diff --git a/configs/model_config.py.example b/configs/model_config.py.example index cac02b8..e08b5a0 100644 --- a/configs/model_config.py.example +++ b/configs/model_config.py.example @@ -1,13 +1,12 @@ import os - # 可以指定一个绝对路径，统一存放所有的Embedding和LLM模型。 # 每个模型可以是一个单独的目录，也可以是某个目录下的二级子目录。 # 如果模型目录名称和 MODEL_PATH 中的 key 或 value 相同，程序会自动检测加载，无需修改 MODEL_PATH 中的路径。 MODEL_ROOT_PATH = "" # 选用的 Embedding 名称 -EMBEDDING_MODEL = "m3e-base" # bge-large-zh +EMBEDDING_MODEL = "bge-large-zh" # Embedding 模型运行设备。设为"auto"会自动检测，也可手动设定为"cuda","mps","cpu"其中之一。 EMBEDDING_DEVICE = "auto" @@ -18,7 +17,7 @@ EMBEDDING_MODEL_OUTPUT_PATH = "output" # 要运行的 LLM 名称，可以包括本地模型和在线模型。 # 第一个将作为 API 和 WEBUI 的默认模型 -LLM_MODELS = ["chatglm2-6b", "zhipu-api", "openai-api"] +LLM_MODELS = ["chatglm3-6b", "zhipu-api", "openai-api"] # AgentLM模型的名称 (可以不指定，指定之后就锁定进入Agent之后的Chain的模型，不指定就是LLM_MODELS[0]) Agent_MODEL = None @@ -153,6 +152,7 @@ MODEL_PATH = { "bge-large-zh-v1.5": "BAAI/bge-large-zh-v1.5", "piccolo-base-zh": "sensenova/piccolo-base-zh", "piccolo-large-zh": "sensenova/piccolo-large-zh", + "nlp_gte_sentence-embedding_chinese-large": "damo/nlp_gte_sentence-embedding_chinese-large", "text-embedding-ada-002": "your OPENAI_API_KEY", }, @@ -169,7 +169,7 @@ MODEL_PATH = { "baichuan-7b": "baichuan-inc/Baichuan-7B", "baichuan-13b": "baichuan-inc/Baichuan-13B", - 'baichuan-13b-chat': 'baichuan-inc/Baichuan-13B-Chat', + "baichuan-13b-chat": "baichuan-inc/Baichuan-13B-Chat", "aquila-7b": "BAAI/Aquila-7B", "aquilachat-7b": "BAAI/AquilaChat-7B", @@ -210,6 +210,12 @@ MODEL_PATH = { "Qwen-14B-Chat": "Qwen/Qwen-14B-Chat", "Qwen-14B-Chat-Int8": "Qwen/Qwen-14B-Chat-Int8", # 确保已经安装了auto-gptq optimum flash-attn "Qwen-14B-Chat-Int4": "Qwen/Qwen-14B-Chat-Int4", # 确保已经安装了auto-gptq optimum flash-attn + + "agentlm-7b": "THUDM/agentlm-7b", + "agentlm-13b": "THUDM/agentlm-13b", + "agentlm-70b": "THUDM/agentlm-70b", + + "Yi-34B-Chat": "https://huggingface.co/01-ai/Yi-34B-Chat", # 更多01-ai模型尚未进行测试。如果需要使用，请自行测试。 }, } @@ -225,7 +231,16 @@ VLLM_MODEL_DICT = { "baichuan-7b": "baichuan-inc/Baichuan-7B", "baichuan-13b": "baichuan-inc/Baichuan-13B", - 'baichuan-13b-chat': 'baichuan-inc/Baichuan-13B-Chat', + "baichuan-13b-chat": "baichuan-inc/Baichuan-13B-Chat", + + "chatglm2-6b": "THUDM/chatglm2-6b", + "chatglm2-6b-32k": "THUDM/chatglm2-6b-32k", + "chatglm3-6b": "THUDM/chatglm3-6b", + "chatglm3-6b-32k": "THUDM/chatglm3-6b-32k", + + "BlueLM-7B-Chat": "vivo-ai/BlueLM-7B-Chat", + "BlueLM-7B-Chat-32k": "vivo-ai/BlueLM-7B-Chat-32k", + # 注意：bloom系列的tokenizer与model是分离的，因此虽然vllm支持，但与fschat框架不兼容 # "bloom":"bigscience/bloom", # "bloomz":"bigscience/bloomz", diff --git a/configs/server_config.py.example b/configs/server_config.py.example index b68637b..8de6b07 100644 --- a/configs/server_config.py.example +++ b/configs/server_config.py.example @@ -91,9 +91,12 @@ FSCHAT_MODEL_WORKERS = { }, # 可以如下示例方式更改默认配置 - # "baichuan-7b": { # 使用default中的IP和端口 + # "Qwen-7B-Chat": { # 使用default中的IP和端口 # "device": "cpu", # }, + "chatglm3-6b": { # 使用default中的IP和端口 + "device": "cuda", + }, #以下配置可以不用修改，在model_config中设置启动的模型 "zhipu-api": { diff --git a/requirements.txt b/requirements.txt index ea4f893..ac18c33 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,21 +1,21 @@ # API requirements langchain>=0.0.334 -langchain-experimental>=0.0.30 -fschat[model_worker]==0.2.32 -xformers>=0.0.22.post4 -openai>=0.28.1 +langchain-experimental>=0.0.42 +fschat[model_worker]>=0.2.33 +xformers>=0.0.22.post7 +openai~=0.28.1 sentence_transformers -transformers>=4.34 -torch>=2.0.1 # suggest version 2.1 +transformers>=4.35.2 +torch==2.1.0 torchvision torchaudio fastapi>=0.104 nltk>=3.8.1 uvicorn~=0.23.1 starlette~=0.27.0 -pydantic~=1.10.11 -unstructured[all-docs]>=0.10.12 +pydantic<2 +unstructured[all-docs]>=0.11.0 python-magic-bin; sys_platform == 'win32' SQLAlchemy==2.0.19 faiss-cpu @@ -38,13 +38,14 @@ pandas~=2.0.3 einops transformers_stream_generator==0.0.4 -vllm>=0.2.0; sys_platform == "linux" +vllm==0.2.2; sys_platform == "linux" -# online api libs -# zhipuai -# dashscope>=1.10.0 # qwen -# qianfan -# volcengine>=1.0.106 # fangzhou +# online api libs dependencies + +# zhipuai>=1.0.7 +# dashscope>=1.10.0 +# qianfan>=0.2.0 +# volcengine>=1.0.106 # uncomment libs if you want to use corresponding vector store # pymilvus==2.1.3 # requires milvus==2.1.3 @@ -53,10 +54,10 @@ vllm>=0.2.0; sys_platform == "linux" # WebUI requirements -streamlit~=1.28.1 +streamlit~=1.28.2 streamlit-option-menu>=0.3.6 -streamlit-antd-components>=0.1.11 +streamlit-antd-components>=0.2.3 streamlit-chatbox>=1.1.11 streamlit-aggrid>=0.3.4.post3 -httpx~=0.24.0 +httpx[brotli,http2,socks]~=0.24.1 watchdog diff --git a/requirements_api.txt b/requirements_api.txt index c97fb57..85b2307 100644 --- a/requirements_api.txt +++ b/requirements_api.txt @@ -1,25 +1,25 @@ # API requirements -langchain>=0.0.334 -langchain-experimental>=0.0.30 -fschat[model_worker]==0.2.32 -xformers>=0.0.22.post4 -openai>=0.28.1 +langchain>=0.0.334 +langchain-experimental>=0.0.42 +fschat[model_worker]>=0.2.33 +xformers>=0.0.22.post7 +openai~=0.28.1 sentence_transformers -transformers>=4.34 -torch>=2.0.1 # suggest version 2.1 +transformers>=4.35.2 +torch==2.1.0 torchvision torchaudio fastapi>=0.104 nltk>=3.8.1 uvicorn~=0.23.1 starlette~=0.27.0 -pydantic~=1.10.11 -unstructured[all-docs]>=0.10.12 +pydantic<2 +unstructured[all-docs]>=0.11.0 python-magic-bin; sys_platform == 'win32' SQLAlchemy==2.0.19 faiss-cpu -accelerate +accelerate>=0.24.1 spacy PyMuPDF rapidocr_onnxruntime @@ -36,7 +36,7 @@ websockets numpy~=1.24.4 pandas~=2.0.3 einops -transformers_stream_generator==0.0.4 +transformers_stream_generator>=0.0.4 vllm>=0.2.0; sys_platform == "linux" diff --git a/requirements_webui.txt b/requirements_webui.txt index 39605bb..0fe3dc8 100644 --- a/requirements_webui.txt +++ b/requirements_webui.txt @@ -1,9 +1,10 @@ # WebUI requirements -streamlit~=1.28.1 +streamlit~=1.28.2 streamlit-option-menu>=0.3.6 -streamlit-antd-components>=0.1.11 +streamlit-antd-components>=0.2.3 streamlit-chatbox>=1.1.11 streamlit-aggrid>=0.3.4.post3 -httpx[brotli,http2,socks]>=0.25.0 +httpx[brotli,http2,socks]~=0.24.1 watchdog + diff --git a/server/knowledge_base/utils.py b/server/knowledge_base/utils.py index f3781a2..d5587ea 100644 --- a/server/knowledge_base/utils.py +++ b/server/knowledge_base/utils.py @@ -51,25 +51,35 @@ def list_kbs_from_folder(): def list_files_from_folder(kb_name: str): - def is_skiped_path(path: str): # 跳过 [temp, tmp, ., ~$] 开头的目录和文件 - tail = os.path.basename(path).lower() - flag = False - for x in ["temp", "tmp", ".", "~$"]: - if tail.startswith(x): - flag = True - break - return flag - doc_path = get_doc_path(kb_name) result = [] - for root, _, files in os.walk(doc_path): - if is_skiped_path(root): - continue - for file in files: - if is_skiped_path(file): - continue - path = Path(doc_path) / root / file - result.append(path.resolve().relative_to(doc_path).as_posix()) + + def is_skiped_path(path: str): + tail = os.path.basename(path).lower() + for x in ["temp", "tmp", ".", "~$"]: + if tail.startswith(x): + return True + return False + + def process_entry(entry): + if is_skiped_path(entry.path): + return + + if entry.is_symlink(): + target_path = os.path.realpath(entry.path) + with os.scandir(target_path) as target_it: + for target_entry in target_it: + process_entry(target_entry) + elif entry.is_file(): + result.append(entry.path) + elif entry.is_dir(): + with os.scandir(entry.path) as it: + for sub_entry in it: + process_entry(sub_entry) + + with os.scandir(doc_path) as it: + for entry in it: + process_entry(entry) return result