release 0.2.6

README.md

@@ -167,6 +167,10 @@ docker run -d --gpus all -p 80:8501 registry.cn-beijing.aliyuncs.com/chatchat/ch
 - [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh)
 - [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh)
 - [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh)
+- [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5)
+- [BAAI/bge-large-zh-v1.5](https://huggingface.co/BAAI/bge-large-zh-v1.5)
+- [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5)
+- [BAAI/bge-large-zh-v1.5](https://huggingface.co/BAAI/bge-large-zh-v1.5)
 - [BAAI/bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct)
 - [sensenova/piccolo-base-zh](https://huggingface.co/sensenova/piccolo-base-zh)
 - [sensenova/piccolo-large-zh](https://huggingface.co/sensenova/piccolo-large-zh)
@@ -274,28 +278,20 @@ $ git clone https://huggingface.co/moka-ai/m3e-base
 在开始执行 Web UI 或命令行交互前，请先检查 [configs/model_config.py](configs/model_config.py) 和 [configs/server_config.py](configs/server_config.py) 中的各项模型参数设计是否符合需求：
 
 - 请确认已下载至本地的 LLM 模型本地存储路径写在 `llm_model_dict` 对应模型的 `local_model_path` 属性中，如:
+```
+"chatglm2-6b": "/Users/xxx/Downloads/chatglm2-6b",
 
-```python
-llm_model_dict={
-                "chatglm2-6b": {
-                        "local_model_path": "/Users/xxx/Downloads/chatglm2-6b",
-                        "api_base_url": "http://localhost:8888/v1",  # "name"修改为 FastChat 服务中的"api_base_url"
-                        "api_key": "EMPTY"
-                    },
-                }
 ```
 
 - 请确认已下载至本地的 Embedding 模型本地存储路径写在 `embedding_model_dict` 对应模型位置，如：
 
-```python
-embedding_model_dict = {
-                        "m3e-base": "/Users/xxx/Downloads/m3e-base",
-                       }
+```
+"m3e-base": "/Users/xxx/Downloads/m3e-base",
 ```
 
 - 请确认本地分词器路径是否已经填写，如：
 
-```python
+```
 text_splitter_dict = {
     "ChineseRecursiveTextSplitter": {
         "source": "huggingface",  ## 选择tiktoken则使用openai的方法,不填写则默认为字符长度切割方法。
@@ -358,7 +354,7 @@ $ python startup.py --all-webui --model-name Qwen-7B-Chat
 
 ```python
 gpus=None, 
-num_gpus=1, 
+num_gpus= 1, 
 max_gpu_memory="20GiB"
 ```
 

README_en.md

@@ -160,6 +160,8 @@ Following models are tested by developers with Embedding class of [HuggingFace](
 - [moka-ai/m3e-large](https://huggingface.co/moka-ai/m3e-large)
 - [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh)
 - [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh)
+- [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5)
+- [BAAI/bge-large-zh-v1.5](https://huggingface.co/BAAI/bge-large-zh-v1.5)
 - [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh)
 - [BAAI/bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct)
 - [sensenova/piccolo-base-zh](https://huggingface.co/sensenova/piccolo-base-zh)
@@ -228,30 +230,33 @@ $ git clone https://huggingface.co/moka-ai/m3e-base
 ```
 
 ### 3. Setting Configuration
+Copy the model-related parameter configuration template file [configs/model_config.py.example](configs/model_config.py.example) and store it under the project path `. /configs` path and rename it `model_config.py`.
 
-Copy the model-related parameter configuration template file [configs/model_config.py.example](configs/model_config.py.example) and save it in the `./configs` path under the project path, and rename it to `model_config.py`.
+Copy the service-related parameter configuration template file [configs/server_config.py.example](configs/server_config.py.example) and store it under the project path `. /configs` path and rename it `server_config.py`.
 
-Copy the service-related parameter configuration template file [configs/server_config.py.example](configs/server_config.py.example) to save in the `./configs` path under the project path, and rename it to `server_config.py`.
+Before you start executing the Web UI or command line interactions, check that each of the items in [configs/model_config.py](configs/model_config.py) and [configs/server_config.py](configs/server_config.py) The model parameters are designed to meet the requirements:
 
-Before starting to execute Web UI or command line interaction, please check whether each model parameter in `configs/model_config.py` and `configs/server_config.py` meets the requirements.
+- Please make sure that the local storage path of the downloaded LLM model is written in the `local_model_path` attribute of the corresponding model in `llm_model_dict`, e.g..
+```
+"chatglm2-6b":"/Users/xxx/Downloads/chatglm2-6b",
+
+```
 
-* Please confirm that the path to local LLM model and embedding model have been written in `llm_dict` of `configs/model_config.py`, here is an example:
-* If you choose to use OpenAI's Embedding model, please write the model's ``key`` into `embedding_model_dict`. To use this model, you need to be able to access the OpenAI official API, or set up a proxy.
+- Please make sure that the local storage path of the downloaded Embedding model is written in `embedding_model_dict` corresponding to the model location, e.g.:
 
-```python
-llm_model_dict={
-                "chatglm2-6b": {
-                        "local_model_path": "/Users/xxx/Downloads/chatglm2-6b",
-                        "api_base_url": "http://localhost:8888/v1",  # "name"修改为 FastChat 服务中的"api_base_url"
-                        "api_key": "EMPTY"
-                    },
-                }
+```
+"m3e-base":"/Users/xxx/Downloads/m3e-base", ``` Please make sure that the local storage path of the downloaded Embedding model is written in the location of the corresponding model, e.g.
 ```
 
-```python
-embedding_model_dict = {
-                        "m3e-base": "/Users/xxx/Downloads/m3e-base",
-                       }
+- Please make sure that the local participle path is filled in, e.g.:
+
+```
+text_splitter_dict = {
+    "ChineseRecursiveTextSplitter": {
+        "source": "huggingface", ## Select tiktoken to use openai's method, don't fill it in then it defaults to character length cutting method.
+        "tokenizer_name_or_path": "", ## Leave blank to use the big model of the tokeniser. 
+    }
+}
 ```
 
 ### 4. Knowledge Base Migration

configs/__init__.py

@@ -5,4 +5,4 @@
 from .prompt_config import *
 
 
-VERSION = "v0.2.5-preview"
+VERSION = "v0.2.6-preview"

configs/kb_config.py.exmaple → configs/kb_config.py.example

@@ -1,7 +1,7 @@
 import os
 
 
-# 默认向量库类型。可选：faiss, milvus, pg.
+# 默认向量库类型。可选：faiss, milvus(离线) & zilliz(在线), pg.
 DEFAULT_VS_TYPE = "faiss"
 
 # 缓存向量库数量（针对FAISS）
@@ -42,13 +42,17 @@ BING_SUBSCRIPTION_KEY = ""
 ZH_TITLE_ENHANCE = False
 
 
-# 通常情况下不需要更改以下内容
+# 每个知识库的初始化介绍，用于在初始化知识库时显示和Agent调用，没写则没有介绍，不会被Agent调用。
+KB_INFO = {
+    "知识库名称": "知识库介绍",
+    "samples": "关于本项目issue的解答",
+}
 
+# 通常情况下不需要更改以下内容
 # 知识库默认存储路径
 KB_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "knowledge_base")
 if not os.path.exists(KB_ROOT_PATH):
     os.mkdir(KB_ROOT_PATH)
-
 # 数据库默认存储路径。
 # 如果使用sqlite，可以直接修改DB_ROOT_PATH；如果使用其它数据库，请直接修改SQLALCHEMY_DATABASE_URI。
 DB_ROOT_PATH = os.path.join(KB_ROOT_PATH, "info.db")
@@ -65,6 +69,13 @@ kbs_config = {
         "password": "",
         "secure": False,
     },
+    "zilliz": {
+        "host": "in01-a7ce524e41e3935.ali-cn-hangzhou.vectordb.zilliz.com.cn",
+        "port": "19530",
+        "user": "",
+        "password": "",
+        "secure": True,
+        },
     "pg": {
         "connection_uri": "postgresql://postgres:postgres@127.0.0.1:5432/langchain_chatchat",
     }
@@ -74,11 +85,11 @@ kbs_config = {
 text_splitter_dict = {
     "ChineseRecursiveTextSplitter": {
         "source": "huggingface",  ## 选择tiktoken则使用openai的方法
-        "tokenizer_name_or_path": "gpt2",
+        "tokenizer_name_or_path": "",
     },
     "SpacyTextSplitter": {
         "source": "huggingface",
-        "tokenizer_name_or_path": "",
+        "tokenizer_name_or_path": "gpt2",
     },
     "RecursiveCharacterTextSplitter": {
         "source": "tiktoken",

configs/model_config.py.example

@@ -30,6 +30,8 @@ MODEL_PATH = {
         "bge-base-zh": "BAAI/bge-base-zh",
         "bge-large-zh": "BAAI/bge-large-zh",
         "bge-large-zh-noinstruct": "BAAI/bge-large-zh-noinstruct",
+        "bge-base-zh-v1.5": "BAAI/bge-base-zh-v1.5",
+        "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",
         "text-embedding-ada-002": "your OPENAI_API_KEY",

configs/prompt_config.py.example

@@ -9,15 +9,106 @@
 #   - context: 从检索结果拼接的知识文本
 #   - question: 用户提出的问题
 
+# Agent对话支持的变量：
 
-PROMPT_TEMPLATES = {
-    # LLM对话模板
-    "llm_chat": "{{ input }}",
+#   - tools: 可用的工具列表
+#   - tool_names: 可用的工具名称列表
+#   - history: 用户和Agent的对话历史
+#   - input: 用户输入内容
+#   - agent_scratchpad: Agent的思维记录
+
+PROMPT_TEMPLATES = {}
+
+PROMPT_TEMPLATES["llm_chat"] = {
+    "default": "{{ input }}",
+
+    "py":
+    """
+    你是一个聪明的代码助手，请你给我写出简单的py代码。 \n
+    {{ input }}
+    """
+    ,
+}
+
+PROMPT_TEMPLATES["knowledge_base_chat"] = {
+    "default":
+        """
+        <指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，不允许在答案中添加编造成分，答案请使用中文。 </指令>
+        <已知信息>{{ context }}</已知信息>、
+        <问题>{{ question }}</问题>
+        """,
+    "text":
+        """
+        <指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，答案请使用中文。 </指令>
+        <已知信息>{{ context }}</已知信息>、
+        <问题>{{ question }}</问题>
+        """,
+}
+PROMPT_TEMPLATES["search_engine_chat"] = {
+    "default":
+        """
+            <指令>这是我搜索到的互联网信息，请你根据这些信息进行提取并有调理，简洁的回答问题。如果无法从中得到答案，请说 “无法搜索到能回答问题的内容”。 </指令>
+            <已知信息>{{ context }}</已知信息>、
+            <问题>{{ question }}</问题>
+            """,
+
+    "search":
+        """
+        <指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，答案请使用中文。 </指令>
+        <已知信息>{{ context }}</已知信息>、
+        <问题>{{ question }}</问题>
+        """,
+}
+PROMPT_TEMPLATES["agent_chat"] = {
+    "default":
+        """
+        Answer the following questions as best you can. If it is in order, you can use some tools appropriately.You have access to the following tools:
+
+        {tools}
+
+        Please note that the "知识库查询工具" is information about the "西交利物浦大学" ,and if a question is asked about it, you must answer with the knowledge base，
+        Please note that the "天气查询工具" can only be used once since Question begin.
+
+        Use the following format:
+        Question: the input question you must answer1
+        Thought: you should always think about what to do and what tools to use.
+        Action: the action to take, should be one of [{tool_names}]
+        Action Input: the input to the action
+        Observation: the result of the action
+        ... (this Thought/Action/Action Input/Observation can be repeated zero or more times)
+        Thought: I now know the final answer
+        Final Answer: the final answer to the original input question
+
+
+        Begin!
+        history:
+        {history}
+        Question: {input}
+        Thought: {agent_scratchpad}
+        """,
+    "ChatGLM":
+        """
+        请请严格按照提供的思维方式来思考。你的知识不一定正确，所以你一定要用提供的工具来思考，并给出用户答案。
+        你有以下工具可以使用:
+        {tools}
+        ```
+        Question: 用户的提问或者观察到的信息，
+        Thought: 你应该思考该做什么，是根据工具的结果来回答问题，还是决定使用什么工具。
+        Action: 需要使用的工具，应该是在[{tool_names}]中的一个。
+        Action Input: 传入工具的内容
+        Observation: 工具给出的答案（不是你生成的）
+        ... (this Thought/Action/Action Input/Observation can be repeated zero or more times)
+        Thought: 通过工具给出的答案，你是否能回答Question。
+        Final Answer是你的答案
 
-    # 基于本地知识问答的提示词模
-    "knowledge_base_chat": """<指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，不允许在答案中添加编造成分，答案请使用中文。 </指令>
+        现在，我们开始！
+        你和用户的历史记录:
+        History:
+        {history}
 
-<已知信息>{{ context }}</已知信息>
+        用户开始以提问：
+        Question: {input}
+        Thought: {agent_scratchpad}
 
-<问题>{{ question }}</问题>""",
+        """,
 }

configs/server_config.py.example

@@ -32,14 +32,16 @@ FSCHAT_OPENAI_API = {
 # fastchat model_worker server
 # 这些模型必须是在model_config.MODEL_PATH或ONLINE_MODEL中正确配置的。
 # 在启动startup.py时，可用通过`--model-worker --model-name xxxx`指定模型，不指定则为LLM_MODEL
+# 必须在这里添加的模型才会出现在WEBUI中可选模型列表里（LLM_MODEL会自动添加）
 FSCHAT_MODEL_WORKERS = {
     # 所有模型共用的默认配置，可在模型专项配置中进行覆盖。
     "default": {
         "host": DEFAULT_BIND_HOST,
         "port": 20002,
         "device": LLM_DEVICE,
         # False,'vllm',使用的推理加速框架,使用vllm如果出现HuggingFace通信问题，参见doc/FAQ
-        "infer_turbo": "vllm" if sys.platform.startswith("linux") else False,
+        # vllm对一些模型支持还不成熟，暂时默认关闭
+        "infer_turbo": False,
 
         # model_worker多卡加载需要配置的参数
         # "gpus": None, # 使用的GPU，以str的格式指定，如"0,1"，如失效请使用CUDA_VISIBLE_DEVICES="0,1"等形式指定
@@ -97,21 +99,24 @@ FSCHAT_MODEL_WORKERS = {
     "zhipu-api": { # 请为每个要运行的在线API设置不同的端口
         "port": 21001,
     },
-    "minimax-api": {
-        "port": 21002,
-    },
-    "xinghuo-api": {
-        "port": 21003,
-    },
-    "qianfan-api": {
-        "port": 21004,
-    },
-    "fangzhou-api": {
-        "port": 21005,
-    },
-    "qwen-api": {
-        "port": 21006,
-    },
+    # "minimax-api": {
+    #     "port": 21002,
+    # },
+    # "xinghuo-api": {
+    #     "port": 21003,
+    # },
+    # "qianfan-api": {
+    #     "port": 21004,
+    # },
+    # "fangzhou-api": {
+    #     "port": 21005,
+    # },
+    # "qwen-api": {
+    #     "port": 21006,
+    # },
+    # "baichuan-api": {
+    #     "port": 21007,
+    # },
 }
 
 # fastchat multi model worker server

requirements.txt

@@ -1,31 +1,32 @@
-langchain>=0.0.302
-fschat[model_worker]==0.2.29
+langchain>=0.0.314
+langchain-experimental>=0.0.30
+fschat[model_worker]==0.2.30
 openai
 sentence_transformers
-transformers>=4.33.0
-torch>=2.0.1
+transformers>=4.34
+torch>=2.0.1 # 推荐2.1
 torchvision
 torchaudio
-fastapi>=0.103.1
+fastapi>=0.103.2
 nltk~=3.8.1
 uvicorn~=0.23.1
 starlette~=0.27.0
 pydantic~=1.10.11
-unstructured[all-docs]>=0.10.4
+unstructured[all-docs]>=0.10.12
 python-magic-bin; sys_platform == 'win32'
 SQLAlchemy==2.0.19
 faiss-cpu
 accelerate
 spacy
-PyMuPDF==1.22.5
-rapidocr_onnxruntime>=1.3.2
+PyMuPDF
+rapidocr_onnxruntime
 
 requests
 pathlib
 pytest
 scikit-learn
 numexpr
-vllm==0.1.7; sys_platform == "linux"
+vllm>=0.2.0; sys_platform == "linux"
 # online api libs
 # zhipuai
 # dashscope>=1.10.0 # qwen