pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix errors (#11804)

Browse Source 
### What problem does this PR solve?

1. typos
2. grammar errors.

### Type of change

- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2025-12-08 12:21:18 +08:00
committed by GitHub
parent 5a2011e687
commit 43f51baa96
25 changed files with 53 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
agent/canvas.py
View File

@ -478,7 +478,7 @@ class Canvas(Graph):
})
await _run_batch(idx, to)
to = len(self.path)
# post processing of components invocation
# post-processing of components invocation
for i in range(idx, to):
cpn = self.get_component(self.path[i])
cpn_obj = self.get_component_obj(self.path[i])

28
agent/tools/yahoofinance.py
View File

@ -75,7 +75,7 @@ class YahooFinance(ToolBase, ABC):
@timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 60)))
def _invoke(self, **kwargs):
if self.check_if_canceled("YahooFinance processing"):
return
return None
if not kwargs.get("stock_code"):
self.set_output("report", "")
@ -84,33 +84,33 @@ class YahooFinance(ToolBase, ABC):
last_e = ""
for _ in range(self._param.max_retries+1):
if self.check_if_canceled("YahooFinance processing"):
return
return None
yohoo_res = []
yahoo_res = []
try:
msft = yf.Ticker(kwargs["stock_code"])
if self.check_if_canceled("YahooFinance processing"):
return
return None
if self._param.info:
yohoo_res.append("# Information:\n" + pd.Series(msft.info).to_markdown() + "\n")
yahoo_res.append("# Information:\n" + pd.Series(msft.info).to_markdown() + "\n")
if self._param.history:
yohoo_res.append("# History:\n" + msft.history().to_markdown() + "\n")
yahoo_res.append("# History:\n" + msft.history().to_markdown() + "\n")
if self._param.financials:
yohoo_res.append("# Calendar:\n" + pd.DataFrame(msft.calendar).to_markdown() + "\n")
yahoo_res.append("# Calendar:\n" + pd.DataFrame(msft.calendar).to_markdown() + "\n")
if self._param.balance_sheet:
yohoo_res.append("# Balance sheet:\n" + msft.balance_sheet.to_markdown() + "\n")
yohoo_res.append("# Quarterly balance sheet:\n" + msft.quarterly_balance_sheet.to_markdown() + "\n")
yahoo_res.append("# Balance sheet:\n" + msft.balance_sheet.to_markdown() + "\n")
yahoo_res.append("# Quarterly balance sheet:\n" + msft.quarterly_balance_sheet.to_markdown() + "\n")
if self._param.cash_flow_statement:
yohoo_res.append("# Cash flow statement:\n" + msft.cashflow.to_markdown() + "\n")
yohoo_res.append("# Quarterly cash flow statement:\n" + msft.quarterly_cashflow.to_markdown() + "\n")
yahoo_res.append("# Cash flow statement:\n" + msft.cashflow.to_markdown() + "\n")
yahoo_res.append("# Quarterly cash flow statement:\n" + msft.quarterly_cashflow.to_markdown() + "\n")
if self._param.news:
yohoo_res.append("# News:\n" + pd.DataFrame(msft.news).to_markdown() + "\n")
self.set_output("report", "\n\n".join(yohoo_res))
yahoo_res.append("# News:\n" + pd.DataFrame(msft.news).to_markdown() + "\n")
self.set_output("report", "\n\n".join(yahoo_res))
return self.output("report")
except Exception as e:
if self.check_if_canceled("YahooFinance processing"):
return
return None
last_e = e
logging.exception(f"YahooFinance error: {e}")

2
api/apps/__init__.py
View File

@ -180,7 +180,7 @@ def login_user(user, remember=False, duration=None, force=False, fresh=True):
user's `is_active` property is ``False``, they will not be logged in
unless `force` is ``True``.
This will return ``True`` if the log in attempt succeeds, and ``False`` if
This will return ``True`` if the login attempt succeeds, and ``False`` if
it fails (i.e. because the user is inactive).
:param user: The user object to log in.

4
api/apps/sdk/doc.py
View File

@ -552,7 +552,7 @@ def list_docs(dataset_id, tenant_id):
create_time_from = int(q.get("create_time_from", 0))
create_time_to = int(q.get("create_time_to", 0))
# map run status (accept text or numeric) - align with API parameter
# map run status (text or numeric) - align with API parameter
run_status_text_to_numeric = {"UNSTART": "0", "RUNNING": "1", "CANCEL": "2", "DONE": "3", "FAIL": "4"}
run_status_converted = [run_status_text_to_numeric.get(v, v) for v in run_status]
@ -890,7 +890,7 @@ def list_chunks(tenant_id, dataset_id, document_id):
type: string
required: false
default: ""
description: Chunk Id.
description: Chunk id.
- in: header
name: Authorization
type: string

12
common/data_source/confluence_connector.py
View File

@ -126,7 +126,7 @@ class OnyxConfluence:
def _renew_credentials(self) -> tuple[dict[str, Any], bool]:
"""credential_json - the current json credentials
Returns a tuple
1. The up to date credentials
1. The up-to-date credentials
2. True if the credentials were updated
This method is intended to be used within a distributed lock.
@ -179,8 +179,8 @@ class OnyxConfluence:
credential_json["confluence_refresh_token"],
)
# store the new credentials to redis and to the db thru the provider
# redis: we use a 5 min TTL because we are given a 10 minute grace period
# store the new credentials to redis and to the db through the provider
# redis: we use a 5 min TTL because we are given a 10 minutes grace period
# when keys are rotated. it's easier to expire the cached credentials
# reasonably frequently rather than trying to handle strong synchronization
# between the db and redis everywhere the credentials might be updated
@ -690,7 +690,7 @@ class OnyxConfluence:
) -> Iterator[dict[str, Any]]:
"""
This function will paginate through the top level query first, then
paginate through all of the expansions.
paginate through all the expansions.
"""
def _traverse_and_update(data: dict | list) -> None:
@ -863,7 +863,7 @@ def get_user_email_from_username__server(
# For now, we'll just return None and log a warning. This means
# we will keep retrying to get the email every group sync.
email = None
# We may want to just return a string that indicates failure so we dont
# We may want to just return a string that indicates failure so we don't
# keep retrying
# email = f"FAILED TO GET CONFLUENCE EMAIL FOR {user_name}"
_USER_EMAIL_CACHE[user_name] = email
@ -912,7 +912,7 @@ def extract_text_from_confluence_html(
confluence_object: dict[str, Any],
fetched_titles: set[str],
) -> str:
"""Parse a Confluence html page and replace the 'user Id' by the real
"""Parse a Confluence html page and replace the 'user id' by the real
User Display Name
Args:

2
common/data_source/google_drive/doc_conversion.py
View File

@ -76,7 +76,7 @@ ALL_ACCEPTED_FILE_EXTENSIONS = ACCEPTED_PLAIN_TEXT_FILE_EXTENSIONS + ACCEPTED_DO
MAX_RETRIEVER_EMAILS = 20
CHUNK_SIZE_BUFFER = 64 # extra bytes past the limit to read
# This is not a standard valid unicode char, it is used by the docs advanced API to
# This is not a standard valid Unicode char, it is used by the docs advanced API to
# represent smart chips (elements like dates and doc links).
SMART_CHIP_CHAR = "\ue907"
WEB_VIEW_LINK_KEY = "webViewLink"

4
common/data_source/google_drive/file_retrieval.py
View File

@ -141,7 +141,7 @@ def crawl_folders_for_files(
# Only mark a folder as done if it was fully traversed without errors
# This usually indicates that the owner of the folder was impersonated.
# In cases where this never happens, most likely the folder owner is
# not part of the google workspace in question (or for oauth, the authenticated
# not part of the Google Workspace in question (or for oauth, the authenticated
# user doesn't own the folder)
if found_files:
update_traversed_ids_func(parent_id)
@ -232,7 +232,7 @@ def get_files_in_shared_drive(
**kwargs,
):
# If we found any files, mark this drive as traversed. When a user has access to a drive,
# they have access to all the files in the drive. Also not a huge deal if we re-traverse
# they have access to all the files in the drive. Also, not a huge deal if we re-traverse
# empty drives.
# NOTE: ^^ the above is not actually true due to folder restrictions:
# https://support.google.com/a/users/answer/12380484?hl=en

4
common/data_source/google_drive/model.py
View File

@ -22,7 +22,7 @@ class GDriveMimeType(str, Enum):
MARKDOWN = "text/markdown"
# These correspond to The major stages of retrieval for google drive.
# These correspond to The major stages of retrieval for Google Drive.
# The stages for the oauth flow are:
# get_all_files_for_oauth(),
# get_all_drive_ids(),
@ -117,7 +117,7 @@ class GoogleDriveCheckpoint(ConnectorCheckpoint):
class RetrievedDriveFile(BaseModel):
"""
Describes a file that has been retrieved from google drive.
Describes a file that has been retrieved from Google Drive.
user_email is the email of the user that the file was retrieved
by impersonating. If an error worthy of being reported is encountered,
error should be set and later propagated as a ConnectorFailure.

4
common/data_source/google_util/resource.py
View File

@ -29,8 +29,8 @@ class GmailService(Resource):
class RefreshableDriveObject:
"""
Running Google drive service retrieval functions
involves accessing methods of the service object (ie. files().list())
Running Google Drive service retrieval functions
involves accessing methods of the service object (i.e. files().list())
which can raise a RefreshError if the access token is expired.
This class is a wrapper that propagates the ability to refresh the access token
and retry the final retrieval function until execute() is called.

2
common/data_source/html_utils.py
View File

@ -120,7 +120,7 @@ def format_document_soup(
# table is standard HTML element
if e.name == "table":
in_table = True
# tr is for rows
# TR is for rows
elif e.name == "tr" and in_table:
text += "\n"
# td for data cell, th for header

3
common/data_source/interfaces.py
View File

@ -395,8 +395,7 @@ class AttachmentProcessingResult(BaseModel):
class IndexingHeartbeatInterface(ABC):
"""Defines a callback interface to be passed to
to run_indexing_entrypoint."""
"""Defines a callback interface to be passed to run_indexing_entrypoint."""
@abstractmethod
def should_stop(self) -> bool:

2
common/data_source/jira/connector.py
View File

@ -80,7 +80,7 @@ _TZ_OFFSET_PATTERN = re.compile(r"([+-])(\d{2})(:?)(\d{2})$")
class JiraConnector(CheckpointedConnectorWithPermSync, SlimConnectorWithPermSync):
"""Retrieve Jira issues and emit them as markdown documents."""
"""Retrieve Jira issues and emit them as Markdown documents."""
def __init__(
self,

4
common/data_source/models.py
View File

@ -54,8 +54,8 @@ class ExternalAccess:
A helper function that returns an *empty* set of external user-emails and group-ids, and sets `is_public` to `False`.
This effectively makes the document in question "private" or inaccessible to anyone else.
This is especially helpful to use when you are performing permission-syncing, and some document's permissions aren't able
to be determined (for whatever reason). Setting its `ExternalAccess` to "private" is a feasible fallback.
This is especially helpful to use when you are performing permission-syncing, and some document's permissions can't
be determined (for whatever reason). Setting its `ExternalAccess` to "private" is a feasible fallback.
"""
return cls(

2
common/string_utils.py
View File

@ -61,7 +61,7 @@ def clean_markdown_block(text):
str: Cleaned text with Markdown code block syntax removed, and stripped of surrounding whitespace
"""
# Remove opening ```markdown tag with optional whitespace and newlines
# Remove opening ```Markdown tag with optional whitespace and newlines
# Matches: optional whitespace + ```markdown + optional whitespace + optional newline
text = re.sub(r'^\s*```markdown\s*\n?', '', text)

4
deepdoc/README.md
View File

@ -51,7 +51,7 @@ We use vision information to resolve problems as human being.
```bash
python deepdoc/vision/t_ocr.py --inputs=path_to_images_or_pdfs --output_dir=path_to_store_result
```
The inputs could be directory to images or PDF, or a image or PDF.
The inputs could be directory to images or PDF, or an image or PDF.
You can look into the folder 'path_to_store_result' where has images which demonstrate the positions of results,
txt files which contain the OCR text.
<div align="center" style="margin-top:20px;margin-bottom:20px;">
@ -78,7 +78,7 @@ We use vision information to resolve problems as human being.
```bash
python deepdoc/vision/t_recognizer.py --inputs=path_to_images_or_pdfs --threshold=0.2 --mode=layout --output_dir=path_to_store_result
```
The inputs could be directory to images or PDF, or a image or PDF.
The inputs could be directory to images or PDF, or an image or PDF.
You can look into the folder 'path_to_store_result' where has images which demonstrate the detection results as following:
<div align="center" style="margin-top:20px;margin-bottom:20px;">
<img src="https://github.com/infiniflow/ragflow/assets/12318111/07e0f625-9b28-43d0-9fbb-5bf586cd286f" width="1000"/>

2
deepdoc/vision/table_structure_recognizer.py
View File

@ -155,7 +155,7 @@ class TableStructureRecognizer(Recognizer):
while i < len(boxes):
if TableStructureRecognizer.is_caption(boxes[i]):
if is_english:
cap + " "
cap += " "
cap += boxes[i]["text"]
boxes.pop(i)
i -= 1

4
docs/references/http_api_reference.md
View File

@ -4013,7 +4013,7 @@ Failure:
**DELETE** `/api/v1/agents/{agent_id}/sessions`
Deletes sessions of a agent by ID.
Deletes sessions of an agent by ID.
#### Request
@ -4072,7 +4072,7 @@ Failure:
Generates five to ten alternative question strings from the user's original query to retrieve more relevant search results.
This operation requires a `Bearer Login Token`, which typically expires with in 24 hours. You can find the it in the Request Headers in your browser easily as shown below:
This operation requires a `Bearer Login Token`, which typically expires with in 24 hours. You can find it in the Request Headers in your browser easily as shown below:
![Image](https://raw.githubusercontent.com/infiniflow/ragflow-docs/main/images/login_token.jpg)

2
docs/references/python_api_reference.md
View File

@ -1740,7 +1740,7 @@ for session in sessions:
Agent.delete_sessions(ids: list[str] = None)
```
Deletes sessions of a agent by ID.
Deletes sessions of an agent by ID.
#### Parameters

2
plugin/README.md
View File

@ -92,6 +92,6 @@ def get_metadata(cls) -> LLMToolMetadata:
The `get_metadata` method is a `classmethod`. It will provide the description of this tool to LLM.
The fields starts with `display` can use a special notation: `$t:xxx`, which will use the i18n mechanism in the RAGFlow frontend, getting text from the `llmTools` category. The frontend will display what you put here if you don't use this notation.
The fields start with `display` can use a special notation: `$t:xxx`, which will use the i18n mechanism in the RAGFlow frontend, getting text from the `llmTools` category. The frontend will display what you put here if you don't use this notation.
Now our tool is ready. You can select it in the `Generate` component and try it out.

2
plugin/embedded_plugins/llm_tools/bad_calculator.py
View File

@ -5,7 +5,7 @@ from plugin.llm_tool_plugin import LLMToolMetadata, LLMToolPlugin
class BadCalculatorPlugin(LLMToolPlugin):
"""
A sample LLM tool plugin, will add two numbers with 100.
It only present for demo purpose. Do not use it in production.
It only presents for demo purpose. Do not use it in production.
"""
_version_ = "1.0.0"

2
rag/app/book.py
View File

@ -70,7 +70,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
"""
Supported file formats are docx, pdf, txt.
Since a book is long and not all the parts are useful, if it's a PDF,
please setup the page ranges for every book in order eliminate negative effects and save elapsed computing time.
please set up the page ranges for every book in order eliminate negative effects and save elapsed computing time.
"""
parser_config = kwargs.get(
"parser_config", {

2
rag/app/qa.py
View File

@ -313,7 +313,7 @@ def mdQuestionLevel(s):
def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", callback=None, **kwargs):
"""
Excel and csv(txt) format files are supported.
If the file is in excel format, there should be 2 column question and answer without header.
If the file is in Excel format, there should be 2 column question and answer without header.
And question column is ahead of answer column.
And it's O.K if it has multiple sheets as long as the columns are rightly composed.

2
rag/app/tag.py
View File

@ -37,7 +37,7 @@ def beAdoc(d, q, a, eng, row_num=-1):
def chunk(filename, binary=None, lang="Chinese", callback=None, **kwargs):
"""
Excel and csv(txt) format files are supported.
If the file is in excel format, there should be 2 column content and tags without header.
If the file is in Excel format, there should be 2 column content and tags without header.
And content column is ahead of tags column.
And it's O.K if it has multiple sheets as long as the columns are rightly composed.

2
web/src/components/json-edit/interface.ts
View File

@ -244,7 +244,7 @@ export interface JsonEditorOptions {
timestampFormat?: string;
/**
* If true, unicode characters are escaped. false by default.
* If true, Unicode characters are escaped. false by default.
*/
escapeUnicode?: boolean;

8
web/src/services/admin.service.d.ts vendored
View File

@ -66,7 +66,7 @@ declare module AdminService {
title: string;
};
export type TaskExectorHeartbeatItem = {
export type TaskExecutorHeartbeatItem = {
name: string;
boot_at: string;
now: string;
@ -79,7 +79,7 @@ declare module AdminService {
pid: number;
};
export type TaskExecutorInfo = Record<string, TaskExectorHeartbeatItem[]>;
export type TaskExecutorInfo = Record<string, TaskExecutorHeartbeatItem[]>;
export type ListServicesItem = {
extra: Record<string, unknown>;
@ -134,7 +134,7 @@ declare module AdminService {
export type RoleDetail = {
id: string;
name: string;
descrtiption: string;
description: string;
create_date: string;
update_date: string;
};
@ -162,7 +162,7 @@ declare module AdminService {
id: number;
email: string;
create_date: string;
createt_time: number;
create_time: number;
update_date: string;
update_time: number;
};