diff --git a/benchmarks/agent/math_tasks.py b/benchmarks/agent/math_tasks.py
index 76b6e09552bc6f7b6d5d470570843dc219690788..bf798763371c25dcc88d27ada6f7838ee9e6b41b 100644
--- a/benchmarks/agent/math_tasks.py
+++ b/benchmarks/agent/math_tasks.py
@@ -7,12 +7,12 @@ from llama_index.tools.function_tool import FunctionTool
def add(a: int, b: int) -> int:
- """Add two integers and returns the result integer"""
+ """Add two integers and returns the result integer."""
return a + b
def multiply(a: int, b: int) -> int:
- """Multiple two integers and returns the result integer"""
+ """Multiple two integers and returns the result integer."""
return a * b
diff --git a/benchmarks/embeddings/bench_embeddings.py b/benchmarks/embeddings/bench_embeddings.py
index b3498cd04badfb29801848d102c17a62d57fee0e..1d0320ecb5778a5b9ef44129b769c91c6ed4dd1d 100644
--- a/benchmarks/embeddings/bench_embeddings.py
+++ b/benchmarks/embeddings/bench_embeddings.py
@@ -16,7 +16,7 @@ def generate_strings(num_strings: int = 100, string_length: int = 10) -> List[st
offset 0: [0:string_length], [string_length:2*string_length], ...
offset 1: [1:1+string_length], [1+string_length:1+2*string_length],...
...
- """
+ """ # noqa: D415
content = (
SimpleDirectoryReader("../../examples/paul_graham_essay/data")
.load_data()[0]
diff --git a/experimental/cli/cli_add.py b/experimental/cli/cli_add.py
index aecb98d9ba8371788bf2dec6ffb143bfd49aa251..076c52b26d128cade52d5833e8d285e4c10cd6e0 100644
--- a/experimental/cli/cli_add.py
+++ b/experimental/cli/cli_add.py
@@ -7,7 +7,7 @@ from .configuration import load_index, save_index
def add_cli(args: Namespace) -> None:
- """Handle subcommand "add" """
+ """Handle subcommand "add"."""
index = load_index()
for p in args.files:
@@ -26,7 +26,7 @@ def add_cli(args: Namespace) -> None:
def register_add_cli(subparsers: _SubParsersAction) -> None:
- """Register subcommand "add" to ArgumentParser"""
+ """Register subcommand "add" to ArgumentParser."""
parser = subparsers.add_parser("add")
parser.add_argument(
"files",
diff --git a/experimental/cli/cli_init.py b/experimental/cli/cli_init.py
index 2d1b68fbe63f3662100a57bc9e290ab31a2146aa..65728d31ed1cb7f83c03ea604b59a8caf7a4c155 100644
--- a/experimental/cli/cli_init.py
+++ b/experimental/cli/cli_init.py
@@ -4,13 +4,13 @@ from .configuration import load_config, save_config
def init_cli(args: Namespace) -> None:
- """Handle subcommand "init" """
+ """Handle subcommand "init"."""
config = load_config(args.directory)
save_config(config, args.directory)
def register_init_cli(subparsers: _SubParsersAction) -> None:
- """Register subcommand "init" to ArgumentParser"""
+ """Register subcommand "init" to ArgumentParser."""
parser = subparsers.add_parser("init")
parser.add_argument(
"directory",
diff --git a/experimental/cli/cli_query.py b/experimental/cli/cli_query.py
index 3550f73a71a56d2240811534cc839fc0ebd43641..dc4543fa129c1dbec8d7250b4ab3221ebd3b9bd0 100644
--- a/experimental/cli/cli_query.py
+++ b/experimental/cli/cli_query.py
@@ -4,14 +4,14 @@ from .configuration import load_index
def query_cli(args: Namespace) -> None:
- """Handle subcommand "query" """
+ """Handle subcommand "query"."""
index = load_index()
query_engine = index.as_query_engine()
print(query_engine.query(args.query))
def register_query_cli(subparsers: _SubParsersAction) -> None:
- """Register subcommand "query" to ArgumentParser"""
+ """Register subcommand "query" to ArgumentParser."""
parser = subparsers.add_parser("query")
parser.add_argument(
"query",
diff --git a/experimental/cli/configuration.py b/experimental/cli/configuration.py
index 395393b48b9d9d78c2373702d34e374287e4131e..4d2d8516cbaa9fac25681f6d3086623eb6ef2c41 100644
--- a/experimental/cli/configuration.py
+++ b/experimental/cli/configuration.py
@@ -28,7 +28,7 @@ DEFAULT_CONFIG = {
def load_config(root: str = ".") -> ConfigParser:
- """Load configuration from file"""
+ """Load configuration from file."""
config = ConfigParser()
config.read_dict(DEFAULT_CONFIG)
config.read(os.path.join(root, CONFIG_FILE_NAME))
@@ -36,13 +36,13 @@ def load_config(root: str = ".") -> ConfigParser:
def save_config(config: ConfigParser, root: str = ".") -> None:
- """Load configuration to file"""
+ """Load configuration to file."""
with open(os.path.join(root, CONFIG_FILE_NAME), "w") as fd:
config.write(fd)
def load_index(root: str = ".") -> BaseIndex[Any]:
- """Load existing index file"""
+ """Load existing index file."""
config = load_config(root)
service_context = _load_service_context(config)
@@ -69,14 +69,14 @@ def load_index(root: str = ".") -> BaseIndex[Any]:
def save_index(index: BaseIndex[Any], root: str = ".") -> None:
- """Save index to file"""
+ """Save index to file."""
config = load_config(root)
persist_dir = config["store"]["persist_dir"]
index.storage_context.persist(persist_dir=persist_dir)
def _load_service_context(config: ConfigParser) -> ServiceContext:
- """Internal function to load service context based on configuration"""
+ """Internal function to load service context based on configuration."""
embed_model = _load_embed_model(config)
llm_predictor = _load_llm_predictor(config)
return ServiceContext.from_defaults(
@@ -90,7 +90,7 @@ def _load_storage_context(config: ConfigParser) -> StorageContext:
def _load_llm_predictor(config: ConfigParser) -> LLMPredictor:
- """Internal function to load LLM predictor based on configuration"""
+ """Internal function to load LLM predictor based on configuration."""
model_type = config["llm_predictor"]["type"].lower()
if model_type == "default":
llm = _load_llm(config["llm_predictor"])
@@ -110,7 +110,7 @@ def _load_llm(section: SectionProxy) -> LLM:
def _load_embed_model(config: ConfigParser) -> BaseEmbedding:
- """Internal function to load embedding model based on configuration"""
+ """Internal function to load embedding model based on configuration."""
model_type = config["embed_model"]["type"]
if model_type == "default":
return OpenAIEmbedding()
diff --git a/experimental/colbert_index/base.py b/experimental/colbert_index/base.py
index 487a1ba2cc7231d59030e475316237f5b6b19089..c0d3bfa143c0889cd785b4b1b4f132b3b6fb559d 100644
--- a/experimental/colbert_index/base.py
+++ b/experimental/colbert_index/base.py
@@ -145,7 +145,7 @@ class ColbertIndex(BaseIndex[IndexDict]):
"""
doc_ids, _, scores = self.store.search(text=query_str, k=top_k)
- node_doc_ids = list(map(lambda id: self._docs_pos_to_node_id[id], doc_ids))
+ node_doc_ids = [self._docs_pos_to_node_id[id] for id in doc_ids]
nodes = self.docstore.get_nodes(node_doc_ids)
nodes_with_score = []
diff --git a/llama_index/agent/react/formatter.py b/llama_index/agent/react/formatter.py
index 97d131fe310b7c793458f2aef6585272f76c506e..7680521239c2f640ed93b211131d9d331d99a283 100644
--- a/llama_index/agent/react/formatter.py
+++ b/llama_index/agent/react/formatter.py
@@ -11,7 +11,7 @@ from llama_index.tools import BaseTool
def get_react_tool_descriptions(tools: Sequence[BaseTool]) -> List[str]:
- """Tool"""
+ """Tool."""
tool_descs = []
for tool in tools:
tool_desc = (
diff --git a/llama_index/callbacks/llama_debug.py b/llama_index/callbacks/llama_debug.py
index 1fff6895146c6a279e3518fb242dfd85b4bc2c0d..dd1073ec8eafbe4e0a8c3e85c905e6ef9330c94c 100644
--- a/llama_index/callbacks/llama_debug.py
+++ b/llama_index/callbacks/llama_debug.py
@@ -116,7 +116,7 @@ class LlamaDebugHandler(BaseCallbackHandler):
def _get_time_stats_from_event_pairs(
self, event_pairs: List[List[CBEvent]]
) -> EventStats:
- """Calculate time-based stats for a set of event pairs"""
+ """Calculate time-based stats for a set of event pairs."""
total_secs = 0.0
for event_pair in event_pairs:
start_time = datetime.strptime(event_pair[0].time, TIMESTAMP_FORMAT)
diff --git a/llama_index/callbacks/open_inference_callback.py b/llama_index/callbacks/open_inference_callback.py
index 0e6a0ff50fbe11c7a6218fff95a1dd7a909fb9a4..9b105ca24193b3b7032750f087366411d166f8fd 100644
--- a/llama_index/callbacks/open_inference_callback.py
+++ b/llama_index/callbacks/open_inference_callback.py
@@ -112,7 +112,7 @@ def as_dataframe(data: Iterable[BaseDataType]) -> "DataFrame":
@dataclass
class TraceData:
- """Trace data"""
+ """Trace data."""
query_data: QueryData = field(default_factory=QueryData)
node_datas: List[NodeData] = field(default_factory=list)
diff --git a/llama_index/callbacks/simple_llm_handler.py b/llama_index/callbacks/simple_llm_handler.py
index 3a89f34faa2aea0d7448dbaebca2debef6fcaee5..cc53a35960a52be0e56113e75b6c7c9eeaafbf71 100644
--- a/llama_index/callbacks/simple_llm_handler.py
+++ b/llama_index/callbacks/simple_llm_handler.py
@@ -5,7 +5,7 @@ from llama_index.callbacks.schema import CBEventType, EventPayload
class SimpleLLMHandler(BaseCallbackHandler):
- """Callback handler for printing llms inputs/outputs"""
+ """Callback handler for printing llms inputs/outputs."""
def __init__(self) -> None:
super().__init__(event_starts_to_ignore=[], event_ends_to_ignore=[])
diff --git a/llama_index/chat_engine/context.py b/llama_index/chat_engine/context.py
index 10ee892c04bba8b2414dfd4019cb8706819e6409..dde6e5698da214ab8d92c9e586a0eb1415cc0b0d 100644
--- a/llama_index/chat_engine/context.py
+++ b/llama_index/chat_engine/context.py
@@ -127,7 +127,7 @@ class ContextChatEngine(BaseChatEngine):
return self._context_template.format(context_str=context_str), nodes
def _get_prefix_messages_with_context(self, context_str: str) -> List[ChatMessage]:
- """Get the prefix messages with context"""
+ """Get the prefix messages with context."""
# ensure we grab the user-configured system prompt
system_prompt = ""
prefix_messages = self._prefix_messages
diff --git a/llama_index/chat_engine/types.py b/llama_index/chat_engine/types.py
index 6b96ba91cbda0ed164b56249ca59556875ff4f67..5b73cb5da77de8e2d9d30b439b2734abd8863899 100644
--- a/llama_index/chat_engine/types.py
+++ b/llama_index/chat_engine/types.py
@@ -18,12 +18,12 @@ logger.setLevel(logging.WARNING)
def is_function(message: ChatMessage) -> bool:
- """Utility for ChatMessage responses from OpenAI models"""
+ """Utility for ChatMessage responses from OpenAI models."""
return "function_call" in message.additional_kwargs
class ChatResponseMode(str, Enum):
- """Flag toggling waiting/streaming in `Agent._chat`"""
+ """Flag toggling waiting/streaming in `Agent._chat`."""
WAIT = "wait"
STREAM = "stream"
diff --git a/llama_index/embeddings/adapter.py b/llama_index/embeddings/adapter.py
index e27e0e3144fc27dc4b804a9c29987386f7d42c55..a02516225e2d2232173fb4e9fad0e48efb2b350c 100644
--- a/llama_index/embeddings/adapter.py
+++ b/llama_index/embeddings/adapter.py
@@ -47,7 +47,7 @@ class AdapterEmbeddingModel(BaseEmbedding):
embed_batch_size: int = DEFAULT_EMBED_BATCH_SIZE,
callback_manager: Optional[CallbackManager] = None,
) -> None:
- """Init params"""
+ """Init params."""
import torch
from llama_index.embeddings.adapter_utils import BaseAdapter, LinearLayer
diff --git a/llama_index/evaluation/benchmarks/hotpotqa.py b/llama_index/evaluation/benchmarks/hotpotqa.py
index f09ef85629c733cfcfaa3187c0b694ecd732f2ef..4651fb70f78a13e2562fd326c52a7e600b1f88ed 100644
--- a/llama_index/evaluation/benchmarks/hotpotqa.py
+++ b/llama_index/evaluation/benchmarks/hotpotqa.py
@@ -22,7 +22,7 @@ hotpot/hotpot_dev_distractor_v1.json"""
class HotpotQAEvaluator:
"""
- Refer to https://hotpotqa.github.io/ for more details on the dataset
+ Refer to https://hotpotqa.github.io/ for more details on the dataset.
"""
def _download_datasets(self) -> Dict[str, str]:
diff --git a/llama_index/evaluation/dataset_generation.py b/llama_index/evaluation/dataset_generation.py
index 299e24c1592355703e71d9e23a3cbfd7e1ae648d..3232f5d7fd5496f43f87a166a8baf2868060d368 100644
--- a/llama_index/evaluation/dataset_generation.py
+++ b/llama_index/evaluation/dataset_generation.py
@@ -1,4 +1,4 @@
-"""Dataset generation from documents"""
+"""Dataset generation from documents."""
from __future__ import annotations
import asyncio
diff --git a/llama_index/indices/base_retriever.py b/llama_index/indices/base_retriever.py
index 2885698a53271300263df72536f20e3fb7d0e21f..3d2f52b5b925a9a73ed1dc08030a0d1935f15c28 100644
--- a/llama_index/indices/base_retriever.py
+++ b/llama_index/indices/base_retriever.py
@@ -47,7 +47,7 @@ class BaseRetriever(ABC):
def get_service_context(self) -> Optional[ServiceContext]:
"""Attempts to resolve a service context.
Short-circuits at self.service_context, self._service_context,
- or self._index.service_context
+ or self._index.service_context.
"""
if hasattr(self, "service_context"):
return self.service_context
diff --git a/llama_index/indices/loading.py b/llama_index/indices/loading.py
index b917f93e33790f4f33dea1a6af92d5dace8efe69..4c65946e70978fbfc5f9b42886171b429ff68a31 100644
--- a/llama_index/indices/loading.py
+++ b/llama_index/indices/loading.py
@@ -50,7 +50,7 @@ def load_indices_from_storage(
index_ids: Optional[Sequence[str]] = None,
**kwargs: Any,
) -> List[BaseIndex]:
- """Load multiple indices from storage context
+ """Load multiple indices from storage context.
Args:
storage_context (StorageContext): storage context containing
diff --git a/llama_index/indices/managed/base.py b/llama_index/indices/managed/base.py
index ac649407bbe177cb0b25f394d1c07db2f5d0bb6b..928ba66d50c5ba3f59a020218af2dfffea761176 100644
--- a/llama_index/indices/managed/base.py
+++ b/llama_index/indices/managed/base.py
@@ -20,7 +20,7 @@ class BaseManagedIndex(BaseIndex[IndexDict], ABC):
The managed service can index documents into a managed service.
How documents are structured into nodes is a detail for the managed service,
and not exposed in this interface (although could be controlled by
- configuration parameters)
+ configuration parameters).
Args:
show_progress (bool): Whether to show tqdm progress bars. Defaults to False.
diff --git a/llama_index/indices/managed/vectara/base.py b/llama_index/indices/managed/vectara/base.py
index 21db9ccc4b1e97299a5060de065e1e4293a7abd5..abd6c1c491c642eee4442cc63b58a407c7838f1b 100644
--- a/llama_index/indices/managed/vectara/base.py
+++ b/llama_index/indices/managed/vectara/base.py
@@ -203,7 +203,7 @@ class VectaraIndex(BaseManagedIndex):
) -> Optional[str]:
"""Vectara provides a way to add files (binary or text) directly via our API
where pre-processing and chunking occurs internally in an optimal way
- This method provides a way to use that API in Llama_index
+ This method provides a way to use that API in Llama_index.
# ruff: noqa: E501
Full API Docs: https://docs.vectara.com/docs/api-reference/indexing-apis/
diff --git a/llama_index/indices/managed/vectara/retriever.py b/llama_index/indices/managed/vectara/retriever.py
index 25155d1b64763aa362d987c50dbd2aaf31ae9e0f..5fb08c263718ee5d8fd4701517edc755ffd2b839 100644
--- a/llama_index/indices/managed/vectara/retriever.py
+++ b/llama_index/indices/managed/vectara/retriever.py
@@ -1,5 +1,5 @@
"""Vectara index.
-An index that that is built on top of Vectara
+An index that that is built on top of Vectara.
"""
import json
diff --git a/llama_index/indices/postprocessor/node.py b/llama_index/indices/postprocessor/node.py
index 6a32ab1260e4eb88346ce7fe502bada39969b874..b1011097367b7fccdd626e85e86da680e25f1036 100644
--- a/llama_index/indices/postprocessor/node.py
+++ b/llama_index/indices/postprocessor/node.py
@@ -362,7 +362,7 @@ class LongContextReorder(BaseNodePostprocessor):
performance typically arises when crucial data is positioned
at the start or conclusion of the input context. Additionally,
as the input context lengthens, performance drops notably, even
- in models designed for long contexts."
+ in models designed for long contexts.".
"""
@classmethod
diff --git a/llama_index/llm_predictor/base.py b/llama_index/llm_predictor/base.py
index 776226587c53fe3341f73b2640484395b23a78a2..5de86901826c8574b29afce81513fe519386b23a 100644
--- a/llama_index/llm_predictor/base.py
+++ b/llama_index/llm_predictor/base.py
@@ -263,7 +263,7 @@ class LLMPredictor(BaseLLMPredictor):
self,
formatted_prompt: str,
) -> str:
- """Add system and query wrapper prompts to base prompt"""
+ """Add system and query wrapper prompts to base prompt."""
extended_prompt = formatted_prompt
if self.system_prompt:
extended_prompt = self.system_prompt + "\n\n" + extended_prompt
@@ -276,7 +276,7 @@ class LLMPredictor(BaseLLMPredictor):
return extended_prompt
def _extend_messages(self, messages: List[ChatMessage]) -> List[ChatMessage]:
- """Add system prompt to chat message list"""
+ """Add system prompt to chat message list."""
if self.system_prompt:
messages = [
ChatMessage(role=MessageRole.SYSTEM, content=self.system_prompt),
diff --git a/llama_index/llms/azure_openai.py b/llama_index/llms/azure_openai.py
index 2dd0eae9c60a98235befe0d45b31b17ead60150c..21bf029ab41e93f2674b2de9a54372f642ef9047 100644
--- a/llama_index/llms/azure_openai.py
+++ b/llama_index/llms/azure_openai.py
@@ -10,7 +10,7 @@ AZURE_OPENAI_API_TYPE = "azure"
class AzureOpenAI(OpenAI):
"""
- Azure OpenAI
+ Azure OpenAI.
To use this, you must first deploy a model on Azure OpenAI.
Unlike OpenAI, you need to specify a `engine` parameter to identify
diff --git a/llama_index/llms/portkey.py b/llama_index/llms/portkey.py
index 4fcbcdf452790870240b12f47c4a5a7561187622..c9e444af99946feaa30d4dfb7d92228b7cb8b318 100644
--- a/llama_index/llms/portkey.py
+++ b/llama_index/llms/portkey.py
@@ -1,5 +1,5 @@
"""
-Portkey integration with Llama_index for enhanced monitoring
+Portkey integration with Llama_index for enhanced monitoring.
"""
from typing import TYPE_CHECKING, Any, List, Optional, Sequence, Union, cast
@@ -38,7 +38,7 @@ if TYPE_CHECKING:
class Portkey(CustomLLM):
- """_summary_
+ """_summary_.
Args:
LLM (_type_): _description_
diff --git a/llama_index/llms/portkey_utils.py b/llama_index/llms/portkey_utils.py
index d15cb4136704d6a9411797fb92e860a375636251..b328ea402f7505b252a7c338e030c49147c7529b 100644
--- a/llama_index/llms/portkey_utils.py
+++ b/llama_index/llms/portkey_utils.py
@@ -1,5 +1,5 @@
"""
-Utility Tools for the Portkey Class
+Utility Tools for the Portkey Class.
This file module contains a collection of utility functions designed to enhance
the functionality and usability of the Portkey class
diff --git a/llama_index/llms/predibase.py b/llama_index/llms/predibase.py
index e0a279653bde32ba86baccd79168d67ba9739786..c70dc631d1ee11cd13ad066463f755ceedcbd024 100644
--- a/llama_index/llms/predibase.py
+++ b/llama_index/llms/predibase.py
@@ -14,7 +14,7 @@ from llama_index.llms.custom import CustomLLM
class PredibaseLLM(CustomLLM):
- """Predibase LLM"""
+ """Predibase LLM."""
model_name: str = Field(description="The Predibase model to use.")
predibase_api_key: str = Field(description="The Predibase API key to use.")
diff --git a/llama_index/node_parser/extractors/metadata_extractors.py b/llama_index/node_parser/extractors/metadata_extractors.py
index 88846e61d67c14b55fbef4a37d244a6a0885834b..166e5b559af0e7a605840efb7af14e5e77bc9955 100644
--- a/llama_index/node_parser/extractors/metadata_extractors.py
+++ b/llama_index/node_parser/extractors/metadata_extractors.py
@@ -403,7 +403,8 @@ class SummaryExtractor(MetadataFeatureExtractor):
"""
Summary extractor. Node-level extractor with adjacent sharing.
Extracts `section_summary`, `prev_section_summary`, `next_section_summary`
- metadata fields
+ metadata fields.
+
Args:
llm_predictor (Optional[BaseLLMPredictor]): LLM predictor
summaries (List[str]): list of summaries to extract: 'self', 'prev', 'next'
diff --git a/llama_index/node_parser/file/html.py b/llama_index/node_parser/file/html.py
index 60b1e387f87830fb74d421299b4cd352636be513..c45498a1a99cbc6b1db5fb50d750b8c9d09a7f1a 100644
--- a/llama_index/node_parser/file/html.py
+++ b/llama_index/node_parser/file/html.py
@@ -88,7 +88,7 @@ class HTMLNodeParser(NodeParser):
return all_nodes
def get_nodes_from_node(self, node: BaseNode) -> List[TextNode]:
- """Get nodes from document"""
+ """Get nodes from document."""
try:
from bs4 import BeautifulSoup
except ImportError:
@@ -144,7 +144,7 @@ class HTMLNodeParser(NodeParser):
node: BaseNode,
metadata: dict,
) -> TextNode:
- """Build node from single text split"""
+ """Build node from single text split."""
node = build_nodes_from_splits(
[text_split], node, self.include_metadata, self.include_prev_next_rel
)[0]
diff --git a/llama_index/node_parser/file/json.py b/llama_index/node_parser/file/json.py
index 207143e55c253125a67fddf55fbc193527f0bc1a..aa8e79a4b6a1bfd9c3f4835ae5562ca1d125818b 100644
--- a/llama_index/node_parser/file/json.py
+++ b/llama_index/node_parser/file/json.py
@@ -80,7 +80,7 @@ class JSONNodeParser(NodeParser):
return all_nodes
def get_nodes_from_node(self, node: BaseNode) -> List[TextNode]:
- """Get nodes from document"""
+ """Get nodes from document."""
text = node.get_content(metadata_mode=MetadataMode.NONE)
try:
data = json.loads(text)
@@ -132,7 +132,7 @@ class JSONNodeParser(NodeParser):
node: BaseNode,
metadata: dict,
) -> TextNode:
- """Build node from single text split"""
+ """Build node from single text split."""
node = build_nodes_from_splits(
[text_split], node, self.include_metadata, self.include_prev_next_rel
)[0]
diff --git a/llama_index/node_parser/file/markdown.py b/llama_index/node_parser/file/markdown.py
index c5f9920509b8ee57513909afe8cec31f1c074179..13ccf80f8e9eadf7542d9b134a426938c1c64c2f 100644
--- a/llama_index/node_parser/file/markdown.py
+++ b/llama_index/node_parser/file/markdown.py
@@ -80,7 +80,7 @@ class MarkdownNodeParser(NodeParser):
return all_nodes
def get_nodes_from_node(self, node: BaseNode) -> List[TextNode]:
- """Get nodes from document"""
+ """Get nodes from document."""
text = node.get_content(metadata_mode=MetadataMode.NONE)
markdown_nodes = []
lines = text.split("\n")
@@ -115,7 +115,7 @@ class MarkdownNodeParser(NodeParser):
def _update_metadata(
self, headers_metadata: dict, new_header: str, new_header_level: int
) -> dict:
- """Update the markdown headers for metadata
+ """Update the markdown headers for metadata.
Removes all headers that are equal or less than the level
of the newly found header
@@ -136,7 +136,7 @@ class MarkdownNodeParser(NodeParser):
node: BaseNode,
metadata: dict,
) -> TextNode:
- """Build node from single text split"""
+ """Build node from single text split."""
node = build_nodes_from_splits(
[text_split], node, self.include_metadata, self.include_prev_next_rel
)[0]
diff --git a/llama_index/objects/tool_node_mapping.py b/llama_index/objects/tool_node_mapping.py
index e17d9cfb581bb014cd91cd325f75a08c6c3fbb91..18ee0c9ae5cafcb639631e17a3836221634747b3 100644
--- a/llama_index/objects/tool_node_mapping.py
+++ b/llama_index/objects/tool_node_mapping.py
@@ -1,4 +1,4 @@
-"""Tool mapping"""
+"""Tool mapping."""
from typing import Any, Optional, Sequence
diff --git a/llama_index/query_engine/citation_query_engine.py b/llama_index/query_engine/citation_query_engine.py
index 7f01c049bd18003e172402be4ba57a945bcd1ad2..52bc021a53013a826e70eef6123f91b801022381 100644
--- a/llama_index/query_engine/citation_query_engine.py
+++ b/llama_index/query_engine/citation_query_engine.py
@@ -136,7 +136,7 @@ class CitationQueryEngine(BaseQueryEngine):
# class-specific args
**kwargs: Any,
) -> "CitationQueryEngine":
- """Initialize a CitationQueryEngine object."
+ """Initialize a CitationQueryEngine object.".
Args:
index: (BastGPTIndex): index to use for querying
diff --git a/llama_index/query_engine/knowledge_graph_query_engine.py b/llama_index/query_engine/knowledge_graph_query_engine.py
index 53b8b9430fe34469343c54d12ddc0ecb5391eea5..8d00b2a44806ff355e2bce8e825ac60f7b8b135d 100644
--- a/llama_index/query_engine/knowledge_graph_query_engine.py
+++ b/llama_index/query_engine/knowledge_graph_query_engine.py
@@ -1,4 +1,4 @@
-""" Knowledge Graph Query Engine"""
+""" Knowledge Graph Query Engine."""
import logging
from typing import Any, List, Optional, Sequence
diff --git a/llama_index/query_engine/retriever_query_engine.py b/llama_index/query_engine/retriever_query_engine.py
index c6bfd389c2a6c9e960ced5a08219bf311d49f832..ad9915390e2e8527ebc8cfaacd8e18092a9ce4da 100644
--- a/llama_index/query_engine/retriever_query_engine.py
+++ b/llama_index/query_engine/retriever_query_engine.py
@@ -67,7 +67,7 @@ class RetrieverQueryEngine(BaseQueryEngine):
# class-specific args
**kwargs: Any,
) -> "RetrieverQueryEngine":
- """Initialize a RetrieverQueryEngine object."
+ """Initialize a RetrieverQueryEngine object.".
Args:
retriever (BaseRetriever): A retriever object.
diff --git a/llama_index/readers/bagel.py b/llama_index/readers/bagel.py
index aecb94ca65f0d154c321ce2087923b9847355446..cdf647f8c47caaef9749900e30748863eeb6bb15 100644
--- a/llama_index/readers/bagel.py
+++ b/llama_index/readers/bagel.py
@@ -18,15 +18,8 @@ Metadatas = List[Metadata]
# Metadata Query Grammar
LiteralValue = Union[str, int, float]
-LogicalOperator = Union[Literal["$and"], Literal["$or"]]
-WhereOperator = Union[
- Literal["$gt"],
- Literal["$gte"],
- Literal["$lt"],
- Literal["$lte"],
- Literal["$ne"],
- Literal["$eq"],
-]
+LogicalOperator = Literal["$and", "$or"]
+WhereOperator = Literal["$gt", "$gte", "$lt", "$lte", "$ne", "$eq"]
OperatorExpression = Dict[Union[WhereOperator, LogicalOperator], LiteralValue]
Where = Dict[
@@ -47,14 +40,7 @@ OneOrMany = Union[T, List[T]]
# This should ust be List[Literal["documents", "embeddings", "metadatas", "distances"]]
# However, this provokes an incompatibility with the Overrides library and Python 3.7
-Include = List[
- Union[
- Literal["documents"],
- Literal["embeddings"],
- Literal["metadatas"],
- Literal["distances"],
- ]
-]
+Include = List[Literal["documents", "embeddings", "metadatas", "distances"]]
LiteralValue = LiteralValue
LogicalOperator = LogicalOperator
diff --git a/llama_index/readers/deeplake.py b/llama_index/readers/deeplake.py
index fa9fb3471c1f6e83115190af27b3f18c1a13844d..00c00f43a66e41c483d45359da3a97cbc2747931 100644
--- a/llama_index/readers/deeplake.py
+++ b/llama_index/readers/deeplake.py
@@ -30,7 +30,7 @@ def vector_search(
distance_metric: distance function 'L2' for Euclidean, 'L1' for Nuclear, 'Max'
l-infinity distance, 'cos' for cosine similarity, 'dot' for dot product
returns:
- nearest_indices: List, indices of nearest neighbors
+ nearest_indices: List, indices of nearest neighbors.
"""
# Calculate the distance between the query_vector and all data_vectors
if isinstance(query_vector, list):
@@ -62,7 +62,7 @@ class DeepLakeReader(BaseReader):
self,
token: Optional[str] = None,
):
- """Initializing the deepLake reader"""
+ """Initializing the deepLake reader."""
import_err_msg = (
"`deeplake` package not found, please run `pip install deeplake`"
)
diff --git a/llama_index/readers/discord_reader.py b/llama_index/readers/discord_reader.py
index 8ea42a0f2e11615a2a7b5d0367b4a425d9a86cbb..0b400d2b38924b76306d5e514265a31814a2d583 100644
--- a/llama_index/readers/discord_reader.py
+++ b/llama_index/readers/discord_reader.py
@@ -70,20 +70,18 @@ async def read_channel(
### Wraps each message in a Document containing the text \
# as well as some useful metadata properties.
- return list(
- map(
- lambda msg: Document(
- text=msg.content,
- metadata={
- "message_id": msg.id,
- "username": msg.author.name,
- "created_at": msg.created_at,
- "edited_at": msg.edited_at,
- },
- ),
- messages,
+ return [
+ Document(
+ text=msg.content,
+ metadata={
+ "message_id": msg.id,
+ "username": msg.author.name,
+ "created_at": msg.created_at,
+ "edited_at": msg.edited_at,
+ },
)
- )
+ for msg in messages
+ ]
class DiscordReader(BasePydanticReader):
diff --git a/llama_index/readers/file/docs_reader.py b/llama_index/readers/file/docs_reader.py
index 4817086932ce35abaa45884520425c043bde321b..4203e37c54389b77afc96e318c9ca5d7b0584268 100644
--- a/llama_index/readers/file/docs_reader.py
+++ b/llama_index/readers/file/docs_reader.py
@@ -71,7 +71,7 @@ class DocxReader(BaseReader):
class HWPReader(BaseReader):
- """Hwp Parser"""
+ """Hwp Parser."""
def __init__(self, *args: Any, **kwargs: Any) -> None:
super().__init__(*args, **kwargs)
diff --git a/llama_index/readers/file/flat_reader.py b/llama_index/readers/file/flat_reader.py
index 4ba16679cf052078663701d86acb53a3daa705ba..05130cfb3873cd56ccebebc77901c9846a5d89e3 100644
--- a/llama_index/readers/file/flat_reader.py
+++ b/llama_index/readers/file/flat_reader.py
@@ -7,7 +7,7 @@ from llama_index.schema import Document
class FlatReader(BaseReader):
- """Flat reader
+ """Flat reader.
Extract raw text from a file and save the file type in the metadata
"""
diff --git a/llama_index/readers/github_readers/github_repository_reader.py b/llama_index/readers/github_readers/github_repository_reader.py
index ef3265e7b0a1819752a01ccaa7f6eb67112b204f..bceee82511f6f3c5d9384a487f151f5752e01f53 100644
--- a/llama_index/readers/github_readers/github_repository_reader.py
+++ b/llama_index/readers/github_readers/github_repository_reader.py
@@ -348,44 +348,42 @@ class GithubRepositoryReader(BaseReader):
+ f"as {file_extension} with "
+ f"{reader.__class__.__name__}",
)
- with tempfile.TemporaryDirectory() as tmpdirname:
- with tempfile.NamedTemporaryFile(
- dir=tmpdirname,
- suffix=f".{file_extension}",
- mode="w+b",
- delete=False,
- ) as tmpfile:
- print_if_verbose(
- self._verbose,
- "created a temporary file"
- + f"{tmpfile.name} for parsing {file_path}",
- )
- tmpfile.write(file_content)
- tmpfile.flush()
- tmpfile.close()
- try:
- docs = reader.load_data(pathlib.Path(tmpfile.name))
- parsed_file = "\n\n".join([doc.get_content() for doc in docs])
- except Exception as e:
- print_if_verbose(self._verbose, f"error while parsing {file_path}")
- logger.error(
- "Error while parsing "
- + f"{file_path} with "
- + f"{reader.__class__.__name__}:\n{e}"
- )
- parsed_file = None
- finally:
- os.remove(tmpfile.name)
- if parsed_file is None:
- return None
- return Document(
- text=parsed_file,
- id_=tree_sha,
- metadata={
- "file_path": file_path,
- "file_name": tree_path,
- },
+ with tempfile.TemporaryDirectory() as tmpdirname, tempfile.NamedTemporaryFile(
+ dir=tmpdirname,
+ suffix=f".{file_extension}",
+ mode="w+b",
+ delete=False,
+ ) as tmpfile:
+ print_if_verbose(
+ self._verbose,
+ "created a temporary file" + f"{tmpfile.name} for parsing {file_path}",
+ )
+ tmpfile.write(file_content)
+ tmpfile.flush()
+ tmpfile.close()
+ try:
+ docs = reader.load_data(pathlib.Path(tmpfile.name))
+ parsed_file = "\n\n".join([doc.get_content() for doc in docs])
+ except Exception as e:
+ print_if_verbose(self._verbose, f"error while parsing {file_path}")
+ logger.error(
+ "Error while parsing "
+ + f"{file_path} with "
+ + f"{reader.__class__.__name__}:\n{e}"
)
+ parsed_file = None
+ finally:
+ os.remove(tmpfile.name)
+ if parsed_file is None:
+ return None
+ return Document(
+ text=parsed_file,
+ id_=tree_sha,
+ metadata={
+ "file_path": file_path,
+ "file_name": tree_path,
+ },
+ )
if __name__ == "__main__":
diff --git a/llama_index/readers/google_readers/gsheets.py b/llama_index/readers/google_readers/gsheets.py
index 03a2a642a5a1f32e2c843bbe08611be0ccaf2e56..74a3f0d4cd17030a621b51a31779801f79807312 100644
--- a/llama_index/readers/google_readers/gsheets.py
+++ b/llama_index/readers/google_readers/gsheets.py
@@ -104,8 +104,7 @@ class GoogleSheetsReader(BasePydanticReader):
.execute()
)
sheet_text += (
- "\n".join(map(lambda row: "\t".join(row), response.get("values", [])))
- + "\n"
+ "\n".join("\t".join(row) for row in response.get("values", [])) + "\n"
)
return sheet_text
diff --git a/llama_index/readers/myscale.py b/llama_index/readers/myscale.py
index aa166307d95f160100dcc5867d09de167ecb3658..fbb31db01e3568c07e51f5e19849e631002bdfce 100644
--- a/llama_index/readers/myscale.py
+++ b/llama_index/readers/myscale.py
@@ -21,7 +21,7 @@ def format_list_to_string(lst: List) -> str:
class MyScaleSettings:
- """MyScale Client Configuration
+ """MyScale Client Configuration.
Attribute:
table (str) : Table name to operate on.
diff --git a/llama_index/readers/psychic.py b/llama_index/readers/psychic.py
index 8c0edf44af86fd98187938493049d6a72807df6f..28485c75c8ab02aa97d7af5c5436a547cbb22911 100644
--- a/llama_index/readers/psychic.py
+++ b/llama_index/readers/psychic.py
@@ -47,7 +47,7 @@ class PsychicReader(BaseReader):
def load_data(
self, connector_id: Optional[str] = None, account_id: Optional[str] = None
) -> List[Document]:
- """Load data from a Psychic connection
+ """Load data from a Psychic connection.
Args:
connector_id (str): The connector ID to connect to
diff --git a/llama_index/readers/redis/utils.py b/llama_index/readers/redis/utils.py
index 007aa6ee90482e18464e23c81463bd45627a689d..da7e1e3e126705c6ca75023b015300c341fe0d5b 100644
--- a/llama_index/readers/redis/utils.py
+++ b/llama_index/readers/redis/utils.py
@@ -70,7 +70,7 @@ def get_redis_query(
sort: bool = True,
filters: str = "*",
) -> "Query":
- """Create a vector query for use with a SearchIndex
+ """Create a vector query for use with a SearchIndex.
Args:
return_fields (t.List[str]): A list of fields to return in the query results
diff --git a/llama_index/response_synthesizers/accumulate.py b/llama_index/response_synthesizers/accumulate.py
index b13b5485d183eefbd4271c925c1f2505e19d45cb..a95a63b2284631fa2ac6c407770a6362c9883370 100644
--- a/llama_index/response_synthesizers/accumulate.py
+++ b/llama_index/response_synthesizers/accumulate.py
@@ -47,7 +47,7 @@ class Accumulate(BaseSynthesizer):
separator: str = "\n---------------------\n",
**response_kwargs: Any,
) -> RESPONSE_TEXT_TYPE:
- """Apply the same prompt to text chunks and return async responses"""
+ """Apply the same prompt to text chunks and return async responses."""
if self._streaming:
raise ValueError("Unable to stream in Accumulate response mode")
@@ -68,7 +68,7 @@ class Accumulate(BaseSynthesizer):
separator: str = "\n---------------------\n",
**response_kwargs: Any,
) -> RESPONSE_TEXT_TYPE:
- """Apply the same prompt to text chunks and return responses"""
+ """Apply the same prompt to text chunks and return responses."""
if self._streaming:
raise ValueError("Unable to stream in Accumulate response mode")
diff --git a/llama_index/selectors/llm_selectors.py b/llama_index/selectors/llm_selectors.py
index f596cda90874896b7c9966e5c005060604c361d6..1ed035b198d7212101c8e1034cd9ebcb70f32158 100644
--- a/llama_index/selectors/llm_selectors.py
+++ b/llama_index/selectors/llm_selectors.py
@@ -41,7 +41,7 @@ def _structured_output_to_selector_result(output: Any) -> SelectorResult:
class LLMSingleSelector(BaseSelector):
- """LLM single selector
+ """LLM single selector.
LLM-based selector that chooses one out of many options.
@@ -124,7 +124,7 @@ class LLMSingleSelector(BaseSelector):
class LLMMultiSelector(BaseSelector):
- """LLM multi selector
+ """LLM multi selector.
LLM-based selector that chooses multiple out of many options.
diff --git a/llama_index/storage/docstore/firestore_docstore.py b/llama_index/storage/docstore/firestore_docstore.py
index 8f335700f9bc9f7ae26d073ea920ce3eb33c16f4..26f71dac4b0f5dfa514522d25c4c05e5c79cb4fe 100644
--- a/llama_index/storage/docstore/firestore_docstore.py
+++ b/llama_index/storage/docstore/firestore_docstore.py
@@ -34,7 +34,7 @@ class FirestoreDocumentStore(KVDocumentStore):
Args:
project (str): The project which the client acts on behalf of.
database (str): The database name that the client targets.
- namespace (str): namespace for the docstore
+ namespace (str): namespace for the docstore.
"""
firestore_kvstore = FirestoreKVStore(project=project, database=database)
return cls(firestore_kvstore, namespace)
diff --git a/llama_index/storage/index_store/firestore_indexstore.py b/llama_index/storage/index_store/firestore_indexstore.py
index 1cea883bf25971c662f134c8d2291d2cda8d813e..8f777f849a4a65780458dc97d72e9c6111e142f5 100644
--- a/llama_index/storage/index_store/firestore_indexstore.py
+++ b/llama_index/storage/index_store/firestore_indexstore.py
@@ -32,7 +32,7 @@ class FirestoreIndexStore(KVIndexStore):
Args:
project (str): The project which the client acts on behalf of.
database (str): The database name that the client targets.
- namespace (str): namespace for the docstore
+ namespace (str): namespace for the docstore.
"""
firestore_kvstore = FirestoreKVStore(project=project, database=database)
return cls(firestore_kvstore, namespace)
diff --git a/llama_index/tools/tool_spec/load_and_search/base.py b/llama_index/tools/tool_spec/load_and_search/base.py
index 0ee04b533d3887d0464c0729d30cbb8d81d3e298..bde2bc6a8b1ddc809cf6006055d51328ac01b636 100644
--- a/llama_index/tools/tool_spec/load_and_search/base.py
+++ b/llama_index/tools/tool_spec/load_and_search/base.py
@@ -17,7 +17,7 @@ from llama_index.tools.utils import create_schema_from_function
class LoadAndSearchToolSpec(BaseToolSpec):
- """Load and Search Tool
+ """Load and Search Tool.
This tool can be used with other tools that load large amounts of
information. Compared to OndemandLoaderTool this returns two tools,
diff --git a/llama_index/tts/elevenlabs.py b/llama_index/tts/elevenlabs.py
index 5b8f2309a10de6d7208af4e3294f89570b115c4a..64aa65868bc7e02badc92ed51566c0688ee44f29 100644
--- a/llama_index/tts/elevenlabs.py
+++ b/llama_index/tts/elevenlabs.py
@@ -14,8 +14,6 @@ class ElevenLabsTTS(BaseTTS):
"""
def __init__(self, api_key: Optional[str] = None) -> None:
- """ """
-
super().__init__()
self.api_key = api_key
diff --git a/llama_index/utils.py b/llama_index/utils.py
index 59241bb6c4e2ff38621add993a926dc38f92d5d0..c2be210b13a6bf0341cf8237fc56799130fade7c 100644
--- a/llama_index/utils.py
+++ b/llama_index/utils.py
@@ -241,7 +241,7 @@ def get_transformer_tokenizer_fn(model_name: str) -> Callable[[str], List[str]]:
"""
Args:
model_name(str): the model name of the tokenizer.
- For instance, fxmarty/tiny-llama-fast-tokenizer
+ For instance, fxmarty/tiny-llama-fast-tokenizer.
"""
try:
from transformers import AutoTokenizer
@@ -255,7 +255,7 @@ def get_transformer_tokenizer_fn(model_name: str) -> Callable[[str], List[str]]:
def get_cache_dir() -> str:
"""Locate a platform-appropriate cache directory for llama_index,
- and create it if it doesn't yet exist
+ and create it if it doesn't yet exist.
"""
# User override
if "LLAMA_INDEX_CACHE_DIR" in os.environ:
diff --git a/llama_index/vector_stores/cassandra.py b/llama_index/vector_stores/cassandra.py
index 2722259289816483c345e2b32d52011cb8a9a294..6afdc7aab52b0b515069a9f6fdeb2392bd0a3964 100644
--- a/llama_index/vector_stores/cassandra.py
+++ b/llama_index/vector_stores/cassandra.py
@@ -171,7 +171,7 @@ class CassandraVectorStore(VectorStore):
@property
def client(self) -> Any:
- """Return the underlying cassIO vector table object"""
+ """Return the underlying cassIO vector table object."""
return self.vector_table
@staticmethod
diff --git a/llama_index/vector_stores/cogsearch.py b/llama_index/vector_stores/cogsearch.py
index ac194b76c9dbb25f57dcde76a0bbb074a48e7979..51e99fb327354bb6aff92883677f2d3aed1e5a46 100644
--- a/llama_index/vector_stores/cogsearch.py
+++ b/llama_index/vector_stores/cogsearch.py
@@ -27,7 +27,7 @@ class MetadataIndexFieldType(int, enum.Enum):
"""
Enumeration representing the supported types for metadata fields in an
Azure Cognitive Search Index, corresponds with types supported in a flat
- metadata dictionary
+ metadata dictionary.
"""
STRING = auto() # "Edm.String"
@@ -38,7 +38,7 @@ class MetadataIndexFieldType(int, enum.Enum):
class IndexManagement(int, enum.Enum):
- """Enumeration representing the supported index management operations"""
+ """Enumeration representing the supported index management operations."""
NO_VALIDATION = auto()
VALIDATE_INDEX = auto()
@@ -85,7 +85,7 @@ class CognitiveSearchVectorStore(VectorStore):
self._create_index(index_name)
def _create_metadata_index_fields(self) -> List[Any]:
- """Create a list of index fields for storing metadata values"""
+ """Create a list of index fields for storing metadata values."""
from azure.search.documents.indexes.models import SimpleField
index_fields = []
@@ -113,7 +113,7 @@ class CognitiveSearchVectorStore(VectorStore):
def _create_index(self, index_name: Optional[str]) -> None:
"""
Creates a default index based on the supplied index name, key field names and
- metadata filtering keys
+ metadata filtering keys.
"""
from azure.search.documents.indexes.models import (
HnswParameters,
@@ -438,7 +438,7 @@ class CognitiveSearchVectorStore(VectorStore):
return ids
def _create_index_document(self, node: BaseNode) -> Dict[str, Any]:
- """Create Cognitive Search index document from embedding result"""
+ """Create Cognitive Search index document from embedding result."""
doc: Dict[str, Any] = {}
doc["id"] = node.node_id
doc["chunk"] = node.get_content(metadata_mode=MetadataMode.NONE) or ""
@@ -478,7 +478,7 @@ class CognitiveSearchVectorStore(VectorStore):
self._search_client.delete_documents(docs_to_delete)
def _create_odata_filter(self, metadata_filters: MetadataFilters) -> str:
- """Generate an OData filter string using supplied metadata filters"""
+ """Generate an OData filter string using supplied metadata filters."""
odata_filter: List[str] = []
for f in metadata_filters.filters:
if not isinstance(f, ExactMatchFilter):
diff --git a/llama_index/vector_stores/dynamodb.py b/llama_index/vector_stores/dynamodb.py
index 8e4c8e6dfb520caf0cd1d8494ff692efc91af3bb..bd89f72447f4bc70f1ab3d0773600618ca2aa6ff 100644
--- a/llama_index/vector_stores/dynamodb.py
+++ b/llama_index/vector_stores/dynamodb.py
@@ -109,7 +109,7 @@ class DynamoDBVectorStore(VectorStore):
)
def query(self, query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult:
- """Get nodes for response"""
+ """Get nodes for response."""
if query.filters is not None:
raise ValueError(
"Metadata filters not implemented for SimpleVectorStore yet."
diff --git a/llama_index/vector_stores/elasticsearch.py b/llama_index/vector_stores/elasticsearch.py
index dab60f7eb9bf48921d6904364242a190feda9d08..cba936152be64f52852cd784037ecf28100bd22d 100644
--- a/llama_index/vector_stores/elasticsearch.py
+++ b/llama_index/vector_stores/elasticsearch.py
@@ -199,12 +199,12 @@ class ElasticsearchStore(VectorStore):
@property
def client(self) -> Any:
- """Get async elasticsearch client"""
+ """Get async elasticsearch client."""
return self._client
@staticmethod
def get_user_agent() -> str:
- """Get user agent for elasticsearch client"""
+ """Get user agent for elasticsearch client."""
import llama_index
return f"llama_index-py-vs/{llama_index.__version__}"
diff --git a/llama_index/vector_stores/myscale.py b/llama_index/vector_stores/myscale.py
index 05e4f25c314d2c9eead7043dbe4b28eb620acc16..94022cd956c4e4af54fc68f68d70cc0b1321bd43 100644
--- a/llama_index/vector_stores/myscale.py
+++ b/llama_index/vector_stores/myscale.py
@@ -241,7 +241,7 @@ class MyScaleVectorStore(VectorStore):
raise NotImplementedError("Delete not yet implemented for MyScale index.")
def drop(self) -> None:
- """Drop MyScale Index and table"""
+ """Drop MyScale Index and table."""
self._client.command(
f"DROP TABLE IF EXISTS {self.config.database}.{self.config.table}"
)
diff --git a/llama_index/vector_stores/neo4jvector.py b/llama_index/vector_stores/neo4jvector.py
index c25a0c5fa39ad21a9fe83aa317c2984433fcf8c2..be3afe357d863998aca6314fb37f5880b91a04d4 100644
--- a/llama_index/vector_stores/neo4jvector.py
+++ b/llama_index/vector_stores/neo4jvector.py
@@ -10,7 +10,7 @@ from llama_index.vector_stores.utils import metadata_dict_to_node, node_to_metad
def check_if_not_null(props: List[str], values: List[Any]) -> None:
- """Check if variable is not null and raise error accordingly"""
+ """Check if variable is not null and raise error accordingly."""
for prop, value in zip(props, values):
if not value:
raise ValueError(f"Parameter `{prop}` must not be None or empty string")
@@ -19,12 +19,12 @@ def check_if_not_null(props: List[str], values: List[Any]) -> None:
def sort_by_index_name(
lst: List[Dict[str, Any]], index_name: str
) -> List[Dict[str, Any]]:
- """Sort first element to match the index_name if exists"""
+ """Sort first element to match the index_name if exists."""
return sorted(lst, key=lambda x: x.get("index_name") != index_name)
def clean_params(params: List[BaseNode]) -> List[Dict[str, Any]]:
- """Convert BaseNode object to a dictionary to be imported into Neo4j"""
+ """Convert BaseNode object to a dictionary to be imported into Neo4j."""
clean_params = []
for record in params:
text = record.get_content(metadata_mode=MetadataMode.NONE)
diff --git a/llama_index/vector_stores/postgres.py b/llama_index/vector_stores/postgres.py
index faa32c99d970b24e748f1581137a6d730d215899..a603af5c132e74ddfddc7c26fd34c4a4cc1ccab1 100644
--- a/llama_index/vector_stores/postgres.py
+++ b/llama_index/vector_stores/postgres.py
@@ -1,6 +1,5 @@
import logging
-from collections import namedtuple
-from typing import Any, List, Optional, Type
+from typing import Any, List, NamedTuple, Optional, Type
from llama_index.bridge.pydantic import PrivateAttr
from llama_index.schema import BaseNode, MetadataMode, TextNode
@@ -13,9 +12,12 @@ from llama_index.vector_stores.types import (
)
from llama_index.vector_stores.utils import metadata_dict_to_node, node_to_metadata_dict
-DBEmbeddingRow = namedtuple(
- "DBEmbeddingRow", ["node_id", "text", "metadata", "similarity"]
-)
+
+class DBEmbeddingRow(NamedTuple):
+ node_id: str # FIXME: verify this type hint
+ text: str
+ metadata: dict
+ similarity: float
_logger = logging.getLogger(__name__)
@@ -30,7 +32,7 @@ def get_data_model(
embed_dim: int = 1536,
) -> Any:
"""
- This part create a dynamic sqlalchemy model with a new table
+ This part create a dynamic sqlalchemy model with a new table.
"""
from pgvector.sqlalchemy import Vector
from sqlalchemy import Column, Computed
@@ -229,18 +231,16 @@ class PGVectorStore(BasePydanticVectorStore):
self._async_session = async_sessionmaker(self._async_engine)
def _create_tables_if_not_exists(self) -> None:
- with self._session() as session:
- with session.begin():
- self._base.metadata.create_all(session.connection())
+ with self._session() as session, session.begin():
+ self._base.metadata.create_all(session.connection())
def _create_extension(self) -> None:
import sqlalchemy
- with self._session() as session:
- with session.begin():
- statement = sqlalchemy.text("CREATE EXTENSION IF NOT EXISTS vector")
- session.execute(statement)
- session.commit()
+ with self._session() as session, session.begin():
+ statement = sqlalchemy.text("CREATE EXTENSION IF NOT EXISTS vector")
+ session.execute(statement)
+ session.commit()
def _initialize(self) -> None:
if not self._is_initialized:
@@ -264,25 +264,23 @@ class PGVectorStore(BasePydanticVectorStore):
def add(self, nodes: List[BaseNode]) -> List[str]:
self._initialize()
ids = []
- with self._session() as session:
- with session.begin():
- for node in nodes:
- ids.append(node.node_id)
- item = self._node_to_table_row(node)
- session.add(item)
- session.commit()
+ with self._session() as session, session.begin():
+ for node in nodes:
+ ids.append(node.node_id)
+ item = self._node_to_table_row(node)
+ session.add(item)
+ session.commit()
return ids
async def async_add(self, nodes: List[BaseNode]) -> List[str]:
self._initialize()
ids = []
- async with self._async_session() as session:
- async with session.begin():
- for node in nodes:
- ids.append(node.node_id)
- item = self._node_to_table_row(node)
- session.add(item)
- await session.commit()
+ async with self._async_session() as session, session.begin():
+ for node in nodes:
+ ids.append(node.node_id)
+ item = self._node_to_table_row(node)
+ session.add(item)
+ await session.commit()
return ids
def _apply_filters_and_limit(
@@ -325,20 +323,19 @@ class PGVectorStore(BasePydanticVectorStore):
metadata_filters: Optional[MetadataFilters] = None,
) -> List[DBEmbeddingRow]:
stmt = self._build_query(embedding, limit, metadata_filters)
- with self._session() as session:
- with session.begin():
- res = session.execute(
- stmt,
+ with self._session() as session, session.begin():
+ res = session.execute(
+ stmt,
+ )
+ return [
+ DBEmbeddingRow(
+ node_id=item.node_id,
+ text=item.text,
+ metadata=item.metadata_,
+ similarity=(1 - distance) if distance is not None else 0,
)
- return [
- DBEmbeddingRow(
- node_id=item.node_id,
- text=item.text,
- metadata=item.metadata_,
- similarity=(1 - distance) if distance is not None else 0,
- )
- for item, distance in res.all()
- ]
+ for item, distance in res.all()
+ ]
async def _aquery_with_score(
self,
@@ -347,18 +344,17 @@ class PGVectorStore(BasePydanticVectorStore):
metadata_filters: Optional[MetadataFilters] = None,
) -> List[DBEmbeddingRow]:
stmt = self._build_query(embedding, limit, metadata_filters)
- async with self._async_session() as async_session:
- async with async_session.begin():
- res = await async_session.execute(stmt)
- return [
- DBEmbeddingRow(
- node_id=item.node_id,
- text=item.text,
- metadata=item.metadata_,
- similarity=(1 - distance) if distance is not None else 0,
- )
- for item, distance in res.all()
- ]
+ async with self._async_session() as async_session, async_session.begin():
+ res = await async_session.execute(stmt)
+ return [
+ DBEmbeddingRow(
+ node_id=item.node_id,
+ text=item.text,
+ metadata=item.metadata_,
+ similarity=(1 - distance) if distance is not None else 0,
+ )
+ for item, distance in res.all()
+ ]
def _build_sparse_query(
self,
@@ -392,18 +388,17 @@ class PGVectorStore(BasePydanticVectorStore):
metadata_filters: Optional[MetadataFilters] = None,
) -> List[DBEmbeddingRow]:
stmt = self._build_sparse_query(query_str, limit, metadata_filters)
- async with self._async_session() as async_session:
- async with async_session.begin():
- res = await async_session.execute(stmt)
- return [
- DBEmbeddingRow(
- node_id=item.node_id,
- text=item.text,
- metadata=item.metadata_,
- similarity=rank,
- )
- for item, rank in res.all()
- ]
+ async with self._async_session() as async_session, async_session.begin():
+ res = await async_session.execute(stmt)
+ return [
+ DBEmbeddingRow(
+ node_id=item.node_id,
+ text=item.text,
+ metadata=item.metadata_,
+ similarity=rank,
+ )
+ for item, rank in res.all()
+ ]
def _sparse_query_with_rank(
self,
@@ -412,18 +407,17 @@ class PGVectorStore(BasePydanticVectorStore):
metadata_filters: Optional[MetadataFilters] = None,
) -> List[DBEmbeddingRow]:
stmt = self._build_sparse_query(query_str, limit, metadata_filters)
- with self._session() as session:
- with session.begin():
- res = session.execute(stmt)
- return [
- DBEmbeddingRow(
- node_id=item.node_id,
- text=item.text,
- metadata=item.metadata_,
- similarity=rank,
- )
- for item, rank in res.all()
- ]
+ with self._session() as session, session.begin():
+ res = session.execute(stmt)
+ return [
+ DBEmbeddingRow(
+ node_id=item.node_id,
+ text=item.text,
+ metadata=item.metadata_,
+ similarity=rank,
+ )
+ for item, rank in res.all()
+ ]
async def _async_hybrid_query(
self, query: VectorStoreQuery
@@ -540,15 +534,14 @@ class PGVectorStore(BasePydanticVectorStore):
import sqlalchemy
self._initialize()
- with self._session() as session:
- with session.begin():
- stmt = sqlalchemy.text(
- f"DELETE FROM public.data_{self.table_name} where "
- f"(metadata_->>'doc_id')::text = '{ref_doc_id}' "
- )
+ with self._session() as session, session.begin():
+ stmt = sqlalchemy.text(
+ f"DELETE FROM public.data_{self.table_name} where "
+ f"(metadata_->>'doc_id')::text = '{ref_doc_id}' "
+ )
- session.execute(stmt)
- session.commit()
+ session.execute(stmt)
+ session.commit()
def _dedup_results(results: List[DBEmbeddingRow]) -> List[DBEmbeddingRow]:
diff --git a/llama_index/vector_stores/redis.py b/llama_index/vector_stores/redis.py
index 08335461407d5c7b92001b08e288a6acdc48c326..ff1c9774deb390b789ce88834aa3faada65bc290 100644
--- a/llama_index/vector_stores/redis.py
+++ b/llama_index/vector_stores/redis.py
@@ -124,7 +124,7 @@ class RedisVectorStore(VectorStore):
@property
def client(self) -> "RedisType":
- """Return the redis client instance"""
+ """Return the redis client instance."""
return self._redis_client
def add(self, nodes: List[BaseNode]) -> List[str]:
diff --git a/llama_index/vector_stores/rocksetdb.py b/llama_index/vector_stores/rocksetdb.py
index 5b715ba773e99411a25f544b02e192e28c2ba1f6..0c3c1e596e634ac5cd5f69962dcebb8c72f249fe 100644
--- a/llama_index/vector_stores/rocksetdb.py
+++ b/llama_index/vector_stores/rocksetdb.py
@@ -24,7 +24,7 @@ T = TypeVar("T", bound="RocksetVectorStore")
def _get_rockset() -> ModuleType:
"""Gets the rockset module and raises an ImportError if
- the rockset package hasn't been installed
+ the rockset package hasn't been installed.
Returns:
rockset module (ModuleType)
@@ -124,7 +124,7 @@ class RocksetVectorStore(VectorStore):
return self.rs
def add(self, nodes: List[BaseNode]) -> List[str]:
- """Stores vectors in the collection
+ """Stores vectors in the collection.
Args:
nodes (List[BaseNode]): List of nodes with embeddings
@@ -151,7 +151,7 @@ class RocksetVectorStore(VectorStore):
]
def delete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
- """Deletes nodes stored in the collection by their ref_doc_id
+ """Deletes nodes stored in the collection by their ref_doc_id.
Args:
ref_doc_id (str): The ref_doc_id of the document
@@ -177,7 +177,7 @@ class RocksetVectorStore(VectorStore):
)
def query(self, query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult:
- """Gets nodes relevant to a query
+ """Gets nodes relevant to a query.
Args:
query (llama_index.vector_stores.types.VectorStoreQuery): The query
diff --git a/llama_index/vector_stores/tair.py b/llama_index/vector_stores/tair.py
index e611be1cac3ba2340c337cf21ec2970b66a1a70e..7eb1501253361f0a37db1794ac556717c1dd7479 100644
--- a/llama_index/vector_stores/tair.py
+++ b/llama_index/vector_stores/tair.py
@@ -122,7 +122,7 @@ class TairVectorStore(VectorStore):
@property
def client(self) -> "Tair":
- """Return the Tair client instance"""
+ """Return the Tair client instance."""
return self._tair_client
def add(self, nodes: List[BaseNode]) -> List[str]:
diff --git a/llama_index/vector_stores/timescalevector.py b/llama_index/vector_stores/timescalevector.py
index bb67bda14148ea6fb8cd800f8e5b9024248a2c07..ec90fdfc5fc05e1b137b1d2e10347e1bf894ee40 100644
--- a/llama_index/vector_stores/timescalevector.py
+++ b/llama_index/vector_stores/timescalevector.py
@@ -15,7 +15,7 @@ from llama_index.vector_stores.utils import metadata_dict_to_node, node_to_metad
class IndexType(enum.Enum):
- """Enumerator for the supported Index types"""
+ """Enumerator for the supported Index types."""
TIMESCALE_VECTOR = 1
PGVECTOR_IVFFLAT = 2
diff --git a/pyproject.toml b/pyproject.toml
index a02d1e4f79c8c0c906a4ee83dd980409f7b7f269..95eb022344dac8a1b7bff12edaa4548568bb5c38 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -18,7 +18,9 @@ exclude = [
"notebooks",
]
ignore = [
- "COM812",
+ "COM812", # Too aggressive
+ "D212", # Using D213
+ "D417", # Too aggressive
"F541", # Messes with prompts.py
"TCH002",
"UP006", # Messes with pydantic
@@ -31,22 +33,7 @@ select = [
"B011",
"B013",
"B014",
- "C400",
- "C401",
- "C402",
- "C403",
- "C404",
- "C405",
- "C406",
- "C408",
- "C409",
- "C410",
- "C411",
- "C413",
- "C414",
- "C416",
- "C418",
- "C419",
+ "C4",
"COM812",
"COM819",
"D201",
@@ -60,23 +47,9 @@ select = [
"D213",
"D214",
"D215",
- "D400",
- "D403",
- "D405",
- "D406",
- "D407",
- "D408",
- "D409",
- "D410",
- "D411",
- "D412",
- "D413",
- "D416",
- "E703",
- "E711",
- "E712",
- "E713",
- "E714",
+ "D3",
+ "D4",
+ "E7",
"EXE004",
"F504",
"F541",
@@ -102,18 +75,7 @@ select = [
"PT006",
"PT02",
"PTH201",
- "PYI009",
- "PYI010",
- "PYI011",
- "PYI012",
- "PYI014",
- "PYI015",
- "PYI020",
- "PYI026",
- "PYI029",
- "PYI032",
- "PYI053",
- "PYI054",
+ "PYI",
"Q",
"RET501",
"RET502",
@@ -128,15 +90,7 @@ select = [
"SIM103",
"SIM109",
"SIM118",
- "SIM201",
- "SIM202",
- "SIM208",
- "SIM211",
- "SIM212",
- "SIM220",
- "SIM221",
- "SIM222",
- "SIM223",
+ "SIM2",
"SIM300",
"SIM9",
"TCH005",
diff --git a/tests/conftest.py b/tests/conftest.py
index 54f5d47b95da331e2ea0e49e1cdfbc62fb53c57b..cc6dac336c5b9cc265550570762a851cce00e1e3 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -122,7 +122,7 @@ class CachedOpenAIApiKeys:
openai.api_key = "sk-" + "a" * 48
# No matter what, set the environment variable back to what it was
- def __exit__(self, *exc: Any) -> None:
+ def __exit__(self, *exc: object) -> None:
os.environ["OPENAI_API_KEY"] = str(self.api_env_variable_was)
os.environ["OPENAI_API_TYPE"] = str(self.api_env_type_was)
openai.api_key = self.openai_api_key_was
diff --git a/tests/indices/postprocessor/test_base.py b/tests/indices/postprocessor/test_base.py
index 2d64821c0017344c90ea7d26ad6d95ced3987197..955002fb51274937efad6ca7a8394a891b29ec01 100644
--- a/tests/indices/postprocessor/test_base.py
+++ b/tests/indices/postprocessor/test_base.py
@@ -25,7 +25,7 @@ from llama_index.schema import (
)
from llama_index.storage.docstore.simple_docstore import SimpleDocumentStore
-spacy_installed = True if find_spec("spacy") else False
+spacy_installed = bool(find_spec("spacy"))
def test_forward_back_processor(tmp_path: Path) -> None:
diff --git a/tests/indices/query/test_embedding_utils.py b/tests/indices/query/test_embedding_utils.py
index 2dbb83e8ded85d166e6ea54030e918837aca4d55..646650d6f6ea68df76fe37a70b4cff0b2575d6a0 100644
--- a/tests/indices/query/test_embedding_utils.py
+++ b/tests/indices/query/test_embedding_utils.py
@@ -1,4 +1,4 @@
-""" Test embedding utility functions"""
+""" Test embedding utility functions."""
import numpy as np
from llama_index.indices.query.embedding_utils import (
@@ -8,7 +8,7 @@ from llama_index.indices.query.embedding_utils import (
def test_get_top_k_mmr_embeddings() -> None:
- """Test Maximum Marginal Relevance"""
+ """Test Maximum Marginal Relevance."""
# Results score should follow from the mmr algorithm
query_embedding = [5.0, 0.0, 0.0]
embeddings = [[4.0, 3.0, 0.0], [3.0, 4.0, 0.0], [-4.0, 3.0, 0.0]]
diff --git a/tests/indices/tree/test_index.py b/tests/indices/tree/test_index.py
index 9cb651ba2dbdc1c50fc094075c79fa2ebbb31b1e..629ca8d8d159e52473f2e1029990cbc2c547dc73 100644
--- a/tests/indices/tree/test_index.py
+++ b/tests/indices/tree/test_index.py
@@ -197,7 +197,7 @@ def test_insert(
def test_twice_insert_empty(
mock_service_context: ServiceContext,
) -> None:
- """# test twice insert from empty (with_id)"""
+ """# test twice insert from empty (with_id)."""
tree = TreeIndex.from_documents([], service_context=mock_service_context)
# test first insert
diff --git a/tests/llm_predictor/vellum/test_predictor.py b/tests/llm_predictor/vellum/test_predictor.py
index cdf5f16ecd05d9ab21f00a112da04c50342ba35f..938111fa1b3f2ae6e072965efb8e11b37a645831 100644
--- a/tests/llm_predictor/vellum/test_predictor.py
+++ b/tests/llm_predictor/vellum/test_predictor.py
@@ -11,7 +11,7 @@ def test_predict__basic(
vellum_predictor_factory: Callable[..., VellumPredictor],
dummy_prompt: BasePromptTemplate,
) -> None:
- """When the Vellum API returns expected values, so should our predictor"""
+ """When the Vellum API returns expected values, so should our predictor."""
vellum_client = mock_vellum_client_factory(
compiled_prompt_text="What's you're favorite greeting?",
completion_text="Hello, world!",
@@ -29,7 +29,7 @@ def test_stream__basic(
vellum_predictor_factory: Callable[..., VellumPredictor],
dummy_prompt: BasePromptTemplate,
) -> None:
- """When the Vellum API streams expected values, so should our predictor"""
+ """When the Vellum API streams expected values, so should our predictor."""
import vellum
vellum_client = mock_vellum_client_factory(
diff --git a/tests/llm_predictor/vellum/test_prompt_registry.py b/tests/llm_predictor/vellum/test_prompt_registry.py
index 0e845bb4c2ade8c723817b3102405606cd5d5c57..0e3146425f126f022a5f84a9f11bef5477cf330d 100644
--- a/tests/llm_predictor/vellum/test_prompt_registry.py
+++ b/tests/llm_predictor/vellum/test_prompt_registry.py
@@ -13,7 +13,7 @@ def test_from_prompt__new(
mock_vellum_client_factory: Callable[..., mock.MagicMock],
vellum_prompt_registry_factory: Callable[..., VellumPromptRegistry],
) -> None:
- """We should register a new prompt if no deployment exists"""
+ """We should register a new prompt if no deployment exists."""
from vellum.core import ApiError
dummy_prompt = PromptTemplate(template="What's your favorite {thing}?")
@@ -32,7 +32,7 @@ def test_from_prompt__existing(
mock_vellum_client_factory: Callable[..., mock.MagicMock],
vellum_prompt_registry_factory: Callable[..., VellumPromptRegistry],
) -> None:
- """We shouldn't register a new prompt if a deployment id or name is provided"""
+ """We shouldn't register a new prompt if a deployment id or name is provided."""
dummy_prompt = PromptTemplate(
template="What's your favorite {thing}?",
metadata={"vellum_deployment_id": "abc"},
@@ -54,7 +54,7 @@ def test_get_compiled_prompt__basic(
mock_vellum_client_factory: Callable[..., mock.MagicMock],
vellum_prompt_registry_factory: Callable[..., VellumPromptRegistry],
) -> None:
- """Verify that we can get a compiled prompt from the registry"""
+ """Verify that we can get a compiled prompt from the registry."""
registered_prompt = VellumRegisteredPrompt(
deployment_id="abc",
deployment_name="my-deployment",
diff --git a/tests/llms/test_localai.py b/tests/llms/test_localai.py
index a468ad65a42981af8c9f8eeccdb0b4f44be22821..5dafe59b4951705803c626326fab78d15bfbb7b9 100644
--- a/tests/llms/test_localai.py
+++ b/tests/llms/test_localai.py
@@ -77,9 +77,8 @@ def test_forgetting_kwarg() -> None:
with patch(
"llama_index.llms.openai.completion_with_retry", return_value={}
- ) as mock_completion:
- with pytest.raises(NotImplementedError, match="/chat/completions"):
- llm.complete("A long time ago in a galaxy far, far away")
+ ) as mock_completion, pytest.raises(NotImplementedError, match="/chat/completions"):
+ llm.complete("A long time ago in a galaxy far, far away")
mock_completion.assert_not_called()
diff --git a/tests/llms/test_openai_utils.py b/tests/llms/test_openai_utils.py
index 0a9d1f884420b2ce82b100763f8f23646fb44bcd..b61491efb75e4b567c699c29fb667bb66931bb32 100644
--- a/tests/llms/test_openai_utils.py
+++ b/tests/llms/test_openai_utils.py
@@ -57,7 +57,7 @@ def openi_message_dicts_with_function_calling() -> List[dict]:
def azure_openi_message_dicts_with_function_calling() -> List[dict]:
"""
Taken from:
- - https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/function-calling
+ - https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/function-calling.
"""
return [
{
diff --git a/tests/memory/test_chat_memory_buffer.py b/tests/memory/test_chat_memory_buffer.py
index c263984268be9afd51bf56009fe5e9ca835a38b2..7b116880d5d00196af3ce7fbae26dab0ae82567b 100644
--- a/tests/memory/test_chat_memory_buffer.py
+++ b/tests/memory/test_chat_memory_buffer.py
@@ -69,7 +69,7 @@ def test_dict_save_load() -> None:
def test_pickle() -> None:
- """Unpickleable tiktoken tokenizer should be circumvented when pickling"""
+ """Unpickleable tiktoken tokenizer should be circumvented when pickling."""
memory = ChatMemoryBuffer.from_defaults()
bytes_ = pickle.dumps(memory)
assert isinstance(pickle.loads(bytes_), ChatMemoryBuffer)
diff --git a/tests/readers/test_file.py b/tests/readers/test_file.py
index 27b12b9afeb1e34d5d27c57d3589fcecc88a044e..4d1bee1d0174e3db6164b479d4bbad71a23eccea 100644
--- a/tests/readers/test_file.py
+++ b/tests/readers/test_file.py
@@ -343,6 +343,5 @@ def test_error_if_not_dir_or_file() -> None:
SimpleDirectoryReader("not_a_dir")
with pytest.raises(ValueError, match="File"):
SimpleDirectoryReader(input_files=["not_a_file"])
- with TemporaryDirectory() as tmp_dir:
- with pytest.raises(ValueError, match="No files"):
- SimpleDirectoryReader(tmp_dir)
+ with TemporaryDirectory() as tmp_dir, pytest.raises(ValueError, match="No files"):
+ SimpleDirectoryReader(tmp_dir)
diff --git a/tests/text_splitter/test_code_splitter.py b/tests/text_splitter/test_code_splitter.py
index 075469c56ac4c6ab73031764fd43da5d51fce18b..e0580d9a39e0f6f7dfcaf7199f6a4c1a64d0c538 100644
--- a/tests/text_splitter/test_code_splitter.py
+++ b/tests/text_splitter/test_code_splitter.py
@@ -5,7 +5,7 @@ from llama_index.text_splitter import CodeSplitter
def test_python_code_splitter() -> None:
- """Test case for code splitting using python"""
+ """Test case for code splitting using python."""
if "CI" in os.environ:
return
@@ -26,7 +26,7 @@ def baz():
def test_typescript_code_splitter() -> None:
- """Test case for code splitting using typescript"""
+ """Test case for code splitting using typescript."""
if "CI" in os.environ:
return
@@ -49,7 +49,7 @@ function baz() {
def test_html_code_splitter() -> None:
- """Test case for code splitting using typescript"""
+ """Test case for code splitting using typescript."""
if "CI" in os.environ:
return
@@ -82,7 +82,7 @@ def test_html_code_splitter() -> None:
def test_tsx_code_splitter() -> None:
- """Test case for code splitting using typescript"""
+ """Test case for code splitting using typescript."""
if "CI" in os.environ:
return
@@ -120,7 +120,7 @@ export default ExampleComponent;"""
def test_cpp_code_splitter() -> None:
- """Test case for code splitting using typescript"""
+ """Test case for code splitting using typescript."""
if "CI" in os.environ:
return
diff --git a/tests/text_splitter/test_sentence_splitter.py b/tests/text_splitter/test_sentence_splitter.py
index 82b1df214db68ed4d8abb46f2ec81fac1d34e230..928dcb30ab89c107bc267d73d58d8344affaa8c6 100644
--- a/tests/text_splitter/test_sentence_splitter.py
+++ b/tests/text_splitter/test_sentence_splitter.py
@@ -58,7 +58,7 @@ def test_split_with_metadata(english_text: str) -> None:
def test_edge_case() -> None:
- """Test case from: https://github.com/jerryjliu/llama_index/issues/7287"""
+ """Test case from: https://github.com/jerryjliu/llama_index/issues/7287."""
text = "\n\nMarch 2020\n\nL&D Metric (Org) - 2.92%\n\n| Training Name | Category | Duration (hrs) | Invitees | Attendance | Target Training Hours | Actual Training Hours | Adoption % |\n| ---------------------------------------------------------------------------------------------------------------------- | --------------- | -------------- | -------- | ---------- | --------------------- | --------------------- | ---------- |\n| Overview of Data Analytics | Technical | 1 | 23 | 10 | 23 | 10 | 43.5 |\n| Sales & Learning Best Practices - Introduction to OTT Platforms | Technical | 0.5 | 16 | 12 | 8 | 6 | 75 |\n| Leading Through OKRs | Lifeskill | 1 | 1 | 1 | 1 | 1 | 100 |\n| COVID: Lockdown Awareness Session | Lifeskill | 2 | 1 | 1 | 2 | 2 | 100 |\n| Navgati Interview | Lifeskill | 2 | 6 | 6 | 12 | 12 | 100 |\n| leadership Summit | Leadership | 18 | 42 | 42 | 756 | 756 | 100 |\n| AWS - AI/ML - Online Conference | Project Related | 15 | 2 | 2 | 30 | 30 | 100 |\n"
splitter = SentenceSplitter(tokenizer=tiktoken.get_encoding("gpt2").encode)
chunks = splitter.split_text(text)
@@ -109,7 +109,7 @@ def test_split_texts_multiple() -> None:
def test_split_texts_with_metadata(english_text: str) -> None:
- """Test case for a list of texts with metadata"""
+ """Test case for a list of texts with metadata."""
chunk_size = 100
metadata_str = "word " * 50
tokenizer = tiktoken.get_encoding("cl100k_base")
diff --git a/tests/tools/test_utils.py b/tests/tools/test_utils.py
index 6f5cc1ae3636c23da92a64ed137fe0770b0de70f..f727d8400b9397c586376c0a7fc738b571d723d1 100644
--- a/tests/tools/test_utils.py
+++ b/tests/tools/test_utils.py
@@ -23,7 +23,7 @@ def test_create_schema_from_function() -> None:
assert schema["properties"]["a"]["type"] == "boolean"
def test_fn2(x: int = 1) -> None:
- """Optional input"""
+ """Optional input."""
SchemaCls = create_schema_from_function("test_schema", test_fn2)
schema = SchemaCls.schema()