Spaces:
Sleeping
Sleeping
|
Download README.md from annasbeef/RFR-Knowledge-Platform: direct link, hf CLI and curl.
- Browser
- Download file 1.94 kB
-
https://huggingface.co/spaces/annasbeef/RFR-Knowledge-Platform/resolve/main/README.md
- Command line
-
hf download hf://spaces/annasbeef/RFR-Knowledge-Platform/README.md
-
curl -L -o README.md https://huggingface.co/spaces/annasbeef/RFR-Knowledge-Platform/resolve/main/README.md
1.94 kB
A newer version of the Streamlit SDK is available: 1.67.0
metadata
title: RFR Knowledge Platform
emoji: π
colorFrom: blue
colorTo: green
sdk: streamlit
app_file: app/app.py
pinned: false
RFR Co-op: LLM-Assisted Managed Retreat RAG Pipeline
A RAG (Retrieval-Augmented Generation) pipeline for extracting and synthesizing insights from managed retreat case study literature, built for the Retreat From Risk (RFR) research initiative.
Setup
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
Usage
# 1. Set API keys
export ANTHROPIC_API_KEY=your_key_here
export OPENAI_API_KEY=your_key_here
# 2. Convert canonical Ver2 memos to JSON chunks, then build embeddings
python ingest/ingest_pipeline_outputs.py
python ingest/create_summary_chunks.py
python ingest/embed_and_index.py
# 3. Run CLI pipeline
python rag/pipeline.py
# 4. Launch Streamlit web app
streamlit run app/app.py
Ingesting documents
# Convert canonical case-study memos into section chunks
python ingest/ingest_pipeline_outputs.py
# Refresh overview-summary chunks for broad comparison queries
python ingest/create_summary_chunks.py
# Build the precomputed embedding store used by rag/retriever.py
python ingest/embed_and_index.py
Project structure
rfr-rag/
βββ data/raw/ # Original PDFs and spreadsheets (not committed)
βββ data/extracted/ # Ver2-derived JSON chunks + embedding store
βββ ingest/ # Ver2 ingestion, summary chunks, embedding script
βββ case_study_pipeline/# Source extraction/audit workflow
βββ rag/ # Retriever, prompt builder, pipeline
βββ persona/ # Decision-maker persona config
βββ questionnaire/ # Guided questionnaire structure
βββ app/ # Streamlit interface
βββ docs/ # Extraction schema, memos
βββ tests/
See CLAUDE.md for full project context.