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:
co-authored by
Claude Opus 5
parent
804e5377aa
commit
8c1557a79c
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
NOTE: This API server is used only for demonstrating usage of AsyncEngine
|
||||
"""NOTE: This API server is used only for demonstrating usage of AsyncEngine
|
||||
and simple performance benchmarks. It is not intended for production use.
|
||||
For production use, we recommend using our OpenAI compatible server.
|
||||
We are also not going to accept PRs modifying this file.
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
vLLM Chat Assistant - A Streamlit Web Interface
|
||||
"""vLLM Chat Assistant - A Streamlit Web Interface.
|
||||
|
||||
A streamlined chat interface that quickly integrates
|
||||
with vLLM API server.
|
||||
@@ -78,6 +77,7 @@ def create_new_chat_session():
|
||||
- current_session: Sets to new session ID
|
||||
- active_session: Sets to new session ID
|
||||
- messages: Resets to empty list
|
||||
|
||||
"""
|
||||
session_id = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
st.session_state.sessions[session_id] = []
|
||||
@@ -101,6 +101,7 @@ def switch_to_chat_session(session_id):
|
||||
- current_session: Updated to specified session_id
|
||||
- active_session: Updated to specified session_id
|
||||
- messages: Loaded from sessions[session_id]
|
||||
|
||||
"""
|
||||
st.session_state.current_session = session_id
|
||||
st.session_state.active_session = session_id
|
||||
@@ -134,6 +135,7 @@ def get_llm_response(messages, model, reason, content_ph=None, reasoning_ph=None
|
||||
Note:
|
||||
The function uses streamlit placeholders for live updates.
|
||||
When reason=True, the reasoning process appears above the response.
|
||||
|
||||
"""
|
||||
full_text = ""
|
||||
think_text = ""
|
||||
@@ -256,6 +258,7 @@ def server_supports_reasoning():
|
||||
|
||||
Returns:
|
||||
bool: True if the model supports reasoning, False otherwise
|
||||
|
||||
"""
|
||||
resp = client.chat.completions.create(
|
||||
model=model,
|
||||
|
||||
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user