Release 0.5.20 (#1132)

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

apps/docs/CHANGELOG.md

@@ -1,5 +1,28 @@
 # docs
 
+## 0.0.61
+
+### Patch Changes
+
+- Updated dependencies [d9d6c56]
+- Updated dependencies [22ff486]
+- Updated dependencies [eed0b04]
+  - llamaindex@0.5.20
+
+## 0.0.60
+
+### Patch Changes
+
+- Updated dependencies [fcbf183]
+  - llamaindex@0.5.19
+
+## 0.0.59
+
+### Patch Changes
+
+- Updated dependencies [8b66cf4]
+  - llamaindex@0.5.18
+
 ## 0.0.58
 
 ### Patch Changes

apps/docs/docs/getting_started/environments.md

@@ -6,10 +6,17 @@ sidebar_position: 2
 
 We support Node.JS versions 18, 20 and 22, with experimental support for Deno, Bun and Vercel Edge functions.
 
-## NextJS App Router
+## NextJS
 
-If you're using NextJS App Router route handlers/serverless functions, you'll need to use the NodeJS mode:
+If you're using NextJS you'll need to add `withLlamaIndex` to your `next.config.js` file. This will add the necessary configuration for included 3rd-party libraries to your build:
 
 ```js
-export const runtime = "nodejs"; // default
+// next.config.js
+const withLlamaIndex = require("llamaindex/next");
+
+module.exports = withLlamaIndex({
+  // your next.js config
+});
 ```
+
+For details, check the latest [withLlamaIndex](https://github.com/run-llama/LlamaIndexTS/blob/main/packages/llamaindex/src/next.ts) implementation.

apps/docs/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docs",
-  "version": "0.0.58",
+  "version": "0.0.61",
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",

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

@@ -1,5 +1,31 @@
 # @llamaindex/autotool-02-next-example
 
+## 0.1.45
+
+### Patch Changes
+
+- Updated dependencies [d9d6c56]
+- Updated dependencies [22ff486]
+- Updated dependencies [eed0b04]
+  - llamaindex@0.5.20
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.44
+
+### Patch Changes
+
+- Updated dependencies [fcbf183]
+  - llamaindex@0.5.19
+  - @llamaindex/autotool@2.0.1
+
+## 0.1.43
+
+### Patch Changes
+
+- Updated dependencies [8b66cf4]
+  - llamaindex@0.5.18
+  - @llamaindex/autotool@2.0.1
+
 ## 0.1.42
 
 ### Patch Changes

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

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool-02-next-example",
   "private": true,
-  "version": "0.1.42",
+  "version": "0.1.45",
   "scripts": {
     "dev": "next dev",
     "build": "next build",

packages/autotool/package.json

@@ -51,7 +51,7 @@
     "unplugin": "^1.10.1"
   },
   "peerDependencies": {
-    "llamaindex": "^0.5.17",
+    "llamaindex": "^0.5.20",
     "openai": "^4",
     "typescript": "^4"
   },

packages/community/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/community
 
+## 0.0.30
+
+### Patch Changes
+
+- Updated dependencies [e27e7dd]
+  - @llamaindex/core@0.1.9
+
 ## 0.0.29
 
 ### Patch Changes

packages/community/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.29",
+  "version": "0.0.30",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/core/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/core
 
+## 0.1.9
+
+### Patch Changes
+
+- e27e7dd: chore: bump `natural` to 8.0.1
+
 ## 0.1.8
 
 ### Patch Changes

packages/core/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.1.8",
+  "version": "0.1.9",
   "description": "LlamaIndex Core Module",
   "exports": {
     "./node-parser": {
@@ -132,7 +132,7 @@
   "devDependencies": {
     "ajv": "^8.16.0",
     "bunchee": "5.3.1",
-    "natural": "^7.1.0"
+    "natural": "^8.0.1"
   },
   "dependencies": {
     "@llamaindex/env": "workspace:*",

packages/core/src/node-parser/sentence_tokenizer.d.ts

@@ -1,4 +1,5 @@
 declare class SentenceTokenizer {
+  constructor(abbreviations?: string[]);
   tokenize(text: string): string[];
 }
 

packages/core/src/node-parser/sentence_tokenizer.js

@@ -0,0 +1,222 @@
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __commonJS = (cb, mod) =>
+  function __require() {
+    return (
+      mod ||
+        (0, cb[__getOwnPropNames(cb)[0]])((mod = { exports: {} }).exports, mod),
+      mod.exports
+    );
+  };
+
+// lib/natural/tokenizers/tokenizer.js
+var require_tokenizer = __commonJS({
+  "lib/natural/tokenizers/tokenizer.js"(exports, module) {
+    "use strict";
+    var Tokenizer = class {
+      trim(array) {
+        while (array[array.length - 1] === "") {
+          array.pop();
+        }
+        while (array[0] === "") {
+          array.shift();
+        }
+        return array;
+      }
+    };
+    module.exports = Tokenizer;
+  },
+});
+
+// lib/natural/tokenizers/sentence_tokenizer.js
+var require_sentence_tokenizer = __commonJS({
+  "lib/natural/tokenizers/sentence_tokenizer.js"(exports, module) {
+    var Tokenizer = require_tokenizer();
+    var NUM = "NUMBER";
+    var DELIM = "DELIM";
+    var URI = "URI";
+    var ABBREV = "ABBREV";
+    var DEBUG = false;
+    function generateUniqueCode(base, index) {
+      return `{{${base}_${index}}}`;
+    }
+    function escapeRegExp(string) {
+      return string.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+    }
+    var SentenceTokenizer = class extends Tokenizer {
+      constructor(abbreviations) {
+        super();
+        if (abbreviations) {
+          this.abbreviations = abbreviations;
+        } else {
+          this.abbreviations = [];
+        }
+        this.replacementMap = null;
+        this.replacementCounter = 0;
+      }
+      replaceUrisWithPlaceholders(text) {
+        const urlPattern =
+          /(https?:\/\/\S+|www\.\S+|ftp:\/\/\S+|(mailto:)?[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}|file:\/\/\S+)/gi;
+        const modifiedText = text.replace(urlPattern, (match) => {
+          const placeholder = generateUniqueCode(
+            URI,
+            this.replacementCounter++,
+          );
+          this.replacementMap.set(placeholder, match);
+          return placeholder;
+        });
+        return modifiedText;
+      }
+      replaceAbbreviations(text) {
+        if (this.abbreviations.length === 0) {
+          return text;
+        }
+        const pattern = new RegExp(
+          `(${this.abbreviations.map((abbrev) => escapeRegExp(abbrev)).join("|")})`,
+          "gi",
+        );
+        const replacedText = text.replace(pattern, (match) => {
+          const code = generateUniqueCode(ABBREV, this.replacementCounter++);
+          this.replacementMap.set(code, match);
+          return code;
+        });
+        return replacedText;
+      }
+      replaceDelimitersWithPlaceholders(text) {
+        const delimiterPattern = /([.?!… ]*)([.?!…])(["'”’)}\]]?)/g;
+        const modifiedText = text.replace(
+          delimiterPattern,
+          (match, p1, p2, p3) => {
+            const placeholder = generateUniqueCode(
+              DELIM,
+              this.replacementCounter++,
+            );
+            this.delimiterMap.set(placeholder, p1 + p2 + p3);
+            return placeholder;
+          },
+        );
+        return modifiedText;
+      }
+      splitOnPlaceholders(text, placeholders) {
+        if (this.delimiterMap.size === 0) {
+          return [text];
+        }
+        const keys = Array.from(this.delimiterMap.keys());
+        const pattern = new RegExp(`(${keys.map(escapeRegExp).join("|")})`);
+        const parts = text.split(pattern);
+        const sentences = [];
+        for (let i = 0; i < parts.length; i += 2) {
+          const sentence = parts[i];
+          const placeholder = parts[i + 1] || "";
+          sentences.push(sentence + placeholder);
+        }
+        return sentences;
+      }
+      replaceNumbersWithCode(text) {
+        const numberPattern = /\b\d{1,3}(?:,\d{3})*(?:\.\d+)?\b/g;
+        const replacedText = text.replace(numberPattern, (match) => {
+          const code = generateUniqueCode(NUM, this.replacementCounter++);
+          this.replacementMap.set(code, match);
+          return code;
+        });
+        return replacedText;
+      }
+      revertReplacements(text) {
+        let originalText = text;
+        for (const [
+          placeholder,
+          replacement,
+        ] of this.replacementMap.entries()) {
+          const pattern = new RegExp(escapeRegExp(placeholder), "g");
+          originalText = originalText.replace(pattern, replacement);
+        }
+        return originalText;
+      }
+      revertDelimiters(text) {
+        let originalText = text;
+        for (const [placeholder, replacement] of this.delimiterMap.entries()) {
+          const pattern = new RegExp(escapeRegExp(placeholder), "g");
+          originalText = originalText.replace(pattern, replacement);
+        }
+        return originalText;
+      }
+      tokenize(text) {
+        this.replacementCounter = 0;
+        this.replacementMap = /* @__PURE__ */ new Map();
+        this.delimiterMap = /* @__PURE__ */ new Map();
+        DEBUG &&
+          console.log(
+            "---Start of sentence tokenization-----------------------",
+          );
+        DEBUG && console.log("Original input: >>>" + text + "<<<");
+        const result1 = this.replaceAbbreviations(text);
+        DEBUG &&
+          console.log(
+            "Phase 1: replacing abbreviations: " + JSON.stringify(result1),
+          );
+        const result2 = this.replaceUrisWithPlaceholders(result1);
+        DEBUG &&
+          console.log("Phase 2: replacing URIs: " + JSON.stringify(result2));
+        const result3 = this.replaceNumbersWithCode(result2);
+        DEBUG &&
+          console.log(
+            "Phase 3: replacing numbers with placeholders: " +
+              JSON.stringify(result3),
+          );
+        const result4 = this.replaceDelimitersWithPlaceholders(result3);
+        DEBUG &&
+          console.log(
+            "Phase 4: replacing delimiters with placeholders: " +
+              JSON.stringify(result4),
+          );
+        const sentences = this.splitOnPlaceholders(result4);
+        DEBUG &&
+          console.log(
+            "Phase 5: splitting into sentences on placeholders: " +
+              JSON.stringify(sentences),
+          );
+        const newSentences = sentences.map((s) => {
+          const s1 = this.revertReplacements(s);
+          return this.revertDelimiters(s1);
+        });
+        DEBUG &&
+          console.log(
+            "Phase 6: replacing back abbreviations, URIs, numbers and delimiters: " +
+              JSON.stringify(newSentences),
+          );
+        const trimmedSentences = this.trim(newSentences);
+        DEBUG &&
+          console.log(
+            "Phase 7: trimming array of empty sentences: " +
+              JSON.stringify(trimmedSentences),
+          );
+        const trimmedSentences2 = trimmedSentences.map((sent) => sent.trim());
+        DEBUG &&
+          console.log(
+            "Phase 8: trimming sentences from surrounding whitespace: " +
+              JSON.stringify(trimmedSentences2),
+          );
+        DEBUG &&
+          console.log(
+            "---End of sentence tokenization--------------------------",
+          );
+        DEBUG &&
+          console.log(
+            "---Replacement map---------------------------------------",
+          );
+        DEBUG && console.log([...this.replacementMap.entries()]);
+        DEBUG &&
+          console.log(
+            "---Delimiter map-----------------------------------------",
+          );
+        DEBUG && console.log([...this.delimiterMap.entries()]);
+        DEBUG &&
+          console.log(
+            "---------------------------------------------------------",
+          );
+        return trimmedSentences2;
+      }
+    };
+    module.exports = SentenceTokenizer;
+  },
+});
+export default require_sentence_tokenizer();

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

@@ -1,5 +1,5 @@
 import type { TextSplitter } from "./base";
-import SentenceTokenizerNew from "./sentence-tokenizer-parser.js";
+import SentenceTokenizer from "./sentence_tokenizer";
 
 export type TextSplitterFn = (text: string) => string[];
 
@@ -31,11 +31,17 @@ export const splitByChar = (): TextSplitterFn => {
   return (text: string) => text.split("");
 };
 
-let sentenceTokenizer: SentenceTokenizerNew | null = null;
+let sentenceTokenizer: SentenceTokenizer | null = null;
 
 export const splitBySentenceTokenizer = (): TextSplitterFn => {
   if (!sentenceTokenizer) {
-    sentenceTokenizer = new SentenceTokenizerNew();
+    sentenceTokenizer = new SentenceTokenizer([
+      "i.e.",
+      "etc.",
+      "vs.",
+      "Inc.",
+      "A.S.A.P.",
+    ]);
   }
   const tokenizer = sentenceTokenizer;
   return (text: string) => {

packages/experimental/CHANGELOG.md

@@ -1,5 +1,28 @@
 # @llamaindex/experimental
 
+## 0.0.70
+
+### Patch Changes
+
+- Updated dependencies [d9d6c56]
+- Updated dependencies [22ff486]
+- Updated dependencies [eed0b04]
+  - llamaindex@0.5.20
+
+## 0.0.69
+
+### Patch Changes
+
+- Updated dependencies [fcbf183]
+  - llamaindex@0.5.19
+
+## 0.0.68
+
+### Patch Changes
+
+- Updated dependencies [8b66cf4]
+  - llamaindex@0.5.18
+
 ## 0.0.67
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.67",
+  "version": "0.0.70",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,27 @@
 # llamaindex
 
+## 0.5.20
+
+### Patch Changes
+
+- d9d6c56: Add support for MetadataFilters for PostgreSQL
+- 22ff486: Add tiktoken WASM to withLlamaIndex
+- eed0b04: fix: use LLM metadata mode for generating context of ContextChatEngine
+
+## 0.5.19
+
+### Patch Changes
+
+- fcbf183: implement llamacloud file service
+
+## 0.5.18
+
+### Patch Changes
+
+- 8b66cf4: feat: support organization id in llamacloud index
+- Updated dependencies [e27e7dd]
+  - @llamaindex/core@0.1.9
+
 ## 0.5.17
 
 ### Patch Changes

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

@@ -1,5 +1,28 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.54
+
+### Patch Changes
+
+- Updated dependencies [d9d6c56]
+- Updated dependencies [22ff486]
+- Updated dependencies [eed0b04]
+  - llamaindex@0.5.20
+
+## 0.0.53
+
+### Patch Changes
+
+- Updated dependencies [fcbf183]
+  - llamaindex@0.5.19
+
+## 0.0.52
+
+### Patch Changes
+
+- Updated dependencies [8b66cf4]
+  - llamaindex@0.5.18
+
 ## 0.0.51
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.51",
+  "version": "0.0.54",
   "type": "module",
   "private": true,
   "scripts": {

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

@@ -1,5 +1,28 @@
 # @llamaindex/next-agent-test
 
+## 0.1.54
+
+### Patch Changes
+
+- Updated dependencies [d9d6c56]
+- Updated dependencies [22ff486]
+- Updated dependencies [eed0b04]
+  - llamaindex@0.5.20
+
+## 0.1.53
+
+### Patch Changes
+
+- Updated dependencies [fcbf183]
+  - llamaindex@0.5.19
+
+## 0.1.52
+
+### Patch Changes
+
+- Updated dependencies [8b66cf4]
+  - llamaindex@0.5.18
+
 ## 0.1.51
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.51",
+  "version": "0.1.54",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,28 @@
 # test-edge-runtime
 
+## 0.1.53
+
+### Patch Changes
+
+- Updated dependencies [d9d6c56]
+- Updated dependencies [22ff486]
+- Updated dependencies [eed0b04]
+  - llamaindex@0.5.20
+
+## 0.1.52
+
+### Patch Changes
+
+- Updated dependencies [fcbf183]
+  - llamaindex@0.5.19
+
+## 0.1.51
+
+### Patch Changes
+
+- Updated dependencies [8b66cf4]
+  - llamaindex@0.5.18
+
 ## 0.1.50
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.50",
+  "version": "0.1.53",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,28 @@
 # @llamaindex/next-node-runtime
 
+## 0.0.35
+
+### Patch Changes
+
+- Updated dependencies [d9d6c56]
+- Updated dependencies [22ff486]
+- Updated dependencies [eed0b04]
+  - llamaindex@0.5.20
+
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [fcbf183]
+  - llamaindex@0.5.19
+
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [8b66cf4]
+  - llamaindex@0.5.18
+
 ## 0.0.32
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.0.32",
+  "version": "0.0.35",
   "private": true,
   "scripts": {
     "dev": "next dev",

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

@@ -1,5 +1,28 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.54
+
+### Patch Changes
+
+- Updated dependencies [d9d6c56]
+- Updated dependencies [22ff486]
+- Updated dependencies [eed0b04]
+  - llamaindex@0.5.20
+
+## 0.0.53
+
+### Patch Changes
+
+- Updated dependencies [fcbf183]
+  - llamaindex@0.5.19
+
+## 0.0.52
+
+### Patch Changes
+
+- Updated dependencies [8b66cf4]
+  - llamaindex@0.5.18
+
 ## 0.0.51
 
 ### Patch Changes

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

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.51",
+  "version": "0.0.54",
   "type": "module",
   "private": true,
   "scripts": {

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.5.17",
+  "version": "0.5.20",
   "license": "MIT",
   "type": "module",
   "keywords": [

packages/llamaindex/src/cloud/LLamaCloudFileService.ts

@@ -0,0 +1,99 @@
+import {
+  FilesService,
+  PipelinesService,
+  ProjectsService,
+} from "@llamaindex/cloud/api";
+import { initService } from "./utils.js";
+
+export class LLamaCloudFileService {
+  /**
+   * Get list of projects, each project contains a list of pipelines
+   */
+  public static async getAllProjectsWithPipelines() {
+    initService();
+    try {
+      const projects = await ProjectsService.listProjectsApiV1ProjectsGet();
+      const pipelines =
+        await PipelinesService.searchPipelinesApiV1PipelinesGet();
+      return projects.map((project) => ({
+        ...project,
+        pipelines: pipelines.filter((p) => p.project_id === project.id),
+      }));
+    } catch (error) {
+      console.error("Error listing projects and pipelines:", error);
+      return [];
+    }
+  }
+
+  /**
+   * Upload a file to a pipeline in LlamaCloud
+   */
+  public static async addFileToPipeline(
+    projectId: string,
+    pipelineId: string,
+    uploadFile: File | Blob,
+    customMetadata: Record<string, any> = {},
+  ) {
+    initService();
+    const file = await FilesService.uploadFileApiV1FilesPost({
+      projectId,
+      formData: {
+        upload_file: uploadFile,
+      },
+    });
+    const files = [
+      {
+        file_id: file.id,
+        custom_metadata: { file_id: file.id, ...customMetadata },
+      },
+    ];
+    await PipelinesService.addFilesToPipelineApiV1PipelinesPipelineIdFilesPut({
+      pipelineId,
+      requestBody: files,
+    });
+
+    // Wait 2s for the file to be processed
+    const maxAttempts = 20;
+    let attempt = 0;
+    while (attempt < maxAttempts) {
+      const result =
+        await PipelinesService.getPipelineFileStatusApiV1PipelinesPipelineIdFilesFileIdStatusGet(
+          {
+            pipelineId,
+            fileId: file.id,
+          },
+        );
+      if (result.status === "ERROR") {
+        throw new Error(`File processing failed: ${JSON.stringify(result)}`);
+      }
+      if (result.status === "SUCCESS") {
+        // File is ingested - return the file id
+        return file.id;
+      }
+      attempt += 1;
+      await new Promise((resolve) => setTimeout(resolve, 100)); // Sleep for 100ms
+    }
+    throw new Error(
+      `File processing did not complete after ${maxAttempts} attempts.`,
+    );
+  }
+
+  /**
+   * Get download URL for a file in LlamaCloud
+   */
+  public static async getFileUrl(pipelineId: string, filename: string) {
+    initService();
+    const allPipelineFiles =
+      await PipelinesService.listPipelineFilesApiV1PipelinesPipelineIdFilesGet({
+        pipelineId,
+      });
+    const file = allPipelineFiles.find((file) => file.name === filename);
+    if (!file?.file_id) return null;
+    const fileContent =
+      await FilesService.readFileContentApiV1FilesIdContentGet({
+        id: file.file_id,
+        projectId: file.project_id,
+      });
+    return fileContent.url;
+  }
+}

packages/llamaindex/src/cloud/LlamaCloudIndex.ts

@@ -8,7 +8,7 @@ import type { CloudRetrieveParams } from "./LlamaCloudRetriever.js";
 import { LlamaCloudRetriever } from "./LlamaCloudRetriever.js";
 import { getPipelineCreate } from "./config.js";
 import type { CloudConstructorParams } from "./constants.js";
-import { getAppBaseUrl, initService } from "./utils.js";
+import { getAppBaseUrl, getProjectId, initService } from "./utils.js";
 
 import { PipelinesService, ProjectsService } from "@llamaindex/cloud/api";
 import { SentenceSplitter } from "@llamaindex/core/node-parser";
@@ -132,18 +132,28 @@ export class LlamaCloudIndex {
     await this.waitForPipelineIngestion(verbose, raiseOnError);
   }
 
-  private async getPipelineId(
-    name: string,
-    projectName: string,
+  public async getPipelineId(
+    name?: string,
+    projectName?: string,
   ): Promise<string> {
     const pipelines = await PipelinesService.searchPipelinesApiV1PipelinesGet({
-      projectName,
-      pipelineName: name,
+      projectId: await this.getProjectId(projectName),
+      pipelineName: name ?? this.params.name,
     });
 
     return pipelines[0].id;
   }
 
+  public async getProjectId(
+    projectName?: string,
+    organizationId?: string,
+  ): Promise<string> {
+    return await getProjectId(
+      projectName ?? this.params.projectName,
+      organizationId ?? this.params.organizationId,
+    );
+  }
+
   static async fromDocuments(
     params: {
       documents: Document[];
@@ -168,6 +178,7 @@ export class LlamaCloudIndex {
     });
 
     const project = await ProjectsService.upsertProjectApiV1ProjectsPut({
+      organizationId: params.organizationId,
       requestBody: {
         name: params.projectName ?? "default",
       },

packages/llamaindex/src/cloud/LlamaCloudRetriever.ts

@@ -11,7 +11,7 @@ import { extractText, wrapEventCaller } from "@llamaindex/core/utils";
 import type { BaseRetriever, RetrieveParams } from "../Retriever.js";
 import type { ClientParams, CloudConstructorParams } from "./constants.js";
 import { DEFAULT_PROJECT_NAME } from "./constants.js";
-import { initService } from "./utils.js";
+import { getProjectId, initService } from "./utils.js";
 
 export type CloudRetrieveParams = Omit<
   RetrievalParams,
@@ -21,6 +21,7 @@ export type CloudRetrieveParams = Omit<
 export class LlamaCloudRetriever implements BaseRetriever {
   clientParams: ClientParams;
   retrieveParams: CloudRetrieveParams;
+  organizationId?: string;
   projectName: string = DEFAULT_PROJECT_NAME;
   pipelineName: string;
 
@@ -49,6 +50,9 @@ export class LlamaCloudRetriever implements BaseRetriever {
     if (params.projectName) {
       this.projectName = params.projectName;
     }
+    if (params.organizationId) {
+      this.organizationId = params.organizationId;
+    }
   }
 
   @wrapEventCaller
@@ -57,7 +61,7 @@ export class LlamaCloudRetriever implements BaseRetriever {
     preFilters,
   }: RetrieveParams): Promise<NodeWithScore[]> {
     const pipelines = await PipelinesService.searchPipelinesApiV1PipelinesGet({
-      projectName: this.projectName,
+      projectId: await getProjectId(this.projectName, this.organizationId),
       pipelineName: this.pipelineName,
     });
 

packages/llamaindex/src/cloud/constants.ts

@@ -8,5 +8,6 @@ export type ClientParams = { apiKey?: string; baseUrl?: string };
 export type CloudConstructorParams = {
   name: string;
   projectName: string;
+  organizationId?: string;
   serviceContext?: ServiceContext;
 } & ClientParams;

packages/llamaindex/src/cloud/index.ts

@@ -1,4 +1,5 @@
 export type { CloudConstructorParams } from "./constants.js";
+export { LLamaCloudFileService } from "./LLamaCloudFileService.js";
 export { LlamaCloudIndex } from "./LlamaCloudIndex.js";
 export {
   LlamaCloudRetriever,

packages/llamaindex/src/cloud/utils.ts

@@ -1,4 +1,4 @@
-import { OpenAPI } from "@llamaindex/cloud/api";
+import { OpenAPI, ProjectsService } from "@llamaindex/cloud/api";
 import { getEnv } from "@llamaindex/env";
 import type { ClientParams } from "./constants.js";
 import { DEFAULT_BASE_URL } from "./constants.js";
@@ -20,3 +20,31 @@ export function initService({ apiKey, baseUrl }: ClientParams = {}) {
     );
   }
 }
+
+export async function getProjectId(
+  projectName: string,
+  organizationId?: string,
+): Promise<string> {
+  const projects = await ProjectsService.listProjectsApiV1ProjectsGet({
+    projectName: projectName,
+    organizationId: organizationId,
+  });
+
+  if (projects.length === 0) {
+    throw new Error(
+      `Unknown project name ${projectName}. Please confirm a managed project with this name exists.`,
+    );
+  } else if (projects.length > 1) {
+    throw new Error(
+      `Multiple projects found with name ${projectName}. Please specify organization_id.`,
+    );
+  }
+
+  const project = projects[0];
+
+  if (!project.id) {
+    throw new Error(`No project found with name ${projectName}`);
+  }
+
+  return project.id;
+}

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

@@ -4,7 +4,7 @@ import type {
   MessageContent,
   MessageType,
 } from "@llamaindex/core/llms";
-import { EngineResponse } from "@llamaindex/core/schema";
+import { EngineResponse, MetadataMode } from "@llamaindex/core/schema";
 import {
   extractText,
   streamConverter,
@@ -53,6 +53,7 @@ export class ContextChatEngine extends PromptMixin implements ChatEngine {
       contextSystemPrompt: init?.contextSystemPrompt,
       nodePostprocessors: init?.nodePostprocessors,
       contextRole: init?.contextRole,
+      metadataMode: MetadataMode.LLM,
     });
     this.systemPrompt = init.systemPrompt;
   }

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

@@ -1,5 +1,5 @@
 import type { MessageContent, MessageType } from "@llamaindex/core/llms";
-import { type NodeWithScore } from "@llamaindex/core/schema";
+import { MetadataMode, type NodeWithScore } from "@llamaindex/core/schema";
 import type { BaseNodePostprocessor } from "../../postprocessors/index.js";
 import type { ContextSystemPrompt } from "../../Prompt.js";
 import { defaultContextSystemPrompt } from "../../Prompt.js";
@@ -16,12 +16,14 @@ export class DefaultContextGenerator
   contextSystemPrompt: ContextSystemPrompt;
   nodePostprocessors: BaseNodePostprocessor[];
   contextRole: MessageType;
+  metadataMode?: MetadataMode;
 
   constructor(init: {
     retriever: BaseRetriever;
     contextSystemPrompt?: ContextSystemPrompt;
     nodePostprocessors?: BaseNodePostprocessor[];
     contextRole?: MessageType;
+    metadataMode?: MetadataMode;
   }) {
     super();
 
@@ -30,6 +32,7 @@ export class DefaultContextGenerator
       init?.contextSystemPrompt ?? defaultContextSystemPrompt;
     this.nodePostprocessors = init.nodePostprocessors || [];
     this.contextRole = init.contextRole ?? "system";
+    this.metadataMode = init.metadataMode ?? MetadataMode.NONE;
   }
 
   protected _getPrompts(): { contextSystemPrompt: ContextSystemPrompt } {
@@ -75,6 +78,8 @@ export class DefaultContextGenerator
     const content = await createMessageContent(
       this.contextSystemPrompt,
       nodes.map((r) => r.node),
+      undefined,
+      this.metadataMode,
     );
 
     return {

packages/llamaindex/src/next.ts

@@ -17,6 +17,13 @@
  */
 export default function withLlamaIndex(config: any) {
   config.experimental = config.experimental ?? {};
+  // copy tiktoken WASM files to the NextJS build
+  config.experimental.outputFileTracingIncludes =
+    config.experimental.outputFileTracingIncludes ?? {};
+  config.experimental.outputFileTracingIncludes["/**/*"] = [
+    "./node_modules/tiktoken/*.wasm",
+  ];
+  // needed for transformers, see https://huggingface.co/docs/transformers.js/en/tutorials/next#step-2-install-and-configure-transformersjs
   config.experimental.serverComponentsExternalPackages =
     config.experimental.serverComponentsExternalPackages ?? [];
   config.experimental.serverComponentsExternalPackages.push(

packages/llamaindex/src/storage/vectorStore/PGVectorStore.ts

@@ -1,13 +1,19 @@
 import type pg from "pg";
 
 import {
+  FilterCondition,
+  FilterOperator,
   VectorStoreBase,
   type IEmbedModel,
+  type MetadataFilter,
+  type MetadataFilterValue,
   type VectorStoreNoEmbedModel,
   type VectorStoreQuery,
   type VectorStoreQueryResult,
 } from "./types.js";
 
+import { escapeLikeString } from "./utils.js";
+
 import type { BaseNode, Metadata } from "@llamaindex/core/schema";
 import { Document, MetadataMode } from "@llamaindex/core/schema";
 
@@ -246,6 +252,120 @@ export class PGVectorStore
     return Promise.resolve();
   }
 
+  private toPostgresCondition(condition: `${FilterCondition}`) {
+    if (condition === FilterCondition.AND) {
+      return "AND";
+    }
+    if (condition === FilterCondition.OR) {
+      return "OR";
+    }
+    // fallback to AND
+    else {
+      return "AND";
+    }
+  }
+
+  private toPostgresOperator(operator: `${FilterOperator}`) {
+    if (operator === FilterOperator.EQ) {
+      return "=";
+    }
+    if (operator === FilterOperator.GT) {
+      return ">";
+    }
+    if (operator === FilterOperator.LT) {
+      return "<";
+    }
+    if (operator === FilterOperator.NE) {
+      return "!=";
+    }
+    if (operator === FilterOperator.GTE) {
+      return ">=";
+    }
+    if (operator === FilterOperator.LTE) {
+      return "<=";
+    }
+    if (operator === FilterOperator.IN) {
+      return "= ANY";
+    }
+    if (operator === FilterOperator.NIN) {
+      return "!= ANY";
+    }
+    if (operator === FilterOperator.CONTAINS) {
+      return "@>";
+    }
+    if (operator === FilterOperator.ANY) {
+      return "?|";
+    }
+    if (operator === FilterOperator.ALL) {
+      return "?&";
+    }
+    // fallback to "="
+    return "=";
+  }
+
+  private buildFilterClause(
+    filter: MetadataFilter,
+    paramIndex: number,
+  ): {
+    clause: string;
+    param: string | string[] | number | number[] | undefined;
+  } {
+    if (
+      filter.operator === FilterOperator.IN ||
+      filter.operator === FilterOperator.NIN
+    ) {
+      return {
+        clause: `metadata->>'${filter.key}' ${this.toPostgresOperator(filter.operator)}($${paramIndex})`,
+        param: filter.value,
+      };
+    }
+
+    if (
+      filter.operator === FilterOperator.ALL ||
+      filter.operator === FilterOperator.ANY
+    ) {
+      return {
+        clause: `metadata->'${filter.key}' ${this.toPostgresOperator(filter.operator)} $${paramIndex}::text[]`,
+        param: filter.value,
+      };
+    }
+
+    if (filter.operator === FilterOperator.CONTAINS) {
+      return {
+        clause: `metadata->'${filter.key}' ${this.toPostgresOperator(filter.operator)} $${paramIndex}::jsonb`,
+        param: JSON.stringify([filter.value]),
+      };
+    }
+
+    if (filter.operator === FilterOperator.IS_EMPTY) {
+      return {
+        clause: `(NOT (metadata ? '${filter.key}') OR metadata->>'${filter.key}' IS NULL OR metadata->>'${filter.key}' = '' OR metadata->'${filter.key}' = '[]'::jsonb)`,
+        param: undefined,
+      };
+    }
+
+    if (filter.operator === FilterOperator.TEXT_MATCH) {
+      const escapedValue = escapeLikeString(filter.value as string);
+      return {
+        clause: `metadata->>'${filter.key}' LIKE $${paramIndex}`,
+        param: `%${escapedValue}%`,
+      };
+    }
+
+    // if value is number, coerce metadata value to float
+    if (typeof filter.value === "number") {
+      return {
+        clause: `(metadata->>'${filter.key}')::float ${this.toPostgresOperator(filter.operator)} $${paramIndex}`,
+        param: filter.value,
+      };
+    }
+
+    return {
+      clause: `metadata->>'${filter.key}' ${this.toPostgresOperator(filter.operator)} $${paramIndex}`,
+      param: filter.value,
+    };
+  }
+
   /**
    * Query the vector store for the closest matching data to the query embeddings
    * @param query The VectorStoreQuery to be used
@@ -265,19 +385,27 @@ export class PGVectorStore
     const max = query.similarityTopK ?? 2;
     const whereClauses = this.collection.length ? ["collection = $2"] : [];
 
-    const params: Array<string | number> = this.collection.length
+    const params: Array<MetadataFilterValue> = this.collection.length
       ? [embedding, this.collection]
       : [embedding];
 
+    const filterClauses: string[] = [];
     query.filters?.filters.forEach((filter, index) => {
       const paramIndex = params.length + 1;
-      whereClauses.push(`metadata->>'${filter.key}' = $${paramIndex}`);
-      // TODO: support filter with other operators
-      if (!Array.isArray(filter.value) && filter.value) {
-        params.push(filter.value);
+      const { clause, param } = this.buildFilterClause(filter, paramIndex);
+      filterClauses.push(clause);
+      if (param) {
+        params.push(param);
       }
     });
 
+    if (filterClauses.length > 0) {
+      const condition = this.toPostgresCondition(
+        query.filters?.condition ?? FilterCondition.AND,
+      );
+      whereClauses.push(`(${filterClauses.join(` ${condition} `)})`);
+    }
+
     const where =
       whereClauses.length > 0 ? `WHERE ${whereClauses.join(" AND ")}` : "";
 

packages/llamaindex/src/storage/vectorStore/utils.ts

@@ -104,3 +104,7 @@ export const parseNumberValue = (value?: MetadataFilterValue): number => {
   if (typeof value !== "number") throw new Error("Value must be a number");
   return value;
 };
+
+export const escapeLikeString = (value: string) => {
+  return value.replace(/[%_\\]/g, "\\$&");
+};

pnpm-lock.yaml

@@ -163,7 +163,7 @@ importers:
         version: link:../packages/llamaindex
       mongodb:
         specifier: ^6.7.0
-        version: 6.8.0(@aws-sdk/credential-providers@3.613.0)
+        version: 6.8.0(@aws-sdk/credential-providers@3.613.0(@aws-sdk/client-sso-oidc@3.613.0(@aws-sdk/client-sts@3.613.0)))
       pathe:
         specifier: ^1.1.2
         version: 1.1.2
@@ -382,8 +382,8 @@ importers:
         specifier: 5.3.1
         version: 5.3.1(typescript@5.5.3)
       natural:
-        specifier: ^7.1.0
-        version: 7.1.0(@aws-sdk/credential-providers@3.613.0)
+        specifier: ^8.0.1
+        version: 8.0.1(@aws-sdk/credential-providers@3.613.0)
 
   packages/core/tests:
     devDependencies:
@@ -568,7 +568,7 @@ importers:
         version: 2.0.0
       mongodb:
         specifier: ^6.7.0
-        version: 6.8.0(@aws-sdk/credential-providers@3.613.0)
+        version: 6.8.0(@aws-sdk/credential-providers@3.613.0(@aws-sdk/client-sso-oidc@3.613.0(@aws-sdk/client-sts@3.613.0)))
       notion-md-crawler:
         specifier: ^1.0.0
         version: 1.0.0(encoding@0.1.13)
@@ -8099,8 +8099,8 @@ packages:
   natural-compare@1.4.0:
     resolution: {integrity: sha512-OWND8ei3VtNC9h7V60qff3SVobHr996CTwgxubgyQYEpg290h9J0buyECNNJexkFm5sOajh5G116RYA1c8ZMSw==}
 
-  natural@7.1.0:
-    resolution: {integrity: sha512-GBhiRgF0VUX+zPWahBVir1ajARQDZF1Fe6UpQORNzyQT57JQ2KLKYvubecvjIYh/uDaociusmySeRh+WL5OdxQ==}
+  natural@8.0.1:
+    resolution: {integrity: sha512-VVw8O5KrfvwqAFeNZEgBbdgA+AQaBlHcXEootWU7TWDaFWFI0VLfzyKMsRjnfdS3cVCpWmI04xLJonCvEv11VQ==}
     engines: {node: '>=0.4.10'}
 
   negotiator@0.6.3:
@@ -12003,7 +12003,7 @@ snapshots:
       '@babel/core': 7.24.7
       '@babel/helper-compilation-targets': 7.24.7
       '@babel/helper-plugin-utils': 7.24.7
-      debug: 4.3.5
+      debug: 4.3.6
       lodash.debounce: 4.0.8
       resolve: 1.22.8
     transitivePeerDependencies:
@@ -15604,7 +15604,7 @@ snapshots:
     dependencies:
       '@typescript-eslint/types': 5.62.0
       '@typescript-eslint/visitor-keys': 5.62.0
-      debug: 4.3.5
+      debug: 4.3.6
       globby: 11.1.0
       is-glob: 4.0.3
       semver: 7.6.2
@@ -15942,7 +15942,7 @@ snapshots:
 
   agent-base@6.0.2:
     dependencies:
-      debug: 4.3.5
+      debug: 4.3.6
     transitivePeerDependencies:
       - supports-color
     optional: true
@@ -17742,6 +17742,16 @@ snapshots:
       - eslint-import-resolver-webpack
       - supports-color
 
+  eslint-module-utils@2.8.1(@typescript-eslint/parser@7.16.0(eslint@8.57.0)(typescript@5.5.3))(eslint-import-resolver-node@0.3.9)(eslint@8.57.0):
+    dependencies:
+      debug: 3.2.7
+    optionalDependencies:
+      '@typescript-eslint/parser': 7.16.0(eslint@8.57.0)(typescript@5.5.3)
+      eslint: 8.57.0
+      eslint-import-resolver-node: 0.3.9
+    transitivePeerDependencies:
+      - supports-color
+
   eslint-module-utils@2.8.1(@typescript-eslint/parser@7.2.0(eslint@8.57.0)(typescript@5.5.3))(eslint-import-resolver-node@0.3.9)(eslint-import-resolver-typescript@3.6.1(@typescript-eslint/parser@7.2.0(eslint@8.57.0)(typescript@5.5.3))(eslint-import-resolver-node@0.3.9)(eslint-plugin-import@2.29.1)(eslint@8.57.0))(eslint@8.57.0):
     dependencies:
       debug: 3.2.7
@@ -17763,7 +17773,7 @@ snapshots:
       doctrine: 2.1.0
       eslint: 8.57.0
       eslint-import-resolver-node: 0.3.9
-      eslint-module-utils: 2.8.1(@typescript-eslint/parser@7.2.0(eslint@8.57.0)(typescript@5.5.3))(eslint-import-resolver-node@0.3.9)(eslint-import-resolver-typescript@3.6.1(@typescript-eslint/parser@7.2.0(eslint@8.57.0)(typescript@5.5.3))(eslint-import-resolver-node@0.3.9)(eslint-plugin-import@2.29.1)(eslint@8.57.0))(eslint@8.57.0)
+      eslint-module-utils: 2.8.1(@typescript-eslint/parser@7.16.0(eslint@8.57.0)(typescript@5.5.3))(eslint-import-resolver-node@0.3.9)(eslint@8.57.0)
       hasown: 2.0.2
       is-core-module: 2.14.0
       is-glob: 4.0.3
@@ -20463,7 +20473,7 @@ snapshots:
     optionalDependencies:
       '@aws-sdk/credential-providers': 3.613.0(@aws-sdk/client-sso-oidc@3.613.0(@aws-sdk/client-sts@3.613.0))
 
-  mongodb@6.8.0(@aws-sdk/credential-providers@3.613.0):
+  mongodb@6.8.0(@aws-sdk/credential-providers@3.613.0(@aws-sdk/client-sso-oidc@3.613.0(@aws-sdk/client-sts@3.613.0))):
     dependencies:
       '@mongodb-js/saslprep': 1.1.7
       bson: 6.8.0
@@ -20494,7 +20504,7 @@ snapshots:
 
   mquery@5.0.0:
     dependencies:
-      debug: 4.3.5
+      debug: 4.3.6
     transitivePeerDependencies:
       - supports-color
 
@@ -20532,7 +20542,7 @@ snapshots:
 
   natural-compare@1.4.0: {}
 
-  natural@7.1.0(@aws-sdk/credential-providers@3.613.0):
+  natural@8.0.1(@aws-sdk/credential-providers@3.613.0):
     dependencies:
       afinn-165: 1.0.4
       afinn-165-financialmarketnews: 3.0.0
@@ -22645,7 +22655,7 @@ snapshots:
 
   spdy-transport@3.0.0:
     dependencies:
-      debug: 4.3.5
+      debug: 4.3.6
       detect-node: 2.1.0
       hpack.js: 2.1.6
       obuf: 1.1.2