修改部分错误的文档，加长了历史记录（for 32k Models） (#1630)

* 更新上agent提示词代码 (#1626) * 修改部分错误的文档，加长了历史记录（for 32k Models） (#1629) * 更新上agent提示词代码 * 按需修改
chatchat-space · Sep 29, 2023 · e88d926 · e88d926
1 parent eb6f5cf
commit e88d926
Show file tree

Hide file tree

Showing 4 changed files with 40 additions and 33 deletions.
diff --git a/README.md b/README.md
@@ -167,6 +167,9 @@ 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 +277,20 @@ $ 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 +353,7 @@ $ python startup.py --all-webui --model-name Qwen-7B-Chat
 
 ```python
 gpus=None, 
-num_gpus=1, 
+num_gpus= 1, 
 max_gpu_memory="20GiB"
 ```
 

diff --git a/README_en.md b/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

diff --git a/configs/model_config.py.example b/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",

diff --git a/webui_pages/dialogue/dialogue.py b/webui_pages/dialogue/dialogue.py
@@ -101,8 +101,10 @@ def llm_model_format_func(x):
                     st.success(msg)
                     st.session_state["prev_llm_model"] = llm_model
 
-        temperature = st.slider("Temperature：", 0.0, 1.0, TEMPERATURE, 0.05)
-        history_len = st.number_input("历史对话轮数：", 0, 10, HISTORY_LEN)
+        temperature = st.slider("Temperature：", 0.0, 1.0, TEMPERATURE, 0.01)
+
+        ## 部分模型可以超过10抡对话
+        history_len = st.number_input("历史对话轮数：", 0, 20, HISTORY_LEN)
 
         def on_kb_change():
             st.toast(f"已加载知识库： {st.session_state.selected_kb}")
@@ -117,7 +119,10 @@ def on_kb_change():
                     key="selected_kb",
                 )
                 kb_top_k = st.number_input("匹配知识条数：", 1, 20, VECTOR_SEARCH_TOP_K)
+
+                ## Bge 模型会超过1
                 score_threshold = st.slider("知识匹配分数阈值：", 0.0, 1.0, float(SCORE_THRESHOLD), 0.01)
+
                 # chunk_content = st.checkbox("关联上下文", False, disabled=True)
                 # chunk_size = st.slider("关联长度：", 0, 500, 250, disabled=True)
         elif dialogue_mode == "搜索引擎问答":