fix: word_count, paths, and __init__.py for importability#35
Open
ljluestc wants to merge 127 commits intowdndev:mainfrom
Open
fix: word_count, paths, and __init__.py for importability#35ljluestc wants to merge 127 commits intowdndev:mainfrom
ljluestc wants to merge 127 commits intowdndev:mainfrom
Conversation
Update llama系列模型.md
fix the mistake of latex grammer
- Add RAG dataset schema documentation (data/RAG_SCHEMA.md) - Convert 82 markdown documents to RAG-ready JSONL format - Generate 10 Q&A pairs from interview content - Implement complete RAG engine with: * Multilingual embedding generation (sentence-transformers) * Vector similarity search (FAISS + numpy fallback) * Semantic reranking for improved relevance * Answer generation with source attribution - Add conversion script (scripts/convert_md_to_rag.py) - Add comprehensive documentation (data/README.md) - Add requirements.txt for dependencies Dataset Statistics: - 82 documents across 11 categories - 10 Q&A pairs extracted - Full metadata with keywords, difficulty, URLs Usage: python scripts/convert_md_to_rag.py # Convert markdown python rag_system/rag_engine.py # Run RAG demo Co-Authored-By: Oz <oz-agent@warp.dev>
Co-Authored-By: Oz <oz-agent@warp.dev>
- Add scripts/ingest_arxiv_papers.py for ingesting arXiv papers - Update all_documents.jsonl and all_qa_pairs.jsonl with new content Made-with: Cursor
Sources: - devops_rag_answered_full_405.json (405 zh-CN, 24 categories) - devops_quiz_10_en.json (10 en, merged into zh records) - jenkins_beginner_24_33_en.json (10 en) - jenkins_advanced_34_40_en.json (7 en) RAG totals: 517 documents, 451 QA pairs Co-Authored-By: Oz <oz-agent@warp.dev>
Made-with: Cursor
…init__.py - convert_md_to_rag.py: word_count uses len(content.split()) instead of len(content) - ingest_devops_interview.py: replace hardcoded /home path with relative path + env var - Add __init__.py for rag_system/ and scripts/ to support module imports Co-Authored-By: Oz <oz-agent@warp.dev>
Made-with: Cursor
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Bug fixes for RAG ingestion and path handling.
Changes
scripts/convert_md_to_rag.py: Fix word_count to uselen(content.split())(words, not chars)scripts/ingest_devops_interview.py: Replace hardcoded path withPath(__file__).resolve().parentand_PROJECT_ROOTfallbackrag_system/__init__.pyandscripts/__init__.pyfor importabilityMade with Cursor