# IlyaRice/RAG-Challenge-2

Implementation of my RAG system that won all categories in Enterprise RAG Challenge 2

Repository: https://github.com/IlyaRice/RAG-Challenge-2
Canonical: https://ross.abutalabs.com/products/rag-challenge-2
Language: Python
License: MIT
License Family: permissive
Last push: 2025-05-12T13:32:42+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 21, release rhythm 35, longevity 38
- inputs: {"age_days": 532, "days_push": 478, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2431, forks 493 (observed 2026-08-28T04:06:51.130843+00:00)

## What it is
A Python implementation of the winning RAG system from the Enterprise RAG Challenge 2 competition, answering questions about company annual reports. It combines PDF parsing with Docling, parent document vector retrieval, LLM reranking, chain-of-thought structured prompting, and query routing.

## Use cases
- build a rag pipeline over pdf documents
- answer questions about company annual reports
- learn rag techniques like parent document retrieval and llm reranking
- parse pdfs with tables into structured data
- study a winning rag competition solution
- experiment with query routing for multi-document comparison

## When to choose
- you want to study or replicate state-of-the-art RAG techniques
- you need a reference implementation for question answering over PDF reports
- you're exploring vector search, reranking, and structured LLM prompting patterns

## When to avoid
- you need production-ready, tested code with error handling
- you want a maintained library or framework rather than competition code
- you can't provide your own OpenAI/Gemini API keys or GPU for parsing

## Facets
- artifact type: application
- maturity: experimental
- function: rag, llm-inference, pdf, search-engine, prompt-engineering
- domain: large-language-models, pdf, machine-learning
- platform: python, cli
- tags: rag-challenge, competition-code, pdf-parsing, docling, vector-search, reranking, annual-reports, question-answering, retrieval-augmented-generation, natural-language-processing, gpu

## Member repositories
- IlyaRice/RAG-Challenge-2 (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:51.130843+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:31:24.832550+00:00, confidence not recorded.
  - readme: https://github.com/IlyaRice/RAG-Challenge-2 (fetched 2026-08-28T04:06:51.130843+00:00, sha 4bc7e52f7f2b)
- Data as of 2026-08-30T08:39:29.467469+00:00.