mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-04-25 11:18:22 +00:00
ddfc988bef
* feat(uploads): add pymupdf4llm PDF converter with auto-fallback and async offload - Introduce pymupdf4llm as an optional PDF converter with better heading detection and table preservation than MarkItDown - Auto mode: prefer pymupdf4llm when installed; fall back to MarkItDown when output is suspiciously sparse (image-based / scanned PDFs) - Sparsity check uses chars-per-page (< 50 chars/page) rather than an absolute threshold, correctly handling both short and long documents - Large files (> 1 MB) are offloaded to asyncio.to_thread() to avoid blocking the event loop (related: #1569) - Add UploadsConfig with pdf_converter field (auto/pymupdf4llm/markitdown) - Add pymupdf4llm as optional dependency: pip install deerflow-harness[pymupdf] - Add 14 unit tests covering sparsity heuristic, routing logic, and async path * fix(uploads): address Copilot review comments on PDF converter - Fix docstring: MIN_CHARS_PYMUPDF -> _MIN_CHARS_PER_PAGE (typo) - Fix file handle leak: wrap pymupdf.open in try/finally to ensure doc.close() - Fix silent fallback gap: _convert_pdf_with_pymupdf4llm now catches all conversion exceptions (not just ImportError), so encrypted/corrupt PDFs fall back to MarkItDown instead of propagating - Tighten type: pdf_converter field changed from str to Literal[auto|pymupdf4llm|markitdown] - Normalize config value: _get_pdf_converter() strips and lowercases the raw config string, warns and falls back to 'auto' on unknown values
46 lines
1.1 KiB
TOML
46 lines
1.1 KiB
TOML
[project]
|
|
name = "deerflow-harness"
|
|
version = "0.1.0"
|
|
description = "DeerFlow agent harness framework"
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"agent-client-protocol>=0.4.0",
|
|
"agent-sandbox>=0.0.19",
|
|
"dotenv>=0.9.9",
|
|
"httpx>=0.28.0",
|
|
"kubernetes>=30.0.0",
|
|
"langchain>=1.2.3",
|
|
"langchain-anthropic>=1.3.4",
|
|
"langchain-deepseek>=1.0.1",
|
|
"langchain-mcp-adapters>=0.1.0",
|
|
"langchain-openai>=1.1.7",
|
|
"langfuse>=3.4.1",
|
|
"langgraph>=1.0.6,<1.0.10",
|
|
"langgraph-api>=0.7.0,<0.8.0",
|
|
"langgraph-cli>=0.4.14",
|
|
"langgraph-runtime-inmem>=0.22.1",
|
|
"markdownify>=1.2.2",
|
|
"markitdown[all,xlsx]>=0.0.1a2",
|
|
"pydantic>=2.12.5",
|
|
"pyyaml>=6.0.3",
|
|
"readabilipy>=0.3.0",
|
|
"tavily-python>=0.7.17",
|
|
"firecrawl-py>=1.15.0",
|
|
"tiktoken>=0.8.0",
|
|
"ddgs>=9.10.0",
|
|
"duckdb>=1.4.4",
|
|
"langchain-google-genai>=4.2.1",
|
|
"langgraph-checkpoint-sqlite>=3.0.3",
|
|
"langgraph-sdk>=0.1.51",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
pymupdf = ["pymupdf4llm>=0.0.17"]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["deerflow"]
|