updated everything

README.md

@@ -8,6 +8,17 @@ app_file: app.py
 pinned: true
 license: mit
 short_description: AI knowledge hub for groups, powered by Nvidia
+tags:
+- hackathon:build-small
+- track:backyard-ai
+- badge:sharing-is-caring
+- badge:field-notes
+- badge:Best Use of Codex
+- badge:Off Grid
+- badge:Best Demo
+- badge:Bonus Quest Champion
+- sponsor:nvidia nemotron
+
 ---
 
 # BuildSmall KnowledgeHub
@@ -20,6 +31,11 @@ BuildSmall KnowledgeHub is a modular Gradio app for loading knowledge from:
 
 It extracts text, captures Medium image references/captions when available, chunks the content, embeds chunks locally with the configured NVIDIA Nemotron embedding model, uploads vectors into Qdrant, and generates grounded answers with NVIDIA's OpenAI-compatible chat API.
 
+## 🔗 Resources & Links
+
+- **Demo Video:** [Watch the Product Demo]([YOUR_DEMO_VIDEO_LINK_HERE](https://youtu.be/aDlKNW10pnw))
+- **Blog Post:** [Read the Full Write-up][(YOUR_BLOG_POST_LINK_HERE](https://huggingface.co/blog/pkheria/knowledgemesh))
+- 
 ## NVIDIA Usage
 
 This project explicitly uses NVIDIA in two places:
@@ -37,20 +53,6 @@ You must provide `NVIDIA_API_KEY` as a Hugging Face Space secret or in your loca
 
 ## Hugging Face Spaces Deployment
 
-Create a new Hugging Face Space with:
-
-- SDK: `Gradio`
-- App file: `app.py`
-- Hardware: `ZeroGPU` if available, otherwise CPU/GPU according to your quota
-- Python dependencies: installed from `requirements.txt`
-
-Push this repository to the Space repo:
-
-```bash
-git remote add space https://huggingface.co/spaces/<your-username>/<your-space-name>
-git push space main
-```
-
 For ZeroGPU Spaces, add these Space variables:
 
 ```bash
@@ -92,16 +94,6 @@ HF_TOKEN=<token-if-needed-for-gated-model-downloads>
 
 Use a hosted Qdrant instance for Hugging Face Spaces. `localhost:6333` only works for local development.
 
-## Medium Article Extraction
-
-Medium articles are fetched through Freedium:
-
-```text
-https://freedium-mirror.cfd/
-```
-
-Pass a Medium article URL into the app. The extractor builds a Freedium mirror URL, extracts the readable article text, collects image URLs and alt/caption text when available, then sends that combined content through the same chunking, embedding, and Qdrant upload pipeline.
-
 ## Qdrant Collection Name
 
 The Ingest and Retrieve tabs each have their own collection-name field. Set both to the same Qdrant collection when you want to search what you just ingested. The fields are intentionally not auto-synced because auto-sync can cause continuous refreshes in hosted Gradio Spaces.
@@ -132,16 +124,3 @@ python app.py
 Open the local Gradio URL printed in the terminal, usually `http://127.0.0.1:7860`.
 
 The app binds to `0.0.0.0:7860`, which is suitable for Hugging Face Spaces and container deployments.
-
-## Project Structure
-
-```text
-app/
-  core/        settings and shared models
-  extractors/  PDF, arXiv, and Medium extraction
-  services/    chunking, embeddings, Qdrant, retrieval, ingestion orchestration
-  ui/          Gradio Blocks UI
-  utils/       source detection helpers
-```
-
-Medium extraction uses `freedium-mirror.cfd`. arXiv ingestion downloads the paper PDF and parses it with `pypdf`.