Download docs/walkthrough.md from YGCXLab/ux-research-agent-slackbot: direct link, hf CLI and curl.
- Browser
- Download file 5.12 kB
-
https://huggingface.co/spaces/YGCXLab/ux-research-agent-slackbot/resolve/main/docs/walkthrough.md
- Command line
-
hf download hf://spaces/YGCXLab/ux-research-agent-slackbot/docs/walkthrough.md
-
curl -L -o walkthrough.md https://huggingface.co/spaces/YGCXLab/ux-research-agent-slackbot/resolve/main/docs/walkthrough.md
UX/Research Chatbot PoC Walkthrough
This document outlines how to set up and run the Proof of Concept (PoC) for the UX/Research Chatbot. This agent searches internal research reports and Baymard guidelines using metadata filtering and LLM generation.
Features
- Multimodal (Image/Video) Analysis: Analyze UI designs for usability issues or search for similar references using uploaded files.
- Unified Search: Searches both
research_report.jsonandbaymard_unified_database_v2.json. - Agentic Retriever (RAG): LLM์ด ์ง์ Fuzzy ๊ฒ์โ๋ฌธ์ ์ฝ๊ธฐโํ๋จ ๋ฃจํ๋ฅผ ์คํํ๋ ์์ด์ ํธ ๊ธฐ๋ฐ ๊ฒ์.
- Source Routing: detect intent (e.g., "์ฌ๋ด ๋ฆฌ์์น๋ง", "๋ฒ ์ด๋ง๋๋ง") to filter data sources.
- Context Awareness: Remembers previous conversation turns to handle follow-up questions (e.g., "๊ทธ ์ค์์ ์ฌ๋ด ๋ฆฌ์์น๋ง ๋ณด์ฌ์ค").
- Smart Filtering: Extracts keywords from natural language queries to filter documents before generation.
- LLM: Powered by Google Gemini 3 Flash (
gemini-3-flash-preview).
Setup
1. Prerequisites
- Python 3.8+
- Google API Key
2. Installation
- Navigate to the project directory:
cd /Users/johan/.gemini/antigravity/brain/e4e4053f-3b95-42ed-b913-7720b36a4303 - Install dependencies (if not already done):
pip install -r requirements.txt - Set up API Key:
- Ensure
.envfile exists and containsGOOGLE_API_KEY=your_key_here.
- Ensure
Deployment
The project is deployed on Hugging Face Spaces as two separate services:
1. Web Application (Streamlit)
- URL: https://huggingface.co/spaces/YGCXLab/ux-research-agent-poc
- Purpose: User-friendly web interface for research and file analysis.
- Deployment:
python deploy_web.py
2. Slackbot
- Space: https://huggingface.co/spaces/YGCXLab/ux-research-agent-slackbot (No UI)
- Purpose: Dedicated bot for Slack integration (Socket Mode).
- Deployment:
python deploy_slack.py
Slackbot Integration & Deployment (2026-01-14)
- Separate Deployment: Deployed Slackbot to a dedicated Hugging Face Space (
ux-research-agent-slackbot) to ensure stability and independent scaling. - Full RAG Support:
- Implemented
indexer.pyimprovements to extract text from original PDF files (Baymard) and Markdown files (Internal Research). - Configured server-side indexing: The bot automatically builds a fresh Vector DB from the uploaded
datafolder on startup, ensuring compatibility and data freshness.
- Implemented
- Multimodal & Interactive:
- Supports image/video inputs for UX analysis.
- Added emoji reactions (๐ค, โ , โ ๏ธ) for better user feedback during processing.
- Enabled "Socket Mode" for reliable communication without public URL exposure.
Web Interface (Streamlit) Local Run
To run the web app locally:
venv/bin/streamlit run app.py
This will open a browser window at http://localhost:8501.
- Enter your question in the chat input.
- Clear chat history using the button in the sidebar.
Usage Examples
Scenario 1: General Research
Ask for materials across all sources.
User: "๋ฆฌ๋ทฐ ๊ด๋ จ ์๋ฃ ์ฐพ์์ค"
Bot:
- [Internal Research] [IDI] ๋ฆฌ๋ทฐ ํ์ ๊ฒฝํ ๊ฐ์ ์ ํ...
- [Baymard Guideline] Allow Users to Sort Reviews #837...
(Summary and links are provided for both sources)
Scenario 2: Source-Specific Search
Ask specifically for internal or external data.
User: "๋ฆฌ๋ทฐ ๊ด๋ จ ์ฌ๋ด๋ฆฌ์์น ๋ด์ฉ ์ฐพ์์ค"
Bot:
- [Internal Research] [IDI] ๋ฆฌ๋ทฐ ํ์ ๊ฒฝํ ๊ฐ์ ์ ํ...
- [Internal Research] ์ถ์ฒ ์ด๋์ ํฐ๋ธ...
(Only internal research items are returned)
Scenario 3: Context-Aware Follow-up
Refine your search using previous context.
User: "๋ฆฌ๋ทฐ ๊ด๋ จ ์๋ฃ ์ฐพ์์ค" Bot: (Returns mixed results) User: "๊ทธ ์ค์์ ์ฌ๋ด ๋ฆฌ์์น๋ง ๋ณด์ฌ์ค" Bot: (Filters previous topic for internal research only)
Scenario 4: Design Critique (Multimodal)
Get feedback on a UI design.
Input: (Uploads screenshot of a checkout page) User: "์ด ํ๋ฉด์ ๋ฌธ์ ์ ์ด ๋ญ์ผ?" Bot: "ํด๋น ํ๋ฉด์์ ๋ค์๊ณผ ๊ฐ์ UX ๋ฌธ์ ์ ์ด ๋ฐ๊ฒฌ๋ฉ๋๋ค:
- '๊ฒฐ์ ํ๊ธฐ' ๋ฒํผ์ด ์คํฌ๋กค ์๋์ ์์ด ๋ฐ๊ฒฌํ๊ธฐ ์ด๋ ต์ต๋๋ค (Baymard Guideline #124 ์ฐธ์กฐ).
- ..."
Scenario 5: Visual Reference Search (Multimodal)
Find guidelines relevant to a specific UI pattern.
Input: (Uploads screenshot of a date picker) User: "์ด๋ฐ UI์ ๊ด๋ จ๋ ๊ฐ์ด๋๋ผ์ธ ์ฐพ์์ค" Bot: "์ด๋ฏธ์ง์์ 'Date Picker', 'Calendar' ์์๊ฐ ์๋ณ๋์์ต๋๋ค. ๊ด๋ จ ๊ฐ์ด๋๋ผ์ธ์ ๋ค์๊ณผ ๊ฐ์ต๋๋ค:
- [Baymard] Date Picker Design Best Practices..."
search_engine.py: Main entry point and logic (CLI, LLM Chain).requirements.txt: Python package dependencies.