[Format] Apply isort and black for python/ (mlc-ai#1097)

[Format] Apply isort and black on `python/`

The commands I am using are:

```
isort --profile black python/
black python/
```

It is always recommended to format the code before submission, given we
don't have a linter CI yet.

Author: junrushao

python/mlc_chat/__init__.py

@@ -2,8 +2,5 @@
 
 MLC Chat is the app runtime of MLC LLM.
 """
+from .chat_module import ChatConfig, ChatModule, ConvConfig, GenerationConfig
 from .libinfo import __version__
-from .chat_module import ChatModule
-from .chat_module import ConvConfig
-from .chat_module import ChatConfig
-from .chat_module import GenerationConfig

python/mlc_chat/chat_module.py

@@ -352,10 +352,12 @@ def _get_chat_config(config_file_path: str, user_chat_config: Optional[ChatConfi
         # We override using user's chat config
         for field in fields(user_chat_config):
             field_name = field.name
-            if field_name == 'model_lib':
-                warn_msg = ('WARNING: Do not override "model_lib" in ChatConfig. '
-                            'This override will be ignored. '
-                            'Please use ChatModule.model_lib_path to override the full model library path instead.')
+            if field_name == "model_lib":
+                warn_msg = (
+                    'WARNING: Do not override "model_lib" in ChatConfig. '
+                    "This override will be ignored. "
+                    "Please use ChatModule.model_lib_path to override the full model library path instead."
+                )
                 warnings.warn(warn_msg)
                 continue
             field_value = getattr(user_chat_config, field_name)
@@ -740,7 +742,12 @@ def __init__(
 
         # 5. Look up model library
         self.model_lib_path = _get_lib_module_path(
-            model, self.model_path, self.chat_config, model_lib_path, device_name, self.config_file_path
+            model,
+            self.model_path,
+            self.chat_config,
+            model_lib_path,
+            device_name,
+            self.config_file_path,
         )
 
         # 6. Call reload

python/mlc_chat/embeddings/openai.py

@@ -1,17 +1,11 @@
 from __future__ import annotations
 
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.embeddings.openai import embed_with_retry, async_embed_with_retry
-
 import logging
-from typing import (
-    List,
-    Optional,
-    Sequence,
-    Tuple,
-)
+from typing import List, Optional, Sequence, Tuple
 
 import numpy as np
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.embeddings.openai import async_embed_with_retry, embed_with_retry
 
 logger = logging.getLogger(__name__)
 
@@ -121,9 +115,9 @@ def _get_len_safe_embeddings(
             self,
             input="",
             **self._invocation_params,
-        )[
-            "data"
-        ][0]["embedding"]
+        )["data"][
+            0
+        ]["embedding"]
         for _result, num_tokens in zip(results, num_tokens_in_batch):
             if len(_result) == 0:
                 average = empty_average
@@ -155,7 +149,9 @@ async def _aget_len_safe_embeddings(
                 input="",
                 **self._invocation_params,
             )
-        )["data"][0]["embedding"]
+        )[
+            "data"
+        ][0]["embedding"]
         for _result, num_tokens in zip(results, num_tokens_in_batch):
             if len(_result) == 0:
                 average = empty_average

python/mlc_chat/gradio.py

@@ -2,10 +2,11 @@
 # pylint: disable=import-error, import-outside-toplevel, invalid-name, line-too-long, protected-access
 # too-many-instance-attributes, too-many-locals, unused-import
 
-from typing import Dict
 import argparse
-import os
 import glob
+import os
+from typing import Dict
+
 import gradio as gr
 
 from .chat_module import ChatModule
@@ -148,7 +149,12 @@ def gradio_stats(self):
 
 
 def launch_gradio(
-    artifact_path: str = "dist", device: str = "auto", port: int = 7860, share: bool = False, host: str = "127.0.0.1"):
+    artifact_path: str = "dist",
+    device: str = "auto",
+    port: int = 7860,
+    share: bool = False,
+    host: str = "127.0.0.1",
+):
     r"""Launch the gradio interface with a given port, creating a publically sharable link if specified."""
 
     # create a gradio module
@@ -230,7 +236,7 @@ def launch_gradio(
         stats_button.click(mod.gradio_stats, [], [stats_output])
 
     # launch to the web
-    demo.launch(share=share, enable_queue=True, server_port=port,server_name=host)
+    demo.launch(share=share, enable_queue=True, server_port=port, server_name=host)
 
 
 if __name__ == "__main__":

python/mlc_chat/interface/openai_api.py

@@ -2,17 +2,19 @@
 Adapted from FastChat's OpenAI protocol: https://github.com/lm-sys/FastChat/blob/main/fastchat/protocol/openai_api_protocol.py
 """
 
-from typing import Literal, Optional, List, Dict, Any, Union
-from pydantic import BaseModel, Field
-import shortuuid
 import time
+from typing import Any, Dict, List, Literal, Optional, Union
+
+import shortuuid
+from pydantic import BaseModel, Field
 
 
 class ChatMessage(BaseModel):
     role: str
     content: str
     name: str | None = None
 
+
 class ChatCompletionRequest(BaseModel):
     model: str
     messages: list[ChatMessage]
@@ -35,16 +37,19 @@ class ChatCompletionRequest(BaseModel):
     # logit_bias
     # user: Optional[str] = None
 
+
 class UsageInfo(BaseModel):
     prompt_tokens: int = 0
     completion_tokens: int | None = 0
     total_tokens: int = 0
 
+
 class ChatCompletionResponseChoice(BaseModel):
     index: int
     message: ChatMessage
     finish_reason: Literal["stop", "length"] | None = None
 
+
 class ChatCompletionResponse(BaseModel):
     id: str = Field(default_factory=lambda: f"chatcmpl-{shortuuid.random()}")
     object: str = "chat.completion"
@@ -53,21 +58,25 @@ class ChatCompletionResponse(BaseModel):
     # TODO: Implement support for the following fields
     usage: UsageInfo | None = None
 
+
 class DeltaMessage(BaseModel):
     role: str | None = None
     content: str | None = None
 
+
 class ChatCompletionResponseStreamChoice(BaseModel):
     index: int
     delta: DeltaMessage
     finish_reason: Literal["stop", "length"] | None = None
 
+
 class ChatCompletionStreamResponse(BaseModel):
     id: str = Field(default_factory=lambda: f"chatcmpl-{shortuuid.random()}")
     object: str = "chat.completion.chunk"
     created: int = Field(default_factory=lambda: int(time.time()))
     choices: list[ChatCompletionResponseStreamChoice]
 
+
 class CompletionRequest(BaseModel):
     model: str
     prompt: str | list[str]
@@ -91,35 +100,41 @@ class CompletionRequest(BaseModel):
     # logit_bias
     # user: Optional[str] = None
 
+
 class CompletionResponseChoice(BaseModel):
     index: int
     text: str
     logprobs: int | None = None
     finish_reason: Literal["stop", "length"] | None = None
 
+
 class CompletionResponse(BaseModel):
     id: str = Field(default_factory=lambda: f"cmpl-{shortuuid.random()}")
     object: str = "text_completion"
     created: int = Field(default_factory=lambda: int(time.time()))
     choices: list[CompletionResponseChoice]
     usage: UsageInfo
 
+
 class CompletionResponseStreamChoice(BaseModel):
     index: int
     text: str
     finish_reason: Optional[Literal["stop", "length"]] = None
 
+
 class CompletionStreamResponse(BaseModel):
     id: str = Field(default_factory=lambda: f"cmpl-{shortuuid.random()}")
     object: str = "text_completion"
     created: int = Field(default_factory=lambda: int(time.time()))
     choices: List[CompletionResponseStreamChoice]
 
+
 class EmbeddingsRequest(BaseModel):
     model: Optional[str] = None
     input: Union[str, List[Any]]
     user: Optional[str] = None
 
+
 class EmbeddingsResponse(BaseModel):
     object: str = "list"
     data: List[Dict[str, Any]]

python/mlc_chat/rest.py

@@ -1,22 +1,19 @@
 import argparse
 import asyncio
 from contextlib import asynccontextmanager
+from dataclasses import dataclass, field, fields
 
-from mlc_chat.chat_module import GenerationConfig
-
+import numpy as np
 import uvicorn
 from fastapi import FastAPI
-from fastapi.responses import StreamingResponse
 from fastapi.middleware.cors import CORSMiddleware
-
-from dataclasses import dataclass, field, fields
+from fastapi.responses import StreamingResponse
+from mlc_chat.chat_module import GenerationConfig
 
 from .base import set_global_random_seed
 from .chat_module import ChatModule
 from .interface.openai_api import *
 
-import numpy as np
-
 
 @dataclass
 class RestAPIArgs:
@@ -327,13 +324,15 @@ async def read_stats():
     """
     return session["chat_mod"].stats()
 
+
 @app.get("/verbose_stats")
 async def read_stats_verbose():
     """
     Get the verbose runtime stats.
     """
     return session["chat_mod"].stats(verbose=True)
 
+
 ARGS = convert_args_to_argparser().parse_args()
 if __name__ == "__main__":
     uvicorn.run("mlc_chat.rest:app", host=ARGS.host, port=ARGS.port, reload=False, access_log=False)