Andy Lee 31fd3c816a 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

2025-08-02 19:04:59 -07:00

..

data

fix ruff errors and formatting

2025-07-27 02:22:54 -07:00

email_data

fix: resolve all ruff linting errors and add lint CI check

2025-07-26 22:38:13 -07:00

history_data

fix ruff errors and formatting

2025-07-27 02:22:54 -07:00

base_rag_example.py

feat: Address review comments

2025-07-29 16:59:24 -07:00

browser_rag.py

fix: update default embedding models for better performance

2025-08-02 19:04:59 -07:00

compare_faiss_vs_leann.py

fix: resolve all ruff linting errors and add lint CI check

2025-07-26 22:38:13 -07:00

document_rag.py

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

2025-07-29 18:31:56 -07:00

document_search.py

fix ruff errors and formatting

2025-07-27 02:22:54 -07:00

email_rag.py

fix: update default embedding models for better performance

2025-08-02 19:04:59 -07:00

faiss_only.py

fix: resolve all ruff linting errors and add lint CI check

2025-07-26 22:38:13 -07:00

mail_reader_llamaindex.py

fix ruff errors and formatting

2025-07-27 02:22:54 -07:00

multi_vector_aggregator.py

fix ruff errors and formatting

2025-07-27 02:22:54 -07:00

openai_hnsw_example.py

fix: resolve all ruff linting errors and add lint CI check

2025-07-26 22:38:13 -07:00

resue_index.py

fix: resolve all ruff linting errors and add lint CI check

2025-07-26 22:38:13 -07:00

run_evaluation.py

fix: resolve all ruff linting errors and add lint CI check

2025-07-26 22:38:13 -07:00

simple_demo.py

fix: resolve all ruff linting errors and add lint CI check

2025-07-26 22:38:13 -07:00

wechat_rag.py

fix: update default embedding models for better performance

2025-08-02 19:04:59 -07:00