tests(gradio.py): update

README.md

@@ -30,12 +30,14 @@ English | [简体中文](README_zh.md)
 
 </div>
 
-HuixiangDou is a **group chat** assistant based on LLM (Large Language Model).
+HuixiangDou is a **professional knowledge assistant** based on LLM.
 
 Advantages:
 
-1. Design a three-stage pipeline of preprocess, rejection and response to cope with group chat scenario, answer user questions without message flooding, see [2401.08772](https://arxiv.org/abs/2401.08772), [2405.02817](https://arxiv.org/abs/2405.02817), [Hybrid Retrieval](./docs/knowledge_graph_en.md) and [Precision Report](./evaluation/).
-2. No training required, with CPU-only, 2G, 10G and 80G configuration
+1. Design three-stage pipelines of preprocess, rejection and response
+  * `chat_in_group` copes with **group chat** scenario, answer user questions without message flooding, see [2401.08772](https://arxiv.org/abs/2401.08772), [2405.02817](https://arxiv.org/abs/2405.02817), [Hybrid Retrieval](./docs/knowledge_graph_en.md) and [Precision Report](./evaluation/)
+  * `chat_with_repo` for **real-time streaming** chat
+2. No training required, with CPU-only, 2G, 10G, 20G and 80G configuration
 3. Offers a complete suite of Web, Android, and pipeline source code, industrial-grade and commercially viable
 
 Check out the [scenes in which HuixiangDou are running](./huixiangdou-inside.md) and join [WeChat Group](resource/figures/wechat.jpg) to try AI assistant inside.
@@ -46,6 +48,7 @@ If this helps you, please give it a star ⭐
 
 Our Web version has been released to [OpenXLab](https://openxlab.org.cn/apps/detail/tpoisonooo/huixiangdou-web), where you can create knowledge base, update positive and negative examples, turn on web search, test chat, and integrate into Feishu/WeChat groups. See [BiliBili](https://www.bilibili.com/video/BV1S2421N7mn) and [YouTube](https://www.youtube.com/watch?v=ylXrT-Tei-Y) !
 
+- \[2024/08\] `chat_with_repo` [pipeline](./huixiangdou/service/parallel_pipeline.py) 👍
 - \[2024/07\] Image and text retrieval & Removal of `langchain` 👍
 - \[2024/07\] [Hybrid Knowledge Graph and Dense Retrieval](./docs/knowledge_graph_en.md) improve 1.7% F1 score 🎯
 - \[2024/06\] [Evaluation of chunksize, splitter, and text2vec model](./evaluation) 🎯

README_zh.md

@@ -29,10 +29,12 @@
 
 </div>
 
-茴香豆是一个基于 LLM 的**群聊**知识助手，优势：
+茴香豆是一个基于 LLM 的专业知识助手，优势：
 
-1. 设计预处理、拒答、响应三阶段 pipeline 应对群聊场景，解答问题同时不会消息泛滥。精髓见 [2401.08772](https://arxiv.org/abs/2401.08772)，[2405.02817](https://arxiv.org/abs/2405.02817)，[混合检索](./docs/knowledge_graph_zh.md)和[业务数据精度测试](./evaluation)
-2. 无需训练适用各行业，提供 CPU-only、2G、10G、80G 规格配置
+1. 设计预处理、拒答、响应三阶段 pipeline：
+  * `chat_in_group` 群聊场景，解答问题时不会消息泛滥。见 [2401.08772](https://arxiv.org/abs/2401.08772)，[2405.02817](https://arxiv.org/abs/2405.02817)，[混合检索](./docs/knowledge_graph_zh.md)和[业务数据精度测试](./evaluation)
+  * `chat_with_repo` 实时聊天场景，响应更快
+2. 无需训练适用各行业，提供 CPU-only、2G、10G、20G、80G 规格配置
 3. 提供一整套前后端 web、android、算法源码，工业级开源可商用
 
 查看[茴香豆已运行在哪些场景](./huixiangdou-inside.md)；加入[微信群](resource/figures/wechat.jpg)直接体验群聊助手效果。
@@ -45,6 +47,7 @@
 
 Web 版视频教程见 [BiliBili](https://www.bilibili.com/video/BV1S2421N7mn) 和 [YouTube](https://www.youtube.com/watch?v=ylXrT-Tei-Y)。
 
+- \[2024/08\] `chat_with_repo` [pipeline](./huixiangdou/service/parallel_pipeline.py) 👍
 - \[2024/07\] 图文检索 & 移除 `langchain` 👍
 - \[2024/07\] [混合知识图谱和稠密检索，F1 提升 1.7%](./docs/knowledge_graph_zh.md) 🎯
 - \[2024/06\] [评估 chunksize，splitter 和 text2vec 模型](./evaluation) 🎯

huixiangdou/gradio.py

@@ -37,9 +37,9 @@ def parse_args():
     args = parser.parse_args()
     return args
 
-language='zh'
-enable_web_search=True
-pipeline='parallel'
+language='en'
+enable_web_search=False
+pipeline='chat_with_repo'
 main_args = None
 paralle_assistant = None
 serial_assistant = None
@@ -71,7 +71,7 @@ def format_refs(refs: List[str]):
     if language == 'zh':
         text += '参考资料：\r\n'
     else:
-        text += 'references:\r\n'
+        text += '**References:**\r\n'
 
     for file_or_url in refs_filter:
         text += '* {}\r\n'.format(file_or_url)
@@ -95,7 +95,7 @@ async def predict(text:str, image:str):
         image_path = None
 
     query = Query(text, image_path)
-    if 'serial' in pipeline:
+    if 'chat_in_group' in pipeline:
         if serial_assistant is None:
             serial_assistant = SerialPipeline(work_dir=main_args.work_dir, config_path=main_args.config_path)
         args = {'query':query, 'history': [], 'groupname':''}
@@ -125,16 +125,15 @@ async def predict(text:str, image:str):
         args = {'query':query, 'history':[], 'language':language}
         args['enable_web_search'] = enable_web_search
 
-        sentence = None
+        sentence = ''
         async for sess in paralle_assistant.generate(**args):
-            if len(sess.delta) > 0:
-                if sentence is None:
-                    sentence = format_refs(sess.references)
+            if sentence == '' and len(sess.references) > 0:
+                sentence = format_refs(sess.references)
 
+            if len(sess.delta) > 0:
                 sentence += sess.delta
                 yield sentence
 
-
         yield sentence
 
 if __name__ == '__main__':
@@ -145,25 +144,31 @@ async def predict(text:str, image:str):
         # hybrid llm serve
         start_llm_server(config_path=main_args.config_path)
 
-    with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    with gr.Blocks(theme=gr.themes.Soft(), title='HuixiangDou AI assistant', analytics_enabled=True) as demo:
+        with gr.Row():
+            gr.Markdown("""
+            #### [HuixiangDou](https://github.com/internlm/huixiangdou) AI assistant
+            """, label='Reply', header_links=True, line_breaks=True,)
         with gr.Row():
             with gr.Column():
-                ui_language = gr.Radio(["zh", "en"], label="Language", info="Use `zh` by default")
-                ui_language.change(fn=on_language_changed, inputs=ui_language, outputs=[])
-            with gr.Column():
-                ui_pipeline = gr.Radio(["parallel", "serial"], label="Pipeline type", info="Serial pipeline is very slow but more accurate, default value is `parallel`")
+                ui_pipeline = gr.Radio(["chat_with_repo", "chat_in_group"], label="Pipeline type", info="Group-chat is slow but accurate and safe, default value is `chat_with_repo`")
                 ui_pipeline.change(fn=on_pipeline_changed, inputs=ui_pipeline, outputs=[])
             with gr.Column():
-                ui_web_search = gr.Radio(["yes", "no"], label="Enable web search", info="Enable by default")
+                ui_language = gr.Radio(["en", "zh"], label="Language", info="Use `en` by default                                 ")
+                ui_language.change(fn=on_language_changed, inputs=ui_language, outputs=[])
+            with gr.Column():
+                ui_web_search = gr.Radio(["no", "yes"], label="Enable web search", info="Disable by default                                 ")
                 ui_web_search.change(on_web_search_changed, inputs=ui_web_search, outputs=[])
 
         with gr.Row():
-            input_question = gr.TextArea(label='Input your question.', placeholder='how to install opencompass ?', show_copy_button=True, lines=9)
+            input_question = gr.TextArea(label='Input your question', placeholder='how to install opencompass ?', show_copy_button=True, lines=9)
             input_image = gr.Image(label='[Optional] Image-text retrieval needs `config-multimodal.ini`')
         with gr.Row():
             run_button = gr.Button()
         with gr.Row():
-            result = gr.TextArea(label='Reply', show_copy_button=True, placeholder='Text Reply or inner status callback, depends on `pipeline type`')
+            result = gr.Markdown('>Text reply or inner status callback here, depends on `pipeline type`', label='Reply', show_label=True, header_links=True, line_breaks=True, show_copy_button=True)
+            # result = gr.TextArea(label='Reply', show_copy_button=True, placeholder='Text Reply or inner status callback, depends on `pipeline type`')
+
         run_button.click(predict, [input_question, input_image], [result])
     demo.queue()
     demo.launch(share=False, server_name='0.0.0.0', debug=True)

huixiangdou/server.py

@@ -18,7 +18,7 @@
 import uvicorn
 import json
 
-assistant = SerialPipeline(work_dir='workdir', config_path='config.ini')
+assistant = None
 app = FastAPI(docs_url='/')
 
 class Talk(BaseModel):
@@ -66,5 +66,31 @@ def event_stream():
             yield json.dumps(pipeline)
     return StreamingResponse(event_stream(), media_type="text/event-stream")
 
+def parse_args():
+    """Parse args."""
+    parser = argparse.ArgumentParser(description='SerialPipeline.')
+    parser.add_argument('--work_dir',
+                        type=str,
+                        default='workdir',
+                        help='Working directory.')
+    parser.add_argument(
+        '--config_path',
+        default='config.ini',
+        type=str,
+        help='Configuration path. Default value is config.ini')
+    parser.add_argument('--standalone',
+                        action='store_true',
+                        default=False,
+                        help='Auto deploy required Hybrid LLM Service.')
+    parser.add_argument('--pipeline', type=str, choices=['chat_with_repo', 'chat_in_group'], default='chat_with_repo', 
+                        help='Select pipeline type for difference scenario, default value is `chat_with_repo`')
+    args = parser.parse_args()
+    return args
+
 if __name__ == '__main__':
+    args = parse_args()
+    if 'chat_with_repo' in args.pipeline:
+        assistant = ParallelPipeline(work_dir=args.work_dir, config_path=args.config_path)
+    elif 'chat_in_group' in args.pipeline:
+        assistant = SerialPipeline(work_dir=args.work_dir, config_path=args.config_path)
     uvicorn.run(app, host='0.0.0.0', port=23333, log_level='info')

requirements.txt

@@ -33,4 +33,4 @@ fastapi
 uvicorn
 termcolor
 opencv-python-headless
-gradio
+gradio>=4.41