Add pydocstyle to the ruff rules (#52136)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <hej.mellor@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Harry Mellor
2026-09-16 16:44:29 +00:00
committed by GitHub
co-authored by Claude Opus 5
parent 804e5377aa
commit 8c1557a79c
2002 changed files with 15024 additions and 14269 deletions
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""
Retrieval Augmented Generation (RAG) Implementation with Langchain
"""Retrieval Augmented Generation (RAG) Implementation with Langchain
==================================================================
This script demonstrates a RAG implementation using LangChain, Milvus
@@ -35,6 +34,7 @@ Notes:
- Ensure both vLLM services are running before executing
- Default ports: 8000 (embedding), 8001 (chat)
- First run may take time to download models
"""
import argparse
@@ -52,9 +52,7 @@ from langchain_text_splitters import RecursiveCharacterTextSplitter
def load_and_split_documents(config: dict[str, Any]):
"""
Load and split documents from web URL
"""
"""Load and split documents from web URL."""
try:
loader = WebBaseLoader(web_paths=(config["url"],))
docs = loader.load()
@@ -70,9 +68,7 @@ def load_and_split_documents(config: dict[str, Any]):
def init_vectorstore(config: dict[str, Any], documents: list[Document]):
"""
Initialize vector store with documents
"""
"""Initialize vector store with documents."""
return Milvus.from_documents(
documents=documents,
embedding=OpenAIEmbeddings(
@@ -86,9 +82,7 @@ def init_vectorstore(config: dict[str, Any], documents: list[Document]):
def init_llm(config: dict[str, Any]):
"""
Initialize llm
"""
"""Initialize llm."""
return ChatOpenAI(
model=config["chat_model"],
openai_api_key=config["vllm_api_key"],
@@ -97,9 +91,7 @@ def init_llm(config: dict[str, Any]):
def get_qa_prompt():
"""
Get question answering prompt template
"""
"""Get question answering prompt template."""
template = """You are an assistant for question-answering tasks.
Use the following pieces of retrieved context to answer the question.
If you don't know the answer, just say that you don't know.
@@ -112,16 +104,12 @@ Answer:
def format_docs(docs: list[Document]):
"""
Format documents for prompt
"""
"""Format documents for prompt."""
return "\n\n".join(doc.page_content for doc in docs)
def create_qa_chain(retriever: Any, llm: ChatOpenAI, prompt: PromptTemplate):
"""
Set up question answering chain
"""
"""Set up question answering chain."""
return (
{
"context": retriever | format_docs,
@@ -134,9 +122,7 @@ def create_qa_chain(retriever: Any, llm: ChatOpenAI, prompt: PromptTemplate):
def get_parser() -> argparse.ArgumentParser:
"""
Parse command line arguments
"""
"""Parse command line arguments."""
parser = argparse.ArgumentParser(description="RAG with vLLM and langchain")
# Add command line arguments
@@ -192,10 +178,7 @@ def get_parser() -> argparse.ArgumentParser:
def init_config(args: Namespace):
"""
Initialize configuration settings from command line arguments
"""
"""Initialize configuration settings from command line arguments."""
return {
"vllm_api_key": args.vllm_api_key,
"vllm_embedding_endpoint": args.vllm_embedding_endpoint,
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""
RAG (Retrieval Augmented Generation) Implementation with LlamaIndex
"""RAG (Retrieval Augmented Generation) Implementation with LlamaIndex
================================================================
This script demonstrates a RAG system using:
@@ -35,6 +34,7 @@ Notes:
- Ensure both vLLM services are running before executing
- Default ports: 8000 (embedding), 8001 (chat)
- First run may take time to download models
"""
import argparse
@@ -50,7 +50,7 @@ from llama_index.vector_stores.milvus import MilvusVectorStore
def init_config(args: Namespace):
"""Initialize configuration with command line arguments"""
"""Initialize configuration with command line arguments."""
return {
"url": args.url,
"embedding_model": args.embedding_model,
@@ -66,12 +66,12 @@ def init_config(args: Namespace):
def load_documents(url: str) -> list:
"""Load and process web documents"""
"""Load and process web documents."""
return SimpleWebPageReader(html_to_text=True).load_data([url])
def setup_models(config: dict[str, Any]):
"""Configure embedding and chat models"""
"""Configure embedding and chat models."""
Settings.embed_model = OpenAILikeEmbedding(
api_base=config["embedding_endpoint"],
api_key=config["vllm_api_key"],
@@ -96,14 +96,14 @@ def setup_models(config: dict[str, Any]):
def setup_vector_store(db_path: str) -> MilvusVectorStore:
"""Initialize vector store"""
"""Initialize vector store."""
sample_emb = Settings.embed_model.get_text_embedding("test")
print(f"Embedding dimension: {len(sample_emb)}")
return MilvusVectorStore(uri=db_path, dim=len(sample_emb), overwrite=True)
def create_index(documents: list, vector_store: MilvusVectorStore):
"""Create document index"""
"""Create document index."""
storage_context = StorageContext.from_defaults(vector_store=vector_store)
return VectorStoreIndex.from_documents(
documents,
@@ -112,13 +112,13 @@ def create_index(documents: list, vector_store: MilvusVectorStore):
def query_document(index: VectorStoreIndex, question: str, top_k: int):
"""Query document with given question"""
"""Query document with given question."""
query_engine = index.as_query_engine(similarity_top_k=top_k)
return query_engine.query(question)
def get_parser() -> argparse.ArgumentParser:
"""Parse command line arguments"""
"""Parse command line arguments."""
parser = argparse.ArgumentParser(description="RAG with vLLM and LlamaIndex")
# Add command line arguments