zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-07-10 21:55:42 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

Browse Source
This commit is contained in:
Wang Qi
2026-07-03 12:53:39 +08:00
committed by GitHub
parent 19fcb4a981
commit 6a4b9be426
588 changed files with 11123 additions and 15412 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
sdk/python/ragflow_sdk/__init__.py
View File

@@ -15,6 +15,7 @@
#
from beartype.claw import beartype_this_package
beartype_this_package()
import importlib.metadata
@@ -30,13 +31,4 @@ from .modules.memory import Memory
__version__ = importlib.metadata.version("ragflow_sdk")
__all__ = [
"RAGFlow",
"DataSet",
"Chat",
"Session",
"Document",
"Chunk",
"Agent",
"Memory"
]
__all__ = ["RAGFlow", "DataSet", "Chat", "Session", "Document", "Chunk", "Agent", "Memory"]

2
sdk/python/ragflow_sdk/modules/__init__.py
View File

@@ -12,4 +12,4 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
#

46
sdk/python/ragflow_sdk/modules/agent.py
View File

@@ -20,7 +20,7 @@ from .session import Session
class Agent(Base):
def __init__(self, rag, res_dict):
self.id = None
self.id = None
self.avatar = None
self.canvas_type = None
self.description = None
@@ -30,42 +30,17 @@ class Agent(Base):
class Dsl(Base):
def __init__(self, rag, res_dict):
self.answer = []
self.components = {
"begin": {
"downstream": ["Answer:China"],
"obj": {
"component_name": "Begin",
"params": {}
},
"upstream": []
}
}
self.components = {"begin": {"downstream": ["Answer:China"], "obj": {"component_name": "Begin", "params": {}}, "upstream": []}}
self.graph = {
"edges": [],
"nodes": [
{
"data": {
"label": "Begin",
"name": "begin"
},
"id": "begin",
"position": {
"x": 50,
"y": 200
},
"sourcePosition": "left",
"targetPosition": "right",
"type": "beginNode"
}
]
"nodes": [{"data": {"label": "Begin", "name": "begin"}, "id": "begin", "position": {"x": 50, "y": 200}, "sourcePosition": "left", "targetPosition": "right", "type": "beginNode"}],
}
self.history = []
self.messages = []
self.path = []
self.history = []
self.messages = []
self.path = []
self.reference = []
super().__init__(rag, res_dict)
def create_session(self, **kwargs) -> Session:
res = self.post(f"/agents/{self.id}/sessions", json=kwargs)
res = res.json()
@@ -73,11 +48,8 @@ class Agent(Base):
return Session(self.rag, res.get("data"))
raise Exception(res.get("message"))
def list_sessions(self, page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True,
id: str = None) -> list[Session]:
res = self.get(f"/agents/{self.id}/sessions",
{"page": page, "page_size": page_size, "orderby": orderby, "desc": desc, "id": id})
def list_sessions(self, page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True, id: str = None) -> list[Session]:
res = self.get(f"/agents/{self.id}/sessions", {"page": page, "page_size": page_size, "orderby": orderby, "desc": desc, "id": id})
res = res.json()
if res.get("code") == 0:
result_list = []
@@ -86,7 +58,7 @@ class Agent(Base):
result_list.append(temp_agent)
return result_list
raise Exception(res.get("message"))
def delete_sessions(self, ids: list[str] | None = None, delete_all: bool = False):
payload = {"ids": ids}
if delete_all:

11
sdk/python/ragflow_sdk/modules/chunk.py
View File

@@ -16,6 +16,7 @@
from .base import Base
class ChunkUpdateError(Exception):
def __init__(self, code=None, message=None, details=None):
self.code = code
@@ -23,6 +24,7 @@ class ChunkUpdateError(Exception):
self.details = details
super().__init__(message)
class Chunk(Base):
def __init__(self, rag, res_dict):
self.id = ""
@@ -48,17 +50,12 @@ class Chunk(Base):
res_dict.pop(k)
super().__init__(rag, res_dict)
#for backward compatibility
# for backward compatibility
if not self.document_name:
self.document_name = self.document_keyword
def update(self, update_message: dict):
res = self.patch(f"/datasets/{self.dataset_id}/documents/{self.document_id}/chunks/{self.id}", update_message)
res = res.json()
if res.get("code") != 0:
raise ChunkUpdateError(
code=res.get("code"),
message=res.get("message"),
details=res.get("details")
)
raise ChunkUpdateError(code=res.get("code"), message=res.get("message"), details=res.get("details"))

9
sdk/python/ragflow_sdk/modules/dataset.py
View File

@@ -113,18 +113,21 @@ class DataSet(Base):
def _get_documents_status(self, document_ids):
import time
terminal_states = {"DONE", "FAIL", "CANCEL"}
interval_sec = 1
pending = set(document_ids)
finished = []
while pending:
for doc_id in list(pending):
def fetch_doc(doc_id: str) -> Document | None:
try:
docs = self.list_documents(id=doc_id)
return docs[0] if docs else None
except Exception:
return None
doc = fetch_doc(doc_id)
if doc is None:
continue
@@ -137,13 +140,12 @@ class DataSet(Base):
if pending:
time.sleep(interval_sec)
return finished
def async_parse_documents(self, document_ids):
res = self.post(f"/datasets/{self.id}/chunks", {"document_ids": document_ids})
res = res.json()
if res.get("code") != 0:
raise Exception(res.get("message"))
def parse_documents(self, document_ids):
try:
@@ -151,9 +153,8 @@ class DataSet(Base):
self._get_documents_status(document_ids)
except KeyboardInterrupt:
self.async_cancel_parse_documents(document_ids)
return self._get_documents_status(document_ids)
return self._get_documents_status(document_ids)
def async_cancel_parse_documents(self, document_ids):
res = self.rm(f"/datasets/{self.id}/chunks", {"document_ids": document_ids})

16
sdk/python/ragflow_sdk/modules/memory.py
View File

@@ -18,7 +18,6 @@ from .base import Base
class Memory(Base):
def __init__(self, rag, res_dict):
self.id = ""
self.name = ""
@@ -33,7 +32,7 @@ class Memory(Base):
self.description = ""
self.memory_size = 5 * 1024 * 1024
self.forgetting_policy = "FIFO"
self.temperature = 0.5,
self.temperature = (0.5,)
self.system_prompt = ""
self.user_prompt = ""
for k in list(res_dict.keys()):
@@ -57,13 +56,8 @@ class Memory(Base):
self._update_from_dict(self.rag, res.get("data", {}))
return self
def list_memory_messages(self, agent_id: str | list[str]=None, keywords: str=None, page: int=1, page_size: int=50):
params = {
"agent_id": agent_id,
"keywords": keywords,
"page": page,
"page_size": page_size
}
def list_memory_messages(self, agent_id: str | list[str] = None, keywords: str = None, page: int = 1, page_size: int = 50):
params = {"agent_id": agent_id, "keywords": keywords, "page": page, "page_size": page_size}
res = self.get(f"/memories/{self.id}", params)
res = res.json()
if res.get("code") != 0:
@@ -78,9 +72,7 @@ class Memory(Base):
return True
def update_message_status(self, message_id: int, status: bool):
update_message = {
"status": status
}
update_message = {"status": status}
res = self.put(f"/messages/{self.id}:{message_id}", update_message)
res = res.json()
if res.get("code") != 0:

25
sdk/python/ragflow_sdk/modules/session.py
View File

@@ -36,7 +36,6 @@ class Session(Base):
self.__session_type = "agent"
super().__init__(rag, res_dict)
def ask(
self,
question="",
@@ -89,8 +88,7 @@ class Session(Base):
if inputs is not None or release is not None or return_trace is not None:
logger.debug(
"Session.ask explicit-params session_type=%s session_id=%s "
"input_keys=%s release=%s return_trace=%s",
"Session.ask explicit-params session_type=%s session_id=%s input_keys=%s release=%s return_trace=%s",
self.__session_type,
getattr(self, "id", None),
list(inputs.keys()) if isinstance(inputs, dict) else None,
@@ -111,7 +109,7 @@ class Session(Base):
continue # Skip empty lines
line = line.strip()
if line.startswith("data:"):
content = line[len("data:"):].strip()
content = line[len("data:") :].strip()
if content == "[DONE]":
break # End of stream
else:
@@ -122,14 +120,11 @@ class Session(Base):
except json.JSONDecodeError:
continue # Skip lines that are not valid JSON
event = json_data.get("event",None)
event = json_data.get("event", None)
if event and event != "message":
continue
if (
(self.__session_type == "agent" and event == "message_end")
or (self.__session_type == "chat" and json_data.get("data") is True)
):
if (self.__session_type == "agent" and event == "message_end") or (self.__session_type == "chat" and json_data.get("data") is True):
return
if self.__session_type == "agent":
yield self._structure_answer(json_data)
@@ -141,7 +136,6 @@ class Session(Base):
except ValueError:
raise Exception(f"Invalid response {res}")
yield self._structure_answer(json_data["data"])
def _structure_answer(self, json_data):
answer = ""
@@ -150,10 +144,7 @@ class Session(Base):
elif self.__session_type == "chat":
answer = json_data["answer"]
reference = json_data.get("reference", {})
temp_dict = {
"content": answer,
"role": "assistant"
}
temp_dict = {"content": answer, "role": "assistant"}
if reference and "chunks" in reference:
chunks = reference["chunks"]
temp_dict["reference"] = chunks
@@ -163,8 +154,7 @@ class Session(Base):
def _ask_chat(self, question: str, stream: bool, **kwargs):
json_data = {"question": question, "stream": stream, "session_id": self.id}
json_data.update(kwargs)
res = self.post(f"/chats/{self.chat_id}/completions",
json_data, stream=stream)
res = self.post(f"/chats/{self.chat_id}/completions", json_data, stream=stream)
return res
def _ask_agent(self, question: str, stream: bool, **kwargs):
@@ -180,8 +170,7 @@ class Session(Base):
return res
def update(self, update_message):
res = self.patch(f"/chats/{self.chat_id}/sessions/{self.id}",
update_message)
res = self.patch(f"/chats/{self.chat_id}/sessions/{self.id}", update_message)
res = res.json()
if res.get("code") != 0:
raise Exception(res.get("message"))

45
sdk/python/ragflow_sdk/ragflow.py
View File

@@ -196,7 +196,7 @@ class RAGFlow:
top_k=1024,
rerank_id: str | None = None,
keyword: bool = False,
cross_languages: list[str]|None = None,
cross_languages: list[str] | None = None,
metadata_condition: dict | None = None,
use_kg: bool = False,
toc_enhance: bool = False,
@@ -217,7 +217,7 @@ class RAGFlow:
"cross_languages": cross_languages,
"metadata_condition": metadata_condition,
"use_kg": use_kg,
"toc_enhance": toc_enhance
"toc_enhance": toc_enhance,
}
# Send a POST request to the backend service (using requests library as an example, actual implementation may vary)
res = self.post("/retrieval", json=data_json)
@@ -331,7 +331,7 @@ class RAGFlow:
"memory_type": memory_type,
"storage_type": storage_type,
"keywords": keywords,
}
},
)
res = res.json()
if res.get("code") != 0:
@@ -339,12 +339,7 @@ class RAGFlow:
result_list = []
for data in res["data"]["memory_list"]:
result_list.append(Memory(self, data))
return {
"code": res.get("code", 0),
"message": res.get("message"),
"memory_list": result_list,
"total_count": res["data"]["total_count"]
}
return {"code": res.get("code", 0), "message": res.get("message"), "memory_list": result_list, "total_count": res["data"]["total_count"]}
def delete_memory(self, memory_id: str):
res = self.delete(f"/memories/{memory_id}", {})
@@ -354,21 +349,24 @@ class RAGFlow:
def add_message(self, memory_id: list[str], agent_id: str, session_id: str, user_input: str, agent_response: str, user_id: str = "") -> str:
"""Append messages to memories; ``user_id`` is forwarded only for API-key auth (external subject)."""
payload = {
"memory_id": memory_id,
"agent_id": agent_id,
"session_id": session_id,
"user_input": user_input,
"agent_response": agent_response,
"user_id": user_id
}
payload = {"memory_id": memory_id, "agent_id": agent_id, "session_id": session_id, "user_input": user_input, "agent_response": agent_response, "user_id": user_id}
res = self.post("/messages", payload)
res = res.json()
if res.get("code") != 0:
raise Exception(res["message"])
return res["message"]
def search_message(self, query: str, memory_id: list[str], agent_id: str=None, session_id: str=None, user_id: str=None, similarity_threshold: float=0.2, keywords_similarity_weight: float=0.7, top_n: int=10) -> list[dict]:
def search_message(
self,
query: str,
memory_id: list[str],
agent_id: str = None,
session_id: str = None,
user_id: str = None,
similarity_threshold: float = 0.2,
keywords_similarity_weight: float = 0.7,
top_n: int = 10,
) -> list[dict]:
params = {
"query": query,
"memory_id": memory_id,
@@ -377,7 +375,7 @@ class RAGFlow:
"user_id": user_id,
"similarity_threshold": similarity_threshold,
"keywords_similarity_weight": keywords_similarity_weight,
"top_n": top_n
"top_n": top_n,
}
res = self.get("/messages/search", params)
res = res.json()
@@ -385,13 +383,8 @@ class RAGFlow:
raise Exception(res["message"])
return res["data"]
def get_recent_messages(self, memory_id: list[str], agent_id: str=None, session_id: str=None, limit: int=10) -> list[dict]:
params = {
"memory_id": memory_id,
"agent_id": agent_id,
"session_id": session_id,
"limit": limit
}
def get_recent_messages(self, memory_id: list[str], agent_id: str = None, session_id: str = None, limit: int = 10) -> list[dict]:
params = {"memory_id": memory_id, "agent_id": agent_id, "session_id": session_id, "limit": limit}
res = self.get("/messages", params)
res = res.json()
if res.get("code") != 0:

6
sdk/python/test.py
View File

@@ -2,7 +2,7 @@ from .ragflow_sdk import RAGFlow
rag_object = RAGFlow(api_key="ragflow-FDfRECsXDRagsKPxb_EfZdDPcmngavSgYEzbU_Blgq4", base_url="http://localhost:9222")
assistant = rag_object.get_agent("b0bc46e43dfc11f1b4ff84ba59bc54d9")
session = assistant.create_session()
session = assistant.create_session()
print("\n==================== Miss R =====================\n")
print("Hello. What can I do for you?")
@@ -10,8 +10,8 @@ print("Hello. What can I do for you?")
while True:
question = input("\n==================== User =====================\n> ")
print("\n==================== Miss R =====================\n")
cont = ""
for ans in session.ask(question, stream=True):
print(ans.content[len(cont):], end='', flush=True)
print(ans.content[len(cont) :], end="", flush=True)
cont = ans.content

37
sdk/python/test/conftest.py
View File

@@ -113,12 +113,7 @@ def add_model_instance(auth):
pytest.exit(f"Critical error in add model provider: {add_provider_res.get('message')}")
add_instance_api = HOST_ADDRESS + "/api/v1/providers/ZHIPU-AI/instances"
add_instance_response = requests.post(url=add_instance_api, headers=authorization, json={
"instance_name": "CI",
"api_key": ZHIPU_AI_API_KEY,
"region": "default",
"base_url": ""
})
add_instance_response = requests.post(url=add_instance_api, headers=authorization, json={"instance_name": "CI", "api_key": ZHIPU_AI_API_KEY, "region": "default", "base_url": ""})
add_instance_res = add_instance_response.json()
if add_instance_res.get("code") != 0:
pytest.exit(f"Critical error in add model instance: {add_instance_res.get('message')}")
@@ -139,41 +134,19 @@ def set_tenant_info(get_auth):
url = HOST_ADDRESS + "/api/v1/models/default"
authorization = {"Authorization": get_auth}
# set chat model
set_default_llm_response = requests.patch(
url=url,
headers=authorization,
json={
"model_provider": "ZHIPU-AI",
"model_instance": "CI",
"model_type": "chat",
"model_name": "glm-4-flash"
})
set_default_llm_response = requests.patch(url=url, headers=authorization, json={"model_provider": "ZHIPU-AI", "model_instance": "CI", "model_type": "chat", "model_name": "glm-4-flash"})
llm_res = set_default_llm_response.json()
if llm_res.get("code") != 0:
raise Exception(llm_res.get("message"))
# set embedding model
set_default_embedding_response = requests.patch(
url=url,
headers=authorization,
json={
"model_provider": "Builtin",
"model_instance": "Local",
"model_type": "embedding",
"model_name": "BAAI/bge-small-en-v1.5"
})
url=url, headers=authorization, json={"model_provider": "Builtin", "model_instance": "Local", "model_type": "embedding", "model_name": "BAAI/bge-small-en-v1.5"}
)
embd_res = set_default_embedding_response.json()
if embd_res.get("code") != 0:
raise Exception(embd_res.get("message"))
# set image to text model
set_default_img2txt_response = requests.patch(
url=url,
headers=authorization,
json={
"model_provider": "ZHIPU-AI",
"model_instance": "CI",
"model_type": "vision",
"model_name": "glm-4v"
})
set_default_img2txt_response = requests.patch(url=url, headers=authorization, json={"model_provider": "ZHIPU-AI", "model_instance": "CI", "model_type": "vision", "model_name": "glm-4v"})
img2txt_res = set_default_img2txt_response.json()
if img2txt_res.get("code") != 0:
raise Exception(img2txt_res.get("message"))

9
sdk/python/test/test_frontend_api/common.py
View File

@@ -73,20 +73,20 @@ def list_document(auth, dataset_id):
def get_docs_info(auth, dataset_id, doc_ids=None, doc_id=None):
"""
Get document information by IDs.
Args:
auth: Authorization header
dataset_id: Dataset ID
doc_ids: List of document IDs (use for multiple) - exclusive with doc_id
doc_id: Single document ID (use for one) - exclusive with doc_ids
Raises:
ValueError: If both doc_id and doc_ids are provided
"""
# Validate that id and ids are not used together
if doc_id and doc_ids:
raise ValueError("Cannot use both 'id' and 'ids' parameters at the same time.")
authorization = {"Authorization": auth}
params = {}
if doc_ids:
@@ -96,7 +96,7 @@ def get_docs_info(auth, dataset_id, doc_ids=None, doc_id=None):
elif doc_id:
# Single ID
params["id"] = doc_id
# Use /api/v1 prefix for dataset API
url = f"{HOST_ADDRESS}/api/v1/datasets/{dataset_id}/documents"
res = requests.get(url=url, headers=authorization, params=params)
@@ -113,4 +113,3 @@ def parse_docs(auth, doc_ids):
def parse_file(auth, document_id):
pass

5
sdk/python/test/test_frontend_api/get_email.py
View File

@@ -14,6 +14,7 @@
# limitations under the License.
#
def test_get_email(get_email):
print("\nEmail account:",flush=True)
print(f"{get_email}\n",flush=True)
print("\nEmail account:", flush=True)
print(f"{get_email}\n", flush=True)

12
sdk/python/test/test_frontend_api/test_chunk.py
View File

@@ -40,15 +40,15 @@ def test_parse_txt_document(get_auth):
break
page_number += 1
filename = 'ragflow_test.txt'
filename = "ragflow_test.txt"
res = upload_file(get_auth, dataset_id, f"../test_sdk_api/test_data/{filename}")
assert res.get("code") == 0, f"{res.get('message')}"
res = list_document(get_auth, dataset_id)
doc_id_list = []
for doc in res['data']['docs']:
doc_id_list.append(doc['id'])
for doc in res["data"]["docs"]:
doc_id_list.append(doc["id"])
res = get_docs_info(get_auth, dataset_id, doc_ids=doc_id_list)
print(doc_id_list)
@@ -59,13 +59,13 @@ def test_parse_txt_document(get_auth):
while True:
res = get_docs_info(get_auth, dataset_id, doc_ids=doc_id_list)
finished_count = 0
for doc_info in res['data']:
if doc_info['progress'] == 1:
for doc_info in res["data"]:
if doc_info["progress"] == 1:
finished_count += 1
if finished_count == doc_count:
break
sleep(1)
print('time cost {:.1f}s'.format(timer() - start_ts))
print("time cost {:.1f}s".format(timer() - start_ts))
# delete dataset
if dataset_list:

26
sdk/python/test/test_frontend_api/test_dataset.py
View File

@@ -89,7 +89,7 @@ def test_duplicated_name_dataset(get_auth):
if isinstance(data, dict):
data = data.get("kbs", [])
dataset_list = []
pattern = r'^test_create_dataset.*'
pattern = r"^test_create_dataset.*"
for item in data:
dataset_name = item.get("name")
dataset_id = item.get("id")
@@ -106,10 +106,10 @@ def test_duplicated_name_dataset(get_auth):
def test_invalid_name_dataset(get_auth):
# create dataset
res = create_dataset(get_auth, {"name": 0})
assert res['code'] != 0
assert res["code"] != 0
res = create_dataset(get_auth, {"name": ""})
assert res['code'] != 0
assert res["code"] != 0
long_string = ""
@@ -117,7 +117,7 @@ def test_invalid_name_dataset(get_auth):
long_string += random.choice(string.ascii_letters + string.digits)
res = create_dataset(get_auth, {"name": long_string})
assert res['code'] != 0
assert res["code"] != 0
print(res)
@@ -144,13 +144,17 @@ def test_update_different_params_dataset_success(get_auth):
print(f"found {len(dataset_list)} datasets")
dataset_id = dataset_list[0]
res = update_dataset(get_auth, dataset_id, {
"name": "test_update_dataset",
"description": "test",
"permission": "me",
"chunk_method": "presentation",
"language": "spanish",
})
res = update_dataset(
get_auth,
dataset_id,
{
"name": "test_update_dataset",
"description": "test",
"permission": "me",
"chunk_method": "presentation",
"language": "spanish",
},
)
assert res.get("code") == 0, f"{res.get('message')}"
# delete dataset