Merge pull request #5861 from open-webui/projects

feat: knowledge/projects
This commit is contained in:
Timothy Jaeryang Baek
2024-10-04 10:00:47 +02:00
committed by GitHub
48 changed files with 2875 additions and 557 deletions

View File

@@ -10,11 +10,11 @@ from open_webui.apps.webui.routers import (
auths,
chats,
configs,
documents,
files,
functions,
memories,
models,
knowledge,
prompts,
tools,
users,
@@ -111,15 +111,15 @@ app.include_router(auths.router, prefix="/auths", tags=["auths"])
app.include_router(users.router, prefix="/users", tags=["users"])
app.include_router(chats.router, prefix="/chats", tags=["chats"])
app.include_router(documents.router, prefix="/documents", tags=["documents"])
app.include_router(models.router, prefix="/models", tags=["models"])
app.include_router(knowledge.router, prefix="/knowledge", tags=["knowledge"])
app.include_router(prompts.router, prefix="/prompts", tags=["prompts"])
app.include_router(memories.router, prefix="/memories", tags=["memories"])
app.include_router(files.router, prefix="/files", tags=["files"])
app.include_router(tools.router, prefix="/tools", tags=["tools"])
app.include_router(functions.router, prefix="/functions", tags=["functions"])
app.include_router(memories.router, prefix="/memories", tags=["memories"])
app.include_router(utils.router, prefix="/utils", tags=["utils"])

View File

@@ -5,7 +5,7 @@ from typing import Optional
from open_webui.apps.webui.internal.db import Base, JSONField, get_db
from open_webui.env import SRC_LOG_LEVELS
from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Column, String, Text
from sqlalchemy import BigInteger, Column, String, Text, JSON
log = logging.getLogger(__name__)
log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -20,19 +20,29 @@ class File(Base):
id = Column(String, primary_key=True)
user_id = Column(String)
hash = Column(Text, nullable=True)
filename = Column(Text)
data = Column(JSON, nullable=True)
meta = Column(JSONField)
created_at = Column(BigInteger)
updated_at = Column(BigInteger)
class FileModel(BaseModel):
model_config = ConfigDict(from_attributes=True)
id: str
user_id: str
filename: str
meta: dict
created_at: int # timestamp in epoch
hash: Optional[str] = None
model_config = ConfigDict(from_attributes=True)
filename: str
data: Optional[dict] = None
meta: dict
created_at: int # timestamp in epoch
updated_at: int # timestamp in epoch
####################
@@ -43,14 +53,21 @@ class FileModel(BaseModel):
class FileModelResponse(BaseModel):
id: str
user_id: str
hash: Optional[str] = None
filename: str
data: Optional[dict] = None
meta: dict
created_at: int # timestamp in epoch
updated_at: int # timestamp in epoch
class FileForm(BaseModel):
id: str
hash: Optional[str] = None
filename: str
data: dict = {}
meta: dict = {}
@@ -62,6 +79,7 @@ class FilesTable:
**form_data.model_dump(),
"user_id": user_id,
"created_at": int(time.time()),
"updated_at": int(time.time()),
}
)
@@ -90,6 +108,13 @@ class FilesTable:
with get_db() as db:
return [FileModel.model_validate(file) for file in db.query(File).all()]
def get_files_by_ids(self, ids: list[str]) -> list[FileModel]:
with get_db() as db:
return [
FileModel.model_validate(file)
for file in db.query(File).filter(File.id.in_(ids)).all()
]
def get_files_by_user_id(self, user_id: str) -> list[FileModel]:
with get_db() as db:
return [
@@ -97,17 +122,38 @@ class FilesTable:
for file in db.query(File).filter_by(user_id=user_id).all()
]
def update_files_metadata_by_id(self, id: str, meta: dict) -> Optional[FileModel]:
def update_file_hash_by_id(self, id: str, hash: str) -> Optional[FileModel]:
with get_db() as db:
try:
file = db.query(File).filter_by(id=id).first()
file.meta = {**file.meta, **meta}
file.hash = hash
db.commit()
return FileModel.model_validate(file)
except Exception:
return None
def update_file_data_by_id(self, id: str, data: dict) -> Optional[FileModel]:
with get_db() as db:
try:
file = db.query(File).filter_by(id=id).first()
file.data = {**(file.data if file.data else {}), **data}
db.commit()
return FileModel.model_validate(file)
except Exception as e:
return None
def update_file_metadata_by_id(self, id: str, meta: dict) -> Optional[FileModel]:
with get_db() as db:
try:
file = db.query(File).filter_by(id=id).first()
file.meta = {**(file.meta if file.meta else {}), **meta}
db.commit()
return FileModel.model_validate(file)
except Exception:
return None
def delete_file_by_id(self, id: str) -> bool:
with get_db() as db:
try:

View File

@@ -0,0 +1,152 @@
import json
import logging
import time
from typing import Optional
import uuid
from open_webui.apps.webui.internal.db import Base, get_db
from open_webui.env import SRC_LOG_LEVELS
from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Column, String, Text, JSON
log = logging.getLogger(__name__)
log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
# Knowledge DB Schema
####################
class Knowledge(Base):
__tablename__ = "knowledge"
id = Column(Text, unique=True, primary_key=True)
user_id = Column(Text)
name = Column(Text)
description = Column(Text)
data = Column(JSON, nullable=True)
meta = Column(JSON, nullable=True)
created_at = Column(BigInteger)
updated_at = Column(BigInteger)
class KnowledgeModel(BaseModel):
model_config = ConfigDict(from_attributes=True)
id: str
user_id: str
name: str
description: str
data: Optional[dict] = None
meta: Optional[dict] = None
created_at: int # timestamp in epoch
updated_at: int # timestamp in epoch
####################
# Forms
####################
class KnowledgeResponse(BaseModel):
id: str
name: str
description: str
data: Optional[dict] = None
meta: Optional[dict] = None
created_at: int # timestamp in epoch
updated_at: int # timestamp in epoch
class KnowledgeForm(BaseModel):
name: str
description: str
data: Optional[dict] = None
class KnowledgeUpdateForm(BaseModel):
name: Optional[str] = None
description: Optional[str] = None
data: Optional[dict] = None
class KnowledgeTable:
def insert_new_knowledge(
self, user_id: str, form_data: KnowledgeForm
) -> Optional[KnowledgeModel]:
with get_db() as db:
knowledge = KnowledgeModel(
**{
**form_data.model_dump(),
"id": str(uuid.uuid4()),
"user_id": user_id,
"created_at": int(time.time()),
"updated_at": int(time.time()),
}
)
try:
result = Knowledge(**knowledge.model_dump())
db.add(result)
db.commit()
db.refresh(result)
if result:
return KnowledgeModel.model_validate(result)
else:
return None
except Exception:
return None
def get_knowledge_items(self) -> list[KnowledgeModel]:
with get_db() as db:
return [
KnowledgeModel.model_validate(knowledge)
for knowledge in db.query(Knowledge)
.order_by(Knowledge.updated_at.desc())
.all()
]
def get_knowledge_by_id(self, id: str) -> Optional[KnowledgeModel]:
try:
with get_db() as db:
knowledge = db.query(Knowledge).filter_by(id=id).first()
return KnowledgeModel.model_validate(knowledge) if knowledge else None
except Exception:
return None
def update_knowledge_by_id(
self, id: str, form_data: KnowledgeUpdateForm, overwrite: bool = False
) -> Optional[KnowledgeModel]:
try:
with get_db() as db:
knowledge = self.get_knowledge_by_id(id=id)
db.query(Knowledge).filter_by(id=id).update(
{
**form_data.model_dump(exclude_none=True),
"updated_at": int(time.time()),
}
)
db.commit()
return self.get_knowledge_by_id(id=id)
except Exception as e:
log.exception(e)
return None
def delete_knowledge_by_id(self, id: str) -> bool:
try:
with get_db() as db:
db.query(Knowledge).filter_by(id=id).delete()
db.commit()
return True
except Exception:
return False
Knowledges = KnowledgeTable()

View File

@@ -4,13 +4,18 @@ import shutil
import uuid
from pathlib import Path
from typing import Optional
from pydantic import BaseModel
from open_webui.apps.webui.models.files import FileForm, FileModel, Files
from open_webui.apps.retrieval.main import process_file, ProcessFileForm
from open_webui.config import UPLOAD_DIR
from open_webui.constants import ERROR_MESSAGES
from open_webui.env import SRC_LOG_LEVELS
from fastapi import APIRouter, Depends, File, HTTPException, UploadFile, status
from fastapi.responses import FileResponse
from fastapi.responses import FileResponse, StreamingResponse
from open_webui.utils.utils import get_admin_user, get_verified_user
log = logging.getLogger(__name__)
@@ -58,6 +63,13 @@ def upload_file(file: UploadFile = File(...), user=Depends(get_verified_user)):
),
)
try:
process_file(ProcessFileForm(file_id=id))
file = Files.get_file_by_id(id=id)
except Exception as e:
log.exception(e)
log.error(f"Error processing file: {file.id}")
if file:
return file
else:
@@ -143,6 +155,55 @@ async def get_file_by_id(id: str, user=Depends(get_verified_user)):
)
############################
# Get File Data Content By Id
############################
@router.get("/{id}/data/content")
async def get_file_data_content_by_id(id: str, user=Depends(get_verified_user)):
file = Files.get_file_by_id(id)
if file and (file.user_id == user.id or user.role == "admin"):
return {"content": file.data.get("content", "")}
else:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail=ERROR_MESSAGES.NOT_FOUND,
)
############################
# Update File Data Content By Id
############################
class ContentForm(BaseModel):
content: str
@router.post("/{id}/data/content/update")
async def update_file_data_content_by_id(
id: str, form_data: ContentForm, user=Depends(get_verified_user)
):
file = Files.get_file_by_id(id)
if file and (file.user_id == user.id or user.role == "admin"):
try:
process_file(ProcessFileForm(file_id=id, content=form_data.content))
file = Files.get_file_by_id(id=id)
except Exception as e:
log.exception(e)
log.error(f"Error processing file: {file.id}")
return {"content": file.data.get("content", "")}
else:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail=ERROR_MESSAGES.NOT_FOUND,
)
############################
# Get File Content By Id
############################
@@ -171,34 +232,37 @@ async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
)
@router.get("/{id}/content/text")
async def get_file_text_content_by_id(id: str, user=Depends(get_verified_user)):
file = Files.get_file_by_id(id)
if file and (file.user_id == user.id or user.role == "admin"):
return {"text": file.meta.get("content", {}).get("text", None)}
else:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail=ERROR_MESSAGES.NOT_FOUND,
)
@router.get("/{id}/content/{file_name}", response_model=Optional[FileModel])
async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
file = Files.get_file_by_id(id)
if file and (file.user_id == user.id or user.role == "admin"):
file_path = Path(file.meta["path"])
file_path = file.meta.get("path")
if file_path:
file_path = Path(file_path)
# Check if the file already exists in the cache
if file_path.is_file():
print(f"file_path: {file_path}")
return FileResponse(file_path)
# Check if the file already exists in the cache
if file_path.is_file():
print(f"file_path: {file_path}")
return FileResponse(file_path)
else:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail=ERROR_MESSAGES.NOT_FOUND,
)
else:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail=ERROR_MESSAGES.NOT_FOUND,
# File path doesnt exist, return the content as .txt if possible
file_content = file.content.get("content", "")
file_name = file.filename
# Create a generator that encodes the file content
def generator():
yield file_content.encode("utf-8")
return StreamingResponse(
generator(),
media_type="text/plain",
headers={"Content-Disposition": f"attachment; filename={file_name}"},
)
else:
raise HTTPException(

View File

@@ -0,0 +1,320 @@
import json
from typing import Optional, Union
from pydantic import BaseModel
from fastapi import APIRouter, Depends, HTTPException, status
from open_webui.apps.webui.models.knowledge import (
Knowledges,
KnowledgeUpdateForm,
KnowledgeForm,
KnowledgeResponse,
)
from open_webui.apps.webui.models.files import Files, FileModel
from open_webui.apps.retrieval.vector.connector import VECTOR_DB_CLIENT
from open_webui.apps.retrieval.main import process_file, ProcessFileForm
from open_webui.constants import ERROR_MESSAGES
from open_webui.utils.utils import get_admin_user, get_verified_user
router = APIRouter()
############################
# GetKnowledgeItems
############################
@router.get(
"/", response_model=Optional[Union[list[KnowledgeResponse], KnowledgeResponse]]
)
async def get_knowledge_items(
id: Optional[str] = None, user=Depends(get_verified_user)
):
if id:
knowledge = Knowledges.get_knowledge_by_id(id=id)
if knowledge:
return knowledge
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.NOT_FOUND,
)
else:
return [
KnowledgeResponse(**knowledge.model_dump())
for knowledge in Knowledges.get_knowledge_items()
]
############################
# CreateNewKnowledge
############################
@router.post("/create", response_model=Optional[KnowledgeResponse])
async def create_new_knowledge(form_data: KnowledgeForm, user=Depends(get_admin_user)):
knowledge = Knowledges.insert_new_knowledge(user.id, form_data)
if knowledge:
return knowledge
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.FILE_EXISTS,
)
############################
# GetKnowledgeById
############################
class KnowledgeFilesResponse(KnowledgeResponse):
files: list[FileModel]
@router.get("/{id}", response_model=Optional[KnowledgeFilesResponse])
async def get_knowledge_by_id(id: str, user=Depends(get_verified_user)):
knowledge = Knowledges.get_knowledge_by_id(id=id)
if knowledge:
file_ids = knowledge.data.get("file_ids", []) if knowledge.data else []
files = Files.get_files_by_ids(file_ids)
return KnowledgeFilesResponse(
**knowledge.model_dump(),
files=files,
)
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail=ERROR_MESSAGES.NOT_FOUND,
)
############################
# UpdateKnowledgeById
############################
@router.post("/{id}/update", response_model=Optional[KnowledgeFilesResponse])
async def update_knowledge_by_id(
id: str,
form_data: KnowledgeUpdateForm,
user=Depends(get_admin_user),
):
knowledge = Knowledges.update_knowledge_by_id(id=id, form_data=form_data)
if knowledge:
file_ids = knowledge.data.get("file_ids", []) if knowledge.data else []
files = Files.get_files_by_ids(file_ids)
return KnowledgeFilesResponse(
**knowledge.model_dump(),
files=files,
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.ID_TAKEN,
)
############################
# AddFileToKnowledge
############################
class KnowledgeFileIdForm(BaseModel):
file_id: str
@router.post("/{id}/file/add", response_model=Optional[KnowledgeFilesResponse])
def add_file_to_knowledge_by_id(
id: str,
form_data: KnowledgeFileIdForm,
user=Depends(get_admin_user),
):
knowledge = Knowledges.get_knowledge_by_id(id=id)
file = Files.get_file_by_id(form_data.file_id)
if not file:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.NOT_FOUND,
)
if not file.data:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.FILE_NOT_PROCESSED,
)
# Add content to the vector database
try:
process_file(ProcessFileForm(file_id=form_data.file_id, collection_name=id))
except Exception as e:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=str(e),
)
if knowledge:
data = knowledge.data or {}
file_ids = data.get("file_ids", [])
if form_data.file_id not in file_ids:
file_ids.append(form_data.file_id)
data["file_ids"] = file_ids
knowledge = Knowledges.update_knowledge_by_id(
id=id, form_data=KnowledgeUpdateForm(data=data)
)
if knowledge:
files = Files.get_files_by_ids(file_ids)
return KnowledgeFilesResponse(
**knowledge.model_dump(),
files=files,
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.DEFAULT("knowledge"),
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.DEFAULT("file_id"),
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.NOT_FOUND,
)
@router.post("/{id}/file/update", response_model=Optional[KnowledgeFilesResponse])
def update_file_from_knowledge_by_id(
id: str,
form_data: KnowledgeFileIdForm,
user=Depends(get_admin_user),
):
knowledge = Knowledges.get_knowledge_by_id(id=id)
file = Files.get_file_by_id(form_data.file_id)
if not file:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.NOT_FOUND,
)
# Remove content from the vector database
VECTOR_DB_CLIENT.delete(
collection_name=knowledge.id, filter={"file_id": form_data.file_id}
)
# Add content to the vector database
try:
process_file(ProcessFileForm(file_id=form_data.file_id, collection_name=id))
except Exception as e:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=str(e),
)
if knowledge:
data = knowledge.data or {}
file_ids = data.get("file_ids", [])
files = Files.get_files_by_ids(file_ids)
return KnowledgeFilesResponse(
**knowledge.model_dump(),
files=files,
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.NOT_FOUND,
)
############################
# RemoveFileFromKnowledge
############################
@router.post("/{id}/file/remove", response_model=Optional[KnowledgeFilesResponse])
def remove_file_from_knowledge_by_id(
id: str,
form_data: KnowledgeFileIdForm,
user=Depends(get_admin_user),
):
knowledge = Knowledges.get_knowledge_by_id(id=id)
file = Files.get_file_by_id(form_data.file_id)
if not file:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.NOT_FOUND,
)
# Remove content from the vector database
VECTOR_DB_CLIENT.delete(
collection_name=knowledge.id, filter={"file_id": form_data.file_id}
)
result = VECTOR_DB_CLIENT.query(
collection_name=knowledge.id,
filter={"file_id": form_data.file_id},
)
Files.delete_file_by_id(form_data.file_id)
if knowledge:
data = knowledge.data or {}
file_ids = data.get("file_ids", [])
if form_data.file_id in file_ids:
file_ids.remove(form_data.file_id)
data["file_ids"] = file_ids
knowledge = Knowledges.update_knowledge_by_id(
id=id, form_data=KnowledgeUpdateForm(data=data)
)
if knowledge:
files = Files.get_files_by_ids(file_ids)
return KnowledgeFilesResponse(
**knowledge.model_dump(),
files=files,
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.DEFAULT("knowledge"),
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.DEFAULT("file_id"),
)
else:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.NOT_FOUND,
)
############################
# DeleteKnowledgeById
############################
@router.delete("/{id}/delete", response_model=bool)
async def delete_knowledge_by_id(id: str, user=Depends(get_admin_user)):
VECTOR_DB_CLIENT.delete_collection(collection_name=id)
result = Knowledges.delete_knowledge_by_id(id=id)
return result