34 lines
1.3 KiB
Text
34 lines
1.3 KiB
Text
# Studio RAG dependencies.
|
|
# Installed by studio/install_python_stack.py in the normal (with-torch)
|
|
# path. Skipped in NO_TORCH (Intel Mac GGUF-only) mode because RAG
|
|
# embedding relies on sentence-transformers, which requires torch.
|
|
|
|
# Vector store + lexical index.
|
|
#
|
|
# sqlite-vec is an Apache-2.0 SQLite extension (asg017/sqlite-vec) that
|
|
# adds vector functions (vec_distance_cosine, serialize_float32, vec0
|
|
# virtual tables). The studio loads it into a dedicated rag.db file and
|
|
# stores vectors as BLOB columns alongside the RAG metadata — no separate
|
|
# vector server, no second client library. The lexical index lives in the
|
|
# same rag.db as a SQLite FTS5 virtual table (built-in, no extra dependency).
|
|
sqlite-vec>=0.1.5
|
|
|
|
# Image preprocessing helpers required by Qwen3-VL-Embedding-2B (the
|
|
# multimodal embedder). Not used in text-only mode.
|
|
qwen-vl-utils>=0.0.14
|
|
|
|
# Layout-aware Markdown extraction (Phase 3A) so the chunker can split
|
|
# on real headings instead of running paragraphs together. pymupdf4llm
|
|
# preserves headings + pipe-tables; mammoth handles DOCX Heading styles;
|
|
# markdownify converts HTML <h*>/<table>/<ul> faithfully.
|
|
pymupdf>=1.24
|
|
pymupdf4llm>=0.0.17
|
|
mammoth>=1.7
|
|
markdownify>=0.13
|
|
|
|
# pypdf is kept as a fallback for malformed PDFs that defeat pymupdf.
|
|
pypdf>=4.0
|
|
python-docx>=1.1
|
|
beautifulsoup4>=4.12
|
|
lxml>=5.0
|
|
chardet>=5.2
|