275 lines
12 KiB
Python
275 lines
12 KiB
Python
import streamlit as st
|
||
from webui_pages.utils import *
|
||
from streamlit_chatbox import *
|
||
from datetime import datetime
|
||
import os
|
||
from configs import LLM_MODEL, TEMPERATURE, HISTORY_LEN
|
||
from typing import List, Dict
|
||
|
||
|
||
chat_box = ChatBox(
|
||
assistant_avatar=os.path.join(
|
||
"img",
|
||
"chatchat_icon_blue_square_v2.png"
|
||
)
|
||
)
|
||
|
||
|
||
def get_messages_history(history_len: int, content_in_expander: bool = False) -> List[Dict]:
|
||
'''
|
||
返回消息历史。
|
||
content_in_expander控制是否返回expander元素中的内容，一般导出的时候可以选上，传入LLM的history不需要
|
||
'''
|
||
|
||
def filter(msg):
|
||
content = [x for x in msg["elements"] if x._output_method in ["markdown", "text"]]
|
||
if not content_in_expander:
|
||
content = [x for x in content if not x._in_expander]
|
||
content = [x.content for x in content]
|
||
|
||
return {
|
||
"role": msg["role"],
|
||
"content": "\n\n".join(content),
|
||
}
|
||
|
||
return chat_box.filter_history(history_len=history_len, filter=filter)
|
||
|
||
|
||
def get_default_llm_model(api: ApiRequest) -> (str, bool):
|
||
'''
|
||
从服务器上获取当前运行的LLM模型，如果本机配置的LLM_MODEL属于本地模型且在其中，则优先返回
|
||
返回类型为（model_name, is_local_model）
|
||
'''
|
||
running_models = api.list_running_models()
|
||
|
||
if not running_models:
|
||
return "", False
|
||
|
||
if LLM_MODEL in running_models:
|
||
return LLM_MODEL, True
|
||
|
||
local_models = [k for k, v in running_models.items() if not v.get("online_api")]
|
||
if local_models:
|
||
return local_models[0], True
|
||
|
||
return running_models[0], False
|
||
|
||
|
||
def dialogue_page(api: ApiRequest):
|
||
chat_box.init_session()
|
||
|
||
with st.sidebar:
|
||
# TODO: 对话模型与会话绑定
|
||
def on_mode_change():
|
||
mode = st.session_state.dialogue_mode
|
||
text = f"已切换到 {mode} 模式。"
|
||
if mode == "知识库问答":
|
||
cur_kb = st.session_state.get("selected_kb")
|
||
if cur_kb:
|
||
text = f"{text} 当前知识库： `{cur_kb}`。"
|
||
st.toast(text)
|
||
|
||
dialogue_mode = st.selectbox("请选择对话模式：",
|
||
["LLM 对话",
|
||
"知识库问答",
|
||
"搜索引擎问答",
|
||
"自定义Agent问答",
|
||
],
|
||
index=3,
|
||
on_change=on_mode_change,
|
||
key="dialogue_mode",
|
||
)
|
||
|
||
def on_llm_change():
|
||
config = api.get_model_config(llm_model)
|
||
if not config.get("online_api"): # 只有本地model_worker可以切换模型
|
||
st.session_state["prev_llm_model"] = llm_model
|
||
st.session_state["cur_llm_model"] = st.session_state.llm_model
|
||
|
||
def llm_model_format_func(x):
|
||
if x in running_models:
|
||
return f"{x} (Running)"
|
||
return x
|
||
|
||
running_models = list(api.list_running_models())
|
||
available_models = []
|
||
config_models = api.list_config_models()
|
||
worker_models = list(config_models.get("worker", {})) # 仅列出在FSCHAT_MODEL_WORKERS中配置的模型
|
||
for m in worker_models:
|
||
if m not in running_models and m != "default":
|
||
available_models.append(m)
|
||
for k, v in config_models.get("online", {}).items(): # 列出ONLINE_MODELS中直接访问的模型（如GPT）
|
||
if not v.get("provider") and k not in running_models:
|
||
print(k, v)
|
||
available_models.append(k)
|
||
|
||
llm_models = running_models + available_models
|
||
index = llm_models.index(st.session_state.get("cur_llm_model", get_default_llm_model(api)[0]))
|
||
llm_model = st.selectbox("选择LLM模型：",
|
||
llm_models,
|
||
index,
|
||
format_func=llm_model_format_func,
|
||
on_change=on_llm_change,
|
||
key="llm_model",
|
||
)
|
||
if (st.session_state.get("prev_llm_model") != llm_model
|
||
and not api.get_model_config(llm_model).get("online_api")
|
||
and llm_model not in running_models):
|
||
with st.spinner(f"正在加载模型： {llm_model}，请勿进行操作或刷新页面"):
|
||
prev_model = st.session_state.get("prev_llm_model")
|
||
r = api.change_llm_model(prev_model, llm_model)
|
||
if msg := check_error_msg(r):
|
||
st.error(msg)
|
||
elif msg := check_success_msg(r):
|
||
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, 20, HISTORY_LEN)
|
||
LLM_MODEL_WEBUI = llm_model
|
||
TEMPERATURE_WEBUI = temperature
|
||
|
||
def on_kb_change():
|
||
st.toast(f"已加载知识库： {st.session_state.selected_kb}")
|
||
|
||
if dialogue_mode == "知识库问答":
|
||
with st.expander("知识库配置", True):
|
||
kb_list = api.list_knowledge_bases()
|
||
selected_kb = st.selectbox(
|
||
"请选择知识库：",
|
||
kb_list,
|
||
on_change=on_kb_change,
|
||
key="selected_kb",
|
||
)
|
||
kb_top_k = st.number_input("匹配知识条数：", 1, 20, VECTOR_SEARCH_TOP_K)
|
||
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":
|
||
search_engine_list = api.list_search_engines()
|
||
with st.expander("搜索引擎配置", True):
|
||
search_engine = st.selectbox(
|
||
label="请选择搜索引擎",
|
||
options=search_engine_list,
|
||
index=search_engine_list.index("duckduckgo") if "duckduckgo" in search_engine_list else 0,
|
||
)
|
||
se_top_k = st.number_input("匹配搜索结果条数：", 1, 20, SEARCH_ENGINE_TOP_K)
|
||
|
||
# Display chat messages from history on app rerun
|
||
|
||
chat_box.output_messages()
|
||
|
||
chat_input_placeholder = "请输入对话内容，换行请使用Shift+Enter "
|
||
|
||
if prompt := st.chat_input(chat_input_placeholder, key="prompt"):
|
||
history = get_messages_history(history_len)
|
||
chat_box.user_say(prompt)
|
||
if dialogue_mode == "LLM 对话":
|
||
chat_box.ai_say("正在思考...")
|
||
text = ""
|
||
r = api.chat_chat(prompt, history=history, model=llm_model, temperature=temperature)
|
||
for t in r:
|
||
if error_msg := check_error_msg(t): # check whether error occured
|
||
st.error(error_msg)
|
||
break
|
||
text += t
|
||
chat_box.update_msg(text)
|
||
chat_box.update_msg(text, streaming=False) # 更新最终的字符串，去除光标
|
||
|
||
|
||
elif dialogue_mode == "自定义Agent问答":
|
||
chat_box.ai_say([
|
||
f"正在思考...",
|
||
Markdown("...", in_expander=True, title="思考过程", state="complete"),
|
||
])
|
||
text = ""
|
||
ans = ""
|
||
support_agent = ["gpt", "Qwen", "qwen-api", "baichuan-api"] # 目前支持agent的模型
|
||
if not any(agent in llm_model for agent in support_agent):
|
||
ans += "正在思考... \n\n <span style='color:red'>该模型并没有进行Agent对齐，无法正常使用Agent功能！</span>\n\n\n<span style='color:red'>请更换 GPT4或Qwen-14B等支持Agent的模型获得更好的体验！ </span> \n\n\n"
|
||
chat_box.update_msg(ans, element_index=0, streaming=False)
|
||
|
||
|
||
for d in api.agent_chat(prompt,
|
||
history=history,
|
||
model=llm_model,
|
||
temperature=temperature):
|
||
try:
|
||
d = json.loads(d)
|
||
except:
|
||
pass
|
||
if error_msg := check_error_msg(d): # check whether error occured
|
||
st.error(error_msg)
|
||
|
||
elif chunk := d.get("final_answer"):
|
||
ans += chunk
|
||
chat_box.update_msg(ans, element_index=0)
|
||
elif chunk := d.get("answer"):
|
||
text += chunk
|
||
chat_box.update_msg(text, element_index=1)
|
||
elif chunk := d.get("tools"):
|
||
text += "\n\n".join(d.get("tools", []))
|
||
chat_box.update_msg(text, element_index=1)
|
||
chat_box.update_msg(ans, element_index=0, streaming=False)
|
||
chat_box.update_msg(text, element_index=1, streaming=False)
|
||
elif dialogue_mode == "知识库问答":
|
||
chat_box.ai_say([
|
||
f"正在查询知识库 `{selected_kb}` ...",
|
||
Markdown("...", in_expander=True, title="知识库匹配结果", state="complete"),
|
||
])
|
||
text = ""
|
||
for d in api.knowledge_base_chat(prompt,
|
||
knowledge_base_name=selected_kb,
|
||
top_k=kb_top_k,
|
||
score_threshold=score_threshold,
|
||
history=history,
|
||
model=llm_model,
|
||
temperature=temperature):
|
||
if error_msg := check_error_msg(d): # check whether error occured
|
||
st.error(error_msg)
|
||
elif chunk := d.get("answer"):
|
||
text += chunk
|
||
chat_box.update_msg(text, element_index=0)
|
||
chat_box.update_msg(text, element_index=0, streaming=False)
|
||
chat_box.update_msg("\n\n".join(d.get("docs", [])), element_index=1, streaming=False)
|
||
elif dialogue_mode == "搜索引擎问答":
|
||
chat_box.ai_say([
|
||
f"正在执行 `{search_engine}` 搜索...",
|
||
Markdown("...", in_expander=True, title="网络搜索结果", state="complete"),
|
||
])
|
||
text = ""
|
||
for d in api.search_engine_chat(prompt,
|
||
search_engine_name=search_engine,
|
||
top_k=se_top_k,
|
||
history=history,
|
||
model=llm_model,
|
||
temperature=temperature):
|
||
if error_msg := check_error_msg(d): # check whether error occured
|
||
st.error(error_msg)
|
||
elif chunk := d.get("answer"):
|
||
text += chunk
|
||
chat_box.update_msg(text, element_index=0)
|
||
chat_box.update_msg(text, element_index=0, streaming=False)
|
||
chat_box.update_msg("\n\n".join(d.get("docs", [])), element_index=1, streaming=False)
|
||
|
||
now = datetime.now()
|
||
with st.sidebar:
|
||
|
||
cols = st.columns(2)
|
||
export_btn = cols[0]
|
||
if cols[1].button(
|
||
"清空对话",
|
||
use_container_width=True,
|
||
):
|
||
chat_box.reset_history()
|
||
st.experimental_rerun()
|
||
|
||
export_btn.download_button(
|
||
"导出记录",
|
||
"".join(chat_box.export2md()),
|
||
file_name=f"{now:%Y-%m-%d %H.%M}_对话记录.md",
|
||
mime="text/markdown",
|
||
use_container_width=True,
|
||
)
|