{"title": "效果如何优化", "file": "2023-04-04.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/14", "detail": "如图所示，将该项目的README.md和该项目结合后，回答效果并不理想，请问可以从哪些方面进行优化", "id": 0}
{"title": "怎么让模型严格根据检索的数据进行回答，减少胡说八道的回答呢", "file": "2023-04-04.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/15", "detail": "举个例子：", "id": 1}
{"title": "When I try to run the `python knowledge_based_chatglm.py`, I got this error in macOS(M1 Max, OS 13.2)", "file": "2023-04-07.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/32", "detail": "```python", "id": 2}
{"title": "萌新求教大佬怎么改成AMD显卡或者CPU？", "file": "2023-04-10.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/48", "detail": "把.cuda()去掉就行", "id": 3}
{"title": "输出answer的时间很长，是否可以把文本向量化的部分提前做好存储起来？", "file": "2023-04-10.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/50", "detail": "GPU：4090 24G显存", "id": 4}
{"title": "报错Use `repo_type` argument if needed.", "file": "2023-04-11.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/57", "detail": "Traceback (most recent call last):", "id": 5}
{"title": "无法打开gradio的页面", "file": "2023-04-11.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/58", "detail": "$ python webui.py", "id": 6}
{"title": "支持word，那word里面的图片正常显示吗？", "file": "2023-04-12.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/60", "detail": "如题，刚刚从隔壁转过来的，想先了解下", "id": 7}
{"title": "detectron2 is not installed. Cannot use the hi_res partitioning strategy. Falling back to partitioning with the fast strategy.", "file": "2023-04-12.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/63", "detail": "能够正常的跑起来，在加载content文件夹中的文件时，每加载一个文件都会提示：", "id": 8}
{"title": "cpu上运行webui，step3 asking时报错", "file": "2023-04-12.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/66", "detail": "web运行，文件加载都正常，asking时报错", "id": 9}
{"title": "建议弄一个插件系统", "file": "2023-04-13.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/67", "detail": "如题弄成stable-diffusion-webui那种能装插件，再开一个存储库给使用者或插件开发，存储或下载插件。", "id": 10}
{"title": "请教加载模型出错！？", "file": "2023-04-13.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/75", "detail": "AttributeError: module 'transformers_modules.chatglm-6b.configuration_chatglm' has no attribute 'ChatGLMConfig 怎么解决呀", "id": 11}
{"title": "从本地知识检索内容的时候，是否可以设置相似度阈值，小于这个阈值的内容不返回，即使会小于设置的VECTOR_SEARCH_TOP_K参数呢？谢谢大佬", "file": "2023-04-13.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/76", "detail": "比如 问一些 你好/你是谁 等一些跟本地知识库无关的问题", "id": 12}
{"title": "如何改成多卡推理？", "file": "2023-04-13.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/77", "detail": "+1", "id": 13}
{"title": "能否弄个懒人包，可以一键体验？", "file": "2023-04-13.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/78", "detail": "能否弄个懒人包，可以一键体验？", "id": 14}
{"title": "连续问问题会导致崩溃", "file": "2023-04-13.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/79", "detail": "看上去不是爆内存的问题，连续问问题后，会出现如下报错", "id": 15}
{"title": "AttributeError: 'NoneType' object has no attribute 'as_retriever'", "file": "2023-04-14.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/86", "detail": "环境：windows 11, anaconda/python 3.8", "id": 16}
{"title": "FileNotFoundError: Could not find module 'nvcuda.dll' (or one of its dependencies). Try using the full path with constructor syntax.", "file": "2023-04-14.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/87", "detail": "请检查一下cuda或cudnn是否存在安装问题", "id": 17}
{"title": "加载txt文件失败？", "file": "2023-04-14.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/89", "detail": "![JppHrGOWFa](https://user-images.githubusercontent.com/109277248/232009383-bf7c46d1-a01e-4e0a-9de6-5b5ed3e36158.jpg)", "id": 18}
{"title": "NameError: name 'chatglm' is not defined", "file": "2023-04-14.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/90", "detail": "This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces", "id": 19}
{"title": "打不开地址？", "file": "2023-04-14.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/91", "detail": "报错数据如下：", "id": 20}
{"title": "加载md文件出错", "file": "2023-04-14.00", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/98", "detail": "运行 webui.py后能访问页面，上传一个md文件后，日志中有错误。等待后能加载完成，提示可以提问了，但提问没反应，日志中有错误。 具体日志如下。", "id": 21}
{"title": "建议增加获取在线知识的能力", "file": "2023-04-15.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/101", "detail": "建议增加获取在线知识的能力", "id": 22}
{"title": "txt 未能成功加载", "file": "2023-04-15.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/103", "detail": "hinese. Creating a new one with MEAN pooling.", "id": 23}
{"title": "pdf加载失败", "file": "2023-04-15.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/105", "detail": "e:\\a.txt加载成功了，e:\\a.pdf加载就失败，pdf文件里面前面几页是图片，后面都是文字，加载失败没有报更多错误，请问该怎么排查？", "id": 24}
{"title": "一直停在文本加载处", "file": "2023-04-15.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/108", "detail": "一直停在文本加载处", "id": 25}
{"title": " File \"/root/.cache/huggingface/modules/transformers_modules/chatglm-6b/modeling_chatglm.py\", line 440, in forward     new_tensor_shape = mixed_raw_layer.size()[:-1] + ( TypeError: torch.Size() takes an iterable of 'int' (item 2 is 'float')", "file": "2023-04-17.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/113", "detail": "按照最新的代码，发现", "id": 26}
{"title": "后续会提供前后端分离的功能吗？", "file": "2023-04-17.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/114", "detail": "类似这种https://github.com/lm-sys/FastChat/tree/main/fastchat/serve", "id": 27}
{"title": "安装依赖报错", "file": "2023-04-17.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/115", "detail": "(test) C:\\Users\\linh\\Desktop\\langchain-ChatGLM-master>pip install -r requirements.txt", "id": 28}
{"title": "问特定问题会出现爆显存", "file": "2023-04-17.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/117", "detail": "正常提问没问题。", "id": 29}
{"title": "Expecting value: line 1 column 1 (char 0)", "file": "2023-04-17.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/118", "detail": "运行后 第一步加载配置一直报错：", "id": 30}
{"title": "embedding  https://huggingface.co/GanymedeNil/text2vec-large-chinese/tree/main是免费的，效果比对openai的如何？", "file": "2023-04-17.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/119", "detail": "-------------------------------------------------------------------------------", "id": 31}
{"title": "这是什么错误，在Colab上运行的。", "file": "2023-04-17.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/120", "detail": "libcuda.so.1: cannot open shared object file: No such file or directory", "id": 32}
{"title": "只想用自己的lora微调后的模型进行对话，不想加载任何本地文档，该如何调整？", "file": "2023-04-18.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/121", "detail": "能出一个单独的教程吗", "id": 33}
{"title": "租的gpu,Running on local URL:  http://0.0.0.0:7860  To create a public link, set `share=True` in `launch()`.  浏览器上访问不了？？？", "file": "2023-04-18.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/122", "detail": "(chatglm20230401) root@autodl-container-e82d11963c-10ece0d7:~/autodl-tmp/chatglm/langchain-ChatGLM-20230418# python3.9 webui.py", "id": 34}
{"title": "本地部署中的报错请教", "file": "2023-04-18.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/124", "detail": "您好，在本地运行langchain-ChatGLM过程中，环境及依赖的包都已经满足条件，但是运行webui.py,报错如下（运行cli_demo.py报错类似），请问是哪里出了错呢？盼望您的回复，谢谢！", "id": 35}
{"title": "报错。The dtype of attention mask (torch.int64) is not bool", "file": "2023-04-18.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/131", "detail": "The dtype of attention mask (torch.int64) is not bool", "id": 36}
{"title": "[求助] pip install -r requirements.txt 的时候出现以下报错。。。有大佬帮忙看看怎么搞么，下的release里面的包", "file": "2023-04-18.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/134", "detail": "$ pip install -r requirements.txt", "id": 37}
{"title": "如何提升根据问题搜索到对应知识的准确率", "file": "2023-04-19.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/136", "detail": "外链知识库最大的问题在于问题是短文本，知识是中长文本。如何根据问题精准的搜索到对应的知识是个最大的问题。这类本地化项目不像百度，由无数的网页，基本上每个问题都可以找到对应的页面。", "id": 38}
{"title": "是否可以增加向量召回的阈值设定，有些召回内容相关性太低，导致模型胡言乱语", "file": "2023-04-20.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/140", "detail": "如题", "id": 39}
{"title": "输入长度问题", "file": "2023-04-20.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/141", "detail": "感谢作者支持ptuning微调模型。", "id": 40}
{"title": "已有部署好的chatGLM-6b，如何通过接口接入？", "file": "2023-04-20.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/144", "detail": "已有部署好的chatGLM-6b，如何通过接口接入，而不是重新加载一个模型；", "id": 41}
{"title": "执行web_demo.py后，显示Killed，就退出了，是不是配置不足呢？", "file": "2023-04-20.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/146", "detail": "![图片](https://user-images.githubusercontent.com/26102866/233256425-c7aab999-11d7-4de9-867b-23ef18d519e4.png)", "id": 42}
{"title": "执行python cli_demo1.py", "file": "2023-04-20.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/147", "detail": "Traceback (most recent call last):", "id": 43}
{"title": "报错：ImportError: cannot import name 'GENERATION_CONFIG_NAME' from 'transformers.utils'", "file": "2023-04-20.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/149", "detail": "(mychatGLM) PS D:\\Users\\admin3\\zrh\\langchain-ChatGLM> python cli_demo.py", "id": 44}
{"title": "上传文件并加载知识库时，会不停地出现临时文件", "file": "2023-04-21.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/153", "detail": "环境：ubuntu 18.04", "id": 45}
{"title": "向知识库中添加文件后点击”上传文件并加载知识库“后Segmentation fault报错。", "file": "2023-04-23.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/161", "detail": "运行服务后的提示如下：", "id": 46}
{"title": "langchain-serve 集成", "file": "2023-04-24.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/162", "detail": "Hey 我是来自 [langchain-serve](https://github.com/jina-ai/langchain-serve) 的dev！", "id": 47}
{"title": "大佬们，wsl的ubuntu怎么配置用cuda加速，装了运行后发现是cpu在跑", "file": "2023-04-24.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/164", "detail": "大佬们，wsl的ubuntu怎么配置用cuda加速，装了运行后发现是cpu在跑", "id": 48}
{"title": "在github codespaces  docker运行出错", "file": "2023-04-24.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/165", "detail": "docker run -d --restart=always --name chatglm -p 7860:7860 -v /www/wwwroot/code/langchain-ChatGLM:/chatGLM  chatglm", "id": 49}
{"title": "有计划接入Moss模型嘛", "file": "2023-04-24.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/166", "detail": "后续会开展测试，目前主要在优化langchain部分效果，如果有兴趣也欢迎提PR", "id": 50}
{"title": "怎么实现 API 部署？", "file": "2023-04-24.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/168", "detail": "利用 fastapi 实现 API 部署方式，具体怎么实现，有方法说明吗？", "id": 51}
{"title": " 'NoneType' object has no attribute 'message_types_by_name'报错", "file": "2023-04-24.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/169", "detail": "_HISTOGRAMPROTO = DESCRIPTOR.message_types_by_name['HistogramProto']", "id": 52}
{"title": "能否指定自己训练的text2vector模型？", "file": "2023-04-25.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/172", "detail": "请问大佬：", "id": 53}
{"title": "关于项目支持的模型以及quantization_bit潜在的影响的问题", "file": "2023-04-26.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/176", "detail": "作者您好～", "id": 54}
{"title": "运行python3.9 api.py  WARNING:  You must pass the application as an import string to enable 'reload' or 'workers'.", "file": "2023-04-26.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/179", "detail": "api.py文件最下面改成这样试试：", "id": 55}
{"title": "ValidationError: 1 validation error for HuggingFaceEmbeddings model_kwargs   extra fields not permitted (type=value_error.extra)", "file": "2023-04-26.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/180", "detail": "ValidationError: 1 validation error for HuggingFaceEmbeddings", "id": 56}
{"title": "如果没有检索到相关性比较高的，回答“我不知道”", "file": "2023-04-26.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/181", "detail": "如果通过设计system_template，让模型在搜索到的文档都不太相关的情况下回答“我不知道”", "id": 57}
{"title": "请问如果不能联网，6B之类的文件从本地上传需要放到哪里", "file": "2023-04-26.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/182", "detail": "感谢大佬的项目，很有启发~", "id": 58}
{"title": "知识库问答--输入新的知识库名称是中文的话，会报error", "file": "2023-04-27.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/184", "detail": "知识库问答--输入新的知识库名称是中文的话，会报error，选择要加载的知识库那里也不显示之前添加的知识库", "id": 59}
{"title": "现在能通过问题匹配的相似度值，来直接返回文档中的文段，而不经过模型吗？因为有些答案在文档中，模型自己回答，不能回答文档中的答案", "file": "2023-04-27.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/186", "detail": "现在能通过问题匹配的相似度值，来直接返回文档中的文段，而不经过模型吗？因为有些答案在文档中，模型自己回答，不能回答文档中的答案。也就是说，提供向量检索回答+模型回答相结合的策略。如果相似度值高于一定数值，直接返回文档中的文本，没有高于就返回模型的回答或者不知道", "id": 60}
{"title": "TypeError: The type of ChatGLM.callback_manager differs from the new default value; if you wish to change the type of this field, please use a type annotation", "file": "2023-04-27.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/188", "detail": "Mac 运行    python3 ./webui.py 报 TypeError: The type of ChatGLM.callback_manager differs from the new default value; if you wish to change the type of this field, please use a type annotation", "id": 61}
{"title": "Not Enough Memory", "file": "2023-04-27.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/190", "detail": "运行命令行程序python cli_demo.py， 已经成功加载pdf文件, 报“DefaultCPUAllocator: not enough memory: you tried to allocate 458288380900 bytes”错误，请问哪里可以配置default memory", "id": 62}
{"title": "参与开发问题", "file": "2023-04-27.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/191", "detail": "1.是否需要进专门的开发群", "id": 63}
{"title": "对话框中代码片段格式需改进", "file": "2023-04-27.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/192", "detail": "最好能改进下输出代码片段的格式，目前输出的格式还不友好。", "id": 64}
{"title": "请问未来有可能支持belle吗", "file": "2023-04-28.01", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/195", "detail": "如题，谢谢大佬", "id": 65}
{"title": "TypeError: cannot unpack non-iterable NoneType object", "file": "2023-04-28.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/200", "detail": "When i tried to change the knowledge vector store through `init_knowledge_vector_store`, the error `TypeError: cannot unpack non-iterable NoneType object` came out.", "id": 66}
{"title": "生成结果", "file": "2023-04-28.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/202", "detail": "你好，想问一下langchain+chatglm-6B，找到相似匹配的prompt，是直接返回prompt对应的答案信息，还是chatglm-6B在此基础上自己优化答案？", "id": 67}
{"title": "在win、ubuntu下都出现这个错误：attributeerror: 't5forconditionalgeneration' object has no attribute 'stream_chat'", "file": "2023-04-29.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/207", "detail": "在win、ubuntu。下载完模型后，没办法修改代码以执行本地模型，每次都要重新输入路径； LLM 模型、Embedding 模型支持也都在官网下的，在其他项目（wenda）下可以使用", "id": 68}
{"title": "[FEATURE] knowledge_based_chatglm.py: renamed or missing?", "file": "2023-04-30.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/210", "detail": "Not found. Was it renamed? Or, is it missing? How can I get it?", "id": 69}
{"title": "sudo apt-get install -y nvidia-container-toolkit-base执行报错", "file": "2023-05-01.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/211", "detail": "**问题描述 / Problem Description**", "id": 70}
{"title": "效果不佳几乎答不上来", "file": "2023-05-01.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/212", "detail": "提供了50条问答的docx文件", "id": 71}
{"title": "有没有可能新增一个基于chatglm api调用的方式构建langchain", "file": "2023-05-02.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/218", "detail": "我有两台8G GPU/40G内存的服务器，一个台做成了chatglm的api ；想基于另外一台服务器部署langchain；网上好像没有类似的代码。", "id": 72}
{"title": "电脑是intel的集成显卡；  运行时告知我找不到nvcuda.dll，模型无法运行", "file": "2023-05-02.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/219", "detail": "您好，我的电脑是intel的集成显卡，不过CPU是i5-11400 @ 2.60GHz   ，内存64G；", "id": 73}
{"title": "根据langchain官方的文档和使用模式，是否可以改Faiss为Elasticsearch？会需要做哪些额外调整？求解", "file": "2023-05-03.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/221", "detail": "本人新手小白，由于业务模式的原因（有一些自己的场景和优化），希望利用Elasticsearch做这个体系内部的检索机制，不知道是否可以替换，同时，还会涉及到哪些地方的改动？或者说可能会有哪些其他影响，希望作者和大佬们不吝赐教！", "id": 74}
{"title": "请问未来有可能支持t5吗", "file": "2023-05-04.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/224", "detail": "请问可能支持基於t5的模型吗?", "id": 75}
{"title": "[BUG] 内存溢出 / torch.cuda.OutOfMemoryError:", "file": "2023-05-04.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/229", "detail": "**问题描述 / Problem Description**", "id": 76}
{"title": "报错 No module named 'chatglm_llm'", "file": "2023-05-04.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/230", "detail": "明明已经安装了包，却在python里吊不出来", "id": 77}
{"title": "能出一个api部署的描述文档吗", "file": "2023-05-04.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/233", "detail": "**功能描述 / Feature Description**", "id": 78}
{"title": "使用docs/API.md 出错", "file": "2023-05-04.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/234", "detail": "使用API.md文档2种方法，出错", "id": 79}
{"title": "加载pdf文档报错？", "file": "2023-05-05.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/238", "detail": "ew one with MEAN pooling.", "id": 80}
{"title": "上传的本地知识文件后再次上传不能显示，只显示成功了一个，别的上传成功后再次刷新就没了", "file": "2023-05-05.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/239", "detail": "您好，项目有很大启发，感谢~", "id": 81}
{"title": "创建了新的虚拟环境，安装了相关包，并且自动下载了相关的模型，但是仍旧出现：OSError: Unable to load weights from pytorch checkpoint file for", "file": "2023-05-05.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/240", "detail": "![78ac8e663fdc312d0e9d78da95925c4](https://user-images.githubusercontent.com/34124260/236378728-9ea4424f-0f7f-4013-9d33-820b723de321.png)", "id": 82}
{"title": "[BUG] 数据加载不进来", "file": "2023-05-05.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/243", "detail": "使用的.txt格式，utf-8编码，报以下错误", "id": 83}
{"title": "不能读取pdf", "file": "2023-05-05.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/244", "detail": "请问是webui还是cli_demo", "id": 84}
{"title": "本地txt文件有500M，加载的时候很慢，如何提高速度？", "file": "2023-05-06.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/251", "detail": "![yayRzxSYHP](https://user-images.githubusercontent.com/109277248/236592902-f5ab338d-c1e9-43dc-ae16-9df2cd3c1378.jpg)", "id": 85}
{"title": "[BUG] gradio上传知识库后刷新之后 知识库就不见了  只有重启才能看到之前的上传的知识库", "file": "2023-05-06.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/253", "detail": "gradio上传知识库后刷新之后 知识库就不见了  只有重启才能看到之前的上传的知识库", "id": 86}
{"title": "[FEATURE] 可以支持 OpenAI 的模型嘛？比如 GPT-3、GPT-3.5、GPT-4；embedding 增加 text-embedding-ada-002", "file": "2023-05-06.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/254", "detail": "**功能描述 / Feature Description**", "id": 87}
{"title": "[FEATURE] 能否增加对于milvus向量数据库的支持 / Concise description of the feature", "file": "2023-05-06.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/256", "detail": "**功能描述 / Feature Description**", "id": 88}
{"title": "CPU和GPU上跑，除了速度有区别，准确率效果回答上有区别吗？", "file": "2023-05-06.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/259", "detail": "理论上没有区别", "id": 89}
{"title": "m1，请问在生成回答时怎么看是否使用了mps or cpu？", "file": "2023-05-06.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/260", "detail": "m1，请问在生成回答时怎么看是否使用了mps or cpu？", "id": 90}
{"title": "知识库一刷新就没了", "file": "2023-05-07.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/263", "detail": "知识库上传后刷新就没了", "id": 91}
{"title": "本地部署报没有模型", "file": "2023-05-07.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/267", "detail": "建议在下载llm和embedding模型至本地后在configs/model_config中写入模型本地存储路径后再运行", "id": 92}
{"title": "[BUG] python3: can't open file 'webui.py': [Errno 2] No such file or directory", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/269", "detail": "**问题描述 / Problem Description**", "id": 93}
{"title": "模块缺失提示", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/271", "detail": "因为已有自己使用的docker环境，直接启动webui.py，提示", "id": 94}
{"title": "运行api.py后，执行curl -X POST \"http://127.0.0.1:7861\" 报错？", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/272", "detail": "执行curl -X POST \"http://127.0.0.1:7861\" \\      -H 'Content-Type: application/json' \\      -d '{\"prompt\": \"你好\", \"history\": []}'，报错怎么解决", "id": 95}
{"title": "[BUG] colab安装requirements提示protobuf版本问题？", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/273", "detail": "pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.", "id": 96}
{"title": "请问项目里面向量相似度使用了什么方法计算呀？", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/275", "detail": "基本按照langchain里的FAISS.similarity_search_with_score_by_vector实现", "id": 97}
{"title": "[BUG] 安装detectron2后，pdf无法加载", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/276", "detail": "**问题描述 / Problem Description**", "id": 98}
{"title": "[BUG] 使用ChatYuan-V2模型无法流式输出，会报错", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/277", "detail": "一方面好像是ChatYuan本身不支持stream_chat，有人在clueai那边提了issue他们说还没开发，所以估计这个attribute调不起来；但是另一方面看报错好像是T5模型本身就不是decoder-only模型，所以不能流式输出吧（个人理解）", "id": 99}
{"title": "[BUG] 无法加载text2vec模型", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/278", "detail": "**问题描述 / Problem Description**", "id": 100}
{"title": "请问能否增加网络搜索功能", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/281", "detail": "请问能否增加网络搜索功能", "id": 101}
{"title": "[FEATURE] 结构化数据sql、excel、csv啥时会支持呐。", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/283", "detail": "**功能描述 / Feature Description**", "id": 102}
{"title": "TypeError: ChatGLM._call() got an unexpected keyword argument 'stop'", "file": "2023-05-08.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/284", "detail": "No sentence-transformers model found with name D:\\DevProject\\langchain-ChatGLM\\GanymedeNil\\text2vec-large-chinese. Creating a new one with MEAN pooling.", "id": 103}
{"title": "关于api.py的一些bug和设计逻辑问题？", "file": "2023-05-09.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/285", "detail": "首先冒昧的问一下，这个api.py，开发者大佬们是在自己电脑上测试后确实没问题吗？", "id": 104}
{"title": "有没有租用的算力平台上，运行api.py后，浏览器http://localhost:7861/报错", "file": "2023-05-09.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/287", "detail": "是不是租用的gpu平台上都会出现这个问题？？？", "id": 105}
{"title": "请问一下项目中有用到文档段落切割方法吗？", "file": "2023-05-09.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/288", "detail": "text_load中的文档切割方法用上了吗？在代码中看好像没有用到？", "id": 106}
{"title": "报错   raise ValueError(f\"Knowledge base {knowledge_base_id} not found\") ValueError: Knowledge base ./vector_store not found", "file": "2023-05-09.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/289", "detail": "File \"/root/autodl-tmp/chatglm/langchain-ChatGLM-master/api.py\", line 183, in chat", "id": 107}
{"title": "能接入vicuna模型吗", "file": "2023-05-09.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/290", "detail": "目前本地已经有了vicuna模型能直接接入吗？", "id": 108}
{"title": "[BUG] 提问公式相关问题大概率爆显存", "file": "2023-05-09.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/291", "detail": "**问题描述 / Problem Description**", "id": 109}
{"title": "安装pycocotools失败，找了好多方法都不能解决。", "file": "2023-05-10.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/292", "detail": "**问题描述 / Problem Description**", "id": 110}
{"title": "使用requirements安装，PyTorch安装的是CPU版本", "file": "2023-05-10.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/294", "detail": "如题目，使用requirements安装，PyTorch安装的是CPU版本，运行程序的时候，也是使用CPU在工作。", "id": 111}
{"title": "能不能给一个毛坯服务器的部署教程", "file": "2023-05-10.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/298", "detail": "“开发部署”你当成服务器的部署教程用就行了。", "id": 112}
{"title": " Error(s) in loading state_dict for ChatGLMForConditionalGeneration:", "file": "2023-05-10.02", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/299", "detail": "运行中出现的问题，7860的端口页面显示不出来，求助。", "id": 113}
{"title": "ChatYuan-large-v2模型加载失败", "file": "2023-05-10.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/300", "detail": "**实际结果 / Actual Result**", "id": 114}
{"title": "新增摘要功能", "file": "2023-05-10.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/303", "detail": "你好，后续会考虑新增对长文本信息进行推理和语音理解功能吗？比如生成摘要", "id": 115}
{"title": "[BUG] pip install -r requirements.txt 出错", "file": "2023-05-10.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/304", "detail": "pip install langchain -i https://pypi.org/simple", "id": 116}
{"title": "[BUG] 上传知识库文件报错", "file": "2023-05-10.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/305", "detail": "![19621e29eaa547d01213bee53d81e6a](https://github.com/imClumsyPanda/langchain-ChatGLM/assets/84606552/7f6ceb46-e494-4b0e-939c-23b585a6d9d8)", "id": 117}
{"title": "[BUG] AssertionError: <class 'gradio.layouts.Accordion'> Component with id 41 not a valid input component.", "file": "2023-05-10.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/306", "detail": "**问题描述 / Problem Description**", "id": 118}
{"title": "[BUG] CUDA out of memory with container deployment", "file": "2023-05-10.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/310", "detail": "**问题描述 / Problem Description**", "id": 119}
{"title": "[FEATURE] 增加微调训练功能", "file": "2023-05-11.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/311", "detail": "**功能描述 / Feature Description**", "id": 120}
{"title": "如何使用多卡部署，多个gpu", "file": "2023-05-11.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/315", "detail": "机器上有多个gpu,如何全使用了", "id": 121}
{"title": "请问这个知识库问答，和chatglm的关系是什么", "file": "2023-05-11.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/319", "detail": "这个知识库问答，哪部分关联到了chatglm，是不是没有这个chatglm，知识库问答也可单单拎出来", "id": 122}
{"title": "[BUG] 运行的时候报错ImportError: libcudnn.so.8: cannot open shared object file: No such file or directory", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/324", "detail": "**问题描述 / Problem Description**raceback (most recent call last):", "id": 123}
{"title": "webui启动成功，但有报错", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/325", "detail": "**问题描述 / Problem Description**", "id": 124}
{"title": "切换MOSS的时候报错", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/327", "detail": "danshi但是发布的源码中，", "id": 125}
{"title": "vicuna模型是否能接入？", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/328", "detail": "您好！关于MOSS模型和vicuna模型，都是AutoModelForCausalLM来加载模型的，但是稍作更改（模型路径这些）会报这个错误。这个错误的造成是什么", "id": 126}
{"title": "你好，请问一下在阿里云CPU服务器上跑可以吗？可以的话比较理想的cpu配置是什么？", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/330", "detail": "你好，请问一下在阿里云CPU服务器上跑可以吗？可以的话比较理想的cpu配置是什么？", "id": 127}
{"title": "你好，请问8核32g的CPU可以跑多轮对话吗？", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/331", "detail": "什么样的cpu配置比较好呢？我目前想部署CPU下的多轮对话？", "id": 128}
{"title": "[BUG] 聊天内容输入超过10000个字符系统出现错误", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/332", "detail": "聊天内容输入超过10000个字符系统出现错误，如下图所示：", "id": 129}
{"title": "能增加API的多用户访问接口部署吗？", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/333", "detail": "默认部署程序仅支持单用户访问，多用户则需要排队访问。测试过相关的几个Github多用户工程，但是其中一些仍然不满足要求。本节将系统介绍如何实现多用户同时访问ChatGLM的部署接口，包括http、websocket（流式输出，stream）和web页面等方式，主要目录如下所示。", "id": 130}
{"title": "多卡部署", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/334", "detail": "用单机多卡或多机多卡，fastapi部署模型，怎样提高并发", "id": 131}
{"title": "WEBUI能否指定知识库目录？", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/335", "detail": "**功能描述 / Feature Description**", "id": 132}
{"title": "[BUG] Cannot read properties of undefined (reading 'error')", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/336", "detail": "**问题描述 / Problem Description**", "id": 133}
{"title": "[BUG] 1 validation error for HuggingFaceEmbeddings model_kwargs extra fields not permitted.", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/337", "detail": "模型加载到 100% 后出现问题：", "id": 134}
{"title": "上传知识库需要重启能不能修复一下", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/338", "detail": "挺严重的这个问题", "id": 135}
{"title": "[BUG] 4块v100卡爆显存，在LLM会话模式也一样", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/339", "detail": "**问题描述 / Problem Description**", "id": 136}
{"title": "针对上传的文件配置不同的TextSpliter", "file": "2023-05-12.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/341", "detail": "1. 目前的ChineseTextSpliter切分对英文尤其是代码文件不友好，而且限制固定长度；导致对话结果不如人意", "id": 137}
{"title": "[FEATURE] 未来可增加Bloom系列模型吗？根据甲骨易的测试，这系列中文评测效果不错", "file": "2023-05-13.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/346", "detail": "**功能描述 / Feature Description**", "id": 138}
{"title": "[BUG] v0.1.12打包镜像后启动webui.py失败 / Concise description of the issue", "file": "2023-05-13.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/347", "detail": "**问题描述 / Problem Description**", "id": 139}
{"title": "切换MOSS模型时报错", "file": "2023-05-13.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/349", "detail": "昨天问了下，说是transformers版本不对，需要4.30.0，发现没有这个版本，今天更新到4.29.1，依旧报错，错误如下", "id": 140}
{"title": "[BUG] pdf文档加载失败", "file": "2023-05-13.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/350", "detail": "**问题描述 / Problem Description**", "id": 141}
{"title": "建议可以在后期增强一波注释，这样也有助于更多人跟进提PR", "file": "2023-05-13.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/351", "detail": "知道作者和团队在疯狂更新审查代码，只是建议后续稳定后可以把核心代码进行一些注释的补充，从而能帮助更多人了解各个模块作者的思路从而提出更好的优化。", "id": 142}
{"title": "[FEATURE] MOSS 量化版支援", "file": "2023-05-13.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/353", "detail": "**功能描述 / Feature Description**", "id": 143}
{"title": "[BUG] moss模型无法加载", "file": "2023-05-13.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/356", "detail": "**问题描述 / Problem Description**", "id": 144}
{"title": "[BUG] load_doc_qa.py 中的 load_file 函数有bug", "file": "2023-05-14.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/358", "detail": "原函数为：", "id": 145}
{"title": "[FEATURE] API模式，知识库加载优化", "file": "2023-05-14.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/359", "detail": "如题，当前版本，每次调用本地知识库接口，都将加载一次知识库，是否有更好的方式？", "id": 146}
{"title": "运行Python api.py脚本后端部署后，怎么使用curl命令调用？", "file": "2023-05-15.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/361", "detail": "也就是说，我现在想做个对话机器人，想和公司的前后端联调？怎么与前后端相互调用呢？可私信，有偿解答！！！", "id": 147}
{"title": "上传知识库需要重启能不能修复一下", "file": "2023-05-15.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/363", "detail": "上传知识库需要重启能不能修复一下", "id": 148}
{"title": "[BUG] pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple", "file": "2023-05-15.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/364", "detail": "我的python是3.8.5的", "id": 149}
{"title": "pip install gradio  报错", "file": "2023-05-15.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/367", "detail": "大佬帮我一下", "id": 150}
{"title": "[BUG] pip install gradio 一直卡不动", "file": "2023-05-15.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/369", "detail": "![aba82742dd9d4d242181662eb5027a7](https://github.com/imClumsyPanda/langchain-ChatGLM/assets/84606552/cd9600d9-f6e7-46b7-b1be-30ed8b99f76b)", "id": 151}
{"title": "[BUG] 简洁阐述问题 / Concise description of the issue", "file": "2023-05-16.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/370", "detail": "初次加载本地知识库成功，但提问后，就无法重写加载本地知识库", "id": 152}
{"title": "[FEATURE] 简洁阐述功能 / Concise description of the feature", "file": "2023-05-16.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/371", "detail": "**功能描述 / Feature Description**", "id": 153}
{"title": "在windows上，模型文件默认会安装到哪", "file": "2023-05-16.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/372", "detail": "-------------------------------------------------------------------------------", "id": 154}
{"title": "[FEATURE] 兼顾对话管理", "file": "2023-05-16.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/374", "detail": "如何在知识库检索的情况下，兼顾对话管理？", "id": 155}
{"title": "llm device: cpu embedding device: cpu", "file": "2023-05-16.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/376", "detail": "**问题描述 / Problem Description**", "id": 156}
{"title": "[FEATURE] 简洁阐述功能 /文本文件的知识点之间使用什么分隔符可以分割？", "file": "2023-05-16.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/377", "detail": "**功能描述 / Feature Description**", "id": 157}
{"title": "[BUG] 上传文件失败：PermissionError: [WinError 32] 另一个程序正在使用此文件，进程无法访问。", "file": "2023-05-16.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/379", "detail": "**问题描述 / Problem Description**", "id": 158}
{"title": "[BUG] 执行python api.py 报错", "file": "2023-05-16.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/383", "detail": "错误信息", "id": 159}
{"title": "model_kwargs extra fields not permitted (type=value_error.extra)", "file": "2023-05-16.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/384", "detail": "大家好，请问这个有遇到的么,？", "id": 160}
{"title": "[BUG] 简洁阐述问题 / Concise description of the issue", "file": "2023-05-17.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/385", "detail": "执行的时候出现了ls1 = [ls[0]]", "id": 161}
{"title": "[FEATURE] 性能优化", "file": "2023-05-17.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/388", "detail": "**功能描述 / Feature Description**", "id": 162}
{"title": "[BUG] Moss模型问答，RuntimeError: probability tensor contains either inf, nan or element < 0", "file": "2023-05-17.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/390", "detail": "**问题描述 / Problem Description**", "id": 163}
{"title": "有没有人知道v100GPU的32G显存，会报错吗？支持V100GPU吗？", "file": "2023-05-17.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/392", "detail": "**问题描述 / Problem Description**", "id": 164}
{"title": "针对于编码问题比如'gbk' codec can't encode character '\\xab' in position 14: illegal multibyte sequence粗浅的解决方法", "file": "2023-05-17.03", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/397", "detail": "**功能描述 / Feature Description**", "id": 165}
{"title": "Could not import sentence_transformers python package. Please install it with `pip install sentence_transformers`.", "file": "2023-05-18.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/400", "detail": "**问题描述 / Problem Description**", "id": 166}
{"title": "支持模型问答与检索问答", "file": "2023-05-18.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/401", "detail": "不同的query，根据意图不一致，回答也应该不一样。", "id": 167}
{"title": "文本分割的时候，能不能按照txt文件的每行进行分割，也就是按照换行符号\\n进行分割？？？", "file": "2023-05-18.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/403", "detail": "下面的代码应该怎么修改？", "id": 168}
{"title": "local_doc_qa/local_doc_chat 接口响应是串行", "file": "2023-05-18.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/405", "detail": "**问题描述 / Problem Description**", "id": 169}
{"title": "为什么找到出处了,但是还是无法回答该问题?", "file": "2023-05-18.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/406", "detail": "![图片](https://github.com/imClumsyPanda/langchain-ChatGLM/assets/3349611/1fc81d61-2409-4330-9065-fdda1a27c86a)", "id": 170}
{"title": "请问下:知识库测试中的:添加单条内容,如果换成文本导入是是怎样的格式?我发现添加单条内容测试效果很好.", "file": "2023-05-18.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/412", "detail": "我发现在知识库测试中`添加单条内容`,并且勾选`禁止内容分句入库`,即使 `不开启上下文关联`的测试效果都非常好.", "id": 171}
{"title": "[BUG] 无法配置知识库", "file": "2023-05-18.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/413", "detail": "**问题描述 / Problem Description**", "id": 172}
{"title": "[BUG] 部署在阿里PAI平台的EAS上访问页面是白屏", "file": "2023-05-19.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/414", "detail": "**问题描述 / Problem Description**", "id": 173}
{"title": "API部署后调用/local_doc_qa/local_doc_chat 返回Knowledge base samples not found", "file": "2023-05-19.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/416", "detail": "入参", "id": 174}
{"title": "[FEATURE] 上传word另存为的txt文件报 'ascii' codec can't decode byte 0xb9 in position 6: ordinal not in range(128)", "file": "2023-05-20.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/421", "detail": "上传word另存为的txt文件报", "id": 175}
{"title": "创建保存的知识库刷新后没有出来，这个知识库是永久保存的吗？可以连外部的 向量知识库吗？", "file": "2023-05-21.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/422", "detail": "创建保存的知识库刷新后没有出来，这个知识库是永久保存的吗？可以连外部的 向量知识库吗？", "id": 176}
{"title": "[BUG] 用colab运行，无法加载模型，报错：'NoneType' object has no attribute 'message_types_by_name'", "file": "2023-05-21.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/423", "detail": "**问题描述 / Problem Description**", "id": 177}
{"title": "请问是否需要用到向量数据库？以及什么时候需要用到向量数据库？", "file": "2023-05-21.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/424", "detail": "目前用的是 text2vec  ， 请问是否需要用到向量数据库？以及什么时候需要用到向量数据库？", "id": 178}
{"title": "huggingface模型引用问题", "file": "2023-05-22.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/427", "detail": "它最近似乎变成了一个Error？", "id": 179}
{"title": "你好，加载本地txt文件出现这个killed错误，TXT文件有100M左右大小。原因是？谢谢。", "file": "2023-05-22.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/429", "detail": "<img width=\"677\" alt=\"929aca3b22b8cd74e997a87b61d241b\" src=\"https://github.com/imClumsyPanda/langchain-ChatGLM/assets/109277248/24024522-c884-4170-b5cf-a498491bd8bc\">", "id": 180}
{"title": "想请问一下，关于对本地知识的管理是如何管理？例如：通过http API接口添加数据 或者 删除某条数据", "file": "2023-05-22.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/430", "detail": "例如：通过http API接口添加、删除、修改 某条数据。", "id": 181}
{"title": "[FEATURE] 双栏pdf识别问题", "file": "2023-05-22.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/432", "detail": "试了一下模型，感觉对单栏pdf识别的准确性较高，但是由于使用的基本是ocr的技术，对一些双栏pdf论文识别出来有很多问题，请问有什么办法改善吗？", "id": 182}
{"title": "部署启动小问题，小弟初学求大佬解答", "file": "2023-05-22.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/433", "detail": "1.python loader/image_loader.py时，提示ModuleNotFoundError: No module named 'configs'，但是跑python webui.py还是还能跑", "id": 183}
{"title": "能否支持检测到目录下文档有增加而去增量加载文档，不影响前台对话，其实就是支持读写分离。如果能支持查询哪些文档向量化了，删除过时文档等就更好了，谢谢。", "file": "2023-05-22.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/434", "detail": "**功能描述 / Feature Description**", "id": 184}
{"title": "[BUG] 简洁阐述问题 / windows 下cuda错误，请用https://github.com/Keith-Hon/bitsandbytes-windows.git", "file": "2023-05-22.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/435", "detail": "pip install git+https://github.com/Keith-Hon/bitsandbytes-windows.git", "id": 185}
{"title": "[BUG] from commit 33bbb47,  Required library version not found: libbitsandbytes_cuda121_nocublaslt.so. Maybe you need to compile it from source?", "file": "2023-05-23.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/438", "detail": "**问题描述 / Problem Description**", "id": 186}
{"title": "[BUG] 简洁阐述问题 / Concise description of the issue上传60m的txt文件报错，显示超时，请问这个能上传的文件大小有限制吗", "file": "2023-05-23.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/439", "detail": "ERROR 2023-05-23 11:13:09,627-1d: Timeout reached while detecting encoding for ./docs/GLM模型格式数据.txt", "id": 187}
{"title": "[BUG] TypeError: issubclass() arg 1 must be a class", "file": "2023-05-23.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/440", "detail": "**问题描述**", "id": 188}
{"title": "执行python3 webui.py后，一直提示”模型未成功加载，请到页面左上角\"模型配置\"选项卡中重新选择后点击\"加载模型\"按钮“", "file": "2023-05-23.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/441", "detail": "**问题描述 / Problem Description**", "id": 189}
{"title": "是否能提供网页文档得导入支持", "file": "2023-05-23.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/444", "detail": "现在很多都是在线文档作为协作得工具，所以通过URL导入在线文档需求更大", "id": 190}
{"title": "[BUG] history 索引问题", "file": "2023-05-23.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/445", "detail": "在比较对话框的history和模型chat function 中的history时， 发现并不匹配，在传入 llm._call 时，history用的索引是不是有点问题，导致上一轮对话的内容并不输入给模型。", "id": 191}
{"title": "[BUG] moss_llm没有实现", "file": "2023-05-23.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/447", "detail": "有些方法没支持，如history_len", "id": 192}
{"title": "请问langchain-ChatGLM如何删除一条本地知识库的数据？", "file": "2023-05-23.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/448", "detail": "例如：用户刚刚提交了一条错误的数据到本地知识库中了，现在如何在本地知识库从找到，并且对此删除。", "id": 193}
{"title": "[BUG] 简洁阐述问题 / UnboundLocalError: local variable 'resp' referenced before assignment", "file": "2023-05-24.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/450", "detail": "在最新一版的代码中， 运行api.py 出现了以上错误（UnboundLocalError: local variable 'resp' referenced before assignment）， 通过debug的方式观察到local_doc_qa.llm.generatorAnswer(prompt=question, history=history,streaming=True)可能不返回任何值。", "id": 194}
{"title": "请问有没有 PROMPT_TEMPLATE 能让模型不回答敏感问题", "file": "2023-05-24.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/452", "detail": "## PROMPT_TEMPLATE问题", "id": 195}
{"title": "[BUG] 测试环境 Python 版本有误", "file": "2023-05-24.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/456", "detail": "**问题描述 / Problem Description**", "id": 196}
{"title": "[BUG] webui 部署后样式不正确", "file": "2023-05-24.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/458", "detail": "**问题描述 / Problem Description**", "id": 197}
{"title": "配置默认LLM模型的问题", "file": "2023-05-24.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/459", "detail": "**问题描述 / Problem Description**", "id": 198}
{"title": "[FEATURE]是时候更新一下autoDL的镜像了", "file": "2023-05-24.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/460", "detail": "如题，跑了下autoDL的镜像，发现是4.27号的，git pull新版本的代码功能+老的依赖环境，各种奇奇怪怪的问题。", "id": 199}
{"title": "[BUG] tag:0.1.13 以cpu模式下，想使用本地模型无法跑起来，各种路径参数问题", "file": "2023-05-24.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/462", "detail": "-------------------------------------------------------------------------------", "id": 200}
{"title": "[BUG] 有没有同学遇到过这个错！！！加载本地txt文件出现这个killed错误，TXT文件有100M左右大小。", "file": "2023-05-25.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/463", "detail": "运行cli_demo.py。是本地的txt文件太大了吗？100M左右。", "id": 201}
{"title": "API版本能否提供WEBSOCKET的流式接口", "file": "2023-05-25.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/464", "detail": "webui 版本中，采用了WS的流式输出，整体感知反应很快", "id": 202}
{"title": "[BUG] 安装bug记录", "file": "2023-05-25.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/465", "detail": "按照[install文档](https://github.com/imClumsyPanda/langchain-ChatGLM/blob/master/docs/INSTALL.md)安装的，", "id": 203}
{"title": "VUE的pnmp i执行失败的修复-用npm i命令即可", "file": "2023-05-25.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/466", "detail": "感谢作者！非常棒的应用，用的很开心。", "id": 204}
{"title": "请教个问题，有没有人知道cuda11.4是否支持？？？", "file": "2023-05-25.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/467", "detail": "请教个问题，有没有人知道cuda11.4是否支持？？？", "id": 205}
{"title": "请问有实现多轮问答中基于问题的搜索上下文关联么", "file": "2023-05-25.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/468", "detail": "在基于知识库的多轮问答中，第一个问题讲述了一个主题，后续的问题描述没有包含这个主题的关键词，但又存在上下文的关联。如果用后续问题去搜索知识库有可能会搜索出无关的信息，从而导致大模型无法正确回答问题。请问这个项目要考虑这种情况吗？", "id": 206}
{"title": "[BUG] 内存不足的问题", "file": "2023-05-26.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/470", "detail": "我用了本地的chatglm-6b-int4模型，然后显示了内存不足（win10+32G内存+1080ti11G），一般需要多少内存才足够？这个bug应该如何解决？", "id": 207}
{"title": "[BUG] 纯内网环境安装pycocotools失败", "file": "2023-05-26.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/472", "detail": "**问题描述 / Problem Description**", "id": 208}
{"title": "[BUG] webui.py 重新加载模型会导致 KeyError", "file": "2023-05-26.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/473", "detail": "**问题描述 / Problem Description**", "id": 209}
{"title": "chatyuan无法使用", "file": "2023-05-26.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/475", "detail": "**问题描述 / Problem Description**", "id": 210}
{"title": "[BUG] 文本分割模型AliTextSplitter存在bug，会把“.”作为分割符", "file": "2023-05-26.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/476", "detail": "阿里达摩院的语义分割模型存在bug，默认会把\".”作为分割符进行分割而不管上下文语义。是否还有其他分割符则未知。建议的修改方案：把“.”统一替换为其他字符，分割后再替换回来。或者添加其他分割模型。", "id": 211}
{"title": "[BUG] RuntimeError: Error in faiss::FileIOReader::FileIOReader(const char*) a", "file": "2023-05-27.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/479", "detail": "**问题描述 / Problem Description**", "id": 212}
{"title": "[FEATURE] 安装，为什么conda create要额外指定路径 用-p ，而不是默认的/envs下面", "file": "2023-05-28.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/481", "detail": "##**功能描述 / Feature Description**", "id": 213}
{"title": "[小白求助] 通过Anaconda执行webui.py后，无法打开web链接", "file": "2023-05-28.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/485", "detail": "在执行webui.py命令后，http://0.0.0.0:7860复制到浏览器后无法打开，显示“无法访问此网站”。", "id": 214}
{"title": "[BUG] 使用 p-tuningv2后的模型，重新加载报错", "file": "2023-05-29.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/486", "detail": "把p-tunningv2训练完后的相关文件放到了p-tunningv2文件夹下，勾选使用p-tuningv2点重新加载模型，控制台输错错误信息：", "id": 215}
{"title": "[小白求助]  服务器上执行webui.py后，在本地无法打开web链接", "file": "2023-05-29.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/487", "detail": "此项目执行在xxx.xx.xxx.xxx服务器上，我在webui.py上的代码为  (demo", "id": 216}
{"title": "[FEATURE] 能不能支持VisualGLM-6B", "file": "2023-05-29.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/488", "detail": "**功能描述 / Feature Description**", "id": 217}
{"title": "你好，问一下各位，后端api部署的时候，支持多用户同时问答吗？？？", "file": "2023-05-29.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/489", "detail": "支持多用户的话，最多支持多少用户问答？根据硬件而定吧？", "id": 218}
{"title": "V100GPU显存占满，而利用率却为0，这是为什么？", "file": "2023-05-29.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/491", "detail": "<img width=\"731\" alt=\"de45fe2b6cb76fa091b6e8f76a3de60\" src=\"https://github.com/imClumsyPanda/langchain-ChatGLM/assets/109277248/c32efd52-7dbf-4e9b-bd4d-0944d73d0b8b\">", "id": 219}
{"title": "[求助] 如果在公司内部搭建产品知识库，使用INT-4模型，200人规模需要配置多少显存的服务器？", "file": "2023-05-29.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/492", "detail": "如题，计划给公司搭一个在线知识库。", "id": 220}
{"title": "你好，请教个问题，目前问答回复需要20秒左右，如何提高速度？V10032G服务器。", "file": "2023-05-29.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/493", "detail": "**问题描述 / Problem Description**", "id": 221}
{"title": "[FEATURE] 如何实现只匹配下文，而不要上文的结果", "file": "2023-05-29.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/494", "detail": "在构建自己的知识库时，主要采用问答对的形式，那么也就是我需要的回答是在我的问题下面的内容，但是目前设置了chunk_size的值以后匹配的是上下文的内容，但我实际并不需要上文的。为了实现更完整的展示下面的答案，我只能调大chunk_size的值，但实际上上文的一半内容都是我不需要的。也就是扔了一半没用的东西给prompt，在faiss.py中我也没找到这块的一些描述，请问该如何进行修改呢？", "id": 222}
{"title": "你好，问一下，我调用api.py部署，为什么用ip加端口可以使用postman调用，而改为域名使用postman无法调用？", "file": "2023-05-30.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/497", "detail": "![5ufBSWxLyF](https://github.com/imClumsyPanda/langchain-ChatGLM/assets/109277248/70e2fbac-5699-48d0-b0d1-3dc84fd042c2)", "id": 223}
{"title": "调用api.py中的stream_chat，返回source_documents中出现中文乱码。", "file": "2023-05-30.04", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/498", "detail": "-------------------------------------------------------------------------------", "id": 224}
{"title": "[BUG] 捉个虫，api.py中的stream_chat解析json问题", "file": "2023-05-30.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/501", "detail": "**问题描述 / Problem Description**", "id": 225}
{"title": "windows本地部署遇到了omp错误", "file": "2023-05-31.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/502", "detail": "**问题描述 / Problem Description**", "id": 226}
{"title": "[BUG] bug14 ,\"POST /local_doc_qa/upload_file HTTP/1.1\" 422 Unprocessable Entity", "file": "2023-05-31.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/503", "detail": "上传的文件报错，返回错误，api.py", "id": 227}
{"title": "你好，请教个问题，api.py部署的时候，如何改为多线程调用？谢谢", "file": "2023-05-31.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/505", "detail": "目前的api.py脚本不支持多线程", "id": 228}
{"title": "你好，请教一下。api.py部署的时候，能不能提供给后端流失返回结果。", "file": "2023-05-31.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/507", "detail": "curl -X 'POST' \\", "id": 229}
{"title": "流式输出，流式接口，使用server-sent events技术。", "file": "2023-05-31.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/508", "detail": "想这样一样，https://blog.csdn.net/weixin_43228814/article/details/130063010", "id": 230}
{"title": "计划增加流式输出功能吗？ChatGLM模型通过api方式调用响应时间慢怎么破，Fastapi流式接口来解惑，能快速提升响应速度", "file": "2023-05-31.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/509", "detail": "**问题描述 / Problem Description**", "id": 231}
{"title": "[BUG] 知识库上传时发生ERROR (could not open xxx for reading: No such file or directory)", "file": "2023-05-31.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/510", "detail": "**问题描述 / Problem Description**", "id": 232}
{"title": "api.py脚本打算增加SSE流式输出吗？", "file": "2023-05-31.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/511", "detail": "curl调用的时候可以检测第一个字，从而提升回复的体验", "id": 233}
{"title": "[BUG] 使用tornado实现webSocket，可以多个客户端同时连接，并且实现流式回复，但是多个客户端同时使用，答案就很乱，是模型不支持多线程吗", "file": "2023-05-31.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/512", "detail": "import asyncio", "id": 234}
{"title": "支持 chinese_alpaca_plus_lora 吗  基于llama的", "file": "2023-06-01.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/514", "detail": "支持 chinese_alpaca_plus_lora 吗  基于llama的，https://github.com/ymcui/Chinese-LLaMA-Alpaca这个项目的", "id": 235}
{"title": "[BUG] 现在能读图片的pdf了，但是文字的pdf反而读不了了，什么情况？？？", "file": "2023-06-01.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/515", "detail": "**问题描述 / Problem Description**", "id": 236}
{"title": "在推理的过程中卡住不动，进程无法正常结束", "file": "2023-06-01.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/516", "detail": "**问题描述 / Problem Description**", "id": 237}
{"title": "curl调用的时候，从第二轮开始，curl如何传参可以实现多轮对话？", "file": "2023-06-01.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/517", "detail": "第一轮调用：", "id": 238}
{"title": "建议添加api.py部署后的日志管理功能？", "file": "2023-06-01.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/518", "detail": "-------------------------------------------------------------------------------", "id": 239}
{"title": "有大佬知道，怎么多线程部署api.py脚本吗？", "file": "2023-06-01.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/519", "detail": "api.py部署后，使用下面的请求，时间较慢，好像是单线程，如何改为多线程部署api.py：", "id": 240}
{"title": "[BUG] 上传文件到知识库 任何格式与内容都永远失败", "file": "2023-06-01.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/520", "detail": "上传知识库的时候，传txt无法解析，就算是穿content/sample里的样例txt也无法解析，上传md、pdf等都无法加载，会持续性等待，等到了超过30分钟也不行。", "id": 241}
{"title": "关于prompt_template的问题", "file": "2023-06-01.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/521", "detail": "请问这段prompt_template是什么意思，要怎么使用？可以给一个具体模板参考下吗？", "id": 242}
{"title": "[BUG] 简洁阐述问题 / Concise description of the issue", "file": "2023-06-01.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/522", "detail": "**问题描述 / Problem Description**", "id": 243}
{"title": "中文分词句号处理（关于表达金额之间的\".\"）", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/523", "detail": "建议处理12.6亿元的这样的分词，最好别分成12 和6亿这样的，需要放到一起", "id": 244}
{"title": "ImportError: cannot import name 'inference' from 'paddle'", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/526", "detail": "在网上找了一圈，有说升级paddle的，我做了还是没有用，有说安装paddlepaddle的，我找了豆瓣的镜像源，但安装报错cannot detect archive format", "id": 245}
{"title": "[BUG]  webscoket 接口串行问题（/local_doc_qa/stream-chat/{knowledge_base_id}）", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/527", "detail": "**问题描述 / Problem Description**", "id": 246}
{"title": "[FEATURE] 刷新页面更新知识库列表", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/528", "detail": "**功能描述以及改进方案**", "id": 247}
{"title": "[BUG] 使用ptuning微调模型后，问答效果并不好", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/530", "detail": "### 未调用ptuning", "id": 248}
{"title": "[BUG] 多轮对话效果不佳", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/532", "detail": "在进行多轮对话的时候，无论设置的history_len是多少，效果都不好。事实上我将其设置成了最大值10，但在对话中，仍然无法实现多轮对话：", "id": 249}
{"title": "RuntimeError: MPS backend out of memory (MPS allocated: 18.00 GB, other allocations: 4.87 MB, max allowed: 18.13 GB)", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/533", "detail": "**问题描述**", "id": 250}
{"title": " 请大家重视这个issue！真正使用肯定是多用户并发问答，希望增加此功能！！！", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/534", "detail": "这得看你有多少显卡", "id": 251}
{"title": "在启动项目的时候如何使用到多张gpu啊？", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/535", "detail": "**在启动项目的时候如何使用到多张gpu啊？**", "id": 252}
{"title": "   使用流式输出的时候，curl调用的格式是什么？", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/536", "detail": "app.websocket(\"/local_doc_qa/stream-chat/{knowledge_base_id}\")(stream_chat)中的knowledge_base_id应该填什么？？？", "id": 253}
{"title": "使用本地 vicuna-7b模型启动错误", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/538", "detail": "环境: ubuntu 22.04 cuda 12.1 没有安装nccl，使用rtx2080与m60显卡并行计算", "id": 254}
{"title": "为什么会不调用GPU直接调用CPU呢", "file": "2023-06-02.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/539", "detail": "我的阿里云配置是16G显存，用默认代码跑webui.py时提示", "id": 255}
{"title": "上传多个文件时会互相覆盖", "file": "2023-06-03.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/541", "detail": "1、在同一个知识库中上传多个文件时会互相覆盖，无法结合多个文档的知识，有大佬知道怎么解决吗？", "id": 256}
{"title": "[BUG] ‘gcc’不是内部或外部命令/LLM对话只能持续一轮", "file": "2023-06-03.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/542", "detail": "No compiled kernel found.", "id": 257}
{"title": "以API模式启动项目却没有知识库的接口列表？", "file": "2023-06-04.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/544", "detail": "请问如何获取知识库的接口列表？如果没有需要自行编写的话，可不可以提供相关的获取方式，感谢", "id": 258}
{"title": "程序以API模式启动的时候，如何才能让接口以stream模式被调用呢？", "file": "2023-06-05.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/546", "detail": "作者您好，我在以API模式进行程序启动后，我发现接口响应时间很长，怎么样才能让接口以stream模式被调用呢？我想实现像webui模式的回答那样", "id": 259}
{"title": "关于原文中表格转为文本后数据相关度问题。", "file": "2023-06-06.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/547", "detail": "原文中表格数据转换为文本，以 （X-Y：值；...） 的格式每一行组织成一句话，但这样做后发现相关度较低，效果很差，有何好的方案吗？", "id": 260}
{"title": "启动后LLM和知识库问答模式均只有最后一轮记录", "file": "2023-06-06.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/548", "detail": "拉取最新代码，问答时，每次页面只显示最后一次问答记录，需要修改什么参数才可以保留历史记录？", "id": 261}
{"title": "提供system message配置，以便于让回答不要超出知识库范围", "file": "2023-06-06.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/549", "detail": "**功能描述 / Feature Description**", "id": 262}
{"title": "[BUG] 使用p-tunningv2报错", "file": "2023-06-06.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/551", "detail": "按照readme的指示把p-tunningv2训练完后的文件放到了p-tunningv2文件夹下，勾选使用p-tuningv2点重新加载模型，控制台提示错误信息：", "id": 263}
{"title": "[BUG] 智障，这么多问题，也好意思放出来，浪费时间", "file": "2023-06-06.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/553", "detail": "。。。", "id": 264}
{"title": "[FEATURE] 我看代码文件中有一个ali_text_splitter.py，为什么不用他这个文本分割器了？", "file": "2023-06-06.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/554", "detail": "我看代码文件中有一个ali_text_splitter.py，为什么不用他这个文本分割器了？", "id": 265}
{"title": "加载文档函数报错", "file": "2023-06-06.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/557", "detail": "def load_file(filepath, sentence_size=SENTENCE_SIZE):", "id": 266}
{"title": "参考指引安装docker后，运行cli_demo.py，提示killed", "file": "2023-06-06.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/558", "detail": "root@b3d1bd08095c:/chatGLM# python3 cli_demo.py", "id": 267}
{"title": "注意：如果安装错误，注意这两个包的版本  wandb==0.11.0 protobuf==3.18.3", "file": "2023-06-06.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/559", "detail": "Error1: 如果启动异常报错 `protobuf`  需要更新到 `protobuf==3.18.3 `", "id": 268}
{"title": "知识库对长文的知识相关度匹配不太理想有何优化方向", "file": "2023-06-07.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/563", "detail": "我们可能录入一个文章有 1W 字，里面涉及这个文章主题的很多角度问题，我们针对他提问，他相关度匹配的内容和实际我们需要的答案相差很大怎么办。", "id": 269}
{"title": "使用stream-chat函数进行流式输出的时候，能使用curl调用吗？", "file": "2023-06-07.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/565", "detail": "为什么下面这样调用会报错？？？", "id": 270}
{"title": "有大佬实践过 并行 或者 多线程 的部署方案吗？", "file": "2023-06-07.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/566", "detail": "+1", "id": 271}
{"title": "多线程部署遇到问题？", "file": "2023-06-07.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/567", "detail": "<img width=\"615\" alt=\"3d87bf74f0cf1a4820cc9e46b245859\" src=\"https://github.com/imClumsyPanda/langchain-ChatGLM/assets/109277248/8787570d-88bd-434e-aaa4-cb9276d1aa50\">", "id": 272}
{"title": "[BUG] 用fastchat加载vicuna-13b模型进行知识库的问答有token的限制错误", "file": "2023-06-07.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/569", "detail": "当我开启fastchat的vicuna-13b的api服务，然后config那里配置好(api本地测试过可以返回结果)，然后知识库加载好之后(知识库大概有1000多个文档，用chatGLM可以正常推理)，进行问答时出现token超过限制，就问了一句hello；", "id": 273}
{"title": "现在的添加知识库，文件多了总是报错，也不知道自己加载了哪些文件，报错后也不知道是全部失败还是一部分成功；希望能有个加载指定文件夹作为知识库的功能", "file": "2023-06-07.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/574", "detail": "**功能描述 / Feature Description**", "id": 274}
{"title": "[BUG] moss模型本地加载报错", "file": "2023-06-08.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/577", "detail": "moss模型本地加载报错：", "id": 275}
{"title": "加载本地moss模型报错Can't instantiate abstract class MOSSLLM with abstract methods _history_len", "file": "2023-06-08.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/578", "detail": "(vicuna) ps@ps[13:56:20]:/data/chat/langchain-ChatGLM2/langchain-ChatGLM-0.1.13$ python webui.py  --model-dir local_models --model moss --no-remote-model", "id": 276}
{"title": "[FEATURE] 能增加在前端页面控制prompt_template吗？或是能支持前端页面选择使用哪个prompt？", "file": "2023-06-08.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/579", "detail": "目前只能在config里修改一个prompt，想在多个不同场景切换比较麻烦", "id": 277}
{"title": "[BUG] streamlit ui的bug，在增加知识库时会报错", "file": "2023-06-08.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/580", "detail": "**问题描述 / Problem Description**", "id": 278}
{"title": "[FEATURE] webui/webui_st可以支持history吗？目前仅能一次对话", "file": "2023-06-08.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/581", "detail": "试了下webui和webui_st都不支持历史对话啊，只能对话一次，不能默认开启所有history吗？", "id": 279}
{"title": "启动python cli_demo.py --model chatglm-6b-int4-qe报错", "file": "2023-06-09.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/585", "detail": "下载好模型，和相关依赖环境，之间运行`python cli_demo.py --model chatglm-6b-int4-qe`报错了：", "id": 280}
{"title": "重新构建知识库报错", "file": "2023-06-09.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/586", "detail": "**问题描述 / Problem Description**", "id": 281}
{"title": "[FEATURE] 能否屏蔽paddle，我不需要OCR，效果差依赖环境还很复杂", "file": "2023-06-09.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/587", "detail": "希望能不依赖paddle", "id": 282}
{"title": "question ：文档向量化这个可以自己手动实现么？", "file": "2023-06-09.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/589", "detail": "现有公司级数据500G+，需要使用这个功能，请问如何手动实现这个向量化，然后并加载", "id": 283}
{"title": "view前端能进行流式的返回吗？？", "file": "2023-06-09.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/590", "detail": "view前端能进行流式的返回吗？？", "id": 284}
{"title": "[BUG]  Load parallel cpu kernel failed, using default cpu kernel code", "file": "2023-06-11.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/594", "detail": "**问题描述 / Problem Description**", "id": 285}
{"title": "[BUG] 简洁阐述问题 / Concise description of the issue", "file": "2023-06-11.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/595", "detail": "**问题描述 / Problem Description**", "id": 286}
{"title": "我在上传本地知识库时提示KeyError: 'name'错误，本地知识库都是.txt文件，文件数量大约是2000+。", "file": "2023-06-12.05", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/597", "detail": "<img width=\"649\" alt=\"KError\" src=\"https://github.com/imClumsyPanda/langchain-ChatGLM/assets/59411575/1ecc8182-aeee-4a0a-bbc3-74c2f1373f2d\">", "id": 287}
{"title": "model_config.py中有vicuna-13b-hf模型的配置信息，但是好像还是不可用？", "file": "2023-06-12.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/600", "detail": "@dongyihua543", "id": 288}
{"title": "ImportError: Using SOCKS proxy, but the 'socksio' package is not installed. Make sure to install httpx using `pip install httpx[socks]`.", "file": "2023-06-12.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/605", "detail": "应该代理问题，但是尝试了好多方法都解决不了，", "id": 289}
{"title": "[BUG] similarity_search_with_score_by_vector在找不到匹配的情况下出错", "file": "2023-06-12.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/607", "detail": "在设置匹配阈值 VECTOR_SEARCH_SCORE_THRESHOLD 的情况下，vectorstore会返回空，此时上述处理函数会出错", "id": 290}
{"title": "[FEATURE] 请问如何搭建英文知识库呢", "file": "2023-06-12.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/609", "detail": "**功能描述 / Feature Description**", "id": 291}
{"title": "谁有vicuna权重？llama转换之后的", "file": "2023-06-13.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/611", "detail": "**问题描述 / Problem Description**", "id": 292}
{"title": "[FEATURE] API能实现上传文件夹的功能么？", "file": "2023-06-13.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/612", "detail": "用户懒得全选所有的文件，就想上传个文件夹，请问下API能实现这个功能么？", "id": 293}
{"title": "请问在多卡部署后，上传单个文件作为知识库，用的是单卡在生成向量还是多卡？", "file": "2023-06-13.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/614", "detail": "目前我检测我本地多卡部署的，好像生成知识库向量的时候用的还是单卡", "id": 294}
{"title": "[BUG] python webui.py提示非法指令", "file": "2023-06-13.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/615", "detail": "(/data/conda-langchain [root@chatglm langchain-ChatGLM]# python webui.py", "id": 295}
{"title": "知识库文件跨行切分问题", "file": "2023-06-13.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/616", "detail": "我的知识库文件txt文件，是一行一条知识，用\\n分行。", "id": 296}
{"title": "[FEATURE] bing搜索问答有流式的API么？", "file": "2023-06-13.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/617", "detail": "web端是有这个bing搜索回答，但api接口没有发现，大佬能给个提示么？", "id": 297}
{"title": "希望出一个macos m2的安装教程", "file": "2023-06-14.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/620", "detail": "mac m2安装，模型加载成功了，知识库文件也上传成功了，但是一问答就会报错，报错内容如下", "id": 298}
{"title": "为【出处】提供高亮显示", "file": "2023-06-14.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/621", "detail": "具体出处里面，对相关的内容高亮显示，不包含前后文。", "id": 299}
{"title": "[BUG] CPU运行cli_demo.py，不回答，hang住", "file": "2023-06-14.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/622", "detail": "没有GPU；32G内存的ubuntu机器。", "id": 300}
{"title": "关于删除知识库里面的文档后，LLM知识库对话的时候还是会返回该被删除文档的内容", "file": "2023-06-14.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/623", "detail": "如题，在vue前端成功执行删除知识库里面文档A.txt后，未能也在faiss索引中也删除该文档，LLM还是会返回这个A.txt的内容，并且以A.txt为出处，未能达到删除的效果", "id": 301}
{"title": "[BUG] 调用知识库进行问答,显存会一直叠加", "file": "2023-06-14.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/625", "detail": "14G的显存,调用的chatglm-6b-int8模型,进行知识库问答时,最多问答四次就会爆显存了,观察了一下显存使用情况,每一次使用就会增加一次显存,请问这样是正常的吗?是否有什么配置需要开启可以解决这个问题?例如进行一次知识库问答清空上次问题的显存?", "id": 302}
{"title": "[BUG] web页面 重新构建数据库 失败，导致 原来的上传的数据库都没了", "file": "2023-06-14.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/626", "detail": "web页面 重新构建数据库 失败，导致 原来的上传的数据库都没了", "id": 303}
{"title": "在CPU上运行webui.py报错Tensor on device cpu is not on the expected device meta!", "file": "2023-06-14.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/627", "detail": "在CPU上运行python webui.py能启动，但最后有：RuntimeError: Tensor on device cpu is not on the expected device meta!", "id": 304}
{"title": "OSError: [WinError 1114] 动态链接库(DLL)初始化例程失败。 Error loading \"E:\\xxx\\envs\\langchain\\lib\\site-packages\\torch\\lib\\caffe2_nvrtc.dll\" or one of its dependencies.哪位大佬知道如何解决吗？", "file": "2023-06-14.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/629", "detail": "**问题描述 / Problem Description**", "id": 305}
{"title": "[BUG] WEBUI删除知识库文档，会导致知识库问答失败", "file": "2023-06-15.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/632", "detail": "如题，从知识库已有文件中选择要删除的文件，点击删除后，在问答框输入内容回车报错", "id": 306}
{"title": "更新后的版本中，删除知识库中的文件，再提问出现error错误", "file": "2023-06-15.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/634", "detail": "针对更新版本，识别到一个问题，过程如下：", "id": 307}
{"title": "我配置好了环境，想要实现本地知识库的问答？可是它返回给我的", "file": "2023-06-15.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/637", "detail": "没有总结，只有相关度的回复，但是我看演示里面表现的，回复是可以实现总结的，我去查询代码", "id": 308}
{"title": "[BUG] NPM run dev can not successfully start the VUE frontend", "file": "2023-06-15.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/638", "detail": "**问题描述 / Problem Description**", "id": 309}
{"title": "[BUG] 简洁阐述问题 / Concise description of the issue", "file": "2023-06-15.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/639", "detail": "**问题描述 / Problem Description**", "id": 310}
{"title": "提一个模型加载的bug，我在截图中修复了，你们有空可以看一下。", "file": "2023-06-15.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/642", "detail": "![model_load_bug](https://github.com/imClumsyPanda/langchain-ChatGLM/assets/59411575/4432adc4-ccdd-45d9-aafc-5f2d1963403b)", "id": 311}
{"title": "[求助]关于设置embedding model路径的问题", "file": "2023-06-16.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/643", "detail": "如题，我之前成功跑起来过一次，但因环境丢失重新配置 再运行webui就总是报错", "id": 312}
{"title": "Lora微调后的模型可以直接使用吗", "file": "2023-06-16.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/646", "detail": "看model_config.py里是有USE_LORA这个参数的，但是在cli_demo.py和webui.py这两个里面都没有用到，实际测试下来模型没有微调的效果，想问问现在这个功能实现了吗", "id": 313}
{"title": "write_check_file在tmp_files目录下生成的load_file.txt是否需要一直保留，占用空间很大，在建完索引后能否删除", "file": "2023-06-16.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/647", "detail": "**功能描述 / Feature Description**", "id": 314}
{"title": "[BUG] /local_doc_qa/list_files?knowledge_base_id=test删除知识库bug", "file": "2023-06-16.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/649", "detail": "1.新建test知识库并上传文件（在vue前端完成并检查后端发现确实生成了test文件夹以及下面的content和vec_store", "id": 315}
{"title": "[BUG] vue webui无法加载知识库", "file": "2023-06-16.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/650", "detail": "拉取了最新的代码，分别运行了后端api和前端web，点击知识库，始终只能显示simple，无法加载知识库", "id": 316}
{"title": "不能本地加载moss模型吗？", "file": "2023-06-16.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/652", "detail": "手动下载模型设置local_model_path路径依旧提示缺少文件，该如何正确配置？", "id": 317}
{"title": "macos m2 pro docker 安装失败", "file": "2023-06-17.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/654", "detail": "macos m2 pro docker 安装失败", "id": 318}
{"title": " [BUG] mac m1 pro  运行提示  zsh: segmentation fault", "file": "2023-06-17.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/655", "detail": "运行：  python webui.py", "id": 319}
{"title": "安装 requirements 报错", "file": "2023-06-17.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/656", "detail": "(langchainchatglm) D:\\github\\langchain-ChatGLM>pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/", "id": 320}
{"title": "[BUG] AssertionError", "file": "2023-06-17.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/658", "detail": "**问题描述 / Problem Description**", "id": 321}
{"title": "[FEATURE] 支持AMD win10 本地部署吗？", "file": "2023-06-18.06", "url": "https://github.com/imClumsyPanda/langchain-ChatGLM/issues/660", "detail": "**功能描述 / Feature Description**", "id": 322}