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

feat: server multi models support (#799)

Browse source
This commit is contained in:
takatost 2023-08-12 00:57:00 +08:00 • committed by GitHub
commit 5fa2161b05
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
213 changed files with 10535 additions and 2558 deletions
Download patch file Download diff file Expand all files Collapse all files

3
.github/workflows/check_no_chinese_comments.py vendored
View file

@ -19,7 +19,8 @@ def check_file_for_chinese_comments(file_path):
def main():
has_chinese = False
excluded_files = ["model_template.py", 'stopwords.py', 'commands.py', 'indexing_runner.py', 'web_reader_tool.py']
excluded_files = ["model_template.py", 'stopwords.py', 'commands.py',
'indexing_runner.py', 'web_reader_tool.py', 'spark_provider.py']
for root, _, files in os.walk("."):
for file in files:

26
api/.env.example
View file

@ -102,3 +102,29 @@ NOTION_INTEGRATION_TYPE=public
NOTION_CLIENT_SECRET=you-client-secret
NOTION_CLIENT_ID=you-client-id
NOTION_INTERNAL_SECRET=you-internal-secret
# Hosted Model Credentials
HOSTED_OPENAI_ENABLED=false
HOSTED_OPENAI_API_KEY=
HOSTED_OPENAI_API_BASE=
HOSTED_OPENAI_API_ORGANIZATION=
HOSTED_OPENAI_QUOTA_LIMIT=200
HOSTED_OPENAI_PAID_ENABLED=false
HOSTED_OPENAI_PAID_STRIPE_PRICE_ID=
HOSTED_OPENAI_PAID_INCREASE_QUOTA=1
HOSTED_AZURE_OPENAI_ENABLED=false
HOSTED_AZURE_OPENAI_API_KEY=
HOSTED_AZURE_OPENAI_API_BASE=
HOSTED_AZURE_OPENAI_QUOTA_LIMIT=200
HOSTED_ANTHROPIC_ENABLED=false
HOSTED_ANTHROPIC_API_BASE=
HOSTED_ANTHROPIC_API_KEY=
HOSTED_ANTHROPIC_QUOTA_LIMIT=1000000
HOSTED_ANTHROPIC_PAID_ENABLED=false
HOSTED_ANTHROPIC_PAID_STRIPE_PRICE_ID=
HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA=1
STRIPE_API_KEY=
STRIPE_WEBHOOK_SECRET=

19
api/app.py
View file

@ -16,8 +16,9 @@ from flask import Flask, request, Response, session
import flask_login
from flask_cors import CORS
from core.model_providers.providers import hosted
from extensions import ext_session, ext_celery, ext_sentry, ext_redis, ext_login, ext_migrate, \
ext_database, ext_storage, ext_mail
ext_database, ext_storage, ext_mail, ext_stripe
from extensions.ext_database import db
from extensions.ext_login import login_manager
@ -71,7 +72,7 @@ def create_app(test_config=None) -> Flask:
register_blueprints(app)
register_commands(app)
core.init_app(app)
hosted.init_app(app)
return app
@ -88,6 +89,7 @@ def initialize_extensions(app):
ext_login.init_app(app)
ext_mail.init_app(app)
ext_sentry.init_app(app)
ext_stripe.init_app(app)
def _create_tenant_for_account(account):
@ -246,5 +248,18 @@ def threads():
}
@app.route('/db-pool-stat')
def pool_stat():
engine = db.engine
return {
'pool_size': engine.pool.size(),
'checked_in_connections': engine.pool.checkedin(),
'checked_out_connections': engine.pool.checkedout(),
'overflow_connections': engine.pool.overflow(),
'connection_timeout': engine.pool.timeout(),
'recycle_time': db.engine.pool._recycle
}
if __name__ == '__main__':
app.run(host='0.0.0.0', port=5001)

37
api/commands.py
View file

@ -1,5 +1,5 @@
import datetime
import logging
import math
import random
import string
import time
@ -9,18 +9,18 @@ from flask import current_app
from werkzeug.exceptions import NotFound
from core.index.index import IndexBuilder
from core.model_providers.providers.hosted import hosted_model_providers
from libs.password import password_pattern, valid_password, hash_password
from libs.helper import email as email_validate
from extensions.ext_database import db
from libs.rsa import generate_key_pair
from models.account import InvitationCode, Tenant
from models.dataset import Dataset, DatasetQuery, Document, DocumentSegment
from models.dataset import Dataset, DatasetQuery, Document
from models.model import Account
import secrets
import base64
from models.provider import Provider, ProviderName
from services.provider_service import ProviderService
from models.provider import Provider, ProviderType, ProviderQuotaType
@click.command('reset-password', help='Reset the account password.')
@ -251,26 +251,37 @@ def clean_unused_dataset_indexes():
@click.command('sync-anthropic-hosted-providers', help='Sync anthropic hosted providers.')
def sync_anthropic_hosted_providers():
if not hosted_model_providers.anthropic:
click.echo(click.style('Anthropic hosted provider is not configured.', fg='red'))
return
click.echo(click.style('Start sync anthropic hosted providers.', fg='green'))
count = 0
page = 1
while True:
try:
tenants = db.session.query(Tenant).order_by(Tenant.created_at.desc()).paginate(page=page, per_page=50)
providers = db.session.query(Provider).filter(
Provider.provider_name == 'anthropic',
Provider.provider_type == ProviderType.SYSTEM.value,
Provider.quota_type == ProviderQuotaType.TRIAL.value,
).order_by(Provider.created_at.desc()).paginate(page=page, per_page=100)
except NotFound:
break
page += 1
for tenant in tenants:
for provider in providers:
try:
click.echo('Syncing tenant anthropic hosted provider: {}'.format(tenant.id))
ProviderService.create_system_provider(
tenant,
ProviderName.ANTHROPIC.value,
current_app.config['ANTHROPIC_HOSTED_QUOTA_LIMIT'],
True
)
click.echo('Syncing tenant anthropic hosted provider: {}'.format(provider.tenant_id))
original_quota_limit = provider.quota_limit
new_quota_limit = hosted_model_providers.anthropic.quota_limit
division = math.ceil(new_quota_limit / 1000)
provider.quota_limit = new_quota_limit if original_quota_limit == 1000 \
else original_quota_limit * division
provider.quota_used = division * provider.quota_used
db.session.commit()
count += 1
except Exception as e:
click.echo(click.style(

50
api/config.py
View file

@ -41,6 +41,7 @@ DEFAULTS = {
'SESSION_USE_SIGNER': 'True',
'DEPLOY_ENV': 'PRODUCTION',
'SQLALCHEMY_POOL_SIZE': 30,
'SQLALCHEMY_POOL_RECYCLE': 3600,
'SQLALCHEMY_ECHO': 'False',
'SENTRY_TRACES_SAMPLE_RATE': 1.0,
'SENTRY_PROFILES_SAMPLE_RATE': 1.0,
@ -50,9 +51,16 @@ DEFAULTS = {
'PDF_PREVIEW': 'True',
'LOG_LEVEL': 'INFO',
'DISABLE_PROVIDER_CONFIG_VALIDATION': 'False',
'DEFAULT_LLM_PROVIDER': 'openai',
'OPENAI_HOSTED_QUOTA_LIMIT': 200,
'ANTHROPIC_HOSTED_QUOTA_LIMIT': 1000,
'HOSTED_OPENAI_QUOTA_LIMIT': 200,
'HOSTED_OPENAI_ENABLED': 'False',
'HOSTED_OPENAI_PAID_ENABLED': 'False',
'HOSTED_OPENAI_PAID_INCREASE_QUOTA': 1,
'HOSTED_AZURE_OPENAI_ENABLED': 'False',
'HOSTED_AZURE_OPENAI_QUOTA_LIMIT': 200,
'HOSTED_ANTHROPIC_QUOTA_LIMIT': 1000000,
'HOSTED_ANTHROPIC_ENABLED': 'False',
'HOSTED_ANTHROPIC_PAID_ENABLED': 'False',
'HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA': 1,
'TENANT_DOCUMENT_COUNT': 100,
'CLEAN_DAY_SETTING': 30
}
@ -182,7 +190,10 @@ class Config:
}
self.SQLALCHEMY_DATABASE_URI = f"postgresql://{db_credentials['DB_USERNAME']}:{db_credentials['DB_PASSWORD']}@{db_credentials['DB_HOST']}:{db_credentials['DB_PORT']}/{db_credentials['DB_DATABASE']}"
self.SQLALCHEMY_ENGINE_OPTIONS = {'pool_size': int(get_env('SQLALCHEMY_POOL_SIZE'))}
self.SQLALCHEMY_ENGINE_OPTIONS = {
'pool_size': int(get_env('SQLALCHEMY_POOL_SIZE')),
'pool_recycle': int(get_env('SQLALCHEMY_POOL_RECYCLE'))
}
self.SQLALCHEMY_ECHO = get_bool_env('SQLALCHEMY_ECHO')
@ -194,20 +205,35 @@ class Config:
self.BROKER_USE_SSL = self.CELERY_BROKER_URL.startswith('rediss://')
# hosted provider credentials
self.OPENAI_API_KEY = get_env('OPENAI_API_KEY')
self.ANTHROPIC_API_KEY = get_env('ANTHROPIC_API_KEY')
self.HOSTED_OPENAI_ENABLED = get_bool_env('HOSTED_OPENAI_ENABLED')
self.HOSTED_OPENAI_API_KEY = get_env('HOSTED_OPENAI_API_KEY')
self.HOSTED_OPENAI_API_BASE = get_env('HOSTED_OPENAI_API_BASE')
self.HOSTED_OPENAI_API_ORGANIZATION = get_env('HOSTED_OPENAI_API_ORGANIZATION')
self.HOSTED_OPENAI_QUOTA_LIMIT = get_env('HOSTED_OPENAI_QUOTA_LIMIT')
self.HOSTED_OPENAI_PAID_ENABLED = get_bool_env('HOSTED_OPENAI_PAID_ENABLED')
self.HOSTED_OPENAI_PAID_STRIPE_PRICE_ID = get_env('HOSTED_OPENAI_PAID_STRIPE_PRICE_ID')
self.HOSTED_OPENAI_PAID_INCREASE_QUOTA = int(get_env('HOSTED_OPENAI_PAID_INCREASE_QUOTA'))
self.OPENAI_HOSTED_QUOTA_LIMIT = get_env('OPENAI_HOSTED_QUOTA_LIMIT')
self.ANTHROPIC_HOSTED_QUOTA_LIMIT = get_env('ANTHROPIC_HOSTED_QUOTA_LIMIT')
self.HOSTED_AZURE_OPENAI_ENABLED = get_bool_env('HOSTED_AZURE_OPENAI_ENABLED')
self.HOSTED_AZURE_OPENAI_API_KEY = get_env('HOSTED_AZURE_OPENAI_API_KEY')
self.HOSTED_AZURE_OPENAI_API_BASE = get_env('HOSTED_AZURE_OPENAI_API_BASE')
self.HOSTED_AZURE_OPENAI_QUOTA_LIMIT = get_env('HOSTED_AZURE_OPENAI_QUOTA_LIMIT')
self.HOSTED_ANTHROPIC_ENABLED = get_bool_env('HOSTED_ANTHROPIC_ENABLED')
self.HOSTED_ANTHROPIC_API_BASE = get_env('HOSTED_ANTHROPIC_API_BASE')
self.HOSTED_ANTHROPIC_API_KEY = get_env('HOSTED_ANTHROPIC_API_KEY')
self.HOSTED_ANTHROPIC_QUOTA_LIMIT = get_env('HOSTED_ANTHROPIC_QUOTA_LIMIT')
self.HOSTED_ANTHROPIC_PAID_ENABLED = get_bool_env('HOSTED_ANTHROPIC_PAID_ENABLED')
self.HOSTED_ANTHROPIC_PAID_STRIPE_PRICE_ID = get_env('HOSTED_ANTHROPIC_PAID_STRIPE_PRICE_ID')
self.HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA = get_env('HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA')
self.STRIPE_API_KEY = get_env('STRIPE_API_KEY')
self.STRIPE_WEBHOOK_SECRET = get_env('STRIPE_WEBHOOK_SECRET')
# By default it is False
# You could disable it for compatibility with certain OpenAPI providers
self.DISABLE_PROVIDER_CONFIG_VALIDATION = get_bool_env('DISABLE_PROVIDER_CONFIG_VALIDATION')
# For temp use only
# set default LLM provider, default is 'openai', support `azure_openai`
self.DEFAULT_LLM_PROVIDER = get_env('DEFAULT_LLM_PROVIDER')
# notion import setting
self.NOTION_CLIENT_ID = get_env('NOTION_CLIENT_ID')
self.NOTION_CLIENT_SECRET = get_env('NOTION_CLIENT_SECRET')

5
api/controllers/console/__init__.py
View file

@ -18,10 +18,13 @@ from .auth import login, oauth, data_source_oauth, activate
from .datasets import datasets, datasets_document, datasets_segments, file, hit_testing, data_source
# Import workspace controllers
from .workspace import workspace, members, model_providers, account, tool_providers
from .workspace import workspace, members, providers, model_providers, account, tool_providers, models
# Import explore controllers
from .explore import installed_app, recommended_app, completion, conversation, message, parameter, saved_message, audio
# Import universal chat controllers
from .universal_chat import chat, conversation, message, parameter, audio
# Import webhook controllers
from .webhook import stripe

26
api/controllers/console/app/app.py
View file

@ -2,16 +2,17 @@
import json
from datetime import datetime
import flask
from flask_login import login_required, current_user
from flask_restful import Resource, reqparse, fields, marshal_with, abort, inputs
from werkzeug.exceptions import Unauthorized, Forbidden
from werkzeug.exceptions import Forbidden
from constants.model_template import model_templates, demo_model_templates
from controllers.console import api
from controllers.console.app.error import AppNotFoundError
from controllers.console.app.error import AppNotFoundError, ProviderNotInitializeError
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from core.model_providers.model_factory import ModelFactory
from core.model_providers.models.entity.model_params import ModelType
from events.app_event import app_was_created, app_was_deleted
from libs.helper import TimestampField
from extensions.ext_database import db
@ -126,9 +127,9 @@ class AppListApi(Resource):
if args['model_config'] is not None:
# validate config
model_configuration = AppModelConfigService.validate_configuration(
tenant_id=current_user.current_tenant_id,
account=current_user,
config=args['model_config'],
mode=args['mode']
config=args['model_config']
)
app = App(
@ -164,6 +165,21 @@ class AppListApi(Resource):
app = App(**model_config_template['app'])
app_model_config = AppModelConfig(**model_config_template['model_config'])
default_model = ModelFactory.get_default_model(
tenant_id=current_user.current_tenant_id,
model_type=ModelType.TEXT_GENERATION
)
if default_model:
model_dict = app_model_config.model_dict
model_dict['provider'] = default_model.provider_name
model_dict['name'] = default_model.model_name
app_model_config.model = json.dumps(model_dict)
else:
raise ProviderNotInitializeError(
f"No Text Generation Model available. Please configure a valid provider "
f"in the Settings -> Model Provider.")
app.name = args['name']
app.mode = args['mode']
app.icon = args['icon']

2
api/controllers/console/app/audio.py
View file

@ -14,7 +14,7 @@ from controllers.console.app.error import AppUnavailableError, \
UnsupportedAudioTypeError, ProviderNotSupportSpeechToTextError
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from core.llm.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from flask_restful import Resource
from services.audio_service import AudioService

12
api/controllers/console/app/completion.py
View file

@ -17,7 +17,7 @@ from controllers.console.app.error import ConversationCompletedError, AppUnavail
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from core.conversation_message_task import PubHandler
from core.llm.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from libs.helper import uuid_value
from flask_restful import Resource, reqparse
@ -41,8 +41,11 @@ class CompletionMessageApi(Resource):
parser.add_argument('inputs', type=dict, required=True, location='json')
parser.add_argument('query', type=str, location='json')
parser.add_argument('model_config', type=dict, required=True, location='json')
parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
args = parser.parse_args()
streaming = args['response_mode'] != 'blocking'
account = flask_login.current_user
try:
@ -51,7 +54,7 @@ class CompletionMessageApi(Resource):
user=account,
args=args,
from_source='console',
streaming=True,
streaming=streaming,
is_model_config_override=True
)
@ -111,8 +114,11 @@ class ChatMessageApi(Resource):
parser.add_argument('query', type=str, required=True, location='json')
parser.add_argument('model_config', type=dict, required=True, location='json')
parser.add_argument('conversation_id', type=uuid_value, location='json')
parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
args = parser.parse_args()
streaming = args['response_mode'] != 'blocking'
account = flask_login.current_user
try:
@ -121,7 +127,7 @@ class ChatMessageApi(Resource):
user=account,
args=args,
from_source='console',
streaming=True,
streaming=streaming,
is_model_config_override=True
)

2
api/controllers/console/app/generator.py
View file

@ -7,7 +7,7 @@ from controllers.console.app.error import ProviderNotInitializeError, ProviderQu
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from core.generator.llm_generator import LLMGenerator
from core.llm.error import ProviderTokenNotInitError, QuotaExceededError, LLMBadRequestError, LLMAPIConnectionError, \
from core.model_providers.error import ProviderTokenNotInitError, QuotaExceededError, LLMBadRequestError, LLMAPIConnectionError, \
LLMAPIUnavailableError, LLMRateLimitError, LLMAuthorizationError, ModelCurrentlyNotSupportError

2
api/controllers/console/app/message.py
View file

@ -14,7 +14,7 @@ from controllers.console.app.error import CompletionRequestError, ProviderNotIni
AppMoreLikeThisDisabledError, ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from core.llm.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
from core.model_providers.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
ProviderTokenNotInitError, LLMAPIUnavailableError, QuotaExceededError, ModelCurrentlyNotSupportError
from libs.helper import uuid_value, TimestampField
from libs.infinite_scroll_pagination import InfiniteScrollPagination

4
api/controllers/console/app/model_config.py
View file

@ -28,9 +28,9 @@ class ModelConfigResource(Resource):
# validate config
model_configuration = AppModelConfigService.validate_configuration(
tenant_id=current_user.current_tenant_id,
account=current_user,
config=request.json,
mode=app_model.mode
config=request.json
)
new_app_model_config = AppModelConfig(

2
api/controllers/console/datasets/data_source.py
View file

@ -255,7 +255,7 @@ class DataSourceNotionApi(Resource):
# validate args
DocumentService.estimate_args_validate(args)
indexing_runner = IndexingRunner()
response = indexing_runner.notion_indexing_estimate(args['notion_info_list'], args['process_rule'])
response = indexing_runner.notion_indexing_estimate(current_user.current_tenant_id, args['notion_info_list'], args['process_rule'])
return response, 200

32
api/controllers/console/datasets/datasets.py
View file

@ -5,10 +5,13 @@ from flask_restful import Resource, reqparse, fields, marshal, marshal_with
from werkzeug.exceptions import NotFound, Forbidden
import services
from controllers.console import api
from controllers.console.app.error import ProviderNotInitializeError
from controllers.console.datasets.error import DatasetNameDuplicateError
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from core.indexing_runner import IndexingRunner
from core.model_providers.error import LLMBadRequestError
from core.model_providers.model_factory import ModelFactory
from libs.helper import TimestampField
from extensions.ext_database import db
from models.dataset import DocumentSegment, Document
@ -97,6 +100,15 @@ class DatasetListApi(Resource):
if current_user.current_tenant.current_role not in ['admin', 'owner']:
raise Forbidden()
try:
ModelFactory.get_embedding_model(
tenant_id=current_user.current_tenant_id
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
f"No Embedding Model available. Please configure a valid provider "
f"in the Settings -> Model Provider.")
try:
dataset = DatasetService.create_empty_dataset(
tenant_id=current_user.current_tenant_id,
@ -235,12 +247,26 @@ class DatasetIndexingEstimateApi(Resource):
raise NotFound("File not found.")
indexing_runner = IndexingRunner()
response = indexing_runner.file_indexing_estimate(file_details, args['process_rule'], args['doc_form'])
try:
response = indexing_runner.file_indexing_estimate(current_user.current_tenant_id, file_details,
args['process_rule'], args['doc_form'])
except LLMBadRequestError:
raise ProviderNotInitializeError(
f"No Embedding Model available. Please configure a valid provider "
f"in the Settings -> Model Provider.")
elif args['info_list']['data_source_type'] == 'notion_import':
indexing_runner = IndexingRunner()
response = indexing_runner.notion_indexing_estimate(args['info_list']['notion_info_list'],
args['process_rule'], args['doc_form'])
try:
response = indexing_runner.notion_indexing_estimate(current_user.current_tenant_id,
args['info_list']['notion_info_list'],
args['process_rule'], args['doc_form'])
except LLMBadRequestError:
raise ProviderNotInitializeError(
f"No Embedding Model available. Please configure a valid provider "
f"in the Settings -> Model Provider.")
else:
raise ValueError('Data source type not support')
return response, 200

48
api/controllers/console/datasets/datasets_document.py
View file

@ -18,7 +18,9 @@ from controllers.console.datasets.error import DocumentAlreadyFinishedError, Inv
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from core.indexing_runner import IndexingRunner
from core.llm.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from core.model_providers.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError, \
LLMBadRequestError
from core.model_providers.model_factory import ModelFactory
from extensions.ext_redis import redis_client
from libs.helper import TimestampField
from extensions.ext_database import db
@ -280,6 +282,15 @@ class DatasetDocumentListApi(Resource):
# validate args
DocumentService.document_create_args_validate(args)
try:
ModelFactory.get_embedding_model(
tenant_id=current_user.current_tenant_id
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
f"No Embedding Model available. Please configure a valid provider "
f"in the Settings -> Model Provider.")
try:
documents, batch = DocumentService.save_document_with_dataset_id(dataset, args, current_user)
except ProviderTokenNotInitError as ex:
@ -319,6 +330,15 @@ class DatasetInitApi(Resource):
parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
args = parser.parse_args()
try:
ModelFactory.get_embedding_model(
tenant_id=current_user.current_tenant_id
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
f"No Embedding Model available. Please configure a valid provider "
f"in the Settings -> Model Provider.")
# validate args
DocumentService.document_create_args_validate(args)
@ -384,7 +404,13 @@ class DocumentIndexingEstimateApi(DocumentResource):
indexing_runner = IndexingRunner()
response = indexing_runner.file_indexing_estimate([file], data_process_rule_dict)
try:
response = indexing_runner.file_indexing_estimate(current_user.current_tenant_id, [file],
data_process_rule_dict)
except LLMBadRequestError:
raise ProviderNotInitializeError(
f"No Embedding Model available. Please configure a valid provider "
f"in the Settings -> Model Provider.")
return response
@ -445,12 +471,24 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
raise NotFound("File not found.")
indexing_runner = IndexingRunner()
response = indexing_runner.file_indexing_estimate(file_details, data_process_rule_dict)
try:
response = indexing_runner.file_indexing_estimate(current_user.current_tenant_id, file_details,
data_process_rule_dict)
except LLMBadRequestError:
raise ProviderNotInitializeError(
f"No Embedding Model available. Please configure a valid provider "
f"in the Settings -> Model Provider.")
elif dataset.data_source_type:
indexing_runner = IndexingRunner()
response = indexing_runner.notion_indexing_estimate(info_list,
data_process_rule_dict)
try:
response = indexing_runner.notion_indexing_estimate(current_user.current_tenant_id,
info_list,
data_process_rule_dict)
except LLMBadRequestError:
raise ProviderNotInitializeError(
f"No Embedding Model available. Please configure a valid provider "
f"in the Settings -> Model Provider.")
else:
raise ValueError('Data source type not support')
return response

4
api/controllers/console/datasets/hit_testing.py
View file

@ -11,7 +11,7 @@ from controllers.console.app.error import ProviderNotInitializeError, ProviderQu
from controllers.console.datasets.error import HighQualityDatasetOnlyError, DatasetNotInitializedError
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from core.llm.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from core.model_providers.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from libs.helper import TimestampField
from services.dataset_service import DatasetService
from services.hit_testing_service import HitTestingService
@ -102,6 +102,8 @@ class HitTestingApi(Resource):
raise ProviderQuotaExceededError()
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
except ValueError as e:
raise ValueError(str(e))
except Exception as e:
logging.exception("Hit testing failed.")
raise InternalServerError(str(e))

2
api/controllers/console/explore/audio.py
View file

@ -11,7 +11,7 @@ from controllers.console.app.error import AppUnavailableError, ProviderNotInitia
NoAudioUploadedError, AudioTooLargeError, \
UnsupportedAudioTypeError, ProviderNotSupportSpeechToTextError
from controllers.console.explore.wraps import InstalledAppResource
from core.llm.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from services.audio_service import AudioService
from services.errors.audio import NoAudioUploadedServiceError, AudioTooLargeServiceError, \

2
api/controllers/console/explore/completion.py
View file

@ -15,7 +15,7 @@ from controllers.console.app.error import ConversationCompletedError, AppUnavail
from controllers.console.explore.error import NotCompletionAppError, NotChatAppError
from controllers.console.explore.wraps import InstalledAppResource
from core.conversation_message_task import PubHandler
from core.llm.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
from libs.helper import uuid_value
from services.completion_service import CompletionService

2
api/controllers/console/explore/message.py
View file

@ -15,7 +15,7 @@ from controllers.console.app.error import AppMoreLikeThisDisabledError, Provider
ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError, CompletionRequestError
from controllers.console.explore.error import NotCompletionAppError, AppSuggestedQuestionsAfterAnswerDisabledError
from controllers.console.explore.wraps import InstalledAppResource
from core.llm.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
from core.model_providers.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
ProviderTokenNotInitError, LLMAPIUnavailableError, QuotaExceededError, ModelCurrentlyNotSupportError
from libs.helper import uuid_value, TimestampField
from services.completion_service import CompletionService

5
api/controllers/console/explore/parameter.py
View file

@ -4,8 +4,6 @@ from flask_restful import marshal_with, fields
from controllers.console import api
from controllers.console.explore.wraps import InstalledAppResource
from core.llm.llm_builder import LLMBuilder
from models.provider import ProviderName
from models.model import InstalledApp
@ -35,13 +33,12 @@ class AppParameterApi(InstalledAppResource):
"""Retrieve app parameters."""
app_model = installed_app.app
app_model_config = app_model.app_model_config
provider_name = LLMBuilder.get_default_provider(installed_app.tenant_id, 'whisper-1')
return {
'opening_statement': app_model_config.opening_statement,
'suggested_questions': app_model_config.suggested_questions_list,
'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
'speech_to_text': app_model_config.speech_to_text_dict if provider_name == ProviderName.OPENAI.value else { 'enabled': False },
'speech_to_text': app_model_config.speech_to_text_dict,
'more_like_this': app_model_config.more_like_this_dict,
'user_input_form': app_model_config.user_input_form_list
}

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