### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/7083
Internal due to when returning from ES, fields changed to str, so the
bool conversion does not work as expected.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
when there are multiple entities, the variable `v` may be a list, which
will lead to this error:
```
| File "/mnt/d/wrf/ragflow/ragflow/graphrag/utils.py", line 59, in replace_all
| result = result.replace(f"{{{k}}}", v)
| TypeError: replace() argument 2 must be str, not list
```
this pr assign this `v` to be a str
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
When running graph resolution with infinity, if single quotation marks
appeared in the entities name that to be delete, an error tokenizing of
sqlglot might occur after calling infinity.
For example:
```
INFINITY delete table ragflow_xxx, filter knowledge_graph_kwd IN ('entity') AND entity_kwd IN ('86 IMAGES FROM PREVIOUS CONTESTS', 'ADAM OPTIMIZATION', 'BACKGROUND'ESTIMATION')
```
may raise error
```
Error tokenizing 'TS', 'ADAM OPTIMIZATION', 'BACKGROUND'ESTIMATION''
```
and make the document parsing failed。
Replace one single quotation mark with double single quotation marks can
let sqlglot tokenize the entity name correctly.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
The assistant message placeholder is incorrect, I have finished
modifying both Chinese and traditional Chinese characters
### Type of change
- [x] Bug Fix
### Related Issue:
https://github.com/infiniflow/ragflow/issues/6548
### Related PR:
https://github.com/infiniflow/ragflow/pull/6861
### Environment:
Commit version:
[[48730e0](48730e00a8)]
### Bug Description:
Unexpected `pymysql.err.InterfaceError: (0, '') `when using Peewee +
PyMySQL + PooledMySQLDatabase after a long-running `chat streamly`
operation.
This is a common issue with Peewee + PyMySQL + connection pooling: you
end up using a connection that was silently closed by the server, but
Peewee doesn't realize it's dead.
**I found that the error only occurs during longer streaming outputs**
and is unrelated to the database connection context, so it's likely
because:
- The prolonged streaming response caused the database connection to
time out
- The original database connection might have been disconnected by the
server during the streaming process
### Why This Happens
This error happens even when using `@DB.connection_context() `after the
stream is done. After investigation, I found this is caused by MySQL
connection pools that appear to be open but are actually dead (expired
due to` wait_timeout`).
1. `@DB.connection_context()` (as a decorator or context manager) pulls
a connection from the pool.
2. If this connection was idle and expired on the MySQL server (e.g.,
due to `wait_timeout`), but not closed in Python, it will still be
considered “open” (`DB.is_closed() == False`).
3. The real error will occur only when I execute a SQL command (such as
.`get_or_none()`), and PyMySQL tries to send it to the server via a
broken socket.
### Changes Made:
1. I implemented manual connection checks before executing SQL:
```
try:
DB.execute_sql("SELECT 1")
except Exception:
print("Connection dead, reconnecting...")
DB.close()
DB.connect()
```
2. Delayed the token count update until after the streaming response is
completed to ensure the streaming output isn't interrupted by database
operations.
```
total_tokens = 0
for txt in chat_streamly(system, history, gen_conf):
if isinstance(txt, int):
total_tokens = txt
......
break
......
if total_tokens > 0:
if not TenantLLMService.increase_usage(self.tenant_id, self.llm_type, txt, self.llm_name):
logging.error("LLMBundle.chat_streamly can't update token usage for {}/CHAT llm_name: {}, content: {}".format(self.tenant_id, self.llm_name, txt))
```
### What problem does this PR solve?
Fix: Files being parsed are not allowed to be deleted in batches #7065
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
docs(api): Fix request method in Related Questions example (DELETE→POST)
### Type of change
- [x] Documentation Update
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/6905
When deleting a document will check before removing it from storage
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add fallback for bad citation output. #6948
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix Helm Ingress template; Trying to access a global variable within a
loop
Fix#6191
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Feat: Remove the rotation state of the button that parses the document
#7008
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
### Type of change
- [x] Documentation Update
---------
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
### What problem does this PR solve?
Fix: The selected state of the TreeView node cannot be seen on Mac #7000
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix update_progress issue introduced by #6975
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Fix api page translation issue. #3221
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Sometimes a slide may trigger a Proxy error (ArgumentException:
Parameter is not valid) due to issues in the original file, and this
error message can be confusing for users.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [x] Other (please describe):
### What problem does this PR solve?
Considering the ragflow_deps image is only available for `linux/amd64`
platform, if we try to run the docker build commands in ,macOS for
instance, without the platform flag, we get an error due to the
different platform. Specifying the platform in the docker build command
fixes this issue.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [X] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
i use PdfParser in local(refer to this case:
https://github.com/infiniflow/ragflow/blob/main/rag/app/paper.py) like
this:
```
import re
import openpyxl
from ragflow.api.db import ParserType
from ragflow.rag.nlp import rag_tokenizer, tokenize, tokenize_table, add_positions, bullets_category, \
title_frequency, \
tokenize_chunks
from ragflow.rag.utils import num_tokens_from_string
from ragflow.deepdoc.parser import PdfParser, ExcelParser, DocxParser,PlainParser
def logger(prog=None, msg=""):
print(msg)
class Pdf(PdfParser):
def __init__(self):
self.model_speciess = ParserType.MANUAL.value
super().__init__()
def __call__(self, filename, binary=None, from_page=0,
to_page=100000, zoomin=3, callback=None):
from timeit import default_timer as timer
start = timer()
callback(msg="OCR is running...")
self.__images__(
filename if not binary else binary,
zoomin,
from_page,
to_page,
callback
)
callback(msg="OCR finished.")
print("OCR:", timer() - start)
self._layouts_rec(zoomin)
callback(0.65, "Layout analysis finished.")
print("layouts:", timer() - start)
self._table_transformer_job(zoomin)
callback(0.67, "Table analysis finished.")
self._text_merge()
tbls = self._extract_table_figure(True, zoomin, True, True)
self._concat_downward()
self._filter_forpages()
callback(0.68, "Text merging finished")
# clean mess
for b in self.boxes:
b["text"] = re.sub(r"([\t ]|\u3000){2,}", " ", b["text"].strip())
return [(b["text"], b.get("layout_no", ""), self.get_position(b, zoomin))
for i, b in enumerate(self.boxes)], tbls
```
show err like this:
```
File "xxxxx/third_party/ragflow/deepdoc/parser/pdf_parser.py", line 1039, in __images__
self.pdf.close()
AttributeError: 'PdfReader' object has no attribute 'close'
```
i found ragflow source code use
`pdfplumber.open`（https://github.com/infiniflow/ragflow/blob/main/deepdoc/parser/pdf_parser.py#L1007C28-L1007C43）
and replace` self.pdf `with ` pdf2_read` （from pypdf import PdfReader as
pdf2_read）in line 1024
(https://github.com/infiniflow/ragflow/blob/main/deepdoc/parser/pdf_parser.py#L1024)
```
self.pdf = pdf2_read
```
---
and I found that `pdfplumber` can be used in this way：
```
file_path="xxx.pdf"
res = pdfplumber.open(file_path)
res.close()
```
but `pypdf.PdfReader` source code do not has `close` func, source code
use like this
```
with open(stream, "rb") as fh:
stream = BytesIO(fh.read())
self._stream_opened = True
```
> https://github.com/py-pdf/pypdf/blob/main/pypdf/_reader.py#L156
so I moved the `self.pdf.close` function call and fixed this problem
hoping to help the project😊
ragflow: v0.17 also encountered this problem. #1453 The task table shows
that the actual task has been completed. Since the process_msg of the
task is not synchronized to the document table, there is no progress
update on the page.
This may be caused by the lock not being released when the exception
occurs.
ragflow：v0.17同样碰到这个问题， 看task表实际任务已经完成，由于没有把task的process_msg同步给document表,
所以在页面看没有进度更新。
可能是这里异常时没有释放锁导致的。
```/api/ragflow_server.py
def update_progress():
lock_value = str(uuid.uuid4())
redis_lock = RedisDistributedLock("update_progress", lock_value=lock_value, timeout=60)
logging.info(f"update_progress lock_value: {lock_value}")
while not stop_event.is_set():
try:
if redis_lock.acquire():
DocumentService.update_progress()
redis_lock.release()
stop_event.wait(6)
except Exception:
logging.exception("update_progress exception")
++ if redis_lock.acquired:
++ redis_lock.release()
```
### What problem does this PR solve?
Fix KB update_time changed whenever system relaunched. #6953
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Sometimes, the **s** in **chunks (s, a)** is an empty string. This
causes the condition **if s and len(a) > 0** in the line **chunks = [(s,
a) for s, a in chunks if s and len(a) > 0]** to fail, which changes the
length of the new chunks. As a result, the final assertion **assert
len(chunks) - end == n_clusters, "{} vs. {}".format(len(chunks) - end,
n_clusters)** fails and raises a confusing error like 7 vs. 8
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Fix: In the dark night theme, the message input box is not displayed
correctly. #6950
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### Related Issue:
https://github.com/infiniflow/ragflow/issues/6741
### Environment:
Using nightly version
Commit version:
[[6051abb](6051abb4a3)]
### Bug Description:
The retrieval function in rag/nlp/search.py returns the original total
chunks number
even after chunks are filtered by similarity_threshold. This creates
inconsistency
between the actual returned chunks and the reported total.
### Changes Made:
Added code to count how many search results actually meet or exceed the
configured similarity threshold
Positioned the calculation after the doc_ids conditional logic to ensure
special cases are handled correctly
Updated the ranks["total"] value to store this filtered count instead of
using the raw search result count
Using NumPy leverages optimized C-level batch operations to optimize
speed
### What problem does this PR solve?
Feat: Add translation text to the prompt word of the generate operator
to distinguish it from the prompt word of the knowledge base #6934
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- Returning 3 similarity scores to the chat completion's `reference`
field. It gives the user more transparency and added flexibility to
display/rerank the reference when needed
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Fix: remove deprecated KB updating `permission` field. #6911
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: local variable referenced before assignment. #6803
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
resolve this issue：https://github.com/infiniflow/ragflow/issues/6876
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
### What problem does this PR solve?
The old logic filters out all assistant messages from messages, which,
in multi-turn conversations, results in only user messages being
retained. This leads to an error in locally deployed models:
Conversation roles must alternate user/assistant/user/assistant/...
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Feat: Install sonner library #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix the issue where waiting tasks couldn't be processed when upstream
components were "switch", "categorize", or "relevant" and the normal
processing path couldn't continue.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
