feat/enhance the multi-modal support (#8818)
This commit is contained in:
parent
7a1d6fe509
commit
e61752bd3a
267 changed files with 6253 additions and 3513 deletions
|
|
@ -233,6 +233,8 @@ VIKINGDB_SOCKET_TIMEOUT=30
|
|||
UPLOAD_FILE_SIZE_LIMIT=15
|
||||
UPLOAD_FILE_BATCH_LIMIT=5
|
||||
UPLOAD_IMAGE_FILE_SIZE_LIMIT=10
|
||||
UPLOAD_VIDEO_FILE_SIZE_LIMIT=100
|
||||
UPLOAD_AUDIO_FILE_SIZE_LIMIT=50
|
||||
|
||||
# Model Configuration
|
||||
MULTIMODAL_SEND_IMAGE_FORMAT=base64
|
||||
|
|
@ -310,6 +312,7 @@ INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000
|
|||
WORKFLOW_MAX_EXECUTION_STEPS=500
|
||||
WORKFLOW_MAX_EXECUTION_TIME=1200
|
||||
WORKFLOW_CALL_MAX_DEPTH=5
|
||||
MAX_VARIABLE_SIZE=204800
|
||||
|
||||
# App configuration
|
||||
APP_MAX_EXECUTION_TIME=1200
|
||||
|
|
|
|||
15
api/.vscode/launch.json.example
vendored
15
api/.vscode/launch.json.example
vendored
|
|
@ -1,8 +1,15 @@
|
|||
{
|
||||
"version": "0.2.0",
|
||||
"compounds": [
|
||||
{
|
||||
"name": "Launch Flask and Celery",
|
||||
"configurations": ["Python: Flask", "Python: Celery"]
|
||||
}
|
||||
],
|
||||
"configurations": [
|
||||
{
|
||||
"name": "Python: Flask",
|
||||
"consoleName": "Flask",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"python": "${workspaceFolder}/.venv/bin/python",
|
||||
|
|
@ -17,12 +24,12 @@
|
|||
},
|
||||
"args": [
|
||||
"run",
|
||||
"--host=0.0.0.0",
|
||||
"--port=5001"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "Python: Celery",
|
||||
"consoleName": "Celery",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"python": "${workspaceFolder}/.venv/bin/python",
|
||||
|
|
@ -45,10 +52,10 @@
|
|||
"-c",
|
||||
"1",
|
||||
"--loglevel",
|
||||
"info",
|
||||
"DEBUG",
|
||||
"-Q",
|
||||
"dataset,generation,mail,ops_trace,app_deletion"
|
||||
]
|
||||
},
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ from extensions.ext_redis import redis_client
|
|||
from libs.helper import email as email_validate
|
||||
from libs.password import hash_password, password_pattern, valid_password
|
||||
from libs.rsa import generate_key_pair
|
||||
from models.account import Tenant
|
||||
from models import Tenant
|
||||
from models.dataset import Dataset, DatasetCollectionBinding, DocumentSegment
|
||||
from models.dataset import Document as DatasetDocument
|
||||
from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation
|
||||
|
|
@ -426,14 +426,14 @@ def convert_to_agent_apps():
|
|||
# fetch first 1000 apps
|
||||
sql_query = """SELECT a.id AS id FROM apps a
|
||||
INNER JOIN app_model_configs am ON a.app_model_config_id=am.id
|
||||
WHERE a.mode = 'chat'
|
||||
AND am.agent_mode is not null
|
||||
WHERE a.mode = 'chat'
|
||||
AND am.agent_mode is not null
|
||||
AND (
|
||||
am.agent_mode like '%"strategy": "function_call"%'
|
||||
am.agent_mode like '%"strategy": "function_call"%'
|
||||
OR am.agent_mode like '%"strategy": "react"%'
|
||||
)
|
||||
)
|
||||
AND (
|
||||
am.agent_mode like '{"enabled": true%'
|
||||
am.agent_mode like '{"enabled": true%'
|
||||
OR am.agent_mode like '{"max_iteration": %'
|
||||
) ORDER BY a.created_at DESC LIMIT 1000
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -20,11 +20,11 @@ class SecurityConfig(BaseSettings):
|
|||
Security-related configurations for the application
|
||||
"""
|
||||
|
||||
SECRET_KEY: Optional[str] = Field(
|
||||
SECRET_KEY: str = Field(
|
||||
description="Secret key for secure session cookie signing."
|
||||
"Make sure you are changing this key for your deployment with a strong key."
|
||||
"Generate a strong key using `openssl rand -base64 42` or set via the `SECRET_KEY` environment variable.",
|
||||
default=None,
|
||||
default="",
|
||||
)
|
||||
|
||||
RESET_PASSWORD_TOKEN_EXPIRY_HOURS: PositiveInt = Field(
|
||||
|
|
@ -186,6 +186,16 @@ class FileUploadConfig(BaseSettings):
|
|||
default=10,
|
||||
)
|
||||
|
||||
UPLOAD_VIDEO_FILE_SIZE_LIMIT: NonNegativeInt = Field(
|
||||
description="video file size limit in Megabytes for uploading files",
|
||||
default=100,
|
||||
)
|
||||
|
||||
UPLOAD_AUDIO_FILE_SIZE_LIMIT: NonNegativeInt = Field(
|
||||
description="audio file size limit in Megabytes for uploading files",
|
||||
default=50,
|
||||
)
|
||||
|
||||
BATCH_UPLOAD_LIMIT: NonNegativeInt = Field(
|
||||
description="Maximum number of files allowed in a batch upload operation",
|
||||
default=20,
|
||||
|
|
@ -364,8 +374,8 @@ class WorkflowConfig(BaseSettings):
|
|||
)
|
||||
|
||||
MAX_VARIABLE_SIZE: PositiveInt = Field(
|
||||
description="Maximum size in bytes for a single variable in workflows. Default to 5KB.",
|
||||
default=5 * 1024,
|
||||
description="Maximum size in bytes for a single variable in workflows. Default to 200 KB.",
|
||||
default=200 * 1024,
|
||||
)
|
||||
|
||||
|
||||
|
|
@ -493,6 +503,7 @@ class RagEtlConfig(BaseSettings):
|
|||
Configuration for RAG ETL processes
|
||||
"""
|
||||
|
||||
# TODO: This config is not only for rag etl, it is also for file upload, we should move it to file upload config
|
||||
ETL_TYPE: str = Field(
|
||||
description="RAG ETL type ('dify' or 'Unstructured'), default to 'dify'",
|
||||
default="dify",
|
||||
|
|
@ -559,7 +570,7 @@ class IndexingConfig(BaseSettings):
|
|||
|
||||
|
||||
class ImageFormatConfig(BaseSettings):
|
||||
MULTIMODAL_SEND_IMAGE_FORMAT: str = Field(
|
||||
MULTIMODAL_SEND_IMAGE_FORMAT: Literal["base64", "url"] = Field(
|
||||
description="Format for sending images in multimodal contexts ('base64' or 'url'), default is base64",
|
||||
default="base64",
|
||||
)
|
||||
|
|
|
|||
|
|
@ -1,2 +1,22 @@
|
|||
from configs import dify_config
|
||||
|
||||
HIDDEN_VALUE = "[__HIDDEN__]"
|
||||
UUID_NIL = "00000000-0000-0000-0000-000000000000"
|
||||
|
||||
IMAGE_EXTENSIONS = ["jpg", "jpeg", "png", "webp", "gif", "svg"]
|
||||
IMAGE_EXTENSIONS.extend([ext.upper() for ext in IMAGE_EXTENSIONS])
|
||||
|
||||
VIDEO_EXTENSIONS = ["mp4", "mov", "mpeg", "mpga"]
|
||||
VIDEO_EXTENSIONS.extend([ext.upper() for ext in VIDEO_EXTENSIONS])
|
||||
|
||||
AUDIO_EXTENSIONS = ["mp3", "m4a", "wav", "webm", "amr"]
|
||||
AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
|
||||
|
||||
|
||||
if dify_config.ETL_TYPE == "Unstructured":
|
||||
DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls"]
|
||||
DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "ppt", "xml", "epub"))
|
||||
DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
|
||||
else:
|
||||
DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
|
||||
DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
|
||||
|
|
|
|||
|
|
@ -1,7 +1,9 @@
|
|||
from contextvars import ContextVar
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from core.workflow.entities.variable_pool import VariablePool
|
||||
if TYPE_CHECKING:
|
||||
from core.workflow.entities.variable_pool import VariablePool
|
||||
|
||||
tenant_id: ContextVar[str] = ContextVar("tenant_id")
|
||||
|
||||
workflow_variable_pool: ContextVar[VariablePool] = ContextVar("workflow_variable_pool")
|
||||
workflow_variable_pool: ContextVar["VariablePool"] = ContextVar("workflow_variable_pool")
|
||||
|
|
|
|||
|
|
@ -22,7 +22,8 @@ from fields.conversation_fields import (
|
|||
)
|
||||
from libs.helper import DatetimeString
|
||||
from libs.login import login_required
|
||||
from models.model import AppMode, Conversation, EndUser, Message, MessageAnnotation
|
||||
from models import Conversation, EndUser, Message, MessageAnnotation
|
||||
from models.model import AppMode
|
||||
|
||||
|
||||
class CompletionConversationApi(Resource):
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@ from controllers.console.wraps import account_initialization_required
|
|||
from extensions.ext_database import db
|
||||
from fields.app_fields import app_site_fields
|
||||
from libs.login import login_required
|
||||
from models.model import Site
|
||||
from models import Site
|
||||
|
||||
|
||||
def parse_app_site_args():
|
||||
|
|
|
|||
|
|
@ -13,14 +13,14 @@ from controllers.console.setup import setup_required
|
|||
from controllers.console.wraps import account_initialization_required
|
||||
from core.app.apps.base_app_queue_manager import AppQueueManager
|
||||
from core.app.entities.app_invoke_entities import InvokeFrom
|
||||
from core.app.segments import factory
|
||||
from core.errors.error import AppInvokeQuotaExceededError
|
||||
from factories import variable_factory
|
||||
from fields.workflow_fields import workflow_fields
|
||||
from fields.workflow_run_fields import workflow_run_node_execution_fields
|
||||
from libs import helper
|
||||
from libs.helper import TimestampField, uuid_value
|
||||
from libs.login import current_user, login_required
|
||||
from models.model import App, AppMode
|
||||
from models import App
|
||||
from models.model import AppMode
|
||||
from services.app_dsl_service import AppDslService
|
||||
from services.app_generate_service import AppGenerateService
|
||||
from services.errors.app import WorkflowHashNotEqualError
|
||||
|
|
@ -101,9 +101,13 @@ class DraftWorkflowApi(Resource):
|
|||
|
||||
try:
|
||||
environment_variables_list = args.get("environment_variables") or []
|
||||
environment_variables = [factory.build_variable_from_mapping(obj) for obj in environment_variables_list]
|
||||
environment_variables = [
|
||||
variable_factory.build_variable_from_mapping(obj) for obj in environment_variables_list
|
||||
]
|
||||
conversation_variables_list = args.get("conversation_variables") or []
|
||||
conversation_variables = [factory.build_variable_from_mapping(obj) for obj in conversation_variables_list]
|
||||
conversation_variables = [
|
||||
variable_factory.build_variable_from_mapping(obj) for obj in conversation_variables_list
|
||||
]
|
||||
workflow = workflow_service.sync_draft_workflow(
|
||||
app_model=app_model,
|
||||
graph=args["graph"],
|
||||
|
|
@ -273,17 +277,15 @@ class DraftWorkflowRunApi(Resource):
|
|||
parser.add_argument("files", type=list, required=False, location="json")
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
response = AppGenerateService.generate(
|
||||
app_model=app_model, user=current_user, args=args, invoke_from=InvokeFrom.DEBUGGER, streaming=True
|
||||
)
|
||||
response = AppGenerateService.generate(
|
||||
app_model=app_model,
|
||||
user=current_user,
|
||||
args=args,
|
||||
invoke_from=InvokeFrom.DEBUGGER,
|
||||
streaming=True,
|
||||
)
|
||||
|
||||
return helper.compact_generate_response(response)
|
||||
except (ValueError, AppInvokeQuotaExceededError) as e:
|
||||
raise e
|
||||
except Exception as e:
|
||||
logging.exception("internal server error.")
|
||||
raise InternalServerError()
|
||||
return helper.compact_generate_response(response)
|
||||
|
||||
|
||||
class WorkflowTaskStopApi(Resource):
|
||||
|
|
|
|||
|
|
@ -7,7 +7,8 @@ from controllers.console.setup import setup_required
|
|||
from controllers.console.wraps import account_initialization_required
|
||||
from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
|
||||
from libs.login import login_required
|
||||
from models.model import App, AppMode
|
||||
from models import App
|
||||
from models.model import AppMode
|
||||
from services.workflow_app_service import WorkflowAppService
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -13,7 +13,8 @@ from fields.workflow_run_fields import (
|
|||
)
|
||||
from libs.helper import uuid_value
|
||||
from libs.login import login_required
|
||||
from models.model import App, AppMode
|
||||
from models import App
|
||||
from models.model import AppMode
|
||||
from services.workflow_run_service import WorkflowRunService
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -13,8 +13,8 @@ from controllers.console.wraps import account_initialization_required
|
|||
from extensions.ext_database import db
|
||||
from libs.helper import DatetimeString
|
||||
from libs.login import login_required
|
||||
from models.enums import WorkflowRunTriggeredFrom
|
||||
from models.model import AppMode
|
||||
from models.workflow import WorkflowRunTriggeredFrom
|
||||
|
||||
|
||||
class WorkflowDailyRunsStatistic(Resource):
|
||||
|
|
|
|||
|
|
@ -5,7 +5,8 @@ from typing import Optional, Union
|
|||
from controllers.console.app.error import AppNotFoundError
|
||||
from extensions.ext_database import db
|
||||
from libs.login import current_user
|
||||
from models.model import App, AppMode
|
||||
from models import App
|
||||
from models.model import AppMode
|
||||
|
||||
|
||||
def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[AppMode]] = None):
|
||||
|
|
|
|||
|
|
@ -13,7 +13,8 @@ from events.tenant_event import tenant_was_created
|
|||
from extensions.ext_database import db
|
||||
from libs.helper import extract_remote_ip
|
||||
from libs.oauth import GitHubOAuth, GoogleOAuth, OAuthUserInfo
|
||||
from models.account import Account, AccountStatus
|
||||
from models import Account
|
||||
from models.account import AccountStatus
|
||||
from services.account_service import AccountService, RegisterService, TenantService
|
||||
from services.errors.account import AccountNotFoundError
|
||||
from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkSpaceNotFoundError
|
||||
|
|
|
|||
|
|
@ -15,8 +15,7 @@ from core.rag.extractor.notion_extractor import NotionExtractor
|
|||
from extensions.ext_database import db
|
||||
from fields.data_source_fields import integrate_list_fields, integrate_notion_info_list_fields
|
||||
from libs.login import login_required
|
||||
from models.dataset import Document
|
||||
from models.source import DataSourceOauthBinding
|
||||
from models import DataSourceOauthBinding, Document
|
||||
from services.dataset_service import DatasetService, DocumentService
|
||||
from tasks.document_indexing_sync_task import document_indexing_sync_task
|
||||
|
||||
|
|
|
|||
|
|
@ -24,8 +24,8 @@ from fields.app_fields import related_app_list
|
|||
from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
|
||||
from fields.document_fields import document_status_fields
|
||||
from libs.login import login_required
|
||||
from models.dataset import Dataset, DatasetPermissionEnum, Document, DocumentSegment
|
||||
from models.model import ApiToken, UploadFile
|
||||
from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
|
||||
from models.dataset import DatasetPermissionEnum
|
||||
from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -46,8 +46,7 @@ from fields.document_fields import (
|
|||
document_with_segments_fields,
|
||||
)
|
||||
from libs.login import login_required
|
||||
from models.dataset import Dataset, DatasetProcessRule, Document, DocumentSegment
|
||||
from models.model import UploadFile
|
||||
from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
|
||||
from services.dataset_service import DatasetService, DocumentService
|
||||
from tasks.add_document_to_index_task import add_document_to_index_task
|
||||
from tasks.remove_document_from_index_task import remove_document_from_index_task
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@ from extensions.ext_database import db
|
|||
from extensions.ext_redis import redis_client
|
||||
from fields.segment_fields import segment_fields
|
||||
from libs.login import login_required
|
||||
from models.dataset import DocumentSegment
|
||||
from models import DocumentSegment
|
||||
from services.dataset_service import DatasetService, DocumentService, SegmentService
|
||||
from tasks.batch_create_segment_to_index_task import batch_create_segment_to_index_task
|
||||
from tasks.disable_segment_from_index_task import disable_segment_from_index_task
|
||||
|
|
|
|||
|
|
@ -1,9 +1,12 @@
|
|||
import urllib.parse
|
||||
|
||||
from flask import request
|
||||
from flask_login import current_user
|
||||
from flask_restful import Resource, marshal_with
|
||||
|
||||
import services
|
||||
from configs import dify_config
|
||||
from constants import DOCUMENT_EXTENSIONS
|
||||
from controllers.console import api
|
||||
from controllers.console.datasets.error import (
|
||||
FileTooLargeError,
|
||||
|
|
@ -13,9 +16,10 @@ from controllers.console.datasets.error import (
|
|||
)
|
||||
from controllers.console.setup import setup_required
|
||||
from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
|
||||
from fields.file_fields import file_fields, upload_config_fields
|
||||
from core.helper import ssrf_proxy
|
||||
from fields.file_fields import file_fields, remote_file_info_fields, upload_config_fields
|
||||
from libs.login import login_required
|
||||
from services.file_service import ALLOWED_EXTENSIONS, UNSTRUCTURED_ALLOWED_EXTENSIONS, FileService
|
||||
from services.file_service import FileService
|
||||
|
||||
PREVIEW_WORDS_LIMIT = 3000
|
||||
|
||||
|
|
@ -51,7 +55,7 @@ class FileApi(Resource):
|
|||
if len(request.files) > 1:
|
||||
raise TooManyFilesError()
|
||||
try:
|
||||
upload_file = FileService.upload_file(file, current_user)
|
||||
upload_file = FileService.upload_file(file=file, user=current_user)
|
||||
except services.errors.file.FileTooLargeError as file_too_large_error:
|
||||
raise FileTooLargeError(file_too_large_error.description)
|
||||
except services.errors.file.UnsupportedFileTypeError:
|
||||
|
|
@ -75,11 +79,24 @@ class FileSupportTypeApi(Resource):
|
|||
@login_required
|
||||
@account_initialization_required
|
||||
def get(self):
|
||||
etl_type = dify_config.ETL_TYPE
|
||||
allowed_extensions = UNSTRUCTURED_ALLOWED_EXTENSIONS if etl_type == "Unstructured" else ALLOWED_EXTENSIONS
|
||||
return {"allowed_extensions": allowed_extensions}
|
||||
return {"allowed_extensions": DOCUMENT_EXTENSIONS}
|
||||
|
||||
|
||||
class RemoteFileInfoApi(Resource):
|
||||
@marshal_with(remote_file_info_fields)
|
||||
def get(self, url):
|
||||
decoded_url = urllib.parse.unquote(url)
|
||||
try:
|
||||
response = ssrf_proxy.head(decoded_url)
|
||||
return {
|
||||
"file_type": response.headers.get("Content-Type", "application/octet-stream"),
|
||||
"file_length": int(response.headers.get("Content-Length", 0)),
|
||||
}
|
||||
except Exception as e:
|
||||
return {"error": str(e)}, 400
|
||||
|
||||
|
||||
api.add_resource(FileApi, "/files/upload")
|
||||
api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
|
||||
api.add_resource(FileSupportTypeApi, "/files/support-type")
|
||||
api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@ from controllers.console.wraps import account_initialization_required, cloud_edi
|
|||
from extensions.ext_database import db
|
||||
from fields.installed_app_fields import installed_app_list_fields
|
||||
from libs.login import login_required
|
||||
from models.model import App, InstalledApp, RecommendedApp
|
||||
from models import App, InstalledApp, RecommendedApp
|
||||
from services.account_service import TenantService
|
||||
|
||||
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Reference in a new issue