🚀 Add Ruff Linter

.github/workflows/ci.yml

@@ -0,0 +1,21 @@
+name: ci
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+ #       with:
+ #         ref: ${{ github.head_ref }}
+      - uses: actions/setup-python@v5
+      - uses: pre-commit/action@v3.0.1
+ #     - uses: stefanzweifel/git-auto-commit-action@v5
+ #       with:
+ #         commit_message: 'pre commit fixes'

.pre-commit-config.yaml

@@ -0,0 +1,25 @@
+repos:
+  # auto update
+  - repo: https://gitlab.com/vojko.pribudic.foss/pre-commit-update
+    rev: "v0.5.0"
+    hooks:
+      - id: pre-commit-update
+        args: [--dry-run, --all-versions]
+
+  # ruff
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: "v0.6.7"
+    hooks:
+      # Run the linter.
+      - id: ruff
+        types_or: [ python, pyi, jupyter ]
+        args: [ --fix ]
+      # Run the formatter.
+      - id: ruff-format
+        types_or: [ python, pyi, jupyter ]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: "v1.11.2"
+    hooks:
+      - id: mypy
+        args: [ '--ignore-missing-imports', '--disable-error-code=top-level-await', "--disable-error-code=empty-body" ]

docker/open_llama/hug_model.py

@@ -1,26 +1,27 @@
-import requests
+import argparse
 import json
 import os
 import struct
-import argparse
+
+import requests
+
 
 def make_request(url, params=None):
     print(f"Making request to {url}...")
     response = requests.get(url, params=params)
     if response.status_code == 200:
         return json.loads(response.text)
-    else:
-        print(f"Request failed with status code {response.status_code}")
-        return None
+    print(f"Request failed with status code {response.status_code}")
+    return None
 
 def check_magic_and_version(filename):
-    with open(filename, 'rb') as f:
+    with open(filename, "rb") as f:
         # Read the first 6 bytes from the file
         data = f.read(6)
 
     # Unpack the binary data, interpreting the first 4 bytes as a little-endian unsigned int
     # and the next 2 bytes as a little-endian unsigned short
-    magic, version = struct.unpack('<I H', data)
+    magic, version = struct.unpack("<I H", data)
 
     print(f"magic: 0x{magic:08x}, version: 0x{version:04x}, file: {filename}")
 
@@ -30,17 +31,17 @@ def download_file(url, destination):
     print(f"Downloading {url} to {destination}...")
     response = requests.get(url, stream=True)
     if response.status_code == 200:
-        with open(destination, 'wb') as f:
+        with open(destination, "wb") as f:
             total_downloaded = 0
             for chunk in response.iter_content(chunk_size=1024):
                 if chunk:  # filter out keep-alive new chunks
                     f.write(chunk)
                     total_downloaded += len(chunk)
                     if total_downloaded >= 10485760:  # 10 MB
-                        print('.', end='', flush=True)
+                        print(".", end="", flush=True)
                         total_downloaded = 0
         print("\nDownload complete.")
-        
+
         # Creating a symbolic link from destination to "model.bin"
         if os.path.isfile("model.bin"):
             os.remove("model.bin")  # remove the existing link if any
@@ -61,30 +62,29 @@ def get_user_choice(model_list):
         if 0 <= index < len(model_list):
             # Return the chosen model
             return model_list[index]
-        else:
-            print("Invalid choice.")
+        print("Invalid choice.")
     except ValueError:
         print("Invalid input. Please enter a number corresponding to a model.")
     except IndexError:
         print("Invalid choice. Index out of range.")
-    
+
     return None
 
 def main():
     # Create an argument parser
-    parser = argparse.ArgumentParser(description='Process some parameters.')
+    parser = argparse.ArgumentParser(description="Process some parameters.")
 
     # Arguments
-    parser.add_argument('-v', '--version', type=int, default=0x0003,
-                        help='hexadecimal version number of ggml file')
-    parser.add_argument('-a', '--author', type=str, default='TheBloke',
-                        help='HuggingFace author filter')
-    parser.add_argument('-t', '--tag', type=str, default='llama',
-                        help='HuggingFace tag filter')
-    parser.add_argument('-s', '--search', type=str, default='',
-                        help='HuggingFace search filter')
-    parser.add_argument('-f', '--filename', type=str, default='q5_1',
-                        help='HuggingFace model repository filename substring match')
+    parser.add_argument("-v", "--version", type=int, default=0x0003,
+                        help="hexadecimal version number of ggml file")
+    parser.add_argument("-a", "--author", type=str, default="TheBloke",
+                        help="HuggingFace author filter")
+    parser.add_argument("-t", "--tag", type=str, default="llama",
+                        help="HuggingFace tag filter")
+    parser.add_argument("-s", "--search", type=str, default="",
+                        help="HuggingFace search filter")
+    parser.add_argument("-f", "--filename", type=str, default="q5_1",
+                        help="HuggingFace model repository filename substring match")
 
     # Parse the arguments
     args = parser.parse_args()
@@ -96,20 +96,20 @@ def main():
         "search": args.search
     }
 
-    models = make_request('https://huggingface.co/api/models', params=params)
+    models = make_request("https://huggingface.co/api/models", params=params)
     if models is None:
         return
 
     model_list = []
     # Iterate over the models
     for model in models:
-        model_id = model['id']
-        model_info = make_request(f'https://huggingface.co/api/models/{model_id}')
+        model_id = model["id"]
+        model_info = make_request(f"https://huggingface.co/api/models/{model_id}")
         if model_info is None:
             continue
 
-        for sibling in model_info.get('siblings', []):
-            rfilename = sibling.get('rfilename')
+        for sibling in model_info.get("siblings", []):
+            rfilename = sibling.get("rfilename")
             if rfilename and args.filename in rfilename:
                 model_list.append((model_id, rfilename))
 
@@ -135,5 +135,5 @@ def main():
         print("Error - model choice was None")
         exit(2)
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

examples/batch-processing/server.py

@@ -23,8 +23,6 @@
 
 app = FastAPI()
 
-import openai.types.chat as types
-
 
 @app.post("/v1/chat/completions")
 def create_chat_completions():

examples/gradio_chat/local.py

@@ -1,13 +1,13 @@
+import gradio as gr
+
 import llama_cpp
 import llama_cpp.llama_tokenizer
 
-import gradio as gr
-
 llama = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
     filename="*q8_0.gguf",
     tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
-        "Qwen/Qwen1.5-0.5B"
+        "Qwen/Qwen1.5-0.5B",
     ),
     verbose=False,
 )
@@ -25,7 +25,7 @@ def predict(message, history):
     messages.append({"role": "user", "content": message})
 
     response = llama.create_chat_completion_openai_v1(
-        model=model, messages=messages, stream=True
+        model=model, messages=messages, stream=True,
     )
 
     text = ""

examples/gradio_chat/server.py

@@ -1,5 +1,4 @@
 import gradio as gr
-
 from openai import OpenAI
 
 client = OpenAI(base_url="http://localhost:8000/v1", api_key="llama.cpp")
@@ -17,7 +16,7 @@ def predict(message, history):
     messages.append({"role": "user", "content": message})
 
     response = client.chat.completions.create(
-        model=model, messages=messages, stream=True
+        model=model, messages=messages, stream=True,
     )
 
     text = ""

examples/hf_pull/main.py

@@ -1,12 +1,11 @@
 import llama_cpp
 import llama_cpp.llama_tokenizer
 
-
 llama = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
     filename="*q8_0.gguf",
     tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
-        "Qwen/Qwen1.5-0.5B"
+        "Qwen/Qwen1.5-0.5B",
     ),
     verbose=False,
 )

examples/high_level_api/fastapi_server.py

@@ -26,6 +26,7 @@
 """
 
 import os
+
 import uvicorn
 
 from llama_cpp.server.app import create_app
@@ -34,5 +35,5 @@
     app = create_app()
 
     uvicorn.run(
-        app, host=os.getenv("HOST", "localhost"), port=int(os.getenv("PORT", 8000))
+        app, host=os.getenv("HOST", "localhost"), port=int(os.getenv("PORT", 8000)),
     )

examples/high_level_api/high_level_api_inference.py

@@ -1,5 +1,5 @@
-import json
 import argparse
+import json
 
 from llama_cpp import Llama
 

examples/high_level_api/high_level_api_infill.py

@@ -33,5 +33,5 @@
     filtered = True
 
 print(
-    f"Fill-in-Middle completion{' (filtered)' if filtered else ''}:\n\n{args.prompt}\033[32m{response}\033[{'33' if filtered else '0'}m{args.suffix}\033[0m"
+    f"Fill-in-Middle completion{' (filtered)' if filtered else ''}:\n\n{args.prompt}\033[32m{response}\033[{'33' if filtered else '0'}m{args.suffix}\033[0m",
 )

examples/high_level_api/high_level_api_streaming.py

@@ -1,5 +1,5 @@
-import json
 import argparse
+import json
 
 from llama_cpp import Llama
 

examples/high_level_api/langchain_custom_llm.py

@@ -1,9 +1,10 @@
 import argparse
-
-from llama_cpp import Llama
+from collections.abc import Mapping
+from typing import Any, List, Optional
 
 from langchain.llms.base import LLM
-from typing import Optional, List, Mapping, Any
+
+from llama_cpp import Llama
 
 
 class LlamaLLM(LLM):
@@ -19,7 +20,7 @@ def __init__(self, model_path: str, **kwargs: Any):
         llm = Llama(model_path=model_path)
         super().__init__(model_path=model_path, llm=llm, **kwargs)
 
-    def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:
+    def _call(self, prompt: str, stop: list[str] | None = None) -> str:
         response = self.llm(prompt, stop=stop or [])
         return response["choices"][0]["text"]
 
@@ -37,13 +38,13 @@ def _identifying_params(self) -> Mapping[str, Any]:
 
 # Basic Q&A
 answer = llm(
-    "Question: What is the capital of France? Answer: ", stop=["Question:", "\n"]
+    "Question: What is the capital of France? Answer: ", stop=["Question:", "\n"],
 )
 print(f"Answer: {answer.strip()}")
 
 # Using in a chain
-from langchain.prompts import PromptTemplate
 from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
 
 prompt = PromptTemplate(
     input_variables=["product"],

examples/low_level_api/Chat.py

@@ -1,5 +1,8 @@
 #!/bin/python
-import sys, os, datetime
+import datetime
+import os
+import sys
+
 from common import GptParams
 from low_level_api_chat_cpp import LLaMAInteract
 
@@ -48,7 +51,7 @@ def env_or_def(env, default):
 {USER_NAME}: What time is it?
 {AI_NAME}: It is {DATE_TIME}.
 {USER_NAME}:""" + " ".join(
-    sys.argv[1:]
+    sys.argv[1:],
 )
 
 print("Loading model...")

examples/low_level_api/Miku.py

@@ -1,5 +1,7 @@
 #!/bin/python
-import sys, os
+import os
+import sys
+
 from common import GptParams
 from low_level_api_chat_cpp import LLaMAInteract
 
@@ -35,7 +37,7 @@ def env_or_def(env, default):
 {AI_NAME}: /think I wonder what {USER_NAME} likes to do in his free time? I should ask him about that!
 {AI_NAME}: What do you like to do in your free time? ^_^
 {USER_NAME}:""" + " ".join(
-    sys.argv[1:]
+    sys.argv[1:],
 )
 
 print("Loading model...")

examples/low_level_api/ReasonAct.py

@@ -1,5 +1,7 @@
 #!/bin/python
-import sys, os, datetime
+import os
+import sys
+
 from common import GptParams
 from low_level_api_chat_cpp import LLaMAInteract
 
@@ -12,7 +14,7 @@ def env_or_def(env, default):
 
 MODEL = env_or_def("MODEL", "./models/llama-13B/ggml-model.bin")
 
-prompt = f"""You run in a loop of Thought, Action, Observation.
+prompt = """You run in a loop of Thought, Action, Observation.
 At the end of the loop either Answer or restate your Thought and Action.
 Use Thought to describe your thoughts about the question you have been asked.
 Use Action to run one of these actions available to you:
@@ -30,7 +32,7 @@ def env_or_def(env, default):
 Thought: Do I need to use an action? No, I know the answer
 Answer: Paris is the capital of France
 Question:""" + " ".join(
-    sys.argv[1:]
+    sys.argv[1:],
 )
 
 print("Loading model...")