test

README.md

@@ -10,4 +10,4 @@ pinned: false
 license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,314 @@
+# import json
+# import os
+
+# import gradio as gr
+# import requests
+# from lagent.schema import AgentStatusCode
+
+# os.system("python -m mindsearch.app --lang cn --model_format internlm_silicon &")
+
+# PLANNER_HISTORY = []
+# SEARCHER_HISTORY = []
+
+
+# def rst_mem(history_planner: list, history_searcher: list):
+#     '''
+#     Reset the chatbot memory.
+#     '''
+#     history_planner = []
+#     history_searcher = []
+#     if PLANNER_HISTORY:
+#         PLANNER_HISTORY.clear()
+#     return history_planner, history_searcher
+
+
+# def format_response(gr_history, agent_return):
+#     if agent_return['state'] in [
+#             AgentStatusCode.STREAM_ING, AgentStatusCode.ANSWER_ING
+#     ]:
+#         gr_history[-1][1] = agent_return['response']
+#     elif agent_return['state'] == AgentStatusCode.PLUGIN_START:
+#         thought = gr_history[-1][1].split('```')[0]
+#         if agent_return['response'].startswith('```'):
+#             gr_history[-1][1] = thought + '\n' + agent_return['response']
+#     elif agent_return['state'] == AgentStatusCode.PLUGIN_END:
+#         thought = gr_history[-1][1].split('```')[0]
+#         if isinstance(agent_return['response'], dict):
+#             gr_history[-1][
+#                 1] = thought + '\n' + f'```json\n{json.dumps(agent_return["response"], ensure_ascii=False, indent=4)}\n```'  # noqa: E501
+#     elif agent_return['state'] == AgentStatusCode.PLUGIN_RETURN:
+#         assert agent_return['inner_steps'][-1]['role'] == 'environment'
+#         item = agent_return['inner_steps'][-1]
+#         gr_history.append([
+#             None,
+#             f"```json\n{json.dumps(item['content'], ensure_ascii=False, indent=4)}\n```"
+#         ])
+#         gr_history.append([None, ''])
+#     return
+
+
+# def predict(history_planner, history_searcher):
+
+#     def streaming(raw_response):
+#         for chunk in raw_response.iter_lines(chunk_size=8192,
+#                                              decode_unicode=False,
+#                                              delimiter=b'\n'):
+#             if chunk:
+#                 decoded = chunk.decode('utf-8')
+#                 if decoded == '\r':
+#                     continue
+#                 if decoded[:6] == 'data: ':
+#                     decoded = decoded[6:]
+#                 elif decoded.startswith(': ping - '):
+#                     continue
+#                 response = json.loads(decoded)
+#                 yield (response['response'], response['current_node'])
+
+#     global PLANNER_HISTORY
+#     PLANNER_HISTORY.append(dict(role='user', content=history_planner[-1][0]))
+#     new_search_turn = True
+
+#     url = 'http://localhost:8002/solve'
+#     headers = {'Content-Type': 'application/json'}
+#     data = {'inputs': PLANNER_HISTORY}
+#     raw_response = requests.post(url,
+#                                  headers=headers,
+#                                  data=json.dumps(data),
+#                                  timeout=20,
+#                                  stream=True)
+
+#     for resp in streaming(raw_response):
+#         agent_return, node_name = resp
+#         if node_name:
+#             if node_name in ['root', 'response']:
+#                 continue
+#             agent_return = agent_return['nodes'][node_name]['detail']
+#             if new_search_turn:
+#                 history_searcher.append([agent_return['content'], ''])
+#                 new_search_turn = False
+#             format_response(history_searcher, agent_return)
+#             if agent_return['state'] == AgentStatusCode.END:
+#                 new_search_turn = True
+#             yield history_planner, history_searcher
+#         else:
+#             new_search_turn = True
+#             format_response(history_planner, agent_return)
+#             if agent_return['state'] == AgentStatusCode.END:
+#                 PLANNER_HISTORY = agent_return['inner_steps']
+#             yield history_planner, history_searcher
+#     return history_planner, history_searcher
+
+
+# with gr.Blocks() as demo:
+#     gr.HTML("""<h1 align="center">MindSearch Gradio Demo</h1>""")
+#     gr.HTML("""<p style="text-align: center; font-family: Arial, sans-serif;">MindSearch is an open-source AI Search Engine Framework with Perplexity.ai Pro performance. You can deploy your own Perplexity.ai-style search engine using either closed-source LLMs (GPT, Claude) or open-source LLMs (InternLM2.5-7b-chat).</p>""")
+#     gr.HTML("""
+#     <div style="text-align: center; font-size: 16px;">
+#         <a href="https://github.com/InternLM/MindSearch" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">🔗 GitHub</a>
+#         <a href="https://arxiv.org/abs/2407.20183" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">📄 Arxiv</a>
+#         <a href="https://huggingface.co/papers/2407.20183" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">📚 Hugging Face Papers</a>
+#         <a href="https://huggingface.co/spaces/internlm/MindSearch" style="text-decoration: none; color: #4A90E2;">🤗 Hugging Face Demo</a>
+#     </div>
+#     """)
+#     with gr.Row():
+#         with gr.Column(scale=10):
+#             with gr.Row():
+#                 with gr.Column():
+#                     planner = gr.Chatbot(label='planner',
+#                                          height=700,
+#                                          show_label=True,
+#                                          show_copy_button=True,
+#                                          bubble_full_width=False,
+#                                          render_markdown=True)
+#                 with gr.Column():
+#                     searcher = gr.Chatbot(label='searcher',
+#                                           height=700,
+#                                           show_label=True,
+#                                           show_copy_button=True,
+#                                           bubble_full_width=False,
+#                                           render_markdown=True)
+#             with gr.Row():
+#                 user_input = gr.Textbox(show_label=False,
+#                                         placeholder='帮我搜索一下 InternLM 开源体系',
+#                                         lines=5,
+#                                         container=False)
+#             with gr.Row():
+#                 with gr.Column(scale=2):
+#                     submitBtn = gr.Button('Submit')
+#                 with gr.Column(scale=1, min_width=20):
+#                     emptyBtn = gr.Button('Clear History')
+
+#     def user(query, history):
+#         return '', history + [[query, '']]
+
+#     submitBtn.click(user, [user_input, planner], [user_input, planner],
+#                     queue=False).then(predict, [planner, searcher],
+#                                       [planner, searcher])
+#     emptyBtn.click(rst_mem, [planner, searcher], [planner, searcher],
+#                    queue=False)
+
+# demo.queue()
+# demo.launch(server_name='0.0.0.0',
+#             server_port=7860,
+#             inbrowser=True,
+#             share=True)
+
+
+import json
+import os
+
+import gradio as gr
+import requests
+from lagent.schema import AgentStatusCode
+
+os.system("python -m mindsearch.app --lang cn --model_format internlm_silicon &")
+
+PLANNER_HISTORY = []
+SEARCHER_HISTORY = []
+
+
+def rst_mem(history_planner: list, history_searcher: list):
+    '''
+    Reset the chatbot memory.
+    '''
+    history_planner = []
+    history_searcher = []
+    if PLANNER_HISTORY:
+        PLANNER_HISTORY.clear()
+    return history_planner, history_searcher
+
+
+def format_response(gr_history, agent_return):
+    if agent_return['state'] in [
+            AgentStatusCode.STREAM_ING, AgentStatusCode.ANSWER_ING
+    ]:
+        gr_history[-1][1] = agent_return['response']
+    elif agent_return['state'] == AgentStatusCode.PLUGIN_START:
+        thought = gr_history[-1][1].split('```')[0]
+        if agent_return['response'].startswith('```'):
+            gr_history[-1][1] = thought + '\n' + agent_return['response']
+    elif agent_return['state'] == AgentStatusCode.PLUGIN_END:
+        thought = gr_history[-1][1].split('```')[0]
+        if isinstance(agent_return['response'], dict):
+            gr_history[-1][
+                1] = thought + '\n' + f'```json\n{json.dumps(agent_return["response"], ensure_ascii=False, indent=4)}\n```'  # noqa: E501
+    elif agent_return['state'] == AgentStatusCode.PLUGIN_RETURN:
+        assert agent_return['inner_steps'][-1]['role'] == 'environment'
+        item = agent_return['inner_steps'][-1]
+        gr_history.append([
+            None,
+            f"```json\n{json.dumps(item['content'], ensure_ascii=False, indent=4)}\n```"
+        ])
+        gr_history.append([None, ''])
+    return
+
+
+def predict(history_planner, history_searcher):
+
+    def streaming(raw_response):
+        for chunk in raw_response.iter_lines(chunk_size=8192,
+                                             decode_unicode=False,
+                                             delimiter=b'\n'):
+            if chunk:
+                decoded = chunk.decode('utf-8')
+                if decoded == '\r':
+                    continue
+                if decoded[:6] == 'data: ':
+                    decoded = decoded[6:]
+                elif decoded.startswith(': ping - '):
+                    continue
+                response = json.loads(decoded)
+                yield (response['response'], response['current_node'])
+
+    global PLANNER_HISTORY
+    PLANNER_HISTORY.append(dict(role='user', content=history_planner[-1][0]))
+    new_search_turn = True
+
+    url = 'http://localhost:8002/solve'
+    headers = {'Content-Type': 'application/json'}
+    data = {'inputs': PLANNER_HISTORY}
+    raw_response = requests.post(url,
+                                 headers=headers,
+                                 data=json.dumps(data),
+                                 timeout=20,
+                                 stream=True)
+
+    for resp in streaming(raw_response):
+        agent_return, node_name = resp
+        if node_name:
+            if node_name in ['root', 'response']:
+                continue
+            agent_return = agent_return['nodes'][node_name]['detail']
+            if new_search_turn:
+                history_searcher.append([agent_return['content'], ''])
+                new_search_turn = False
+            format_response(history_searcher, agent_return)
+            if agent_return['state'] == AgentStatusCode.END:
+                new_search_turn = True
+            yield history_planner, history_searcher
+        else:
+            new_search_turn = True
+            format_response(history_planner, agent_return)
+            if agent_return['state'] == AgentStatusCode.END:
+                PLANNER_HISTORY = agent_return['inner_steps']
+            yield history_planner, history_searcher
+    return history_planner, history_searcher
+
+
+with gr.Blocks(css=".gradio-container {background-color: #f9f9f9;} .gr-button {background-color: #4A90E2; color: white; border-radius: 10px;} .gr-textbox {border: 2px solid #4A90E2; border-radius: 5px;} .gr-row {margin-bottom: 10px;}") as demo:
+    gr.HTML("""<h1 align="center" style="color:#4A90E2;">MindSearch Gradio Demo</h1>""")
+    gr.HTML("""<p style="text-align: center; font-family: Arial, sans-serif; color: #333;">MindSearch is an open-source AI Search Engine Framework with Perplexity.ai Pro performance. You can deploy your own Perplexity.ai-style search engine using either closed-source LLMs (GPT, Claude) or open-source LLMs (InternLM2.5-7b-chat).</p>""")
+    gr.HTML("""
+    <div style="text-align: center; font-size: 16px; margin-bottom: 20px;">
+        <a href="https://github.com/InternLM/MindSearch" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">🔗 GitHub</a>
+        <a href="https://arxiv.org/abs/2407.20183" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">📄 Arxiv</a>
+        <a href="https://huggingface.co/papers/2407.20183" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">📚 Hugging Face Papers</a>
+        <a href="https://huggingface.co/spaces/internlm/MindSearch" style="text-decoration: none; color: #4A90E2;">🤗 Hugging Face Demo</a>
+    </div>
+    """)
+    with gr.Row():
+        with gr.Column(scale=10):
+            with gr.Row():
+                with gr.Column():
+                    planner = gr.Chatbot(label='Planner',
+                                         height=700,
+                                         show_label=True,
+                                         show_copy_button=True,
+                                         bubble_full_width=True,
+                                         render_markdown=True,
+                                         container=False,
+                                         elem_id="planner")
+                with gr.Column():
+                    searcher = gr.Chatbot(label='Searcher',
+                                          height=700,
+                                          show_label=True,
+                                          show_copy_button=True,
+                                          bubble_full_width=True,
+                                          render_markdown=True,
+                                          container=False,
+                                          elem_id="searcher")
+            with gr.Row():
+                user_input = gr.Textbox(show_label=False,
+                                        placeholder='帮我搜索一下 InternLM 开源体系',
+                                        lines=5,
+                                        container=False)
+            with gr.Row():
+                with gr.Column(scale=2):
+                    submitBtn = gr.Button('Submit', elem_id="submitBtn")
+                with gr.Column(scale=1, min_width=20):
+                    emptyBtn = gr.Button('Clear History', elem_id="emptyBtn")
+
+    def user(query, history):
+        return '', history + [[query, '']]
+
+    submitBtn.click(user, [user_input, planner], [user_input, planner],
+                    queue=False).then(predict, [planner, searcher],
+                                      [planner, searcher])
+    emptyBtn.click(rst_mem, [planner, searcher], [planner, searcher],
+                   queue=False)
+
+demo.queue()
+demo.launch(server_name='0.0.0.0',
+            server_port=7860,
+            inbrowser=True,
+            share=True)

requirements.txt

@@ -0,0 +1,12 @@
+duckduckgo_search==5.3.1b1
+einops
+fastapi
+git+https://github.com/InternLM/lagent.git
+gradio
+janus
+lmdeploy
+pyvis
+sse-starlette
+termcolor
+transformers==4.41.0
+uvicorn