ux-research-agent-slackbot / docs /walkthrough.md
debug-log
Claude Opus 4.6
feat: Insight Repository โ€” GitLab ์ดˆ๊ธฐํ™” + HF ์ž๋™ ๋ฐฐํฌ
501bc8c
|
Raw History Blame Contribute Delete
5.12 kB

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.json and baymard_unified_database_v2.json.
  • Agentic Retriever (RAG): LLM์ด ์ง์ ‘ Fuzzy ๊ฒ€์ƒ‰โ†’๋ฌธ์„œ ์ฝ๊ธฐโ†’ํŒ๋‹จ ๋ฃจํ”„๋ฅผ ์‹คํ–‰ํ•˜๋Š” ์—์ด์ „ํŠธ ๊ธฐ๋ฐ˜ ๊ฒ€์ƒ‰.
  • Source Routing: detect intent (e.g., "์‚ฌ๋‚ด ๋ฆฌ์„œ์น˜๋งŒ", "๋ฒ ์ด๋งˆ๋“œ๋งŒ") to filter data sources.
  • Context Awareness: Remembers previous conversation turns to handle follow-up questions (e.g., "๊ทธ ์ค‘์—์„œ ์‚ฌ๋‚ด ๋ฆฌ์„œ์น˜๋งŒ ๋ณด์—ฌ์ค˜").
  • 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

  1. Navigate to the project directory:
    cd /Users/johan/.gemini/antigravity/brain/e4e4053f-3b95-42ed-b913-7720b36a4303
    
  2. Install dependencies (if not already done):
    pip install -r requirements.txt
    
  3. Set up API Key:
    • Ensure .env file exists and contains GOOGLE_API_KEY=your_key_here.

Deployment

The project is deployed on Hugging Face Spaces as two separate services:

1. Web Application (Streamlit)

2. Slackbot

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.py improvements 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 data folder on startup, ensuring compatibility and data freshness.
  • Multimodal & Interactive:
    • Supports image/video inputs for UX analysis.
    • Added emoji reactions (๐Ÿค”, โœ…, โš ๏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 ๊ด€๋ จ ์ž๋ฃŒ ์ฐพ์•„์ค˜"

Bot:

  • [Internal Research] [IDI] ๋ฆฌ๋ทฐ ํƒ์ƒ‰ ๊ฒฝํ—˜ ๊ฐœ์„  ์„ ํ–‰...
  • [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 ๊ด€๋ จ ์‚ฌ๋‚ด๋ฆฌ์„œ์น˜ ๋‚ด์šฉ ์ฐพ์•„์ค˜"

Bot:

  • [Internal Research] [IDI] ๋ฆฌ๋ทฐ ํƒ์ƒ‰ ๊ฒฝํ—˜ ๊ฐœ์„  ์„ ํ–‰...
  • [Internal Research] ์ถ”์ฒœ ์ด๋‹ˆ์…”ํ‹ฐ๋ธŒ...

(Only internal research items are returned)

Scenario 3: Context-Aware Follow-up

Refine your search using previous context.

User: "๋ฆฌ๋ทฐ ๊ด€๋ จ ์ž๋ฃŒ ์ฐพ์•„์ค˜" Bot: (Returns mixed results) User: "๊ทธ ์ค‘์—์„œ ์‚ฌ๋‚ด ๋ฆฌ์„œ์น˜๋งŒ ๋ณด์—ฌ์ค˜" 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 œ์ ์ด ๋ญ์•ผ?" Bot: "ํ•ด๋‹น ํ™”๋ฉด์—์„œ ๋‹ค์Œ๊ณผ ๊ฐ™์€ UX ๋ฌธ์ œ์ ์ด ๋ฐœ๊ฒฌ๋ฉ๋‹ˆ๋‹ค:

  1. '๊ฒฐ์ œํ•˜๊ธฐ' ๋ฒ„ํŠผ์ด ์Šคํฌ๋กค ์•„๋ž˜์— ์žˆ์–ด ๋ฐœ๊ฒฌํ•˜๊ธฐ ์–ด๋ ต์Šต๋‹ˆ๋‹ค (Baymard Guideline #124 ์ฐธ์กฐ).
  2. ..."

Scenario 5: Visual Reference Search (Multimodal)

Find guidelines relevant to a specific UI pattern.

Input: (Uploads screenshot of a date picker) User: "์ด๋Ÿฐ UI์™€ ๊ด€๋ จ๋œ ๊ฐ€์ด๋“œ๋ผ์ธ ์ฐพ์•„์ค˜" Bot: "์ด๋ฏธ์ง€์—์„œ 'Date Picker', 'Calendar' ์š”์†Œ๊ฐ€ ์‹๋ณ„๋˜์—ˆ์Šต๋‹ˆ๋‹ค. ๊ด€๋ จ ๊ฐ€์ด๋“œ๋ผ์ธ์€ ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค:

  • [Baymard] Date Picker Design Best Practices..."
  • search_engine.py: Main entry point and logic (CLI, LLM Chain).
  • requirements.txt: Python package dependencies.