Merge pull request #40 from Shishir435/feature/enhanced-knowledge-system

Feature/enhanced knowledge system

Author: Shishir435

README.md

@@ -71,10 +71,13 @@
 - 🔧 **Configurable** – Chunk size, overlap, similarity threshold, search limits
 - 📁 **Context-Aware** – Search across all chats or within current session
 
-### 📎 File Upload & Processing (Beta v0.3.0)
+### 📎 File Upload & Processing (Beta v0.3.0+)
 - 📄 **Text Files** – Support for .txt, .md and text based files
-- 📕 **PDF Support** – Full text extraction from PDF documents
+- 📁 **PDF Support** – Extract and process text from PDF documents
 - 📘 **DOCX Support** – Extract text from Word documents
+- 📊 **CSV Support** – Parse CSV, TSV, PSV with custom delimiters and column extraction (Beta v0.5.0)
+- 🌐 **HTML Support** – Convert HTML to Markdown for clean text extraction (Beta v0.5.0)
+with 50+ language support (Beta v0.5.0)
 - ⚙️ **Auto-Embedding** – Automatic embedding generation for uploaded files
 - 📊 **Progress Tracking** – Real-time progress indicators during processing
 - 🎛️ **Configurable Limits** – User-defined max file size in settings
@@ -457,11 +460,18 @@ Here’s what’s coming up next in **Ollama Client**—grouped by priority:
   - [x] Configurable max file size
   - [x] Auto-embed toggle
   - [x] Embedding batch size configuration
-- [ ] Image OCR via **Tesseract.js** (Deferred - CSP issues in Manifest V3)
+- [x] **CSV Support** (Beta v0.5.0 - Completed):
+  - [x] CSV parsing with d3-dsv
+  - [x] Custom delimiter support (comma, tab, pipe, semicolon)
+  - [x] Column extraction
+  - [x] TSV and PSV file support
+- [x] **HTML Support** (Beta v0.5.0 - Completed):
+  - [x] HTML to Markdown conversion via Turndown
+  - [x] Structure and link preservation
 
 ### UX & Metrics Enhancements
 
-- [ ] Track **Per-Session Token Usage** and display in chat metadata (duration, token count)
+- [x] Track **Per-Session Token Usage** and display in chat metadata (duration, token count)
 - [x] Enable **Semantic Chat Search / Filter** once embeddings are in place
 - [x] Add **Export/Import UI Buttons** in chat selector ui
 

dummy.txt

@@ -1,7 +1,7 @@
 {
   "name": "ollama-client",
   "displayName": "Ollama Client - Chat with Local LLM Models",
-  "version": "0.4.1",
+  "version": "0.5.3",
   "description": "Privacy-first Ollama Chrome extension to chat with local AI models like LLaMA, Mistral, Gemma — fully offline.",
   "author": "Shishir Chaurasiya",
   "keywords": [
@@ -91,10 +91,12 @@
     "@radix-ui/react-slot": "1.1.2",
     "@radix-ui/react-switch": "^1.2.5",
     "@radix-ui/react-tabs": "^1.1.12",
+    "@radix-ui/react-toggle": "^1.1.10",
     "@radix-ui/react-tooltip": "^1.2.7",
     "class-variance-authority": "0.7.1",
     "clsx": "2.1.1",
     "cmdk": "^1.1.1",
+    "d3-dsv": "^3.0.1",
     "defuddle": "^0.6.6",
     "dexie": "^4.0.11",
     "dompurify": "^3.2.6",
@@ -125,6 +127,7 @@
     "tailwind-merge": "3.0.1",
     "tailwind-scrollbar": "^4.0.2",
     "tailwindcss-animate": "1.0.7",
+    "turndown": "^7.2.2",
     "vectra": "^0.11.1",
     "webextension-polyfill": "^0.12.0",
     "zustand": "^5.0.8"
@@ -135,6 +138,7 @@
     "@testing-library/jest-dom": "^6.9.1",
     "@testing-library/react": "^16.3.0",
     "@types/chrome": "0.0.258",
+    "@types/d3-dsv": "^3.0.7",
     "@types/html2pdf.js": "^0.10.0",
     "@types/markdown-it": "^14.1.2",
     "@types/markdown-it-container": "^2.0.10",
@@ -143,6 +147,7 @@
     "@types/node": "20.11.5",
     "@types/react": "18.2.48",
     "@types/react-dom": "18.2.18",
+    "@types/turndown": "^5.0.6",
     "@types/webextension-polyfill": "^0.12.4",
     "@vitejs/plugin-react": "^5.1.1",
     "@vitest/coverage-v8": "4.0.14",