fix ruff errors and formatting

packages/__init__.py

@@ -1 +0,0 @@
-

packages/leann-backend-diskann/pyproject.toml

@@ -16,4 +16,4 @@ wheel.packages = ["leann_backend_diskann"]
 editable.mode = "redirect"
 cmake.build-type = "Release"
 build.verbose = true
-build.tool-args = ["-j8"]
+build.tool-args = ["-j8"]

packages/leann-backend-diskann/third_party/embedding.proto

@@ -2,12 +2,12 @@ syntax = "proto3";
 
 package protoembedding;
 
-message NodeEmbeddingRequest { 
-  repeated uint32 node_ids = 1; 
+message NodeEmbeddingRequest {
+  repeated uint32 node_ids = 1;
 }
 
 message NodeEmbeddingResponse {
   bytes embeddings_data = 1;        // All embedded binary datas
   repeated int32 dimensions = 2;    // Shape [batch_size, embedding_dim]
   repeated uint32 missing_ids = 3;  // Missing node ids
-}
+}

packages/leann-backend-hnsw/CMakeLists.txt

@@ -52,4 +52,4 @@ set(FAISS_BUILD_AVX512 OFF CACHE BOOL "" FORCE)
 # IMPORTANT: Disable building AVX versions to speed up compilation
 set(FAISS_BUILD_AVX_VERSIONS OFF CACHE BOOL "" FORCE)
 
-add_subdirectory(third_party/faiss)
+add_subdirectory(third_party/faiss)

packages/leann-backend-hnsw/leann_backend_hnsw/convert_to_csr.py

@@ -72,7 +72,11 @@ def read_vector_raw(f, element_fmt_char):
 def read_numpy_vector(f, np_dtype, struct_fmt_char):
     """Reads a vector into a NumPy array."""
     count = -1  # Initialize count for robust error handling
-    print(f"  Reading vector (dtype={np_dtype}, fmt='{struct_fmt_char}')... ", end="", flush=True)
+    print(
+        f"  Reading vector (dtype={np_dtype}, fmt='{struct_fmt_char}')... ",
+        end="",
+        flush=True,
+    )
     try:
         count, data_bytes = read_vector_raw(f, struct_fmt_char)
         print(f"Count={count}, Bytes={len(data_bytes)}")
@@ -647,7 +651,10 @@ def convert_hnsw_graph_to_csr(input_filename, output_filename, prune_embeddings=
         print(f"Error: Input file not found: {input_filename}", file=sys.stderr)
         return False
     except MemoryError as e:
-        print(f"\nFatal MemoryError during conversion: {e}. Insufficient RAM.", file=sys.stderr)
+        print(
+            f"\nFatal MemoryError during conversion: {e}. Insufficient RAM.",
+            file=sys.stderr,
+        )
         # Clean up potentially partially written output file?
         try:
             os.remove(output_filename)

packages/leann-backend-hnsw/pyproject.toml

@@ -9,7 +9,7 @@ name = "leann-backend-hnsw"
 version = "0.1.14"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.1.14", 
+    "leann-core==0.1.14",
     "numpy",
     "pyzmq>=23.0.0",
     "msgpack>=1.0.0",
@@ -24,4 +24,4 @@ build.tool-args = ["-j8"]
 
 # CMake definitions to optimize compilation
 [tool.scikit-build.cmake.define]
-CMAKE_BUILD_PARALLEL_LEVEL = "8"
+CMAKE_BUILD_PARALLEL_LEVEL = "8"

packages/leann-core/pyproject.toml

@@ -46,4 +46,4 @@ colab = [
 leann = "leann.cli:main"
 
 [tool.setuptools.packages.find]
-where = ["src"]
+where = ["src"]

packages/leann-core/src/leann/chat.py

@@ -245,7 +245,11 @@ def search_hf_models_fuzzy(query: str, limit: int = 10) -> list[str]:
 
         # HF Hub's search is already fuzzy! It handles typos and partial matches
         models = list_models(
-            search=query, filter="text-generation", sort="downloads", direction=-1, limit=limit
+            search=query,
+            filter="text-generation",
+            sort="downloads",
+            direction=-1,
+            limit=limit,
         )
 
         model_names = [model.id if hasattr(model, "id") else str(model) for model in models]
@@ -582,7 +586,11 @@ class HFChat(LLMInterface):
 
         # Tokenize input
         inputs = self.tokenizer(
-            formatted_prompt, return_tensors="pt", padding=True, truncation=True, max_length=2048
+            formatted_prompt,
+            return_tensors="pt",
+            padding=True,
+            truncation=True,
+            max_length=2048,
         )
 
         # Move inputs to device

packages/leann/README.md

@@ -37,4 +37,4 @@ For full documentation, visit [https://leann.readthedocs.io](https://leann.readt
 
 ## License
 
-MIT License 
+MIT License

packages/leann/pyproject.toml

@@ -39,4 +39,4 @@ diskann = [
 Homepage = "https://github.com/yourusername/leann"
 Documentation = "https://leann.readthedocs.io"
 Repository = "https://github.com/yourusername/leann"
-Issues = "https://github.com/yourusername/leann/issues" 
+Issues = "https://github.com/yourusername/leann/issues"

packages/wechat-exporter/main.py

@@ -1,6 +1,6 @@
 import json
 import sqlite3
-import xml.etree.ElementTree as ET
+import xml.etree.ElementTree as ElementTree
 from pathlib import Path
 from typing import Annotated
 
@@ -26,7 +26,7 @@ def get_safe_path(s: str) -> str:
 def process_history(history: str):
     if history.startswith("<?xml") or history.startswith("<msg>"):
         try:
-            root = ET.fromstring(history)
+            root = ElementTree.fromstring(history)
             title = root.find(".//title").text if root.find(".//title") is not None else None
             quoted = (
                 root.find(".//refermsg/content").text
@@ -52,7 +52,8 @@ def get_message(history: dict | str):
 
 def export_chathistory(user_id: str):
     res = requests.get(
-        "http://localhost:48065/wechat/chatlog", params={"userId": user_id, "count": 100000}
+        "http://localhost:48065/wechat/chatlog",
+        params={"userId": user_id, "count": 100000},
     ).json()
     for i in range(len(res["chatLogs"])):
         res["chatLogs"][i]["content"] = process_history(res["chatLogs"][i]["content"])
@@ -116,7 +117,8 @@ def export_sqlite(
     all_users = requests.get("http://localhost:48065/wechat/allcontacts").json()
     for user in tqdm(all_users):
         cursor.execute(
-            "INSERT OR IGNORE INTO users (id, name) VALUES (?, ?)", (user["arg"], user["title"])
+            "INSERT OR IGNORE INTO users (id, name) VALUES (?, ?)",
+            (user["arg"], user["title"]),
         )
         usr_chatlog = export_chathistory(user["arg"])
         for msg in usr_chatlog: