merge feat/attachments

api/app.py

@@ -10,44 +10,20 @@ if os.environ.get("DEBUG", "false").lower() != "true":
     grpc.experimental.gevent.init_gevent()
 
 import json
-import logging
-import sys
 import threading
 import time
 import warnings
-from logging.handlers import RotatingFileHandler
 
-from flask import Flask, Response, request
-from flask_cors import CORS
-from werkzeug.exceptions import Unauthorized
+from flask import Response
 
-import contexts
-from commands import register_commands
-from configs import dify_config
+from app_factory import create_app
 
 # DO NOT REMOVE BELOW
 from events import event_handlers  # noqa: F401
-from extensions import (
-    ext_celery,
-    ext_code_based_extension,
-    ext_compress,
-    ext_database,
-    ext_hosting_provider,
-    ext_login,
-    ext_mail,
-    ext_migrate,
-    ext_proxy_fix,
-    ext_redis,
-    ext_sentry,
-    ext_storage,
-)
 from extensions.ext_database import db
-from extensions.ext_login import login_manager
-from libs.passport import PassportService
 
 # TODO: Find a way to avoid importing models here
 from models import account, dataset, model, source, task, tool, tools, web  # noqa: F401
-from services.account_service import AccountService
 
 # DO NOT REMOVE ABOVE
 
@@ -60,189 +36,12 @@ if hasattr(time, "tzset"):
     time.tzset()
 
 
-class DifyApp(Flask):
-    pass
-
-
 # -------------
 # Configuration
 # -------------
-
-
 config_type = os.getenv("EDITION", default="SELF_HOSTED")  # ce edition first
 
 
-# ----------------------------
-# Application Factory Function
-# ----------------------------
-
-
-def create_flask_app_with_configs() -> Flask:
-    """
-    create a raw flask app
-    with configs loaded from .env file
-    """
-    dify_app = DifyApp(__name__)
-    dify_app.config.from_mapping(dify_config.model_dump())
-
-    # populate configs into system environment variables
-    for key, value in dify_app.config.items():
-        if isinstance(value, str):
-            os.environ[key] = value
-        elif isinstance(value, int | float | bool):
-            os.environ[key] = str(value)
-        elif value is None:
-            os.environ[key] = ""
-
-    return dify_app
-
-
-def create_app() -> Flask:
-    app = create_flask_app_with_configs()
-
-    app.secret_key = app.config["SECRET_KEY"]
-
-    log_handlers = None
-    log_file = app.config.get("LOG_FILE")
-    if log_file:
-        log_dir = os.path.dirname(log_file)
-        os.makedirs(log_dir, exist_ok=True)
-        log_handlers = [
-            RotatingFileHandler(
-                filename=log_file,
-                maxBytes=1024 * 1024 * 1024,
-                backupCount=5,
-            ),
-            logging.StreamHandler(sys.stdout),
-        ]
-
-    logging.basicConfig(
-        level=app.config.get("LOG_LEVEL"),
-        format=app.config["LOG_FORMAT"],
-        datefmt=app.config.get("LOG_DATEFORMAT"),
-        handlers=log_handlers,
-        force=True,
-    )
-    log_tz = app.config.get("LOG_TZ")
-    if log_tz:
-        from datetime import datetime
-
-        import pytz
-
-        timezone = pytz.timezone(log_tz)
-
-        def time_converter(seconds):
-            return datetime.utcfromtimestamp(seconds).astimezone(timezone).timetuple()
-
-        for handler in logging.root.handlers:
-            assert handler.formatter
-            handler.formatter.converter = time_converter
-    initialize_extensions(app)
-    register_blueprints(app)
-    register_commands(app)
-
-    return app
-
-
-def initialize_extensions(app):
-    # Since the application instance is now created, pass it to each Flask
-    # extension instance to bind it to the Flask application instance (app)
-    ext_compress.init_app(app)
-    ext_code_based_extension.init()
-    ext_database.init_app(app)
-    ext_migrate.init(app, db)
-    ext_redis.init_app(app)
-    ext_storage.init_app(app)
-    ext_celery.init_app(app)
-    ext_login.init_app(app)
-    ext_mail.init_app(app)
-    ext_hosting_provider.init_app(app)
-    ext_sentry.init_app(app)
-    ext_proxy_fix.init_app(app)
-
-
-# Flask-Login configuration
-@login_manager.request_loader
-def load_user_from_request(request_from_flask_login):
-    """Load user based on the request."""
-    if request.blueprint not in {"console", "inner_api"}:
-        return None
-    # Check if the user_id contains a dot, indicating the old format
-    auth_header = request.headers.get("Authorization", "")
-    if not auth_header:
-        auth_token = request.args.get("_token")
-        if not auth_token:
-            raise Unauthorized("Invalid Authorization token.")
-    else:
-        if " " not in auth_header:
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-        auth_scheme, auth_token = auth_header.split(None, 1)
-        auth_scheme = auth_scheme.lower()
-        if auth_scheme != "bearer":
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-
-    decoded = PassportService().verify(auth_token)
-    user_id = decoded.get("user_id")
-
-    logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
-    if logged_in_account:
-        contexts.tenant_id.set(logged_in_account.current_tenant_id)
-    return logged_in_account
-
-
-@login_manager.unauthorized_handler
-def unauthorized_handler():
-    """Handle unauthorized requests."""
-    return Response(
-        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
-        status=401,
-        content_type="application/json",
-    )
-
-
-# register blueprint routers
-def register_blueprints(app):
-    from controllers.console import bp as console_app_bp
-    from controllers.files import bp as files_bp
-    from controllers.inner_api import bp as inner_api_bp
-    from controllers.service_api import bp as service_api_bp
-    from controllers.web import bp as web_bp
-
-    CORS(
-        service_api_bp,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-    )
-    app.register_blueprint(service_api_bp)
-
-    CORS(
-        web_bp,
-        resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(web_bp)
-
-    CORS(
-        console_app_bp,
-        resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(console_app_bp)
-
-    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
-    app.register_blueprint(files_bp)
-
-    app.register_blueprint(inner_api_bp)
-
-
 # create app
 app = create_app()
 celery = app.extensions["celery"]

api/app_factory.py

@@ -0,0 +1,213 @@
+import os
+
+if os.environ.get("DEBUG", "false").lower() != "true":
+    from gevent import monkey
+
+    monkey.patch_all()
+
+    import grpc.experimental.gevent
+
+    grpc.experimental.gevent.init_gevent()
+
+import json
+import logging
+import sys
+from logging.handlers import RotatingFileHandler
+
+from flask import Flask, Response, request
+from flask_cors import CORS
+from werkzeug.exceptions import Unauthorized
+
+import contexts
+from commands import register_commands
+from configs import dify_config
+from extensions import (
+    ext_celery,
+    ext_code_based_extension,
+    ext_compress,
+    ext_database,
+    ext_hosting_provider,
+    ext_login,
+    ext_mail,
+    ext_migrate,
+    ext_proxy_fix,
+    ext_redis,
+    ext_sentry,
+    ext_storage,
+)
+from extensions.ext_database import db
+from extensions.ext_login import login_manager
+from libs.passport import PassportService
+from services.account_service import AccountService
+
+
+class DifyApp(Flask):
+    pass
+
+
+# ----------------------------
+# Application Factory Function
+# ----------------------------
+def create_flask_app_with_configs() -> Flask:
+    """
+    create a raw flask app
+    with configs loaded from .env file
+    """
+    dify_app = DifyApp(__name__)
+    dify_app.config.from_mapping(dify_config.model_dump())
+
+    # populate configs into system environment variables
+    for key, value in dify_app.config.items():
+        if isinstance(value, str):
+            os.environ[key] = value
+        elif isinstance(value, int | float | bool):
+            os.environ[key] = str(value)
+        elif value is None:
+            os.environ[key] = ""
+
+    return dify_app
+
+
+def create_app() -> Flask:
+    app = create_flask_app_with_configs()
+
+    app.secret_key = app.config["SECRET_KEY"]
+
+    log_handlers = None
+    log_file = app.config.get("LOG_FILE")
+    if log_file:
+        log_dir = os.path.dirname(log_file)
+        os.makedirs(log_dir, exist_ok=True)
+        log_handlers = [
+            RotatingFileHandler(
+                filename=log_file,
+                maxBytes=1024 * 1024 * 1024,
+                backupCount=5,
+            ),
+            logging.StreamHandler(sys.stdout),
+        ]
+
+    logging.basicConfig(
+        level=app.config.get("LOG_LEVEL"),
+        format=app.config.get("LOG_FORMAT"),
+        datefmt=app.config.get("LOG_DATEFORMAT"),
+        handlers=log_handlers,
+        force=True,
+    )
+    log_tz = app.config.get("LOG_TZ")
+    if log_tz:
+        from datetime import datetime
+
+        import pytz
+
+        timezone = pytz.timezone(log_tz)
+
+        def time_converter(seconds):
+            return datetime.utcfromtimestamp(seconds).astimezone(timezone).timetuple()
+
+        for handler in logging.root.handlers:
+            handler.formatter.converter = time_converter
+    initialize_extensions(app)
+    register_blueprints(app)
+    register_commands(app)
+
+    return app
+
+
+def initialize_extensions(app):
+    # Since the application instance is now created, pass it to each Flask
+    # extension instance to bind it to the Flask application instance (app)
+    ext_compress.init_app(app)
+    ext_code_based_extension.init()
+    ext_database.init_app(app)
+    ext_migrate.init(app, db)
+    ext_redis.init_app(app)
+    ext_storage.init_app(app)
+    ext_celery.init_app(app)
+    ext_login.init_app(app)
+    ext_mail.init_app(app)
+    ext_hosting_provider.init_app(app)
+    ext_sentry.init_app(app)
+    ext_proxy_fix.init_app(app)
+
+
+# Flask-Login configuration
+@login_manager.request_loader
+def load_user_from_request(request_from_flask_login):
+    """Load user based on the request."""
+    if request.blueprint not in {"console", "inner_api"}:
+        return None
+    # Check if the user_id contains a dot, indicating the old format
+    auth_header = request.headers.get("Authorization", "")
+    if not auth_header:
+        auth_token = request.args.get("_token")
+        if not auth_token:
+            raise Unauthorized("Invalid Authorization token.")
+    else:
+        if " " not in auth_header:
+            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
+        auth_scheme, auth_token = auth_header.split(None, 1)
+        auth_scheme = auth_scheme.lower()
+        if auth_scheme != "bearer":
+            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
+
+    decoded = PassportService().verify(auth_token)
+    user_id = decoded.get("user_id")
+
+    logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
+    if logged_in_account:
+        contexts.tenant_id.set(logged_in_account.current_tenant_id)
+    return logged_in_account
+
+
+@login_manager.unauthorized_handler
+def unauthorized_handler():
+    """Handle unauthorized requests."""
+    return Response(
+        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
+        status=401,
+        content_type="application/json",
+    )
+
+
+# register blueprint routers
+def register_blueprints(app):
+    from controllers.console import bp as console_app_bp
+    from controllers.files import bp as files_bp
+    from controllers.inner_api import bp as inner_api_bp
+    from controllers.service_api import bp as service_api_bp
+    from controllers.web import bp as web_bp
+
+    CORS(
+        service_api_bp,
+        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+    )
+    app.register_blueprint(service_api_bp)
+
+    CORS(
+        web_bp,
+        resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
+        supports_credentials=True,
+        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+        expose_headers=["X-Version", "X-Env"],
+    )
+
+    app.register_blueprint(web_bp)
+
+    CORS(
+        console_app_bp,
+        resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
+        supports_credentials=True,
+        allow_headers=["Content-Type", "Authorization"],
+        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
+        expose_headers=["X-Version", "X-Env"],
+    )
+
+    app.register_blueprint(console_app_bp)
+
+    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
+    app.register_blueprint(files_bp)
+
+    app.register_blueprint(inner_api_bp)

api/commands.py

@@ -259,6 +259,25 @@ def migrate_knowledge_vector_database():
     skipped_count = 0
     total_count = 0
     vector_type = dify_config.VECTOR_STORE
+    upper_colletion_vector_types = {
+        VectorType.MILVUS,
+        VectorType.PGVECTOR,
+        VectorType.RELYT,
+        VectorType.WEAVIATE,
+        VectorType.ORACLE,
+        VectorType.ELASTICSEARCH,
+    }
+    lower_colletion_vector_types = {
+        VectorType.ANALYTICDB,
+        VectorType.CHROMA,
+        VectorType.MYSCALE,
+        VectorType.PGVECTO_RS,
+        VectorType.TIDB_VECTOR,
+        VectorType.OPENSEARCH,
+        VectorType.TENCENT,
+        VectorType.BAIDU,
+        VectorType.VIKINGDB,
+    }
     page = 1
     while True:
         try:
@@ -284,11 +303,9 @@ def migrate_knowledge_vector_database():
                         skipped_count = skipped_count + 1
                         continue
                 collection_name = ""
-                if vector_type == VectorType.WEAVIATE:
                 dataset_id = dataset.id
+                if vector_type in upper_colletion_vector_types:
                     collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.WEAVIATE, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
                 elif vector_type == VectorType.QDRANT:
                     if dataset.collection_binding_id:
                         dataset_collection_binding = (
@@ -301,63 +318,15 @@ def migrate_knowledge_vector_database():
                         else:
                             raise ValueError("Dataset Collection Binding not found")
                     else:
-                        dataset_id = dataset.id
                         collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.QDRANT, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
 
-                elif vector_type == VectorType.MILVUS:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.MILVUS, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.RELYT:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": "relyt", "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.TENCENT:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.TENCENT, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.PGVECTOR:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.PGVECTOR, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.OPENSEARCH:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {
-                        "type": VectorType.OPENSEARCH,
-                        "vector_store": {"class_prefix": collection_name},
-                    }
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.ANALYTICDB:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {
-                        "type": VectorType.ANALYTICDB,
-                        "vector_store": {"class_prefix": collection_name},
-                    }
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.ELASTICSEARCH:
-                    dataset_id = dataset.id
-                    index_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": "elasticsearch", "vector_store": {"class_prefix": index_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.BAIDU:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {
-                        "type": VectorType.BAIDU,
-                        "vector_store": {"class_prefix": collection_name},
-                    }
-                    dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type in lower_colletion_vector_types:
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
                 else:
                     raise ValueError(f"Vector store {vector_type} is not supported.")
 
+                index_struct_dict = {"type": vector_type, "vector_store": {"class_prefix": collection_name}}
+                dataset.index_struct = json.dumps(index_struct_dict)
                 vector = Vector(dataset)
                 click.echo(f"Migrating dataset {dataset.id}.")
 

api/core/model_manager.py

@@ -3,7 +3,7 @@ import os
 from collections.abc import Callable, Generator, Iterable, Sequence
 from typing import IO, Any, Optional, Union, cast
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.entities.provider_configuration import ProviderConfiguration, ProviderModelBundle
 from core.entities.provider_entities import ModelLoadBalancingConfiguration
 from core.errors.error import ProviderTokenNotInitError

api/core/model_runtime/model_providers/__base/text_embedding_model.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from pydantic import ConfigDict
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import ModelPropertyKey, ModelType
 from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
 from core.model_runtime.model_providers.__base.ai_model import AIModel

api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py

@@ -7,7 +7,7 @@ import numpy as np
 import tiktoken
 from openai import AzureOpenAI
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import AIModelEntity, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.validate import CredentialsValidateFailedError

api/core/model_runtime/model_providers/baichuan/text_embedding/text_embedding.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from requests import post
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (

api/core/model_runtime/model_providers/bedrock/text_embedding/text_embedding.py

@@ -13,7 +13,7 @@ from botocore.exceptions import (
     UnknownServiceError,
 )
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (

api/core/model_runtime/model_providers/cohere/text_embedding/text_embedding.py

@@ -5,7 +5,7 @@ import cohere
 import numpy as np
 from cohere.core import RequestOptions
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (

api/core/model_runtime/model_providers/fireworks/text_embedding/text_embedding.py

@@ -5,7 +5,7 @@ from typing import Optional, Union
 import numpy as np
 from openai import OpenAI
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.validate import CredentialsValidateFailedError

api/core/model_runtime/model_providers/groq/groq.yaml

@@ -18,6 +18,7 @@ help:
     en_US: https://console.groq.com/
 supported_model_types:
   - llm
+  - speech2text
 configurate_methods:
   - predefined-model
 provider_credential_schema:

api/core/model_runtime/model_providers/groq/llm/llama-3.2-11b-vision-preview.yaml

@@ -0,0 +1,26 @@
+model: llama-3.2-11b-vision-preview
+label:
+  zh_Hans: Llama 3.2 11B Vision (Preview)
+  en_US: Llama 3.2 11B Vision (Preview)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.05'
+  output: '0.1'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/groq/llm/llama-3.2-90b-vision-preview.yaml

@@ -0,0 +1,26 @@
+model: llama-3.2-90b-vision-preview
+label:
+  zh_Hans: Llama 3.2 90B Vision (Preview)
+  en_US: Llama 3.2 90B Vision (Preview)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.05'
+  output: '0.1'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/groq/speech2text/distil-whisper-large-v3-en.yaml

@@ -0,0 +1,5 @@
+model: distil-whisper-large-v3-en
+model_type: speech2text
+model_properties:
+  file_upload_limit: 1
+  supported_file_extensions: flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm

api/core/model_runtime/model_providers/groq/speech2text/speech2text.py

@@ -0,0 +1,30 @@
+from typing import IO, Optional
+
+from core.model_runtime.model_providers.openai_api_compatible.speech2text.speech2text import OAICompatSpeech2TextModel
+
+
+class GroqSpeech2TextModel(OAICompatSpeech2TextModel):
+    """
+    Model class for Groq Speech to text model.
+    """
+
+    def _invoke(self, model: str, credentials: dict, file: IO[bytes], user: Optional[str] = None) -> str:
+        """
+        Invoke speech2text model
+
+        :param model: model name
+        :param credentials: model credentials
+        :param file: audio file
+        :param user: unique user id
+        :return: text for given audio file
+        """
+        self._add_custom_parameters(credentials)
+        return super()._invoke(model, credentials, file)
+
+    def validate_credentials(self, model: str, credentials: dict) -> None:
+        self._add_custom_parameters(credentials)
+        return super().validate_credentials(model, credentials)
+
+    @classmethod
+    def _add_custom_parameters(cls, credentials: dict) -> None:
+        credentials["endpoint_url"] = "https://api.groq.com/openai/v1"

api/core/model_runtime/model_providers/groq/speech2text/whisper-large-v3-turbo.yaml

@@ -0,0 +1,5 @@
+model: whisper-large-v3-turbo
+model_type: speech2text
+model_properties:
+  file_upload_limit: 1
+  supported_file_extensions: flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm

api/core/model_runtime/model_providers/groq/speech2text/whisper-large-v3.yaml

@@ -0,0 +1,5 @@
+model: whisper-large-v3
+model_type: speech2text
+model_properties:
+  file_upload_limit: 1
+  supported_file_extensions: flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm

api/core/model_runtime/model_providers/huggingface_hub/text_embedding/text_embedding.py

@@ -6,7 +6,7 @@ import numpy as np
 import requests
 from huggingface_hub import HfApi, InferenceClient
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

api/core/model_runtime/model_providers/huggingface_tei/text_embedding/text_embedding.py

@@ -1,7 +1,7 @@
 import time
 from typing import Optional
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

api/core/model_runtime/model_providers/hunyuan/text_embedding/text_embedding.py

@@ -9,7 +9,7 @@ from tencentcloud.common.profile.client_profile import ClientProfile
 from tencentcloud.common.profile.http_profile import HttpProfile
 from tencentcloud.hunyuan.v20230901 import hunyuan_client, models
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (

api/core/model_runtime/model_providers/jina/text_embedding/text_embedding.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from requests import post
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

api/core/model_runtime/model_providers/localai/text_embedding/text_embedding.py

@@ -5,7 +5,7 @@ from typing import Optional
 from requests import post
 from yarl import URL
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

api/core/model_runtime/model_providers/minimax/text_embedding/text_embedding.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from requests import post
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (

api/core/model_runtime/model_providers/mixedbread/text_embedding/text_embedding.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 import requests
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

api/core/model_runtime/model_providers/nomic/text_embedding/text_embedding.py

@@ -5,7 +5,7 @@ from typing import Optional
 from nomic import embed
 from nomic import login as nomic_login
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import (
     EmbeddingUsage,

api/core/model_runtime/model_providers/nvidia/text_embedding/text_embedding.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from requests import post
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (

api/core/model_runtime/model_providers/oci/text_embedding/text_embedding.py

@@ -6,7 +6,7 @@ from typing import Optional
 import numpy as np
 import oci
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (

api/core/model_runtime/model_providers/ollama/text_embedding/text_embedding.py

@@ -8,7 +8,7 @@ from urllib.parse import urljoin
 import numpy as np
 import requests
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import (
     AIModelEntity,

api/core/model_runtime/model_providers/openai/text_embedding/text_embedding.py

@@ -6,7 +6,7 @@ import numpy as np
 import tiktoken
 from openai import OpenAI
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.validate import CredentialsValidateFailedError

api/core/model_runtime/model_providers/openai_api_compatible/text_embedding/text_embedding.py

@@ -7,7 +7,7 @@ from urllib.parse import urljoin
 import numpy as np
 import requests
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import (
     AIModelEntity,

api/core/model_runtime/model_providers/openllm/text_embedding/text_embedding.py

@@ -5,7 +5,7 @@ from typing import Optional
 from requests import post
 from requests.exceptions import ConnectionError, InvalidSchema, MissingSchema
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (

api/core/model_runtime/model_providers/openrouter/llm/deepseek-chat.yaml

@@ -35,6 +35,15 @@ parameter_rules:
     help:
       zh_Hans: 控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。
       en_US: Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
     default: 0

api/core/model_runtime/model_providers/openrouter/llm/deepseek-coder.yaml

@@ -18,6 +18,15 @@ parameter_rules:
     min: 0
     max: 1
     default: 1
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: max_tokens
     use_template: max_tokens
     min: 1

api/core/model_runtime/model_providers/openrouter/llm/gpt-3.5-turbo.yaml

@@ -14,6 +14,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/gpt-4-32k.yaml

@@ -14,6 +14,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/gpt-4.yaml

@@ -14,6 +14,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/gpt-4o-2024-08-06.yaml

@@ -16,6 +16,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/gpt-4o-mini.yaml

@@ -15,6 +15,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/gpt-4o.yaml

@@ -15,6 +15,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/llama-3-70b-instruct.yaml

@@ -10,6 +10,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: max_tokens
     use_template: max_tokens
     required: true

api/core/model_runtime/model_providers/openrouter/llm/llama-3-8b-instruct.yaml

@@ -10,6 +10,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: max_tokens
     use_template: max_tokens
     required: true

api/core/model_runtime/model_providers/openrouter/llm/llama-3.1-405b-instruct.yaml

@@ -10,6 +10,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: max_tokens
     use_template: max_tokens
     required: true

api/core/model_runtime/model_providers/openrouter/llm/llama-3.1-70b-instruct.yaml

@@ -10,6 +10,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: max_tokens
     use_template: max_tokens
     required: true

api/core/model_runtime/model_providers/openrouter/llm/llama-3.1-8b-instruct.yaml

@@ -10,6 +10,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: max_tokens
     use_template: max_tokens
     required: true

api/core/model_runtime/model_providers/openrouter/llm/mistral-7b-instruct.yaml

@@ -18,6 +18,15 @@ parameter_rules:
     default: 1
     min: 0
     max: 1
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: max_tokens
     use_template: max_tokens
     default: 1024

api/core/model_runtime/model_providers/openrouter/llm/mixtral-8x22b-instruct.yaml

@@ -18,6 +18,15 @@ parameter_rules:
     default: 1
     min: 0
     max: 1
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: max_tokens
     use_template: max_tokens
     default: 1024

api/core/model_runtime/model_providers/openrouter/llm/mixtral-8x7b-instruct.yaml

@@ -19,6 +19,15 @@ parameter_rules:
     default: 1
     min: 0
     max: 1
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: max_tokens
     use_template: max_tokens
     default: 1024

api/core/model_runtime/model_providers/openrouter/llm/o1-mini.yaml

@@ -12,6 +12,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/o1-preview.yaml

@@ -12,6 +12,15 @@ parameter_rules:
     use_template: temperature
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: presence_penalty
     use_template: presence_penalty
   - name: frequency_penalty

api/core/model_runtime/model_providers/openrouter/llm/qwen2-72b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/openrouter/llm/qwen2.5-72b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/perfxcloud/text_embedding/text_embedding.py

@@ -7,7 +7,7 @@ from urllib.parse import urljoin
 import numpy as np
 import requests
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import (
     AIModelEntity,

api/core/model_runtime/model_providers/replicate/text_embedding/text_embedding.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from replicate import Client as ReplicateClient
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

api/core/model_runtime/model_providers/sagemaker/speech2text/speech2text.py

@@ -14,6 +14,7 @@ from core.model_runtime.errors.invoke import (
     InvokeRateLimitError,
     InvokeServerUnavailableError,
 )
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.model_providers.__base.speech2text_model import Speech2TextModel
 from core.model_runtime.model_providers.sagemaker.sagemaker import generate_presigned_url
 
@@ -77,7 +78,8 @@ class SageMakerSpeech2TextModel(Speech2TextModel):
             json_obj = json.loads(json_str)
             asr_text = json_obj["text"]
         except Exception as e:
-            logger.exception(f"Exception {e}, line : {line}")
+            logger.exception(f"failed to invoke speech2text model, {e}")
+            raise CredentialsValidateFailedError(str(e))
 
         return asr_text
 

api/core/model_runtime/model_providers/sagemaker/text_embedding/text_embedding.py

@@ -6,7 +6,7 @@ from typing import Any, Optional
 
 import boto3
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

api/core/model_runtime/model_providers/siliconflow/llm/deepdeek-coder-v2-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2-chat.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2.5.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/gemma-2-27b-it.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/gemma-2-9b-it.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/glm4-9b-chat.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/internlm2_5-20b-chat.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/internlm2_5-7b-chat.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/meta-mlama-3-70b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/meta-mlama-3-8b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/meta-mlama-3.1-405b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/meta-mlama-3.1-70b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/meta-mlama-3.1-8b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/mistral-7b-instruct-v0.2.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/mistral-8x7b-instruct-v0.1.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-1.5b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-57b-a14b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-72b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/qwen2-7b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/qwen2.5-14b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/qwen2.5-32b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/qwen2.5-72b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/qwen2.5-7b-instruct.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-34b-chat.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-6b-chat.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/llm/yi-1.5-9b-chat.yaml

@@ -21,6 +21,15 @@ parameter_rules:
       en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
   - name: top_p
     use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:

api/core/model_runtime/model_providers/siliconflow/text_embedding/text_embedding.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
 from core.model_runtime.model_providers.openai_api_compatible.text_embedding.text_embedding import (
     OAICompatEmbeddingModel,

api/core/model_runtime/model_providers/tongyi/text_embedding/text_embedding.py

@@ -4,7 +4,7 @@ from typing import Optional
 import dashscope
 import numpy as np
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import (
     EmbeddingUsage,

api/core/model_runtime/model_providers/upstage/text_embedding/text_embedding.py

@@ -7,7 +7,7 @@ import numpy as np
 from openai import OpenAI
 from tokenizers import Tokenizer
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.validate import CredentialsValidateFailedError

api/core/model_runtime/model_providers/vertex_ai/text_embedding/text_embedding.py

@@ -9,7 +9,7 @@ from google.cloud import aiplatform
 from google.oauth2 import service_account
 from vertexai.language_models import TextEmbeddingModel as VertexTextEmbeddingModel
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import (
     AIModelEntity,

api/core/model_runtime/model_providers/volcengine_maas/text_embedding/text_embedding.py

@@ -2,7 +2,7 @@ import time
 from decimal import Decimal
 from typing import Optional
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import (
     AIModelEntity,

api/core/model_runtime/model_providers/voyage/text_embedding/text_embedding.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 import requests
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

api/core/model_runtime/model_providers/wenxin/_common.py

@@ -120,6 +120,7 @@ class _CommonWenxin:
         "bge-large-en": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/bge_large_en",
         "bge-large-zh": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/bge_large_zh",
         "tao-8k": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/tao_8k",
+        "bce-reranker-base_v1": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/reranker/bce_reranker_base",
     }
 
     function_calling_supports = [

api/core/model_runtime/model_providers/wenxin/rerank/bce-reranker-base_v1.yaml

@@ -0,0 +1,8 @@
+model: bce-reranker-base_v1
+model_type: rerank
+model_properties:
+  context_size: 4096
+pricing:
+  input: '0.0005'
+  unit: '0.001'
+  currency: RMB

api/core/model_runtime/model_providers/wenxin/rerank/rerank.py

@@ -0,0 +1,147 @@
+from typing import Optional
+
+import httpx
+
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType
+from core.model_runtime.entities.rerank_entities import RerankDocument, RerankResult
+from core.model_runtime.errors.invoke import (
+    InvokeAuthorizationError,
+    InvokeBadRequestError,
+    InvokeConnectionError,
+    InvokeError,
+    InvokeRateLimitError,
+    InvokeServerUnavailableError,
+)
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.__base.rerank_model import RerankModel
+from core.model_runtime.model_providers.wenxin._common import _CommonWenxin
+
+
+class WenxinRerank(_CommonWenxin):
+    def rerank(self, model: str, query: str, docs: list[str], top_n: Optional[int] = None):
+        access_token = self._get_access_token()
+        url = f"{self.api_bases[model]}?access_token={access_token}"
+
+        try:
+            response = httpx.post(
+                url,
+                json={"model": model, "query": query, "documents": docs, "top_n": top_n},
+                headers={"Content-Type": "application/json"},
+            )
+            response.raise_for_status()
+            return response.json()
+        except httpx.HTTPStatusError as e:
+            raise InvokeServerUnavailableError(str(e))
+
+
+class WenxinRerankModel(RerankModel):
+    """
+    Model class for wenxin rerank model.
+    """
+
+    def _invoke(
+        self,
+        model: str,
+        credentials: dict,
+        query: str,
+        docs: list[str],
+        score_threshold: Optional[float] = None,
+        top_n: Optional[int] = None,
+        user: Optional[str] = None,
+    ) -> RerankResult:
+        """
+        Invoke rerank model
+
+        :param model: model name
+        :param credentials: model credentials
+        :param query: search query
+        :param docs: docs for reranking
+        :param score_threshold: score threshold
+        :param top_n: top n documents to return
+        :param user: unique user id
+        :return: rerank result
+        """
+        if len(docs) == 0:
+            return RerankResult(model=model, docs=[])
+
+        api_key = credentials["api_key"]
+        secret_key = credentials["secret_key"]
+
+        wenxin_rerank: WenxinRerank = WenxinRerank(api_key, secret_key)
+
+        try:
+            results = wenxin_rerank.rerank(model, query, docs, top_n)
+
+            rerank_documents = []
+            for result in results["results"]:
+                index = result["index"]
+                if "document" in result:
+                    text = result["document"]
+                else:
+                    # llama.cpp rerank maynot return original documents
+                    text = docs[index]
+
+                rerank_document = RerankDocument(
+                    index=index,
+                    text=text,
+                    score=result["relevance_score"],
+                )
+
+                if score_threshold is None or result["relevance_score"] >= score_threshold:
+                    rerank_documents.append(rerank_document)
+
+            return RerankResult(model=model, docs=rerank_documents)
+        except httpx.HTTPStatusError as e:
+            raise InvokeServerUnavailableError(str(e))
+
+    def validate_credentials(self, model: str, credentials: dict) -> None:
+        """
+        Validate model credentials
+
+        :param model: model name
+        :param credentials: model credentials
+        :return:
+        """
+        try:
+            self._invoke(
+                model=model,
+                credentials=credentials,
+                query="What is the capital of the United States?",
+                docs=[
+                    "Carson City is the capital city of the American state of Nevada. At the 2010 United States "
+                    "Census, Carson City had a population of 55,274.",
+                    "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean that "
+                    "are a political division controlled by the United States. Its capital is Saipan.",
+                ],
+                score_threshold=0.8,
+            )
+        except Exception as ex:
+            raise CredentialsValidateFailedError(str(ex))
+
+    @property
+    def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+        """
+        Map model invoke error to unified error
+        """
+        return {
+            InvokeConnectionError: [httpx.ConnectError],
+            InvokeServerUnavailableError: [httpx.RemoteProtocolError],
+            InvokeRateLimitError: [],
+            InvokeAuthorizationError: [httpx.HTTPStatusError],
+            InvokeBadRequestError: [httpx.RequestError],
+        }
+
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
+        """
+        generate custom model entities from credentials
+        """
+        entity = AIModelEntity(
+            model=model,
+            label=I18nObject(en_US=model),
+            model_type=ModelType.RERANK,
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size"))},
+        )
+
+        return entity

api/core/model_runtime/model_providers/wenxin/text_embedding/text_embedding.py

@@ -7,7 +7,7 @@ from typing import Any, Optional
 import numpy as np
 from requests import Response, post
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import InvokeError

api/core/model_runtime/model_providers/wenxin/wenxin.yaml

@@ -18,6 +18,7 @@ help:
 supported_model_types:
   - llm
   - text-embedding
+  - rerank
 configurate_methods:
   - predefined-model
 provider_credential_schema:

api/core/model_runtime/model_providers/xinference/text_embedding/text_embedding.py

@@ -3,7 +3,7 @@ from typing import Optional
 
 from xinference_client.client.restful.restful_client import Client, RESTfulEmbeddingModelHandle
 
-from core.embedding.embedding_constant import EmbeddingInputType
+from core.entities.embedding_type import EmbeddingInputType
 from core.model_runtime.entities.common_entities import I18nObject
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult

api/core/model_runtime/model_providers/yi/llm/_position.yaml

@@ -7,3 +7,4 @@
 - yi-medium-200k
 - yi-spark
 - yi-large-turbo
+- yi-lightning

api/core/model_runtime/model_providers/yi/llm/llm.py

@@ -4,12 +4,22 @@ from urllib.parse import urlparse
 
 import tiktoken
 
-from core.model_runtime.entities.llm_entities import LLMResult
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.llm_entities import LLMMode, LLMResult
 from core.model_runtime.entities.message_entities import (
     PromptMessage,
     PromptMessageTool,
     SystemPromptMessage,
 )
+from core.model_runtime.entities.model_entities import (
+    AIModelEntity,
+    FetchFrom,
+    ModelFeature,
+    ModelPropertyKey,
+    ModelType,
+    ParameterRule,
+    ParameterType,
+)
 from core.model_runtime.model_providers.openai.llm.llm import OpenAILargeLanguageModel
 
 
@@ -125,3 +135,58 @@ class YiLargeLanguageModel(OpenAILargeLanguageModel):
         else:
             parsed_url = urlparse(credentials["endpoint_url"])
             credentials["openai_api_base"] = f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
+        return AIModelEntity(
+            model=model,
+            label=I18nObject(en_US=model, zh_Hans=model),
+            model_type=ModelType.LLM,
+            features=[ModelFeature.TOOL_CALL, ModelFeature.MULTI_TOOL_CALL, ModelFeature.STREAM_TOOL_CALL]
+            if credentials.get("function_calling_type") == "tool_call"
+            else [],
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={
+                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", 8000)),
+                ModelPropertyKey.MODE: LLMMode.CHAT.value,
+            },
+            parameter_rules=[
+                ParameterRule(
+                    name="temperature",
+                    use_template="temperature",
+                    label=I18nObject(en_US="Temperature", zh_Hans="温度"),
+                    type=ParameterType.FLOAT,
+                ),
+                ParameterRule(
+                    name="max_tokens",
+                    use_template="max_tokens",
+                    default=512,
+                    min=1,
+                    max=int(credentials.get("max_tokens", 8192)),
+                    label=I18nObject(
+                        en_US="Max Tokens", zh_Hans="指定生成结果长度的上限。如果生成结果截断，可以调大该参数"
+                    ),
+                    type=ParameterType.INT,
+                ),
+                ParameterRule(
+                    name="top_p",
+                    use_template="top_p",
+                    label=I18nObject(
+                        en_US="Top P",
+                        zh_Hans="控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。",
+                    ),
+                    type=ParameterType.FLOAT,
+                ),
+                ParameterRule(
+                    name="top_k",
+                    use_template="top_k",
+                    label=I18nObject(en_US="Top K", zh_Hans="取样数量"),
+                    type=ParameterType.FLOAT,
+                ),
+                ParameterRule(
+                    name="frequency_penalty",
+                    use_template="frequency_penalty",
+                    label=I18nObject(en_US="Frequency Penalty", zh_Hans="重复惩罚"),
+                    type=ParameterType.FLOAT,
+                ),
+            ],
+        )

api/core/model_runtime/model_providers/yi/llm/yi-lightning.yaml

@@ -0,0 +1,43 @@
+model: yi-lightning
+label:
+  zh_Hans: yi-lightning
+  en_US: yi-lightning
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 16384
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    type: float
+    default: 0.3
+    min: 0.0
+    max: 2.0
+    help:
+      zh_Hans: 控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。
+      en_US: Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 1024
+    min: 1
+    max: 4000
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+    type: float
+    default: 0.9
+    min: 0.01
+    max: 1.00
+    help:
+      zh_Hans: 控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。
+      en_US: Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.
+pricing:
+  input: '0.99'
+  output: '0.99'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/yi/yi.yaml

@@ -20,6 +20,7 @@ supported_model_types:
   - llm
 configurate_methods:
   - predefined-model
+  - customizable-model
 provider_credential_schema:
   credential_form_schemas:
     - variable: api_key
@@ -39,3 +40,57 @@ provider_credential_schema:
       placeholder:
         zh_Hans: Base URL, e.g. https://api.lingyiwanwu.com/v1
         en_US: Base URL, e.g. https://api.lingyiwanwu.com/v1
+model_credential_schema:
+  model:
+    label:
+      en_US: Model Name
+      zh_Hans: 模型名称
+    placeholder:
+      en_US: Enter your model name
+      zh_Hans: 输入模型名称
+  credential_form_schemas:
+    - variable: api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      required: true
+      placeholder:
+        zh_Hans: 在此输入您的 API Key
+        en_US: Enter your API Key
+    - variable: context_size
+      label:
+        zh_Hans: 模型上下文长度
+        en_US: Model context size
+      required: true
+      type: text-input
+      default: '4096'
+      placeholder:
+        zh_Hans: 在此输入您的模型上下文长度
+        en_US: Enter your Model context size
+    - variable: max_tokens
+      label:
+        zh_Hans: 最大 token 上限
+        en_US: Upper bound for max tokens
+      default: '4096'
+      type: text-input
+      show_on:
+        - variable: __model_type
+          value: llm
+    - variable: function_calling_type
+      label:
+        en_US: Function calling
+      type: select
+      required: false
+      default: no_call
+      options:
+        - value: no_call
+          label:
+            en_US: Not Support
+            zh_Hans: 不支持
+        - value: function_call
+          label:
+            en_US: Support
+            zh_Hans: 支持
+      show_on:
+        - variable: __model_type
+          value: llm