Webui更新说明

1、自动读取knowledge_based_chatglm.py中LLM及embedding模型枚举，选择后点击setting进行模型加载，可随时切换模型进行测试
2、可手动调节保留对话历史长度，可根据显存大小自行调节
3、添加上传文件功能，通过下拉框选择已上传的文件，点击loading加载文件，过程中可随时更换加载的文件
4、底部添加use via API可对接到自己系统

TODO：
1、添加模型加载进度条
2、添加输出内容及错误提示
3、国家化语言切换
4、引用标注
5、添加插件系统（可基础lora训练等）

knowledge_based_chatglm.py

@@ -28,23 +28,32 @@ embedding_model_dict = {
 llm_model_dict = {
     "chatglm-6b": "THUDM/chatglm-6b",
     "chatglm-6b-int4": "THUDM/chatglm-6b-int4",
-    "chatglm-6b-int4-qe": "THUDM/chatglm-6b-int4-qe",
+    # "chatglm-6b-int4-qe": "THUDM/chatglm-6b-int4-qe",
 }
 
-chatglm = ChatGLM()
-chatglm.load_model(model_name_or_path=llm_model_dict[LLM_MODEL])
-chatglm.history_len = LLM_HISTORY_LEN
+chatglm = None
+embeddings = None
+
+def init_cfg(LLM_MODEL,EMBEDDING_MODEL, LLM_HISTORY_LEN,V_SEARCH_TOP_K=6):
+    global chatglm,embeddings,VECTOR_SEARCH_TOP_K
+    VECTOR_SEARCH_TOP_K=V_SEARCH_TOP_K
+
+    chatglm = ChatGLM()
+    chatglm.load_model(model_name_or_path=llm_model_dict[LLM_MODEL])
+    chatglm.history_len = LLM_HISTORY_LEN
 
-def init_knowledge_vector_store(filepath):
     embeddings = HuggingFaceEmbeddings(model_name=embedding_model_dict[EMBEDDING_MODEL], )
+
+def init_knowledge_vector_store(filepath):
+    
     loader = UnstructuredFileLoader(filepath, mode="elements")
     docs = loader.load()
-
     vector_store = FAISS.from_documents(docs, embeddings)
     return vector_store
 
 
 def get_knowledge_based_answer(query, vector_store, chat_history=[]):
+    global chatglm,embeddings
     system_template = """基于以下内容，简洁和专业的来回答用户的问题。
     如果无法从中得到答案，请说 "不知道" 或 "没有足够的相关信息"，不要试图编造答案。答案请使用中文。
     ----------------
@@ -72,6 +81,7 @@ def get_knowledge_based_answer(query, vector_store, chat_history=[]):
 
 
 if __name__ == "__main__":
+    init_cfg(LLM_MODEL,EMBEDDING_MODEL, LLM_HISTORY_LEN)
     filepath = input("Input your local knowledge file path 请输入本地知识文件路径：")
     vector_store = init_knowledge_vector_store(filepath)
     history = []

webui.py

+import gradio as gr
+import os
+import shutil
+import knowledge_based_chatglm as kb
+
+
+# class kb:
+#     def __init__(self):
+#         pass
+
+#     def init_knowledge_vector_store(filepath):
+#         return filepath
+
+#     def get_knowledge_based_answer(*args):
+#         return args
+
+
+def get_file_list():
+    if not os.path.exists("content"):
+        return []
+    return [f for f in os.listdir("content")]
+
+
+file_list = get_file_list()
+
+embedding_model_dict_list = list(kb.embedding_model_dict.keys())
+
+llm_model_dict_list = list(kb.llm_model_dict.keys())
+
+
+def upload_file(file):
+    if not os.path.exists("content"):
+        os.mkdir("content")
+    filename = os.path.basename(file.name)
+    shutil.move(file.name, "content/"+filename)
+    # file_list首位插入新上传的文件
+    file_list.insert(0, filename)
+    return gr.Dropdown.update(choices=file_list, value=filename)
+
+
+def getAnswer(q, v, h):
+    resp, history = kb.get_knowledge_based_answer(
+        query=q, vector_store=v, chat_history=h)
+    return history, history
+
+
+with gr.Blocks(css="""
+.importantButton {
+    background: linear-gradient(45deg, #7e0570,#5d1c99, #6e00ff) !important;
+    border: none !important;
+}
+
+.importantButton:hover {
+    background: linear-gradient(45deg, #ff00e0,#8500ff, #6e00ff) !important;
+    border: none !important;
+}
+
+""") as demo:
+    gr.Markdown(
+        f"""
+# 🎉langchain-ChatGLM WebUI🎉
+
+👍 [https://github.com/imClumsyPanda/langchain-ChatGLM](https://github.com/imClumsyPanda/langchain-ChatGLM)
+
+""")
+    with gr.Row():
+        with gr.Column(scale=2):
+            chatbot = gr.Chatbot(elem_id="chat-box",
+                                 show_label=False).style(height=600)
+        with gr.Column(scale=1):
+            with gr.Column():
+                llm_model = gr.Radio(
+                    llm_model_dict_list, label="llm model",
+                    value="chatglm-6b", interactive=True)
+                LLM_HISTORY_LEN = gr.Slider(
+                    1, 10, value=3, step=1, label="LLM history len", interactive=True)
+                embedding_model = gr.Radio(
+                    embedding_model_dict_list, label="embedding model",
+                    value="text2vec", interactive=True)
+                VECTOR_SEARCH_TOP_K = gr.Slider(
+                    1, 20, value=6, step=1, label="vector search top k", interactive=True)
+                load_model_button = gr.Button("step.1：setting")
+                load_model_button.click(lambda *args:
+                                        kb.init_cfg(args[0], args[1], args[2], args[3]),
+                                        show_progress=True,
+                                        api_name="init_cfg",
+                                        inputs=[llm_model, embedding_model, VECTOR_SEARCH_TOP_K, LLM_HISTORY_LEN])
+
+            with gr.Column():
+                with gr.Tab("select"):
+                    selectFile = gr.Dropdown(
+                        file_list, label="content file", interactive=True, value=file_list[0] if len(file_list) > 0 else None)
+                with gr.Tab("upload"):
+                    file = gr.File(label="content file", file_types=[
+                                   '.txt', '.md', '.docx']).style(height=100)
+                    # 将上传的文件保存到content文件夹下,并更新下拉框
+                    file.upload(upload_file, inputs=file, outputs=selectFile)
+                history = gr.State([])
+                vector_store = gr.State()
+                load_button = gr.Button("step.2：loading")
+                load_button.click(lambda fileName:
+                                  kb.init_knowledge_vector_store(
+                                      "content/"+fileName),
+                                  show_progress=True,
+                                  api_name="init_knowledge_vector_store",
+                                  inputs=selectFile, outputs=vector_store)
+
+    with gr.Row():
+        with gr.Column(scale=2):
+            query = gr.Textbox(show_label=False, placeholder="Prompts", lines=1, value="用200字总结一下").style(
+                container=False)
+        with gr.Column(scale=1):
+            generate_button = gr.Button(
+                "step.3：asking", elem_classes="importantButton")
+            generate_button.click(getAnswer, [query, vector_store, history],
+                                [chatbot, history],api_name="get_knowledge_based_answer")
+
+
+demo.queue(concurrency_count=3).launch(
+    server_name='0.0.0.0', share=False, inbrowser=False)