|
Download docs/task.md from YGCXLab/ux-research-agent-slackbot: direct link, hf CLI and curl.
- Browser
- Download file 6.45 kB
-
https://huggingface.co/spaces/YGCXLab/ux-research-agent-slackbot/resolve/main/docs/task.md
- Command line
-
hf download hf://spaces/YGCXLab/ux-research-agent-slackbot/docs/task.md
-
curl -L -o task.md https://huggingface.co/spaces/YGCXLab/ux-research-agent-slackbot/resolve/main/docs/task.md
6.45 kB
| # Task Management | |
| - [/] Research Data Sources <!-- id: 0 --> | |
| - [ ] Analyze `research_report.json` structure <!-- id: 1 --> | |
| - [x] Analyze `baymard_unified_database_v2.json` structure <!-- id: 2 --> | |
| - [ ] Draft Product Requirements Document (PRD) <!-- id: 3 --> | |
| - [x] Define User Personas and Goals <!-- id: 4 --> | |
| - [x] detailed Feature Specifications (Search, RAG, Image Analysis) <!-- id: 5 --> | |
| - [x] Define Technical Architecture (High-level) <!-- id: 6 --> | |
| - [x] Define Metrics and Success Criteria <!-- id: 7 --> | |
| - [x] Research File Linking <!-- id: 9 --> | |
| - [x] Explore `research_pages` directory naming convention <!-- id: 10 --> | |
| - [x] Create script to match JSON entries with file paths <!-- id: 11 --> | |
| - [x] Update `research_report.json` with file paths <!-- id: 12 --> | |
| - [x] Update File Structure <!-- id: 13 --> | |
| - [x] Update script for new paths and relative linking <!-- id: 14 --> | |
| - [x] Run script to fix `research_report.json` <!-- id: 15 --> | |
| - [x] Verify Match Quality <!-- id: 16 --> | |
| - [x] Create script to check similarity between JSON title and file path <!-- id: 17 --> | |
| - [x] Report ambiguous matches to user <!-- id: 18 --> | |
| - [x] Handle Unmatched Items <!-- id: 19 --> | |
| - [x] Mark missing file paths as "ํ์ผ ์์" <!-- id: 20 --> | |
| - [/] Review PRD with User <!-- id: 8 --> | |
| - [x] Review PRD with User <!-- id: 8 --> | |
| - [x] Update PRD with finalized data structure (file_path) <!-- id: 21 --> | |
| - [x] Request final PRD approval <!-- id: 22 --> | |
| ## Chatbot PoC Development (Metadata Search) | |
| - [x] Setup Development Environment <!-- id: 23 --> | |
| - [x] Create virtual environment and install dependencies (langchain, google-genai) <!-- id: 24 --> | |
| - [ ] Verify Gemini API Key (`gemini-3-flash-preview`) <!-- id: 25 --> | |
| - [x] Data Loader Implementation <!-- id: 26 --> | |
| - [x] Implement `data_loader.py` for both JSON sources <!-- id: 27 --> | |
| - [x] Search Logic Implementation <!-- id: 30 --> | |
| - [x] Implement keyword extraction & source routing with LLM <!-- id: 31 --> | |
| - [x] Implement filtering logic for JSON data <!-- id: 32_1 --> | |
| - [x] Implement answer generation with Gemini 3 Flash <!-- id: 32 --> | |
| - [x] Interface Implementation <!-- id: 33 --> | |
| - [x] Build CLI for testing <!-- id: 34 --> | |
| - [x] Verify specific used cases (Review, Internal Only, etc.) <!-- id: 35 --> | |
| ## Web App Development (Streamlit) | |
| - [x] Setup Web Environment <!-- id: 36 --> | |
| - [x] Update `requirements.txt` with `streamlit` <!-- id: 37 --> | |
| - [x] Install new dependencies <!-- id: 38 --> | |
| - [x] Implement Web Interface <!-- id: 39 --> | |
| - [x] Create `app.py` using Streamlit chat elements <!-- id: 40 --> | |
| - [x] Integrate `SearchEngine` with Streamlit session state <!-- id: 41 --> | |
| - [x] Verification <!-- id: 42 --> | |
| - [x] Run Streamlit app and verify chat flow <!-- id: 43 --> | |
| ## Feature Enhancements | |
| - [x] Add Conversation Context <!-- id: 44 --> | |
| - [x] Update `search_engine.py` to handle chat history <!-- id: 45 --> | |
| - [x] Update `app.py` to pass session history <!-- id: 46 --> | |
| - [x] Verify context-aware follow-up questions <!-- id: 47 --> | |
| ## RAG Integration Phase | |
| - [x] Data Preparation: Assign Unique IDs <!-- id: 50 --> | |
| - [x] Create script to assign IDs to JSON and sync with MD files <!-- id: 51 --> | |
| - [x] Run ID assignment script <!-- id: 52 --> | |
| - [x] Vector DB Setup <!-- id: 53 --> | |
| - [x] Install search dependencies <!-- id: 54 --> | |
| - [x] Implement search indexing for separate collections (Internal/Baymard) <!-- id: 55 --> | |
| - [x] Hybrid Search Implementation <!-- id: 56 --> | |
| - [x] Update `search_engine.py` to combine Metadata + Vector Search <!-- id: 57 --> | |
| - [x] Verify RAG results <!-- id: 58 --> | |
| - [x] Enhance Baymard Indexing (PDF Extraction) <!-- id: 59 --> | |
| ## Multimodal Support | |
| - [x] Implement File Upload in Web App <!-- id: 60 --> | |
| - [x] Add `st.file_uploader` to `app.py` <!-- id: 61 --> | |
| - [x] Update `search_engine.py` to handle image input <!-- id: 62 --> | |
| - [x] Verification <!-- id: 63 --> | |
| - [x] Test image analysis flow <!-- id: 64 --> | |
| - [x] Deployment | |
| - [x] Prepare for Hugging Face Space <!-- id: 70 --> | |
| - [x] Update `.env` with HF Token <!-- id: 71 --> | |
| - [x] Copy Data to Project Directory (Containerization) <!-- id: 73 --> | |
| - [x] Update Path Logic in Code (Relative Paths) <!-- id: 74 --> | |
| - [x] Create `Dockerfile` <!-- id: 75 --> | |
| - [x] Create `deploy_to_hf.py` script <!-- id: 72 --> | |
| - [x] Review PRD with User <!-- id: 8 --> | |
| ## Slackbot Integration | |
| - [x] Slack App Setup <!-- id: 80 --> | |
| - [x] Create Setup Guide <!-- id: 81 --> | |
| - [x] Configure Scopes & Tokens <!-- id: 82 --> | |
| - [x] Implement Slackbot Logic <!-- id: 83 --> | |
| - [x] Add `slack_bolt` dependency <!-- id: 84 --> | |
| - [x] Create `slack_bot.py` <!-- id: 85 --> | |
| - [x] Handle File Uploads (Images/Videos) <!-- id: 86 --> | |
| - [x] Handle DMs and Thread Replies <!-- id: 87 --> | |
| - [x] Implement Thread Context Awareness <!-- id: 91 --> | |
| - [x] Update `slack_bot.py` to fetch thread history <!-- id: 92 --> | |
| - [x] Convert Slack history to SearchEngine format <!-- id: 93 --> | |
| - [x] Deployment Updates <!-- id: 88 --> | |
| - [x] Update Dockerfile for dual execution (or separate) <!-- id: 89 --> | |
| - [x] Separate Web App and Slackbot Deployments <!-- id: 90 --> | |
| - [x] Migrate Data to HF Dataset (Fix Storage Limit) <!-- id: 94 --> | |
| - [x] Upload `data` to HF Dataset <!-- id: 95 --> | |
| - [x] Update `Dockerfile` to download data on startup <!-- id: 96 --> | |
| - [x] Create `Dockerfile.web` and `deploy_web.py` | |
| - [x] Create `Dockerfile.slack` and `deploy_slack.py` | |
| - [x] Deploy to separate Spaces | |
| - [x] Fix Slack Formatting Issues (Markdown to mrkdwn) <!-- id: 98 --> | |
| - [x] Update search_engine for strict formatting instructions <!-- id: 99 --> | |
| - [x] Implement deterministic Regex converter <!-- id: 100 --> | |
| - [x] Redeploy Slackbot (Clean Install) <!-- id: 101 --> | |
| ## Search & Context Improvements | |
| - [x] Improve Search Quality <!-- id: 102 --> | |
| - [x] Add `thefuzz` for fuzzy matching logic <!-- id: 103 --> | |
| - [x] Refactor `filter_internal_data` to use fuzzy scoring <!-- id: 104 --> | |
| - [x] Enhance Context Awareness <!-- id: 105 --> | |
| - [x] Update `keyword_extraction_prompt` to inherit context from history <!-- id: 106 --> | |
| - [x] Verify multi-turn conversation flow <!-- id: 107 --> | |