🔥 0.3.0 改进项与预期新增功能

[imClumsyPanda]

🐞 改进项

✅ 已发布

• 修复依赖包不完整导致 chatchat-kb -r 命令执行过程中发生依赖库缺失的报错

🕑 已完成待发布

• 配置项除命令行修改方式外，重新支持本地文件修改方式
• 优化模型推理框架接入方式，减少所需配置内容，已支持 xinference 框架中除 audio 类模型外的其他类型模型中已启动模型的自动检测。
• 支持在 windows 系统中 ctrl+c 中止 chatchat-kb -r 过程
• 修复 max_token 不生效的问题

🏗️ 待开发完成

• 修复 ollama 接入过程中可能发生报错的问题
• 因 ollama 启动的模型名称中带有冒号导致无法完成知识库创建

💡 新增功能

✅ 已发布

🕑 已完成待发布

🏗️ 待开发完成

• 增加 rag 测试页面，可针对搜索结果及问答效果进行测试和对比
• 基于 lobe-chat 的前端页面
• 支持多模态对话
• 支持多模态 RAG

[yuehua-s]

“max_token 不生效的问题”已修复

[630bdd]

多模态对话和rag会在0.3.0发布吗

[imClumsyPanda]

多模态对话和rag会在0.3.0发布吗

会。目前预期是一个版本修复bug，一个版本新增功能。

[kogwang]

0.3.0会支持并发吗？

[Qi0716]

在ollama框架中启动langchain0.3版本进行知识库初始化还是报错chatchat-kb -r

(langchain) D:\other\Langchain-Chatchat-master>chatchat-kb -r
recreating all vector stores
C:\Users\30759.conda\envs\langchain\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(
2024-07-03 10:22:16,321 - utils.py[line:260] - ERROR: failed to create Embeddings for model: bge-large-zh-v1.5.
Traceback (most recent call last):
File "C:\Users\30759.conda\envs\langchain\lib\site-packages\chatchat\server\utils.py", line 258, in get_Embeddings
return LocalAIEmbeddings(**params)
File "C:\Users\30759.conda\envs\langchain\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_KEY which contains it, or pass openai_api_key as a named parameter. (type=value_error)
2024-07-03 10:22:16,322 - faiss_cache.py[line:140] - ERROR: 'NoneType' object has no attribute 'embed_documents'
Traceback (most recent call last):
File "C:\Users\30759.conda\envs\langchain\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\30759.conda\envs\langchain\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\30759.conda\envs\langchain\lib\site-packages\langchain_core\vectorstores.py", line 550, in from_documents
return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs)
File "C:\Users\30759.conda\envs\langchain\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'
2024-07-03 10:22:16,323 - init_database.py[line:150] - ERROR: 向量库 samples 加载失败。
Traceback (most recent call last):
File "C:\Users\30759.conda\envs\langchain\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\30759.conda\envs\langchain\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\30759.conda\envs\langchain\lib\site-packages\langchain_core\vectorstores.py", line 550, in from_documents
return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs)
File "C:\Users\30759.conda\envs\langchain\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\30759.conda\envs\langchain\lib\site-packages\chatchat\init_database.py", line 129, in main
folder2db(
File "C:\Users\30759.conda\envs\langchain\lib\site-packages\chatchat\server\knowledge_base\migrate.py", line 152, in folder2db
kb.create_kb()
File "C:\Users\30759.conda\envs\langchain\lib\site-packages\chatchat\server\knowledge_base\kb_service\base.py", line 102, in create_kb
self.do_create_kb()
File "C:\Users\30759.conda\envs\langchain\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\30759.conda\envs\langchain\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\30759.conda\envs\langchain\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。
2024-07-03 10:22:16,325 - init_database.py[line:151] - WARNING: Caught KeyboardInterrupt! Setting stop event...

[Qi0716]

在ollama框架中启动langchain0.3版本进行知识库初始化还是报错chatchat-kb -r

(langchain) D:\other\Langchain-Chatchat-master>chatchat-kb -r
recreating all vector stores
C:\Users\30759.conda\envs\langchain\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(
2024-07-03 10:22:16,321 - utils.py[line:260] - ERROR: failed to create Embeddings for model: bge-large-zh-v1.5.
Traceback (most recent call last):
File "C:\Users\30759.conda\envs\langchain\lib\site-packages\chatchat\server\utils.py", line 258, in get_Embeddings
return LocalAIEmbeddings(**params)
File "C:\Users\30759.conda\envs\langchain\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_KEY which contains it, or pass openai_api_key as a named parameter. (type=value_error)
2024-07-03 10:22:16,322 - faiss_cache.py[line:140] - ERROR: 'NoneType' object has no attribute 'embed_documents'
Traceback (most recent call last):
File "C:\Users\30759.conda\envs\langchain\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\30759.conda\envs\langchain\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\30759.conda\envs\langchain\lib\site-packages\langchain_core\vectorstores.py", line 550, in from_documents
return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs)
File "C:\Users\30759.conda\envs\langchain\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'
2024-07-03 10:22:16,323 - init_database.py[line:150] - ERROR: 向量库 samples 加载失败。
Traceback (most recent call last):
File "C:\Users\30759.conda\envs\langchain\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\30759.conda\envs\langchain\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\30759.conda\envs\langchain\lib\site-packages\langchain_core\vectorstores.py", line 550, in from_documents
return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs)
File "C:\Users\30759.conda\envs\langchain\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\30759.conda\envs\langchain\lib\site-packages\chatchat\init_database.py", line 129, in main
folder2db(
File "C:\Users\30759.conda\envs\langchain\lib\site-packages\chatchat\server\knowledge_base\migrate.py", line 152, in folder2db
kb.create_kb()
File "C:\Users\30759.conda\envs\langchain\lib\site-packages\chatchat\server\knowledge_base\kb_service\base.py", line 102, in create_kb
self.do_create_kb()
File "C:\Users\30759.conda\envs\langchain\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\30759.conda\envs\langchain\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\30759.conda\envs\langchain\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。
2024-07-03 10:22:16,325 - init_database.py[line:151] - WARNING: Caught KeyboardInterrupt! Setting stop event...

[mrkingsun]

建议前端优化，参考主流的设计，比如“会话”应占据整个左侧边栏；知识库管理、模型配置等集成到左下角或右上角的设置界面。

[yuehua-s]

新增text2promql功能