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

Introduced beartype (#3460)

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

Introduced [beartype](https://github.com/beartype/beartype) for runtime
type-checking.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Zhichang Yu
2024-11-18 17:38:17 +08:00
committed by GitHub
parent 3824c1fec0
commit 4413683898
32 changed files with 125 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
sdk/python/poetry.lock generated
View File

@ -1,5 +1,23 @@
# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
[[package]]
name = "beartype"
version = "0.18.5"
description = "Unbearably fast runtime type checking in pure Python."
optional = false
python-versions = ">=3.8.0"
files = [
{file = "beartype-0.18.5-py3-none-any.whl", hash = "sha256:5301a14f2a9a5540fe47ec6d34d758e9cd8331d36c4760fc7a5499ab86310089"},
{file = "beartype-0.18.5.tar.gz", hash = "sha256:264ddc2f1da9ec94ff639141fbe33d22e12a9f75aa863b83b7046ffff1381927"},
]
[package.extras]
all = ["typing-extensions (>=3.10.0.0)"]
dev = ["autoapi (>=0.9.0)", "coverage (>=5.5)", "equinox", "mypy (>=0.800)", "numpy", "pandera", "pydata-sphinx-theme (<=0.7.2)", "pytest (>=4.0.0)", "sphinx", "sphinx (>=4.2.0,<6.0.0)", "sphinxext-opengraph (>=0.7.5)", "tox (>=3.20.1)", "typing-extensions (>=3.10.0.0)"]
doc-rtd = ["autoapi (>=0.9.0)", "pydata-sphinx-theme (<=0.7.2)", "sphinx (>=4.2.0,<6.0.0)", "sphinxext-opengraph (>=0.7.5)"]
test-tox = ["equinox", "mypy (>=0.800)", "numpy", "pandera", "pytest (>=4.0.0)", "sphinx", "typing-extensions (>=3.10.0.0)"]
test-tox-coverage = ["coverage (>=5.5)"]
[[package]]
name = "certifi"
version = "2024.8.30"
@ -177,13 +195,13 @@ files = [
[[package]]
name = "packaging"
version = "24.1"
version = "24.2"
description = "Core utilities for Python packages"
optional = false
python-versions = ">=3.8"
files = [
{file = "packaging-24.1-py3-none-any.whl", hash = "sha256:5b8f2217dbdbd2f7f384c41c628544e6d52f2d0f53c6d0c3ea61aa5d1d7ff124"},
{file = "packaging-24.1.tar.gz", hash = "sha256:026ed72c8ed3fcce5bf8950572258698927fd1dbda10a5e981cdf0ac37f4f002"},
{file = "packaging-24.2-py3-none-any.whl", hash = "sha256:09abb1bccd265c01f4a3aa3f7a7db064b36514d2cba19a2f694fe6150451a759"},
{file = "packaging-24.2.tar.gz", hash = "sha256:c228a6dc5e932d346bc5739379109d49e8853dd8223571c7c5b55260edc0b97f"},
]
[[package]]
@ -246,13 +264,13 @@ use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
[[package]]
name = "tomli"
version = "2.0.2"
version = "2.1.0"
description = "A lil' TOML parser"
optional = false
python-versions = ">=3.8"
files = [
{file = "tomli-2.0.2-py3-none-any.whl", hash = "sha256:2ebe24485c53d303f690b0ec092806a085f07af5a5aa1464f3931eec36caaa38"},
{file = "tomli-2.0.2.tar.gz", hash = "sha256:d46d457a85337051c36524bc5349dd91b1877838e2979ac5ced3e710ed8a60ed"},
{file = "tomli-2.1.0-py3-none-any.whl", hash = "sha256:a5c57c3d1c56f5ccdf89f6523458f60ef716e210fc47c4cfb188c5ba473e0391"},
{file = "tomli-2.1.0.tar.gz", hash = "sha256:3f646cae2aec94e17d04973e4249548320197cfabdf130015d023de4b74d8ab8"},
]
[[package]]
@ -275,4 +293,4 @@ zstd = ["zstandard (>=0.18.0)"]
[metadata]
lock-version = "2.0"
python-versions = "^3.10"
content-hash = "202bfd3e121f1d57a2f9c9d91cd7a50eacf2362cd1995c9f6347bcb100cf9336"
content-hash = "19565d31d822b0573f505662c664d735194134a505f43bbd1657c033f87bb82d"

1
sdk/python/pyproject.toml
View File

@ -10,6 +10,7 @@ package-mode = true
[tool.poetry.dependencies]
python = "^3.10"
requests = "^2.30.0"
beartype = "^0.18.5"
pytest = "^8.0.0"

3
sdk/python/ragflow_sdk/__init__.py
View File

@ -1,3 +1,6 @@
from beartype.claw import beartype_this_package
beartype_this_package() # <-- raise exceptions in your code
import importlib.metadata
__version__ = importlib.metadata.version("ragflow_sdk")

5
sdk/python/ragflow_sdk/modules/chat.py
View File

@ -1,4 +1,3 @@
from typing import List
from .base import Base
from .session import Session
@ -58,7 +57,7 @@ class Chat(Base):
raise Exception(res["message"])
def list_sessions(self,page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True,
id: str = None, name: str = None) -> List[Session]:
id: str = None, name: str = None) -> list[Session]:
res = self.get(f'/chats/{self.id}/sessions',{"page": page, "page_size": page_size, "orderby": orderby, "desc": desc, "id": id, "name": name} )
res = res.json()
if res.get("code") == 0:
@ -68,7 +67,7 @@ class Chat(Base):
return result_list
raise Exception(res["message"])
def delete_sessions(self,ids:List[str]=None):
def delete_sessions(self,ids: list[str] | None = None):
res = self.rm(f"/chats/{self.id}/sessions", {"ids": ids})
res = res.json()
if res.get("code") != 0:

8
sdk/python/ragflow_sdk/modules/dataset.py
View File

@ -1,5 +1,3 @@
from typing import List
from .document import Document
from .base import Base
@ -35,7 +33,7 @@ class DataSet(Base):
if res.get("code") != 0:
raise Exception(res["message"])
def upload_documents(self,document_list: List[dict]):
def upload_documents(self,document_list: list[dict]):
url = f"/datasets/{self.id}/documents"
files = [("file",(ele["displayed_name"],ele["blob"])) for ele in document_list]
res = self.post(path=url,json=None,files=files)
@ -48,7 +46,7 @@ class DataSet(Base):
return doc_list
raise Exception(res.get("message"))
def list_documents(self, id: str = None, keywords: str = None, page: int =1, page_size: int = 30, orderby: str = "create_time", desc: bool = True):
def list_documents(self, id: str | None = None, keywords: str | None = None, page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True):
res = self.get(f"/datasets/{self.id}/documents",params={"id": id,"keywords": keywords,"page": page,"page_size": page_size,"orderby": orderby,"desc": desc})
res = res.json()
documents = []
@ -58,7 +56,7 @@ class DataSet(Base):
return documents
raise Exception(res["message"])
def delete_documents(self,ids: List[str] = None):
def delete_documents(self,ids: list[str] | None = None):
res = self.rm(f"/datasets/{self.id}/documents",{"ids":ids})
res = res.json()
if res.get("code") != 0:

5
sdk/python/ragflow_sdk/modules/document.py
View File

@ -1,7 +1,6 @@
import json
from .base import Base
from .chunk import Chunk
from typing import List
class Document(Base):
@ -63,14 +62,14 @@ class Document(Base):
raise Exception(res.get("message"))
def add_chunk(self, content: str,important_keywords:List[str]=[]):
def add_chunk(self, content: str,important_keywords: list[str] = []):
res = self.post(f'/datasets/{self.dataset_id}/documents/{self.id}/chunks', {"content":content,"important_keywords":important_keywords})
res = res.json()
if res.get("code") == 0:
return Chunk(self.rag,res["data"].get("chunk"))
raise Exception(res.get("message"))
def delete_chunks(self,ids:List[str] = None):
def delete_chunks(self,ids:list[str] | None = None):
res = self.rm(f"/datasets/{self.dataset_id}/documents/{self.id}/chunks",{"chunk_ids":ids})
res = res.json()
if res.get("code")!=0:

21
sdk/python/ragflow_sdk/ragflow.py
View File

@ -13,14 +13,11 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import List
import requests
from .modules.chat import Chat
from .modules.chunk import Chunk
from .modules.dataset import DataSet
from .modules.document import Document
class RAGFlow:
@ -64,7 +61,7 @@ class RAGFlow:
return DataSet(self, res["data"])
raise Exception(res["message"])
def delete_datasets(self, ids: List[str] = None):
def delete_datasets(self, ids: list[str] | None = None):
res = self.delete("/datasets",{"ids": ids})
res=res.json()
if res.get("code") != 0:
@ -77,8 +74,8 @@ class RAGFlow:
raise Exception("Dataset %s not found" % name)
def list_datasets(self, page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True,
id: str = None, name: str = None) -> \
List[DataSet]:
id: str | None = None, name: str | None = None) -> \
list[DataSet]:
res = self.get("/datasets",
{"page": page, "page_size": page_size, "orderby": orderby, "desc": desc, "id": id, "name": name})
res = res.json()
@ -89,8 +86,8 @@ class RAGFlow:
return result_list
raise Exception(res["message"])
def create_chat(self, name: str, avatar: str = "", dataset_ids: List[str] = [],
llm: Chat.LLM = None, prompt: Chat.Prompt = None) -> Chat:
def create_chat(self, name: str, avatar: str = "", dataset_ids: list[str] = [],
llm: Chat.LLM | None = None, prompt: Chat.Prompt | None = None) -> Chat:
dataset_list = []
for id in dataset_ids:
dataset_list.append(id)
@ -135,7 +132,7 @@ class RAGFlow:
return Chat(self, res["data"])
raise Exception(res["message"])
def delete_chats(self,ids: List[str] = None) -> bool:
def delete_chats(self,ids: list[str] | None = None):
res = self.delete('/chats',
{"ids":ids})
res = res.json()
@ -143,7 +140,7 @@ class RAGFlow:
raise Exception(res["message"])
def list_chats(self, page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True,
id: str = None, name: str = None) -> List[Chat]:
id: str | None = None, name: str | None = None) -> list[Chat]:
res = self.get("/chats",{"page": page, "page_size": page_size, "orderby": orderby, "desc": desc, "id": id, "name": name})
res = res.json()
result_list = []
@ -154,7 +151,7 @@ class RAGFlow:
raise Exception(res["message"])
def retrieve(self, dataset_ids, document_ids=None, question="", page=1, page_size=30, similarity_threshold=0.2, vector_similarity_weight=0.3, top_k=1024, rerank_id:str=None, keyword:bool=False, ):
def retrieve(self, dataset_ids, document_ids=None, question="", page=1, page_size=30, similarity_threshold=0.2, vector_similarity_weight=0.3, top_k=1024, rerank_id: str | None = None, keyword:bool=False, ):
if document_ids is None:
document_ids = []
data_json ={
@ -170,7 +167,7 @@ class RAGFlow:
"documents": document_ids
}
# Send a POST request to the backend service (using requests library as an example, actual implementation may vary)
res = self.post(f'/retrieval',json=data_json)
res = self.post('/retrieval',json=data_json)
res = res.json()
if res.get("code") ==0:
chunks=[]