pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-23 06:46:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Merge main branch (#10377)

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


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com>
Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com>
Co-authored-by: He Wang <wanghechn@qq.com>
Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com>
Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box>
Co-authored-by: Stephen Hu <stephenhu@seismic.com>
Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com>
Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com>
Co-authored-by: mxc <mxc@example.com>
Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com>
Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com>
Co-authored-by: mcoder6425 <mcoder64@gmail.com>
Co-authored-by: TeslaZY <TeslaZY@outlook.com>
Co-authored-by: lemsn <lemsn@msn.com>
Co-authored-by: lemsn <lemsn@126.com>
Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com>
Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com>
Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
This commit is contained in:
Kevin Hu
2025-09-30 13:13:15 +08:00
committed by GitHub
parent 4d6ff672eb
commit 20b577a72c
201 changed files with 7929 additions and 1110 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
agent/component/agent_with_tools.py
View File

@ -28,9 +28,8 @@ from api.db.services.llm_service import LLMBundle
from api.db.services.tenant_llm_service import TenantLLMService
from api.db.services.mcp_server_service import MCPServerService
from api.utils.api_utils import timeout
from rag.prompts import message_fit_in
from rag.prompts.prompts import next_step, COMPLETE_TASK, analyze_task, \
citation_prompt, reflect, rank_memories, kb_prompt, citation_plus, full_question
from rag.prompts.generator import next_step, COMPLETE_TASK, analyze_task, \
citation_prompt, reflect, rank_memories, kb_prompt, citation_plus, full_question, message_fit_in
from rag.utils.mcp_tool_call_conn import MCPToolCallSession, mcp_tool_metadata_to_openai_tool
from agent.component.llm import LLMParam, LLM
@ -138,7 +137,7 @@ class Agent(LLM, ToolBase):
res.update(cpn.get_input_form())
return res
@timeout(os.environ.get("COMPONENT_EXEC_TIMEOUT", 20*60))
@timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 20*60)))
def _invoke(self, **kwargs):
if kwargs.get("user_prompt"):
usr_pmt = ""

4
agent/component/base.py
View File

@ -244,7 +244,7 @@ class ComponentParamBase(ABC):
if not value_legal:
raise ValueError(
"Plase check runtime conf, {} = {} does not match user-parameter restriction".format(
"Please check runtime conf, {} = {} does not match user-parameter restriction".format(
variable, value
)
)
@ -431,7 +431,7 @@ class ComponentBase(ABC):
self.set_output("_elapsed_time", time.perf_counter() - self.output("_created_time"))
return self.output()
@timeout(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60))
@timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
def _invoke(self, **kwargs):
raise NotImplementedError()

10
agent/component/categorize.py
View File

@ -28,7 +28,7 @@ from rag.llm.chat_model import ERROR_PREFIX
class CategorizeParam(LLMParam):
"""
Define the Categorize component parameters.
Define the categorize component parameters.
"""
def __init__(self):
super().__init__()
@ -80,7 +80,7 @@ Here's description of each category:
- Prioritize the most specific applicable category
- Return only the category name without explanations
- Use "Other" only when no other category fits
""".format(
"\n - ".join(list(self.category_description.keys())),
"\n".join(descriptions)
@ -96,7 +96,7 @@ Here's description of each category:
class Categorize(LLM, ABC):
component_name = "Categorize"
@timeout(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60))
@timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
def _invoke(self, **kwargs):
msg = self._canvas.get_history(self._param.message_history_window_size)
if not msg:
@ -112,7 +112,7 @@ class Categorize(LLM, ABC):
user_prompt = """
---- Real Data ----
{} →
{} →
""".format(" | ".join(["{}: \"{}\"".format(c["role"].upper(), re.sub(r"\n", "", c["content"], flags=re.DOTALL)) for c in msg]))
ans = chat_mdl.chat(self._param.sys_prompt, [{"role": "user", "content": user_prompt}], self._param.gen_conf())
logging.info(f"input: {user_prompt}, answer: {str(ans)}")
@ -134,4 +134,4 @@ class Categorize(LLM, ABC):
self.set_output("_next", cpn_ids)
def thoughts(self) -> str:
return "Which should it falls into {}? ...".format(",".join([f"`{c}`" for c, _ in self._param.category_description.items()]))
return "Which should it falls into {}? ...".format(",".join([f"`{c}`" for c, _ in self._param.category_description.items()]))

2
agent/component/invoke.py
View File

@ -53,7 +53,7 @@ class InvokeParam(ComponentParamBase):
class Invoke(ComponentBase, ABC):
component_name = "Invoke"
@timeout(os.environ.get("COMPONENT_EXEC_TIMEOUT", 3))
@timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 3)))
def _invoke(self, **kwargs):
args = {}
for para in self._param.variables:

13
agent/component/llm.py
View File

@ -26,8 +26,7 @@ from api.db.services.llm_service import LLMBundle
from api.db.services.tenant_llm_service import TenantLLMService
from agent.component.base import ComponentBase, ComponentParamBase
from api.utils.api_utils import timeout
from rag.prompts import message_fit_in, citation_prompt
from rag.prompts.prompts import tool_call_summary
from rag.prompts.generator import tool_call_summary, message_fit_in, citation_prompt
class LLMParam(ComponentParamBase):
@ -82,9 +81,9 @@ class LLMParam(ComponentParamBase):
class LLM(ComponentBase):
component_name = "LLM"
def __init__(self, canvas, id, param: ComponentParamBase):
super().__init__(canvas, id, param)
def __init__(self, canvas, component_id, param: ComponentParamBase):
super().__init__(canvas, component_id, param)
self.chat_mdl = LLMBundle(self._canvas.get_tenant_id(), TenantLLMService.llm_id2llm_type(self._param.llm_id),
self._param.llm_id, max_retries=self._param.max_retries,
retry_interval=self._param.delay_after_error
@ -206,7 +205,7 @@ class LLM(ComponentBase):
for txt in self.chat_mdl.chat_streamly(msg[0]["content"], msg[1:], self._param.gen_conf(), images=self.imgs, **kwargs):
yield delta(txt)
@timeout(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60))
@timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
def _invoke(self, **kwargs):
def clean_formated_answer(ans: str) -> str:
ans = re.sub(r"^.*</think>", "", ans, flags=re.DOTALL)
@ -214,7 +213,7 @@ class LLM(ComponentBase):
return re.sub(r"```\n*$", "", ans, flags=re.DOTALL)
prompt, msg, _ = self._prepare_prompt_variables()
error = ""
error: str = ""
if self._param.output_structure:
prompt += "\nThe output MUST follow this JSON format:\n"+json.dumps(self._param.output_structure, ensure_ascii=False, indent=2)

8
agent/component/message.py
View File

@ -49,7 +49,7 @@ class MessageParam(ComponentParamBase):
class Message(ComponentBase):
component_name = "Message"
def get_kwargs(self, script:str, kwargs:dict = {}, delimeter:str=None) -> tuple[str, dict[str, str | list | Any]]:
def get_kwargs(self, script:str, kwargs:dict = {}, delimiter:str=None) -> tuple[str, dict[str, str | list | Any]]:
for k,v in self.get_input_elements_from_text(script).items():
if k in kwargs:
continue
@ -60,8 +60,8 @@ class Message(ComponentBase):
if isinstance(v, partial):
for t in v():
ans += t
elif isinstance(v, list) and delimeter:
ans = delimeter.join([str(vv) for vv in v])
elif isinstance(v, list) and delimiter:
ans = delimiter.join([str(vv) for vv in v])
elif not isinstance(v, str):
try:
ans = json.dumps(v, ensure_ascii=False)
@ -127,7 +127,7 @@ class Message(ComponentBase):
]
return any([re.search(p, content) for p in patt])
@timeout(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60))
@timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
def _invoke(self, **kwargs):
rand_cnt = random.choice(self._param.content)
if self._param.stream and not self._is_jinjia2(rand_cnt):

4
agent/component/string_transform.py
View File

@ -56,7 +56,7 @@ class StringTransform(Message, ABC):
"type": "line"
} for k, o in self.get_input_elements_from_text(self._param.script).items()}
@timeout(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60))
@timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60)))
def _invoke(self, **kwargs):
if self._param.method == "split":
self._split(kwargs.get("line"))
@ -90,7 +90,7 @@ class StringTransform(Message, ABC):
for k,v in kwargs.items():
if not v:
v = ""
script = re.sub(k, v, script)
script = re.sub(k, lambda match: v, script)
self.set_output("result", script)

2
agent/component/switch.py
View File

@ -61,7 +61,7 @@ class SwitchParam(ComponentParamBase):
class Switch(ComponentBase, ABC):
component_name = "Switch"
@timeout(os.environ.get("COMPONENT_EXEC_TIMEOUT", 3))
@timeout(int(os.environ.get("COMPONENT_EXEC_TIMEOUT", 3)))
def _invoke(self, **kwargs):
for cond in self._param.conditions:
res = []