cleanup: remove obsolete llm-ChatGLM2 and llm-Baichuan2 plugins (#6444)

These plugins provided OpenAI-compatible API wrappers for ChatGLM2 and
Baichuan2 models. Both are now obsolete:

- ChatGLM2 (2023) has been superseded by GLM-4 series with official
  OpenAI-compatible APIs
- Baichuan2 (2023) has been superseded by Baichuan 4 with official
  OpenAI-compatible APIs

FastGPT's model system already supports any OpenAI-compatible endpoint
via requestUrl/requestAuth configuration — no self-hosted wrapper needed.

Zero references to these plugins exist in the codebase.

plugins/model/llm-Baichuan2/openai_api.py

@@ -1,233 +0,0 @@
-# coding=utf-8
-# Implements API for Baichuan2-7B-Chat in OpenAI's format. (https://platform.openai.com/docs/api-reference/chat)
-# Usage: python openai_api.py
-
-import gc
-import time
-import torch
-import uvicorn
-from pydantic import BaseModel, Field, validator
-from fastapi import FastAPI, HTTPException
-from fastapi.middleware.cors import CORSMiddleware
-from contextlib import asynccontextmanager
-from typing import Any, Dict, List, Optional, Union
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from sse_starlette.sse import ServerSentEvent, EventSourceResponse
-from transformers.generation.utils import GenerationConfig
-import random
-import string
-
-
-@asynccontextmanager
-async def lifespan(app: FastAPI): # collects GPU memory
-    yield
-    if torch.cuda.is_available():
-        torch.cuda.empty_cache()
-        torch.cuda.ipc_collect()
-
-
-app = FastAPI(lifespan=lifespan)
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-class ModelCard(BaseModel):
-    id: str
-    object: str = "model"
-    created: int = Field(default_factory=lambda: int(time.time()))
-    owned_by: str = "owner"
-    root: Optional[str] = None
-    parent: Optional[str] = None
-    permission: Optional[list] = None
-
-class ModelList(BaseModel):
-    object: str = "list"
-    data: List[str] = []  # Assuming ModelCard is a string type. Replace with the correct type if not.
-
-class ChatMessage(BaseModel):
-    role: str
-    content: str
-
-    @validator('role')
-    def check_role(cls, v):
-        if v not in ["user", "assistant", "system"]:
-            raise ValueError('role must be one of "user", "assistant", "system"')
-        return v
-
-class DeltaMessage(BaseModel):
-    role: Optional[str] = None
-    content: Optional[str] = None
-
-    @validator('role', allow_reuse=True)
-    def check_role(cls, v):
-        if v is not None and v not in ["user", "assistant", "system"]:
-            raise ValueError('role must be one of "user", "assistant", "system"')
-        return v
-
-class ChatCompletionRequest(BaseModel):
-    model: str
-    messages: List[ChatMessage]
-    temperature: Optional[float] = None
-    top_p: Optional[float] = None
-    max_length: Optional[int] = 8192  # max_length should be an integer.
-    stream: Optional[bool] = False
-
-class ChatCompletionResponseChoice(BaseModel):
-    index: int
-    message: ChatMessage
-    finish_reason: str
-
-    @validator('finish_reason')
-    def check_finish_reason(cls, v):
-        if v not in ["stop", "length"]:
-            raise ValueError('finish_reason must be one of "stop" or "length"')
-        return v
-
-class ChatCompletionResponseStreamChoice(BaseModel):
-     index: int
-     delta: DeltaMessage
-     finish_reason: Optional[str]
-
-     @validator('finish_reason', allow_reuse=True)
-     def check_finish_reason(cls, v):
-         if v is not None and v not in ["stop", "length"]:
-             raise ValueError('finish_reason must be one of "stop" or "length"')
-         return v
-
-class ChatCompletionResponse(BaseModel):
-     id:str 
-     object:str 
-     
-     @validator('object')
-     def check_object(cls,v): 
-         if v not in ["chat.completion","chat.completion.chunk"]: 
-             raise ValueError("object must be one of 'chat.completion' or 'chat.completion.chunk'")
-         return v
-     
-     created :Optional[int]=Field(default_factory=lambda:int(time.time()))
-     model:str 
-     choices :List[Union[ChatCompletionResponseChoice,ChatCompletionResponseStreamChoice]]
-
-
-def generate_id():
-    possible_characters = string.ascii_letters + string.digits
-    random_string = ''.join(random.choices(possible_characters, k=29))
-    return 'chatcmpl-' + random_string
-    
-
-@app.get("/v1/models", response_model=ModelList)
-async def list_models():
-    global model_args
-    model_card = ModelCard(id="gpt-3.5-turbo")
-    return ModelList(data=[model_card])
-
-
-@app.post("/v1/chat/completions", response_model=ChatCompletionResponse)
-async def create_chat_completion(request: ChatCompletionRequest):
-    global model, tokenizer
-    if request.messages[-1].role != "user":
-        raise HTTPException(status_code=400, detail="Invalid request")
-    query = request.messages[-1].content
-    prev_messages = request.messages[:-1]
-    if len(prev_messages) > 0 and prev_messages[0].role == "system":
-        query = prev_messages.pop(0).content + query
-    messages = []
-    for message in prev_messages:
-        messages.append({"role": message.role, "content": message.content})
-    
-    messages.append({"role": "user", "content": query})
-    
-    if request.stream:
-        generate = predict(messages, request.model)
-        return EventSourceResponse(generate, media_type="text/event-stream")
-    
-    response = '本接口不支持非stream模式'
-    choice_data = ChatCompletionResponseChoice(
-        index=0,
-        message=ChatMessage(role="assistant", content=response),
-        finish_reason="stop"
-    )
-    id='chatcmpl-7QyqpwdfhqwajicIEznoc6Q47XAyW'
-
-    return ChatCompletionResponse(id=id,model=request.model, choices=[choice_data], object="chat.completion")
-
-
-async def predict(messages: List[List[str]], model_id: str):
-    global model, tokenizer
-    id = generate_id()
-    created = int(time.time())
-    choice_data = ChatCompletionResponseStreamChoice(
-        index=0,
-        delta=DeltaMessage(role="assistant",content=""),
-        finish_reason=None
-    )
-    chunk = ChatCompletionResponse(id=id,object="chat.completion.chunk",created=created,model=model_id, choices=[choice_data])
-    yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
-
-    current_length = 0
-
-    for new_response in model.chat(tokenizer, messages, stream=True):
-        if len(new_response) == current_length:
-            continue
-
-        new_text = new_response[current_length:]
-        current_length = len(new_response)
-
-        choice_data = ChatCompletionResponseStreamChoice(
-            index=0,
-            delta=DeltaMessage(content=new_text),
-            finish_reason=None
-        )
-        chunk = ChatCompletionResponse(id=id,object="chat.completion.chunk",created=created,model=model_id, choices=[choice_data])
-        yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
-
-
-    choice_data = ChatCompletionResponseStreamChoice(
-        index=0,
-        delta=DeltaMessage(),
-        finish_reason="stop"
-    )
-    chunk = ChatCompletionResponse(id=id,object="chat.completion.chunk",created=created,model=model_id, choices=[choice_data])
-    yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
-    yield '[DONE]'
-
-
-def load_models():
-    print("本次加载的大语言模型为: Baichuan-13B-Chat")
-    tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan2-7B-Chat", use_fast=False, trust_remote_code=True)
-    # model = AutoModelForCausalLM.from_pretrained("Baichuan2-13B-Chat", torch_dtype=torch.float32, trust_remote_code=True)
-    model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan2-7B-Chat", torch_dtype=torch.float16, trust_remote_code=True)
-    model = model.cuda() 
-    model.generation_config = GenerationConfig.from_pretrained("baichuan-inc/Baichuan2-7B-Chat") 
-    return tokenizer, model
-
-if __name__ == "__main__":
-    tokenizer, model = load_models()
-    uvicorn.run(app, host='0.0.0.0', port=6006, workers=1)
-
-    while True:
-        try:
-            # 在这里执行您的程序逻辑
-
-            # 检查显存使用情况，如果超过阈值（例如90%），则触发垃圾回收
-            if torch.cuda.is_available():
-                gpu_memory_usage = torch.cuda.memory_allocated() / torch.cuda.max_memory_allocated()
-                if gpu_memory_usage > 0.9:
-                    gc.collect()
-                    torch.cuda.empty_cache()
-        except RuntimeError as e:
-            if "out of memory" in str(e):
-                print("显存不足，正在重启程序...")
-                gc.collect()
-                torch.cuda.empty_cache()
-                time.sleep(5) # 等待一段时间以确保显存已释放
-                tokenizer, model = load_models()
-            else:
-                raise e
-
-    

plugins/model/llm-Baichuan2/requirements.txt

@@ -1,14 +0,0 @@
-protobuf
-transformers==4.53.0
-cpm_kernels
-torch>=2.0
-gradio
-mdtex2html
-sentencepiece
-accelerate
-sse-starlette
-fastapi==0.99.1
-pydantic==1.10.7
-uvicorn==0.21.1
-xformers
-bitsandbytes

plugins/model/llm-ChatGLM2/openai_api.py

@@ -1,260 +0,0 @@
-# coding=utf-8
-import argparse
-import time
-from contextlib import asynccontextmanager
-from typing import List, Literal, Optional, Union
-
-import numpy as np
-import tiktoken
-import torch
-import uvicorn
-from fastapi import Depends, FastAPI, HTTPException, Request
-from fastapi.middleware.cors import CORSMiddleware
-from pydantic import BaseModel, Field
-from sentence_transformers import SentenceTransformer
-from sklearn.preprocessing import PolynomialFeatures
-from sse_starlette.sse import EventSourceResponse
-from starlette.status import HTTP_401_UNAUTHORIZED
-from transformers import AutoModel, AutoTokenizer
-
-
-@asynccontextmanager
-async def lifespan(app: FastAPI):  # collects GPU memory
-    yield
-    if torch.cuda.is_available():
-        torch.cuda.empty_cache()
-        torch.cuda.ipc_collect()
-
-
-app = FastAPI(lifespan=lifespan)
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-
-class ChatMessage(BaseModel):
-    role: Literal["user", "assistant", "system"]
-    content: str
-
-
-class DeltaMessage(BaseModel):
-    role: Optional[Literal["user", "assistant", "system"]] = None
-    content: Optional[str] = None
-
-
-class ChatCompletionRequest(BaseModel):
-    model: str
-    messages: List[ChatMessage]
-    temperature: Optional[float] = None
-    top_p: Optional[float] = None
-    max_length: Optional[int] = None
-    stream: Optional[bool] = False
-
-
-class ChatCompletionResponseChoice(BaseModel):
-    index: int
-    message: ChatMessage
-    finish_reason: Literal["stop", "length"]
-
-
-class ChatCompletionResponseStreamChoice(BaseModel):
-    index: int
-    delta: DeltaMessage
-    finish_reason: Optional[Literal["stop", "length"]]
-
-
-class ChatCompletionResponse(BaseModel):
-    model: str
-    object: Literal["chat.completion", "chat.completion.chunk"]
-    choices: List[
-        Union[ChatCompletionResponseChoice, ChatCompletionResponseStreamChoice]
-    ]
-    created: Optional[int] = Field(default_factory=lambda: int(time.time()))
-
-
-async def verify_token(request: Request):
-    auth_header = request.headers.get('Authorization')
-    if auth_header:
-        token_type, _, token = auth_header.partition(' ')
-        if (
-            token_type.lower() == "bearer"
-            and token == "sk-aaabbbcccdddeeefffggghhhiiijjjkkk"
-        ):  # 这里配置你的token
-            return True
-    raise HTTPException(
-        status_code=HTTP_401_UNAUTHORIZED,
-        detail="Invalid authorization credentials",
-    )
-
-
-class EmbeddingRequest(BaseModel):
-    input: List[str]
-    model: str
-
-
-class EmbeddingResponse(BaseModel):
-    data: list
-    model: str
-    object: str
-    usage: dict
-
-
-def num_tokens_from_string(string: str) -> int:
-    """Returns the number of tokens in a text string."""
-    encoding = tiktoken.get_encoding('cl100k_base')
-    num_tokens = len(encoding.encode(string))
-    return num_tokens
-
-
-def expand_features(embedding, target_length):
-    poly = PolynomialFeatures(degree=2)
-    expanded_embedding = poly.fit_transform(embedding.reshape(1, -1))
-    expanded_embedding = expanded_embedding.flatten()
-    if len(expanded_embedding) > target_length:
-        # 如果扩展后的特征超过目标长度，可以通过截断或其他方法来减少维度
-        expanded_embedding = expanded_embedding[:target_length]
-    elif len(expanded_embedding) < target_length:
-        # 如果扩展后的特征少于目标长度，可以通过填充或其他方法来增加维度
-        expanded_embedding = np.pad(
-            expanded_embedding, (0, target_length - len(expanded_embedding))
-        )
-    return expanded_embedding
-
-
-@app.post("/v1/chat/completions", response_model=ChatCompletionResponse)
-async def create_chat_completion(
-    request: ChatCompletionRequest, token: bool = Depends(verify_token)
-):
-    global model, tokenizer
-
-    if request.messages[-1].role != "user":
-        raise HTTPException(status_code=400, detail="Invalid request")
-    query = request.messages[-1].content
-
-    prev_messages = request.messages[:-1]
-    if len(prev_messages) > 0 and prev_messages[0].role == "system":
-        query = prev_messages.pop(0).content + query
-
-    history = []
-    if len(prev_messages) % 2 == 0:
-        for i in range(0, len(prev_messages), 2):
-            if (
-                prev_messages[i].role == "user"
-                and prev_messages[i + 1].role == "assistant"
-            ):
-                history.append([prev_messages[i].content, prev_messages[i + 1].content])
-
-    if request.stream:
-        generate = predict(query, history, request.model)
-        return EventSourceResponse(generate, media_type="text/event-stream")
-
-    response, _ = model.chat(tokenizer, query, history=history)
-    choice_data = ChatCompletionResponseChoice(
-        index=0,
-        message=ChatMessage(role="assistant", content=response),
-        finish_reason="stop",
-    )
-
-    return ChatCompletionResponse(
-        model=request.model, choices=[choice_data], object="chat.completion"
-    )
-
-
-async def predict(query: str, history: List[List[str]], model_id: str):
-    global model, tokenizer
-
-    choice_data = ChatCompletionResponseStreamChoice(
-        index=0, delta=DeltaMessage(role="assistant"), finish_reason=None
-    )
-    chunk = ChatCompletionResponse(
-        model=model_id, choices=[choice_data], object="chat.completion.chunk"
-    )
-    yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
-
-    current_length = 0
-
-    for new_response, _ in model.stream_chat(tokenizer, query, history):
-        if len(new_response) == current_length:
-            continue
-
-        new_text = new_response[current_length:]
-        current_length = len(new_response)
-
-        choice_data = ChatCompletionResponseStreamChoice(
-            index=0, delta=DeltaMessage(content=new_text), finish_reason=None
-        )
-        chunk = ChatCompletionResponse(
-            model=model_id, choices=[choice_data], object="chat.completion.chunk"
-        )
-        yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
-
-    choice_data = ChatCompletionResponseStreamChoice(
-        index=0, delta=DeltaMessage(), finish_reason="stop"
-    )
-    chunk = ChatCompletionResponse(
-        model=model_id, choices=[choice_data], object="chat.completion.chunk"
-    )
-    yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
-    yield '[DONE]'
-
-
-@app.post("/v1/embeddings", response_model=EmbeddingResponse)
-async def get_embeddings(
-    request: EmbeddingRequest, token: bool = Depends(verify_token)
-):
-    # 计算嵌入向量和tokens数量
-    embeddings = [embeddings_model.encode(text) for text in request.input]
-
-    # 如果嵌入向量的维度不为1536，则使用插值法扩展至1536维度
-    embeddings = [
-        expand_features(embedding, 1536) if len(embedding) < 1536 else embedding
-        for embedding in embeddings
-    ]
-
-    # Min-Max normalization 归一化
-    embeddings = [embedding / np.linalg.norm(embedding) for embedding in embeddings]
-
-    # 将numpy数组转换为列表
-    embeddings = [embedding.tolist() for embedding in embeddings]
-    prompt_tokens = sum(len(text.split()) for text in request.input)
-    total_tokens = sum(num_tokens_from_string(text) for text in request.input)
-
-    response = {
-        "data": [
-            {"embedding": embedding, "index": index, "object": "embedding"}
-            for index, embedding in enumerate(embeddings)
-        ],
-        "model": request.model,
-        "object": "list",
-        "usage": {
-            "prompt_tokens": prompt_tokens,
-            "total_tokens": total_tokens,
-        },
-    }
-
-    return response
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--model_name", default="16", type=str, help="Model name")
-    args = parser.parse_args()
-
-    model_dict = {
-        "4": "THUDM/chatglm2-6b-int4",
-        "8": "THUDM/chatglm2-6b-int8",
-        "16": "THUDM/chatglm2-6b",
-    }
-
-    model_name = model_dict.get(args.model_name, "THUDM/chatglm2-6b")
-
-    tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
-    model = AutoModel.from_pretrained(model_name, trust_remote_code=True).cuda()
-    embeddings_model = SentenceTransformer('moka-ai/m3e-large', device='cpu')
-
-    uvicorn.run(app, host='0.0.0.0', port=6006, workers=1)

plugins/model/llm-ChatGLM2/requirements.txt

@@ -1,11 +0,0 @@
-fastapi==0.101.1
-numpy==1.24.3
-pydantic==1.10.7
-scikit_learn==1.2.2
-sentence_transformers==2.2.2
-sse_starlette==1.6.5
-starlette==0.49.1
-tiktoken==0.4.0
-torch==2.7.1
-transformers==4.53.0
-uvicorn==0.23.2