zx1159652666
commented
4 days ago 我也遇到了，怎么解决呀
Open limengjieb opened 4 days ago
zx1159652666
commented
4 days ago 我也遇到了，怎么解决呀
limengjieb
commented
4 days ago 我也遇到了，怎么解决呀
我还没有找到解决办法
joveth1
commented
3 days ago 感觉像是向量库模型没加载成功，直接修改model_providers.yaml 这个是没用的，要修改 _model_config.py 文件让它的MODEL_PLATFORMS 里面的embed_models 包含你的bce-embedding-base_v1向量库模型，我看他源码里面就支持 bge-large-zh-v1.5这个模型，你的这个模型不在它列表里面，他是没法加载。
或者你通过他文档里面描述的一样，去设置这个向量库：
把里面的 bge-large-zh-v1.5 换成你的，default_embedding_model 只是修改 self.DEFAULT_EMBEDDING_MODEL 这个变量吧，当然我也不确定对不对。
1：Xinference已经启动成功，并且下载了2个模型，一个是 qwen1.5-chat, bce-embedding-base_v1 2：修改了 \Lib\site-packages\chatchat\configs 文件夹下 model_providers.yaml 文件的配置，修改之后的配置如下：
xinference: model_credential:
3：启动之前修改了配置，执行命令如下 chatchat-config model --default_llm_model qwen1.5-chat chatchat-config model --default_embedding_model bce-embedding-base_v1
4：执行 chatchat-kb -r 失败，失败信息如下：
(chat) C:\Users\dev\Langchain3>chatchat-kb -r
recreating all vector stores C:\Users\dev\Langchain3\chat\Lib\site-packages\langchain_api\module_import.py:87: LangChainDeprecationWarning: Importing GuardrailsOutputParser from langchain.output_parsers is deprecated. Please replace the import with the following: from langchain_community.output_parsers.rail_parser import GuardrailsOutputParser warnings.warn( 2024-07-04 15:00:14,882 - utils.py[line:260] - ERROR: failed to create Embeddings for model: bce-embedding-base_v1. Traceback (most recent call last): File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\server\utils.py", line 258, in get_Embeddings return LocalAIEmbeddings(params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\dev\Langchain3\chat\Lib\site-packages\pydantic\v1\main.py", line 341, in init raise validation_error pydantic.v1.error_wrappers.ValidationError: 1 validation error for LocalAIEmbeddings root Did not find openai_api_key, please add an environment variable
OPENAI_API_KEYwhich contains it, or passopenai_api_keyas a named parameter. (type=value_error) 2024-07-04 15:00:14,883 - faiss_cache.py[line:140] - ERROR: 'NoneType' object has no attribute 'embed_documents' Traceback (most recent call last): File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\server\knowledge_base\kb_cache\faiss_cache.py", line 126, in load_vector_store vector_store = self.new_vector_store( ^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\server\knowledge_base\kb_cache\faiss_cache.py", line 63, in new_vector_store vector_store = FAISS.from_documents([doc], embeddings, normalize_L2=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\dev\Langchain3\chat\Lib\site-packages\langchain_core\vectorstores.py", line 550, in from_documents return cls.from_texts(texts, embedding, metadatas=metadatas, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\dev\Langchain3\chat\Lib\site-packages\langchain_community\vectorstores\faiss.py", line 930, in from_texts embeddings = embedding.embed_documents(texts) ^^^^^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'NoneType' object has no attribute 'embed_documents' 2024-07-04 15:00:14,884 - init_database.py[line:150] - ERROR: 向量库 samples 加载失败。 Traceback (most recent call last): File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\server\knowledge_base\kb_cache\faiss_cache.py", line 126, in load_vector_store vector_store = self.new_vector_store( ^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\server\knowledge_base\kb_cache\faiss_cache.py", line 63, in new_vector_store vector_store = FAISS.from_documents([doc], embeddings, normalize_L2=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\dev\Langchain3\chat\Lib\site-packages\langchain_core\vectorstores.py", line 550, in from_documents return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\dev\Langchain3\chat\Lib\site-packages\langchain_community\vectorstores\faiss.py", line 930, in from_texts embeddings = embedding.embed_documents(texts) ^^^^^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'NoneType' object has no attribute 'embed_documents'During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\init_database.py", line 129, in main folder2db( File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\server\knowledge_base\migrate.py", line 152, in folder2db kb.create_kb() File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\server\knowledge_base\kb_service\base.py", line 102, in create_kb self.do_create_kb() File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\server\knowledge_base\kb_service\faiss_kb_service.py", line 57, in do_create_kb self.load_vector_store() File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\server\knowledge_base\kb_service\faiss_kb_service.py", line 32, in load_vector_store return kb_faiss_pool.load_vector_store( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\dev\Langchain3\chat\Lib\site-packages\chatchat\server\knowledge_base\kb_cache\faiss_cache.py", line 141, in load_vector_store raise RuntimeError(f"向量库 {kb_name} 加载失败。") RuntimeError: 向量库 samples 加载失败。 2024-07-04 15:00:14,885 - init_database.py[line:151] - WARNING: Caught KeyboardInterrupt! Setting stop event...
5：chatchat -a 能启动成功，webUI 页面能正常访问，对话正常，知识库创建失败，上传文件成功，文件内容识别失败，知识库对话失败