Langchain-Chatchat

Langchain-Chatchat copied to clipboard

大佬有计划往web_ui.py加入打字机功能吗

1

目前在载入了知识库后，单张V100 32G在回答垂直领域的问题时也需要20S以上，没有打字机逐字输出的使用体验还是比较煎熬的....

forgot-glory

如果没有检索到相关性比较高的，回答“我不知道”

6

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”

lyx3911

控制台调api.py报警告

10

you must pass the application as an import string to enable "reload" or "workers" 这是啥原因呢

wuhu6

运行python3.9 api.py WARNING: You must pass the application as an import string to enable 'reload' or 'workers'.

3

cristianohello

AttributeError: 'Chatbot' object has no attribute 'value'

1

Traceback (most recent call last): File "/home/heyiheng/work/langchain/langchain-ChatGLM/webui.py", line 155, in chatbot = gr.Chatbot([[None, init_message], [None, model_status.value]], File "/home/young/anaconda3/envs/sakura/lib/python3.10/site-packages/gradio/components.py", line 3862, in __init__ IOComponent.__init__( File "/home/young/anaconda3/envs/sakura/lib/python3.10/site-packages/gradio/components.py", line 185, in __init__ else...

AnitaSherry

ValidationError: 1 validation error for HuggingFaceEmbeddings model_kwargs extra fields not permitted (type=value_error.extra)

4

ValidationError: 1 validation error for HuggingFaceEmbeddings model_kwargs extra fields not permitted (type=value_error.extra) Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:12

cristianohello

作者您好～ 我看到目前支持的模型有chatglm-6b-int4-qe，chatglm-6b-int4，chatglm-6b，chatyuan。请问是否支持基于chatGLM finetune后的模型呢（ptuning或者lora）? 我在加载自己本地finetune后的checkpoint的时候，遇到如下警告，模型没有加载成功。 Some weights of ChatGLMForConditionalGeneration were not initialized from the model checkpoint at (我的路径）/ChatGLM-6B/ptuning/output/adgen-chatglm-6b-pt-2048-2e-2/checkpoint-3000 and are newly initialized: ['transformer.layers.5.mlp.dense_4h_to_h.bias', 'transformer.layers.13.mlp.dense_4h_to_h.bias', 'transformer.layers.21.attention.dense.weight', 'transformer.layers.3.mlp.dense_4h_to_h.bias', 'transformer.layers.17.mlp.dense_h_to_4h.weight', 'transformer.layers.19.attention.dense.bias', 'transformer.layers.6.mlp.dense_h_to_4h.weight', 'transformer.layers.18.input_layernorm.bias', 'transformer.layers.22.input_layernorm.weight',...

LOGIC-10

对话框中代码片段格式需改进

1

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。 比如 Q: 请给我一个k8s创建pod的manifest A: 好的，以下是一个基本的 KubernetesPod manifest，您可以根据需要进行修改： apiVersion: v1kind: Podmetadata: name: my-podspec: containers: - name: my-container image: my-image:latest ports: - containerPort: 8080 - name: my-other-container image: my-image:latest ports: -...

cocomany

目前的webui.py和cli_demo.py并没有正确的把VECTOR_SEARCH_TOP_K和LLM_HISTORY_LEN参数进行传入，因此我进行了修改，让这两个参数传入LocalDocQA类

roydcai

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

4

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...

gsshawn