Files

Andy Lee 8899734952 refactor: Unify examples interface with BaseRAGExample (#12 )

* refactor: Unify examples interface with BaseRAGExample

- Create BaseRAGExample base class for all RAG examples
- Refactor 4 examples to use unified interface:
  - document_rag.py (replaces main_cli_example.py)
  - email_rag.py (replaces mail_reader_leann.py)
  - browser_rag.py (replaces google_history_reader_leann.py)
  - wechat_rag.py (replaces wechat_history_reader_leann.py)
- Maintain 100% parameter compatibility with original files
- Add interactive mode support for all examples
- Unify parameter names (--max-items replaces --max-emails/--max-entries)
- Update README.md with new examples usage
- Add PARAMETER_CONSISTENCY.md documenting all parameter mappings
- Keep main_cli_example.py for backward compatibility with migration notice

All default values, LeannBuilder parameters, and chunking settings
remain identical to ensure full compatibility with existing indexes.

* fix: Update CI tests for new unified examples interface

- Rename test_main_cli.py to test_document_rag.py
- Update all references from main_cli_example.py to document_rag.py
- Update tests/README.md documentation

The tests now properly test the new unified interface while maintaining
the same test coverage and functionality.

* fix: Fix pre-commit issues and update tests

- Fix import sorting and unused imports
- Update type annotations to use built-in types (list, dict) instead of typing.List/Dict
- Fix trailing whitespace and end-of-file issues
- Fix Chinese fullwidth comma to regular comma
- Update test_main_cli.py to test_document_rag.py
- Add backward compatibility test for main_cli_example.py
- Pass all pre-commit hooks (ruff, ruff-format, etc.)

* refactor: Remove old example scripts and migration references

- Delete old example scripts (mail_reader_leann.py, google_history_reader_leann.py, etc.)
- Remove migration hints and backward compatibility
- Update tests to use new unified examples directly
- Clean up all references to old script names
- Users now only see the new unified interface

* fix: Restore embedding-mode parameter to all examples

- All examples now have --embedding-mode parameter (unified interface benefit)
- Default is 'sentence-transformers' (consistent with original behavior)
- Users can now use OpenAI or MLX embeddings with any data source
- Maintains functional equivalence with original scripts

* docs: Improve parameter categorization in README

- Clearly separate core (shared) vs specific parameters
- Move LLM and embedding examples to 'Example Commands' section
- Add descriptive comments for all specific parameters
- Keep only truly data-source-specific parameters in specific sections

* docs: Make example commands more representative

- Add default values to parameter descriptions
- Replace generic examples with real-world use cases
- Focus on data-source-specific features in examples
- Remove redundant demonstrations of common parameters

* docs: Reorganize parameter documentation structure

- Move common parameters to a dedicated section before all examples
- Rename sections to 'X-Specific Arguments' for clarity
- Remove duplicate common parameters from individual examples
- Better information architecture for users

* docs: polish applications

* docs: Add CLI installation instructions

- Add two installation options: venv and global uv tool
- Clearly explain when to use each option
- Make CLI more accessible for daily use

* docs: Clarify CLI global installation process

- Explain the transition from venv to global installation
- Add upgrade command for global installation
- Make it clear that global install allows usage without venv activation

* docs: Add collapsible section for CLI installation

- Wrap CLI installation instructions in details/summary tags
- Keep consistent with other collapsible sections in README
- Improve document readability and navigation

* style: format

* docs: Fix collapsible sections

- Make Common Parameters collapsible (as it's lengthy reference material)
- Keep CLI Installation visible (important for users to see immediately)
- Better information hierarchy

* docs: Add introduction for Common Parameters section

- Add 'Flexible Configuration' heading with descriptive sentence
- Create parallel structure with 'Generation Model Setup' section
- Improve document flow and readability

* docs: nit

* fix: Fix issues in unified examples

- Add smart path detection for data directory
- Fix add_texts -> add_text method call
- Handle both running from project root and examples directory

* fix: Fix async/await and add_text issues in unified examples

- Remove incorrect await from chat.ask() calls (not async)
- Fix add_texts -> add_text method calls
- Verify search-complexity correctly maps to efSearch parameter
- All examples now run successfully

* feat: Address review comments

- Add complexity parameter to LeannChat initialization (default: search_complexity)
- Fix chunk-size default in README documentation (256, not 2048)
- Add more index building parameters as CLI arguments:
  - --backend-name (hnsw/diskann)
  - --graph-degree (default: 32)
  - --build-complexity (default: 64)
  - --no-compact (disable compact storage)
  - --no-recompute (disable embedding recomputation)
- Update README to document all new parameters

* feat: Add chunk-size parameters and improve file type filtering

- Add --chunk-size and --chunk-overlap parameters to all RAG examples
- Preserve original default values for each data source:
  - Document: 256/128 (optimized for general documents)
  - Email: 256/25 (smaller overlap for email threads)
  - Browser: 256/128 (standard for web content)
  - WeChat: 192/64 (smaller chunks for chat messages)
- Make --file-types optional filter instead of restriction in document_rag
- Update README to clarify interactive mode and parameter usage
- Fix LLM default model documentation (gpt-4o, not gpt-4o-mini)

* feat: Update documentation based on review feedback

- Add MLX embedding example to README
- Clarify examples/data content description (two papers, Pride and Prejudice, Chinese README)
- Move chunk parameters to common parameters section
- Remove duplicate chunk parameters from document-specific section

* docs: Emphasize diverse data sources in examples/data description

* fix: update default embedding models for better performance

- Change WeChat, Browser, and Email RAG examples to use all-MiniLM-L6-v2
- Previous Qwen/Qwen3-Embedding-0.6B was too slow for these use cases
- all-MiniLM-L6-v2 is a fast 384-dim model, ideal for large-scale personal data

* add response highlight

* change rebuild logic

* fix some example

* feat: check if k is larger than #docs

* fix: WeChat history reader bugs and refactor wechat_rag to use unified architecture

* fix email wrong -1 to process all file

* refactor: reorgnize all examples/ and test/

* refactor: reorganize examples and add link checker

* fix: add init.py

* fix: handle certificate errors in link checker

* fix wechat

* merge

* docs: update README to use proper module imports for apps

- Change from 'python apps/xxx.py' to 'python -m apps.xxx'
- More professional and pythonic module calling
- Ensures proper module resolution and imports
- Better separation between apps/ (production tools) and examples/ (demos)

---------

Co-authored-by: yichuan520030910320 <yichuan_wang@berkeley.edu>

2025-08-03 23:06:24 -07:00

2.5 KiB

Raw Blame History

Normalized Embeddings Support in LEANN

LEANN now automatically detects normalized embedding models and sets the appropriate distance metric for optimal performance.

What are Normalized Embeddings?

Normalized embeddings are vectors with L2 norm = 1 (unit vectors). These embeddings are optimized for cosine similarity rather than Maximum Inner Product Search (MIPS).

Automatic Detection

When you create a LeannBuilder instance with a normalized embedding model, LEANN will:

Automatically set distance_metric="cosine" if not specified
Show a warning if you manually specify a different distance metric
Provide optimal search performance with the correct metric

Supported Normalized Embedding Models

OpenAI

All OpenAI text embedding models are normalized:

text-embedding-ada-002
text-embedding-3-small
text-embedding-3-large

Voyage AI

All Voyage AI embedding models are normalized:

voyage-2
voyage-3
voyage-large-2
voyage-multilingual-2
voyage-code-2

Cohere

All Cohere embedding models are normalized:

embed-english-v3.0
embed-multilingual-v3.0
embed-english-light-v3.0
embed-multilingual-light-v3.0

Example Usage

from leann.api import LeannBuilder

# Automatic detection - will use cosine distance
builder = LeannBuilder(
    backend_name="hnsw",
    embedding_model="text-embedding-3-small",
    embedding_mode="openai"
)
# Warning: Detected normalized embeddings model 'text-embedding-3-small'...
# Automatically setting distance_metric='cosine'

# Manual override (not recommended)
builder = LeannBuilder(
    backend_name="hnsw",
    embedding_model="text-embedding-3-small",
    embedding_mode="openai",
    distance_metric="mips"  # Will show warning
)
# Warning: Using 'mips' distance metric with normalized embeddings...

Non-Normalized Embeddings

Models like facebook/contriever and other sentence-transformers models that are not normalized will continue to use MIPS by default, which is optimal for them.

Why This Matters

Using the wrong distance metric with normalized embeddings can lead to:

Poor search quality due to HNSW's early termination with narrow score ranges
Incorrect ranking of search results
Suboptimal performance compared to using the correct metric

For more details on why this happens, see our analysis in the embedding detection code which automatically handles normalized embeddings and MIPS distance metric issues.

2.5 KiB Raw Blame History