fix bug

README.md

@@ -296,8 +296,6 @@ async def main():
             model="text-embedding-3-large",
             api_key="your-api-key",
         ),
-        embedding_dim=3072,
-        max_token_size=8192
     )
 
     # Process a document
@@ -422,6 +420,7 @@ import asyncio
 from raganything import RAGAnything
 from lightrag import LightRAG
 from lightrag.llm.openai import openai_complete_if_cache, openai_embed
+from lightrag.utils import EmbeddingFunc
 import os
 
 async def load_existing_lightrag():
@@ -445,13 +444,16 @@ async def load_existing_lightrag():
             api_key="your-api-key",
             **kwargs,
         ),
-        embedding_func=lambda texts: openai_embed(
-            texts,
-            model="text-embedding-3-large",
-            api_key="your-api-key",
-        ),
-        embedding_dim=3072,
-        max_token_size=8192
+        embedding_func=EmbeddingFunc(
+            embedding_dim=3072,
+            max_token_size=8192,
+            func=lambda texts: openai_embed(
+                texts,
+                model="text-embedding-3-large",
+                api_key=api_key,
+                base_url=base_url,
+            ),
+        )
     )
 
     # Initialize storage (this will load existing data if available)

README_zh.md

@@ -292,8 +292,6 @@ async def main():
             model="text-embedding-3-large",
             api_key="your-api-key",
         ),
-        embedding_dim=3072,
-        max_token_size=8192
     )
 
     # 处理文档
@@ -418,6 +416,7 @@ import asyncio
 from raganything import RAGAnything
 from lightrag import LightRAG
 from lightrag.llm.openai import openai_complete_if_cache, openai_embed
+from lightrag.utils import EmbeddingFunc
 import os
 
 async def load_existing_lightrag():
@@ -441,13 +440,16 @@ async def load_existing_lightrag():
             api_key="your-api-key",
             **kwargs,
         ),
-        embedding_func=lambda texts: openai_embed(
-            texts,
-            model="text-embedding-3-large",
-            api_key="your-api-key",
-        ),
-        embedding_dim=3072,
-        max_token_size=8192
+        embedding_func=EmbeddingFunc(
+            embedding_dim=3072,
+            max_token_size=8192,
+            func=lambda texts: openai_embed(
+                texts,
+                model="text-embedding-3-large",
+                api_key=api_key,
+                base_url=base_url,
+            ),
+        )
     )
 
     # 初始化存储（如果有现有数据，这将加载它们）

examples/raganything_example.py

@@ -12,6 +12,7 @@ import os
 import argparse
 import asyncio
 from lightrag.llm.openai import openai_complete_if_cache, openai_embed
+from lightrag.utils import EmbeddingFunc
 from raganything.raganything import RAGAnything
 
 
@@ -89,14 +90,16 @@ async def process_with_rag(
                 base_url=base_url,
                 **kwargs,
             ),
-            embedding_func=lambda texts: openai_embed(
-                texts,
-                model="text-embedding-3-large",
-                api_key=api_key,
-                base_url=base_url,
+            embedding_func=EmbeddingFunc(
+                embedding_dim=3072,
+                max_token_size=8192,
+                func=lambda texts: openai_embed(
+                    texts,
+                    model="text-embedding-3-large",
+                    api_key=api_key,
+                    base_url=base_url,
+                ),
             ),
-            embedding_dim=3072,
-            max_token_size=8192,
         )
 
         # Process document

raganything/__init__.py

@@ -1,5 +1,5 @@
 from .raganything import RAGAnything as RAGAnything
 
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 __author__ = "Zirui Guo"
 __url__ = "https://github.com/HKUDS/RAG-Anything"

raganything/raganything.py

@@ -18,7 +18,7 @@ import sys
 sys.path.insert(0, str(Path(__file__).parent.parent))
 
 from lightrag import LightRAG, QueryParam
-from lightrag.utils import EmbeddingFunc, setup_logger
+from lightrag.utils import setup_logger
 
 # Import parser and multimodal processors
 from raganything.mineru_parser import MineruParser
@@ -42,8 +42,6 @@ class RAGAnything:
         vision_model_func: Optional[Callable] = None,
         embedding_func: Optional[Callable] = None,
         working_dir: str = "./rag_storage",
-        embedding_dim: int = 3072,
-        max_token_size: int = 8192,
     ):
         """
         Initialize Multimodal Document Processing Pipeline
@@ -54,15 +52,11 @@ class RAGAnything:
             vision_model_func: Vision model function for image analysis
             embedding_func: Embedding function for text vectorization
             working_dir: Working directory for storage (used when creating new RAG)
-            embedding_dim: Embedding dimension (used when creating new RAG)
-            max_token_size: Maximum token size for embeddings (used when creating new RAG)
         """
         self.working_dir = working_dir
         self.llm_model_func = llm_model_func
         self.vision_model_func = vision_model_func
         self.embedding_func = embedding_func
-        self.embedding_dim = embedding_dim
-        self.max_token_size = max_token_size
 
         # Set up logging
         setup_logger("RAGAnything")
@@ -136,11 +130,7 @@ class RAGAnything:
         self.lightrag = LightRAG(
             working_dir=self.working_dir,
             llm_model_func=self.llm_model_func,
-            embedding_func=EmbeddingFunc(
-                embedding_dim=self.embedding_dim,
-                max_token_size=self.max_token_size,
-                func=self.embedding_func,
-            ),
+            embedding_func=self.embedding_func,
         )
 
         await self.lightrag.initialize_storages()