Feat/rag knowledge base

[SHarg9876]

Description

Added documents as sources. Chunk and embed sources and embed user input for similarity search to retrieve related tags/buckets.

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Refactoring (code improvement without changing functionality)
• Documentation update
• Configuration/infrastructure change
• Performance improvement
• Test coverage improvement

What Changed?

• added data/raw with documents
• added chunking and embedding of documents
• added embedding of user input
• added similarity search to get most relevant chunks
• knowledge_chunk.py, chunk_repository.py, seed_knowledge.py (for testing), pdfconvert.py, ingest.py

Testing & Validation

passes current tests

How this was tested

Screenshots/Recordings

Unfinished Work & Known Issues

• [ x] None, this PR is complete and production-ready
• The following items are intentionally deferred:

  • ---

  • ---

  • ---

Notes & Nuances

• ---

• ---

Pre-Merge Checklist

Code Quality

• Code follows the project's style guidelines and conventions
• Self-review completed (I've reviewed my own code for obvious issues)
• No debugging code, console logs, or commented-out code left behind
• No merge conflicts with the base branch
• Meaningful commit messages that explain the "why"

Testing & CI

• All CI checks are passing
• All new and existing tests pass locally
• Test coverage hasn't decreased (or decrease is justified)
• Linting passes without errors

Documentation

• Code is self-documenting or includes helpful comments for complex logic
• API documentation updated (if backend endpoints changed)
• Type definitions are accurate and up-to-date

Reviewer Notes

• Areas needing extra attention: ...
• Questions for reviewers: ...