We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Linux
=3.11
latest release
Installation From Source
Docker Installation
Docker Compose Installation
Cluster Installation
AutoDL Image
Other
nothing
1、新版分重构的不干净。 0.5.8版本中以及main分支中(截止该issue提出时刻)。 dbgpt/app/knowlege/service.py中第223行,调用了未被定义的方法_sync_knowledge_document。 2、chroma库标量过滤,需要给的入参格式是 {"$and": [{"field_a":1, "filed_b": 2}]},我们代码dbgpt/storage/vector_store/chroma_store.py 第198行的实现需要调整一下 现在的逻辑解析出来的格式是{"$FilterCondition.AND": [{"field_a":1, "filed_b": 2}]} 3、chroma向量库召回数据的score计算,重构前langchain的实现如下图,代码位置langchain/schema/vectorstore.py253行 重构后丢失了评分的计算,重构后的代码位置dbgpt/storage/vector_store/chroma_store.py 第136行 4、document的mysql表操作没有及时close链接,导致当并发高时,会出现链接不可用 代码位置dbgpt/app/knowledge/document_db.py第221行和第255行
No response
The text was updated successfully, but these errors were encountered:
fix bug for issue eosphoros-ai#1669
e173c1d
fix: Fix bug for issue #1669 (#1672)
cd2163e
Co-authored-by: WangTing <wangting@192.168.1.10> Co-authored-by: aries_ckt <916701291@qq.com>
fix: Fix bug for issue eosphoros-ai#1669 (eosphoros-ai#1672)
ecce7e6
Successfully merging a pull request may close this issue.
Search before asking
Operating system information
Linux
Python version information
DB-GPT version
latest release
Related scenes
Installation Information
Installation From Source
Docker Installation
Docker Compose Installation
Cluster Installation
AutoDL Image
Other
Device information
nothing
Models information
nothing
What happened
1、新版分重构的不干净。
0.5.8版本中以及main分支中(截止该issue提出时刻)。
dbgpt/app/knowlege/service.py中第223行,调用了未被定义的方法_sync_knowledge_document。
2、chroma库标量过滤,需要给的入参格式是 {"$and": [{"field_a":1, "filed_b": 2}]},我们代码dbgpt/storage/vector_store/chroma_store.py 第198行的实现需要调整一下
现在的逻辑解析出来的格式是{"$FilterCondition.AND": [{"field_a":1, "filed_b": 2}]}
3、chroma向量库召回数据的score计算,重构前langchain的实现如下图,代码位置langchain/schema/vectorstore.py253行
重构后丢失了评分的计算,重构后的代码位置dbgpt/storage/vector_store/chroma_store.py 第136行
4、document的mysql表操作没有及时close链接,导致当并发高时,会出现链接不可用
代码位置dbgpt/app/knowledge/document_db.py第221行和第255行
What you expected to happen
nothing
How to reproduce
nothing
Additional context
No response
Are you willing to submit PR?
The text was updated successfully, but these errors were encountered: