jyapayne/langflow
Watch
1
0
Fork
You've already forked langflow
 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

Merge branch 'saveComponent' into feature/store

Browse source
This commit is contained in:
cristhianzl 2023-10-19 00:02:21 -03:00
commit e473570c5d
58 changed files with 6458 additions and 1288 deletions
Download patch file Download diff file Expand all files Collapse all files

4
.env.example
View file

@ -71,3 +71,7 @@ LANGFLOW_SUPERUSER=
# Superuser password
# Example: LANGFLOW_SUPERUSER_PASSWORD=123456
LANGFLOW_SUPERUSER_PASSWORD=
# STORE_URL
# Example: LANGFLOW_STORE_URL=https://langflow.store
LANGFLOW_STORE_URL=

4
.gitignore vendored
View file

@ -254,4 +254,6 @@ langflow.db
/tmp/*
src/backend/langflow/frontend/
.docker
.docker
.idea

4
Makefile
View file

@ -74,10 +74,10 @@ backend:
make install_backend
ifeq ($(login),1)
@echo "Running backend without autologin";
poetry run langflow run --backend-only --port 7860 --host 0.0.0.0 --no-open-browser
poetry run langflow run --backend-only --port 7860 --host 0.0.0.0 --no-open-browser --env-file .env
else
@echo "Running backend with autologin";
LANGFLOW_AUTO_LOGIN=True poetry run langflow run --backend-only --port 7860 --host 0.0.0.0 --no-open-browser
LANGFLOW_AUTO_LOGIN=True poetry run langflow run --backend-only --port 7860 --host 0.0.0.0 --no-open-browser --env-file .env
endif
build_and_run:

38
docs/docs/components/llms.mdx
View file

@ -217,4 +217,40 @@ Vertex AI is a cloud computing platform offered by Google Cloud Platform (GCP).
- **top_k:** How the model selects tokens for output, the next token is selected from – defaults to `40`.
- **top_p:** Tokens are selected from most probable to least until the sum of their – defaults to `0.95`.
- **tuned_model_name:** The name of a tuned model. If provided, model_name is ignored.
- **verbose:** This parameter is used to control the level of detail in the output of the chain. When set to True, it will print out some internal states of the chain while it is being run, which can help debug and understand the chain's behavior. If set to False, it will suppress the verbose output – defaults to `False`.
- **verbose:** This parameter is used to control the level of detail in the output of the chain. When set to True, it will print out some internal states of the chain while it is being run, which can help debug and understand the chain's behavior. If set to False, it will suppress the verbose output – defaults to `False`.
---
### QianfanLLMEndpoint
Wrapper around [Baidu Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html) large language models.
:::info
The Qianfan Big Model Platform is a one-stop platform for enterprise developers to develop and operate large models and services. It provides data management based on ERNIE Bot's underlying model (Ernie Bot), automatic model customization and fine-tuning, and one-stop large-scale model customization services for cloud deployment of prediction services, and provides ERNIE Bot's enterprise level service API that can be quickly called, helping to implement the demand for generative AI applications in various industries.
:::
- **Model Name:** Model name. you could get from https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu preset models are mapping to an endpoint. `Model Name` will be ignored if `Endpoint` is set.
- **Qianfan Ak:** which you could get from https://cloud.baidu.com/product/wenxinworkshop.
- **Qianfan Sk:** which you could get from https://cloud.baidu.com/product/wenxinworkshop.
- **Top p:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. The diversity of the output text is affected, and the larger the value, the stronger the diversity of the generated text - defaults to `0.8`.
- **Temperature:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. Higher values make the output more random, while lower values make it more concentrated and deterministic - defaults to `0.95`.
- **Penalty Score:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. By increasing the penalty for generated tokens, the phenomenon of duplicate generation is reduced. A higher value indicates a higher penalty - defaults to `1.0`.
- **Endpoint:** Endpoint of the Qianfan LLM, required if custom model used.
---
### QianfanChatEndpoint
Wrapper around [Baidu Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html) chat large language models. This component supports some of the LLMs (Large Language Models) available by Baidu qianfan and is used for tasks such as chatbots, Generative Question-Answering (GQA), and summarization.
:::info
The Qianfan Big Model Platform is a one-stop platform for enterprise developers to develop and operate large models and services. It provides data management based on ERNIE Bot's underlying model (Ernie Bot), automatic model customization and fine-tuning, and one-stop large-scale model customization services for cloud deployment of prediction services, and provides ERNIE Bot's enterprise level service API that can be quickly called, helping to implement the demand for generative AI applications in various industries.
:::
- **Model Name:** Model name. you could get from https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu preset models are mapping to an endpoint. `Model Name` will be ignored if `Endpoint` is set.
- **Qianfan Ak:** which you could get from https://cloud.baidu.com/product/wenxinworkshop.
- **Qianfan Sk:** which you could get from https://cloud.baidu.com/product/wenxinworkshop.
- **Top p:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. The diversity of the output text is affected, and the larger the value, the stronger the diversity of the generated text - defaults to `0.8`.
- **Temperature:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. Higher values make the output more random, while lower values make it more concentrated and deterministic - defaults to `0.95`.
- **Penalty Score:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. By increasing the penalty for generated tokens, the phenomenon of duplicate generation is reduced. A higher value indicates a higher penalty - defaults to `1.0`.
- **Endpoint:** Endpoint of the Qianfan LLM, required if custom model used.

1559
poetry.lock generated
View file

File diff suppressed because it is too large Load diff

3
pyproject.toml
View file

@ -33,7 +33,7 @@ google-search-results = "^2.4.1"
google-api-python-client = "^2.79.0"
typer = "^0.9.0"
gunicorn = "^21.2.0"
langchain = "^0.0.308"
langchain = "^0.0.312"
openai = "^0.27.8"
pandas = "2.0.3"
chromadb = "^0.3.21"
@ -91,6 +91,7 @@ pillow = "^10.0.0"
metal-sdk = "^2.2.0"
markupsafe = "^2.1.3"
numexpr = "^2.8.6"
qianfan = "0.0.5"
[tool.poetry.group.dev.dependencies]

48
src/backend/langflow/alembic/versions/7843803a87b5_store_updates.py Normal file
View file

@ -0,0 +1,48 @@
"""Store updates
Revision ID: 7843803a87b5
Revises: eb5866d51fd2
Create Date: 2023-10-18 23:08:57.744906
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
import sqlmodel
# revision identifiers, used by Alembic.
revision: str = "7843803a87b5"
down_revision: Union[str, None] = "eb5866d51fd2"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
try:
with op.batch_alter_table("flow", schema=None) as batch_op:
batch_op.add_column(sa.Column("is_component", sa.Boolean(), nullable=True))
with op.batch_alter_table("user", schema=None) as batch_op:
batch_op.add_column(
sa.Column(
"store_api_key", sqlmodel.sql.sqltypes.AutoString(), nullable=True
)
)
except Exception:
pass
# ### end Alembic commands ###
def downgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
with op.batch_alter_table("user", schema=None) as batch_op:
batch_op.drop_column("store_api_key")
with op.batch_alter_table("flow", schema=None) as batch_op:
batch_op.drop_column("is_component")
# ### end Alembic commands ###

42
src/backend/langflow/alembic/versions/f5ee9749d1a6_user_id_can_be_null_in_flow.py Normal file
View file

@ -0,0 +1,42 @@
"""User id can be null in Flow
Revision ID: f5ee9749d1a6
Revises: 7843803a87b5
Create Date: 2023-10-18 23:12:27.297016
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
import sqlmodel
# revision identifiers, used by Alembic.
revision: str = "f5ee9749d1a6"
down_revision: Union[str, None] = "7843803a87b5"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
try:
with op.batch_alter_table("flow", schema=None) as batch_op:
batch_op.alter_column(
"user_id", existing_type=sa.CHAR(length=32), nullable=True
)
except Exception:
pass
# ### end Alembic commands ###
def downgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
with op.batch_alter_table("flow", schema=None) as batch_op:
batch_op.alter_column(
"user_id", existing_type=sa.CHAR(length=32), nullable=False
)
# ### end Alembic commands ###

4
src/backend/langflow/api/router.py
View file

@ -5,7 +5,7 @@ from langflow.api.v1 import (
endpoints_router,
validate_router,
flows_router,
component_router,
store_router,
users_router,
api_key_router,
login_router,
@ -17,7 +17,7 @@ router = APIRouter(
router.include_router(chat_router)
router.include_router(endpoints_router)
router.include_router(validate_router)
router.include_router(component_router)
router.include_router(store_router)
router.include_router(flows_router)
router.include_router(users_router)
router.include_router(api_key_router)

4
src/backend/langflow/api/v1/__init__.py
View file

@ -2,7 +2,7 @@ from langflow.api.v1.endpoints import router as endpoints_router
from langflow.api.v1.validate import router as validate_router
from langflow.api.v1.chat import router as chat_router
from langflow.api.v1.flows import router as flows_router
from langflow.api.v1.components import router as component_router
from langflow.api.v1.store import router as store_router
from langflow.api.v1.users import router as users_router
from langflow.api.v1.api_key import router as api_key_router
from langflow.api.v1.login import router as login_router
@ -10,7 +10,7 @@ from langflow.api.v1.login import router as login_router
__all__ = [
"chat_router",
"endpoints_router",
"component_router",
"store_router",
"validate_router",
"flows_router",
"users_router",

39
src/backend/langflow/api/v1/api_key.py
View file

@ -1,7 +1,7 @@
from uuid import UUID
from fastapi import APIRouter, HTTPException, Depends
from langflow.api.v1.schemas import ApiKeysResponse
from langflow.services.auth.utils import get_current_active_user
from langflow.api.v1.schemas import ApiKeysResponse, ApiKeyCreateRequest
from langflow.services.auth import utils as auth_utils
from langflow.services.database.models.api_key.api_key import (
ApiKeyCreate,
UnmaskedApiKeyRead,
@ -14,9 +14,17 @@ from langflow.services.database.models.api_key.crud import (
delete_api_key,
)
from langflow.services.database.models.user.user import User
from langflow.services.deps import get_session
from langflow.services.deps import (
get_session,
get_settings_service,
)
from typing import TYPE_CHECKING
from sqlmodel import Session
if TYPE_CHECKING:
pass
router = APIRouter(tags=["APIKey"], prefix="/api_key")
@ -24,7 +32,7 @@ router = APIRouter(tags=["APIKey"], prefix="/api_key")
@router.get("/", response_model=ApiKeysResponse)
def get_api_keys_route(
db: Session = Depends(get_session),
current_user: User = Depends(get_current_active_user),
current_user: User = Depends(auth_utils.get_current_active_user),
):
try:
user_id = current_user.id
@ -38,7 +46,7 @@ def get_api_keys_route(
@router.post("/", response_model=UnmaskedApiKeyRead)
def create_api_key_route(
req: ApiKeyCreate,
current_user: User = Depends(get_current_active_user),
current_user: User = Depends(auth_utils.get_current_active_user),
db: Session = Depends(get_session),
):
try:
@ -51,7 +59,7 @@ def create_api_key_route(
@router.delete("/{api_key_id}")
def delete_api_key_route(
api_key_id: UUID,
current_user=Depends(get_current_active_user),
current_user=Depends(auth_utils.get_current_active_user),
db: Session = Depends(get_session),
):
try:
@ -59,3 +67,22 @@ def delete_api_key_route(
return {"detail": "API Key deleted"}
except Exception as e:
raise HTTPException(status_code=400, detail=str(e)) from e
@router.post("/store")
def save_store_api_key(
api_key: ApiKeyCreateRequest,
current_user: User = Depends(auth_utils.get_current_active_user),
db: Session = Depends(get_session),
settings_service=Depends(get_settings_service),
):
try:
# Encrypt the API key
encrypted = auth_utils.encrypt_api_key(
api_key, fernet=auth_utils.get_fernet(settings_service)
)
current_user.store_api_key = encrypted
db.commit()
return {"detail": "API Key saved"}
except Exception as e:
raise HTTPException(status_code=400, detail=str(e)) from e

77
src/backend/langflow/api/v1/components.py
View file

@ -1,77 +0,0 @@
from datetime import timezone
from typing import List
from uuid import UUID
from langflow.services.database.models.component import Component, ComponentModel
from langflow.services.deps import get_session
from sqlmodel import Session, select
from fastapi import APIRouter, Depends, HTTPException
from sqlalchemy.exc import IntegrityError
from datetime import datetime
COMPONENT_NOT_FOUND = "Component not found"
COMPONENT_ALREADY_EXISTS = "A component with the same id already exists."
COMPONENT_DELETED = "Component deleted"
router = APIRouter(prefix="/components", tags=["Components"])
@router.post("/", response_model=Component)
def create_component(component: ComponentModel, db: Session = Depends(get_session)):
db_component = Component(**component.dict())
try:
db.add(db_component)
db.commit()
db.refresh(db_component)
except IntegrityError as e:
db.rollback()
raise HTTPException(
status_code=400,
detail=COMPONENT_ALREADY_EXISTS,
) from e
return db_component
@router.get("/{component_id}", response_model=Component)
def read_component(component_id: UUID, db: Session = Depends(get_session)):
if component := db.get(Component, component_id):
return component
else:
raise HTTPException(status_code=404, detail=COMPONENT_NOT_FOUND)
@router.get("/", response_model=List[Component])
def read_components(skip: int = 0, limit: int = 50, db: Session = Depends(get_session)):
query = select(Component)
query = query.offset(skip).limit(limit)
return db.execute(query).fetchall()
@router.patch("/{component_id}", response_model=Component)
def update_component(
component_id: UUID, component: ComponentModel, db: Session = Depends(get_session)
):
db_component = db.get(Component, component_id)
if not db_component:
raise HTTPException(status_code=404, detail=COMPONENT_NOT_FOUND)
component_data = component.dict(exclude_unset=True)
for key, value in component_data.items():
setattr(db_component, key, value)
db_component.update_at = datetime.now(timezone.utc)
db.commit()
db.refresh(db_component)
return db_component
@router.delete("/{component_id}")
def delete_component(component_id: UUID, db: Session = Depends(get_session)):
component = db.get(Component, component_id)
if not component:
raise HTTPException(status_code=404, detail=COMPONENT_NOT_FOUND)
db.delete(component)
db.commit()
return {"detail": COMPONENT_DELETED}

4
src/backend/langflow/api/v1/schemas.py
View file

@ -198,3 +198,7 @@ class Token(BaseModel):
access_token: str
refresh_token: str
token_type: str
class ApiKeyCreateRequest(BaseModel):
api_key: str

120
src/backend/langflow/api/v1/store.py Normal file
View file

@ -0,0 +1,120 @@
from typing import List, Optional
from uuid import UUID
from langflow.services.auth import utils as auth_utils
from langflow.services.database.models.flow.flow import Flow
from langflow.services.database.models.user.user import User
from langflow.services.deps import (
get_session,
get_store_service,
get_settings_service,
)
from langflow.services.store.schema import ComponentResponse
from fastapi import APIRouter, Depends, HTTPException, Query
from datetime import datetime
from langflow.services.store.service import StoreService
router = APIRouter(prefix="/store", tags=["Components Store"])
@router.post("/", response_model=ComponentResponse)
def create_component(
component: Flow,
store_service: StoreService = Depends(get_store_service),
user=Depends(auth_utils.get_current_active_user),
settings_service=Depends(get_settings_service),
):
try:
api_key = user.store_api_key
decrypted = auth_utils.decrypt_api_key(api_key, settings_service)
return store_service.upload(decrypted, component.dict())
except Exception as exc:
raise HTTPException(status_code=400, detail=str(exc))
@router.get("/{component_id}", response_model=ComponentResponse)
def read_component(
component_id: UUID,
store_service: StoreService = Depends(get_store_service),
user: User = Depends(auth_utils.get_current_active_user),
session=Depends(get_session),
):
if not user.store_api_key:
raise HTTPException(
status_code=400, detail="You must have a store API key set."
)
# If the component is from the store, we need to get it from the store
try:
api_key = user.store_api_key
component = store_service.get(api_key, component_id)
if component is not None:
# Turn component into a Flow
required_fields = ["data", "name", "description", "is_component"]
if all(field in component for field in required_fields):
component = Flow(
name=component["name"],
description=component["description"],
data=component["data"],
user_id=user.id,
)
session.add(component)
session.commit()
session.refresh(component)
except Exception as exc:
raise HTTPException(status_code=400, detail=str(exc)) from exc
if component is None:
raise HTTPException(status_code=400, detail="Component not found")
return component
@router.get("/", response_model=List[ComponentResponse])
def list_components(
page: int = 1,
limit: int = 10,
store_service: StoreService = Depends(get_store_service),
user=Depends(auth_utils.get_current_active_user),
settings_service=Depends(get_settings_service),
):
if user.store_api_key:
decrypted = auth_utils.decrypt_api_key(user.store_api_key, settings_service)
else:
decrypted = None
return store_service.list_components(decrypted, page, limit)
@router.get("/search", response_model=List[ComponentResponse])
async def search_endpoint(
api_key: Optional[str] = Query(None),
query: str = Query(...),
page: int = Query(1),
limit: int = Query(10),
status: Optional[str] = Query(None),
tags: Optional[List[str]] = Query(None),
date_from: Optional[datetime] = Query(None),
date_to: Optional[datetime] = Query(None),
sort_by: Optional[str] = Query("likes"),
sort: Optional[List[str]] = Query(None),
fields: Optional[List[str]] = Query(None),
store_service: "StoreService" = Depends(get_store_service),
):
try:
return await store_service.search(
api_key=api_key,
query=query,
page=page,
limit=limit,
status=status,
tags=tags,
date_from=date_from,
date_to=date_to,
sort_by=sort_by,
sort=sort,
fields=fields,
)
except Exception as exc:
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(exc)
)

92
src/backend/langflow/components/llms/BaiduQianfanChatEndpoints.py Normal file
View file

@ -0,0 +1,92 @@
from typing import Optional
from langflow import CustomComponent
from langchain.chat_models.baidu_qianfan_endpoint import QianfanChatEndpoint
from langchain.llms.base import BaseLLM
class QianfanChatEndpointComponent(CustomComponent):
display_name: str = "QianfanChatEndpoint"
description: str = (
"Baidu Qianfan chat models. Get more detail from "
"https://python.langchain.com/docs/integrations/chat/baidu_qianfan_endpoint."
)
def build_config(self):
return {
"model": {
"display_name": "Model Name",
"options": [
"ERNIE-Bot",
"ERNIE-Bot-turbo",
"BLOOMZ-7B",
"Llama-2-7b-chat",
"Llama-2-13b-chat",
"Llama-2-70b-chat",
"Qianfan-BLOOMZ-7B-compressed",
"Qianfan-Chinese-Llama-2-7B",
"ChatGLM2-6B-32K",
"AquilaChat-7B",
],
"info": "https://python.langchain.com/docs/integrations/chat/baidu_qianfan_endpoint",
"required": True,
},
"qianfan_ak": {
"display_name": "Qianfan Ak",
"required": True,
"password": True,
"info": "which you could get from https://cloud.baidu.com/product/wenxinworkshop",
},
"qianfan_sk": {
"display_name": "Qianfan Sk",
"required": True,
"password": True,
"info": "which you could get from https://cloud.baidu.com/product/wenxinworkshop",
},
"top_p": {
"display_name": "Top p",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 0.8,
},
"temperature": {
"display_name": "Temperature",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 0.95,
},
"penalty_score": {
"display_name": "Penalty Score",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 1.0,
},
"endpoint": {
"display_name": "Endpoint",
"info": "Endpoint of the Qianfan LLM, required if custom model used.",
},
"code": {"show": False},
}
def build(
self,
model: str = "ERNIE-Bot-turbo",
qianfan_ak: Optional[str] = None,
qianfan_sk: Optional[str] = None,
top_p: Optional[float] = None,
temperature: Optional[float] = None,
penalty_score: Optional[float] = None,
endpoint: Optional[str] = None,
) -> BaseLLM:
try:
output = QianfanChatEndpoint( # type: ignore
model=model,
qianfan_ak=qianfan_ak,
qianfan_sk=qianfan_sk,
top_p=top_p,
temperature=temperature,
penalty_score=penalty_score,
endpoint=endpoint,
)
except Exception as e:
raise ValueError("Could not connect to Baidu Qianfan API.") from e
return output # type: ignore

92
src/backend/langflow/components/llms/BaiduQianfanLLMEndpoints.py Normal file
View file

@ -0,0 +1,92 @@
from typing import Optional
from langflow import CustomComponent
from langchain.llms.baidu_qianfan_endpoint import QianfanLLMEndpoint
from langchain.llms.base import BaseLLM
class QianfanLLMEndpointComponent(CustomComponent):
display_name: str = "QianfanLLMEndpoint"
description: str = (
"Baidu Qianfan hosted open source or customized models. "
"Get more detail from https://python.langchain.com/docs/integrations/chat/baidu_qianfan_endpoint"
)
def build_config(self):
return {
"model": {
"display_name": "Model Name",
"options": [
"ERNIE-Bot",
"ERNIE-Bot-turbo",
"BLOOMZ-7B",
"Llama-2-7b-chat",
"Llama-2-13b-chat",
"Llama-2-70b-chat",
"Qianfan-BLOOMZ-7B-compressed",
"Qianfan-Chinese-Llama-2-7B",
"ChatGLM2-6B-32K",
"AquilaChat-7B",
],
"info": "https://python.langchain.com/docs/integrations/chat/baidu_qianfan_endpoint",
"required": True,
},
"qianfan_ak": {
"display_name": "Qianfan Ak",
"required": True,
"password": True,
"info": "which you could get from https://cloud.baidu.com/product/wenxinworkshop",
},
"qianfan_sk": {
"display_name": "Qianfan Sk",
"required": True,
"password": True,
"info": "which you could get from https://cloud.baidu.com/product/wenxinworkshop",
},
"top_p": {
"display_name": "Top p",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 0.8,
},
"temperature": {
"display_name": "Temperature",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 0.95,
},
"penalty_score": {
"display_name": "Penalty Score",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 1.0,
},
"endpoint": {
"display_name": "Endpoint",
"info": "Endpoint of the Qianfan LLM, required if custom model used.",
},
"code": {"show": False},
}
def build(
self,
model: str = "ERNIE-Bot-turbo",
qianfan_ak: Optional[str] = None,
qianfan_sk: Optional[str] = None,
top_p: Optional[float] = None,
temperature: Optional[float] = None,
penalty_score: Optional[float] = None,
endpoint: Optional[str] = None,
) -> BaseLLM:
try:
output = QianfanLLMEndpoint( # type: ignore
model=model,
qianfan_ak=qianfan_ak,
qianfan_sk=qianfan_sk,
top_p=top_p,
temperature=temperature,
penalty_score=penalty_score,
endpoint=endpoint,
)
except Exception as e:
raise ValueError("Could not connect to Baidu Qianfan API.") from e
return output # type: ignore

8
src/backend/langflow/components/vectorstores/Vectara.py
View file

@ -5,7 +5,6 @@ from langchain.vectorstores import Vectara
from langchain.schema import Document
from langchain.vectorstores.base import VectorStore
from langchain.schema import BaseRetriever
from langchain.embeddings.base import Embeddings
class VectaraComponent(CustomComponent):
@ -22,7 +21,6 @@ class VectaraComponent(CustomComponent):
"vectara_api_key": {"display_name": "Vectara API Key", "password": True},
"code": {"show": False},
"documents": {"display_name": "Documents"},
"embedding": {"display_name": "Embedding"},
}
def build(
@ -30,21 +28,21 @@ class VectaraComponent(CustomComponent):
vectara_customer_id: str,
vectara_corpus_id: str,
vectara_api_key: str,
embedding: Optional[Embeddings] = None,
documents: Optional[Document] = None,
) -> Union[VectorStore, BaseRetriever]:
# If documents, then we need to create a Vectara instance using .from_documents
if documents is not None and embedding is not None:
if documents is not None:
return Vectara.from_documents(
documents=documents, # type: ignore
vectara_customer_id=vectara_customer_id,
vectara_corpus_id=vectara_corpus_id,
vectara_api_key=vectara_api_key,
embedding=embedding,
source="langflow",
)
return Vectara(
vectara_customer_id=vectara_customer_id,
vectara_corpus_id=vectara_corpus_id,
vectara_api_key=vectara_api_key,
source="langflow",
)

24
src/backend/langflow/services/auth/utils.py
View file

@ -14,6 +14,7 @@ from langflow.services.database.models.user.crud import (
)
from langflow.services.deps import get_session, get_settings_service
from sqlmodel import Session
from cryptography.fernet import Fernet
oauth2_login = OAuth2PasswordBearer(tokenUrl="api/v1/login")
@ -294,3 +295,26 @@ def authenticate_user(
raise HTTPException(status_code=400, detail="Inactive user")
return user if verify_password(password, user.password) else None
def get_fernet(settings_service=Depends(get_settings_service)):
SECRET_KEY = settings_service.auth_settings.SECRET_KEY
# It's important that your secret key is 32 url-safe base64-encoded bytes
fernet = Fernet(SECRET_KEY)
return fernet
def encrypt_api_key(api_key: str, settings_service=Depends(get_settings_service)):
fernet = get_fernet(settings_service)
# Two-way encryption
encrypted_key = fernet.encrypt(api_key.encode())
return encrypted_key
def decrypt_api_key(
encrypted_api_key: str, settings_service=Depends(get_settings_service)
):
fernet = get_fernet(settings_service)
# Two-way decryption
decrypted_key = fernet.decrypt(encrypted_api_key.encode()).decode()
return decrypted_key

3
src/backend/langflow/services/database/models/flow/flow.py
View file

@ -15,6 +15,7 @@ class FlowBase(SQLModelSerializable):
name: str = Field(index=True)
description: Optional[str] = Field(index=True)
data: Optional[Dict] = Field(default=None, nullable=True)
is_component: bool = Field(default=False, nullable=True)
@validator("data")
def validate_json(v):
@ -35,7 +36,7 @@ class FlowBase(SQLModelSerializable):
class Flow(FlowBase, table=True):
id: UUID = Field(default_factory=uuid4, primary_key=True, unique=True)
data: Optional[Dict] = Field(default=None, sa_column=Column(JSON))
user_id: UUID = Field(index=True, foreign_key="user.id")
user_id: UUID = Field(index=True, foreign_key="user.id", nullable=True)
user: "User" = Relationship(back_populates="flows")

1
src/backend/langflow/services/database/models/user/user.py
View file

@ -25,6 +25,7 @@ class User(SQLModelSerializable, table=True):
back_populates="user",
sa_relationship_kwargs={"cascade": "delete"},
)
store_api_key: str = Field(default=None, nullable=True)
flows: list["Flow"] = Relationship(back_populates="user")

Some files were not shown because too many files have changed in this diff Show more