d8006ff5cb
* feat: content-type aware chunking and unified embedding - Add chunking.py with HTML, Markdown, and plain text detection - Add embedding.py with mean pooling for large content - Create dedicated commands: embed_note, embed_insight, embed_source - Use fire-and-forget pattern for embedding via submit_command() - Refactor rebuild_embeddings_command to delegate to individual commands - Remove legacy commands and needs_embedding() methods - Reduce chunk size to 1500 chars for Ollama compatibility - Update CLAUDE.md documentation for new architecture Fixes #350, #142 * fix: address code review issues - Note.save() now returns command_id for tracking embedding jobs - Add length check after generate_embeddings() to fail fast on mismatch - Add numpy as explicit dependency (was transitive) - Remove hardcoded chunk sizes from docstrings * docs: address code review comments - Rename "SYNC PATH" to "DOMAIN MODEL PATH" in embedding router - Add test_chunking.py and test_embedding.py to Testing Strategy - Clarify auto-embedding behavior for each domain model * fix: clean thinking tags from prompt graph output Adds clean_thinking_content() to prompt.py to handle extended thinking models that return <think>...</think> tags. This fixes empty titles when saving notes from chat. * chore: remove local docker-compose from git * fix(frontend): handle null parent_id in search results Add defensive check for null parent_id in search results to prevent "Cannot read properties of null (reading 'split')" error. This can happen with orphaned records in the database. * fix: cascade delete embeddings and insights when source is deleted When deleting a Source, now also deletes associated: - source_embedding records - source_insight records This prevents orphaned records that cause null parent_id errors in vector search results. * fix: add cleanup for orphan embedding/insight records in migration 10 Deletes source_embedding and source_insight records where the linked source no longer exists (source.id = NONE). * chore: bump esperanto to 2.16 Increases ctx_num for Ollama models to accommodate larger notebook context windows. See: https://github.com/lfnovo/esperanto/pull/69
98 lines
2.4 KiB
TOML
98 lines
2.4 KiB
TOML
[project]
|
|
name = "open-notebook"
|
|
version = "1.6.0"
|
|
description = "An open source implementation of a research assistant, inspired by Google Notebook LM"
|
|
authors = [
|
|
{name = "Luis Novo", email = "lfnovo@gmail.com"}
|
|
]
|
|
readme = "README.md"
|
|
classifiers = [
|
|
"License :: OSI Approved :: MIT License",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.11",
|
|
]
|
|
requires-python = ">=3.11,<3.13"
|
|
dependencies = [
|
|
"fastapi>=0.104.0",
|
|
"uvicorn>=0.24.0",
|
|
"pydantic>=2.9.2",
|
|
"loguru>=0.7.2",
|
|
"langchain>=1.2.0",
|
|
"langgraph>=1.0.5",
|
|
"tiktoken>=0.12.0",
|
|
"langgraph-checkpoint-sqlite>=3.0.1",
|
|
"langchain-community>=0.4.1",
|
|
"langchain-openai>=1.1.6",
|
|
"langchain-anthropic>=1.3.0",
|
|
"langchain-ollama>=1.0.1",
|
|
"langchain-google-genai>=4.1.2",
|
|
"langchain-groq>=1.1.1",
|
|
"langchain_mistralai>=1.1.1",
|
|
"langchain_deepseek>=1.0.0",
|
|
"langchain-google-vertexai>=3.2.0",
|
|
"tomli>=2.0.2",
|
|
"python-dotenv>=1.0.1",
|
|
"httpx[socks]>=0.27.0",
|
|
"content-core>=1.0.2",
|
|
"ai-prompter>=0.3",
|
|
"esperanto>=2.16",
|
|
"surrealdb>=1.0.4",
|
|
"podcast-creator>=0.7.0",
|
|
"surreal-commands>=1.3.0",
|
|
"numpy>=2.4.1",
|
|
]
|
|
|
|
[tool.setuptools]
|
|
package-dir = {"open_notebook" = "open_notebook"}
|
|
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"ipykernel>=6.29.5",
|
|
"ruff>=0.5.5",
|
|
"mypy>=1.11.1",
|
|
"types-requests>=2.32.0.20241016",
|
|
"ipywidgets>=8.1.5",
|
|
"pre-commit>=4.0.1",
|
|
"pytest>=8.0.0",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["setuptools>=61.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"pre-commit>=4.1.0",
|
|
"pytest-asyncio>=1.2.0",
|
|
"types-requests>=2.32.4.20250913",
|
|
]
|
|
|
|
[tool.isort]
|
|
profile = "black"
|
|
line_length = 88
|
|
|
|
[tool.ruff]
|
|
line-length = 88
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I"]
|
|
ignore = [
|
|
"E501", # line too long
|
|
"E402", # module level import not at top of file (Streamlit requires this pattern)
|
|
"E722", # do not use bare except (legacy code pattern)
|
|
"F401", # imported but unused (may be used in type hints or re-exports)
|
|
"F541", # f-string without placeholders
|
|
"F841", # local variable assigned but never used
|
|
]
|
|
|
|
[tool.ruff.lint.per-file-ignores]
|
|
# Streamlit files need nest_asyncio.apply() before imports
|
|
"app_home.py" = ["E402"]
|
|
"pages/**/*.py" = ["E402"]
|
|
|
|
[tool.mypy]
|
|
# Exclude Streamlit UI pages from type checking
|
|
[[tool.mypy.overrides]]
|
|
module = "pages.*"
|
|
ignore_errors = true
|