### What problem does this PR solve?
when``` if 'signature_version' in self.s3_config:``` and ```if
'addressing_style' in self.s3_config:``` both true.
the config init is error, will be overwrite by last one.
this pr is for fix that case.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
Fix: fix typo in OpenAI error logging message (#8865)
### What problem does this PR solve?
Correct the logging message from "OpenAI cat_with_tools" to "OpenAI
chat_with_tools" in the `_exceptions` method of the `Base` class to
accurately reflect the method name and improve error traceability.
### Type of change
- [x] Typo
Fix: fixed invalid save() arguments for slide thumbnails (#8851)
### What problem does this PR solve?
Fixed invalid save() arguments for slide thumbnails.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Fix: fixed context loss caused by separating markdown tables from original text (#8844)
### What problem does this PR solve?
Fix context loss caused by separating markdown tables from original
text. #6871, #8804.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fixes no chunks parsed out for Law. #5113
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add xAI provider (experimental feature, requires user feedback).
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Based on https://github.com/infiniflow/ragflow/issues/8740
1. A better handle for 'NoneType' object is not subscriptable
2. Add some logs to get the internal message
### Type of change
- [x] Refactoring
### What problem does this PR solve?
1. Remove the useless pop logic due to already been checked at the if
logic
2. merge log logic
### Type of change
- [x] Refactoring
fix: retry embedding with Qwen family models when limits temporarily reached. (#8690)
fix: retry embedding with Qwen family models when limits temporarily
reached.
APIs of Qwen family models are limited by calling rates. When reached,
the "output" attribute of the "resp" will be None, and in turn cause
TypeError when trying to retrieve "embeddings". Since these limits are
almost temporary, I have added a simple retry mechanism to avoid it.
Besides, if retry_max reached, the error can be early raised, instead of
hidden behind "TypeError".
### What problem does this PR solve?
Sometimes Qwen blocks calling due to rate limits, but it will cause the
whole parsing procedure stops when creating knowledge base. In this
situation, resp["output"] will be None, and resp["output"]["embeddings"]
will cause TypeError. Since the limits are temporary, I apply a simple
retry mechanism to solve it.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Fix a small typo in count of used fragments (#8673)
### What problem does this PR solve?
Fix a small typo in count of used fragments.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
The following error occurred during local testing, which should be fixed
by configuring 'exist_ok=True'.
```log
set_progress(7461edc253), progress: -1, progress_msg: 21:41:41 Page(1~100000001): [ERROR][Errno 17] File exists: '/ragflow/tmp'
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
fix opendal config 'oss_table' and 'max_allowed_packet' (#8611)
### What problem does this PR solve?
Fix the config option name of the opendal table name and setting of
'max_allowed_packet'.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: He Wang <wanghechn@qq.com>
Add Google Cloud Vision API Integration (Image2Text) (#8608)
### What problem does this PR solve?
This PR introduces Google Cloud Vision API integration to enhance image
understanding capabilities in the application. It addresses the need for
advanced image description and chat functionalities by implementing a
new `GoogleCV` class to handle API interactions and updating relevant
configurations. This enables users to leverage Google Cloud Vision for
image-to-text tasks, improving the application's ability to process and
interpret visual data.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
docx parse error.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Some docx parse with naive cause error. `block.style.name` in Function
`__get_nearest_title` will be None in some case.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: wenxuan.zhang <wenxuan.zhang@chinacreator.com>
fix: Correctly format message parts in GoogleChat (#8596)
### What problem does this PR solve?
This PR addresses an incompatibility issue with the Google Chat API by
correcting the message content format in the `GoogleChat` class.
Previously, the content was directly assigned to the "parts" field,
which did not align with the API's expected format. This change ensures
that messages are properly formatted with a "text" key within a
dictionary, as required by the API.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: the output log is incorrect
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: liang <xiaofeng.liang@landstech.com.cn>
Fix memory leaks in PIL image and BytesIO handling during chunk processing (#8522)
### What problem does this PR solve?
This PR addresses critical memory leaks in the task executor's image
processing pipeline. The current implementation fails to properly
dispose of PIL Image objects and BytesIO buffers during chunk
processing, leading to progressive memory accumulation that can cause
the task executor to consume excessive memory over time.
### Background context
- The `upload_to_minio` function processes images from document chunks
and converts them to JPEG format for storage.
- PIL Image objects hold significant memory resources that must be
explicitly closed to prevent memory leaks.
- BytesIO objects also consume memory and should be properly disposed of
after use.
- In high-throughput scenarios with many image-containing documents,
these memory leaks can lead to out-of-memory errors and degraded
performance.
### Specific issues fixed
- PIL Image objects were not being explicitly closed after processing.
- BytesIO buffers lacked proper cleanup in all code paths.
- Converted images (RGBA/P to RGB) were not disposing of the original
image object.
- Memory references to large image data were not being cleared promptly.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Performance Improvement
### Changes made
- Added explicit `d["image"].close()` calls after image processing
operations.
- Implemented proper cleanup of converted images when changing formats
from RGBA/P to RGB.
- Enhanced BytesIO cleanup with `try/finally` blocks to ensure disposal
in all code paths.
- Added explicit `del d["image"]` to clear memory references after
processing.
This fix ensures stable memory usage during long-running document
processing tasks and prevents potential out-of-memory conditions in
production environments.
Refactor:improve the logic to check cancel (#8524)
### What problem does this PR solve?
improve the logic to check cancel
### Type of change
- [x] Refactoring
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Fix parser_config access for layout_recognize in presentation.py (#8492)
### What problem does this PR solve?
This PR addresses an issue in the presentation parser where the
`layout_recognize` configuration was incorrectly retrieved from
`kwargs.get("layout_recognize", "DeepDOC")`. Instead, it should be
sourced from the `parser_config` parameter, specifically
`parser_config.get("layout_recognize", "DeepDOC")`.
This mismatch could cause the parser to default to the "DeepDOC" layout
recognizer, ignoring any alternative recognition method specified in the
parser configuration. As a result, PDF document parsing might use an
incorrect recognition engine.
The fix ensures the presentation parser consistently uses the
`layout_recognize` setting from `parser_config`, aligning with the
configuration access patterns used elsewhere in the codebase.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
fix the error 'Unknown field for GenerationConfig: max_tokens' when u… (#8473)
### What problem does this PR solve?
[https://github.com/infiniflow/ragflow/issues/8324](url)
docker image version: v0.19.1
The `_clean_conf` function was not implemented in the `_chat` and
`chat_streamly` methods of the `GeminiChat` class, causing the error
"Unknown field for GenerationConfig: max_tokens" when the default LLM
config includes the "max_tokens" parameter.
**Buggy Code(ragflow/rag/llm/chat_model.py)**
```python
class GeminiChat(Base):
def __init__(self, key, model_name, base_url=None, **kwargs):
super().__init__(key, model_name, base_url=base_url, **kwargs)
from google.generativeai import GenerativeModel, client
client.configure(api_key=key)
_client = client.get_default_generative_client()
self.model_name = "models/" + model_name
self.model = GenerativeModel(model_name=self.model_name)
self.model._client = _client
def _clean_conf(self, gen_conf):
for k in list(gen_conf.keys()):
if k not in ["temperature", "top_p"]:
del gen_conf[k]
return gen_conf
def _chat(self, history, gen_conf):
from google.generativeai.types import content_types
system = history[0]["content"] if history and history[0]["role"] == "system" else ""
hist = []
for item in history:
if item["role"] == "system":
continue
hist.append(deepcopy(item))
item = hist[-1]
if "role" in item and item["role"] == "assistant":
item["role"] = "model"
if "role" in item and item["role"] == "system":
item["role"] = "user"
if "content" in item:
item["parts"] = item.pop("content")
if system:
self.model._system_instruction = content_types.to_content(system)
response = self.model.generate_content(hist, generation_config=gen_conf)
ans = response.text
return ans, response.usage_metadata.total_token_count
def chat_streamly(self, system, history, gen_conf):
from google.generativeai.types import content_types
if system:
self.model._system_instruction = content_types.to_content(system)
#❌_clean_conf was not implemented
for k in list(gen_conf.keys()):
if k not in ["temperature", "top_p", "max_tokens"]:
del gen_conf[k]
for item in history:
if "role" in item and item["role"] == "assistant":
item["role"] = "model"
if "content" in item:
item["parts"] = item.pop("content")
ans = ""
try:
response = self.model.generate_content(history, generation_config=gen_conf, stream=True)
for resp in response:
ans = resp.text
yield ans
yield response._chunks[-1].usage_metadata.total_token_count
except Exception as e:
yield ans + "\n**ERROR**: " + str(e)
yield 0
```
**Implement the _clean_conf function**
```python
class GeminiChat(Base):
def __init__(self, key, model_name, base_url=None, **kwargs):
super().__init__(key, model_name, base_url=base_url, **kwargs)
from google.generativeai import GenerativeModel, client
client.configure(api_key=key)
_client = client.get_default_generative_client()
self.model_name = "models/" + model_name
self.model = GenerativeModel(model_name=self.model_name)
self.model._client = _client
def _clean_conf(self, gen_conf):
for k in list(gen_conf.keys()):
if k not in ["temperature", "top_p"]:
del gen_conf[k]
return gen_conf
def _chat(self, history, gen_conf):
from google.generativeai.types import content_types
#✅ implement _clean_conf to remove the wrong parameters
gen_conf = self._clean_conf(gen_conf)
system = history[0]["content"] if history and history[0]["role"] == "system" else ""
hist = []
for item in history:
if item["role"] == "system":
continue
hist.append(deepcopy(item))
item = hist[-1]
if "role" in item and item["role"] == "assistant":
item["role"] = "model"
if "role" in item and item["role"] == "system":
item["role"] = "user"
if "content" in item:
item["parts"] = item.pop("content")
if system:
self.model._system_instruction = content_types.to_content(system)
response = self.model.generate_content(hist, generation_config=gen_conf)
ans = response.text
return ans, response.usage_metadata.total_token_count
def chat_streamly(self, system, history, gen_conf):
from google.generativeai.types import content_types
#✅ implement _clean_conf to remove the wrong parameters
gen_conf = self._clean_conf(gen_conf)
if system:
self.model._system_instruction = content_types.to_content(system)
#✅Removed duplicate parameter filtering logic "for k in list(gen_conf.keys()):"
for item in history:
if "role" in item and item["role"] == "assistant":
item["role"] = "model"
if "content" in item:
item["parts"] = item.pop("content")
ans = ""
try:
response = self.model.generate_content(history, generation_config=gen_conf, stream=True)
for resp in response:
ans = resp.text
yield ans
yield response._chunks[-1].usage_metadata.total_token_count
except Exception as e:
yield ans + "\n**ERROR**: " + str(e)
yield 0
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Fix: Solve the OOM issue when passing large PDF files while using QA chunking method. (#8464)
### What problem does this PR solve?
Using the QA chunking method with a large PDF (e.g., 300+ pages) may
lead to OOM in the ragflow-worker module.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
湛露先生
Stephen Hu
Kevin Hu
Liu An
Yongteng Lei
6607changchun
kwrobel.eth
He Wang
Tuan Le
wenxuan.zhang
symvation
Rainman
liuzhenghua