支持图片吗? #2884
-
1、提问者能不能发送一张图片,请模型回答? |
Beta Was this translation helpful? Give feedback.
Replies: 3 comments 1 reply
-
🤖 嘿,@ClayGminx!又见面了,真是太棒了!希望这次我们能解决你的新问题。🚀 根据我在Langchain-Chatchat v0.2.10版本的代码中的查找,用户可以上传文件,这是通过 elif dialogue_mode == "文件对话":
with st.expander("文件对话配置", True):
files = st.file_uploader("上传知识文件:",
[i for ls in LOADER_DICT.values() for i in ls],
accept_multiple_files=True,
)
kb_top_k = st.number_input("匹配知识条数:", 1, 20, VECTOR_SEARCH_TOP_K)
## Bge 模型会超过1
score_threshold = st.slider("知识匹配分数阈值:", 0.0, 2.0, float(SCORE_THRESHOLD), 0.01)
if st.button("开始上传", disabled=len(files) == 0):
st.session_state["file_chat_id"] = upload_temp_docs(files, api) 然而,这个功能是为了上传知识文件,而不是图片。代码并没有指出任何特定的功能用于上传或发送图片。 至于模型是否能识别知识库文件中的图片,并且学习图片中的知识,我在代码库中没有找到相关的信息。可能需要更多的上下文信息或者详细的功能需求来确定这个问题。 如果您有更多的信息或者具体的需求,欢迎提供,我会尽力帮助您解答。 SourcesThis response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant. If you want to continue the conversation, start your reply with @dosu-bot. |
Beta Was this translation helpful? Give feedback.
-
🤖 It seems like this issue requires a deeper look, @imClumsyPanda could you please lend your expertise? This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant. If you want to continue the conversation, start your reply with @dosu-bot. |
Beta Was this translation helpful? Give feedback.
不支持