Init

app/agents/vectorization_agent.py

@@ -2,32 +2,32 @@
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from ..core.vector_store import vector_store, embedding_model
 
-# 初始化文本分割器，用于将长文档切成小块
+# Initialize the text splitter to divide long documents into smaller chunks
 text_splitter = RecursiveCharacterTextSplitter(
-    chunk_size=500,  # 每个块的大小（字符数）
-    chunk_overlap=50, # 块之间的重叠部分
+    chunk_size=500,
+    chunk_overlap=50,
 )
 
 def agent_vectorize_and_store(doc_id: str, text: str, category: str):
-    """Agent 4: 向量化并存储 (真实实现)"""
-    print(f"--- [Agent 4] 正在向量化文档 (ID: {doc_id})...")
+    """Agent 4: Vectorization and Storage (Real Implementation)"""
+    print(f"--- [Agent 4] Vectorizing document (ID: {doc_id})...")
 
-    # 1. 将文档文本分割成块
+    # 1. Split the document text into chunks
     chunks = text_splitter.split_text(text)
-    print(f"--- [Agent 4] 文档被切分为 {len(chunks)} 个块。")
+    print(f"--- [Agent 4] Document split into {len(chunks)} chunks.")
 
     if not chunks:
-        print(f"--- [Agent 4] 文档内容为空，跳过向量化。")
+        print(f"--- [Agent 4] Document is empty, skipping vectorization.")
         return
 
-    # 2. 为每个块创建唯一的ID和元数据
+    # 2. Create a unique ID and metadata for each chunk
     chunk_ids = [f"{doc_id}_{i}" for i in range(len(chunks))]
     metadatas = [{"doc_id": doc_id, "category": category, "chunk_number": i} for i in range(len(chunks))]
 
-    # 3. 使用嵌入模型为所有块生成向量
+    # 3. Use an embedding model to generate vectors for all chunks
     embeddings = embedding_model.embed_documents(chunks)
 
-    # 4. 将ID、向量、元数据和文本块本身添加到ChromaDB
+    # 4. Add the IDs, vectors, metadata, and text chunks to ChromaDB
     vector_store.add(
         ids=chunk_ids,
         embeddings=embeddings,
@@ -35,4 +35,4 @@ def agent_vectorize_and_store(doc_id: str, text: str, category: str):
         metadatas=metadatas
     )
 
-    print(f"--- [Agent 4] 文档 {doc_id} 的向量已存入ChromaDB。")
+    print(f"--- [Agent 4] document {doc_id} stored in ChromaDB。")