Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

example/sdk/chat_assistant_example.py

@@ -15,7 +15,7 @@
 #
 
 """
-The example demonstrates how to create a chat assistant, manage sessions, 
+The example demonstrates how to create a chat assistant, manage sessions,
 and perform both standard and streaming chat.
 """
 
@@ -39,7 +39,7 @@ try:
         name="Test Assistant",
         dataset_ids=[dataset.id],
         llm_id="deepseek-chat",  # Example LLM ID, replace with your actual model ID
-        prompt_config={"system": "You are a helpful assistant."}
+        prompt_config={"system": "You are a helpful assistant."},
     )
     print(f"Assistant created: {assistant.name} (ID: {assistant.id})")
 
@@ -52,12 +52,12 @@ try:
     print("\n--- Standard Chat ---")
     question = "What is RAGFlow?"
     print(f"User: {question}")
-    
+
     # ask returns a generator of Message objects
     # for stream=False, it yields once with the full answer
     for message in session.ask(question=question, stream=False):
         print(f"Assistant: {message.content}")
-        if hasattr(message, 'reference') and message.reference:
+        if hasattr(message, "reference") and message.reference:
             print(f"References used: {len(message.reference)} chunks")
 
     # 5. Streaming chat
@@ -65,10 +65,10 @@ try:
     question = "Tell me more about its features."
     print(f"User: {question}")
     print("Assistant: ", end="", flush=True)
-    
+
     for message in session.ask(question=question, stream=True):
         # In streaming mode, each message.content usually contains the incremental part
-        # or the full content so far depending on the SDK implementation. 
+        # or the full content so far depending on the SDK implementation.
         # Based on RAGFlow SDK, it typically yields incremental parts.
         print(message.content, end="", flush=True)
     print("\n")

example/sdk/chunk_example.py

@@ -38,21 +38,21 @@ try:
     print("Uploading document...")
     # Using a simple text content for example
     content = "RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding."
-    docs = dataset.upload_documents([{"display_name": "sample.txt", "blob": content.encode('utf-8')}])
+    docs = dataset.upload_documents([{"display_name": "sample.txt", "blob": content.encode("utf-8")}])
     doc = docs[0]
 
     # 3. Parse the document (required before manual chunk operations if you want it to be processed)
     print("Parsing document...")
     dataset.async_parse_documents([doc.id])
-    
+
     # Wait for parsing to complete with timeout
     MAX_WAIT = 120  # seconds
     elapsed = 0
     while elapsed < MAX_WAIT:
         doc_status = dataset.list_documents(id=doc.id)[0]
         if doc_status.run == "1" and doc_status.progress >= 1.0:
-             print("Parsing completed.")
-             break
+            print("Parsing completed.")
+            break
         print(f"Parsing progress: {doc_status.progress:.2f}")
         time.sleep(2)
         elapsed += 2
@@ -75,7 +75,7 @@ try:
     # 6. Update a chunk
     print("Updating chunk...")
     chunk.update({"content": "RAGFlow features a streamlined and powerful RAG workflow."})
-    
+
     # 7. Delete the chunk
     print("Deleting chunk...")
     doc.delete_chunks([chunk.id])
@@ -83,7 +83,7 @@ try:
     # Cleanup
     print("Cleaning up dataset...")
     rag.delete_datasets(ids=[dataset.id])
-    
+
     print("Chunk example done.")
     sys.exit(0)
 

example/sdk/dataset_example.py

@@ -32,7 +32,7 @@ try:
     dataset_instance = ragflow_instance.create_dataset(name="dataset_instance")
 
     # update the dataset instance
-    updated_message = {"name":"updated_dataset"}
+    updated_message = {"name": "updated_dataset"}
     updated_dataset = dataset_instance.update(updated_message)
 
     # get the dataset (list datasets)
@@ -49,5 +49,3 @@ try:
 except Exception as e:
     print(str(e))
     sys.exit(-1)
-
-

example/sdk/retrieval_example.py

@@ -37,9 +37,9 @@ try:
     # 2. Upload and parse a document to have content for retrieval
     print("Uploading and parsing document...")
     content = "RAGFlow is an open-source RAG engine based on deep document understanding. It features a streamlined RAG workflow for businesses of any size."
-    docs = dataset.upload_documents([{"display_name": "ragflow_info.txt", "blob": content.encode('utf-8')}])
+    docs = dataset.upload_documents([{"display_name": "ragflow_info.txt", "blob": content.encode("utf-8")}])
     doc = docs[0]
-    
+
     # Wait for parsing to complete with timeout
     print("Parsing document...")
     dataset.async_parse_documents([doc.id])
@@ -48,7 +48,7 @@ try:
     while elapsed < MAX_WAIT:
         doc_status = dataset.list_documents(id=doc.id)[0]
         if doc_status.run == "1" and doc_status.progress >= 1.0:
-             break
+            break
         print(f"Parsing progress: {doc_status.progress:.2f}")
         time.sleep(2)
         elapsed += 2
@@ -61,18 +61,13 @@ try:
     print("\n--- Performing Retrieval ---")
     question = "What is RAGFlow?"
     print(f"Question: {question}")
-    
+
     # Retrieve relevant chunks from one or more datasets
-    chunks = rag.retrieve(
-        dataset_ids=[dataset.id],
-        question=question,
-        top_k=5,
-        similarity_threshold=0.1
-    )
+    chunks = rag.retrieve(dataset_ids=[dataset.id], question=question, top_k=5, similarity_threshold=0.1)
 
     print(f"Found {len(chunks)} relevant chunks:")
     for i, chunk in enumerate(chunks):
-        print(f"\nChunk {i+1}:")
+        print(f"\nChunk {i + 1}:")
         print(f"Content: {chunk.content[:200]}...")
         print(f"Similarity Score: {chunk.similarity:.4f}")
         print(f"Source Document: {chunk.document_name}")
@@ -83,10 +78,10 @@ try:
         dataset_ids=[dataset.id],
         question="workflow for businesses",
         top_k=3,
-        keyword=True  # Enable keyword search in addition to semantic search
+        keyword=True,  # Enable keyword search in addition to semantic search
     )
     for i, chunk in enumerate(chunks):
-        print(f"Chunk {i+1}: {chunk.content[:100]}... (Score: {chunk.similarity:.4f})")
+        print(f"Chunk {i + 1}: {chunk.content[:100]}... (Score: {chunk.similarity:.4f})")
 
     # Cleanup
     print("\nCleaning up...")