Remove docling dependency and related packages from project

* Remove docling from pyproject.toml
* Update requirements files
* Clean up uv.lock dependencies
* Reduce offline docker image size

(cherry picked from commit f2b6a068e3)

pyproject.toml

@@ -29,7 +29,7 @@ dependencies = [
     "nano-vectordb",
     "networkx",
     "numpy",
-    "pandas>=2.0.0",
+    "pandas>=2.0.0,<2.3.0",
     "pipmaster",
     "pydantic",
     "pypinyin",
@@ -51,8 +51,8 @@ api = [
     "nano-vectordb",
     "networkx",
     "numpy",
-    "openai",
+    "openai>=1.0.0,<2.0.0",
-    "pandas>=2.0.0",
+    "pandas>=2.0.0,<2.3.0",
     "pipmaster",
     "pydantic",
     "pypinyin",
@@ -72,7 +72,7 @@ api = [
     "jiter",
     "passlib[bcrypt]",
     "psutil",
-    "PyJWT",
+    "PyJWT>=2.8.0,<3.0.0",
     "python-jose[cryptography]",
     "python-multipart",
     "pytz",
@@ -82,34 +82,33 @@ api = [
 # Offline deployment dependencies (layered design for flexibility)
 offline-docs = [
     # Document processing dependencies
-    "docling>=1.0.0",
     "pypdf2>=3.0.0",
-    "python-docx>=0.8.11",
+    "python-docx>=0.8.11,<2.0.0",
-    "python-pptx>=0.6.21",
+    "python-pptx>=0.6.21,<2.0.0",
-    "openpyxl>=3.0.0",
+    "openpyxl>=3.0.0,<4.0.0",
 ]
 
 offline-storage = [
     # Storage backend dependencies
-    "redis>=5.0.0",
+    "redis>=5.0.0,<7.0.0",
-    "neo4j>=5.0.0",
+    "neo4j>=5.0.0,<7.0.0",
-    "pymilvus>=2.6.2",
+    "pymilvus>=2.6.2,<3.0.0",
-    "pymongo>=4.0.0",
+    "pymongo>=4.0.0,<5.0.0",
-    "asyncpg>=0.29.0",
+    "asyncpg>=0.29.0,<1.0.0",
-    "qdrant-client>=1.7.0",
+    "qdrant-client>=1.7.0,<2.0.0",
 ]
 
 offline-llm = [
     # LLM provider dependencies
-    "openai>=1.0.0",
+    "openai>=1.0.0,<2.0.0",
-    "anthropic>=0.18.0",
+    "anthropic>=0.18.0,<1.0.0",
-    "ollama>=0.1.0",
+    "ollama>=0.1.0,<1.0.0",
-    "zhipuai>=2.0.0",
+    "zhipuai>=2.0.0,<3.0.0",
-    "aioboto3>=12.0.0",
+    "aioboto3>=12.0.0,<16.0.0",
-    "voyageai>=0.2.0",
+    "voyageai>=0.2.0,<1.0.0",
-    "llama-index>=0.9.0",
+    "llama-index>=0.9.0,<1.0.0",
-    "transformers>=4.30.0",
+    "transformers>=4.30.0,<5.0.0",
-    "torch>=2.0.0",
+    "torch>=2.0.0,<2.3.0",
 ]
 
 offline = [
@@ -130,6 +129,7 @@ Repository = "https://github.com/HKUDS/LightRAG"
 
 [tool.setuptools.packages.find]
 include = ["lightrag*"]
+exclude = ["data*", "tests*", "scripts*", "examples*", "dickens*", "reproduce*", "output_complete*", "rag_storage*", "inputs*"]
 
 [tool.setuptools]
 include-package-data = true

requirements-offline-docs.txt

@@ -3,10 +3,12 @@
 # For offline installation:
 #   pip download -r requirements-offline-docs.txt -d ./packages
 #   pip install --no-index --find-links=./packages -r requirements-offline-docs.txt
+#
+# Recommended: Use pip install lightrag-hku[offline-docs] for the same effect
+# Or use constraints: pip install --constraint constraints-offline.txt -r requirements-offline-docs.txt
 
-# Document processing dependencies
+# Document processing dependencies (with version constraints matching pyproject.toml)
-docling>=1.0.0
+openpyxl>=3.0.0,<4.0.0
-openpyxl>=3.0.0
 pypdf2>=3.0.0
-python-docx>=0.8.11
+python-docx>=0.8.11,<2.0.0
-python-pptx>=0.6.21
+python-pptx>=0.6.21,<2.0.0

requirements-offline.txt

@@ -4,30 +4,30 @@
 #   pip download -r requirements-offline.txt -d ./packages
 #   pip install --no-index --find-links=./packages -r requirements-offline.txt
 #
-# Or use pip install lightrag-hku[offline] for the same effect
+# Recommended: Use pip install lightrag-hku[offline] for the same effect
+# Or use constraints: pip install --constraint constraints-offline.txt -r requirements-offline.txt
 
-aioboto3>=12.0.0
+# LLM provider dependencies (with version constraints matching pyproject.toml)
-anthropic>=0.18.0
+aioboto3>=12.0.0,<16.0.0
-asyncpg>=0.29.0
+anthropic>=0.18.0,<1.0.0
-# Document processing dependencies
-docling>=1.0.0
-llama-index>=0.9.0
-neo4j>=5.0.0
-ollama>=0.1.0
-
-# LLM provider dependencies
-openai>=1.0.0
-openpyxl>=3.0.0
-pymilvus==2.5.2
-pymongo>=4.0.0
-pypdf2>=3.0.0
-python-docx>=0.8.11
-python-pptx>=0.6.21
-qdrant-client>=1.7.0
 
 # Storage backend dependencies
-redis>=5.0.0
+asyncpg>=0.29.0,<1.0.0
-torch>=2.0.0
+
-transformers>=4.30.0
+# Document processing dependencies
-voyageai>=0.2.0
+llama-index>=0.9.0,<1.0.0
-zhipuai>=2.0.0
+neo4j>=5.0.0,<7.0.0
+ollama>=0.1.0,<1.0.0
+openai>=1.0.0,<2.0.0
+openpyxl>=3.0.0,<4.0.0
+pymilvus>=2.6.2,<3.0.0
+pymongo>=4.0.0,<5.0.0
+pypdf2>=3.0.0
+python-docx>=0.8.11,<2.0.0
+python-pptx>=0.6.21,<2.0.0
+qdrant-client>=1.7.0,<2.0.0
+redis>=5.0.0,<7.0.0
+torch>=2.0.0,<2.3.0
+transformers>=4.30.0,<5.0.0
+voyageai>=0.2.0,<1.0.0
+zhipuai>=2.0.0,<3.0.0