@hazeljs/rag 0.3.1 → 0.4.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +13 -1
  2. package/package.json +4 -4
package/README.md CHANGED
@@ -2,12 +2,24 @@
2
2
 
3
3
  **Your docs. Your data. AI that actually knows them.**
4
4
 
5
- Load documents from any source, build a knowledge graph, embed into vector stores, and retrieve answers with semantic, hybrid, or graph-based search. Full RAG + GraphRAG pipeline — no PhD required.
5
+ Part of the HazelJS AI-Native Backend Framework. Load documents from any source, build a knowledge graph, embed into vector stores, and retrieve answers with semantic, hybrid, or graph-based search. Full RAG + GraphRAG pipeline — no PhD required.
6
+
7
+ **🚀 Trusted by 200K+ monthly downloads • 37+ GitHub stars • 15+ daily active developers**
6
8
 
7
9
  [![npm version](https://img.shields.io/npm/v/@hazeljs/rag.svg)](https://www.npmjs.com/package/@hazeljs/rag)
8
10
  [![npm downloads](https://img.shields.io/npm/dm/@hazeljs/rag)](https://www.npmjs.com/package/@hazeljs/rag)
9
11
  [![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://www.apache.org/licenses/LICENSE-2.0)
10
12
 
13
+ ## Why @hazeljs/rag?
14
+
15
+ Built for **AI-native applications** - not just another RAG library. When you combine @hazeljs/rag with @hazeljs/core, @hazeljs/ai, and @hazeljs/agent, you get a complete stack for intelligent backends.
16
+
17
+ **Perfect for:**
18
+ - AI startups building knowledge-based applications
19
+ - Teams implementing document Q&A systems
20
+ - Developers who want semantic search without complexity
21
+ - Projects needing GraphRAG and entity extraction
22
+
11
23
  ## Features
12
24
 
13
25
  - 📂 **11 Document Loaders** — TXT, Markdown, JSON, CSV, HTML, PDF, DOCX, web scraping, YouTube transcripts, GitHub repos, and inline text. All return the same `Document[]` interface.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@hazeljs/rag",
3
- "version": "0.3.1",
3
+ "version": "0.4.1",
4
4
  "description": "Retrieval-Augmented Generation (RAG) and vector search for HazelJS framework",
5
5
  "main": "dist/index.js",
6
6
  "types": "dist/index.d.ts",
@@ -25,7 +25,7 @@
25
25
  "clean": "rm -rf dist"
26
26
  },
27
27
  "dependencies": {
28
- "@hazeljs/prompts": "^0.3.1",
28
+ "@hazeljs/prompts": "^0.4.1",
29
29
  "reflect-metadata": "^0.2.1"
30
30
  },
31
31
  "peerDependencies": {
@@ -121,7 +121,7 @@
121
121
  }
122
122
  },
123
123
  "devDependencies": {
124
- "@hazeljs/memory": "^0.3.1",
124
+ "@hazeljs/memory": "^0.4.1",
125
125
  "@types/node": "^20.17.50",
126
126
  "@typescript-eslint/eslint-plugin": "^8.18.2",
127
127
  "@typescript-eslint/parser": "^8.18.2",
@@ -159,5 +159,5 @@
159
159
  "url": "https://github.com/hazeljs/hazel-js/issues"
160
160
  },
161
161
  "homepage": "https://hazeljs.ai",
162
- "gitHead": "db6df492988e5d7b03253a98977c71c7a4540e1c"
162
+ "gitHead": "151d5678aa2aeddd75fb75b1b5c55fabe8cb8050"
163
163
  }