSplits(
+    const sentenceSplitter = new SentenceSplitter({
+      chunkSize: 9,
+      chunkOverlap: 0,
+    });
+    const splits = sentenceSplitter.splitText(
       "This is a sentence. This is another sentence.",
-      undefined,
     );
     expect(splits).toEqual([
       "This is a sentence.",
@@ -89,9 +89,10 @@ describe("SentenceSplitter", () => {
 
   test("splits cjk", () => {
     const sentenceSplitter = new SentenceSplitter({
-      chunkSize: 12,
+      chunkSize: 30,
       chunkOverlap: 0,
-      chunkingTokenizerFn: cjkSentenceTokenizer,
+      secondaryChunkingRegex:
+        '.*?([﹒﹔﹖﹗．；。！？]["’”」』]{0,2}|：(?=["‘“「『]{1,2}|$))',
     });
 
     const splits = sentenceSplitter.splitText(

packages/core/tests/package.json

@@ -7,6 +7,6 @@
   },
   "devDependencies": {
     "@llamaindex/core": "workspace:*",
-    "vitest": "^1.6.0"
+    "vitest": "^2.0.2"
   }
 }

packages/env/package.json

@@ -68,11 +68,11 @@
   },
   "devDependencies": {
     "@aws-crypto/sha256-js": "^5.2.0",
-    "@swc/cli": "^0.3.12",
+    "@swc/cli": "^0.4.0",
     "@swc/core": "^1.6.3",
     "concurrently": "^8.2.2",
     "pathe": "^1.1.2",
-    "vitest": "^1.6.0"
+    "vitest": "^2.0.2"
   },
   "dependencies": {
     "@types/lodash": "^4.17.5",

packages/experimental/CHANGELOG.md

@@ -1,5 +1,61 @@
 # @llamaindex/experimental
 
+## 0.0.59
+
+### Patch Changes
+
+- Updated dependencies [15962b3]
+  - llamaindex@0.5.9
+
+## 0.0.58
+
+### Patch Changes
+
+- Updated dependencies [3d5ba08]
+- Updated dependencies [d917cdc]
+  - llamaindex@0.5.8
+
+## 0.0.57
+
+### Patch Changes
+
+- Updated dependencies [ec59acd]
+  - llamaindex@0.5.7
+
+## 0.0.56
+
+### Patch Changes
+
+- Updated dependencies [2562244]
+- Updated dependencies [325aa51]
+- Updated dependencies [ab700ea]
+- Updated dependencies [92f0782]
+- Updated dependencies [6cf6ae6]
+- Updated dependencies [b7cfe5b]
+  - llamaindex@0.5.6
+
+## 0.0.55
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - llamaindex@0.5.5
+
+## 0.0.54
+
+### Patch Changes
+
+- Updated dependencies [1a65ead]
+  - llamaindex@0.5.4
+
+## 0.0.53
+
+### Patch Changes
+
+- Updated dependencies [9bbbc67]
+- Updated dependencies [b3681bf]
+  - llamaindex@0.5.3
+
 ## 0.0.52
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.52",
+  "version": "0.0.59",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",
@@ -56,7 +56,7 @@
   },
   "devDependencies": {
     "@aws-crypto/sha256-js": "^5.2.0",
-    "@swc/cli": "^0.3.12",
+    "@swc/cli": "^0.4.0",
     "@swc/core": "^1.6.3",
     "@types/jsonpath": "^0.2.4",
     "concurrently": "^8.2.2",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,68 @@
 # llamaindex
 
+## 0.5.9
+
+### Patch Changes
+
+- 15962b3: feat: node parser refactor
+
+  Align the text splitter logic with Python; it has almost the same logic as Python; Zod checks for input and better error messages and event system.
+
+  This change will not be considered a breaking change since it doesn't have a significant output difference from the last version,
+  but some edge cases will change, like the page separator and parameter for the constructor.
+
+- Updated dependencies [15962b3]
+  - @llamaindex/core@0.1.4
+
+## 0.5.8
+
+### Patch Changes
+
+- 3d5ba08: fix: update user agent in AssemblyAI
+- d917cdc: Add azure interpreter tool to tool factory
+
+## 0.5.7
+
+### Patch Changes
+
+- ec59acd: fix: bundling issue with pnpm
+
+## 0.5.6
+
+### Patch Changes
+
+- 2562244: feat: add gpt4o-mini
+- 325aa51: Implement Jina embedding through Jina api
+- ab700ea: Add missing authentication to LlamaCloudIndex.fromDocuments
+- 92f0782: feat: use query bundle
+- 6cf6ae6: feat: abstract query type
+- b7cfe5b: fix: passing max_token option to replicate's api call
+- Updated dependencies [6cf6ae6]
+  - @llamaindex/core@0.1.3
+
+## 0.5.5
+
+### Patch Changes
+
+- b974eea: Add support for Metadata filters
+- Updated dependencies [b974eea]
+  - @llamaindex/core@0.1.2
+
+## 0.5.4
+
+### Patch Changes
+
+- 1a65ead: feat: add vendorMultimodal params to LlamaParseReader
+
+## 0.5.3
+
+### Patch Changes
+
+- 9bbbc67: feat: add a reader for Discord messages
+- b3681bf: fix: DataCloneError when using FunctionTool
+- Updated dependencies [b3681bf]
+  - @llamaindex/core@0.1.1
+
 ## 0.5.2
 
 ### Patch Changes

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

@@ -1,5 +1,61 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.43
+
+### Patch Changes
+
+- Updated dependencies [15962b3]
+  - llamaindex@0.5.9
+
+## 0.0.42
+
+### Patch Changes
+
+- Updated dependencies [3d5ba08]
+- Updated dependencies [d917cdc]
+  - llamaindex@0.5.8
+
+## 0.0.41
+
+### Patch Changes
+
+- Updated dependencies [ec59acd]
+  - llamaindex@0.5.7
+
+## 0.0.40
+
+### Patch Changes
+
+- Updated dependencies [2562244]
+- Updated dependencies [325aa51]
+- Updated dependencies [ab700ea]
+- Updated dependencies [92f0782]
+- Updated dependencies [6cf6ae6]
+- Updated dependencies [b7cfe5b]
+  - llamaindex@0.5.6
+
+## 0.0.39
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - llamaindex@0.5.5
+
+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [1a65ead]
+  - llamaindex@0.5.4
+
+## 0.0.37
+
+### Patch Changes
+
+- Updated dependencies [9bbbc67]
+- Updated dependencies [b3681bf]
+  - llamaindex@0.5.3
+
 ## 0.0.36
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.36",
+  "version": "0.0.43",
   "type": "module",
   "private": true,
   "scripts": {
@@ -12,13 +12,13 @@
     "cf-typegen": "wrangler types"
   },
   "devDependencies": {
-    "@cloudflare/vitest-pool-workers": "^0.4.3",
-    "@cloudflare/workers-types": "^4.20240605.0",
-    "@vitest/runner": "1.3.0",
-    "@vitest/snapshot": "1.3.0",
-    "typescript": "^5.5.2",
-    "vitest": "1.3.0",
-    "wrangler": "^3.60.1"
+    "@cloudflare/vitest-pool-workers": "^0.4.10",
+    "@cloudflare/workers-types": "^4.20240620.0",
+    "@vitest/runner": "1.5.3",
+    "@vitest/snapshot": "1.5.3",
+    "typescript": "^5.5.3",
+    "vitest": "1.5.3",
+    "wrangler": "^3.63.2"
   },
   "dependencies": {
     "llamaindex": "workspace:*"

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

@@ -1,5 +1,61 @@
 # @llamaindex/next-agent-test
 
+## 0.1.43
+
+### Patch Changes
+
+- Updated dependencies [15962b3]
+  - llamaindex@0.5.9
+
+## 0.1.42
+
+### Patch Changes
+
+- Updated dependencies [3d5ba08]
+- Updated dependencies [d917cdc]
+  - llamaindex@0.5.8
+
+## 0.1.41
+
+### Patch Changes
+
+- Updated dependencies [ec59acd]
+  - llamaindex@0.5.7
+
+## 0.1.40
+
+### Patch Changes
+
+- Updated dependencies [2562244]
+- Updated dependencies [325aa51]
+- Updated dependencies [ab700ea]
+- Updated dependencies [92f0782]
+- Updated dependencies [6cf6ae6]
+- Updated dependencies [b7cfe5b]
+  - llamaindex@0.5.6
+
+## 0.1.39
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - llamaindex@0.5.5
+
+## 0.1.38
+
+### Patch Changes
+
+- Updated dependencies [1a65ead]
+  - llamaindex@0.5.4
+
+## 0.1.37
+
+### Patch Changes
+
+- Updated dependencies [9bbbc67]
+- Updated dependencies [b3681bf]
+  - llamaindex@0.5.3
+
 ## 0.1.36
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.36",
+  "version": "0.1.43",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -11,7 +11,7 @@
   "dependencies": {
     "ai": "^3.2.1",
     "llamaindex": "workspace:*",
-    "next": "14.2.4",
+    "next": "14.2.5",
     "react": "18.3.1",
     "react-dom": "18.3.1"
   },
@@ -20,9 +20,9 @@
     "@types/react": "^18.3.3",
     "@types/react-dom": "^18.3.0",
     "eslint": "^8.57.0",
-    "eslint-config-next": "14.2.3",
+    "eslint-config-next": "14.2.5",
     "postcss": "^8",
     "tailwindcss": "^3.4.4",
-    "typescript": "^5.5.2"
+    "typescript": "^5.5.3"
   }
 }

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

@@ -1,5 +1,61 @@
 # test-edge-runtime
 
+## 0.1.42
+
+### Patch Changes
+
+- Updated dependencies [15962b3]
+  - llamaindex@0.5.9
+
+## 0.1.41
+
+### Patch Changes
+
+- Updated dependencies [3d5ba08]
+- Updated dependencies [d917cdc]
+  - llamaindex@0.5.8
+
+## 0.1.40
+
+### Patch Changes
+
+- Updated dependencies [ec59acd]
+  - llamaindex@0.5.7
+
+## 0.1.39
+
+### Patch Changes
+
+- Updated dependencies [2562244]
+- Updated dependencies [325aa51]
+- Updated dependencies [ab700ea]
+- Updated dependencies [92f0782]
+- Updated dependencies [6cf6ae6]
+- Updated dependencies [b7cfe5b]
+  - llamaindex@0.5.6
+
+## 0.1.38
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - llamaindex@0.5.5
+
+## 0.1.37
+
+### Patch Changes
+
+- Updated dependencies [1a65ead]
+  - llamaindex@0.5.4
+
+## 0.1.36
+
+### Patch Changes
+
+- Updated dependencies [9bbbc67]
+- Updated dependencies [b3681bf]
+  - llamaindex@0.5.3
+
 ## 0.1.35
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.35",
+  "version": "0.1.42",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -9,7 +9,7 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "next": "14.2.4",
+    "next": "14.2.5",
     "react": "^18.3.1",
     "react-dom": "^18.3.1"
   },
@@ -17,6 +17,6 @@
     "@types/node": "^20.12.11",
     "@types/react": "^18.3.3",
     "@types/react-dom": "^18.3.0",
-    "typescript": "^5.5.2"
+    "typescript": "^5.5.3"
   }
 }

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

@@ -1,5 +1,61 @@
 # @llamaindex/next-node-runtime
 
+## 0.0.24
+
+### Patch Changes
+
+- Updated dependencies [15962b3]
+  - llamaindex@0.5.9
+
+## 0.0.23
+
+### Patch Changes
+
+- Updated dependencies [3d5ba08]
+- Updated dependencies [d917cdc]
+  - llamaindex@0.5.8
+
+## 0.0.22
+
+### Patch Changes
+
+- Updated dependencies [ec59acd]
+  - llamaindex@0.5.7
+
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [2562244]
+- Updated dependencies [325aa51]
+- Updated dependencies [ab700ea]
+- Updated dependencies [92f0782]
+- Updated dependencies [6cf6ae6]
+- Updated dependencies [b7cfe5b]
+  - llamaindex@0.5.6
+
+## 0.0.20
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - llamaindex@0.5.5
+
+## 0.0.19
+
+### Patch Changes
+
+- Updated dependencies [1a65ead]
+  - llamaindex@0.5.4
+
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [9bbbc67]
+- Updated dependencies [b3681bf]
+  - llamaindex@0.5.3
+
 ## 0.0.17
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.0.17",
+  "version": "0.0.24",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -10,7 +10,7 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "next": "14.2.4",
+    "next": "14.2.5",
     "react": "18.3.1",
     "react-dom": "18.3.1"
   },
@@ -19,9 +19,9 @@
     "@types/react": "^18.3.3",
     "@types/react-dom": "^18.3.0",
     "eslint": "^8.57.0",
-    "eslint-config-next": "14.2.3",
+    "eslint-config-next": "14.2.5",
     "postcss": "^8",
     "tailwindcss": "^3.4.4",
-    "typescript": "^5.5.2"
+    "typescript": "^5.5.3"
   }
 }

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

@@ -1,5 +1,61 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.43
+
+### Patch Changes
+
+- Updated dependencies [15962b3]
+  - llamaindex@0.5.9
+
+## 0.0.42
+
+### Patch Changes
+
+- Updated dependencies [3d5ba08]
+- Updated dependencies [d917cdc]
+  - llamaindex@0.5.8
+
+## 0.0.41
+
+### Patch Changes
+
+- Updated dependencies [ec59acd]
+  - llamaindex@0.5.7
+
+## 0.0.40
+
+### Patch Changes
+
+- Updated dependencies [2562244]
+- Updated dependencies [325aa51]
+- Updated dependencies [ab700ea]
+- Updated dependencies [92f0782]
+- Updated dependencies [6cf6ae6]
+- Updated dependencies [b7cfe5b]
+  - llamaindex@0.5.6
+
+## 0.0.39
+
+### Patch Changes
+
+- Updated dependencies [b974eea]
+  - llamaindex@0.5.5
+
+## 0.0.38
+
+### Patch Changes
+
+- Updated dependencies [1a65ead]
+  - llamaindex@0.5.4
+
+## 0.0.37
+
+### Patch Changes
+
+- Updated dependencies [9bbbc67]
+- Updated dependencies [b3681bf]
+  - llamaindex@0.5.3
+
 ## 0.0.36
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.36",
+  "version": "0.0.43",
   "type": "module",
   "private": true,
   "scripts": {
@@ -10,16 +10,16 @@
   },
   "dependencies": {
     "llamaindex": "workspace:*",
-    "react": "19.0.0-canary-e3ebcd54b-20240405",
-    "react-dom": "19.0.0-canary-e3ebcd54b-20240405",
-    "react-server-dom-webpack": "19.0.0-canary-e3ebcd54b-20240405",
-    "waku": "0.20.1"
+    "react": "19.0.0-beta-e7d213dfb0-20240507",
+    "react-dom": "19.0.0-beta-e7d213dfb0-20240507",
+    "react-server-dom-webpack": "19.0.0-beta-e7d213dfb0-20240507",
+    "waku": "0.20.2"
   },
   "devDependencies": {
-    "@types/react": "18.3.1",
+    "@types/react": "18.3.3",
     "@types/react-dom": "18.3.0",
     "autoprefixer": "10.4.19",
-    "tailwindcss": "3.4.3",
-    "typescript": "5.4.5"
+    "tailwindcss": "3.4.4",
+    "typescript": "5.5.3"
   }
 }

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

@@ -7,8 +7,8 @@ import {
   OpenAI,
   OpenAIAgent,
   QueryEngineTool,
+  SentenceSplitter,
   Settings,
-  SimpleNodeParser,
   SimpleToolNodeMapping,
   SubQuestionQueryEngine,
   SummaryIndex,
@@ -124,7 +124,7 @@ await test("agent with object retriever", async (t) => {
   const alexInfoText = await readFile(alexInfoPath, "utf-8");
   const alexDocument = new Document({ text: alexInfoText, id_: alexInfoPath });
 
-  const nodes = new SimpleNodeParser({
+  const nodes = new SentenceSplitter({
     chunkSize: 200,
     chunkOverlap: 20,
   }).getNodesFromDocuments([alexDocument]);

packages/llamaindex/e2e/node/snapshot/agent.snap

@@ -22,7 +22,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_sH6QfjsymHW7JFl68j8AY6xg",
+                "id": "call_8kF02T5eJKwUL5hCGF8upWgn",
                 "name": "Weather",
                 "input": "{\"location\":\"San Francisco\"}"
               }
@@ -30,13 +30,13 @@
           }
         },
         {
-          "role": "user",
           "content": "35 degrees and sunny in San Francisco",
+          "role": "user",
           "options": {
             "toolResult": {
               "result": "35 degrees and sunny in San Francisco",
               "isError": false,
-              "id": "call_sH6QfjsymHW7JFl68j8AY6xg"
+              "id": "call_8kF02T5eJKwUL5hCGF8upWgn"
             }
           }
         }
@@ -64,7 +64,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_V7zs8cyDT5FqJhjwBqcCydgA",
+                "id": "call_xsgmMFgliEDiOmZuLaBjUiXE",
                 "name": "unique_id",
                 "input": "{\"firstName\":\"Alex\",\"lastName\":\"Yang\"}"
               }
@@ -72,13 +72,13 @@
           }
         },
         {
-          "role": "user",
           "content": "123456789",
+          "role": "user",
           "options": {
             "toolResult": {
               "result": "123456789",
               "isError": false,
-              "id": "call_V7zs8cyDT5FqJhjwBqcCydgA"
+              "id": "call_xsgmMFgliEDiOmZuLaBjUiXE"
             }
           }
         }
@@ -106,7 +106,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_BrlGGU6GDGWr0hrwXt9qZKyt",
+                "id": "call_OTMrLMikpT37PLm6KOIG5LCF",
                 "name": "sumNumbers",
                 "input": "{\"a\":1,\"b\":1}"
               }
@@ -114,13 +114,13 @@
           }
         },
         {
-          "role": "user",
           "content": "2",
+          "role": "user",
           "options": {
             "toolResult": {
               "result": "2",
               "isError": false,
-              "id": "call_BrlGGU6GDGWr0hrwXt9qZKyt"
+              "id": "call_OTMrLMikpT37PLm6KOIG5LCF"
             }
           }
         }
@@ -138,7 +138,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_sH6QfjsymHW7JFl68j8AY6xg",
+                "id": "call_8kF02T5eJKwUL5hCGF8upWgn",
                 "name": "Weather",
                 "input": "{\"location\":\"San Francisco\"}"
               }
@@ -168,7 +168,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_V7zs8cyDT5FqJhjwBqcCydgA",
+                "id": "call_xsgmMFgliEDiOmZuLaBjUiXE",
                 "name": "unique_id",
                 "input": "{\"firstName\":\"Alex\",\"lastName\":\"Yang\"}"
               }
@@ -198,7 +198,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_BrlGGU6GDGWr0hrwXt9qZKyt",
+                "id": "call_OTMrLMikpT37PLm6KOIG5LCF",
                 "name": "sumNumbers",
                 "input": "{\"a\":1,\"b\":1}"
               }

packages/llamaindex/e2e/node/snapshot/agent_stream.snap

@@ -23,7 +23,7 @@
             "toolCall": [
               {
                 "name": "divideNumbers",
-                "id": "call_V4daSdWk9QeYeSMKLBisNbSf",
+                "id": "call_XgB0tixgYDhGXXSgdY19XDmt",
                 "input": {
                   "a": 16,
                   "b": 2
@@ -31,7 +31,7 @@
               },
               {
                 "name": "sumNumbers",
-                "id": "call_n2OlBxlaoeMIMVeU9DeDfiPX",
+                "id": "call_nXP1Rc85Ntdv5XcI6FBWmB6d",
                 "input": "{\"a\": 8, \"b\": 20}"
               }
             ]
@@ -44,7 +44,7 @@
             "toolResult": {
               "result": "8",
               "isError": false,
-              "id": "call_V4daSdWk9QeYeSMKLBisNbSf"
+              "id": "call_XgB0tixgYDhGXXSgdY19XDmt"
             }
           }
         },
@@ -55,7 +55,7 @@
             "toolResult": {
               "result": "28",
               "isError": false,
-              "id": "call_n2OlBxlaoeMIMVeU9DeDfiPX"
+              "id": "call_nXP1Rc85Ntdv5XcI6FBWmB6d"
             }
           }
         }
@@ -74,7 +74,7 @@
             "toolCall": [
               {
                 "name": "sumNumbers",
-                "id": "call_n2OlBxlaoeMIMVeU9DeDfiPX",
+                "id": "call_nXP1Rc85Ntdv5XcI6FBWmB6d",
                 "input": "{\"a\": 8, \"b\": 20}"
               }
             ]
@@ -87,7 +87,7 @@
       "response": {
         "raw": null,
         "message": {
-          "content": "The result of dividing 16 by 2 is 8. When you add 20 to 8, the total is 28.",
+          "content": "After dividing 16 by 2, we get 8. Adding 20 to 8 gives us 28.",
           "role": "assistant",
           "options": {}
         }
@@ -103,7 +103,7 @@
           "toolCall": [
             {
               "name": "divideNumbers",
-              "id": "call_V4daSdWk9QeYeSMKLBisNbSf",
+              "id": "call_XgB0tixgYDhGXXSgdY19XDmt",
               "input": "{\"a\": 16, \"b\": 2}"
             }
           ]
@@ -119,7 +119,7 @@
           "toolCall": [
             {
               "name": "divideNumbers",
-              "id": "call_V4daSdWk9QeYeSMKLBisNbSf",
+              "id": "call_XgB0tixgYDhGXXSgdY19XDmt",
               "input": "{\"a\": 16, \"b\": 2}"
             }
           ]
@@ -135,7 +135,7 @@
           "toolCall": [
             {
               "name": "divideNumbers",
-              "id": "call_V4daSdWk9QeYeSMKLBisNbSf",
+              "id": "call_XgB0tixgYDhGXXSgdY19XDmt",
               "input": "{\"a\": 16, \"b\": 2}"
             }
           ]
@@ -151,7 +151,7 @@
           "toolCall": [
             {
               "name": "divideNumbers",
-              "id": "call_V4daSdWk9QeYeSMKLBisNbSf",
+              "id": "call_XgB0tixgYDhGXXSgdY19XDmt",
               "input": "{\"a\": 16, \"b\": 2}"
             }
           ]
@@ -167,7 +167,7 @@
           "toolCall": [
             {
               "name": "divideNumbers",
-              "id": "call_V4daSdWk9QeYeSMKLBisNbSf",
+              "id": "call_XgB0tixgYDhGXXSgdY19XDmt",
               "input": "{\"a\": 16, \"b\": 2}"
             }
           ]
@@ -183,7 +183,7 @@
           "toolCall": [
             {
               "name": "divideNumbers",
-              "id": "call_V4daSdWk9QeYeSMKLBisNbSf",
+              "id": "call_XgB0tixgYDhGXXSgdY19XDmt",
               "input": {
                 "a": 16,
                 "b": 2
@@ -202,7 +202,7 @@
           "toolCall": [
             {
               "name": "sumNumbers",
-              "id": "call_n2OlBxlaoeMIMVeU9DeDfiPX",
+              "id": "call_nXP1Rc85Ntdv5XcI6FBWmB6d",
               "input": "{\"a\": 8, \"b\": 20}"
             }
           ]
@@ -218,7 +218,7 @@
           "toolCall": [
             {
               "name": "sumNumbers",
-              "id": "call_n2OlBxlaoeMIMVeU9DeDfiPX",
+              "id": "call_nXP1Rc85Ntdv5XcI6FBWmB6d",
               "input": "{\"a\": 8, \"b\": 20}"
             }
           ]
@@ -234,7 +234,7 @@
           "toolCall": [
             {
               "name": "sumNumbers",
-              "id": "call_n2OlBxlaoeMIMVeU9DeDfiPX",
+              "id": "call_nXP1Rc85Ntdv5XcI6FBWmB6d",
               "input": "{\"a\": 8, \"b\": 20}"
             }
           ]
@@ -250,7 +250,7 @@
           "toolCall": [
             {
               "name": "sumNumbers",
-              "id": "call_n2OlBxlaoeMIMVeU9DeDfiPX",
+              "id": "call_nXP1Rc85Ntdv5XcI6FBWmB6d",
               "input": "{\"a\": 8, \"b\": 20}"
             }
           ]
@@ -263,23 +263,7 @@
       "chunk": {
         "raw": null,
         "options": {},
-        "delta": "The"
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "options": {},
-        "delta": " result"
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "options": {},
-        "delta": " of"
+        "delta": "After"
       }
     },
     {
@@ -335,7 +319,23 @@
       "chunk": {
         "raw": null,
         "options": {},
-        "delta": " is"
+        "delta": ","
+      }
+    },
+    {
+      "id": "PRESERVE_1",
+      "chunk": {
+        "raw": null,
+        "options": {},
+        "delta": " we"
+      }
+    },
+    {
+      "id": "PRESERVE_1",
+      "chunk": {
+        "raw": null,
+        "options": {},
+        "delta": " get"
       }
     },
     {
@@ -367,23 +367,7 @@
       "chunk": {
         "raw": null,
         "options": {},
-        "delta": " When"
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "options": {},
-        "delta": " you"
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "options": {},
-        "delta": " add"
+        "delta": " Adding"
       }
     },
     {
@@ -431,7 +415,7 @@
       "chunk": {
         "raw": null,
         "options": {},
-        "delta": ","
+        "delta": " gives"
       }
     },
     {
@@ -439,23 +423,7 @@
       "chunk": {
         "raw": null,
         "options": {},
-        "delta": " the"
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "options": {},
-        "delta": " total"
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "options": {},
-        "delta": " is"
+        "delta": " us"
       }
     },
     {

packages/llamaindex/e2e/node/snapshot/agent_with_object_function_call.snap

@@ -22,7 +22,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_uERMumWlJLTO2GW93X6C2W3N",
+                "id": "call_FNnPEPNeSDmdDj7b5x4LIxBG",
                 "name": "get_weather",
                 "input": "{\"location\":\"San Francisco\"}"
               }
@@ -30,8 +30,8 @@
           }
         },
         {
-          "role": "user",
           "content": "{\n  location: San Francisco,\n  temperature: 72,\n  weather: cloudy,\n  rain_prediction: 0.89\n}",
+          "role": "user",
           "options": {
             "toolResult": {
               "result": {
@@ -41,7 +41,7 @@
                 "rain_prediction": 0.89
               },
               "isError": false,
-              "id": "call_uERMumWlJLTO2GW93X6C2W3N"
+              "id": "call_FNnPEPNeSDmdDj7b5x4LIxBG"
             }
           }
         }
@@ -59,7 +59,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_uERMumWlJLTO2GW93X6C2W3N",
+                "id": "call_FNnPEPNeSDmdDj7b5x4LIxBG",
                 "name": "get_weather",
                 "input": "{\"location\":\"San Francisco\"}"
               }

packages/llamaindex/e2e/node/snapshot/agent_with_object_retriever.snap

@@ -17,7 +17,7 @@
       "id": "PRESERVE_1",
       "messages": [
         {
-          "content": "Context information is below.\n---------------------\nAlex is a male. What's very important, Alex is not in the Brazil.\n---------------------\nGiven the context information and not prior knowledge, answer the query.\nQuery: Alex\nAnswer:",
+          "content": "Context information is below.\n---------------------\nAlex is a male.\nWhat's very important, Alex is not in the Brazil.\n---------------------\nGiven the context information and not prior knowledge, answer the query.\nQuery: Alex\nAnswer:",
           "role": "user"
         }
       ]
@@ -26,7 +26,7 @@
       "id": "PRESERVE_2",
       "messages": [
         {
-          "content": "Context information is below.\n---------------------\nAlex is a male. What's very important, Alex is not in the Brazil.\n---------------------\nGiven the context information and not prior knowledge, answer the query.\nQuery: Brazil\nAnswer:",
+          "content": "Context information is below.\n---------------------\nAlex is a male.\nWhat's very important, Alex is not in the Brazil.\n---------------------\nGiven the context information and not prior knowledge, answer the query.\nQuery: Brazil\nAnswer:",
           "role": "user"
         }
       ]
@@ -48,12 +48,12 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_vv1XW3xv4j2us5sZOtzCU2lL",
+                "id": "call_xkMkcEJYa2vVFUpg1Ng3UZTK",
                 "name": "summary_tool",
                 "input": "{\"query\": \"Alex\"}"
               },
               {
-                "id": "call_V36LMHbwUJkEa20A3GoA4wIr",
+                "id": "call_BYhP9Coo4NIBJDFaEKRA5qSl",
                 "name": "summary_tool",
                 "input": "{\"query\": \"Brazil\"}"
               }
@@ -61,24 +61,24 @@
           }
         },
         {
-          "role": "user",
           "content": "Alex is not in Brazil.",
+          "role": "user",
           "options": {
             "toolResult": {
               "result": "Alex is not in Brazil.",
               "isError": false,
-              "id": "call_vv1XW3xv4j2us5sZOtzCU2lL"
+              "id": "call_xkMkcEJYa2vVFUpg1Ng3UZTK"
             }
           }
         },
         {
-          "role": "user",
           "content": "Alex is not in Brazil.",
+          "role": "user",
           "options": {
             "toolResult": {
               "result": "Alex is not in Brazil.",
               "isError": false,
-              "id": "call_V36LMHbwUJkEa20A3GoA4wIr"
+              "id": "call_BYhP9Coo4NIBJDFaEKRA5qSl"
             }
           }
         }
@@ -96,12 +96,12 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_vv1XW3xv4j2us5sZOtzCU2lL",
+                "id": "call_xkMkcEJYa2vVFUpg1Ng3UZTK",
                 "name": "summary_tool",
                 "input": "{\"query\": \"Alex\"}"
               },
               {
-                "id": "call_V36LMHbwUJkEa20A3GoA4wIr",
+                "id": "call_BYhP9Coo4NIBJDFaEKRA5qSl",
                 "name": "summary_tool",
                 "input": "{\"query\": \"Brazil\"}"
               }

packages/llamaindex/e2e/node/snapshot/anthropic-agent-multiple-chat.snap

@@ -20,7 +20,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+              "text": "<thinking>\nThe user has simply asked me to respond with the word \"Yes\". This is a very straightforward request that does not require the use of any tools. I have all the information I need to directly provide the response the user has requested.\n</thinking>\n\nYes"
             }
           ],
           "role": "assistant",
@@ -43,7 +43,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+              "text": "<thinking>\nThe user has simply asked me to respond with the word \"Yes\". This is a very straightforward request that does not require the use of any tools. I have all the information I need to directly provide the response the user has requested.\n</thinking>\n\nYes"
             }
           ],
           "role": "assistant",
@@ -57,7 +57,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+              "text": "<thinking>\nThe user has now asked me to respond with the word \"No\" instead of \"Yes\". Once again, this is a very simple and direct request. No additional information or tool usage is needed. I can immediately provide the response the user has requested by simply replying with the word \"No\".\n</thinking>\n\nNo"
             }
           ],
           "role": "assistant",
@@ -80,7 +80,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+              "text": "<thinking>\nThe user has simply asked me to respond with the word \"Yes\". This is a very straightforward request that does not require the use of any tools. I have all the information I need to directly provide the response the user has requested.\n</thinking>\n\nYes"
             }
           ],
           "role": "assistant",
@@ -94,7 +94,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+              "text": "<thinking>\nThe user has now asked me to respond with the word \"No\" instead of \"Yes\". Once again, this is a very simple and direct request. No additional information or tool usage is needed. I can immediately provide the response the user has requested by simply replying with the word \"No\".\n</thinking>\n\nNo"
             }
           ],
           "role": "assistant",
@@ -108,7 +108,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Maybe\".\n</thinking>\n\nMaybe"
+              "text": "<thinking>\nThe user has made another simple request, this time asking me to respond with the word \"Maybe\". Just like the previous requests for \"Yes\" and \"No\", I have all the necessary information to fulfill this request without needing to use any tools or gather additional details. I can provide the requested response by replying with only the word \"Maybe\".\n</thinking>\n\nMaybe"
             }
           ],
           "role": "assistant",
@@ -131,7 +131,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+              "text": "<thinking>\nThe user has simply asked me to respond with the word \"Yes\". This is a very straightforward request that does not require the use of any tools. I have all the information I need to directly provide the response the user has requested.\n</thinking>\n\nYes"
             }
           ],
           "role": "assistant",
@@ -145,7 +145,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+              "text": "<thinking>\nThe user has now asked me to respond with the word \"No\" instead of \"Yes\". Once again, this is a very simple and direct request. No additional information or tool usage is needed. I can immediately provide the response the user has requested by simply replying with the word \"No\".\n</thinking>\n\nNo"
             }
           ],
           "role": "assistant",
@@ -159,7 +159,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Maybe\".\n</thinking>\n\nMaybe"
+              "text": "<thinking>\nThe user has made another simple request, this time asking me to respond with the word \"Maybe\". Just like the previous requests for \"Yes\" and \"No\", I have all the necessary information to fulfill this request without needing to use any tools or gather additional details. I can provide the requested response by replying with only the word \"Maybe\".\n</thinking>\n\nMaybe"
             }
           ],
           "role": "assistant",
@@ -173,14 +173,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has asked for the weather in a specific city, San Francisco. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"San Francisco\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+              "text": "<thinking>\nThe user has asked for the current weather in San Francisco. To answer this, I will need to use the getWeather tool.\n\nLooking at the parameters for getWeather, I see it requires a single parameter:\n- city (string): The city to get the weather for \n\nThe user has directly provided the value for the city parameter in their request - they want the weather for San Francisco.\n\nI have all the required information to make the getWeather tool call, so I will proceed with calling the tool with \"San Francisco\" as the city parameter value.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_017MxwaxaLYkmt4dpP5HKzFe",
+                "id": "toolu_01Q5tWdx8CTrqUaQty8C1PD5",
                 "name": "getWeather",
                 "input": {
                   "city": "San Francisco"
@@ -196,7 +196,7 @@
             "toolResult": {
               "result": "The weather in San Francisco is 72 degrees",
               "isError": false,
-              "id": "toolu_017MxwaxaLYkmt4dpP5HKzFe"
+              "id": "toolu_01Q5tWdx8CTrqUaQty8C1PD5"
             }
           }
         }
@@ -213,7 +213,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+              "text": "<thinking>\nThe user has simply asked me to respond with the word \"Yes\". This is a very straightforward request that does not require the use of any tools. I have all the information I need to directly provide the response the user has requested.\n</thinking>\n\nYes"
             }
           ],
           "role": "assistant",
@@ -227,7 +227,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+              "text": "<thinking>\nThe user has now asked me to respond with the word \"No\" instead of \"Yes\". Once again, this is a very simple and direct request. No additional information or tool usage is needed. I can immediately provide the response the user has requested by simply replying with the word \"No\".\n</thinking>\n\nNo"
             }
           ],
           "role": "assistant",
@@ -241,7 +241,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Maybe\".\n</thinking>\n\nMaybe"
+              "text": "<thinking>\nThe user has made another simple request, this time asking me to respond with the word \"Maybe\". Just like the previous requests for \"Yes\" and \"No\", I have all the necessary information to fulfill this request without needing to use any tools or gather additional details. I can provide the requested response by replying with only the word \"Maybe\".\n</thinking>\n\nMaybe"
             }
           ],
           "role": "assistant",
@@ -255,14 +255,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has asked for the weather in a specific city, San Francisco. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"San Francisco\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+              "text": "<thinking>\nThe user has asked for the current weather in San Francisco. To answer this, I will need to use the getWeather tool.\n\nLooking at the parameters for getWeather, I see it requires a single parameter:\n- city (string): The city to get the weather for \n\nThe user has directly provided the value for the city parameter in their request - they want the weather for San Francisco.\n\nI have all the required information to make the getWeather tool call, so I will proceed with calling the tool with \"San Francisco\" as the city parameter value.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_017MxwaxaLYkmt4dpP5HKzFe",
+                "id": "toolu_01Q5tWdx8CTrqUaQty8C1PD5",
                 "name": "getWeather",
                 "input": {
                   "city": "San Francisco"
@@ -278,7 +278,7 @@
             "toolResult": {
               "result": "The weather in San Francisco is 72 degrees",
               "isError": false,
-              "id": "toolu_017MxwaxaLYkmt4dpP5HKzFe"
+              "id": "toolu_01Q5tWdx8CTrqUaQty8C1PD5"
             }
           }
         },
@@ -286,7 +286,7 @@
           "content": [
             {
               "type": "text",
-              "text": "The current weather in San Francisco is 72 degrees."
+              "text": "Based on the result from calling the getWeather tool, the current weather in San Francisco is 72 degrees."
             }
           ],
           "role": "assistant",
@@ -309,7 +309,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+              "text": "<thinking>\nThe user has simply asked me to respond with the word \"Yes\". This is a very straightforward request that does not require the use of any tools. I have all the information I need to directly provide the response the user has requested.\n</thinking>\n\nYes"
             }
           ],
           "role": "assistant",
@@ -323,7 +323,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+              "text": "<thinking>\nThe user has now asked me to respond with the word \"No\" instead of \"Yes\". Once again, this is a very simple and direct request. No additional information or tool usage is needed. I can immediately provide the response the user has requested by simply replying with the word \"No\".\n</thinking>\n\nNo"
             }
           ],
           "role": "assistant",
@@ -337,7 +337,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Maybe\".\n</thinking>\n\nMaybe"
+              "text": "<thinking>\nThe user has made another simple request, this time asking me to respond with the word \"Maybe\". Just like the previous requests for \"Yes\" and \"No\", I have all the necessary information to fulfill this request without needing to use any tools or gather additional details. I can provide the requested response by replying with only the word \"Maybe\".\n</thinking>\n\nMaybe"
             }
           ],
           "role": "assistant",
@@ -351,14 +351,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has asked for the weather in a specific city, San Francisco. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"San Francisco\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+              "text": "<thinking>\nThe user has asked for the current weather in San Francisco. To answer this, I will need to use the getWeather tool.\n\nLooking at the parameters for getWeather, I see it requires a single parameter:\n- city (string): The city to get the weather for \n\nThe user has directly provided the value for the city parameter in their request - they want the weather for San Francisco.\n\nI have all the required information to make the getWeather tool call, so I will proceed with calling the tool with \"San Francisco\" as the city parameter value.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_017MxwaxaLYkmt4dpP5HKzFe",
+                "id": "toolu_01Q5tWdx8CTrqUaQty8C1PD5",
                 "name": "getWeather",
                 "input": {
                   "city": "San Francisco"
@@ -374,7 +374,7 @@
             "toolResult": {
               "result": "The weather in San Francisco is 72 degrees",
               "isError": false,
-              "id": "toolu_017MxwaxaLYkmt4dpP5HKzFe"
+              "id": "toolu_01Q5tWdx8CTrqUaQty8C1PD5"
             }
           }
         },
@@ -382,7 +382,7 @@
           "content": [
             {
               "type": "text",
-              "text": "The current weather in San Francisco is 72 degrees."
+              "text": "Based on the result from calling the getWeather tool, the current weather in San Francisco is 72 degrees."
             }
           ],
           "role": "assistant",
@@ -396,14 +396,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has asked for the weather in a specific city, Shanghai. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"Shanghai\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+              "text": "<thinking>\nThe user has now asked for the current weather in Shanghai. This is very similar to the previous request for San Francisco's weather. I will once again need to use the getWeather tool to answer this.\n\nThe getWeather tool requires the following parameter:\n- city (string): The city to get the weather for\n\nThe user has provided the city they want the weather for directly in their request - in this case, the city is Shanghai.\n\nSince I have the value for the required city parameter, I can go ahead and call the getWeather tool, passing in \"Shanghai\" as the city.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_013ZnATGKhvPkt2jjxdFheDK",
+                "id": "toolu_01HxDqJpm33QxDXAExTxm6zu",
                 "name": "getWeather",
                 "input": {
                   "city": "Shanghai"
@@ -419,7 +419,7 @@
             "toolResult": {
               "result": "The weather in Shanghai is 72 degrees",
               "isError": false,
-              "id": "toolu_013ZnATGKhvPkt2jjxdFheDK"
+              "id": "toolu_01HxDqJpm33QxDXAExTxm6zu"
             }
           }
         }
@@ -435,7 +435,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Yes\".\n</thinking>\n\nYes"
+              "text": "<thinking>\nThe user has simply asked me to respond with the word \"Yes\". This is a very straightforward request that does not require the use of any tools. I have all the information I need to directly provide the response the user has requested.\n</thinking>\n\nYes"
             }
           ],
           "role": "assistant",
@@ -451,7 +451,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"No\".\n</thinking>\n\nNo"
+              "text": "<thinking>\nThe user has now asked me to respond with the word \"No\" instead of \"Yes\". Once again, this is a very simple and direct request. No additional information or tool usage is needed. I can immediately provide the response the user has requested by simply replying with the word \"No\".\n</thinking>\n\nNo"
             }
           ],
           "role": "assistant",
@@ -467,7 +467,7 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has not asked a question that requires using any of the available tools. They have simply requested that I respond with the word \"Maybe\".\n</thinking>\n\nMaybe"
+              "text": "<thinking>\nThe user has made another simple request, this time asking me to respond with the word \"Maybe\". Just like the previous requests for \"Yes\" and \"No\", I have all the necessary information to fulfill this request without needing to use any tools or gather additional details. I can provide the requested response by replying with only the word \"Maybe\".\n</thinking>\n\nMaybe"
             }
           ],
           "role": "assistant",
@@ -483,14 +483,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has asked for the weather in a specific city, San Francisco. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"San Francisco\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+              "text": "<thinking>\nThe user has asked for the current weather in San Francisco. To answer this, I will need to use the getWeather tool.\n\nLooking at the parameters for getWeather, I see it requires a single parameter:\n- city (string): The city to get the weather for \n\nThe user has directly provided the value for the city parameter in their request - they want the weather for San Francisco.\n\nI have all the required information to make the getWeather tool call, so I will proceed with calling the tool with \"San Francisco\" as the city parameter value.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_017MxwaxaLYkmt4dpP5HKzFe",
+                "id": "toolu_01Q5tWdx8CTrqUaQty8C1PD5",
                 "name": "getWeather",
                 "input": {
                   "city": "San Francisco"
@@ -509,7 +509,7 @@
           "content": [
             {
               "type": "text",
-              "text": "The current weather in San Francisco is 72 degrees."
+              "text": "Based on the result from calling the getWeather tool, the current weather in San Francisco is 72 degrees."
             }
           ],
           "role": "assistant",
@@ -525,14 +525,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has asked for the weather in a specific city, Shanghai. The relevant tool to answer this is the getWeather function.\n\nLooking at the required parameters for getWeather:\ncity (string): The user directly provided the city \"Shanghai\"\n\nSince the required \"city\" parameter has been provided, we can proceed with the getWeather function call.\n</thinking>"
+              "text": "<thinking>\nThe user has now asked for the current weather in Shanghai. This is very similar to the previous request for San Francisco's weather. I will once again need to use the getWeather tool to answer this.\n\nThe getWeather tool requires the following parameter:\n- city (string): The city to get the weather for\n\nThe user has provided the city they want the weather for directly in their request - in this case, the city is Shanghai.\n\nSince I have the value for the required city parameter, I can go ahead and call the getWeather tool, passing in \"Shanghai\" as the city.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_013ZnATGKhvPkt2jjxdFheDK",
+                "id": "toolu_01HxDqJpm33QxDXAExTxm6zu",
                 "name": "getWeather",
                 "input": {
                   "city": "Shanghai"
@@ -551,7 +551,7 @@
           "content": [
             {
               "type": "text",
-              "text": "The current weather in Shanghai is 72 degrees."
+              "text": "The getWeather tool indicates that the current weather in Shanghai is 72 degrees."
             }
           ],
           "role": "assistant",

packages/llamaindex/e2e/node/snapshot/anthropic-agent.snap

@@ -20,14 +20,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has asked for the weather in a specific location, San Francisco. The Weather tool is the relevant function to answer this request, as it returns weather information for a given location.\n\nThe Weather tool requires a single parameter:\n- location (string, required): The user has directly provided the location as \"San Francisco\".\n\nSince the required location parameter has been provided, we have enough information to call the Weather tool.\n</thinking>"
+              "text": "<thinking>\nThe Weather tool is relevant to answer this question, as it can provide weather information for a specified location.\n\nThe Weather tool requires a \"location\" parameter. The user has directly provided the location of \"San Francisco\" in their request.\n\nSince the required \"location\" parameter has been provided, we can proceed with calling the Weather tool to get the weather information for San Francisco. No other tools are needed.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_011YcKkPygw2woJZrVWRRMwH",
+                "id": "toolu_01Y6KpbYCFw4XGtvyXEmeTrB",
                 "name": "Weather",
                 "input": {
                   "location": "San Francisco"
@@ -43,7 +43,7 @@
             "toolResult": {
               "result": "35 degrees and sunny in San Francisco",
               "isError": false,
-              "id": "toolu_011YcKkPygw2woJZrVWRRMwH"
+              "id": "toolu_01Y6KpbYCFw4XGtvyXEmeTrB"
             }
           }
         }
@@ -69,14 +69,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe unique_id function takes firstName and lastName as required parameters. The user has provided their first name (Alex) and last name (Yang) in the request, so we have all the necessary information to call the function.\n</thinking>"
+              "text": "<thinking>\nThe unique_id tool looks relevant for answering this request, as it can provide a unique identifier for a user given their first and last name. \nThe tool requires two parameters:\n- firstName (string)\n- lastName (string)\nLooking at the user's request, they have provided both their first name (Alex) and last name (Yang). So we have all the required parameters to call the unique_id tool.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_012ZLUq5SWsghkXUjsEXsB1f",
+                "id": "toolu_01Q7wYKoNtpGAphTbRSv51fE",
                 "name": "unique_id",
                 "input": {
                   "firstName": "Alex",
@@ -93,7 +93,7 @@
             "toolResult": {
               "result": "123456789",
               "isError": false,
-              "id": "toolu_012ZLUq5SWsghkXUjsEXsB1f"
+              "id": "toolu_01Q7wYKoNtpGAphTbRSv51fE"
             }
           }
         }
@@ -119,14 +119,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user is asking to sum the numbers 1 and 1. The relevant tool is the sumNumbers function, which takes two number parameters a and b.\nThe user has directly provided the values for the required parameters:\na = 1 \nb = 1\nSince all the required parameters are provided, we can proceed with calling the function.\n</thinking>"
+              "text": "<thinking>\nThe user is asking to sum the numbers 1 and 1. The sumNumbers tool is directly relevant for this request.\n\nLooking at the required parameters for sumNumbers:\na (number): The user provided the value 1 for this\nb (number): The user also provided the value 1 for this\n\nSince the user has directly provided values for all the required parameters, we can proceed with calling the sumNumbers tool without needing any additional information from the user.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_01SQD2XkaXkDNLQ2xaFzmguG",
+                "id": "toolu_01AxEUd1s1UmhPc6Y91LBSmw",
                 "name": "sumNumbers",
                 "input": {
                   "a": 1,
@@ -143,7 +143,7 @@
             "toolResult": {
               "result": "2",
               "isError": false,
-              "id": "toolu_01SQD2XkaXkDNLQ2xaFzmguG"
+              "id": "toolu_01AxEUd1s1UmhPc6Y91LBSmw"
             }
           }
         }
@@ -159,14 +159,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user has asked for the weather in a specific location, San Francisco. The Weather tool is the relevant function to answer this request, as it returns weather information for a given location.\n\nThe Weather tool requires a single parameter:\n- location (string, required): The user has directly provided the location as \"San Francisco\".\n\nSince the required location parameter has been provided, we have enough information to call the Weather tool.\n</thinking>"
+              "text": "<thinking>\nThe Weather tool is relevant to answer this question, as it can provide weather information for a specified location.\n\nThe Weather tool requires a \"location\" parameter. The user has directly provided the location of \"San Francisco\" in their request.\n\nSince the required \"location\" parameter has been provided, we can proceed with calling the Weather tool to get the weather information for San Francisco. No other tools are needed.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_011YcKkPygw2woJZrVWRRMwH",
+                "id": "toolu_01Y6KpbYCFw4XGtvyXEmeTrB",
                 "name": "Weather",
                 "input": {
                   "location": "San Francisco"
@@ -201,14 +201,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe unique_id function takes firstName and lastName as required parameters. The user has provided their first name (Alex) and last name (Yang) in the request, so we have all the necessary information to call the function.\n</thinking>"
+              "text": "<thinking>\nThe unique_id tool looks relevant for answering this request, as it can provide a unique identifier for a user given their first and last name. \nThe tool requires two parameters:\n- firstName (string)\n- lastName (string)\nLooking at the user's request, they have provided both their first name (Alex) and last name (Yang). So we have all the required parameters to call the unique_id tool.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_012ZLUq5SWsghkXUjsEXsB1f",
+                "id": "toolu_01Q7wYKoNtpGAphTbRSv51fE",
                 "name": "unique_id",
                 "input": {
                   "firstName": "Alex",
@@ -244,14 +244,14 @@
           "content": [
             {
               "type": "text",
-              "text": "<thinking>\nThe user is asking to sum the numbers 1 and 1. The relevant tool is the sumNumbers function, which takes two number parameters a and b.\nThe user has directly provided the values for the required parameters:\na = 1 \nb = 1\nSince all the required parameters are provided, we can proceed with calling the function.\n</thinking>"
+              "text": "<thinking>\nThe user is asking to sum the numbers 1 and 1. The sumNumbers tool is directly relevant for this request.\n\nLooking at the required parameters for sumNumbers:\na (number): The user provided the value 1 for this\nb (number): The user also provided the value 1 for this\n\nSince the user has directly provided values for all the required parameters, we can proceed with calling the sumNumbers tool without needing any additional information from the user.\n</thinking>"
             }
           ],
           "role": "assistant",
           "options": {
             "toolCall": [
               {
-                "id": "toolu_01SQD2XkaXkDNLQ2xaFzmguG",
+                "id": "toolu_01AxEUd1s1UmhPc6Y91LBSmw",
                 "name": "sumNumbers",
                 "input": {
                   "a": 1,
@@ -271,7 +271,7 @@
           "content": [
             {
               "type": "text",
-              "text": "So 1 + 1 = 2."
+              "text": "So 1 + 1 = 2"
             }
           ],
           "role": "assistant",

packages/llamaindex/e2e/node/snapshot/gpt-4-turbo.snap

@@ -22,7 +22,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_Xa2Kxa2zUE073mnougPWzRlh",
+                "id": "call_UMsqyh51lvDjy2JvMKFoyai3",
                 "name": "Weather",
                 "input": "{\"location\":\"San Jose\"}"
               }
@@ -30,13 +30,13 @@
           }
         },
         {
-          "role": "user",
           "content": "45 degrees and sunny in San Jose",
+          "role": "user",
           "options": {
             "toolResult": {
               "result": "45 degrees and sunny in San Jose",
               "isError": false,
-              "id": "call_Xa2Kxa2zUE073mnougPWzRlh"
+              "id": "call_UMsqyh51lvDjy2JvMKFoyai3"
             }
           }
         }
@@ -54,7 +54,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_Xa2Kxa2zUE073mnougPWzRlh",
+                "id": "call_UMsqyh51lvDjy2JvMKFoyai3",
                 "name": "Weather",
                 "input": "{\"location\":\"San Jose\"}"
               }

packages/llamaindex/e2e/node/snapshot/llm-anthropic.snap

@@ -49,7 +49,7 @@
       "id": "PRESERVE_1",
       "chunk": {
         "raw": null,
-        "delta": "Hello",
+        "delta": "Hello! How can",
         "options": {}
       }
     },
@@ -57,55 +57,7 @@
       "id": "PRESERVE_1",
       "chunk": {
         "raw": null,
-        "delta": "!",
-        "options": {}
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "delta": " How",
-        "options": {}
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "delta": " can",
-        "options": {}
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "delta": " I",
-        "options": {}
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "delta": " assist",
-        "options": {}
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "delta": " you",
-        "options": {}
-      }
-    },
-    {
-      "id": "PRESERVE_1",
-      "chunk": {
-        "raw": null,
-        "delta": " today",
+        "delta": " I assist you today",
         "options": {}
       }
     },

packages/llamaindex/e2e/node/snapshot/openai_agent_system_prompt.snap

@@ -30,7 +30,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_1SlugFuJ7rhwsmXd5aRnJhPe",
+                "id": "call_i3rlYaBlvhTf60phYJh8irvZ",
                 "name": "getWeather",
                 "input": "{\"city\":\"San Francisco\"}"
               }
@@ -38,13 +38,13 @@
           }
         },
         {
-          "role": "user",
           "content": "The weather in San Francisco is 72 degrees",
+          "role": "user",
           "options": {
             "toolResult": {
               "result": "The weather in San Francisco is 72 degrees",
               "isError": false,
-              "id": "call_1SlugFuJ7rhwsmXd5aRnJhPe"
+              "id": "call_i3rlYaBlvhTf60phYJh8irvZ"
             }
           }
         }
@@ -62,7 +62,7 @@
           "options": {
             "toolCall": [
               {
-                "id": "call_1SlugFuJ7rhwsmXd5aRnJhPe",
+                "id": "call_i3rlYaBlvhTf60phYJh8irvZ",
                 "name": "getWeather",
                 "input": "{\"city\":\"San Francisco\"}"
               }

packages/llamaindex/e2e/node/snapshot/queryEngine_subquestion.snap

@@ -13,7 +13,7 @@
       "id": "PRESERVE_1",
       "messages": [
         {
-          "content": "Context information is below.\n---------------------\nBill Gates stole from Apple. Steve Jobs stole from Xerox.\n---------------------\nGiven the context information and not prior knowledge, answer the query.\nQuery: What is Bill Gates' idea\nAnswer:",
+          "content": "Context information is below.\n---------------------\nBill Gates stole from Apple.\n Steve Jobs stole from Xerox.\n---------------------\nGiven the context information and not prior knowledge, answer the query.\nQuery: What idea did Bill Gates get?\nAnswer:",
           "role": "user"
         }
       ]
@@ -22,7 +22,7 @@
       "id": "PRESERVE_2",
       "messages": [
         {
-          "content": "Context information is below.\n---------------------\nSub question: What is Bill Gates' idea\nResponse: Bill Gates' idea was to steal from Apple.\n---------------------\nGiven the context information and not prior knowledge, answer the query.\nQuery: What did Bill Gates steal from?\nAnswer:",
+          "content": "Context information is below.\n---------------------\nSub question: What idea did Bill Gates get?\nResponse: Bill Gates got the idea from Apple.\n---------------------\nGiven the context information and not prior knowledge, answer the query.\nQuery: What did Bill Gates steal from?\nAnswer:",
           "role": "user"
         }
       ]
@@ -34,7 +34,7 @@
       "response": {
         "raw": null,
         "message": {
-          "content": "```json\n[\n    {\n        \"subQuestion\": \"What is Bill Gates' idea\",\n        \"toolName\": \"bill_gates_idea\"\n    }\n]\n```",
+          "content": "```json\n[\n    {\n        \"subQuestion\": \"What idea did Bill Gates get?\",\n        \"toolName\": \"bill_gates_idea\"\n    }\n]\n```",
           "role": "assistant",
           "options": {}
         }
@@ -45,7 +45,7 @@
       "response": {
         "raw": null,
         "message": {
-          "content": "Bill Gates' idea was to steal from Apple.",
+          "content": "Bill Gates got the idea from Apple.",
           "role": "assistant",
           "options": {}
         }
@@ -56,7 +56,7 @@
       "response": {
         "raw": null,
         "message": {
-          "content": "Bill Gates stole from Apple.",
+          "content": "Bill Gates stole the idea from Apple.",
           "role": "assistant",
           "options": {}
         }

packages/llamaindex/e2e/node/snapshot/react-agent-stream.snap

@@ -41,7 +41,7 @@
       "response": {
         "raw": null,
         "message": {
-          "content": "Thought: I need to use a tool to help me answer the question. \nAction: getWeather\nAction Input: {\"city\": \"San Francisco\"}",
+          "content": "Thought: I need to use a tool to help me answer the question.\nAction: getWeather\nAction Input: {\"city\": \"San Francisco\"}",
           "role": "assistant",
           "options": {}
         }
@@ -177,15 +177,7 @@
       "chunk": {
         "raw": null,
         "options": {},
-        "delta": "."
-      }
-    },
-    {
-      "id": "PRESERVE_0",
-      "chunk": {
-        "raw": null,
-        "options": {},
-        "delta": " \n"
+        "delta": ".\n"
       }
     },
     {

packages/llamaindex/e2e/node/utils.ts

@@ -42,7 +42,7 @@ export async function mockLLMEvent(
     newLLMCompleteMockStorage.llmEventStart.push({
       ...event.detail,
       // @ts-expect-error id is not UUID, but it is fine for testing
-      id: idMap.get(event.detail.payload.id)!,
+      id: idMap.get(event.detail.id)!,
     });
   }
 
@@ -50,7 +50,7 @@ export async function mockLLMEvent(
     newLLMCompleteMockStorage.llmEventEnd.push({
       ...event.detail,
       // @ts-expect-error id is not UUID, but it is fine for testing
-      id: idMap.get(event.detail.payload.id)!,
+      id: idMap.get(event.detail.id)!,
       response: {
         ...event.detail.response,
         // hide raw object since it might too big
@@ -63,7 +63,7 @@ export async function mockLLMEvent(
     newLLMCompleteMockStorage.llmEventStream.push({
       ...event.detail,
       // @ts-expect-error id is not UUID, but it is fine for testing
-      id: idMap.get(event.detail.payload.id)!,
+      id: idMap.get(event.detail.id)!,
       chunk: {
         ...event.detail.chunk,
         // hide raw object since it might too big

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.5.2",
+  "version": "0.5.9",
   "license": "MIT",
   "type": "module",
   "keywords": [
@@ -20,18 +20,20 @@
     "llamaindex"
   ],
   "dependencies": {
-    "@anthropic-ai/sdk": "^0.21.1",
+    "@anthropic-ai/sdk": "0.21.1",
     "@aws-crypto/sha256-js": "^5.2.0",
     "@azure/identity": "^4.2.1",
     "@datastax/astra-db-ts": "^1.2.1",
+    "@discordjs/rest": "^2.3.0",
     "@google-cloud/vertexai": "^1.2.0",
-    "@google/generative-ai": "^0.12.0",
-    "@grpc/grpc-js": "^1.10.8",
+    "@google/generative-ai": "0.12.0",
+    "@grpc/grpc-js": "^1.10.11",
     "@huggingface/inference": "^2.7.0",
     "@llamaindex/cloud": "workspace:*",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
-    "@mistralai/mistralai": "^0.4.0",
+    "@mistralai/mistralai": "^0.5.0",
+    "@mixedbread-ai/sdk": "^2.2.11",
     "@pinecone-database/pinecone": "^2.2.2",
     "@qdrant/js-client-rest": "^1.9.0",
     "@types/lodash": "^4.17.4",
@@ -39,13 +41,13 @@
     "@types/papaparse": "^5.3.14",
     "@types/pg": "^8.11.6",
     "@xenova/transformers": "^2.17.2",
-    "@zilliz/milvus2-sdk-node": "^2.4.2",
+    "@zilliz/milvus2-sdk-node": "^2.4.4",
     "ajv": "^8.16.0",
-    "assemblyai": "^4.4.5",
+    "assemblyai": "^4.6.0",
     "chromadb": "1.8.1",
-    "cohere-ai": "7.9.5",
+    "cohere-ai": "7.10.6",
+    "discord-api-types": "^0.37.92",
     "groq-sdk": "^0.5.0",
-    "@mixedbread-ai/sdk": "^2.2.11",
     "js-tiktoken": "^1.0.12",
     "lodash": "^4.17.21",
     "magic-bytes.js": "^1.10.0",
@@ -53,16 +55,16 @@
     "md-utils-ts": "^2.0.0",
     "mongodb": "^6.7.0",
     "notion-md-crawler": "^1.0.0",
-    "openai": "^4.52.0",
+    "openai": "^4.52.5",
     "papaparse": "^5.4.1",
     "pathe": "^1.1.2",
     "pg": "^8.12.0",
-    "pgvector": "^0.1.8",
-    "portkey-ai": "^0.1.16",
+    "pgvector": "^0.2.0",
+    "portkey-ai": "0.1.16",
     "rake-modified": "^1.0.8",
     "string-strip-html": "^13.4.8",
     "tiktoken": "^1.0.15",
-    "unpdf": "^0.10.1",
+    "unpdf": "^0.11.0",
     "wikipedia": "^2.1.2",
     "wink-nlp": "^2.3.0",
     "zod": "^3.23.8"
@@ -77,11 +79,11 @@
   },
   "devDependencies": {
     "@notionhq/client": "^2.2.15",
-    "@swc/cli": "^0.3.12",
+    "@swc/cli": "^0.4.0",
     "@swc/core": "^1.6.3",
     "concurrently": "^8.2.2",
-    "glob": "^10.4.2",
-    "typescript": "^5.5.2"
+    "glob": "^11.0.0",
+    "typescript": "^5.5.3"
   },
   "engines": {
     "node": ">=18.0.0"

packages/llamaindex/src/PromptHelper.ts

@@ -1,6 +1,6 @@
-import { tokenizers, type Tokenizer } from "@llamaindex/env";
+import { SentenceSplitter } from "@llamaindex/core/node-parser";
+import { type Tokenizer, tokenizers } from "@llamaindex/env";
 import type { SimplePrompt } from "./Prompt.js";
-import { SentenceSplitter } from "./TextSplitter.js";
 import {
   DEFAULT_CHUNK_OVERLAP_RATIO,
   DEFAULT_CONTEXT_WINDOW,
@@ -107,8 +107,7 @@ export class PromptHelper {
       throw new Error("Got 0 as available chunk size");
     }
     const chunkOverlap = this.chunkOverlapRatio * chunkSize;
-    const textSplitter = new SentenceSplitter({ chunkSize, chunkOverlap });
-    return textSplitter;
+    return new SentenceSplitter({ chunkSize, chunkOverlap });
   }
 
   /**

packages/llamaindex/src/QuestionGenerator.ts

@@ -1,4 +1,6 @@
 import type { LLM, ToolMetadata } from "@llamaindex/core/llms";
+import type { QueryType } from "@llamaindex/core/query-engine";
+import { extractText } from "@llamaindex/core/utils";
 import { SubQuestionOutputParser } from "./OutputParser.js";
 import type { SubQuestionPrompt } from "./Prompt.js";
 import { buildToolsText, defaultSubQuestionPrompt } from "./Prompt.js";
@@ -43,9 +45,12 @@ export class LLMQuestionGenerator
     }
   }
 
-  async generate(tools: ToolMetadata[], query: string): Promise<SubQuestion[]> {
+  async generate(
+    tools: ToolMetadata[],
+    query: QueryType,
+  ): Promise<SubQuestion[]> {
     const toolsStr = buildToolsText(tools);
-    const queryStr = query;
+    const queryStr = extractText(query);
     const prediction = (
       await this.llm.complete({
         prompt: this.prompt({

packages/llamaindex/src/ServiceContext.ts

@@ -1,10 +1,12 @@
+import type { BaseEmbedding } from "@llamaindex/core/embeddings";
 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 type { BaseEmbedding } from "./embeddings/types.js";
 import { OpenAI } from "./llm/openai.js";
-import { SimpleNodeParser } from "./nodeParsers/SimpleNodeParser.js";
-import type { NodeParser } from "./nodeParsers/types.js";
 
 /**
  * The ServiceContext is a collection of components that are used in different parts of the application.
@@ -33,7 +35,7 @@ export function serviceContextFromDefaults(options?: ServiceContextOptions) {
     embedModel: options?.embedModel ?? new OpenAIEmbedding(),
     nodeParser:
       options?.nodeParser ??
-      new SimpleNodeParser({
+      new SentenceSplitter({
         chunkSize: options?.chunkSize,
         chunkOverlap: options?.chunkOverlap,
       }),

packages/llamaindex/src/Settings.ts

@@ -5,18 +5,20 @@ import {
 import { OpenAI } from "./llm/openai.js";
 
 import { PromptHelper } from "./PromptHelper.js";
-import { SimpleNodeParser } from "./nodeParsers/SimpleNodeParser.js";
 
+import type { BaseEmbedding } from "@llamaindex/core/embeddings";
 import type { LLM } from "@llamaindex/core/llms";
+import {
+  type NodeParser,
+  SentenceSplitter,
+} from "@llamaindex/core/node-parser";
 import { AsyncLocalStorage, getEnv } from "@llamaindex/env";
 import type { ServiceContext } from "./ServiceContext.js";
-import type { BaseEmbedding } from "./embeddings/types.js";
 import {
   getEmbeddedModel,
   setEmbeddedModel,
   withEmbeddedModel,
 } from "./internal/settings/EmbedModel.js";
-import type { NodeParser } from "./nodeParsers/types.js";
 
 export type PromptConfig = {
   llm?: string;
@@ -108,7 +110,7 @@ class GlobalSettings implements Config {
 
   get nodeParser(): NodeParser {
     if (this.#nodeParser === null) {
-      this.#nodeParser = new SimpleNodeParser({
+      this.#nodeParser = new SentenceSplitter({
         chunkSize: this.chunkSize,
         chunkOverlap: this.chunkOverlap,
       });