Rag Documentation Assistant

B 81 completed
Other
unknown / python · tiny
43
Files
3,286
LOC
2
Frameworks
7
Languages

Pipeline State

completed
Run ID
#393156
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
35.14
Framework unique
Isolation
Last stage change
2026-04-16 18:15:42
Deduplication group #47716
Member of a group with 1 similar repo(s) — canonical #99869 view group →
Top concepts (2)
Project DescriptionWeb Backend
Repobility — the code-quality scanner for AI-generated software · https://repobility.com

AI Prompt

Create a production-ready Retrieval-Augmented Generation (RAG) system using Python. I need it to answer questions based on a document knowledge base. The system should handle document ingestion, which involves uploading files to S3, triggering a process via SQS, and using a Lambda function to download, chunk, and embed the text. For querying, it should use an API Gateway endpoint that calls a Lambda function to embed the question, search vectors in OpenSearch, and finally call the Claude API to generate an answer, citing sources. The entire system should be designed for deployment on AWS serverless architecture.
python rag aws fastapi serverless llm claude aws-s3 aws-sqs openai retrieval-augmented-generation
Generated by gemma4:latest

Catalog Information

A production-ready Retrieval-Augmented Generation (RAG) system that answers questions based on your document knowledge base. Deployed on AWS with serverless architecture.

Description

A production-ready Retrieval-Augmented Generation (RAG) system that answers questions based on your document knowledge base. Deployed on AWS with serverless architecture.

Novelty

3/10

Tags

python rag aws fastapi serverless llm claude aws-s3 aws-sqs openai retrieval-augmented-generation

Technologies

anthropic fastapi gradio pydantic

Claude Models

claude-opus-4-6

Quality Score

B
80.9/100
Structure
89
Code Quality
85
Documentation
62
Testing
85
Practices
66
Security
100
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Good test coverage (73% test-to-source ratio)
  • Code linting configured (ruff (possible))
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected
  • Properly licensed project

Security & Health

4.1h
Tech Debt (C)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (3)
Methodology: Repobility · https://repobility.com/research/state-of-ai-code-2026/
MIT
License
5.6%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
67.2%
markdown
10.4%
yaml
8.6%
json
7.6%
text
5.3%
shell
0.6%
toml
0.4%

Frameworks

FastAPI pytest

Concepts (2)

Repobility (https://repobility.com) — every score reproducible
CategoryNameDescriptionConfidence
Source: Repobility analyzer · https://repobility.com
auto_descriptionProject DescriptionA production-ready Retrieval-Augmented Generation (RAG) system that answers questions based on your document knowledge base. Deployed on AWS with serverless architecture.80%
auto_categoryWeb Backendweb-backend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/117498.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV