Fix: Every time you switch the page number of a chunk, the PDF document will be reloaded. #4046 (#4047)
### What problem does this PR solve?
Fix: Every time you switch the page number of a chunk, the PDF document
will be reloaded. #4046
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Remove Redundant None Check for vector_similarity_weight (#4037)
### What problem does this PR solve?
The removed if statement is unnecessary and adds cognitive load for
readers.
The original code:
```
vector_similarity_weight = req.get("vector_similarity_weight", 0.3)
if vector_similarity_weight is None:
vector_similarity_weight = 0.3
```
has been simplified to:
```
vector_similarity_weight = req.get("vector_similarity_weight", 0.3)
```
### Type of change
- [x] Refactoring
Fix xinfo_groups returns unexpected result (#4026)
### What problem does this PR solve?
Fix xinfo_groups returns unexpected result. Close #3545
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Feat: Reparse a file shall reuse existing chunks if possible #3793 (#4021)
### What problem does this PR solve?
Feat: Reparse a file shall reuse existing chunks if possible #3793
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Feat: Supports to debug single component in Agent. #3993 (#4007)
### What problem does this PR solve?
Feat: Supports to debug single component in Agent. #3993
Fix: The github button on the login page is displayed incorrectly #4002
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Fix bugs in agent api and update api document (#3996)
### What problem does this PR solve?
Fix bugs in agent api and update api document
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
### What problem does this PR solve?
Fix hierarchical_merge function. From idx vs. actual value to actual
value vs. actual value.
Related issue #4003
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: luopan <luopan@example.com>
### What problem does this PR solve?
Fix json file parsing
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: jinhai <haijin.chn@gmail.com>
some thing
- execsql add connection mssql
- fix bug duckduckgo-search rate limit
- update typo vi res
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Fix: Completion AttributeError: 'list' object has no attribute 'get' (#3999)
### What problem does this PR solve?
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: lizheng@ssc-hn.com <lizheng@ssc-hn.com>
### What problem does this PR solve?
Try to reuse existing chunks. Close #3793
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Documentation Update
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Fix: Fixed the issue where two consecutive indexes were displayed incorrectly #3839 (#3988)
### What problem does this PR solve?
Fix: Fixed the issue where two consecutive indexes were displayed
incorrectly #3839
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Update api documents
### Type of change
- [x] Documentation Update
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
update typo vietnamese
### Type of change
- [x] Refactoring
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: bill <yibie_jingnian@163.com>
### What problem does this PR solve?
The initial Helm chart implementation added in #3815 suffers from an
issue where the 5GB data volume for the SQL DB is filled up with
[binlog](https://dev.mysql.com/doc/refman/8.4/en/binary-log.html) files
after just a few days. Since the app uses a non-replicated SQL DB config
I think it makes sense to disable the binlog in the SQL DB container.
This is achieved by simply adding the required argument to the container
startup command.
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
Fix: Answers with links to information not parsing #3839 (#3968)
### What problem does this PR solve?
Fix: Answers with links to information not parsing #3839
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fixed retrieval TypeError: unhashable type: 'list'
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Feat: Exclude reference from the data returned by the conversation/get interface #3909 (#3962)
### What problem does this PR solve?
Feat: Exclude reference from the data returned by the conversation/get
interface #3909
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Feat: Modify the data structure of the chunk in the conversation #3909 (#3955)
### What problem does this PR solve?
Feat: Modify the data structure of the chunk in the conversation #3909
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Rename page_num_list, top_list, position_list to page_num_int, top_int,
position_int
### Type of change
- [x] Refactoring
### What problem does this PR solve?
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
DOC_ENGINE="INFINITY" or "Infinity" or "Elasticsearch" also works
### Type of change
- [x] Refactoring
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
This PR organize chunks in the prompt by document and indicate what is
the name of the document in this way
```
Document: {doc_name} \nContains the following relevant fragments:
chunk1
chunk2
chunk3
Document: {doc_name} \nContains the following relevant fragments:
chunk4
chunk5
```
Maybe can be a baseline to add metadata to the documents.
This allow in my case to improve llm context about the orgin of the
information.
### Type of change
- [X] New Feature (non-breaking change which adds functionality)
Co-authored-by: Miguel <your-noreply-github-email>
api http return error when content is not found
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Kevin Hu
balibabu
Michael Luo
so95
writinwaters
Zhichang Yu
liuhua
Luo Pan
Jin Hai
Roccat
Scott Davidson
devMls