feat(读文章写摘要):支持pdf文件批量阅读及总结

crazy_functions/读文章写摘要.py

@@ -48,8 +48,54 @@ def 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, hist
         yield chatbot, history, msg
 
 
+def 解析PDF(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt):
+    import time, glob, os, codecs, fitz
+    print('begin analysis on:', file_manifest)
+    for index, fp in enumerate(file_manifest):
+        with fitz.open(fp) as doc:
+            file_content = ""
+            for page in doc:
+                file_content += page.getText()
+            print(file_content)
+
+        prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index==0 else ""
+        i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
+        i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
+        chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
+        print('[1] yield chatbot, history')
+        yield chatbot, history, '正常'
+
+        if not fast_debug: 
+            msg = '正常'
+            # ** gpt request **
+            gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temperature, history=[])   # 带超时倒计时
+
+            print('[2] end gpt req')
+            chatbot[-1] = (i_say_show_user, gpt_say)
+            history.append(i_say_show_user); history.append(gpt_say)
+            print('[3] yield chatbot, history')
+            yield chatbot, history, msg
+            print('[4] next')
+            if not fast_debug: time.sleep(2)
+
+    all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)])
+    i_say = f'根据以上你自己的分析，对全文进行概括，用学术性语言写一段中文摘要，然后再写一段英文摘要（包括{all_file}）。'
+    chatbot.append((i_say, "[Local Message] waiting gpt response."))
+    yield chatbot, history, '正常'
+
+    if not fast_debug: 
+        msg = '正常'
+        # ** gpt request **
+        gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say, chatbot, top_p, temperature, history=history)   # 带超时倒计时
+
+        chatbot[-1] = (i_say, gpt_say)
+        history.append(i_say); history.append(gpt_say)
+        yield chatbot, history, msg
+        res = write_results_to_file(history)
+        chatbot.append(("完成了吗？", res))
+        yield chatbot, history, msg
+
 
-@CatchException
 def 读文章写摘要(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT):
     history = []    # 清空历史，以免输入溢出
     import glob, os
@@ -60,11 +106,15 @@ def 读文章写摘要(txt, top_p, temperature, chatbot, history, systemPromptTx
         report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield chatbot, history, '正常'
         return
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] # + \
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] + \
+                    [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)] # + \
                     # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
                     # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
+        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex或.pdf文件: {txt}")
         yield chatbot, history, '正常'
         return
-    yield from 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)
+    if '.pdf' in file_manifest[0]:
+        yield from 解析PDF(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)
+    else:
+        yield from 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)

main.py

@@ -4,8 +4,7 @@ from predict import predict
 from toolbox import format_io, find_free_port
 
 # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
-try: from config_private import proxies, WEB_PORT, LLM_MODEL
-except: from config import proxies, WEB_PORT, LLM_MODEL
+from config_private import proxies, WEB_PORT, LLM_MODEL
 
 # 如果WEB_PORT是-1, 则随机选取WEB端口
 PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT